diff options
Diffstat (limited to 'contrib/expat')
57 files changed, 22251 insertions, 0 deletions
diff --git a/contrib/expat/COPYING b/contrib/expat/COPYING new file mode 100644 index 0000000..dcb4506 --- /dev/null +++ b/contrib/expat/COPYING @@ -0,0 +1,22 @@ +Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + and Clark Cooper +Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006 Expat maintainers. + +Permission is hereby granted, free of charge, to any person obtaining +a copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. diff --git a/contrib/expat/Changes b/contrib/expat/Changes new file mode 100644 index 0000000..08897b9 --- /dev/null +++ b/contrib/expat/Changes @@ -0,0 +1,205 @@ +Release 2.1.0 Sat March 24 2012 + - Bug Fixes: + #1742315: Harmful XML_ParserCreateNS suggestion. + #2895533: CVE-2012-1147 - Resource leak in readfilemap.c. + #1785430: Expat build fails on linux-amd64 with gcc version>=4.1 -O3. + #1983953, 2517952, 2517962, 2649838: + Build modifications using autoreconf instead of buildconf.sh. + #2815947, #2884086: OBJEXT and EXEEXT support while building. + #1990430: CVE-2009-3720 - Parser crash with special UTF-8 sequences. + #2517938: xmlwf should return non-zero exit status if not well-formed. + #2517946: Wrong statement about XMLDecl in xmlwf.1 and xmlwf.sgml. + #2855609: Dangling positionPtr after error. + #2894085: CVE-2009-3560 - Buffer over-read and crash in big2_toUtf8(). + #2958794: CVE-2012-1148 - Memory leak in poolGrow. + #2990652: CMake support. + #3010819: UNEXPECTED_STATE with a trailing "%" in entity value. + #3206497: Unitialized memory returned from XML_Parse. + #3287849: make check fails on mingw-w64. + #3496608: CVE-2012-0876 - Hash DOS attack. + - Patches: + #1749198: pkg-config support. + #3010222: Fix for bug #3010819. + #3312568: CMake support. + #3446384: Report byte offsets for attr names and values. + - New Features / API changes: + Added new API member XML_SetHashSalt() that allows setting an intial + value (salt) for hash calculations. This is part of the fix for + bug #3496608 to randomize hash parameters. + When compiled with XML_ATTR_INFO defined, adds new API member + XML_GetAttributeInfo() that allows retrieving the byte + offsets for attribute names and values (patch #3446384). + Added CMake build system. + See bug #2990652 and patch #3312568. + Added run-benchmark target to Makefile.in - relies on testdata module + present in the same relative location as in the repository. + +Release 2.0.1 Tue June 5 2007 + - Fixed bugs #1515266, #1515600: The character data handler's calling + of XML_StopParser() was not handled properly; if the parser was + stopped and the handler set to NULL, the parser would segfault. + - Fixed bug #1690883: Expat failed on EBCDIC systems as it assumed + some character constants to be ASCII encoded. + - Minor cleanups of the test harness. + - Fixed xmlwf bug #1513566: "out of memory" error on file size zero. + - Fixed outline.c bug #1543233: missing a final XML_ParserFree() call. + - Fixes and improvements for Windows platform: + bugs #1409451, #1476160, #1548182, #1602769, #1717322. + - Build fixes for various platforms: + HP-UX, Tru64, Solaris 9: patch #1437840, bug #1196180. + All Unix: #1554618 (refreshed config.sub/config.guess). + #1490371, #1613457: support both, DESTDIR and INSTALL_ROOT, + without relying on GNU-Make specific features. + #1647805: Patched configure.in to work better with Intel compiler. + - Fixes to Makefile.in to have make check work correctly: + bugs #1408143, #1535603, #1536684. + - Added Open Watcom support: patch #1523242. + +Release 2.0.0 Wed Jan 11 2006 + - We no longer use the "check" library for C unit testing; we + always use the (partial) internal implementation of the API. + - Report XML_NS setting via XML_GetFeatureList(). + - Fixed headers for use from C++. + - XML_GetCurrentLineNumber() and XML_GetCurrentColumnNumber() + now return unsigned integers. + - Added XML_LARGE_SIZE switch to enable 64-bit integers for + byte indexes and line/column numbers. + - Updated to use libtool 1.5.22 (the most recent). + - Added support for AmigaOS. + - Some mostly minor bug fixes. SF issues include: #1006708, + #1021776, #1023646, #1114960, #1156398, #1221160, #1271642. + +Release 1.95.8 Fri Jul 23 2004 + - Major new feature: suspend/resume. Handlers can now request + that a parse be suspended for later resumption or aborted + altogether. See "Temporarily Stopping Parsing" in the + documentation for more details. + - Some mostly minor bug fixes, but compilation should no + longer generate warnings on most platforms. SF issues + include: #827319, #840173, #846309, #888329, #896188, #923913, + #928113, #961698, #985192. + +Release 1.95.7 Mon Oct 20 2003 + - Fixed enum XML_Status issue (reported on SourceForge many + times), so compilers that are properly picky will be happy. + - Introduced an XMLCALL macro to control the calling + convention used by the Expat API; this macro should be used + to annotate prototypes and definitions of callback + implementations in code compiled with a calling convention + other than the default convention for the host platform. + - Improved ability to build without the configure-generated + expat_config.h header. This is useful for applications + which embed Expat rather than linking in the library. + - Fixed a variety of bugs: see SF issues #458907, #609603, + #676844, #679754, #692878, #692964, #695401, #699323, #699487, + #820946. + - Improved hash table lookups. + - Added more regression tests and improved documentation. + +Release 1.95.6 Tue Jan 28 2003 + - Added XML_FreeContentModel(). + - Added XML_MemMalloc(), XML_MemRealloc(), XML_MemFree(). + - Fixed a variety of bugs: see SF issues #615606, #616863, + #618199, #653180, #673791. + - Enhanced the regression test suite. + - Man page improvements: includes SF issue #632146. + +Release 1.95.5 Fri Sep 6 2002 + - Added XML_UseForeignDTD() for improved SAX2 support. + - Added XML_GetFeatureList(). + - Defined XML_Bool type and the values XML_TRUE and XML_FALSE. + - Use an incomplete struct instead of a void* for the parser + (may not retain). + - Fixed UTF-8 decoding bug that caused legal UTF-8 to be rejected. + - Finally fixed bug where default handler would report DTD + events that were already handled by another handler. + Initial patch contributed by Darryl Miles. + - Removed unnecessary DllMain() function that caused static + linking into a DLL to be difficult. + - Added VC++ projects for building static libraries. + - Reduced line-length for all source code and headers to be + no longer than 80 characters, to help with AS/400 support. + - Reduced memory copying during parsing (SF patch #600964). + - Fixed a variety of bugs: see SF issues #580793, #434664, + #483514, #580503, #581069, #584041, #584183, #584832, #585537, + #596555, #596678, #598352, #598944, #599715, #600479, #600971. + +Release 1.95.4 Fri Jul 12 2002 + - Added support for VMS, contributed by Craig Berry. See + vms/README.vms for more information. + - Added Mac OS (classic) support, with a makefile for MPW, + contributed by Thomas Wegner and Daryle Walker. + - Added Borland C++ Builder 5 / BCC 5.5 support, contributed + by Patrick McConnell (SF patch #538032). + - Fixed a variety of bugs: see SF issues #441449, #563184, + #564342, #566334, #566901, #569461, #570263, #575168, #579196. + - Made skippedEntityHandler conform to SAX2 (see source comment) + - Re-implemented WFC: Entity Declared from XML 1.0 spec and + added a new error "entity declared in parameter entity": + see SF bug report #569461 and SF patch #578161 + - Re-implemented section 5.1 from XML 1.0 spec: + see SF bug report #570263 and SF patch #578161 + +Release 1.95.3 Mon Jun 3 2002 + - Added a project to the MSVC workspace to create a wchar_t + version of the library; the DLLs are named libexpatw.dll. + - Changed the name of the Windows DLLs from expat.dll to + libexpat.dll; this fixes SF bug #432456. + - Added the XML_ParserReset() API function. + - Fixed XML_SetReturnNSTriplet() to work for element names. + - Made the XML_UNICODE builds usable (thanks, Karl!). + - Allow xmlwf to read from standard input. + - Install a man page for xmlwf on Unix systems. + - Fixed many bugs; see SF bug reports #231864, #461380, #464837, + #466885, #469226, #477667, #484419, #487840, #494749, #496505, + #547350. Other bugs which we can't test as easily may also + have been fixed, especially in the area of build support. + +Release 1.95.2 Fri Jul 27 2001 + - More changes to make MSVC happy with the build; add a single + workspace to support both the library and xmlwf application. + - Added a Windows installer for Windows users; includes + xmlwf.exe. + - Added compile-time constants that can be used to determine the + Expat version + - Removed a lot of GNU-specific dependencies to aide portability + among the various Unix flavors. + - Fix the UTF-8 BOM bug. + - Cleaned up warning messages for several compilers. + - Added the -Wall, -Wstrict-prototypes options for GCC. + +Release 1.95.1 Sun Oct 22 15:11:36 EDT 2000 + - Changes to get expat to build under Microsoft compiler + - Removed all aborts and instead return an UNEXPECTED_STATE error. + - Fixed a bug where a stray '%' in an entity value would cause an + abort. + - Defined XML_SetEndNamespaceDeclHandler. Thanks to Darryl Miles for + finding this oversight. + - Changed default patterns in lib/Makefile.in to fit non-GNU makes + Thanks to robin@unrated.net for reporting and providing an + account to test on. + - The reference had the wrong label for XML_SetStartNamespaceDecl. + Reported by an anonymous user. + +Release 1.95.0 Fri Sep 29 2000 + - XML_ParserCreate_MM + Allows you to set a memory management suite to replace the + standard malloc,realloc, and free. + - XML_SetReturnNSTriplet + If you turn this feature on when namespace processing is in + effect, then qualified, prefixed element and attribute names + are returned as "uri|name|prefix" where '|' is whatever + separator character is used in namespace processing. + - Merged in features from perl-expat + o XML_SetElementDeclHandler + o XML_SetAttlistDeclHandler + o XML_SetXmlDeclHandler + o XML_SetEntityDeclHandler + o StartDoctypeDeclHandler takes 3 additional parameters: + sysid, pubid, has_internal_subset + o Many paired handler setters (like XML_SetElementHandler) + now have corresponding individual handler setters + o XML_GetInputContext for getting the input context of + the current parse position. + - Added reference material + - Packaged into a distribution that builds a sharable library diff --git a/contrib/expat/FREEBSD-Xlist b/contrib/expat/FREEBSD-Xlist new file mode 100644 index 0000000..26bed47 --- /dev/null +++ b/contrib/expat/FREEBSD-Xlist @@ -0,0 +1,19 @@ +# $FreeBSD$ +*.MPW +*.cmake +*.def +*.dsp +*.dsw +*.m4 +*.pc.in +*config.h +CMake* +Configure* +amiga +bcb5 +configure +conftools +doc/valid-xhtml10.png +m4 +vms +win32 diff --git a/contrib/expat/MANIFEST b/contrib/expat/MANIFEST new file mode 100644 index 0000000..7a020dc --- /dev/null +++ b/contrib/expat/MANIFEST @@ -0,0 +1,141 @@ +amiga/launch.c +amiga/expat_68k.c +amiga/expat_68k.h +amiga/expat_68k_handler_stubs.c +amiga/expat_base.h +amiga/expat_vectors.c +amiga/expat_lib.c +amiga/expat.xml +amiga/README.txt +amiga/Makefile +amiga/include/proto/expat.h +amiga/include/libraries/expat.h +amiga/include/interfaces/expat.h +amiga/include/inline4/expat.h +bcb5/README.txt +bcb5/all_projects.bpg +bcb5/elements.bpf +bcb5/elements.bpr +bcb5/elements.mak +bcb5/expat.bpf +bcb5/expat.bpr +bcb5/expat.mak +bcb5/expat_static.bpf +bcb5/expat_static.bpr +bcb5/expat_static.mak +bcb5/expatw.bpf +bcb5/expatw.bpr +bcb5/expatw.mak +bcb5/expatw_static.bpf +bcb5/expatw_static.bpr +bcb5/expatw_static.mak +bcb5/libexpat_mtd.def +bcb5/libexpatw_mtd.def +bcb5/makefile.mak +bcb5/outline.bpf +bcb5/outline.bpr +bcb5/outline.mak +bcb5/setup.bat +bcb5/xmlwf.bpf +bcb5/xmlwf.bpr +bcb5/xmlwf.mak +doc/expat.png +doc/reference.html +doc/style.css +doc/valid-xhtml10.png +doc/xmlwf.1 +doc/xmlwf.sgml +CMakeLists.txt +CMake.README +COPYING +Changes +ConfigureChecks.cmake +MANIFEST +Makefile.in +README +configure +configure.in +expat_config.h.in +expat_config.h.cmake +expat.pc.in +expat.dsw +aclocal.m4 +conftools/PrintPath +conftools/ac_c_bigendian_cross.m4 +conftools/expat.m4 +conftools/get-version.sh +conftools/mkinstalldirs +conftools/config.guess +conftools/config.sub +conftools/install-sh +conftools/ltmain.sh +m4/libtool.m4 +m4/ltversion.m4 +m4/ltoptions.m4 +m4/ltsugar.m4 +m4/lt~obsolete.m4 +examples/elements.c +examples/elements.dsp +examples/outline.c +examples/outline.dsp +lib/Makefile.MPW +lib/amigaconfig.h +lib/ascii.h +lib/asciitab.h +lib/expat.dsp +lib/expat.h +lib/expat_external.h +lib/expat_static.dsp +lib/expatw.dsp +lib/expatw_static.dsp +lib/iasciitab.h +lib/internal.h +lib/latin1tab.h +lib/libexpat.def +lib/libexpatw.def +lib/macconfig.h +lib/nametab.h +lib/utf8tab.h +lib/winconfig.h +lib/xmlparse.c +lib/xmlrole.c +lib/xmlrole.h +lib/xmltok.c +lib/xmltok.h +lib/xmltok_impl.c +lib/xmltok_impl.h +lib/xmltok_ns.c +tests/benchmark/README.txt +tests/benchmark/benchmark.c +tests/benchmark/benchmark.dsp +tests/benchmark/benchmark.dsw +tests/README.txt +tests/chardata.c +tests/chardata.h +tests/minicheck.c +tests/minicheck.h +tests/runtests.c +tests/runtestspp.cpp +tests/xmltest.sh +vms/README.vms +vms/descrip.mms +vms/expat_config.h +win32/MANIFEST.txt +win32/README.txt +win32/expat.iss +xmlwf/codepage.c +xmlwf/codepage.h +xmlwf/ct.c +xmlwf/filemap.h +xmlwf/readfilemap.c +xmlwf/unixfilemap.c +xmlwf/win32filemap.c +xmlwf/xmlfile.c +xmlwf/xmlfile.h +xmlwf/xmlmime.c +xmlwf/xmlmime.h +xmlwf/xmltchar.h +xmlwf/xmlurl.h +xmlwf/xmlwf.c +xmlwf/xmlwf.dsp +xmlwf/xmlwin32url.cxx diff --git a/contrib/expat/Makefile.in b/contrib/expat/Makefile.in new file mode 100644 index 0000000..9c0f5d4 --- /dev/null +++ b/contrib/expat/Makefile.in @@ -0,0 +1,201 @@ +################################################################ +# Process this file with top-level configure script to produce Makefile +# +# Copyright 2000 Clark Cooper +# +# This file is part of EXPAT. +# +# EXPAT is free software; you can redistribute it and/or modify it +# under the terms of the License (based on the MIT/X license) contained +# in the file COPYING that comes with this distribution. +# +# EXPAT IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +# SOFTWARE OR THE USE OR OTHER DEALINGS IN EXPAT. +# + +SHELL = @SHELL@ + +srcdir = @srcdir@ +top_srcdir = @top_srcdir@ +VPATH = @srcdir@ + +prefix = @prefix@ +exec_prefix = @exec_prefix@ + +bindir = @bindir@ +libdir = @libdir@ +includedir = @includedir@ +man1dir = @mandir@/man1 +pkgconfigdir = $(libdir)/pkgconfig + +top_builddir = . + + +INSTALL = @INSTALL@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_DATA = @INSTALL_DATA@ +mkinstalldirs = $(SHELL) $(top_srcdir)/conftools/mkinstalldirs + +MANFILE = $(srcdir)/doc/xmlwf.1 +APIHEADER = $(srcdir)/lib/expat.h $(srcdir)/lib/expat_external.h +LIBRARY = libexpat.la + +DESTDIR = $(INSTALL_ROOT) + +default: buildlib xmlwf/xmlwf@EXEEXT@ + +buildlib: $(LIBRARY) expat.pc + +all: $(LIBRARY) expat.pc xmlwf/xmlwf@EXEEXT@ examples/elements examples/outline + +clean: + cd lib && rm -f $(LIBRARY) *.@OBJEXT@ *.lo && rm -rf .libs _libs + cd xmlwf && rm -f xmlwf *.@OBJEXT@ *.lo && rm -rf .libs _libs + cd examples && rm -f elements outline *.@OBJEXT@ *.lo && rm -rf .libs _libs + cd tests && rm -rf .libs runtests runtests.@OBJEXT@ runtestspp runtestspp.@OBJEXT@ + cd tests && rm -f chardata.@OBJEXT@ minicheck.@OBJEXT@ + rm -rf .libs libexpat.la + rm -f examples/core tests/core xmlwf/core + +clobber: clean + +distclean: clean + rm -f expat_config.h config.status config.log config.cache libtool + rm -f Makefile expat.pc + +extraclean: distclean + rm -f expat_config.h.in configure + rm -f aclocal.m4 m4/* + rm -f conftools/ltmain.sh conftools/install-sh conftools/config.guess conftools/config.sub + +check: tests/runtests tests/runtestspp + tests/runtests + tests/runtestspp + +install: xmlwf/xmlwf@EXEEXT@ installlib + $(mkinstalldirs) $(DESTDIR)$(bindir) $(DESTDIR)$(man1dir) + $(LIBTOOL) --mode=install $(INSTALL_PROGRAM) xmlwf/xmlwf@EXEEXT@ $(DESTDIR)$(bindir)/xmlwf + $(INSTALL_DATA) $(MANFILE) $(DESTDIR)$(man1dir) + +installlib: $(LIBRARY) $(APIHEADER) expat.pc + $(mkinstalldirs) $(DESTDIR)$(libdir) $(DESTDIR)$(includedir) $(DESTDIR)$(pkgconfigdir) + $(LIBTOOL) --mode=install $(INSTALL) $(LIBRARY) $(DESTDIR)$(libdir)/$(LIBRARY) + for FN in $(APIHEADER) ; do $(INSTALL_DATA) $$FN $(DESTDIR)$(includedir) ; done + $(INSTALL_DATA) expat.pc $(DESTDIR)$(pkgconfigdir)/expat.pc + +uninstall: uninstalllib + $(LIBTOOL) --mode=uninstall rm -f $(DESTDIR)$(bindir)/xmlwf@EXEEXT@ + rm -f $(DESTDIR)$(man1dir)/xmlwf.1 + +uninstalllib: + $(LIBTOOL) --mode=uninstall rm -f $(DESTDIR)$(libdir)/$(LIBRARY) + rm -f $(DESTDIR)$(includedir)/expat.h + rm -f $(DESTDIR)$(includedir)/expat_external.h + rm -f $(DESTDIR)$(pkgconfigdir)/expat.pc + +# for VPATH builds (invoked by configure) +mkdir-init: + @for d in lib xmlwf examples tests ; do \ + (mkdir $$d 2> /dev/null || test 1) ; \ + done + +CC = @CC@ +CXX = @CXX@ +LIBTOOL = @LIBTOOL@ + +INCLUDES = -I$(srcdir)/lib -I. +LDFLAGS = @LDFLAGS@ +CPPFLAGS = @CPPFLAGS@ -DHAVE_EXPAT_CONFIG_H +CFLAGS = @CFLAGS@ +CXXFLAGS = @CXXFLAGS@ +VSNFLAG = -version-info @LIBCURRENT@:@LIBREVISION@:@LIBAGE@ + +### autoconf this? +LTFLAGS = --silent + +COMPILE = $(CC) $(INCLUDES) $(CFLAGS) $(DEFS) $(CPPFLAGS) +CXXCOMPILE = $(CXX) $(INCLUDES) $(CXXFLAGS) $(DEFS) $(CPPFLAGS) +LTCOMPILE = $(LIBTOOL) $(LTFLAGS) --mode=compile $(COMPILE) +LINK_LIB = $(LIBTOOL) $(LTFLAGS) --mode=link $(COMPILE) -no-undefined $(VSNFLAG) -rpath $(libdir) $(LDFLAGS) -o $@ +LINK_EXE = $(LIBTOOL) $(LTFLAGS) --mode=link $(COMPILE) $(LDFLAGS) -o $@ +LINK_CXX_EXE = $(LIBTOOL) $(LTFLAGS) --mode=link $(CXXCOMPILE) $(LDFLAGS) -o $@ + +LIB_OBJS = lib/xmlparse.lo lib/xmltok.lo lib/xmlrole.lo +$(LIBRARY): $(LIB_OBJS) + $(LINK_LIB) $(LIB_OBJS) + +expat.pc: $(top_builddir)/config.status + cd $(top_builddir) && $(SHELL) ./config.status $@ + +lib/xmlparse.lo: lib/xmlparse.c lib/expat.h lib/xmlrole.h lib/xmltok.h \ + $(top_builddir)/expat_config.h lib/expat_external.h lib/internal.h + +lib/xmlrole.lo: lib/xmlrole.c lib/ascii.h lib/xmlrole.h \ + $(top_builddir)/expat_config.h lib/expat_external.h lib/internal.h + +lib/xmltok.lo: lib/xmltok.c lib/xmltok_impl.c lib/xmltok_ns.c \ + lib/ascii.h lib/asciitab.h lib/iasciitab.h lib/latin1tab.h \ + lib/nametab.h lib/utf8tab.h lib/xmltok.h lib/xmltok_impl.h \ + $(top_builddir)/expat_config.h lib/expat_external.h lib/internal.h + + +XMLWF_OBJS = xmlwf/xmlwf.@OBJEXT@ xmlwf/xmlfile.@OBJEXT@ xmlwf/codepage.@OBJEXT@ xmlwf/@FILEMAP@.@OBJEXT@ +xmlwf/xmlwf.@OBJEXT@: xmlwf/xmlwf.c +xmlwf/xmlfile.@OBJEXT@: xmlwf/xmlfile.c +xmlwf/codepage.@OBJEXT@: xmlwf/codepage.c +xmlwf/@FILEMAP@.@OBJEXT@: xmlwf/@FILEMAP@.c +xmlwf/xmlwf@EXEEXT@: $(XMLWF_OBJS) $(LIBRARY) + $(LINK_EXE) $(XMLWF_OBJS) $(LIBRARY) + +examples/elements.@OBJEXT@: examples/elements.c +examples/elements: examples/elements.@OBJEXT@ $(LIBRARY) + $(LINK_EXE) $< $(LIBRARY) + +examples/outline.@OBJEXT@: examples/outline.c +examples/outline: examples/outline.@OBJEXT@ $(LIBRARY) + $(LINK_EXE) $< $(LIBRARY) + +tests/chardata.@OBJEXT@: tests/chardata.c tests/chardata.h +tests/minicheck.@OBJEXT@: tests/minicheck.c tests/minicheck.h +tests/runtests.@OBJEXT@: tests/runtests.c tests/chardata.h +tests/runtests: tests/runtests.@OBJEXT@ tests/chardata.@OBJEXT@ tests/minicheck.@OBJEXT@ $(LIBRARY) + $(LINK_EXE) tests/runtests.@OBJEXT@ tests/chardata.@OBJEXT@ tests/minicheck.@OBJEXT@ $(LIBRARY) +tests/runtestspp.@OBJEXT@: tests/runtestspp.cpp tests/runtests.c tests/chardata.h +tests/runtestspp: tests/runtestspp.@OBJEXT@ tests/chardata.@OBJEXT@ tests/minicheck.@OBJEXT@ $(LIBRARY) + $(LINK_CXX_EXE) tests/runtestspp.@OBJEXT@ tests/chardata.@OBJEXT@ tests/minicheck.@OBJEXT@ $(LIBRARY) + +tests/benchmark/benchmark.@OBJEXT@: tests/benchmark/benchmark.c +tests/benchmark/benchmark: tests/benchmark/benchmark.@OBJEXT@ $(LIBRARY) + $(LINK_EXE) tests/benchmark/benchmark.@OBJEXT@ $(LIBRARY) + +run-benchmark: tests/benchmark/benchmark + tests/benchmark/benchmark@EXEEXT@ -n $(top_srcdir)/../testdata/largefiles/recset.xml 65535 3 + +tests/xmlts.zip: + wget --output-document=tests/xmlts.zip \ + http://www.w3.org/XML/Test/xmlts20080827.zip + +tests/XML-Test-Suite: tests/xmlts.zip + cd tests && unzip -q xmlts.zip + +run-xmltest: xmlwf/xmlwf@EXEEXT@ tests/XML-Test-Suite + tests/xmltest.sh + +.SUFFIXES: .c .cpp .lo .@OBJEXT@ + +.cpp.@OBJEXT@: + $(CXXCOMPILE) -o $@ -c $< +.c.@OBJEXT@: + $(COMPILE) -o $@ -c $< +.c.lo: + $(LTCOMPILE) -o $@ -c $< + +.PHONY: buildlib all \ + clean distclean extraclean maintainer-clean \ + dist distdir \ + install uninstall diff --git a/contrib/expat/README b/contrib/expat/README new file mode 100644 index 0000000..1f88467 --- /dev/null +++ b/contrib/expat/README @@ -0,0 +1,139 @@ + + Expat, Release 2.1.0 + +This is Expat, a C library for parsing XML, written by James Clark. +Expat is a stream-oriented XML parser. This means that you register +handlers with the parser before starting the parse. These handlers +are called when the parser discovers the associated structures in the +document being parsed. A start tag is an example of the kind of +structures for which you may register handlers. + +Windows users should use the expat_win32bin package, which includes +both precompiled libraries and executables, and source code for +developers. + +Expat is free software. You may copy, distribute, and modify it under +the terms of the License contained in the file COPYING distributed +with this package. This license is the same as the MIT/X Consortium +license. + +Versions of Expat that have an odd minor version (the middle number in +the release above), are development releases and should be considered +as beta software. Releases with even minor version numbers are +intended to be production grade software. + +If you are building Expat from a check-out from the CVS repository, +you need to run a script that generates the configure script using the +GNU autoconf and libtool tools. To do this, you need to have +autoconf 2.58 or newer. Run the script like this: + + ./buildconf.sh + +Once this has been done, follow the same instructions as for building +from a source distribution. + +To build Expat from a source distribution, you first run the +configuration shell script in the top level distribution directory: + + ./configure + +There are many options which you may provide to configure (which you +can discover by running configure with the --help option). But the +one of most interest is the one that sets the installation directory. +By default, the configure script will set things up to install +libexpat into /usr/local/lib, expat.h into /usr/local/include, and +xmlwf into /usr/local/bin. If, for example, you'd prefer to install +into /home/me/mystuff/lib, /home/me/mystuff/include, and +/home/me/mystuff/bin, you can tell configure about that with: + + ./configure --prefix=/home/me/mystuff + +Another interesting option is to enable 64-bit integer support for +line and column numbers and the over-all byte index: + + ./configure CPPFLAGS=-DXML_LARGE_SIZE + +However, such a modification would be a breaking change to the ABI +and is therefore not recommended for general use - e.g. as part of +a Linux distribution - but rather for builds with special requirements. + +After running the configure script, the "make" command will build +things and "make install" will install things into their proper +location. Have a look at the "Makefile" to learn about additional +"make" options. Note that you need to have write permission into +the directories into which things will be installed. + +If you are interested in building Expat to provide document +information in UTF-16 encoding rather than the default UTF-8, follow +these instructions (after having run "make distclean"): + + 1. For UTF-16 output as unsigned short (and version/error + strings as char), run: + + ./configure CPPFLAGS=-DXML_UNICODE + + For UTF-16 output as wchar_t (incl. version/error strings), + run: + + ./configure CFLAGS="-g -O2 -fshort-wchar" \ + CPPFLAGS=-DXML_UNICODE_WCHAR_T + + 2. Edit the MakeFile, changing: + + LIBRARY = libexpat.la + + to: + + LIBRARY = libexpatw.la + + (Note the additional "w" in the library name.) + + 3. Run "make buildlib" (which builds the library only). + Or, to save step 2, run "make buildlib LIBRARY=libexpatw.la". + + 4. Run "make installlib" (which installs the library only). + Or, if step 2 was omitted, run "make installlib LIBRARY=libexpatw.la". + +Using DESTDIR or INSTALL_ROOT is enabled, with INSTALL_ROOT being the default +value for DESTDIR, and the rest of the make file using only DESTDIR. +It works as follows: + $ make install DESTDIR=/path/to/image +overrides the in-makefile set DESTDIR, while both + $ INSTALL_ROOT=/path/to/image make install + $ make install INSTALL_ROOT=/path/to/image +use DESTDIR=$(INSTALL_ROOT), even if DESTDIR eventually is defined in the +environment, because variable-setting priority is +1) commandline +2) in-makefile +3) environment + +Note: This only applies to the Expat library itself, building UTF-16 versions +of xmlwf and the tests is currently not supported. + +Note for Solaris users: The "ar" command is usually located in +"/usr/ccs/bin", which is not in the default PATH. You will need to +add this to your path for the "make" command, and probably also switch +to GNU make (the "make" found in /usr/ccs/bin does not seem to work +properly -- appearantly it does not understand .PHONY directives). If +you're using ksh or bash, use this command to build: + + PATH=/usr/ccs/bin:$PATH make + +When using Expat with a project using autoconf for configuration, you +can use the probing macro in conftools/expat.m4 to determine how to +include Expat. See the comments at the top of that file for more +information. + +A reference manual is available in the file doc/reference.html in this +distribution. + +The homepage for this project is http://www.libexpat.org/. There +are links there to connect you to the bug reports page. If you need +to report a bug when you don't have access to a browser, you may also +send a bug report by email to expat-bugs@mail.libexpat.org. + +Discussion related to the direction of future expat development takes +place on expat-discuss@mail.libexpat.org. Archives of this list and +other Expat-related lists may be found at: + + http://mail.libexpat.org/mailman/listinfo/ diff --git a/contrib/expat/configure.in b/contrib/expat/configure.in new file mode 100644 index 0000000..7e968c4 --- /dev/null +++ b/contrib/expat/configure.in @@ -0,0 +1,155 @@ +dnl configuration script for expat +dnl Process this file with autoconf to produce a configure script. +dnl +dnl Copyright 2000 Clark Cooper +dnl +dnl This file is part of EXPAT. +dnl +dnl EXPAT is free software; you can redistribute it and/or modify it +dnl under the terms of the License (based on the MIT/X license) contained +dnl in the file COPYING that comes with this distribution. +dnl + +dnl Ensure that Expat is configured with autoconf 2.58 or newer +AC_PREREQ(2.58) + +dnl Get the version number of Expat, using m4's esyscmd() command to run +dnl the command at m4-generation time. This allows us to create an m4 +dnl symbol holding the correct version number. AC_INIT() requires the +dnl version number at m4-time, rather than when ./configure is run, so +dnl all this must happen as part of m4, not as part of the shell code +dnl contained in ./configure. +dnl +dnl NOTE: esyscmd() is a GNU M4 extension. Thus, we wrap it in an appropriate +dnl test. I believe this test will work, but I don't have a place with non- +dnl GNU M4 to test it right now. +define([expat_version], ifdef([__gnu__], + [esyscmd(conftools/get-version.sh lib/expat.h)], + [2.1.x])) +AC_INIT(expat, expat_version, expat-bugs@libexpat.org) +undefine([expat_version]) + +AC_CONFIG_SRCDIR(Makefile.in) +AC_CONFIG_AUX_DIR(conftools) +AC_CONFIG_MACRO_DIR([m4]) + + +dnl +dnl Increment LIBREVISION if source code has changed at all +dnl +dnl If the API has changed, increment LIBCURRENT and set LIBREVISION to 0 +dnl +dnl If the API changes compatibly (i.e. simply adding a new function +dnl without changing or removing earlier interfaces), then increment LIBAGE. +dnl +dnl If the API changes incompatibly set LIBAGE back to 0 +dnl + +LIBCURRENT=7 +LIBREVISION=0 +LIBAGE=6 + +AC_CONFIG_HEADER(expat_config.h) + +sinclude(conftools/ac_c_bigendian_cross.m4) + +AC_LIBTOOL_WIN32_DLL +AC_PROG_LIBTOOL + +AC_SUBST(LIBCURRENT) +AC_SUBST(LIBREVISION) +AC_SUBST(LIBAGE) + +dnl Checks for programs. +AC_PROG_CC +AC_PROG_CXX +AC_PROG_INSTALL + +if test "$GCC" = yes ; then + dnl + dnl Be careful about adding the -fexceptions option; some versions of + dnl GCC don't support it and it causes extra warnings that are only + dnl distracting; avoid. + dnl + OLDCFLAGS="$CFLAGS -Wall -Wmissing-prototypes -Wstrict-prototypes" + CFLAGS="$OLDCFLAGS -fexceptions" + AC_MSG_CHECKING(whether $CC accepts -fexceptions) + AC_TRY_LINK( , , + AC_MSG_RESULT(yes), + AC_MSG_RESULT(no); CFLAGS="$OLDCFLAGS") + CXXFLAGS=`echo "$CFLAGS" | sed 's/ -Wmissing-prototypes -Wstrict-prototypes//'` +fi + +dnl Checks for header files. +AC_HEADER_STDC + +dnl Checks for typedefs, structures, and compiler characteristics. + +dnl Note: Avoid using AC_C_BIGENDIAN because it does not +dnl work in a cross compile. +AC_C_BIGENDIAN_CROSS + +AC_C_CONST +AC_TYPE_SIZE_T +AC_CHECK_FUNCS(memmove bcopy) + +dnl Only needed for xmlwf: +AC_CHECK_HEADERS(fcntl.h unistd.h) +AC_TYPE_OFF_T +AC_FUNC_MMAP + +if test "$ac_cv_func_mmap_fixed_mapped" = "yes"; then + FILEMAP=unixfilemap +else + FILEMAP=readfilemap +fi +AC_SUBST(FILEMAP) + +dnl Needed for the test support code; this was found at +dnl http://lists.gnu.org/archive/html/bug-autoconf/2002-07/msg00028.html + +# AC_CPP_FUNC +# ------------------ # +# Checks to see if ANSI C99 CPP variable __func__ works. +# If not, perhaps __FUNCTION__ works instead. +# If not, we'll just define __func__ to "". +AC_DEFUN([AC_CPP_FUNC], +[AC_REQUIRE([AC_PROG_CC_STDC])dnl +AC_CACHE_CHECK([for an ANSI C99-conforming __func__], ac_cv_cpp_func, +[AC_COMPILE_IFELSE([AC_LANG_PROGRAM([], +[[char *foo = __func__;]])], + [ac_cv_cpp_func=yes], + [AC_COMPILE_IFELSE([AC_LANG_PROGRAM([], +[[char *foo = __FUNCTION__;]])], + [ac_cv_cpp_func=__FUNCTION__], + [ac_cv_cpp_func=no])])]) +if test $ac_cv_cpp_func = __FUNCTION__; then + AC_DEFINE(__func__,__FUNCTION__, + [Define to __FUNCTION__ or "" if `__func__' does not conform to +ANSI C.]) +elif test $ac_cv_cpp_func = no; then + AC_DEFINE(__func__,"", + [Define to __FUNCTION__ or "" if `__func__' does not conform to +ANSI C.]) +fi +])# AC_CPP_FUNC + +AC_CPP_FUNC + + +dnl Some basic configuration: +AC_DEFINE([XML_NS], 1, + [Define to make XML Namespaces functionality available.]) +AC_DEFINE([XML_DTD], 1, + [Define to make parameter entity parsing functionality available.]) +AC_DEFINE([XML_CONTEXT_BYTES], 1024, + [Define to specify how much context to retain around the current parse point.]) + +AC_CONFIG_FILES([Makefile expat.pc]) +AC_OUTPUT + +abs_srcdir="`cd $srcdir && pwd`" +abs_builddir="`pwd`" +if test "$abs_srcdir" != "$abs_builddir"; then + make mkdir-init +fi diff --git a/contrib/expat/doc/expat.png b/contrib/expat/doc/expat.png Binary files differnew file mode 100644 index 0000000..5bc0726 --- /dev/null +++ b/contrib/expat/doc/expat.png diff --git a/contrib/expat/doc/reference.html b/contrib/expat/doc/reference.html new file mode 100644 index 0000000..8811a33 --- /dev/null +++ b/contrib/expat/doc/reference.html @@ -0,0 +1,2390 @@ +<?xml version="1.0" encoding="iso-8859-1"?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +<html> +<head> +<!-- Copyright 1999,2000 Clark Cooper <coopercc@netheaven.com> + All rights reserved. + This is free software. You may distribute or modify according to + the terms of the MIT/X License --> + <title>Expat XML Parser</title> + <meta name="author" content="Clark Cooper, coopercc@netheaven.com" /> + <meta http-equiv="Content-Style-Type" content="text/css" /> + <link href="style.css" rel="stylesheet" type="text/css" /> +</head> +<body> + <table cellspacing="0" cellpadding="0" width="100%"> + <tr> + <td class="corner"><img src="expat.png" alt="(Expat logo)" /></td> + <td class="banner"><h1>The Expat XML Parser</h1></td> + </tr> + <tr> + <td class="releaseno">Release 2.0.1</td> + <td></td> + </tr> + </table> +<div class="content"> + +<p>Expat is a library, written in C, for parsing XML documents. It's +the underlying XML parser for the open source Mozilla project, Perl's +<code>XML::Parser</code>, Python's <code>xml.parsers.expat</code>, and +other open-source XML parsers.</p> + +<p>This library is the creation of James Clark, who's also given us +groff (an nroff look-alike), Jade (an implemention of ISO's DSSSL +stylesheet language for SGML), XP (a Java XML parser package), XT (a +Java XSL engine). James was also the technical lead on the XML +Working Group at W3C that produced the XML specification.</p> + +<p>This is free software, licensed under the <a +href="../COPYING">MIT/X Consortium license</a>. You may download it +from <a href="http://www.libexpat.org/">the Expat home page</a>. +</p> + +<p>The bulk of this document was originally commissioned as an article +by <a href="http://www.xml.com/">XML.com</a>. They graciously allowed +Clark Cooper to retain copyright and to distribute it with Expat. +This version has been substantially extended to include documentation +on features which have been added since the original article was +published, and additional information on using the original +interface.</p> + +<hr /> +<h2>Table of Contents</h2> +<ul> + <li><a href="#overview">Overview</a></li> + <li><a href="#building">Building and Installing</a></li> + <li><a href="#using">Using Expat</a></li> + <li><a href="#reference">Reference</a> + <ul> + <li><a href="#creation">Parser Creation Functions</a> + <ul> + <li><a href="#XML_ParserCreate">XML_ParserCreate</a></li> + <li><a href="#XML_ParserCreateNS">XML_ParserCreateNS</a></li> + <li><a href="#XML_ParserCreate_MM">XML_ParserCreate_MM</a></li> + <li><a href="#XML_ExternalEntityParserCreate">XML_ExternalEntityParserCreate</a></li> + <li><a href="#XML_ParserFree">XML_ParserFree</a></li> + <li><a href="#XML_ParserReset">XML_ParserReset</a></li> + </ul> + </li> + <li><a href="#parsing">Parsing Functions</a> + <ul> + <li><a href="#XML_Parse">XML_Parse</a></li> + <li><a href="#XML_ParseBuffer">XML_ParseBuffer</a></li> + <li><a href="#XML_GetBuffer">XML_GetBuffer</a></li> + <li><a href="#XML_StopParser">XML_StopParser</a></li> + <li><a href="#XML_ResumeParser">XML_ResumeParser</a></li> + <li><a href="#XML_GetParsingStatus">XML_GetParsingStatus</a></li> + </ul> + </li> + <li><a href="#setting">Handler Setting Functions</a> + <ul> + <li><a href="#XML_SetStartElementHandler">XML_SetStartElementHandler</a></li> + <li><a href="#XML_SetEndElementHandler">XML_SetEndElementHandler</a></li> + <li><a href="#XML_SetElementHandler">XML_SetElementHandler</a></li> + <li><a href="#XML_SetCharacterDataHandler">XML_SetCharacterDataHandler</a></li> + <li><a href="#XML_SetProcessingInstructionHandler">XML_SetProcessingInstructionHandler</a></li> + <li><a href="#XML_SetCommentHandler">XML_SetCommentHandler</a></li> + <li><a href="#XML_SetStartCdataSectionHandler">XML_SetStartCdataSectionHandler</a></li> + <li><a href="#XML_SetEndCdataSectionHandler">XML_SetEndCdataSectionHandler</a></li> + <li><a href="#XML_SetCdataSectionHandler">XML_SetCdataSectionHandler</a></li> + <li><a href="#XML_SetDefaultHandler">XML_SetDefaultHandler</a></li> + <li><a href="#XML_SetDefaultHandlerExpand">XML_SetDefaultHandlerExpand</a></li> + <li><a href="#XML_SetExternalEntityRefHandler">XML_SetExternalEntityRefHandler</a></li> + <li><a href="#XML_SetExternalEntityRefHandlerArg">XML_SetExternalEntityRefHandlerArg</a></li> + <li><a href="#XML_SetSkippedEntityHandler">XML_SetSkippedEntityHandler</a></li> + <li><a href="#XML_SetUnknownEncodingHandler">XML_SetUnknownEncodingHandler</a></li> + <li><a href="#XML_SetStartNamespaceDeclHandler">XML_SetStartNamespaceDeclHandler</a></li> + <li><a href="#XML_SetEndNamespaceDeclHandler">XML_SetEndNamespaceDeclHandler</a></li> + <li><a href="#XML_SetNamespaceDeclHandler">XML_SetNamespaceDeclHandler</a></li> + <li><a href="#XML_SetXmlDeclHandler">XML_SetXmlDeclHandler</a></li> + <li><a href="#XML_SetStartDoctypeDeclHandler">XML_SetStartDoctypeDeclHandler</a></li> + <li><a href="#XML_SetEndDoctypeDeclHandler">XML_SetEndDoctypeDeclHandler</a></li> + <li><a href="#XML_SetDoctypeDeclHandler">XML_SetDoctypeDeclHandler</a></li> + <li><a href="#XML_SetElementDeclHandler">XML_SetElementDeclHandler</a></li> + <li><a href="#XML_SetAttlistDeclHandler">XML_SetAttlistDeclHandler</a></li> + <li><a href="#XML_SetEntityDeclHandler">XML_SetEntityDeclHandler</a></li> + <li><a href="#XML_SetUnparsedEntityDeclHandler">XML_SetUnparsedEntityDeclHandler</a></li> + <li><a href="#XML_SetNotationDeclHandler">XML_SetNotationDeclHandler</a></li> + <li><a href="#XML_SetNotStandaloneHandler">XML_SetNotStandaloneHandler</a></li> + </ul> + </li> + <li><a href="#position">Parse Position and Error Reporting Functions</a> + <ul> + <li><a href="#XML_GetErrorCode">XML_GetErrorCode</a></li> + <li><a href="#XML_ErrorString">XML_ErrorString</a></li> + <li><a href="#XML_GetCurrentByteIndex">XML_GetCurrentByteIndex</a></li> + <li><a href="#XML_GetCurrentLineNumber">XML_GetCurrentLineNumber</a></li> + <li><a href="#XML_GetCurrentColumnNumber">XML_GetCurrentColumnNumber</a></li> + <li><a href="#XML_GetCurrentByteCount">XML_GetCurrentByteCount</a></li> + <li><a href="#XML_GetInputContext">XML_GetInputContext</a></li> + </ul> + </li> + <li><a href="#miscellaneous">Miscellaneous Functions</a> + <ul> + <li><a href="#XML_SetUserData">XML_SetUserData</a></li> + <li><a href="#XML_GetUserData">XML_GetUserData</a></li> + <li><a href="#XML_UseParserAsHandlerArg">XML_UseParserAsHandlerArg</a></li> + <li><a href="#XML_SetBase">XML_SetBase</a></li> + <li><a href="#XML_GetBase">XML_GetBase</a></li> + <li><a href="#XML_GetSpecifiedAttributeCount">XML_GetSpecifiedAttributeCount</a></li> + <li><a href="#XML_GetIdAttributeIndex">XML_GetIdAttributeIndex</a></li> + <li><a href="#XML_GetAttributeInfo">XML_GetAttributeInfo</a></li> + <li><a href="#XML_SetEncoding">XML_SetEncoding</a></li> + <li><a href="#XML_SetParamEntityParsing">XML_SetParamEntityParsing</a></li> + <li><a href="#XML_SetHashSalt">XML_SetHashSalt</a></li> + <li><a href="#XML_UseForeignDTD">XML_UseForeignDTD</a></li> + <li><a href="#XML_SetReturnNSTriplet">XML_SetReturnNSTriplet</a></li> + <li><a href="#XML_DefaultCurrent">XML_DefaultCurrent</a></li> + <li><a href="#XML_ExpatVersion">XML_ExpatVersion</a></li> + <li><a href="#XML_ExpatVersionInfo">XML_ExpatVersionInfo</a></li> + <li><a href="#XML_GetFeatureList">XML_GetFeatureList</a></li> + <li><a href="#XML_FreeContentModel">XML_FreeContentModel</a></li> + <li><a href="#XML_MemMalloc">XML_MemMalloc</a></li> + <li><a href="#XML_MemRealloc">XML_MemRealloc</a></li> + <li><a href="#XML_MemFree">XML_MemFree</a></li> + </ul> + </li> + </ul> + </li> +</ul> + +<hr /> +<h2><a name="overview">Overview</a></h2> + +<p>Expat is a stream-oriented parser. You register callback (or +handler) functions with the parser and then start feeding it the +document. As the parser recognizes parts of the document, it will +call the appropriate handler for that part (if you've registered one.) +The document is fed to the parser in pieces, so you can start parsing +before you have all the document. This also allows you to parse really +huge documents that won't fit into memory.</p> + +<p>Expat can be intimidating due to the many kinds of handlers and +options you can set. But you only need to learn four functions in +order to do 90% of what you'll want to do with it:</p> + +<dl> + +<dt><code><a href= "#XML_ParserCreate" + >XML_ParserCreate</a></code></dt> + <dd>Create a new parser object.</dd> + +<dt><code><a href= "#XML_SetElementHandler" + >XML_SetElementHandler</a></code></dt> + <dd>Set handlers for start and end tags.</dd> + +<dt><code><a href= "#XML_SetCharacterDataHandler" + >XML_SetCharacterDataHandler</a></code></dt> + <dd>Set handler for text.</dd> + +<dt><code><a href= "#XML_Parse" + >XML_Parse</a></code></dt> + <dd>Pass a buffer full of document to the parser</dd> +</dl> + +<p>These functions and others are described in the <a +href="#reference">reference</a> part of this document. The reference +section also describes in detail the parameters passed to the +different types of handlers.</p> + +<p>Let's look at a very simple example program that only uses 3 of the +above functions (it doesn't need to set a character handler.) The +program <a href="../examples/outline.c">outline.c</a> prints an +element outline, indenting child elements to distinguish them from the +parent element that contains them. The start handler does all the +work. It prints two indenting spaces for every level of ancestor +elements, then it prints the element and attribute +information. Finally it increments the global <code>Depth</code> +variable.</p> + +<pre class="eg"> +int Depth; + +void XMLCALL +start(void *data, const char *el, const char **attr) { + int i; + + for (i = 0; i < Depth; i++) + printf(" "); + + printf("%s", el); + + for (i = 0; attr[i]; i += 2) { + printf(" %s='%s'", attr[i], attr[i + 1]); + } + + printf("\n"); + Depth++; +} /* End of start handler */ +</pre> + +<p>The end tag simply does the bookkeeping work of decrementing +<code>Depth</code>.</p> +<pre class="eg"> +void XMLCALL +end(void *data, const char *el) { + Depth--; +} /* End of end handler */ +</pre> + +<p>Note the <code>XMLCALL</code> annotation used for the callbacks. +This is used to ensure that the Expat and the callbacks are using the +same calling convention in case the compiler options used for Expat +itself and the client code are different. Expat tries not to care +what the default calling convention is, though it may require that it +be compiled with a default convention of "cdecl" on some platforms. +For code which uses Expat, however, the calling convention is +specified by the <code>XMLCALL</code> annotation on most platforms; +callbacks should be defined using this annotation.</p> + +<p>The <code>XMLCALL</code> annotation was added in Expat 1.95.7, but +existing working Expat applications don't need to add it (since they +are already using the "cdecl" calling convention, or they wouldn't be +working). The annotation is only needed if the default calling +convention may be something other than "cdecl". To use the annotation +safely with older versions of Expat, you can conditionally define it +<em>after</em> including Expat's header file:</p> + +<pre class="eg"> +#include <expat.h> + +#ifndef XMLCALL +#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) +#define XMLCALL __cdecl +#elif defined(__GNUC__) +#define XMLCALL __attribute__((cdecl)) +#else +#define XMLCALL +#endif +#endif +</pre> + +<p>After creating the parser, the main program just has the job of +shoveling the document to the parser so that it can do its work.</p> + +<hr /> +<h2><a name="building">Building and Installing Expat</a></h2> + +<p>The Expat distribution comes as a compressed (with GNU gzip) tar +file. You may download the latest version from <a href= +"http://sourceforge.net/projects/expat/" >Source Forge</a>. After +unpacking this, cd into the directory. Then follow either the Win32 +directions or Unix directions below.</p> + +<h3>Building under Win32</h3> + +<p>If you're using the GNU compiler under cygwin, follow the Unix +directions in the next section. Otherwise if you have Microsoft's +Developer Studio installed, then from Windows Explorer double-click on +"expat.dsp" in the lib directory and build and install in the usual +manner.</p> + +<p>Alternatively, you may download the Win32 binary package that +contains the "expat.h" include file and a pre-built DLL.</p> + +<h3>Building under Unix (or GNU)</h3> + +<p>First you'll need to run the configure shell script in order to +configure the Makefiles and headers for your system.</p> + +<p>If you're happy with all the defaults that configure picks for you, +and you have permission on your system to install into /usr/local, you +can install Expat with this sequence of commands:</p> + +<pre class="eg"> +./configure +make +make install +</pre> + +<p>There are some options that you can provide to this script, but the +only one we'll mention here is the <code>--prefix</code> option. You +can find out all the options available by running configure with just +the <code>--help</code> option.</p> + +<p>By default, the configure script sets things up so that the library +gets installed in <code>/usr/local/lib</code> and the associated +header file in <code>/usr/local/include</code>. But if you were to +give the option, <code>--prefix=/home/me/mystuff</code>, then the +library and header would get installed in +<code>/home/me/mystuff/lib</code> and +<code>/home/me/mystuff/include</code> respectively.</p> + +<h3>Configuring Expat Using the Pre-Processor</h3> + +<p>Expat's feature set can be configured using a small number of +pre-processor definitions. The definition of this symbols does not +affect the set of entry points for Expat, only the behavior of the API +and the definition of character types in the case of +<code>XML_UNICODE_WCHAR_T</code>. The symbols are:</p> + +<dl class="cpp-symbols"> +<dt>XML_DTD</dt> +<dd>Include support for using and reporting DTD-based content. If +this is defined, default attribute values from an external DTD subset +are reported and attribute value normalization occurs based on the +type of attributes defined in the external subset. Without +this, Expat has a smaller memory footprint and can be faster, but will +not load external entities or process conditional sections. This does +not affect the set of functions available in the API.</dd> + +<dt>XML_NS</dt> +<dd>When defined, support for the <cite><a href= +"http://www.w3.org/TR/REC-xml-names/" >Namespaces in XML</a></cite> +specification is included.</dd> + +<dt>XML_UNICODE</dt> +<dd>When defined, character data reported to the application is +encoded in UTF-16 using wide characters of the type +<code>XML_Char</code>. This is implied if +<code>XML_UNICODE_WCHAR_T</code> is defined.</dd> + +<dt>XML_UNICODE_WCHAR_T</dt> +<dd>If defined, causes the <code>XML_Char</code> character type to be +defined using the <code>wchar_t</code> type; otherwise, <code>unsigned +short</code> is used. Defining this implies +<code>XML_UNICODE</code>.</dd> + +<dt>XML_LARGE_SIZE</dt> +<dd>If defined, causes the <code>XML_Size</code> and <code>XML_Index</code> +integer types to be at least 64 bits in size. This is intended to support +processing of very large input streams, where the return values of +<code><a href="#XML_GetCurrentByteIndex" >XML_GetCurrentByteIndex</a></code>, +<code><a href="#XML_GetCurrentLineNumber" >XML_GetCurrentLineNumber</a></code> and +<code><a href="#XML_GetCurrentColumnNumber" >XML_GetCurrentColumnNumber</a></code> +could overflow. It may not be supported by all compilers, and is turned +off by default.</dd> + +<dt>XML_CONTEXT_BYTES</dt> +<dd>The number of input bytes of markup context which the parser will +ensure are available for reporting via <code><a href= +"#XML_GetInputContext" >XML_GetInputContext</a></code>. This is +normally set to 1024, and must be set to a positive interger. If this +is not defined, the input context will not be available and <code><a +href= "#XML_GetInputContext" >XML_GetInputContext</a></code> will +always report NULL. Without this, Expat has a smaller memory +footprint and can be faster.</dd> + +<dt>XML_STATIC</dt> +<dd>On Windows, this should be set if Expat is going to be linked +statically with the code that calls it; this is required to get all +the right MSVC magic annotations correct. This is ignored on other +platforms.</dd> + +<dt>XML_ATTR_INFO</dt> +<dd>If defined, makes the the additional function <code><a href= +"#XML_GetAttributeInfo" >XML_GetAttributeInfo</a></code> available +for reporting attribute byte offsets.</dd> +</dl> + +<hr /> +<h2><a name="using">Using Expat</a></h2> + +<h3>Compiling and Linking Against Expat</h3> + +<p>Unless you installed Expat in a location not expected by your +compiler and linker, all you have to do to use Expat in your programs +is to include the Expat header (<code>#include <expat.h></code>) +in your files that make calls to it and to tell the linker that it +needs to link against the Expat library. On Unix systems, this would +usually be done with the <code>-lexpat</code> argument. Otherwise, +you'll need to tell the compiler where to look for the Expat header +and the linker where to find the Expat library. You may also need to +take steps to tell the operating system where to find this library at +run time.</p> + +<p>On a Unix-based system, here's what a Makefile might look like when +Expat is installed in a standard location:</p> + +<pre class="eg"> +CC=cc +LDFLAGS= +LIBS= -lexpat +xmlapp: xmlapp.o + $(CC) $(LDFLAGS) -o xmlapp xmlapp.o $(LIBS) +</pre> + +<p>If you installed Expat in, say, <code>/home/me/mystuff</code>, then +the Makefile would look like this:</p> + +<pre class="eg"> +CC=cc +CFLAGS= -I/home/me/mystuff/include +LDFLAGS= +LIBS= -L/home/me/mystuff/lib -lexpat +xmlapp: xmlapp.o + $(CC) $(LDFLAGS) -o xmlapp xmlapp.o $(LIBS) +</pre> + +<p>You'd also have to set the environment variable +<code>LD_LIBRARY_PATH</code> to <code>/home/me/mystuff/lib</code> (or +to <code>${LD_LIBRARY_PATH}:/home/me/mystuff/lib</code> if +LD_LIBRARY_PATH already has some directories in it) in order to run +your application.</p> + +<h3>Expat Basics</h3> + +<p>As we saw in the example in the overview, the first step in parsing +an XML document with Expat is to create a parser object. There are <a +href="#creation">three functions</a> in the Expat API for creating a +parser object. However, only two of these (<code><a href= +"#XML_ParserCreate" >XML_ParserCreate</a></code> and <code><a href= +"#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>) can be used for +constructing a parser for a top-level document. The object returned +by these functions is an opaque pointer (i.e. "expat.h" declares it as +void *) to data with further internal structure. In order to free the +memory associated with this object you must call <code><a href= +"#XML_ParserFree" >XML_ParserFree</a></code>. Note that if you have +provided any <a href="#userdata">user data</a> that gets stored in the +parser, then your application is responsible for freeing it prior to +calling <code>XML_ParserFree</code>.</p> + +<p>The objects returned by the parser creation functions are good for +parsing only one XML document or external parsed entity. If your +application needs to parse many XML documents, then it needs to create +a parser object for each one. The best way to deal with this is to +create a higher level object that contains all the default +initialization you want for your parser objects.</p> + +<p>Walking through a document hierarchy with a stream oriented parser +will require a good stack mechanism in order to keep track of current +context. For instance, to answer the simple question, "What element +does this text belong to?" requires a stack, since the parser may have +descended into other elements that are children of the current one and +has encountered this text on the way out.</p> + +<p>The things you're likely to want to keep on a stack are the +currently opened element and it's attributes. You push this +information onto the stack in the start handler and you pop it off in +the end handler.</p> + +<p>For some tasks, it is sufficient to just keep information on what +the depth of the stack is (or would be if you had one.) The outline +program shown above presents one example. Another such task would be +skipping over a complete element. When you see the start tag for the +element you want to skip, you set a skip flag and record the depth at +which the element started. When the end tag handler encounters the +same depth, the skipped element has ended and the flag may be +cleared. If you follow the convention that the root element starts at +1, then you can use the same variable for skip flag and skip +depth.</p> + +<pre class="eg"> +void +init_info(Parseinfo *info) { + info->skip = 0; + info->depth = 1; + /* Other initializations here */ +} /* End of init_info */ + +void XMLCALL +rawstart(void *data, const char *el, const char **attr) { + Parseinfo *inf = (Parseinfo *) data; + + if (! inf->skip) { + if (should_skip(inf, el, attr)) { + inf->skip = inf->depth; + } + else + start(inf, el, attr); /* This does rest of start handling */ + } + + inf->depth++; +} /* End of rawstart */ + +void XMLCALL +rawend(void *data, const char *el) { + Parseinfo *inf = (Parseinfo *) data; + + inf->depth--; + + if (! inf->skip) + end(inf, el); /* This does rest of end handling */ + + if (inf->skip == inf->depth) + inf->skip = 0; +} /* End rawend */ +</pre> + +<p>Notice in the above example the difference in how depth is +manipulated in the start and end handlers. The end tag handler should +be the mirror image of the start tag handler. This is necessary to +properly model containment. Since, in the start tag handler, we +incremented depth <em>after</em> the main body of start tag code, then +in the end handler, we need to manipulate it <em>before</em> the main +body. If we'd decided to increment it first thing in the start +handler, then we'd have had to decrement it last thing in the end +handler.</p> + +<h3 id="userdata">Communicating between handlers</h3> + +<p>In order to be able to pass information between different handlers +without using globals, you'll need to define a data structure to hold +the shared variables. You can then tell Expat (with the <code><a href= +"#XML_SetUserData" >XML_SetUserData</a></code> function) to pass a +pointer to this structure to the handlers. This is the first +argument received by most handlers. In the <a href="#reference" +>reference section</a>, an argument to a callback function is named +<code>userData</code> and have type <code>void *</code> if the user +data is passed; it will have the type <code>XML_Parser</code> if the +parser itself is passed. When the parser is passed, the user data may +be retrieved using <code><a href="#XML_GetUserData" +>XML_GetUserData</a></code>.</p> + +<p>One common case where multiple calls to a single handler may need +to communicate using an application data structure is the case when +content passed to the character data handler (set by <code><a href= +"#XML_SetCharacterDataHandler" +>XML_SetCharacterDataHandler</a></code>) needs to be accumulated. A +common first-time mistake with any of the event-oriented interfaces to +an XML parser is to expect all the text contained in an element to be +reported by a single call to the character data handler. Expat, like +many other XML parsers, reports such data as a sequence of calls; +there's no way to know when the end of the sequence is reached until a +different callback is made. A buffer referenced by the user data +structure proves both an effective and convenient place to accumulate +character data.</p> + +<!-- XXX example needed here --> + + +<h3>XML Version</h3> + +<p>Expat is an XML 1.0 parser, and as such never complains based on +the value of the <code>version</code> pseudo-attribute in the XML +declaration, if present.</p> + +<p>If an application needs to check the version number (to support +alternate processing), it should use the <code><a href= +"#XML_SetXmlDeclHandler" >XML_SetXmlDeclHandler</a></code> function to +set a handler that uses the information in the XML declaration to +determine what to do. This example shows how to check that only a +version number of <code>"1.0"</code> is accepted:</p> + +<pre class="eg"> +static int wrong_version; +static XML_Parser parser; + +static void XMLCALL +xmldecl_handler(void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone) +{ + static const XML_Char Version_1_0[] = {'1', '.', '0', 0}; + + int i; + + for (i = 0; i < (sizeof(Version_1_0) / sizeof(Version_1_0[0])); ++i) { + if (version[i] != Version_1_0[i]) { + wrong_version = 1; + /* also clear all other handlers: */ + XML_SetCharacterDataHandler(parser, NULL); + ... + return; + } + } + ... +} +</pre> + +<h3>Namespace Processing</h3> + +<p>When the parser is created using the <code><a href= +"#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>, function, Expat +performs namespace processing. Under namespace processing, Expat +consumes <code>xmlns</code> and <code>xmlns:...</code> attributes, +which declare namespaces for the scope of the element in which they +occur. This means that your start handler will not see these +attributes. Your application can still be informed of these +declarations by setting namespace declaration handlers with <a href= +"#XML_SetNamespaceDeclHandler" +><code>XML_SetNamespaceDeclHandler</code></a>.</p> + +<p>Element type and attribute names that belong to a given namespace +are passed to the appropriate handler in expanded form. By default +this expanded form is a concatenation of the namespace URI, the +separator character (which is the 2nd argument to <code><a href= +"#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>), and the local +name (i.e. the part after the colon). Names with undeclared prefixes +are not well-formed when namespace processing is enabled, and will +trigger an error. Unprefixed attribute names are never expanded, +and unprefixed element names are only expanded when they are in the +scope of a default namespace.</p> + +<p>However if <code><a href= "#XML_SetReturnNSTriplet" +>XML_SetReturnNSTriplet</a></code> has been called with a non-zero +<code>do_nst</code> parameter, then the expanded form for names with +an explicit prefix is a concatenation of: URI, separator, local name, +separator, prefix.</p> + +<p>You can set handlers for the start of a namespace declaration and +for the end of a scope of a declaration with the <code><a href= +"#XML_SetNamespaceDeclHandler" >XML_SetNamespaceDeclHandler</a></code> +function. The StartNamespaceDeclHandler is called prior to the start +tag handler and the EndNamespaceDeclHandler is called after the +corresponding end tag that ends the namespace's scope. The namespace +start handler gets passed the prefix and URI for the namespace. For a +default namespace declaration (xmlns='...'), the prefix will be null. +The URI will be null for the case where the default namespace is being +unset. The namespace end handler just gets the prefix for the closing +scope.</p> + +<p>These handlers are called for each declaration. So if, for +instance, a start tag had three namespace declarations, then the +StartNamespaceDeclHandler would be called three times before the start +tag handler is called, once for each declaration.</p> + +<h3>Character Encodings</h3> + +<p>While XML is based on Unicode, and every XML processor is required +to recognized UTF-8 and UTF-16 (1 and 2 byte encodings of Unicode), +other encodings may be declared in XML documents or entities. For the +main document, an XML declaration may contain an encoding +declaration:</p> +<pre> +<?xml version="1.0" encoding="ISO-8859-2"?> +</pre> + +<p>External parsed entities may begin with a text declaration, which +looks like an XML declaration with just an encoding declaration:</p> +<pre> +<?xml encoding="Big5"?> +</pre> + +<p>With Expat, you may also specify an encoding at the time of +creating a parser. This is useful when the encoding information may +come from a source outside the document itself (like a higher level +protocol.)</p> + +<p><a name="builtin_encodings"></a>There are four built-in encodings +in Expat:</p> +<ul> +<li>UTF-8</li> +<li>UTF-16</li> +<li>ISO-8859-1</li> +<li>US-ASCII</li> +</ul> + +<p>Anything else discovered in an encoding declaration or in the +protocol encoding specified in the parser constructor, triggers a call +to the <code>UnknownEncodingHandler</code>. This handler gets passed +the encoding name and a pointer to an <code>XML_Encoding</code> data +structure. Your handler must fill in this structure and return +<code>XML_STATUS_OK</code> if it knows how to deal with the +encoding. Otherwise the handler should return +<code>XML_STATUS_ERROR</code>. The handler also gets passed a pointer +to an optional application data structure that you may indicate when +you set the handler.</p> + +<p>Expat places restrictions on character encodings that it can +support by filling in the <code>XML_Encoding</code> structure. +include file:</p> +<ol> +<li>Every ASCII character that can appear in a well-formed XML document +must be represented by a single byte, and that byte must correspond to +it's ASCII encoding (except for the characters $@\^'{}~)</li> +<li>Characters must be encoded in 4 bytes or less.</li> +<li>All characters encoded must have Unicode scalar values less than or +equal to 65535 (0xFFFF)<em>This does not apply to the built-in support +for UTF-16 and UTF-8</em></li> +<li>No character may be encoded by more that one distinct sequence of +bytes</li> +</ol> + +<p><code>XML_Encoding</code> contains an array of integers that +correspond to the 1st byte of an encoding sequence. If the value in +the array for a byte is zero or positive, then the byte is a single +byte encoding that encodes the Unicode scalar value contained in the +array. A -1 in this array indicates a malformed byte. If the value is +-2, -3, or -4, then the byte is the beginning of a 2, 3, or 4 byte +sequence respectively. Multi-byte sequences are sent to the convert +function pointed at in the <code>XML_Encoding</code> structure. This +function should return the Unicode scalar value for the sequence or -1 +if the sequence is malformed.</p> + +<p>One pitfall that novice Expat users are likely to fall into is that +although Expat may accept input in various encodings, the strings that +it passes to the handlers are always encoded in UTF-8 or UTF-16 +(depending on how Expat was compiled). Your application is responsible +for any translation of these strings into other encodings.</p> + +<h3>Handling External Entity References</h3> + +<p>Expat does not read or parse external entities directly. Note that +any external DTD is a special case of an external entity. If you've +set no <code>ExternalEntityRefHandler</code>, then external entity +references are silently ignored. Otherwise, it calls your handler with +the information needed to read and parse the external entity.</p> + +<p>Your handler isn't actually responsible for parsing the entity, but +it is responsible for creating a subsidiary parser with <code><a href= +"#XML_ExternalEntityParserCreate" +>XML_ExternalEntityParserCreate</a></code> that will do the job. This +returns an instance of <code>XML_Parser</code> that has handlers and +other data structures initialized from the parent parser. You may then +use <code><a href= "#XML_Parse" >XML_Parse</a></code> or <code><a +href= "#XML_ParseBuffer">XML_ParseBuffer</a></code> calls against this +parser. Since external entities my refer to other external entities, +your handler should be prepared to be called recursively.</p> + +<h3>Parsing DTDs</h3> + +<p>In order to parse parameter entities, before starting the parse, +you must call <code><a href= "#XML_SetParamEntityParsing" +>XML_SetParamEntityParsing</a></code> with one of the following +arguments:</p> +<dl> +<dt><code>XML_PARAM_ENTITY_PARSING_NEVER</code></dt> +<dd>Don't parse parameter entities or the external subset</dd> +<dt><code>XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE</code></dt> +<dd>Parse parameter entites and the external subset unless +<code>standalone</code> was set to "yes" in the XML declaration.</dd> +<dt><code>XML_PARAM_ENTITY_PARSING_ALWAYS</code></dt> +<dd>Always parse parameter entities and the external subset</dd> +</dl> + +<p>In order to read an external DTD, you also have to set an external +entity reference handler as described above.</p> + +<h3 id="stop-resume">Temporarily Stopping Parsing</h3> + +<p>Expat 1.95.8 introduces a new feature: its now possible to stop +parsing temporarily from within a handler function, even if more data +has already been passed into the parser. Applications for this +include</p> + +<ul> + <li>Supporting the <a href= "http://www.w3.org/TR/xinclude/" + >XInclude</a> specification.</li> + + <li>Delaying further processing until additional information is + available from some other source.</li> + + <li>Adjusting processor load as task priorities shift within an + application.</li> + + <li>Stopping parsing completely (simply free or reset the parser + instead of resuming in the outer parsing loop). This can be useful + if a application-domain error is found in the XML being parsed or if + the result of the parse is determined not to be useful after + all.</li> +</ul> + +<p>To take advantage of this feature, the main parsing loop of an +application needs to support this specifically. It cannot be +supported with a parsing loop compatible with Expat 1.95.7 or +earlier (though existing loops will continue to work without +supporting the stop/resume feature).</p> + +<p>An application that uses this feature for a single parser will have +the rough structure (in pseudo-code):</p> + +<pre class="pseudocode"> +fd = open_input() +p = create_parser() + +if parse_xml(p, fd) { + /* suspended */ + + int suspended = 1; + + while (suspended) { + do_something_else() + if ready_to_resume() { + suspended = continue_parsing(p, fd); + } + } +} +</pre> + +<p>An application that may resume any of several parsers based on +input (either from the XML being parsed or some other source) will +certainly have more interesting control structures.</p> + +<p>This C function could be used for the <code>parse_xml</code> +function mentioned in the pseudo-code above:</p> + +<pre class="eg"> +#define BUFF_SIZE 10240 + +/* Parse a document from the open file descriptor 'fd' until the parse + is complete (the document has been completely parsed, or there's + been an error), or the parse is stopped. Return non-zero when + the parse is merely suspended. +*/ +int +parse_xml(XML_Parser p, int fd) +{ + for (;;) { + int last_chunk; + int bytes_read; + enum XML_Status status; + + void *buff = XML_GetBuffer(p, BUFF_SIZE); + if (buff == NULL) { + /* handle error... */ + return 0; + } + bytes_read = read(fd, buff, BUFF_SIZE); + if (bytes_read < 0) { + /* handle error... */ + return 0; + } + status = XML_ParseBuffer(p, bytes_read, bytes_read == 0); + switch (status) { + case XML_STATUS_ERROR: + /* handle error... */ + return 0; + case XML_STATUS_SUSPENDED: + return 1; + } + if (bytes_read == 0) + return 0; + } +} +</pre> + +<p>The corresponding <code>continue_parsing</code> function is +somewhat simpler, since it only need deal with the return code from +<code><a href= "#XML_ResumeParser">XML_ResumeParser</a></code>; it can +delegate the input handling to the <code>parse_xml</code> +function:</p> + +<pre class="eg"> +/* Continue parsing a document which had been suspended. The 'p' and + 'fd' arguments are the same as passed to parse_xml(). Return + non-zero when the parse is suspended. +*/ +int +continue_parsing(XML_Parser p, int fd) +{ + enum XML_Status status = XML_ResumeParser(p); + switch (status) { + case XML_STATUS_ERROR: + /* handle error... */ + return 0; + case XML_ERROR_NOT_SUSPENDED: + /* handle error... */ + return 0;. + case XML_STATUS_SUSPENDED: + return 1; + } + return parse_xml(p, fd); +} +</pre> + +<p>Now that we've seen what a mess the top-level parsing loop can +become, what have we gained? Very simply, we can now use the <code><a +href= "#XML_StopParser" >XML_StopParser</a></code> function to stop +parsing, without having to go to great lengths to avoid additional +processing that we're expecting to ignore. As a bonus, we get to stop +parsing <em>temporarily</em>, and come back to it when we're +ready.</p> + +<p>To stop parsing from a handler function, use the <code><a href= +"#XML_StopParser" >XML_StopParser</a></code> function. This function +takes two arguments; the parser being stopped and a flag indicating +whether the parse can be resumed in the future.</p> + +<!-- XXX really need more here --> + + +<hr /> +<!-- ================================================================ --> + +<h2><a name="reference">Expat Reference</a></h2> + +<h3><a name="creation">Parser Creation</a></h3> + +<pre class="fcndec" id="XML_ParserCreate"> +XML_Parser XMLCALL +XML_ParserCreate(const XML_Char *encoding); +</pre> +<div class="fcndef"> +Construct a new parser. If encoding is non-null, it specifies a +character encoding to use for the document. This overrides the document +encoding declaration. There are four built-in encodings: +<ul> +<li>US-ASCII</li> +<li>UTF-8</li> +<li>UTF-16</li> +<li>ISO-8859-1</li> +</ul> +Any other value will invoke a call to the UnknownEncodingHandler. +</div> + +<pre class="fcndec" id="XML_ParserCreateNS"> +XML_Parser XMLCALL +XML_ParserCreateNS(const XML_Char *encoding, + XML_Char sep); +</pre> +<div class="fcndef"> +Constructs a new parser that has namespace processing in effect. Namespace +expanded element names and attribute names are returned as a concatenation +of the namespace URI, <em>sep</em>, and the local part of the name. This +means that you should pick a character for <em>sep</em> that can't be part +of an URI. Since Expat does not check namespace URIs for conformance, the +only safe choice for a namespace separator is a character that is illegal +in XML. For instance, <code>'\xFF'</code> is not legal in UTF-8, and +<code>'\xFFFF'</code> is not legal in UTF-16. There is a special case when +<em>sep</em> is the null character <code>'\0'</code>: the namespace URI and +the local part will be concatenated without any separator - this is intended +to support RDF processors. It is a programming error to use the null separator +with <a href= "#XML_SetReturnNSTriplet">namespace triplets</a>.</div> + +<pre class="fcndec" id="XML_ParserCreate_MM"> +XML_Parser XMLCALL +XML_ParserCreate_MM(const XML_Char *encoding, + const XML_Memory_Handling_Suite *ms, + const XML_Char *sep); +</pre> +<pre class="signature"> +typedef struct { + void *(XMLCALL *malloc_fcn)(size_t size); + void *(XMLCALL *realloc_fcn)(void *ptr, size_t size); + void (XMLCALL *free_fcn)(void *ptr); +} XML_Memory_Handling_Suite; +</pre> +<div class="fcndef"> +<p>Construct a new parser using the suite of memory handling functions +specified in <code>ms</code>. If <code>ms</code> is NULL, then use the +standard set of memory management functions. If <code>sep</code> is +non NULL, then namespace processing is enabled in the created parser +and the character pointed at by sep is used as the separator between +the namespace URI and the local part of the name.</p> +</div> + +<pre class="fcndec" id="XML_ExternalEntityParserCreate"> +XML_Parser XMLCALL +XML_ExternalEntityParserCreate(XML_Parser p, + const XML_Char *context, + const XML_Char *encoding); +</pre> +<div class="fcndef"> +Construct a new <code>XML_Parser</code> object for parsing an external +general entity. Context is the context argument passed in a call to a +ExternalEntityRefHandler. Other state information such as handlers, +user data, namespace processing is inherited from the parser passed as +the 1st argument. So you shouldn't need to call any of the behavior +changing functions on this parser (unless you want it to act +differently than the parent parser). +</div> + +<pre class="fcndec" id="XML_ParserFree"> +void XMLCALL +XML_ParserFree(XML_Parser p); +</pre> +<div class="fcndef"> +Free memory used by the parser. Your application is responsible for +freeing any memory associated with <a href="#userdata">user data</a>. +</div> + +<pre class="fcndec" id="XML_ParserReset"> +XML_Bool XMLCALL +XML_ParserReset(XML_Parser p, + const XML_Char *encoding); +</pre> +<div class="fcndef"> +Clean up the memory structures maintained by the parser so that it may +be used again. After this has been called, <code>parser</code> is +ready to start parsing a new document. All handlers are cleared from +the parser, except for the unknownEncodingHandler. The parser's external +state is re-initialized except for the values of ns and ns_triplets. +This function may not be used on a parser created using <code><a href= +"#XML_ExternalEntityParserCreate" >XML_ExternalEntityParserCreate</a +></code>; it will return <code>XML_FALSE</code> in that case. Returns +<code>XML_TRUE</code> on success. Your application is responsible for +dealing with any memory associated with <a href="#userdata">user data</a>. +</div> + +<h3><a name="parsing">Parsing</a></h3> + +<p>To state the obvious: the three parsing functions <code><a href= +"#XML_Parse" >XML_Parse</a></code>, <code><a href= "#XML_ParseBuffer"> +XML_ParseBuffer</a></code> and <code><a href= "#XML_GetBuffer"> +XML_GetBuffer</a></code> must not be called from within a handler +unless they operate on a separate parser instance, that is, one that +did not call the handler. For example, it is OK to call the parsing +functions from within an <code>XML_ExternalEntityRefHandler</code>, +if they apply to the parser created by +<code><a href= "#XML_ExternalEntityParserCreate" +>XML_ExternalEntityParserCreate</a></code>.</p> + +<p>Note: the <code>len</code> argument passed to these functions +should be considerably less than the maximum value for an integer, +as it could create an integer overflow situation if the added +lengths of a buffer and the unprocessed portion of the previous buffer +exceed the maximum integer value. Input data at the end of a buffer +will remain unprocessed if it is part of an XML token for which the +end is not part of that buffer.</p> + +<pre class="fcndec" id="XML_Parse"> +enum XML_Status XMLCALL +XML_Parse(XML_Parser p, + const char *s, + int len, + int isFinal); +</pre> +<pre class="signature"> +enum XML_Status { + XML_STATUS_ERROR = 0, + XML_STATUS_OK = 1 +}; +</pre> +<div class="fcndef"> +Parse some more of the document. The string <code>s</code> is a buffer +containing part (or perhaps all) of the document. The number of bytes of s +that are part of the document is indicated by <code>len</code>. This means +that <code>s</code> doesn't have to be null terminated. It also means that +if <code>len</code> is larger than the number of bytes in the block of +memory that <code>s</code> points at, then a memory fault is likely. The +<code>isFinal</code> parameter informs the parser that this is the last +piece of the document. Frequently, the last piece is empty (i.e. +<code>len</code> is zero.) +If a parse error occurred, it returns <code>XML_STATUS_ERROR</code>. +Otherwise it returns <code>XML_STATUS_OK</code> value. +</div> + +<pre class="fcndec" id="XML_ParseBuffer"> +enum XML_Status XMLCALL +XML_ParseBuffer(XML_Parser p, + int len, + int isFinal); +</pre> +<div class="fcndef"> +This is just like <code><a href= "#XML_Parse" >XML_Parse</a></code>, +except in this case Expat provides the buffer. By obtaining the +buffer from Expat with the <code><a href= "#XML_GetBuffer" +>XML_GetBuffer</a></code> function, the application can avoid double +copying of the input. +</div> + +<pre class="fcndec" id="XML_GetBuffer"> +void * XMLCALL +XML_GetBuffer(XML_Parser p, + int len); +</pre> +<div class="fcndef"> +Obtain a buffer of size <code>len</code> to read a piece of the document +into. A NULL value is returned if Expat can't allocate enough memory for +this buffer. This has to be called prior to every call to +<code><a href= "#XML_ParseBuffer" >XML_ParseBuffer</a></code>. A +typical use would look like this: + +<pre class="eg"> +for (;;) { + int bytes_read; + void *buff = XML_GetBuffer(p, BUFF_SIZE); + if (buff == NULL) { + /* handle error */ + } + + bytes_read = read(docfd, buff, BUFF_SIZE); + if (bytes_read < 0) { + /* handle error */ + } + + if (! XML_ParseBuffer(p, bytes_read, bytes_read == 0)) { + /* handle parse error */ + } + + if (bytes_read == 0) + break; +} +</pre> +</div> + +<pre class="fcndec" id="XML_StopParser"> +enum XML_Status XMLCALL +XML_StopParser(XML_Parser p, + XML_Bool resumable); +</pre> +<div class="fcndef"> + +<p>Stops parsing, causing <code><a href= "#XML_Parse" +>XML_Parse</a></code> or <code><a href= "#XML_ParseBuffer" +>XML_ParseBuffer</a></code> to return. Must be called from within a +call-back handler, except when aborting (when <code>resumable</code> +is <code>XML_FALSE</code>) an already suspended parser. Some +call-backs may still follow because they would otherwise get +lost, including +<ul> + <li> the end element handler for empty elements when stopped in the + start element handler,</li> + <li> the end namespace declaration handler when stopped in the end + element handler,</li> + <li> the character data handler when stopped in the character data handler + while making multiple call-backs on a contiguous chunk of characters,</li> +</ul> +and possibly others.</p> + +<p>This can be called from most handlers, including DTD related +call-backs, except when parsing an external parameter entity and +<code>resumable</code> is <code>XML_TRUE</code>. Returns +<code>XML_STATUS_OK</code> when successful, +<code>XML_STATUS_ERROR</code> otherwise. The possible error codes +are:</p> +<dl> + <dt><code>XML_ERROR_SUSPENDED</code></dt> + <dd>when suspending an already suspended parser.</dd> + <dt><code>XML_ERROR_FINISHED</code></dt> + <dd>when the parser has already finished.</dd> + <dt><code>XML_ERROR_SUSPEND_PE</code></dt> + <dd>when suspending while parsing an external PE.</dd> +</dl> + +<p>Since the stop/resume feature requires application support in the +outer parsing loop, it is an error to call this function for a parser +not being handled appropriately; see <a href= "#stop-resume" +>Temporarily Stopping Parsing</a> for more information.</p> + +<p>When <code>resumable</code> is <code>XML_TRUE</code> then parsing +is <em>suspended</em>, that is, <code><a href= "#XML_Parse" +>XML_Parse</a></code> and <code><a href= "#XML_ParseBuffer" +>XML_ParseBuffer</a></code> return <code>XML_STATUS_SUSPENDED</code>. +Otherwise, parsing is <em>aborted</em>, that is, <code><a href= +"#XML_Parse" >XML_Parse</a></code> and <code><a href= +"#XML_ParseBuffer" >XML_ParseBuffer</a></code> return +<code>XML_STATUS_ERROR</code> with error code +<code>XML_ERROR_ABORTED</code>.</p> + +<p><strong>Note:</strong> +This will be applied to the current parser instance only, that is, if +there is a parent parser then it will continue parsing when the +external entity reference handler returns. It is up to the +implementation of that handler to call <code><a href= +"#XML_StopParser" >XML_StopParser</a></code> on the parent parser +(recursively), if one wants to stop parsing altogether.</p> + +<p>When suspended, parsing can be resumed by calling <code><a href= +"#XML_ResumeParser" >XML_ResumeParser</a></code>.</p> + +<p>New in Expat 1.95.8.</p> +</div> + +<pre class="fcndec" id="XML_ResumeParser"> +enum XML_Status XMLCALL +XML_ResumeParser(XML_Parser p); +</pre> +<div class="fcndef"> +<p>Resumes parsing after it has been suspended with <code><a href= +"#XML_StopParser" >XML_StopParser</a></code>. Must not be called from +within a handler call-back. Returns same status codes as <code><a +href= "#XML_Parse">XML_Parse</a></code> or <code><a href= +"#XML_ParseBuffer" >XML_ParseBuffer</a></code>. An additional error +code, <code>XML_ERROR_NOT_SUSPENDED</code>, will be returned if the +parser was not currently suspended.</p> + +<p><strong>Note:</strong> +This must be called on the most deeply nested child parser instance +first, and on its parent parser only after the child parser has +finished, to be applied recursively until the document entity's parser +is restarted. That is, the parent parser will not resume by itself +and it is up to the application to call <code><a href= +"#XML_ResumeParser" >XML_ResumeParser</a></code> on it at the +appropriate moment.</p> + +<p>New in Expat 1.95.8.</p> +</div> + +<pre class="fcndec" id="XML_GetParsingStatus"> +void XMLCALL +XML_GetParsingStatus(XML_Parser p, + XML_ParsingStatus *status); +</pre> +<pre class="signature"> +enum XML_Parsing { + XML_INITIALIZED, + XML_PARSING, + XML_FINISHED, + XML_SUSPENDED +}; + +typedef struct { + enum XML_Parsing parsing; + XML_Bool finalBuffer; +} XML_ParsingStatus; +</pre> +<div class="fcndef"> +<p>Returns status of parser with respect to being initialized, +parsing, finished, or suspended, and whether the final buffer is being +processed. The <code>status</code> parameter <em>must not</em> be +NULL.</p> + +<p>New in Expat 1.95.8.</p> +</div> + + +<h3><a name="setting">Handler Setting</a></h3> + +<p>Although handlers are typically set prior to parsing and left alone, an +application may choose to set or change the handler for a parsing event +while the parse is in progress. For instance, your application may choose +to ignore all text not descended from a <code>para</code> element. One +way it could do this is to set the character handler when a para start tag +is seen, and unset it for the corresponding end tag.</p> + +<p>A handler may be <em>unset</em> by providing a NULL pointer to the +appropriate handler setter. None of the handler setting functions have +a return value.</p> + +<p>Your handlers will be receiving strings in arrays of type +<code>XML_Char</code>. This type is conditionally defined in expat.h as +either <code>char</code>, <code>wchar_t</code> or <code>unsigned short</code>. +The former implies UTF-8 encoding, the latter two imply UTF-16 encoding. +Note that you'll receive them in this form independent of the original +encoding of the document.</p> + +<div class="handler"> +<pre class="setter" id="XML_SetStartElementHandler"> +void XMLCALL +XML_SetStartElementHandler(XML_Parser p, + XML_StartElementHandler start); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_StartElementHandler)(void *userData, + const XML_Char *name, + const XML_Char **atts); +</pre> +<p>Set handler for start (and empty) tags. Attributes are passed to the start +handler as a pointer to a vector of char pointers. Each attribute seen in +a start (or empty) tag occupies 2 consecutive places in this vector: the +attribute name followed by the attribute value. These pairs are terminated +by a null pointer.</p> +<p>Note that an empty tag generates a call to both start and end handlers +(in that order).</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetEndElementHandler"> +void XMLCALL +XML_SetEndElementHandler(XML_Parser p, + XML_EndElementHandler); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_EndElementHandler)(void *userData, + const XML_Char *name); +</pre> +<p>Set handler for end (and empty) tags. As noted above, an empty tag +generates a call to both start and end handlers.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetElementHandler"> +void XMLCALL +XML_SetElementHandler(XML_Parser p, + XML_StartElementHandler start, + XML_EndElementHandler end); +</pre> +<p>Set handlers for start and end tags with one call.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetCharacterDataHandler"> +void XMLCALL +XML_SetCharacterDataHandler(XML_Parser p, + XML_CharacterDataHandler charhndl) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_CharacterDataHandler)(void *userData, + const XML_Char *s, + int len); +</pre> +<p>Set a text handler. The string your handler receives +is <em>NOT nul-terminated</em>. You have to use the length argument +to deal with the end of the string. A single block of contiguous text +free of markup may still result in a sequence of calls to this handler. +In other words, if you're searching for a pattern in the text, it may +be split across calls to this handler. Note: Setting this handler to NULL +may <em>NOT immediately</em> terminate call-backs if the parser is currently +processing such a single block of contiguous markup-free text, as the parser +will continue calling back until the end of the block is reached.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetProcessingInstructionHandler"> +void XMLCALL +XML_SetProcessingInstructionHandler(XML_Parser p, + XML_ProcessingInstructionHandler proc) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_ProcessingInstructionHandler)(void *userData, + const XML_Char *target, + const XML_Char *data); + +</pre> +<p>Set a handler for processing instructions. The target is the first word +in the processing instruction. The data is the rest of the characters in +it after skipping all whitespace after the initial word.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetCommentHandler"> +void XMLCALL +XML_SetCommentHandler(XML_Parser p, + XML_CommentHandler cmnt) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_CommentHandler)(void *userData, + const XML_Char *data); +</pre> +<p>Set a handler for comments. The data is all text inside the comment +delimiters.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetStartCdataSectionHandler"> +void XMLCALL +XML_SetStartCdataSectionHandler(XML_Parser p, + XML_StartCdataSectionHandler start); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_StartCdataSectionHandler)(void *userData); +</pre> +<p>Set a handler that gets called at the beginning of a CDATA section.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetEndCdataSectionHandler"> +void XMLCALL +XML_SetEndCdataSectionHandler(XML_Parser p, + XML_EndCdataSectionHandler end); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_EndCdataSectionHandler)(void *userData); +</pre> +<p>Set a handler that gets called at the end of a CDATA section.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetCdataSectionHandler"> +void XMLCALL +XML_SetCdataSectionHandler(XML_Parser p, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end) +</pre> +<p>Sets both CDATA section handlers with one call.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetDefaultHandler"> +void XMLCALL +XML_SetDefaultHandler(XML_Parser p, + XML_DefaultHandler hndl) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_DefaultHandler)(void *userData, + const XML_Char *s, + int len); +</pre> + +<p>Sets a handler for any characters in the document which wouldn't +otherwise be handled. This includes both data for which no handlers +can be set (like some kinds of DTD declarations) and data which could +be reported but which currently has no handler set. The characters +are passed exactly as they were present in the XML document except +that they will be encoded in UTF-8 or UTF-16. Line boundaries are not +normalized. Note that a byte order mark character is not passed to the +default handler. There are no guarantees about how characters are +divided between calls to the default handler: for example, a comment +might be split between multiple calls. Setting the handler with +this call has the side effect of turning off expansion of references +to internally defined general entities. Instead these references are +passed to the default handler.</p> + +<p>See also <code><a +href="#XML_DefaultCurrent">XML_DefaultCurrent</a></code>.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetDefaultHandlerExpand"> +void XMLCALL +XML_SetDefaultHandlerExpand(XML_Parser p, + XML_DefaultHandler hndl) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_DefaultHandler)(void *userData, + const XML_Char *s, + int len); +</pre> +<p>This sets a default handler, but doesn't inhibit the expansion of +internal entity references. The entity reference will not be passed +to the default handler.</p> + +<p>See also <code><a +href="#XML_DefaultCurrent">XML_DefaultCurrent</a></code>.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetExternalEntityRefHandler"> +void XMLCALL +XML_SetExternalEntityRefHandler(XML_Parser p, + XML_ExternalEntityRefHandler hndl) +</pre> +<pre class="signature"> +typedef int +(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser p, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); +</pre> +<p>Set an external entity reference handler. This handler is also +called for processing an external DTD subset if parameter entity parsing +is in effect. (See <a href="#XML_SetParamEntityParsing"> +<code>XML_SetParamEntityParsing</code></a>.)</p> + +<p>The <code>context</code> parameter specifies the parsing context in +the format expected by the <code>context</code> argument to <code><a +href="#XML_ExternalEntityParserCreate" +>XML_ExternalEntityParserCreate</a></code>. <code>code</code> is +valid only until the handler returns, so if the referenced entity is +to be parsed later, it must be copied. <code>context</code> is NULL +only when the entity is a parameter entity, which is how one can +differentiate between general and parameter entities.</p> + +<p>The <code>base</code> parameter is the base to use for relative +system identifiers. It is set by <code><a +href="#XML_SetBase">XML_SetBase</a></code> and may be NULL. The +<code>publicId</code> parameter is the public id given in the entity +declaration and may be NULL. <code>systemId</code> is the system +identifier specified in the entity declaration and is never NULL.</p> + +<p>There are a couple of ways in which this handler differs from +others. First, this handler returns a status indicator (an +integer). <code>XML_STATUS_OK</code> should be returned for successful +handling of the external entity reference. Returning +<code>XML_STATUS_ERROR</code> indicates failure, and causes the +calling parser to return an +<code>XML_ERROR_EXTERNAL_ENTITY_HANDLING</code> error.</p> + +<p>Second, instead of having the user data as its first argument, it +receives the parser that encountered the entity reference. This, along +with the context parameter, may be used as arguments to a call to +<code><a href= "#XML_ExternalEntityParserCreate" +>XML_ExternalEntityParserCreate</a></code>. Using the returned +parser, the body of the external entity can be recursively parsed.</p> + +<p>Since this handler may be called recursively, it should not be saving +information into global or static variables.</p> +</div> + +<pre class="fcndec" id="XML_SetExternalEntityRefHandlerArg"> +void XMLCALL +XML_SetExternalEntityRefHandlerArg(XML_Parser p, + void *arg) +</pre> +<div class="fcndef"> +<p>Set the argument passed to the ExternalEntityRefHandler. If +<code>arg</code> is not NULL, it is the new value passed to the +handler set using <code><a href="#XML_SetExternalEntityRefHandler" +>XML_SetExternalEntityRefHandler</a></code>; if <code>arg</code> is +NULL, the argument passed to the handler function will be the parser +object itself.</p> + +<p><strong>Note:</strong> +The type of <code>arg</code> and the type of the first argument to the +ExternalEntityRefHandler do not match. This function takes a +<code>void *</code> to be passed to the handler, while the handler +accepts an <code>XML_Parser</code>. This is a historical accident, +but will not be corrected before Expat 2.0 (at the earliest) to avoid +causing compiler warnings for code that's known to work with this +API. It is the responsibility of the application code to know the +actual type of the argument passed to the handler and to manage it +properly.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetSkippedEntityHandler"> +void XMLCALL +XML_SetSkippedEntityHandler(XML_Parser p, + XML_SkippedEntityHandler handler) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_SkippedEntityHandler)(void *userData, + const XML_Char *entityName, + int is_parameter_entity); +</pre> +<p>Set a skipped entity handler. This is called in two situations:</p> +<ol> + <li>An entity reference is encountered for which no declaration + has been read <em>and</em> this is not an error.</li> + <li>An internal entity reference is read, but not expanded, because + <a href="#XML_SetDefaultHandler"><code>XML_SetDefaultHandler</code></a> + has been called.</li> +</ol> +<p>The <code>is_parameter_entity</code> argument will be non-zero for +a parameter entity and zero for a general entity.</p> <p>Note: skipped +parameter entities in declarations and skipped general entities in +attribute values cannot be reported, because the event would be out of +sync with the reporting of the declarations or attribute values</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetUnknownEncodingHandler"> +void XMLCALL +XML_SetUnknownEncodingHandler(XML_Parser p, + XML_UnknownEncodingHandler enchandler, + void *encodingHandlerData) +</pre> +<pre class="signature"> +typedef int +(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, + const XML_Char *name, + XML_Encoding *info); + +typedef struct { + int map[256]; + void *data; + int (XMLCALL *convert)(void *data, const char *s); + void (XMLCALL *release)(void *data); +} XML_Encoding; +</pre> +<p>Set a handler to deal with encodings other than the <a +href="#builtin_encodings">built in set</a>. This should be done before +<code><a href= "#XML_Parse" >XML_Parse</a></code> or <code><a href= +"#XML_ParseBuffer" >XML_ParseBuffer</a></code> have been called on the +given parser.</p> <p>If the handler knows how to deal with an encoding +with the given name, it should fill in the <code>info</code> data +structure and return <code>XML_STATUS_OK</code>. Otherwise it +should return <code>XML_STATUS_ERROR</code>. The handler will be called +at most once per parsed (external) entity. The optional application +data pointer <code>encodingHandlerData</code> will be passed back to +the handler.</p> + +<p>The map array contains information for every possible possible leading +byte in a byte sequence. If the corresponding value is >= 0, then it's +a single byte sequence and the byte encodes that Unicode value. If the +value is -1, then that byte is invalid as the initial byte in a sequence. +If the value is -n, where n is an integer > 1, then n is the number of +bytes in the sequence and the actual conversion is accomplished by a +call to the function pointed at by convert. This function may return -1 +if the sequence itself is invalid. The convert pointer may be null if +there are only single byte codes. The data parameter passed to the convert +function is the data pointer from <code>XML_Encoding</code>. The +string s is <em>NOT</em> nul-terminated and points at the sequence of +bytes to be converted.</p> + +<p>The function pointed at by <code>release</code> is called by the +parser when it is finished with the encoding. It may be NULL.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetStartNamespaceDeclHandler"> +void XMLCALL +XML_SetStartNamespaceDeclHandler(XML_Parser p, + XML_StartNamespaceDeclHandler start); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData, + const XML_Char *prefix, + const XML_Char *uri); +</pre> +<p>Set a handler to be called when a namespace is declared. Namespace +declarations occur inside start tags. But the namespace declaration start +handler is called before the start tag handler for each namespace declared +in that start tag.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetEndNamespaceDeclHandler"> +void XMLCALL +XML_SetEndNamespaceDeclHandler(XML_Parser p, + XML_EndNamespaceDeclHandler end); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData, + const XML_Char *prefix); +</pre> +<p>Set a handler to be called when leaving the scope of a namespace +declaration. This will be called, for each namespace declaration, +after the handler for the end tag of the element in which the +namespace was declared.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetNamespaceDeclHandler"> +void XMLCALL +XML_SetNamespaceDeclHandler(XML_Parser p, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end) +</pre> +<p>Sets both namespace declaration handlers with a single call.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetXmlDeclHandler"> +void XMLCALL +XML_SetXmlDeclHandler(XML_Parser p, + XML_XmlDeclHandler xmldecl); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_XmlDeclHandler)(void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone); +</pre> +<p>Sets a handler that is called for XML declarations and also for +text declarations discovered in external entities. The way to +distinguish is that the <code>version</code> parameter will be NULL +for text declarations. The <code>encoding</code> parameter may be NULL +for an XML declaration. The <code>standalone</code> argument will +contain -1, 0, or 1 indicating respectively that there was no +standalone parameter in the declaration, that it was given as no, or +that it was given as yes.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetStartDoctypeDeclHandler"> +void XMLCALL +XML_SetStartDoctypeDeclHandler(XML_Parser p, + XML_StartDoctypeDeclHandler start); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset); +</pre> +<p>Set a handler that is called at the start of a DOCTYPE declaration, +before any external or internal subset is parsed. Both <code>sysid</code> +and <code>pubid</code> may be NULL. The <code>has_internal_subset</code> +will be non-zero if the DOCTYPE declaration has an internal subset.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetEndDoctypeDeclHandler"> +void XMLCALL +XML_SetEndDoctypeDeclHandler(XML_Parser p, + XML_EndDoctypeDeclHandler end); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); +</pre> +<p>Set a handler that is called at the end of a DOCTYPE declaration, +after parsing any external subset.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetDoctypeDeclHandler"> +void XMLCALL +XML_SetDoctypeDeclHandler(XML_Parser p, + XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end); +</pre> +<p>Set both doctype handlers with one call.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetElementDeclHandler"> +void XMLCALL +XML_SetElementDeclHandler(XML_Parser p, + XML_ElementDeclHandler eldecl); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_ElementDeclHandler)(void *userData, + const XML_Char *name, + XML_Content *model); +</pre> +<pre class="signature"> +enum XML_Content_Type { + XML_CTYPE_EMPTY = 1, + XML_CTYPE_ANY, + XML_CTYPE_MIXED, + XML_CTYPE_NAME, + XML_CTYPE_CHOICE, + XML_CTYPE_SEQ +}; + +enum XML_Content_Quant { + XML_CQUANT_NONE, + XML_CQUANT_OPT, + XML_CQUANT_REP, + XML_CQUANT_PLUS +}; + +typedef struct XML_cp XML_Content; + +struct XML_cp { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + const XML_Char * name; + unsigned int numchildren; + XML_Content * children; +}; +</pre> +<p>Sets a handler for element declarations in a DTD. The handler gets +called with the name of the element in the declaration and a pointer +to a structure that contains the element model. It is the +application's responsibility to free this data structure using +<code><a href="#XML_FreeContentModel" +>XML_FreeContentModel</a></code>.</p> + +<p>The <code>model</code> argument is the root of a tree of +<code>XML_Content</code> nodes. If <code>type</code> equals +<code>XML_CTYPE_EMPTY</code> or <code>XML_CTYPE_ANY</code>, then +<code>quant</code> will be <code>XML_CQUANT_NONE</code>, and the other +fields will be zero or NULL. If <code>type</code> is +<code>XML_CTYPE_MIXED</code>, then <code>quant</code> will be +<code>XML_CQUANT_NONE</code> or <code>XML_CQUANT_REP</code> and +<code>numchildren</code> will contain the number of elements that are +allowed to be mixed in and <code>children</code> points to an array of +<code>XML_Content</code> structures that will all have type +XML_CTYPE_NAME with no quantification. Only the root node can be type +<code>XML_CTYPE_EMPTY</code>, <code>XML_CTYPE_ANY</code>, or +<code>XML_CTYPE_MIXED</code>.</p> + +<p>For type <code>XML_CTYPE_NAME</code>, the <code>name</code> field +points to the name and the <code>numchildren</code> and +<code>children</code> fields will be zero and NULL. The +<code>quant</code> field will indicate any quantifiers placed on the +name.</p> + +<p>Types <code>XML_CTYPE_CHOICE</code> and <code>XML_CTYPE_SEQ</code> +indicate a choice or sequence respectively. The +<code>numchildren</code> field indicates how many nodes in the choice +or sequence and <code>children</code> points to the nodes.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetAttlistDeclHandler"> +void XMLCALL +XML_SetAttlistDeclHandler(XML_Parser p, + XML_AttlistDeclHandler attdecl); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_AttlistDeclHandler)(void *userData, + const XML_Char *elname, + const XML_Char *attname, + const XML_Char *att_type, + const XML_Char *dflt, + int isrequired); +</pre> +<p>Set a handler for attlist declarations in the DTD. This handler is +called for <em>each</em> attribute. So a single attlist declaration +with multiple attributes declared will generate multiple calls to this +handler. The <code>elname</code> parameter returns the name of the +element for which the attribute is being declared. The attribute name +is in the <code>attname</code> parameter. The attribute type is in the +<code>att_type</code> parameter. It is the string representing the +type in the declaration with whitespace removed.</p> + +<p>The <code>dflt</code> parameter holds the default value. It will be +NULL in the case of "#IMPLIED" or "#REQUIRED" attributes. You can +distinguish these two cases by checking the <code>isrequired</code> +parameter, which will be true in the case of "#REQUIRED" attributes. +Attributes which are "#FIXED" will have also have a true +<code>isrequired</code>, but they will have the non-NULL fixed value +in the <code>dflt</code> parameter.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetEntityDeclHandler"> +void XMLCALL +XML_SetEntityDeclHandler(XML_Parser p, + XML_EntityDeclHandler handler); +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_EntityDeclHandler)(void *userData, + const XML_Char *entityName, + int is_parameter_entity, + const XML_Char *value, + int value_length, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); +</pre> +<p>Sets a handler that will be called for all entity declarations. +The <code>is_parameter_entity</code> argument will be non-zero in the +case of parameter entities and zero otherwise.</p> + +<p>For internal entities (<code><!ENTITY foo "bar"></code>), +<code>value</code> will be non-NULL and <code>systemId</code>, +<code>publicId</code>, and <code>notationName</code> will all be NULL. +The value string is <em>not</em> NULL terminated; the length is +provided in the <code>value_length</code> parameter. Do not use +<code>value_length</code> to test for internal entities, since it is +legal to have zero-length values. Instead check for whether or not +<code>value</code> is NULL.</p> <p>The <code>notationName</code> +argument will have a non-NULL value only for unparsed entity +declarations.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetUnparsedEntityDeclHandler"> +void XMLCALL +XML_SetUnparsedEntityDeclHandler(XML_Parser p, + XML_UnparsedEntityDeclHandler h) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_UnparsedEntityDeclHandler)(void *userData, + const XML_Char *entityName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); +</pre> +<p>Set a handler that receives declarations of unparsed entities. These +are entity declarations that have a notation (NDATA) field:</p> + +<div id="eg"><pre> +<!ENTITY logo SYSTEM "images/logo.gif" NDATA gif> +</pre></div> +<p>This handler is obsolete and is provided for backwards +compatibility. Use instead <a href= "#XML_SetEntityDeclHandler" +>XML_SetEntityDeclHandler</a>.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetNotationDeclHandler"> +void XMLCALL +XML_SetNotationDeclHandler(XML_Parser p, + XML_NotationDeclHandler h) +</pre> +<pre class="signature"> +typedef void +(XMLCALL *XML_NotationDeclHandler)(void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); +</pre> +<p>Set a handler that receives notation declarations.</p> +</div> + +<div class="handler"> +<pre class="setter" id="XML_SetNotStandaloneHandler"> +void XMLCALL +XML_SetNotStandaloneHandler(XML_Parser p, + XML_NotStandaloneHandler h) +</pre> +<pre class="signature"> +typedef int +(XMLCALL *XML_NotStandaloneHandler)(void *userData); +</pre> +<p>Set a handler that is called if the document is not "standalone". +This happens when there is an external subset or a reference to a +parameter entity, but does not have standalone set to "yes" in an XML +declaration. If this handler returns <code>XML_STATUS_ERROR</code>, +then the parser will throw an <code>XML_ERROR_NOT_STANDALONE</code> +error.</p> +</div> + +<h3><a name="position">Parse position and error reporting functions</a></h3> + +<p>These are the functions you'll want to call when the parse +functions return <code>XML_STATUS_ERROR</code> (a parse error has +occurred), although the position reporting functions are useful outside +of errors. The position reported is the byte position (in the original +document or entity encoding) of the first of the sequence of +characters that generated the current event (or the error that caused +the parse functions to return <code>XML_STATUS_ERROR</code>.) The +exceptions are callbacks trigged by declarations in the document +prologue, in which case they exact position reported is somewhere in the +relevant markup, but not necessarily as meaningful as for other +events.</p> + +<p>The position reporting functions are accurate only outside of the +DTD. In other words, they usually return bogus information when +called from within a DTD declaration handler.</p> + +<pre class="fcndec" id="XML_GetErrorCode"> +enum XML_Error XMLCALL +XML_GetErrorCode(XML_Parser p); +</pre> +<div class="fcndef"> +Return what type of error has occurred. +</div> + +<pre class="fcndec" id="XML_ErrorString"> +const XML_LChar * XMLCALL +XML_ErrorString(enum XML_Error code); +</pre> +<div class="fcndef"> +Return a string describing the error corresponding to code. +The code should be one of the enums that can be returned from +<code><a href= "#XML_GetErrorCode" >XML_GetErrorCode</a></code>. +</div> + +<pre class="fcndec" id="XML_GetCurrentByteIndex"> +XML_Index XMLCALL +XML_GetCurrentByteIndex(XML_Parser p); +</pre> +<div class="fcndef"> +Return the byte offset of the position. This always corresponds to +the values returned by <code><a href= "#XML_GetCurrentLineNumber" +>XML_GetCurrentLineNumber</a></code> and <code><a href= +"#XML_GetCurrentColumnNumber" >XML_GetCurrentColumnNumber</a></code>. +</div> + +<pre class="fcndec" id="XML_GetCurrentLineNumber"> +XML_Size XMLCALL +XML_GetCurrentLineNumber(XML_Parser p); +</pre> +<div class="fcndef"> +Return the line number of the position. The first line is reported as +<code>1</code>. +</div> + +<pre class="fcndec" id="XML_GetCurrentColumnNumber"> +XML_Size XMLCALL +XML_GetCurrentColumnNumber(XML_Parser p); +</pre> +<div class="fcndef"> +Return the offset, from the beginning of the current line, of +the position. +</div> + +<pre class="fcndec" id="XML_GetCurrentByteCount"> +int XMLCALL +XML_GetCurrentByteCount(XML_Parser p); +</pre> +<div class="fcndef"> +Return the number of bytes in the current event. Returns +<code>0</code> if the event is inside a reference to an internal +entity and for the end-tag event for empty element tags (the later can +be used to distinguish empty-element tags from empty elements using +separate start and end tags). +</div> + +<pre class="fcndec" id="XML_GetInputContext"> +const char * XMLCALL +XML_GetInputContext(XML_Parser p, + int *offset, + int *size); +</pre> +<div class="fcndef"> + +<p>Returns the parser's input buffer, sets the integer pointed at by +<code>offset</code> to the offset within this buffer of the current +parse position, and set the integer pointed at by <code>size</code> to +the size of the returned buffer.</p> + +<p>This should only be called from within a handler during an active +parse and the returned buffer should only be referred to from within +the handler that made the call. This input buffer contains the +untranslated bytes of the input.</p> + +<p>Only a limited amount of context is kept, so if the event +triggering a call spans over a very large amount of input, the actual +parse position may be before the beginning of the buffer.</p> + +<p>If <code>XML_CONTEXT_BYTES</code> is not defined, this will always +return NULL.</p> +</div> + +<h3><a name="miscellaneous">Miscellaneous functions</a></h3> + +<p>The functions in this section either obtain state information from +the parser or can be used to dynamicly set parser options.</p> + +<pre class="fcndec" id="XML_SetUserData"> +void XMLCALL +XML_SetUserData(XML_Parser p, + void *userData); +</pre> +<div class="fcndef"> +This sets the user data pointer that gets passed to handlers. It +overwrites any previous value for this pointer. Note that the +application is responsible for freeing the memory associated with +<code>userData</code> when it is finished with the parser. So if you +call this when there's already a pointer there, and you haven't freed +the memory associated with it, then you've probably just leaked +memory. +</div> + +<pre class="fcndec" id="XML_GetUserData"> +void * XMLCALL +XML_GetUserData(XML_Parser p); +</pre> +<div class="fcndef"> +This returns the user data pointer that gets passed to handlers. +It is actually implemented as a macro. +</div> + +<pre class="fcndec" id="XML_UseParserAsHandlerArg"> +void XMLCALL +XML_UseParserAsHandlerArg(XML_Parser p); +</pre> +<div class="fcndef"> +After this is called, handlers receive the parser in their +<code>userData</code> arguments. The user data can still be obtained +using the <code><a href= "#XML_GetUserData" +>XML_GetUserData</a></code> function. +</div> + +<pre class="fcndec" id="XML_SetBase"> +enum XML_Status XMLCALL +XML_SetBase(XML_Parser p, + const XML_Char *base); +</pre> +<div class="fcndef"> +Set the base to be used for resolving relative URIs in system +identifiers. The return value is <code>XML_STATUS_ERROR</code> if +there's no memory to store base, otherwise it's +<code>XML_STATUS_OK</code>. +</div> + +<pre class="fcndec" id="XML_GetBase"> +const XML_Char * XMLCALL +XML_GetBase(XML_Parser p); +</pre> +<div class="fcndef"> +Return the base for resolving relative URIs. +</div> + +<pre class="fcndec" id="XML_GetSpecifiedAttributeCount"> +int XMLCALL +XML_GetSpecifiedAttributeCount(XML_Parser p); +</pre> +<div class="fcndef"> +When attributes are reported to the start handler in the atts vector, +attributes that were explicitly set in the element occur before any +attributes that receive their value from default information in an +ATTLIST declaration. This function returns the number of attributes +that were explicitly set times two, thus giving the offset in the +<code>atts</code> array passed to the start tag handler of the first +attribute set due to defaults. It supplies information for the last +call to a start handler. If called inside a start handler, then that +means the current call. +</div> + +<pre class="fcndec" id="XML_GetIdAttributeIndex"> +int XMLCALL +XML_GetIdAttributeIndex(XML_Parser p); +</pre> +<div class="fcndef"> +Returns the index of the ID attribute passed in the atts array in the +last call to <code><a href= "#XML_StartElementHandler" +>XML_StartElementHandler</a></code>, or -1 if there is no ID +attribute. If called inside a start handler, then that means the +current call. +</div> + +<pre class="fcndec" id="XML_GetAttributeInfo"> +const XML_AttrInfo * XMLCALL +XML_GetAttributeInfo(XML_Parser parser); +</pre> +<pre class="signature"> +typedef struct { + XML_Index nameStart; /* Offset to beginning of the attribute name. */ + XML_Index nameEnd; /* Offset after the attribute name's last byte. */ + XML_Index valueStart; /* Offset to beginning of the attribute value. */ + XML_Index valueEnd; /* Offset after the attribute value's last byte. */ +} XML_AttrInfo; +</pre> +<div class="fcndef"> +Returns an array of <code>XML_AttrInfo</code> structures for the +attribute/value pairs passed in the last call to the +<code>XML_StartElementHandler</code> that were specified +in the start-tag rather than defaulted. Each attribute/value pair counts +as 1; thus the number of entries in the array is +<code>XML_GetSpecifiedAttributeCount(parser) / 2</code>. +</div> + +<pre class="fcndec" id="XML_SetEncoding"> +enum XML_Status XMLCALL +XML_SetEncoding(XML_Parser p, + const XML_Char *encoding); +</pre> +<div class="fcndef"> +Set the encoding to be used by the parser. It is equivalent to +passing a non-null encoding argument to the parser creation functions. +It must not be called after <code><a href= "#XML_Parse" +>XML_Parse</a></code> or <code><a href= "#XML_ParseBuffer" +>XML_ParseBuffer</a></code> have been called on the given parser. +Returns <code>XML_STATUS_OK</code> on success or +<code>XML_STATUS_ERROR</code> on error. +</div> + +<pre class="fcndec" id="XML_SetParamEntityParsing"> +int XMLCALL +XML_SetParamEntityParsing(XML_Parser p, + enum XML_ParamEntityParsing code); +</pre> +<div class="fcndef"> +This enables parsing of parameter entities, including the external +parameter entity that is the external DTD subset, according to +<code>code</code>. +The choices for <code>code</code> are: +<ul> +<li><code>XML_PARAM_ENTITY_PARSING_NEVER</code></li> +<li><code>XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE</code></li> +<li><code>XML_PARAM_ENTITY_PARSING_ALWAYS</code></li> +</ul> +<b>Note:</b> If <code>XML_SetParamEntityParsing</code> is called after +<code>XML_Parse</code> or <code>XML_ParseBuffer</code>, then it has +no effect and will always return 0. +</div> + +<pre class="fcndec" id="XML_SetHashSalt"> +int XMLCALL +XML_SetHashSalt(XML_Parser p, + unsigned long hash_salt); +</pre> +<div class="fcndef"> +Sets the hash salt to use for internal hash calculations. +Helps in preventing DoS attacks based on predicting hash +function behavior. In order to have an effect this must be called +before parsing has started. Returns 1 if successful, 0 when called +after <code>XML_Parse</code> or <code>XML_ParseBuffer</code>. +<p><b>Note:</b> This call is optional, as the parser will auto-generate a new +random salt value if no value has been set at the start of parsing.</p> +</div> + +<pre class="fcndec" id="XML_UseForeignDTD"> +enum XML_Error XMLCALL +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); +</pre> +<div class="fcndef"> +<p>This function allows an application to provide an external subset +for the document type declaration for documents which do not specify +an external subset of their own. For documents which specify an +external subset in their DOCTYPE declaration, the application-provided +subset will be ignored. If the document does not contain a DOCTYPE +declaration at all and <code>useDTD</code> is true, the +application-provided subset will be parsed, but the +<code>startDoctypeDeclHandler</code> and +<code>endDoctypeDeclHandler</code> functions, if set, will not be +called. The setting of parameter entity parsing, controlled using +<code><a href= "#XML_SetParamEntityParsing" +>XML_SetParamEntityParsing</a></code>, will be honored.</p> + +<p>The application-provided external subset is read by calling the +external entity reference handler set via <code><a href= +"#XML_SetExternalEntityRefHandler" +>XML_SetExternalEntityRefHandler</a></code> with both +<code>publicId</code> and <code>systemId</code> set to NULL.</p> + +<p>If this function is called after parsing has begun, it returns +<code>XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING</code> and ignores +<code>useDTD</code>. If called when Expat has been compiled without +DTD support, it returns +<code>XML_ERROR_FEATURE_REQUIRES_XML_DTD</code>. Otherwise, it +returns <code>XML_ERROR_NONE</code>.</p> + +<p><b>Note:</b> For the purpose of checking WFC: Entity Declared, passing +<code>useDTD == XML_TRUE</code> will make the parser behave as if +the document had a DTD with an external subset. This holds true even if +the external entity reference handler returns without action.</p> +</div> + +<pre class="fcndec" id="XML_SetReturnNSTriplet"> +void XMLCALL +XML_SetReturnNSTriplet(XML_Parser parser, + int do_nst); +</pre> +<div class="fcndef"> +<p> +This function only has an effect when using a parser created with +<code><a href= "#XML_ParserCreateNS" >XML_ParserCreateNS</a></code>, +i.e. when namespace processing is in effect. The <code>do_nst</code> +sets whether or not prefixes are returned with names qualified with a +namespace prefix. If this function is called with <code>do_nst</code> +non-zero, then afterwards namespace qualified names (that is qualified +with a prefix as opposed to belonging to a default namespace) are +returned as a triplet with the three parts separated by the namespace +separator specified when the parser was created. The order of +returned parts is URI, local name, and prefix.</p> <p>If +<code>do_nst</code> is zero, then namespaces are reported in the +default manner, URI then local_name separated by the namespace +separator.</p> +</div> + +<pre class="fcndec" id="XML_DefaultCurrent"> +void XMLCALL +XML_DefaultCurrent(XML_Parser parser); +</pre> +<div class="fcndef"> +This can be called within a handler for a start element, end element, +processing instruction or character data. It causes the corresponding +markup to be passed to the default handler set by <code><a +href="#XML_SetDefaultHandler" >XML_SetDefaultHandler</a></code> or +<code><a href="#XML_SetDefaultHandlerExpand" +>XML_SetDefaultHandlerExpand</a></code>. It does nothing if there is +not a default handler. +</div> + +<pre class="fcndec" id="XML_ExpatVersion"> +XML_LChar * XMLCALL +XML_ExpatVersion(); +</pre> +<div class="fcndef"> +Return the library version as a string (e.g. <code>"expat_1.95.1"</code>). +</div> + +<pre class="fcndec" id="XML_ExpatVersionInfo"> +struct XML_Expat_Version XMLCALL +XML_ExpatVersionInfo(); +</pre> +<pre class="signature"> +typedef struct { + int major; + int minor; + int micro; +} XML_Expat_Version; +</pre> +<div class="fcndef"> +Return the library version information as a structure. +Some macros are also defined that support compile-time tests of the +library version: +<ul> +<li><code>XML_MAJOR_VERSION</code></li> +<li><code>XML_MINOR_VERSION</code></li> +<li><code>XML_MICRO_VERSION</code></li> +</ul> +Testing these constants is currently the best way to determine if +particular parts of the Expat API are available. +</div> + +<pre class="fcndec" id="XML_GetFeatureList"> +const XML_Feature * XMLCALL +XML_GetFeatureList(); +</pre> +<pre class="signature"> +enum XML_FeatureEnum { + XML_FEATURE_END = 0, + XML_FEATURE_UNICODE, + XML_FEATURE_UNICODE_WCHAR_T, + XML_FEATURE_DTD, + XML_FEATURE_CONTEXT_BYTES, + XML_FEATURE_MIN_SIZE, + XML_FEATURE_SIZEOF_XML_CHAR, + XML_FEATURE_SIZEOF_XML_LCHAR, + XML_FEATURE_NS, + XML_FEATURE_LARGE_SIZE +}; + +typedef struct { + enum XML_FeatureEnum feature; + XML_LChar *name; + long int value; +} XML_Feature; +</pre> +<div class="fcndef"> +<p>Returns a list of "feature" records, providing details on how +Expat was configured at compile time. Most applications should not +need to worry about this, but this information is otherwise not +available from Expat. This function allows code that does need to +check these features to do so at runtime.</p> + +<p>The return value is an array of <code>XML_Feature</code>, +terminated by a record with a <code>feature</code> of +<code>XML_FEATURE_END</code> and <code>name</code> of NULL, +identifying the feature-test macros Expat was compiled with. Since an +application that requires this kind of information needs to determine +the type of character the <code>name</code> points to, records for the +<code>XML_FEATURE_SIZEOF_XML_CHAR</code> and +<code>XML_FEATURE_SIZEOF_XML_LCHAR</code> will be located at the +beginning of the list, followed by <code>XML_FEATURE_UNICODE</code> +and <code>XML_FEATURE_UNICODE_WCHAR_T</code>, if they are present at +all.</p> + +<p>Some features have an associated value. If there isn't an +associated value, the <code>value</code> field is set to 0. At this +time, the following features have been defined to have values:</p> + +<dl> + <dt><code>XML_FEATURE_SIZEOF_XML_CHAR</code></dt> + <dd>The number of bytes occupied by one <code>XML_Char</code> + character.</dd> + <dt><code>XML_FEATURE_SIZEOF_XML_LCHAR</code></dt> + <dd>The number of bytes occupied by one <code>XML_LChar</code> + character.</dd> + <dt><code>XML_FEATURE_CONTEXT_BYTES</code></dt> + <dd>The maximum number of characters of context which can be + reported by <code><a href= "#XML_GetInputContext" + >XML_GetInputContext</a></code>.</dd> +</dl> +</div> + +<pre class="fcndec" id="XML_FreeContentModel"> +void XMLCALL +XML_FreeContentModel(XML_Parser parser, XML_Content *model); +</pre> +<div class="fcndef"> +Function to deallocate the <code>model</code> argument passed to the +<code>XML_ElementDeclHandler</code> callback set using <code><a +href="#XML_SetElementDeclHandler" >XML_ElementDeclHandler</a></code>. +This function should not be used for any other purpose. +</div> + +<p>The following functions allow external code to share the memory +allocator an <code>XML_Parser</code> has been configured to use. This +is especially useful for third-party libraries that interact with a +parser object created by application code, or heavily layered +applications. This can be essential when using dynamically loaded +libraries which use different C standard libraries (this can happen on +Windows, at least).</p> + +<pre class="fcndec" id="XML_MemMalloc"> +void * XMLCALL +XML_MemMalloc(XML_Parser parser, size_t size); +</pre> +<div class="fcndef"> +Allocate <code>size</code> bytes of memory using the allocator the +<code>parser</code> object has been configured to use. Returns a +pointer to the memory or NULL on failure. Memory allocated in this +way must be freed using <code><a href="#XML_MemFree" +>XML_MemFree</a></code>. +</div> + +<pre class="fcndec" id="XML_MemRealloc"> +void * XMLCALL +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); +</pre> +<div class="fcndef"> +Allocate <code>size</code> bytes of memory using the allocator the +<code>parser</code> object has been configured to use. +<code>ptr</code> must point to a block of memory allocated by <code><a +href="#XML_MemMalloc" >XML_MemMalloc</a></code> or +<code>XML_MemRealloc</code>, or be NULL. This function tries to +expand the block pointed to by <code>ptr</code> if possible. Returns +a pointer to the memory or NULL on failure. On success, the original +block has either been expanded or freed. On failure, the original +block has not been freed; the caller is responsible for freeing the +original block. Memory allocated in this way must be freed using +<code><a href="#XML_MemFree" +>XML_MemFree</a></code>. +</div> + +<pre class="fcndec" id="XML_MemFree"> +void XMLCALL +XML_MemFree(XML_Parser parser, void *ptr); +</pre> +<div class="fcndef"> +Free a block of memory pointed to by <code>ptr</code>. The block must +have been allocated by <code><a href="#XML_MemMalloc" +>XML_MemMalloc</a></code> or <code>XML_MemRealloc</code>, or be NULL. +</div> + +<hr /> +<p><a href="http://validator.w3.org/check/referer"><img + src="valid-xhtml10.png" alt="Valid XHTML 1.0!" + height="31" width="88" class="noborder" /></a></p> +</div> +</body> +</html> diff --git a/contrib/expat/doc/style.css b/contrib/expat/doc/style.css new file mode 100644 index 0000000..69df30b --- /dev/null +++ b/contrib/expat/doc/style.css @@ -0,0 +1,101 @@ +body { + background-color: white; + border: 0px; + margin: 0px; + padding: 0px; +} + +.corner { + width: 200px; + height: 80px; + text-align: center; +} + +.banner { + background-color: rgb(110,139,61); + color: rgb(255,236,176); + padding-left: 2em; +} + +.banner h1 { + font-size: 200%; +} + +.content { + padding: 0em 2em 1em 2em; +} + +.releaseno { + background-color: rgb(110,139,61); + color: rgb(255,236,176); + padding-bottom: 0.3em; + padding-top: 0.5em; + text-align: center; + font-weight: bold; +} + +.noborder { + border-width: 0px; +} + +.eg { + padding-left: 1em; + padding-top: .5em; + padding-bottom: .5em; + border: solid thin; + margin: 1em 0; + background-color: tan; + margin-left: 2em; + margin-right: 10%; +} + +.pseudocode { + padding-left: 1em; + padding-top: .5em; + padding-bottom: .5em; + border: solid thin; + margin: 1em 0; + background-color: rgb(250,220,180); + margin-left: 2em; + margin-right: 10%; +} + +.handler { + width: 100%; + border-top-width: thin; + margin-bottom: 1em; +} + +.handler p { + margin-left: 2em; +} + +.setter { + font-weight: bold; +} + +.signature { + color: navy; +} + +.fcndec { + width: 100%; + border-top-width: thin; + font-weight: bold; +} + +.fcndef { + margin-left: 2em; + margin-bottom: 2em; +} + +dd { + margin-bottom: 2em; +} + +.cpp-symbols dt { + font-family: monospace; +} +.cpp-symbols dd { + margin-bottom: 1em; +} diff --git a/contrib/expat/doc/xmlwf.1 b/contrib/expat/doc/xmlwf.1 new file mode 100644 index 0000000..174719a --- /dev/null +++ b/contrib/expat/doc/xmlwf.1 @@ -0,0 +1,251 @@ +.\" This manpage has been automatically generated by docbook2man +.\" from a DocBook document. This tool can be found at: +.\" <http://shell.ipoline.com/~elmert/comp/docbook2X/> +.\" Please send any bug reports, improvements, comments, patches, +.\" etc. to Steve Cheng <steve@ggi-project.org>. +.TH "XMLWF" "1" "24 January 2003" "" "" +.SH NAME +xmlwf \- Determines if an XML document is well-formed +.SH SYNOPSIS + +\fBxmlwf\fR [ \fB-s\fR] [ \fB-n\fR] [ \fB-p\fR] [ \fB-x\fR] [ \fB-e \fIencoding\fB\fR] [ \fB-w\fR] [ \fB-d \fIoutput-dir\fB\fR] [ \fB-c\fR] [ \fB-m\fR] [ \fB-r\fR] [ \fB-t\fR] [ \fB-v\fR] [ \fBfile ...\fR] + +.SH "DESCRIPTION" +.PP +\fBxmlwf\fR uses the Expat library to +determine if an XML document is well-formed. It is +non-validating. +.PP +If you do not specify any files on the command-line, and you +have a recent version of \fBxmlwf\fR, the +input file will be read from standard input. +.SH "WELL-FORMED DOCUMENTS" +.PP +A well-formed document must adhere to the +following rules: +.TP 0.2i +\(bu +The file begins with an XML declaration. For instance, +<?xml version="1.0" standalone="yes"?>. +\fBNOTE:\fR +\fBxmlwf\fR does not currently +check for a valid XML declaration. +.TP 0.2i +\(bu +Every start tag is either empty (<tag/>) +or has a corresponding end tag. +.TP 0.2i +\(bu +There is exactly one root element. This element must contain +all other elements in the document. Only comments, white +space, and processing instructions may come after the close +of the root element. +.TP 0.2i +\(bu +All elements nest properly. +.TP 0.2i +\(bu +All attribute values are enclosed in quotes (either single +or double). +.PP +If the document has a DTD, and it strictly complies with that +DTD, then the document is also considered \fBvalid\fR. +\fBxmlwf\fR is a non-validating parser -- +it does not check the DTD. However, it does support +external entities (see the \fB-x\fR option). +.SH "OPTIONS" +.PP +When an option includes an argument, you may specify the argument either +separately ("\fB-d\fR output") or concatenated with the +option ("\fB-d\fRoutput"). \fBxmlwf\fR +supports both. +.TP +\fB-c\fR +If the input file is well-formed and \fBxmlwf\fR +doesn't encounter any errors, the input file is simply copied to +the output directory unchanged. +This implies no namespaces (turns off \fB-n\fR) and +requires \fB-d\fR to specify an output file. +.TP +\fB-d output-dir\fR +Specifies a directory to contain transformed +representations of the input files. +By default, \fB-d\fR outputs a canonical representation +(described below). +You can select different output formats using \fB-c\fR +and \fB-m\fR. + +The output filenames will +be exactly the same as the input filenames or "STDIN" if the input is +coming from standard input. Therefore, you must be careful that the +output file does not go into the same directory as the input +file. Otherwise, \fBxmlwf\fR will delete the +input file before it generates the output file (just like running +cat < file > file in most shells). + +Two structurally equivalent XML documents have a byte-for-byte +identical canonical XML representation. +Note that ignorable white space is considered significant and +is treated equivalently to data. +More on canonical XML can be found at +http://www.jclark.com/xml/canonxml.html . +.TP +\fB-e encoding\fR +Specifies the character encoding for the document, overriding +any document encoding declaration. \fBxmlwf\fR +supports four built-in encodings: +US-ASCII, +UTF-8, +UTF-16, and +ISO-8859-1. +Also see the \fB-w\fR option. +.TP +\fB-m\fR +Outputs some strange sort of XML file that completely +describes the input file, including character positions. +Requires \fB-d\fR to specify an output file. +.TP +\fB-n\fR +Turns on namespace processing. (describe namespaces) +\fB-c\fR disables namespaces. +.TP +\fB-p\fR +Tells xmlwf to process external DTDs and parameter +entities. + +Normally \fBxmlwf\fR never parses parameter +entities. \fB-p\fR tells it to always parse them. +\fB-p\fR implies \fB-x\fR. +.TP +\fB-r\fR +Normally \fBxmlwf\fR memory-maps the XML file +before parsing; this can result in faster parsing on many +platforms. +\fB-r\fR turns off memory-mapping and uses normal file +IO calls instead. +Of course, memory-mapping is automatically turned off +when reading from standard input. + +Use of memory-mapping can cause some platforms to report +substantially higher memory usage for +\fBxmlwf\fR, but this appears to be a matter of +the operating system reporting memory in a strange way; there is +not a leak in \fBxmlwf\fR. +.TP +\fB-s\fR +Prints an error if the document is not standalone. +A document is standalone if it has no external subset and no +references to parameter entities. +.TP +\fB-t\fR +Turns on timings. This tells Expat to parse the entire file, +but not perform any processing. +This gives a fairly accurate idea of the raw speed of Expat itself +without client overhead. +\fB-t\fR turns off most of the output options +(\fB-d\fR, \fB-m\fR, \fB-c\fR, +\&...). +.TP +\fB-v\fR +Prints the version of the Expat library being used, including some +information on the compile-time configuration of the library, and +then exits. +.TP +\fB-w\fR +Enables support for Windows code pages. +Normally, \fBxmlwf\fR will throw an error if it +runs across an encoding that it is not equipped to handle itself. With +\fB-w\fR, xmlwf will try to use a Windows code +page. See also \fB-e\fR. +.TP +\fB-x\fR +Turns on parsing external entities. + +Non-validating parsers are not required to resolve external +entities, or even expand entities at all. +Expat always expands internal entities (?), +but external entity parsing must be enabled explicitly. + +External entities are simply entities that obtain their +data from outside the XML file currently being parsed. + +This is an example of an internal entity: + +.nf +<!ENTITY vers '1.0.2'> +.fi + +And here are some examples of external entities: + +.nf +<!ENTITY header SYSTEM "header-&vers;.xml"> (parsed) +<!ENTITY logo SYSTEM "logo.png" PNG> (unparsed) +.fi +.TP +\fB--\fR +(Two hyphens.) +Terminates the list of options. This is only needed if a filename +starts with a hyphen. For example: + +.nf +xmlwf -- -myfile.xml +.fi + +will run \fBxmlwf\fR on the file +\fI-myfile.xml\fR. +.PP +Older versions of \fBxmlwf\fR do not support +reading from standard input. +.SH "OUTPUT" +.PP +If an input file is not well-formed, +\fBxmlwf\fR prints a single line describing +the problem to standard output. If a file is well formed, +\fBxmlwf\fR outputs nothing. +Note that the result code is \fBnot\fR set. +.SH "BUGS" +.PP +According to the W3C standard, an XML file without a +declaration at the beginning is not considered well-formed. +However, \fBxmlwf\fR allows this to pass. +.PP +\fBxmlwf\fR returns a 0 - noerr result, +even if the file is not well-formed. There is no good way for +a program to use \fBxmlwf\fR to quickly +check a file -- it must parse \fBxmlwf\fR's +standard output. +.PP +The errors should go to standard error, not standard output. +.PP +There should be a way to get \fB-d\fR to send its +output to standard output rather than forcing the user to send +it to a file. +.PP +I have no idea why anyone would want to use the +\fB-d\fR, \fB-c\fR, and +\fB-m\fR options. If someone could explain it to +me, I'd like to add this information to this manpage. +.SH "ALTERNATIVES" +.PP +Here are some XML validators on the web: + +.nf +http://www.hcrc.ed.ac.uk/~richard/xml-check.html +http://www.stg.brown.edu/service/xmlvalid/ +http://www.scripting.com/frontier5/xml/code/xmlValidator.html +http://www.xml.com/pub/a/tools/ruwf/check.html +.fi +.SH "SEE ALSO" +.PP + +.nf +The Expat home page: http://www.libexpat.org/ +The W3 XML specification: http://www.w3.org/TR/REC-xml +.fi +.SH "AUTHOR" +.PP +This manual page was written by Scott Bronson <bronson@rinspin.com> for +the Debian GNU/Linux system (but may be used by others). Permission is +granted to copy, distribute and/or modify this document under +the terms of the GNU Free Documentation +License, Version 1.1. diff --git a/contrib/expat/doc/xmlwf.sgml b/contrib/expat/doc/xmlwf.sgml new file mode 100644 index 0000000..313cfbc --- /dev/null +++ b/contrib/expat/doc/xmlwf.sgml @@ -0,0 +1,468 @@ +<!doctype refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN" [ + +<!-- Process this file with docbook-to-man to generate an nroff manual + page: `docbook-to-man manpage.sgml > manpage.1'. You may view + the manual page with: `docbook-to-man manpage.sgml | nroff -man | + less'. A typical entry in a Makefile or Makefile.am is: + +manpage.1: manpage.sgml + docbook-to-man $< > $@ + --> + + <!-- Fill in your name for FIRSTNAME and SURNAME. --> + <!ENTITY dhfirstname "<firstname>Scott</firstname>"> + <!ENTITY dhsurname "<surname>Bronson</surname>"> + <!-- Please adjust the date whenever revising the manpage. --> + <!ENTITY dhdate "<date>December 5, 2001</date>"> + <!-- SECTION should be 1-8, maybe w/ subsection other parameters are + allowed: see man(7), man(1). --> + <!ENTITY dhsection "<manvolnum>1</manvolnum>"> + <!ENTITY dhemail "<email>bronson@rinspin.com</email>"> + <!ENTITY dhusername "Scott Bronson"> + <!ENTITY dhucpackage "<refentrytitle>XMLWF</refentrytitle>"> + <!ENTITY dhpackage "xmlwf"> + + <!ENTITY debian "<productname>Debian GNU/Linux</productname>"> + <!ENTITY gnu "<acronym>GNU</acronym>"> +]> + +<refentry> + <refentryinfo> + <address> + &dhemail; + </address> + <author> + &dhfirstname; + &dhsurname; + </author> + <copyright> + <year>2001</year> + <holder>&dhusername;</holder> + </copyright> + &dhdate; + </refentryinfo> + <refmeta> + &dhucpackage; + + &dhsection; + </refmeta> + <refnamediv> + <refname>&dhpackage;</refname> + + <refpurpose>Determines if an XML document is well-formed</refpurpose> + </refnamediv> + <refsynopsisdiv> + <cmdsynopsis> + <command>&dhpackage;</command> + <arg><option>-s</option></arg> + <arg><option>-n</option></arg> + <arg><option>-p</option></arg> + <arg><option>-x</option></arg> + + <arg><option>-e <replaceable>encoding</replaceable></option></arg> + <arg><option>-w</option></arg> + + <arg><option>-d <replaceable>output-dir</replaceable></option></arg> + <arg><option>-c</option></arg> + <arg><option>-m</option></arg> + + <arg><option>-r</option></arg> + <arg><option>-t</option></arg> + + <arg><option>-v</option></arg> + + <arg>file ...</arg> + </cmdsynopsis> + </refsynopsisdiv> + + <refsect1> + <title>DESCRIPTION</title> + + <para> + <command>&dhpackage;</command> uses the Expat library to + determine if an XML document is well-formed. It is + non-validating. + </para> + + <para> + If you do not specify any files on the command-line, and you + have a recent version of <command>&dhpackage;</command>, the + input file will be read from standard input. + </para> + + </refsect1> + + <refsect1> + <title>WELL-FORMED DOCUMENTS</title> + + <para> + A well-formed document must adhere to the + following rules: + </para> + + <itemizedlist> + <listitem><para> + The file begins with an XML declaration. For instance, + <literal><?xml version="1.0" standalone="yes"?></literal>. + <emphasis>NOTE:</emphasis> + <command>&dhpackage;</command> does not currently + check for a valid XML declaration. + </para></listitem> + <listitem><para> + Every start tag is either empty (<tag/>) + or has a corresponding end tag. + </para></listitem> + <listitem><para> + There is exactly one root element. This element must contain + all other elements in the document. Only comments, white + space, and processing instructions may come after the close + of the root element. + </para></listitem> + <listitem><para> + All elements nest properly. + </para></listitem> + <listitem><para> + All attribute values are enclosed in quotes (either single + or double). + </para></listitem> + </itemizedlist> + + <para> + If the document has a DTD, and it strictly complies with that + DTD, then the document is also considered <emphasis>valid</emphasis>. + <command>&dhpackage;</command> is a non-validating parser -- + it does not check the DTD. However, it does support + external entities (see the <option>-x</option> option). + </para> + </refsect1> + + <refsect1> + <title>OPTIONS</title> + +<para> +When an option includes an argument, you may specify the argument either +separately ("<option>-d</option> output") or concatenated with the +option ("<option>-d</option>output"). <command>&dhpackage;</command> +supports both. +</para> + + <variablelist> + + <varlistentry> + <term><option>-c</option></term> + <listitem> + <para> + If the input file is well-formed and <command>&dhpackage;</command> + doesn't encounter any errors, the input file is simply copied to + the output directory unchanged. + This implies no namespaces (turns off <option>-n</option>) and + requires <option>-d</option> to specify an output file. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-d output-dir</option></term> + <listitem> + <para> + Specifies a directory to contain transformed + representations of the input files. + By default, <option>-d</option> outputs a canonical representation + (described below). + You can select different output formats using <option>-c</option> + and <option>-m</option>. + </para> + <para> + The output filenames will + be exactly the same as the input filenames or "STDIN" if the input is + coming from standard input. Therefore, you must be careful that the + output file does not go into the same directory as the input + file. Otherwise, <command>&dhpackage;</command> will delete the + input file before it generates the output file (just like running + <literal>cat < file > file</literal> in most shells). + </para> + <para> + Two structurally equivalent XML documents have a byte-for-byte + identical canonical XML representation. + Note that ignorable white space is considered significant and + is treated equivalently to data. + More on canonical XML can be found at + http://www.jclark.com/xml/canonxml.html . + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-e encoding</option></term> + <listitem> + <para> + Specifies the character encoding for the document, overriding + any document encoding declaration. <command>&dhpackage;</command> + supports four built-in encodings: + <literal>US-ASCII</literal>, + <literal>UTF-8</literal>, + <literal>UTF-16</literal>, and + <literal>ISO-8859-1</literal>. + Also see the <option>-w</option> option. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-m</option></term> + <listitem> + <para> + Outputs some strange sort of XML file that completely + describes the the input file, including character postitions. + Requires <option>-d</option> to specify an output file. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-n</option></term> + <listitem> + <para> + Turns on namespace processing. (describe namespaces) + <option>-c</option> disables namespaces. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-p</option></term> + <listitem> + <para> + Tells xmlwf to process external DTDs and parameter + entities. + </para> + <para> + Normally <command>&dhpackage;</command> never parses parameter + entities. <option>-p</option> tells it to always parse them. + <option>-p</option> implies <option>-x</option>. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-r</option></term> + <listitem> + <para> + Normally <command>&dhpackage;</command> memory-maps the XML file + before parsing; this can result in faster parsing on many + platforms. + <option>-r</option> turns off memory-mapping and uses normal file + IO calls instead. + Of course, memory-mapping is automatically turned off + when reading from standard input. + </para> + <para> + Use of memory-mapping can cause some platforms to report + substantially higher memory usage for + <command>&dhpackage;</command>, but this appears to be a matter of + the operating system reporting memory in a strange way; there is + not a leak in <command>&dhpackage;</command>. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-s</option></term> + <listitem> + <para> + Prints an error if the document is not standalone. + A document is standalone if it has no external subset and no + references to parameter entities. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-t</option></term> + <listitem> + <para> + Turns on timings. This tells Expat to parse the entire file, + but not perform any processing. + This gives a fairly accurate idea of the raw speed of Expat itself + without client overhead. + <option>-t</option> turns off most of the output options + (<option>-d</option>, <option>-m</option>, <option>-c</option>, + ...). + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-v</option></term> + <listitem> + <para> + Prints the version of the Expat library being used, including some + information on the compile-time configuration of the library, and + then exits. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-w</option></term> + <listitem> + <para> + Enables support for Windows code pages. + Normally, <command>&dhpackage;</command> will throw an error if it + runs across an encoding that it is not equipped to handle itself. With + <option>-w</option>, &dhpackage; will try to use a Windows code + page. See also <option>-e</option>. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>-x</option></term> + <listitem> + <para> + Turns on parsing external entities. + </para> +<para> + Non-validating parsers are not required to resolve external + entities, or even expand entities at all. + Expat always expands internal entities (?), + but external entity parsing must be enabled explicitly. + </para> + <para> + External entities are simply entities that obtain their + data from outside the XML file currently being parsed. + </para> + <para> + This is an example of an internal entity: +<literallayout> +<!ENTITY vers '1.0.2'> +</literallayout> + </para> + <para> + And here are some examples of external entities: + +<literallayout> +<!ENTITY header SYSTEM "header-&vers;.xml"> (parsed) +<!ENTITY logo SYSTEM "logo.png" PNG> (unparsed) +</literallayout> + + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><option>--</option></term> + <listitem> + <para> + (Two hyphens.) + Terminates the list of options. This is only needed if a filename + starts with a hyphen. For example: + </para> +<literallayout> +&dhpackage; -- -myfile.xml +</literallayout> + <para> + will run <command>&dhpackage;</command> on the file + <filename>-myfile.xml</filename>. + </para> + </listitem> + </varlistentry> + </variablelist> + + <para> + Older versions of <command>&dhpackage;</command> do not support + reading from standard input. + </para> + </refsect1> + + <refsect1> + <title>OUTPUT</title> + <para> + If an input file is not well-formed, + <command>&dhpackage;</command> prints a single line describing + the problem to standard output. If a file is well formed, + <command>&dhpackage;</command> outputs nothing. + Note that the result code is <emphasis>not</emphasis> set. + </para> + </refsect1> + + <refsect1> + <title>BUGS</title> + <para> + <command>&dhpackage;</command> returns a 0 - noerr result, + even if the file is not well-formed. There is no good way for + a program to use <command>&dhpackage;</command> to quickly + check a file -- it must parse <command>&dhpackage;</command>'s + standard output. + </para> + <para> + The errors should go to standard error, not standard output. + </para> + <para> + There should be a way to get <option>-d</option> to send its + output to standard output rather than forcing the user to send + it to a file. + </para> + <para> + I have no idea why anyone would want to use the + <option>-d</option>, <option>-c</option>, and + <option>-m</option> options. If someone could explain it to + me, I'd like to add this information to this manpage. + </para> + </refsect1> + + <refsect1> + <title>ALTERNATIVES</title> + <para> + Here are some XML validators on the web: + +<literallayout> +http://www.hcrc.ed.ac.uk/~richard/xml-check.html +http://www.stg.brown.edu/service/xmlvalid/ +http://www.scripting.com/frontier5/xml/code/xmlValidator.html +http://www.xml.com/pub/a/tools/ruwf/check.html +</literallayout> + + </para> + </refsect1> + + <refsect1> + <title>SEE ALSO</title> + <para> + +<literallayout> +The Expat home page: http://www.libexpat.org/ +The W3 XML specification: http://www.w3.org/TR/REC-xml +</literallayout> + + </para> + </refsect1> + + <refsect1> + <title>AUTHOR</title> + <para> + This manual page was written by &dhusername; &dhemail; for + the &debian; system (but may be used by others). Permission is + granted to copy, distribute and/or modify this document under + the terms of the <acronym>GNU</acronym> Free Documentation + License, Version 1.1. + </para> + </refsect1> +</refentry> + +<!-- Keep this comment at the end of the file +Local variables: +mode: sgml +sgml-omittag:t +sgml-shorttag:t +sgml-minimize-attributes:nil +sgml-always-quote-attributes:t +sgml-indent-step:2 +sgml-indent-data:t +sgml-parent-document:nil +sgml-default-dtd-file:nil +sgml-exposed-tags:nil +sgml-local-catalogs:nil +sgml-local-ecat-files:nil +End: +--> diff --git a/contrib/expat/examples/elements.c b/contrib/expat/examples/elements.c new file mode 100644 index 0000000..6b8f855 --- /dev/null +++ b/contrib/expat/examples/elements.c @@ -0,0 +1,65 @@ +/* This is simple demonstration of how to use expat. This program + reads an XML document from standard input and writes a line with + the name of each element to standard output indenting child + elements by one tab stop more than their parent element. + It must be used with Expat compiled for UTF-8 output. +*/ + +#include <stdio.h> +#include "expat.h" + +#if defined(__amigaos__) && defined(__USE_INLINE__) +#include <proto/expat.h> +#endif + +#ifdef XML_LARGE_SIZE +#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400 +#define XML_FMT_INT_MOD "I64" +#else +#define XML_FMT_INT_MOD "ll" +#endif +#else +#define XML_FMT_INT_MOD "l" +#endif + +static void XMLCALL +startElement(void *userData, const char *name, const char **atts) +{ + int i; + int *depthPtr = (int *)userData; + for (i = 0; i < *depthPtr; i++) + putchar('\t'); + puts(name); + *depthPtr += 1; +} + +static void XMLCALL +endElement(void *userData, const char *name) +{ + int *depthPtr = (int *)userData; + *depthPtr -= 1; +} + +int +main(int argc, char *argv[]) +{ + char buf[BUFSIZ]; + XML_Parser parser = XML_ParserCreate(NULL); + int done; + int depth = 0; + XML_SetUserData(parser, &depth); + XML_SetElementHandler(parser, startElement, endElement); + do { + int len = (int)fread(buf, 1, sizeof(buf), stdin); + done = len < sizeof(buf); + if (XML_Parse(parser, buf, len, done) == XML_STATUS_ERROR) { + fprintf(stderr, + "%s at line %" XML_FMT_INT_MOD "u\n", + XML_ErrorString(XML_GetErrorCode(parser)), + XML_GetCurrentLineNumber(parser)); + return 1; + } + } while (!done); + XML_ParserFree(parser); + return 0; +} diff --git a/contrib/expat/examples/outline.c b/contrib/expat/examples/outline.c new file mode 100644 index 0000000..3a3c838 --- /dev/null +++ b/contrib/expat/examples/outline.c @@ -0,0 +1,106 @@ +/***************************************************************** + * outline.c + * + * Copyright 1999, Clark Cooper + * All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the license contained in the + * COPYING file that comes with the expat distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY + * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * Read an XML document from standard input and print an element + * outline on standard output. + * Must be used with Expat compiled for UTF-8 output. + */ + + +#include <stdio.h> +#include <expat.h> + +#if defined(__amigaos__) && defined(__USE_INLINE__) +#include <proto/expat.h> +#endif + +#ifdef XML_LARGE_SIZE +#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400 +#define XML_FMT_INT_MOD "I64" +#else +#define XML_FMT_INT_MOD "ll" +#endif +#else +#define XML_FMT_INT_MOD "l" +#endif + +#define BUFFSIZE 8192 + +char Buff[BUFFSIZE]; + +int Depth; + +static void XMLCALL +start(void *data, const char *el, const char **attr) +{ + int i; + + for (i = 0; i < Depth; i++) + printf(" "); + + printf("%s", el); + + for (i = 0; attr[i]; i += 2) { + printf(" %s='%s'", attr[i], attr[i + 1]); + } + + printf("\n"); + Depth++; +} + +static void XMLCALL +end(void *data, const char *el) +{ + Depth--; +} + +int +main(int argc, char *argv[]) +{ + XML_Parser p = XML_ParserCreate(NULL); + if (! p) { + fprintf(stderr, "Couldn't allocate memory for parser\n"); + exit(-1); + } + + XML_SetElementHandler(p, start, end); + + for (;;) { + int done; + int len; + + len = (int)fread(Buff, 1, BUFFSIZE, stdin); + if (ferror(stdin)) { + fprintf(stderr, "Read error\n"); + exit(-1); + } + done = feof(stdin); + + if (XML_Parse(p, Buff, len, done) == XML_STATUS_ERROR) { + fprintf(stderr, "Parse error at line %" XML_FMT_INT_MOD "u:\n%s\n", + XML_GetCurrentLineNumber(p), + XML_ErrorString(XML_GetErrorCode(p))); + exit(-1); + } + + if (done) + break; + } + XML_ParserFree(p); + return 0; +} diff --git a/contrib/expat/expat_config.h.in b/contrib/expat/expat_config.h.in new file mode 100644 index 0000000..8c6e514 --- /dev/null +++ b/contrib/expat/expat_config.h.in @@ -0,0 +1,102 @@ +/* expat_config.h.in. Generated from configure.in by autoheader. */ + +/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +#undef BYTEORDER + +/* Define to 1 if you have the `bcopy' function. */ +#undef HAVE_BCOPY + +/* Define to 1 if you have the <dlfcn.h> header file. */ +#undef HAVE_DLFCN_H + +/* Define to 1 if you have the <fcntl.h> header file. */ +#undef HAVE_FCNTL_H + +/* Define to 1 if you have the `getpagesize' function. */ +#undef HAVE_GETPAGESIZE + +/* Define to 1 if you have the <inttypes.h> header file. */ +#undef HAVE_INTTYPES_H + +/* Define to 1 if you have the `memmove' function. */ +#undef HAVE_MEMMOVE + +/* Define to 1 if you have the <memory.h> header file. */ +#undef HAVE_MEMORY_H + +/* Define to 1 if you have a working `mmap' system call. */ +#undef HAVE_MMAP + +/* Define to 1 if you have the <stdint.h> header file. */ +#undef HAVE_STDINT_H + +/* Define to 1 if you have the <stdlib.h> header file. */ +#undef HAVE_STDLIB_H + +/* Define to 1 if you have the <strings.h> header file. */ +#undef HAVE_STRINGS_H + +/* Define to 1 if you have the <string.h> header file. */ +#undef HAVE_STRING_H + +/* Define to 1 if you have the <sys/param.h> header file. */ +#undef HAVE_SYS_PARAM_H + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#undef HAVE_SYS_STAT_H + +/* Define to 1 if you have the <sys/types.h> header file. */ +#undef HAVE_SYS_TYPES_H + +/* Define to 1 if you have the <unistd.h> header file. */ +#undef HAVE_UNISTD_H + +/* Define to the sub-directory in which libtool stores uninstalled libraries. + */ +#undef LT_OBJDIR + +/* Define to the address where bug reports for this package should be sent. */ +#undef PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#undef PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#undef PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#undef PACKAGE_TARNAME + +/* Define to the home page for this package. */ +#undef PACKAGE_URL + +/* Define to the version of this package. */ +#undef PACKAGE_VERSION + +/* Define to 1 if you have the ANSI C header files. */ +#undef STDC_HEADERS + +/* whether byteorder is bigendian */ +#undef WORDS_BIGENDIAN + +/* Define to specify how much context to retain around the current parse + point. */ +#undef XML_CONTEXT_BYTES + +/* Define to make parameter entity parsing functionality available. */ +#undef XML_DTD + +/* Define to make XML Namespaces functionality available. */ +#undef XML_NS + +/* Define to __FUNCTION__ or "" if `__func__' does not conform to ANSI C. */ +#undef __func__ + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to `long int' if <sys/types.h> does not define. */ +#undef off_t + +/* Define to `unsigned int' if <sys/types.h> does not define. */ +#undef size_t diff --git a/contrib/expat/lib/ascii.h b/contrib/expat/lib/ascii.h new file mode 100644 index 0000000..d10530b --- /dev/null +++ b/contrib/expat/lib/ascii.h @@ -0,0 +1,92 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#define ASCII_A 0x41 +#define ASCII_B 0x42 +#define ASCII_C 0x43 +#define ASCII_D 0x44 +#define ASCII_E 0x45 +#define ASCII_F 0x46 +#define ASCII_G 0x47 +#define ASCII_H 0x48 +#define ASCII_I 0x49 +#define ASCII_J 0x4A +#define ASCII_K 0x4B +#define ASCII_L 0x4C +#define ASCII_M 0x4D +#define ASCII_N 0x4E +#define ASCII_O 0x4F +#define ASCII_P 0x50 +#define ASCII_Q 0x51 +#define ASCII_R 0x52 +#define ASCII_S 0x53 +#define ASCII_T 0x54 +#define ASCII_U 0x55 +#define ASCII_V 0x56 +#define ASCII_W 0x57 +#define ASCII_X 0x58 +#define ASCII_Y 0x59 +#define ASCII_Z 0x5A + +#define ASCII_a 0x61 +#define ASCII_b 0x62 +#define ASCII_c 0x63 +#define ASCII_d 0x64 +#define ASCII_e 0x65 +#define ASCII_f 0x66 +#define ASCII_g 0x67 +#define ASCII_h 0x68 +#define ASCII_i 0x69 +#define ASCII_j 0x6A +#define ASCII_k 0x6B +#define ASCII_l 0x6C +#define ASCII_m 0x6D +#define ASCII_n 0x6E +#define ASCII_o 0x6F +#define ASCII_p 0x70 +#define ASCII_q 0x71 +#define ASCII_r 0x72 +#define ASCII_s 0x73 +#define ASCII_t 0x74 +#define ASCII_u 0x75 +#define ASCII_v 0x76 +#define ASCII_w 0x77 +#define ASCII_x 0x78 +#define ASCII_y 0x79 +#define ASCII_z 0x7A + +#define ASCII_0 0x30 +#define ASCII_1 0x31 +#define ASCII_2 0x32 +#define ASCII_3 0x33 +#define ASCII_4 0x34 +#define ASCII_5 0x35 +#define ASCII_6 0x36 +#define ASCII_7 0x37 +#define ASCII_8 0x38 +#define ASCII_9 0x39 + +#define ASCII_TAB 0x09 +#define ASCII_SPACE 0x20 +#define ASCII_EXCL 0x21 +#define ASCII_QUOT 0x22 +#define ASCII_AMP 0x26 +#define ASCII_APOS 0x27 +#define ASCII_MINUS 0x2D +#define ASCII_PERIOD 0x2E +#define ASCII_COLON 0x3A +#define ASCII_SEMI 0x3B +#define ASCII_LT 0x3C +#define ASCII_EQUALS 0x3D +#define ASCII_GT 0x3E +#define ASCII_LSQB 0x5B +#define ASCII_RSQB 0x5D +#define ASCII_UNDERSCORE 0x5F +#define ASCII_LPAREN 0x28 +#define ASCII_RPAREN 0x29 +#define ASCII_FF 0x0C +#define ASCII_SLASH 0x2F +#define ASCII_HASH 0x23 +#define ASCII_PIPE 0x7C +#define ASCII_COMMA 0x2C diff --git a/contrib/expat/lib/asciitab.h b/contrib/expat/lib/asciitab.h new file mode 100644 index 0000000..79a15c2 --- /dev/null +++ b/contrib/expat/lib/asciitab.h @@ -0,0 +1,36 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, +/* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML, +/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, +/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, +/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, +/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, +/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, +/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, +/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, +/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, +/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/contrib/expat/lib/expat.h b/contrib/expat/lib/expat.h new file mode 100644 index 0000000..9a21680 --- /dev/null +++ b/contrib/expat/lib/expat.h @@ -0,0 +1,1047 @@ +/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef Expat_INCLUDED +#define Expat_INCLUDED 1 + +#ifdef __VMS +/* 0 1 2 3 0 1 2 3 + 1234567890123456789012345678901 1234567890123456789012345678901 */ +#define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler +#define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler +#define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler +#define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg +#endif + +#include <stdlib.h> +#include "expat_external.h" + +#ifdef __cplusplus +extern "C" { +#endif + +struct XML_ParserStruct; +typedef struct XML_ParserStruct *XML_Parser; + +/* Should this be defined using stdbool.h when C99 is available? */ +typedef unsigned char XML_Bool; +#define XML_TRUE ((XML_Bool) 1) +#define XML_FALSE ((XML_Bool) 0) + +/* The XML_Status enum gives the possible return values for several + API functions. The preprocessor #defines are included so this + stanza can be added to code that still needs to support older + versions of Expat 1.95.x: + + #ifndef XML_STATUS_OK + #define XML_STATUS_OK 1 + #define XML_STATUS_ERROR 0 + #endif + + Otherwise, the #define hackery is quite ugly and would have been + dropped. +*/ +enum XML_Status { + XML_STATUS_ERROR = 0, +#define XML_STATUS_ERROR XML_STATUS_ERROR + XML_STATUS_OK = 1, +#define XML_STATUS_OK XML_STATUS_OK + XML_STATUS_SUSPENDED = 2 +#define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED +}; + +enum XML_Error { + XML_ERROR_NONE, + XML_ERROR_NO_MEMORY, + XML_ERROR_SYNTAX, + XML_ERROR_NO_ELEMENTS, + XML_ERROR_INVALID_TOKEN, + XML_ERROR_UNCLOSED_TOKEN, + XML_ERROR_PARTIAL_CHAR, + XML_ERROR_TAG_MISMATCH, + XML_ERROR_DUPLICATE_ATTRIBUTE, + XML_ERROR_JUNK_AFTER_DOC_ELEMENT, + XML_ERROR_PARAM_ENTITY_REF, + XML_ERROR_UNDEFINED_ENTITY, + XML_ERROR_RECURSIVE_ENTITY_REF, + XML_ERROR_ASYNC_ENTITY, + XML_ERROR_BAD_CHAR_REF, + XML_ERROR_BINARY_ENTITY_REF, + XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, + XML_ERROR_MISPLACED_XML_PI, + XML_ERROR_UNKNOWN_ENCODING, + XML_ERROR_INCORRECT_ENCODING, + XML_ERROR_UNCLOSED_CDATA_SECTION, + XML_ERROR_EXTERNAL_ENTITY_HANDLING, + XML_ERROR_NOT_STANDALONE, + XML_ERROR_UNEXPECTED_STATE, + XML_ERROR_ENTITY_DECLARED_IN_PE, + XML_ERROR_FEATURE_REQUIRES_XML_DTD, + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, + /* Added in 1.95.7. */ + XML_ERROR_UNBOUND_PREFIX, + /* Added in 1.95.8. */ + XML_ERROR_UNDECLARING_PREFIX, + XML_ERROR_INCOMPLETE_PE, + XML_ERROR_XML_DECL, + XML_ERROR_TEXT_DECL, + XML_ERROR_PUBLICID, + XML_ERROR_SUSPENDED, + XML_ERROR_NOT_SUSPENDED, + XML_ERROR_ABORTED, + XML_ERROR_FINISHED, + XML_ERROR_SUSPEND_PE, + /* Added in 2.0. */ + XML_ERROR_RESERVED_PREFIX_XML, + XML_ERROR_RESERVED_PREFIX_XMLNS, + XML_ERROR_RESERVED_NAMESPACE_URI +}; + +enum XML_Content_Type { + XML_CTYPE_EMPTY = 1, + XML_CTYPE_ANY, + XML_CTYPE_MIXED, + XML_CTYPE_NAME, + XML_CTYPE_CHOICE, + XML_CTYPE_SEQ +}; + +enum XML_Content_Quant { + XML_CQUANT_NONE, + XML_CQUANT_OPT, + XML_CQUANT_REP, + XML_CQUANT_PLUS +}; + +/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be + XML_CQUANT_NONE, and the other fields will be zero or NULL. + If type == XML_CTYPE_MIXED, then quant will be NONE or REP and + numchildren will contain number of elements that may be mixed in + and children point to an array of XML_Content cells that will be + all of XML_CTYPE_NAME type with no quantification. + + If type == XML_CTYPE_NAME, then the name points to the name, and + the numchildren field will be zero and children will be NULL. The + quant fields indicates any quantifiers placed on the name. + + CHOICE and SEQ will have name NULL, the number of children in + numchildren and children will point, recursively, to an array + of XML_Content cells. + + The EMPTY, ANY, and MIXED types will only occur at top level. +*/ + +typedef struct XML_cp XML_Content; + +struct XML_cp { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + XML_Char * name; + unsigned int numchildren; + XML_Content * children; +}; + + +/* This is called for an element declaration. See above for + description of the model argument. It's the caller's responsibility + to free model when finished with it. +*/ +typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, + const XML_Char *name, + XML_Content *model); + +XMLPARSEAPI(void) +XML_SetElementDeclHandler(XML_Parser parser, + XML_ElementDeclHandler eldecl); + +/* The Attlist declaration handler is called for *each* attribute. So + a single Attlist declaration with multiple attributes declared will + generate multiple calls to this handler. The "default" parameter + may be NULL in the case of the "#IMPLIED" or "#REQUIRED" + keyword. The "isrequired" parameter will be true and the default + value will be NULL in the case of "#REQUIRED". If "isrequired" is + true and default is non-NULL, then this is a "#FIXED" default. +*/ +typedef void (XMLCALL *XML_AttlistDeclHandler) ( + void *userData, + const XML_Char *elname, + const XML_Char *attname, + const XML_Char *att_type, + const XML_Char *dflt, + int isrequired); + +XMLPARSEAPI(void) +XML_SetAttlistDeclHandler(XML_Parser parser, + XML_AttlistDeclHandler attdecl); + +/* The XML declaration handler is called for *both* XML declarations + and text declarations. The way to distinguish is that the version + parameter will be NULL for text declarations. The encoding + parameter may be NULL for XML declarations. The standalone + parameter will be -1, 0, or 1 indicating respectively that there + was no standalone parameter in the declaration, that it was given + as no, or that it was given as yes. +*/ +typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone); + +XMLPARSEAPI(void) +XML_SetXmlDeclHandler(XML_Parser parser, + XML_XmlDeclHandler xmldecl); + + +typedef struct { + void *(*malloc_fcn)(size_t size); + void *(*realloc_fcn)(void *ptr, size_t size); + void (*free_fcn)(void *ptr); +} XML_Memory_Handling_Suite; + +/* Constructs a new parser; encoding is the encoding specified by the + external protocol or NULL if there is none specified. +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreate(const XML_Char *encoding); + +/* Constructs a new parser and namespace processor. Element type + names and attribute names that belong to a namespace will be + expanded; unprefixed attribute names are never expanded; unprefixed + element type names are expanded only if there is a default + namespace. The expanded name is the concatenation of the namespace + URI, the namespace separator character, and the local part of the + name. If the namespace separator is '\0' then the namespace URI + and the local part will be concatenated without any separator. + It is a programming error to use the separator '\0' with namespace + triplets (see XML_SetReturnNSTriplet). +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); + + +/* Constructs a new parser using the memory management suite referred to + by memsuite. If memsuite is NULL, then use the standard library memory + suite. If namespaceSeparator is non-NULL it creates a parser with + namespace processing as described above. The character pointed at + will serve as the namespace separator. + + All further memory operations used for the created parser will come from + the given suite. +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreate_MM(const XML_Char *encoding, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *namespaceSeparator); + +/* Prepare a parser object to be re-used. This is particularly + valuable when memory allocation overhead is disproportionatly high, + such as when a large number of small documnents need to be parsed. + All handlers are cleared from the parser, except for the + unknownEncodingHandler. The parser's external state is re-initialized + except for the values of ns and ns_triplets. + + Added in Expat 1.95.3. +*/ +XMLPARSEAPI(XML_Bool) +XML_ParserReset(XML_Parser parser, const XML_Char *encoding); + +/* atts is array of name/value pairs, terminated by 0; + names and values are 0 terminated. +*/ +typedef void (XMLCALL *XML_StartElementHandler) (void *userData, + const XML_Char *name, + const XML_Char **atts); + +typedef void (XMLCALL *XML_EndElementHandler) (void *userData, + const XML_Char *name); + + +/* s is not 0 terminated. */ +typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, + const XML_Char *s, + int len); + +/* target and data are 0 terminated */ +typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( + void *userData, + const XML_Char *target, + const XML_Char *data); + +/* data is 0 terminated */ +typedef void (XMLCALL *XML_CommentHandler) (void *userData, + const XML_Char *data); + +typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); +typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); + +/* This is called for any characters in the XML document for which + there is no applicable handler. This includes both characters that + are part of markup which is of a kind that is not reported + (comments, markup declarations), or characters that are part of a + construct which could be reported but for which no handler has been + supplied. The characters are passed exactly as they were in the XML + document except that they will be encoded in UTF-8 or UTF-16. + Line boundaries are not normalized. Note that a byte order mark + character is not passed to the default handler. There are no + guarantees about how characters are divided between calls to the + default handler: for example, a comment might be split between + multiple calls. +*/ +typedef void (XMLCALL *XML_DefaultHandler) (void *userData, + const XML_Char *s, + int len); + +/* This is called for the start of the DOCTYPE declaration, before + any DTD or internal subset is parsed. +*/ +typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( + void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset); + +/* This is called for the start of the DOCTYPE declaration when the + closing > is encountered, but after processing any external + subset. +*/ +typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); + +/* This is called for entity declarations. The is_parameter_entity + argument will be non-zero if the entity is a parameter entity, zero + otherwise. + + For internal entities (<!ENTITY foo "bar">), value will + be non-NULL and systemId, publicID, and notationName will be NULL. + The value string is NOT nul-terminated; the length is provided in + the value_length argument. Since it is legal to have zero-length + values, do not use this argument to test for internal entities. + + For external entities, value will be NULL and systemId will be + non-NULL. The publicId argument will be NULL unless a public + identifier was provided. The notationName argument will have a + non-NULL value only for unparsed entity declarations. + + Note that is_parameter_entity can't be changed to XML_Bool, since + that would break binary compatibility. +*/ +typedef void (XMLCALL *XML_EntityDeclHandler) ( + void *userData, + const XML_Char *entityName, + int is_parameter_entity, + const XML_Char *value, + int value_length, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); + +XMLPARSEAPI(void) +XML_SetEntityDeclHandler(XML_Parser parser, + XML_EntityDeclHandler handler); + +/* OBSOLETE -- OBSOLETE -- OBSOLETE + This handler has been superceded by the EntityDeclHandler above. + It is provided here for backward compatibility. + + This is called for a declaration of an unparsed (NDATA) entity. + The base argument is whatever was set by XML_SetBase. The + entityName, systemId and notationName arguments will never be + NULL. The other arguments may be. +*/ +typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( + void *userData, + const XML_Char *entityName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); + +/* This is called for a declaration of notation. The base argument is + whatever was set by XML_SetBase. The notationName will never be + NULL. The other arguments can be. +*/ +typedef void (XMLCALL *XML_NotationDeclHandler) ( + void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* When namespace processing is enabled, these are called once for + each namespace declaration. The call to the start and end element + handlers occur between the calls to the start and end namespace + declaration handlers. For an xmlns attribute, prefix will be + NULL. For an xmlns="" attribute, uri will be NULL. +*/ +typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( + void *userData, + const XML_Char *prefix, + const XML_Char *uri); + +typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( + void *userData, + const XML_Char *prefix); + +/* This is called if the document is not standalone, that is, it has an + external subset or a reference to a parameter entity, but does not + have standalone="yes". If this handler returns XML_STATUS_ERROR, + then processing will not continue, and the parser will return a + XML_ERROR_NOT_STANDALONE error. + If parameter entity parsing is enabled, then in addition to the + conditions above this handler will only be called if the referenced + entity was actually read. +*/ +typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); + +/* This is called for a reference to an external parsed general + entity. The referenced entity is not automatically parsed. The + application can parse it immediately or later using + XML_ExternalEntityParserCreate. + + The parser argument is the parser parsing the entity containing the + reference; it can be passed as the parser argument to + XML_ExternalEntityParserCreate. The systemId argument is the + system identifier as specified in the entity declaration; it will + not be NULL. + + The base argument is the system identifier that should be used as + the base for resolving systemId if systemId was relative; this is + set by XML_SetBase; it may be NULL. + + The publicId argument is the public identifier as specified in the + entity declaration, or NULL if none was specified; the whitespace + in the public identifier will have been normalized as required by + the XML spec. + + The context argument specifies the parsing context in the format + expected by the context argument to XML_ExternalEntityParserCreate; + context is valid only until the handler returns, so if the + referenced entity is to be parsed later, it must be copied. + context is NULL only when the entity is a parameter entity. + + The handler should return XML_STATUS_ERROR if processing should not + continue because of a fatal error in the handling of the external + entity. In this case the calling parser will return an + XML_ERROR_EXTERNAL_ENTITY_HANDLING error. + + Note that unlike other handlers the first argument is the parser, + not userData. +*/ +typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( + XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* This is called in two situations: + 1) An entity reference is encountered for which no declaration + has been read *and* this is not an error. + 2) An internal entity reference is read, but not expanded, because + XML_SetDefaultHandler has been called. + Note: skipped parameter entities in declarations and skipped general + entities in attribute values cannot be reported, because + the event would be out of sync with the reporting of the + declarations or attribute values +*/ +typedef void (XMLCALL *XML_SkippedEntityHandler) ( + void *userData, + const XML_Char *entityName, + int is_parameter_entity); + +/* This structure is filled in by the XML_UnknownEncodingHandler to + provide information to the parser about encodings that are unknown + to the parser. + + The map[b] member gives information about byte sequences whose + first byte is b. + + If map[b] is c where c is >= 0, then b by itself encodes the + Unicode scalar value c. + + If map[b] is -1, then the byte sequence is malformed. + + If map[b] is -n, where n >= 2, then b is the first byte of an + n-byte sequence that encodes a single Unicode scalar value. + + The data member will be passed as the first argument to the convert + function. + + The convert function is used to convert multibyte sequences; s will + point to a n-byte sequence where map[(unsigned char)*s] == -n. The + convert function must return the Unicode scalar value represented + by this byte sequence or -1 if the byte sequence is malformed. + + The convert function may be NULL if the encoding is a single-byte + encoding, that is if map[b] >= -1 for all bytes b. + + When the parser is finished with the encoding, then if release is + not NULL, it will call release passing it the data member; once + release has been called, the convert function will not be called + again. + + Expat places certain restrictions on the encodings that are supported + using this mechanism. + + 1. Every ASCII character that can appear in a well-formed XML document, + other than the characters + + $@\^`{}~ + + must be represented by a single byte, and that byte must be the + same byte that represents that character in ASCII. + + 2. No character may require more than 4 bytes to encode. + + 3. All characters encoded must have Unicode scalar values <= + 0xFFFF, (i.e., characters that would be encoded by surrogates in + UTF-16 are not allowed). Note that this restriction doesn't + apply to the built-in support for UTF-8 and UTF-16. + + 4. No Unicode character may be encoded by more than one distinct + sequence of bytes. +*/ +typedef struct { + int map[256]; + void *data; + int (XMLCALL *convert)(void *data, const char *s); + void (XMLCALL *release)(void *data); +} XML_Encoding; + +/* This is called for an encoding that is unknown to the parser. + + The encodingHandlerData argument is that which was passed as the + second argument to XML_SetUnknownEncodingHandler. + + The name argument gives the name of the encoding as specified in + the encoding declaration. + + If the callback can provide information about the encoding, it must + fill in the XML_Encoding structure, and return XML_STATUS_OK. + Otherwise it must return XML_STATUS_ERROR. + + If info does not describe a suitable encoding, then the parser will + return an XML_UNKNOWN_ENCODING error. +*/ +typedef int (XMLCALL *XML_UnknownEncodingHandler) ( + void *encodingHandlerData, + const XML_Char *name, + XML_Encoding *info); + +XMLPARSEAPI(void) +XML_SetElementHandler(XML_Parser parser, + XML_StartElementHandler start, + XML_EndElementHandler end); + +XMLPARSEAPI(void) +XML_SetStartElementHandler(XML_Parser parser, + XML_StartElementHandler handler); + +XMLPARSEAPI(void) +XML_SetEndElementHandler(XML_Parser parser, + XML_EndElementHandler handler); + +XMLPARSEAPI(void) +XML_SetCharacterDataHandler(XML_Parser parser, + XML_CharacterDataHandler handler); + +XMLPARSEAPI(void) +XML_SetProcessingInstructionHandler(XML_Parser parser, + XML_ProcessingInstructionHandler handler); +XMLPARSEAPI(void) +XML_SetCommentHandler(XML_Parser parser, + XML_CommentHandler handler); + +XMLPARSEAPI(void) +XML_SetCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end); + +XMLPARSEAPI(void) +XML_SetStartCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start); + +XMLPARSEAPI(void) +XML_SetEndCdataSectionHandler(XML_Parser parser, + XML_EndCdataSectionHandler end); + +/* This sets the default handler and also inhibits expansion of + internal entities. These entity references will be passed to the + default handler, or to the skipped entity handler, if one is set. +*/ +XMLPARSEAPI(void) +XML_SetDefaultHandler(XML_Parser parser, + XML_DefaultHandler handler); + +/* This sets the default handler but does not inhibit expansion of + internal entities. The entity reference will not be passed to the + default handler. +*/ +XMLPARSEAPI(void) +XML_SetDefaultHandlerExpand(XML_Parser parser, + XML_DefaultHandler handler); + +XMLPARSEAPI(void) +XML_SetDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end); + +XMLPARSEAPI(void) +XML_SetStartDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start); + +XMLPARSEAPI(void) +XML_SetEndDoctypeDeclHandler(XML_Parser parser, + XML_EndDoctypeDeclHandler end); + +XMLPARSEAPI(void) +XML_SetUnparsedEntityDeclHandler(XML_Parser parser, + XML_UnparsedEntityDeclHandler handler); + +XMLPARSEAPI(void) +XML_SetNotationDeclHandler(XML_Parser parser, + XML_NotationDeclHandler handler); + +XMLPARSEAPI(void) +XML_SetNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end); + +XMLPARSEAPI(void) +XML_SetStartNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start); + +XMLPARSEAPI(void) +XML_SetEndNamespaceDeclHandler(XML_Parser parser, + XML_EndNamespaceDeclHandler end); + +XMLPARSEAPI(void) +XML_SetNotStandaloneHandler(XML_Parser parser, + XML_NotStandaloneHandler handler); + +XMLPARSEAPI(void) +XML_SetExternalEntityRefHandler(XML_Parser parser, + XML_ExternalEntityRefHandler handler); + +/* If a non-NULL value for arg is specified here, then it will be + passed as the first argument to the external entity ref handler + instead of the parser object. +*/ +XMLPARSEAPI(void) +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, + void *arg); + +XMLPARSEAPI(void) +XML_SetSkippedEntityHandler(XML_Parser parser, + XML_SkippedEntityHandler handler); + +XMLPARSEAPI(void) +XML_SetUnknownEncodingHandler(XML_Parser parser, + XML_UnknownEncodingHandler handler, + void *encodingHandlerData); + +/* This can be called within a handler for a start element, end + element, processing instruction or character data. It causes the + corresponding markup to be passed to the default handler. +*/ +XMLPARSEAPI(void) +XML_DefaultCurrent(XML_Parser parser); + +/* If do_nst is non-zero, and namespace processing is in effect, and + a name has a prefix (i.e. an explicit namespace qualifier) then + that name is returned as a triplet in a single string separated by + the separator character specified when the parser was created: URI + + sep + local_name + sep + prefix. + + If do_nst is zero, then namespace information is returned in the + default manner (URI + sep + local_name) whether or not the name + has a prefix. + + Note: Calling XML_SetReturnNSTriplet after XML_Parse or + XML_ParseBuffer has no effect. +*/ + +XMLPARSEAPI(void) +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); + +/* This value is passed as the userData argument to callbacks. */ +XMLPARSEAPI(void) +XML_SetUserData(XML_Parser parser, void *userData); + +/* Returns the last value set by XML_SetUserData or NULL. */ +#define XML_GetUserData(parser) (*(void **)(parser)) + +/* This is equivalent to supplying an encoding argument to + XML_ParserCreate. On success XML_SetEncoding returns non-zero, + zero otherwise. + Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer + has no effect and returns XML_STATUS_ERROR. +*/ +XMLPARSEAPI(enum XML_Status) +XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); + +/* If this function is called, then the parser will be passed as the + first argument to callbacks instead of userData. The userData will + still be accessible using XML_GetUserData. +*/ +XMLPARSEAPI(void) +XML_UseParserAsHandlerArg(XML_Parser parser); + +/* If useDTD == XML_TRUE is passed to this function, then the parser + will assume that there is an external subset, even if none is + specified in the document. In such a case the parser will call the + externalEntityRefHandler with a value of NULL for the systemId + argument (the publicId and context arguments will be NULL as well). + Note: For the purpose of checking WFC: Entity Declared, passing + useDTD == XML_TRUE will make the parser behave as if the document + had a DTD with an external subset. + Note: If this function is called, then this must be done before + the first call to XML_Parse or XML_ParseBuffer, since it will + have no effect after that. Returns + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. + Note: If the document does not have a DOCTYPE declaration at all, + then startDoctypeDeclHandler and endDoctypeDeclHandler will not + be called, despite an external subset being parsed. + Note: If XML_DTD is not defined when Expat is compiled, returns + XML_ERROR_FEATURE_REQUIRES_XML_DTD. +*/ +XMLPARSEAPI(enum XML_Error) +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); + + +/* Sets the base to be used for resolving relative URIs in system + identifiers in declarations. Resolving relative identifiers is + left to the application: this value will be passed through as the + base argument to the XML_ExternalEntityRefHandler, + XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base + argument will be copied. Returns XML_STATUS_ERROR if out of memory, + XML_STATUS_OK otherwise. +*/ +XMLPARSEAPI(enum XML_Status) +XML_SetBase(XML_Parser parser, const XML_Char *base); + +XMLPARSEAPI(const XML_Char *) +XML_GetBase(XML_Parser parser); + +/* Returns the number of the attribute/value pairs passed in last call + to the XML_StartElementHandler that were specified in the start-tag + rather than defaulted. Each attribute/value pair counts as 2; thus + this correspondds to an index into the atts array passed to the + XML_StartElementHandler. +*/ +XMLPARSEAPI(int) +XML_GetSpecifiedAttributeCount(XML_Parser parser); + +/* Returns the index of the ID attribute passed in the last call to + XML_StartElementHandler, or -1 if there is no ID attribute. Each + attribute/value pair counts as 2; thus this correspondds to an + index into the atts array passed to the XML_StartElementHandler. +*/ +XMLPARSEAPI(int) +XML_GetIdAttributeIndex(XML_Parser parser); + +#ifdef XML_ATTR_INFO +/* Source file byte offsets for the start and end of attribute names and values. + The value indices are exclusive of surrounding quotes; thus in a UTF-8 source + file an attribute value of "blah" will yield: + info->valueEnd - info->valueStart = 4 bytes. +*/ +typedef struct { + XML_Index nameStart; /* Offset to beginning of the attribute name. */ + XML_Index nameEnd; /* Offset after the attribute name's last byte. */ + XML_Index valueStart; /* Offset to beginning of the attribute value. */ + XML_Index valueEnd; /* Offset after the attribute value's last byte. */ +} XML_AttrInfo; + +/* Returns an array of XML_AttrInfo structures for the attribute/value pairs + passed in last call to the XML_StartElementHandler that were specified + in the start-tag rather than defaulted. Each attribute/value pair counts + as 1; thus the number of entries in the array is + XML_GetSpecifiedAttributeCount(parser) / 2. +*/ +XMLPARSEAPI(const XML_AttrInfo *) +XML_GetAttributeInfo(XML_Parser parser); +#endif + +/* Parses some input. Returns XML_STATUS_ERROR if a fatal error is + detected. The last call to XML_Parse must have isFinal true; len + may be zero for this call (or any other). + + Though the return values for these functions has always been + described as a Boolean value, the implementation, at least for the + 1.95.x series, has always returned exactly one of the XML_Status + values. +*/ +XMLPARSEAPI(enum XML_Status) +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); + +XMLPARSEAPI(void *) +XML_GetBuffer(XML_Parser parser, int len); + +XMLPARSEAPI(enum XML_Status) +XML_ParseBuffer(XML_Parser parser, int len, int isFinal); + +/* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. + Must be called from within a call-back handler, except when aborting + (resumable = 0) an already suspended parser. Some call-backs may + still follow because they would otherwise get lost. Examples: + - endElementHandler() for empty elements when stopped in + startElementHandler(), + - endNameSpaceDeclHandler() when stopped in endElementHandler(), + and possibly others. + + Can be called from most handlers, including DTD related call-backs, + except when parsing an external parameter entity and resumable != 0. + Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. + Possible error codes: + - XML_ERROR_SUSPENDED: when suspending an already suspended parser. + - XML_ERROR_FINISHED: when the parser has already finished. + - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. + + When resumable != 0 (true) then parsing is suspended, that is, + XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. + Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() + return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. + + *Note*: + This will be applied to the current parser instance only, that is, if + there is a parent parser then it will continue parsing when the + externalEntityRefHandler() returns. It is up to the implementation of + the externalEntityRefHandler() to call XML_StopParser() on the parent + parser (recursively), if one wants to stop parsing altogether. + + When suspended, parsing can be resumed by calling XML_ResumeParser(). +*/ +XMLPARSEAPI(enum XML_Status) +XML_StopParser(XML_Parser parser, XML_Bool resumable); + +/* Resumes parsing after it has been suspended with XML_StopParser(). + Must not be called from within a handler call-back. Returns same + status codes as XML_Parse() or XML_ParseBuffer(). + Additional error code XML_ERROR_NOT_SUSPENDED possible. + + *Note*: + This must be called on the most deeply nested child parser instance + first, and on its parent parser only after the child parser has finished, + to be applied recursively until the document entity's parser is restarted. + That is, the parent parser will not resume by itself and it is up to the + application to call XML_ResumeParser() on it at the appropriate moment. +*/ +XMLPARSEAPI(enum XML_Status) +XML_ResumeParser(XML_Parser parser); + +enum XML_Parsing { + XML_INITIALIZED, + XML_PARSING, + XML_FINISHED, + XML_SUSPENDED +}; + +typedef struct { + enum XML_Parsing parsing; + XML_Bool finalBuffer; +} XML_ParsingStatus; + +/* Returns status of parser with respect to being initialized, parsing, + finished, or suspended and processing the final buffer. + XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, + XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED +*/ +XMLPARSEAPI(void) +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); + +/* Creates an XML_Parser object that can parse an external general + entity; context is a '\0'-terminated string specifying the parse + context; encoding is a '\0'-terminated string giving the name of + the externally specified encoding, or NULL if there is no + externally specified encoding. The context string consists of a + sequence of tokens separated by formfeeds (\f); a token consisting + of a name specifies that the general entity of the name is open; a + token of the form prefix=uri specifies the namespace for a + particular prefix; a token of the form =uri specifies the default + namespace. This can be called at any point after the first call to + an ExternalEntityRefHandler so longer as the parser has not yet + been freed. The new parser is completely independent and may + safely be used in a separate thread. The handlers and userData are + initialized from the parser argument. Returns NULL if out of memory. + Otherwise returns a new XML_Parser object. +*/ +XMLPARSEAPI(XML_Parser) +XML_ExternalEntityParserCreate(XML_Parser parser, + const XML_Char *context, + const XML_Char *encoding); + +enum XML_ParamEntityParsing { + XML_PARAM_ENTITY_PARSING_NEVER, + XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, + XML_PARAM_ENTITY_PARSING_ALWAYS +}; + +/* Controls parsing of parameter entities (including the external DTD + subset). If parsing of parameter entities is enabled, then + references to external parameter entities (including the external + DTD subset) will be passed to the handler set with + XML_SetExternalEntityRefHandler. The context passed will be 0. + + Unlike external general entities, external parameter entities can + only be parsed synchronously. If the external parameter entity is + to be parsed, it must be parsed during the call to the external + entity ref handler: the complete sequence of + XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and + XML_ParserFree calls must be made during this call. After + XML_ExternalEntityParserCreate has been called to create the parser + for the external parameter entity (context must be 0 for this + call), it is illegal to make any calls on the old parser until + XML_ParserFree has been called on the newly created parser. + If the library has been compiled without support for parameter + entity parsing (ie without XML_DTD being defined), then + XML_SetParamEntityParsing will return 0 if parsing of parameter + entities is requested; otherwise it will return non-zero. + Note: If XML_SetParamEntityParsing is called after XML_Parse or + XML_ParseBuffer, then it has no effect and will always return 0. +*/ +XMLPARSEAPI(int) +XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing parsing); + +/* Sets the hash salt to use for internal hash calculations. + Helps in preventing DoS attacks based on predicting hash + function behavior. This must be called before parsing is started. + Returns 1 if successful, 0 when called after parsing has started. +*/ +XMLPARSEAPI(int) +XML_SetHashSalt(XML_Parser parser, + unsigned long hash_salt); + +/* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then + XML_GetErrorCode returns information about the error. +*/ +XMLPARSEAPI(enum XML_Error) +XML_GetErrorCode(XML_Parser parser); + +/* These functions return information about the current parse + location. They may be called from any callback called to report + some parse event; in this case the location is the location of the + first of the sequence of characters that generated the event. When + called from callbacks generated by declarations in the document + prologue, the location identified isn't as neatly defined, but will + be within the relevant markup. When called outside of the callback + functions, the position indicated will be just past the last parse + event (regardless of whether there was an associated callback). + + They may also be called after returning from a call to XML_Parse + or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then + the location is the location of the character at which the error + was detected; otherwise the location is the location of the last + parse event, as described above. +*/ +XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); +XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); +XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); + +/* Return the number of bytes in the current event. + Returns 0 if the event is in an internal entity. +*/ +XMLPARSEAPI(int) +XML_GetCurrentByteCount(XML_Parser parser); + +/* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets + the integer pointed to by offset to the offset within this buffer + of the current parse position, and sets the integer pointed to by size + to the size of this buffer (the number of input bytes). Otherwise + returns a NULL pointer. Also returns a NULL pointer if a parse isn't + active. + + NOTE: The character pointer returned should not be used outside + the handler that makes the call. +*/ +XMLPARSEAPI(const char *) +XML_GetInputContext(XML_Parser parser, + int *offset, + int *size); + +/* For backwards compatibility with previous versions. */ +#define XML_GetErrorLineNumber XML_GetCurrentLineNumber +#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber +#define XML_GetErrorByteIndex XML_GetCurrentByteIndex + +/* Frees the content model passed to the element declaration handler */ +XMLPARSEAPI(void) +XML_FreeContentModel(XML_Parser parser, XML_Content *model); + +/* Exposing the memory handling functions used in Expat */ +XMLPARSEAPI(void *) +XML_MemMalloc(XML_Parser parser, size_t size); + +XMLPARSEAPI(void *) +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); + +XMLPARSEAPI(void) +XML_MemFree(XML_Parser parser, void *ptr); + +/* Frees memory used by the parser. */ +XMLPARSEAPI(void) +XML_ParserFree(XML_Parser parser); + +/* Returns a string describing the error. */ +XMLPARSEAPI(const XML_LChar *) +XML_ErrorString(enum XML_Error code); + +/* Return a string containing the version number of this expat */ +XMLPARSEAPI(const XML_LChar *) +XML_ExpatVersion(void); + +typedef struct { + int major; + int minor; + int micro; +} XML_Expat_Version; + +/* Return an XML_Expat_Version structure containing numeric version + number information for this version of expat. +*/ +XMLPARSEAPI(XML_Expat_Version) +XML_ExpatVersionInfo(void); + +/* Added in Expat 1.95.5. */ +enum XML_FeatureEnum { + XML_FEATURE_END = 0, + XML_FEATURE_UNICODE, + XML_FEATURE_UNICODE_WCHAR_T, + XML_FEATURE_DTD, + XML_FEATURE_CONTEXT_BYTES, + XML_FEATURE_MIN_SIZE, + XML_FEATURE_SIZEOF_XML_CHAR, + XML_FEATURE_SIZEOF_XML_LCHAR, + XML_FEATURE_NS, + XML_FEATURE_LARGE_SIZE, + XML_FEATURE_ATTR_INFO + /* Additional features must be added to the end of this enum. */ +}; + +typedef struct { + enum XML_FeatureEnum feature; + const XML_LChar *name; + long int value; +} XML_Feature; + +XMLPARSEAPI(const XML_Feature *) +XML_GetFeatureList(void); + + +/* Expat follows the GNU/Linux convention of odd number minor version for + beta/development releases and even number minor version for stable + releases. Micro is bumped with each release, and set to 0 with each + change to major or minor version. +*/ +#define XML_MAJOR_VERSION 2 +#define XML_MINOR_VERSION 1 +#define XML_MICRO_VERSION 0 + +#ifdef __cplusplus +} +#endif + +#endif /* not Expat_INCLUDED */ diff --git a/contrib/expat/lib/expat_external.h b/contrib/expat/lib/expat_external.h new file mode 100644 index 0000000..2c03284 --- /dev/null +++ b/contrib/expat/lib/expat_external.h @@ -0,0 +1,115 @@ +/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef Expat_External_INCLUDED +#define Expat_External_INCLUDED 1 + +/* External API definitions */ + +#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) +#define XML_USE_MSC_EXTENSIONS 1 +#endif + +/* Expat tries very hard to make the API boundary very specifically + defined. There are two macros defined to control this boundary; + each of these can be defined before including this header to + achieve some different behavior, but doing so it not recommended or + tested frequently. + + XMLCALL - The calling convention to use for all calls across the + "library boundary." This will default to cdecl, and + try really hard to tell the compiler that's what we + want. + + XMLIMPORT - Whatever magic is needed to note that a function is + to be imported from a dynamically loaded library + (.dll, .so, or .sl, depending on your platform). + + The XMLCALL macro was added in Expat 1.95.7. The only one which is + expected to be directly useful in client code is XMLCALL. + + Note that on at least some Unix versions, the Expat library must be + compiled with the cdecl calling convention as the default since + system headers may assume the cdecl convention. +*/ +#ifndef XMLCALL +#if defined(_MSC_VER) +#define XMLCALL __cdecl +#elif defined(__GNUC__) && defined(__i386) && !defined(__INTEL_COMPILER) +#define XMLCALL __attribute__((cdecl)) +#else +/* For any platform which uses this definition and supports more than + one calling convention, we need to extend this definition to + declare the convention used on that platform, if it's possible to + do so. + + If this is the case for your platform, please file a bug report + with information on how to identify your platform via the C + pre-processor and how to specify the same calling convention as the + platform's malloc() implementation. +*/ +#define XMLCALL +#endif +#endif /* not defined XMLCALL */ + + +#if !defined(XML_STATIC) && !defined(XMLIMPORT) +#ifndef XML_BUILDING_EXPAT +/* using Expat from an application */ + +#ifdef XML_USE_MSC_EXTENSIONS +#define XMLIMPORT __declspec(dllimport) +#endif + +#endif +#endif /* not defined XML_STATIC */ + + +/* If we didn't define it above, define it away: */ +#ifndef XMLIMPORT +#define XMLIMPORT +#endif + + +#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL + +#ifdef __cplusplus +extern "C" { +#endif + +#ifdef XML_UNICODE_WCHAR_T +#define XML_UNICODE +#endif + +#ifdef XML_UNICODE /* Information is UTF-16 encoded. */ +#ifdef XML_UNICODE_WCHAR_T +typedef wchar_t XML_Char; +typedef wchar_t XML_LChar; +#else +typedef unsigned short XML_Char; +typedef char XML_LChar; +#endif /* XML_UNICODE_WCHAR_T */ +#else /* Information is UTF-8 encoded. */ +typedef char XML_Char; +typedef char XML_LChar; +#endif /* XML_UNICODE */ + +#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */ +#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400 +typedef __int64 XML_Index; +typedef unsigned __int64 XML_Size; +#else +typedef long long XML_Index; +typedef unsigned long long XML_Size; +#endif +#else +typedef long XML_Index; +typedef unsigned long XML_Size; +#endif /* XML_LARGE_SIZE */ + +#ifdef __cplusplus +} +#endif + +#endif /* not Expat_External_INCLUDED */ diff --git a/contrib/expat/lib/iasciitab.h b/contrib/expat/lib/iasciitab.h new file mode 100644 index 0000000..24a1d5c --- /dev/null +++ b/contrib/expat/lib/iasciitab.h @@ -0,0 +1,37 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */ +/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, +/* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML, +/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, +/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, +/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, +/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, +/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, +/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, +/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, +/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, +/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/contrib/expat/lib/internal.h b/contrib/expat/lib/internal.h new file mode 100644 index 0000000..dd54548 --- /dev/null +++ b/contrib/expat/lib/internal.h @@ -0,0 +1,73 @@ +/* internal.h + + Internal definitions used by Expat. This is not needed to compile + client code. + + The following calling convention macros are defined for frequently + called functions: + + FASTCALL - Used for those internal functions that have a simple + body and a low number of arguments and local variables. + + PTRCALL - Used for functions called though function pointers. + + PTRFASTCALL - Like PTRCALL, but for low number of arguments. + + inline - Used for selected internal functions for which inlining + may improve performance on some platforms. + + Note: Use of these macros is based on judgement, not hard rules, + and therefore subject to change. +*/ + +#if defined(__GNUC__) && defined(__i386__) && !defined(__MINGW32__) +/* We'll use this version by default only where we know it helps. + + regparm() generates warnings on Solaris boxes. See SF bug #692878. + + Instability reported with egcs on a RedHat Linux 7.3. + Let's comment out: + #define FASTCALL __attribute__((stdcall, regparm(3))) + and let's try this: +*/ +#define FASTCALL __attribute__((regparm(3))) +#define PTRFASTCALL __attribute__((regparm(3))) +#endif + +/* Using __fastcall seems to have an unexpected negative effect under + MS VC++, especially for function pointers, so we won't use it for + now on that platform. It may be reconsidered for a future release + if it can be made more effective. + Likely reason: __fastcall on Windows is like stdcall, therefore + the compiler cannot perform stack optimizations for call clusters. +*/ + +/* Make sure all of these are defined if they aren't already. */ + +#ifndef FASTCALL +#define FASTCALL +#endif + +#ifndef PTRCALL +#define PTRCALL +#endif + +#ifndef PTRFASTCALL +#define PTRFASTCALL +#endif + +#ifndef XML_MIN_SIZE +#if !defined(__cplusplus) && !defined(inline) +#ifdef __GNUC__ +#define inline __inline +#endif /* __GNUC__ */ +#endif +#endif /* XML_MIN_SIZE */ + +#ifdef __cplusplus +#define inline inline +#else +#ifndef inline +#define inline +#endif +#endif diff --git a/contrib/expat/lib/latin1tab.h b/contrib/expat/lib/latin1tab.h new file mode 100644 index 0000000..53c25d7 --- /dev/null +++ b/contrib/expat/lib/latin1tab.h @@ -0,0 +1,36 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, +/* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME, +/* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, +/* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, diff --git a/contrib/expat/lib/nametab.h b/contrib/expat/lib/nametab.h new file mode 100644 index 0000000..b05e62c --- /dev/null +++ b/contrib/expat/lib/nametab.h @@ -0,0 +1,150 @@ +static const unsigned namingBitmap[] = { +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0x00000000, 0x04000000, 0x87FFFFFE, 0x07FFFFFE, +0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF, +0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE00F, 0xFC31FFFF, +0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, +0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, +0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, +0xFFFF0003, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, +0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, +0x0000007F, 0x00000000, 0xFFFF0000, 0x000707FF, +0x00000000, 0x07FFFFFE, 0x000007FE, 0xFFFE0000, +0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060, +0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003, +0xFFF99FE0, 0x03C5FDFF, 0xB0000000, 0x00030003, +0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000, +0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001, +0xFFF99FE0, 0x23CDFDFF, 0xB0000000, 0x00000003, +0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000, +0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003, +0xFFFDDFE0, 0x03EFFDFF, 0x40000000, 0x00000003, +0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFE, 0x000D7FFF, 0x0000003F, 0x00000000, +0xFEF02596, 0x200D6CAE, 0x0000001F, 0x00000000, +0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF, +0x0007DAED, 0x50000000, 0x82315001, 0x002C62AB, +0x40000000, 0xF580C900, 0x00000007, 0x02010800, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF, +0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF, +0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF, +0x00000000, 0x00004C40, 0x00000000, 0x00000000, +0x00000007, 0x00000000, 0x00000000, 0x00000000, +0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF, +0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF, +0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0xFFFFFFFF, 0x0000000F, 0x00000000, 0x00000000, +0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE, +0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF, +0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, +0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003, +0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, +0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, +0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, +0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, +0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF, +0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF, +0xFFFFFFFF, 0x7CFFFFFF, 0xFFEF7FFF, 0x03FF3DFF, +0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF, +0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF, +0xFFF987E4, 0xD36DFDFF, 0x5E003987, 0x001FFFC0, +0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1, +0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3, +0xD63DC7EC, 0xC3BFC718, 0x00803DC7, 0x0000FF80, +0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3, +0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3, +0xFFFDDFEC, 0xC3FFFDFF, 0x00803DCF, 0x0000FFC3, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000, +0xFEF02596, 0x3BFF6CAE, 0x03FF3F5F, 0x00000000, +0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF, +0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x1FFF0000, 0x00000002, +0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF, +0x661FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x77FFFFFF, +}; +static const unsigned char nmstrtPages[] = { +0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00, +0x00, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, +0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, +0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x15, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; +static const unsigned char namePages[] = { +0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00, +0x00, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, +0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, +0x26, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x27, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; diff --git a/contrib/expat/lib/utf8tab.h b/contrib/expat/lib/utf8tab.h new file mode 100644 index 0000000..7bb3e77 --- /dev/null +++ b/contrib/expat/lib/utf8tab.h @@ -0,0 +1,37 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + + +/* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4, +/* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM, diff --git a/contrib/expat/lib/xmlparse.c b/contrib/expat/lib/xmlparse.c new file mode 100644 index 0000000..f35aa36 --- /dev/null +++ b/contrib/expat/lib/xmlparse.c @@ -0,0 +1,6403 @@ +/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stddef.h> +#include <string.h> /* memset(), memcpy() */ +#include <assert.h> +#include <limits.h> /* UINT_MAX */ +#include <time.h> /* time() */ + +#define XML_BUILDING_EXPAT 1 + +#ifdef COMPILED_FROM_DSP +#include "winconfig.h" +#elif defined(MACOS_CLASSIC) +#include "macconfig.h" +#elif defined(__amigaos__) +#include "amigaconfig.h" +#elif defined(__WATCOMC__) +#include "watcomconfig.h" +#elif defined(HAVE_EXPAT_CONFIG_H) +#include <expat_config.h> +#endif /* ndef COMPILED_FROM_DSP */ + +#include "ascii.h" +#include "expat.h" + +#ifdef XML_UNICODE +#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX +#define XmlConvert XmlUtf16Convert +#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding +#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS +#define XmlEncode XmlUtf16Encode +/* Using pointer subtraction to convert to integer type. */ +#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((char *)(s) - (char *)NULL) & 1)) +typedef unsigned short ICHAR; +#else +#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX +#define XmlConvert XmlUtf8Convert +#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding +#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS +#define XmlEncode XmlUtf8Encode +#define MUST_CONVERT(enc, s) (!(enc)->isUtf8) +typedef char ICHAR; +#endif + + +#ifndef XML_NS + +#define XmlInitEncodingNS XmlInitEncoding +#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding +#undef XmlGetInternalEncodingNS +#define XmlGetInternalEncodingNS XmlGetInternalEncoding +#define XmlParseXmlDeclNS XmlParseXmlDecl + +#endif + +#ifdef XML_UNICODE + +#ifdef XML_UNICODE_WCHAR_T +#define XML_T(x) (const wchar_t)x +#define XML_L(x) L ## x +#else +#define XML_T(x) (const unsigned short)x +#define XML_L(x) x +#endif + +#else + +#define XML_T(x) x +#define XML_L(x) x + +#endif + +/* Round up n to be a multiple of sz, where sz is a power of 2. */ +#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1)) + +/* Handle the case where memmove() doesn't exist. */ +#ifndef HAVE_MEMMOVE +#ifdef HAVE_BCOPY +#define memmove(d,s,l) bcopy((s),(d),(l)) +#else +#error memmove does not exist on this platform, nor is a substitute available +#endif /* HAVE_BCOPY */ +#endif /* HAVE_MEMMOVE */ + +#include "internal.h" +#include "xmltok.h" +#include "xmlrole.h" + +typedef const XML_Char *KEY; + +typedef struct { + KEY name; +} NAMED; + +typedef struct { + NAMED **v; + unsigned char power; + size_t size; + size_t used; + const XML_Memory_Handling_Suite *mem; +} HASH_TABLE; + +/* Basic character hash algorithm, taken from Python's string hash: + h = h * 1000003 ^ character, the constant being a prime number. + +*/ +#ifdef XML_UNICODE +#define CHAR_HASH(h, c) \ + (((h) * 0xF4243) ^ (unsigned short)(c)) +#else +#define CHAR_HASH(h, c) \ + (((h) * 0xF4243) ^ (unsigned char)(c)) +#endif + +/* For probing (after a collision) we need a step size relative prime + to the hash table size, which is a power of 2. We use double-hashing, + since we can calculate a second hash value cheaply by taking those bits + of the first hash value that were discarded (masked out) when the table + index was calculated: index = hash & mask, where mask = table->size - 1. + We limit the maximum step size to table->size / 4 (mask >> 2) and make + it odd, since odd numbers are always relative prime to a power of 2. +*/ +#define SECOND_HASH(hash, mask, power) \ + ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2)) +#define PROBE_STEP(hash, mask, power) \ + ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1)) + +typedef struct { + NAMED **p; + NAMED **end; +} HASH_TABLE_ITER; + +#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ +#define INIT_DATA_BUF_SIZE 1024 +#define INIT_ATTS_SIZE 16 +#define INIT_ATTS_VERSION 0xFFFFFFFF +#define INIT_BLOCK_SIZE 1024 +#define INIT_BUFFER_SIZE 1024 + +#define EXPAND_SPARE 24 + +typedef struct binding { + struct prefix *prefix; + struct binding *nextTagBinding; + struct binding *prevPrefixBinding; + const struct attribute_id *attId; + XML_Char *uri; + int uriLen; + int uriAlloc; +} BINDING; + +typedef struct prefix { + const XML_Char *name; + BINDING *binding; +} PREFIX; + +typedef struct { + const XML_Char *str; + const XML_Char *localPart; + const XML_Char *prefix; + int strLen; + int uriLen; + int prefixLen; +} TAG_NAME; + +/* TAG represents an open element. + The name of the element is stored in both the document and API + encodings. The memory buffer 'buf' is a separately-allocated + memory area which stores the name. During the XML_Parse()/ + XMLParseBuffer() when the element is open, the memory for the 'raw' + version of the name (in the document encoding) is shared with the + document buffer. If the element is open across calls to + XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to + contain the 'raw' name as well. + + A parser re-uses these structures, maintaining a list of allocated + TAG objects in a free list. +*/ +typedef struct tag { + struct tag *parent; /* parent of this element */ + const char *rawName; /* tagName in the original encoding */ + int rawNameLength; + TAG_NAME name; /* tagName in the API encoding */ + char *buf; /* buffer for name components */ + char *bufEnd; /* end of the buffer */ + BINDING *bindings; +} TAG; + +typedef struct { + const XML_Char *name; + const XML_Char *textPtr; + int textLen; /* length in XML_Chars */ + int processed; /* # of processed bytes - when suspended */ + const XML_Char *systemId; + const XML_Char *base; + const XML_Char *publicId; + const XML_Char *notation; + XML_Bool open; + XML_Bool is_param; + XML_Bool is_internal; /* true if declared in internal subset outside PE */ +} ENTITY; + +typedef struct { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + const XML_Char * name; + int firstchild; + int lastchild; + int childcnt; + int nextsib; +} CONTENT_SCAFFOLD; + +#define INIT_SCAFFOLD_ELEMENTS 32 + +typedef struct block { + struct block *next; + int size; + XML_Char s[1]; +} BLOCK; + +typedef struct { + BLOCK *blocks; + BLOCK *freeBlocks; + const XML_Char *end; + XML_Char *ptr; + XML_Char *start; + const XML_Memory_Handling_Suite *mem; +} STRING_POOL; + +/* The XML_Char before the name is used to determine whether + an attribute has been specified. */ +typedef struct attribute_id { + XML_Char *name; + PREFIX *prefix; + XML_Bool maybeTokenized; + XML_Bool xmlns; +} ATTRIBUTE_ID; + +typedef struct { + const ATTRIBUTE_ID *id; + XML_Bool isCdata; + const XML_Char *value; +} DEFAULT_ATTRIBUTE; + +typedef struct { + unsigned long version; + unsigned long hash; + const XML_Char *uriName; +} NS_ATT; + +typedef struct { + const XML_Char *name; + PREFIX *prefix; + const ATTRIBUTE_ID *idAtt; + int nDefaultAtts; + int allocDefaultAtts; + DEFAULT_ATTRIBUTE *defaultAtts; +} ELEMENT_TYPE; + +typedef struct { + HASH_TABLE generalEntities; + HASH_TABLE elementTypes; + HASH_TABLE attributeIds; + HASH_TABLE prefixes; + STRING_POOL pool; + STRING_POOL entityValuePool; + /* false once a parameter entity reference has been skipped */ + XML_Bool keepProcessing; + /* true once an internal or external PE reference has been encountered; + this includes the reference to an external subset */ + XML_Bool hasParamEntityRefs; + XML_Bool standalone; +#ifdef XML_DTD + /* indicates if external PE has been read */ + XML_Bool paramEntityRead; + HASH_TABLE paramEntities; +#endif /* XML_DTD */ + PREFIX defaultPrefix; + /* === scaffolding for building content model === */ + XML_Bool in_eldecl; + CONTENT_SCAFFOLD *scaffold; + unsigned contentStringLen; + unsigned scaffSize; + unsigned scaffCount; + int scaffLevel; + int *scaffIndex; +} DTD; + +typedef struct open_internal_entity { + const char *internalEventPtr; + const char *internalEventEndPtr; + struct open_internal_entity *next; + ENTITY *entity; + int startTagLevel; + XML_Bool betweenDecl; /* WFC: PE Between Declarations */ +} OPEN_INTERNAL_ENTITY; + +typedef enum XML_Error PTRCALL Processor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr); + +static Processor prologProcessor; +static Processor prologInitProcessor; +static Processor contentProcessor; +static Processor cdataSectionProcessor; +#ifdef XML_DTD +static Processor ignoreSectionProcessor; +static Processor externalParEntProcessor; +static Processor externalParEntInitProcessor; +static Processor entityValueProcessor; +static Processor entityValueInitProcessor; +#endif /* XML_DTD */ +static Processor epilogProcessor; +static Processor errorProcessor; +static Processor externalEntityInitProcessor; +static Processor externalEntityInitProcessor2; +static Processor externalEntityInitProcessor3; +static Processor externalEntityContentProcessor; +static Processor internalEntityProcessor; + +static enum XML_Error +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName); +static enum XML_Error +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, + const char *s, const char *next); +static enum XML_Error +initializeEncoding(XML_Parser parser); +static enum XML_Error +doProlog(XML_Parser parser, const ENCODING *enc, const char *s, + const char *end, int tok, const char *next, const char **nextPtr, + XML_Bool haveMore); +static enum XML_Error +processInternalEntity(XML_Parser parser, ENTITY *entity, + XML_Bool betweenDecl); +static enum XML_Error +doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, + const char *start, const char *end, const char **endPtr, + XML_Bool haveMore); +static enum XML_Error +doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore); +#ifdef XML_DTD +static enum XML_Error +doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore); +#endif /* XML_DTD */ + +static enum XML_Error +storeAtts(XML_Parser parser, const ENCODING *, const char *s, + TAG_NAME *tagNamePtr, BINDING **bindingsPtr); +static enum XML_Error +addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, + const XML_Char *uri, BINDING **bindingsPtr); +static int +defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, + XML_Bool isId, const XML_Char *dfltValue, XML_Parser parser); +static enum XML_Error +storeAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata, + const char *, const char *, STRING_POOL *); +static enum XML_Error +appendAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata, + const char *, const char *, STRING_POOL *); +static ATTRIBUTE_ID * +getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end); +static int +setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); +static enum XML_Error +storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end); +static int +reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static int +reportComment(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end); +static void +reportDefault(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end); + +static const XML_Char * getContext(XML_Parser parser); +static XML_Bool +setContext(XML_Parser parser, const XML_Char *context); + +static void FASTCALL normalizePublicId(XML_Char *s); + +static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms); +/* do not call if parentParser != NULL */ +static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms); +static void +dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms); +static int +dtdCopy(XML_Parser oldParser, + DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms); +static int +copyEntityTable(XML_Parser oldParser, + HASH_TABLE *, STRING_POOL *, const HASH_TABLE *); +static NAMED * +lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize); +static void FASTCALL +hashTableInit(HASH_TABLE *, const XML_Memory_Handling_Suite *ms); +static void FASTCALL hashTableClear(HASH_TABLE *); +static void FASTCALL hashTableDestroy(HASH_TABLE *); +static void FASTCALL +hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); +static NAMED * FASTCALL hashTableIterNext(HASH_TABLE_ITER *); + +static void FASTCALL +poolInit(STRING_POOL *, const XML_Memory_Handling_Suite *ms); +static void FASTCALL poolClear(STRING_POOL *); +static void FASTCALL poolDestroy(STRING_POOL *); +static XML_Char * +poolAppend(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); +static XML_Char * +poolStoreString(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); +static XML_Bool FASTCALL poolGrow(STRING_POOL *pool); +static const XML_Char * FASTCALL +poolCopyString(STRING_POOL *pool, const XML_Char *s); +static const XML_Char * +poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n); +static const XML_Char * FASTCALL +poolAppendString(STRING_POOL *pool, const XML_Char *s); + +static int FASTCALL nextScaffoldPart(XML_Parser parser); +static XML_Content * build_model(XML_Parser parser); +static ELEMENT_TYPE * +getElementType(XML_Parser parser, const ENCODING *enc, + const char *ptr, const char *end); + +static unsigned long generate_hash_secret_salt(void); +static XML_Bool startParsing(XML_Parser parser); + +static XML_Parser +parserCreate(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep, + DTD *dtd); + +static void +parserInit(XML_Parser parser, const XML_Char *encodingName); + +#define poolStart(pool) ((pool)->start) +#define poolEnd(pool) ((pool)->ptr) +#define poolLength(pool) ((pool)->ptr - (pool)->start) +#define poolChop(pool) ((void)--(pool->ptr)) +#define poolLastChar(pool) (((pool)->ptr)[-1]) +#define poolDiscard(pool) ((pool)->ptr = (pool)->start) +#define poolFinish(pool) ((pool)->start = (pool)->ptr) +#define poolAppendChar(pool, c) \ + (((pool)->ptr == (pool)->end && !poolGrow(pool)) \ + ? 0 \ + : ((*((pool)->ptr)++ = c), 1)) + +struct XML_ParserStruct { + /* The first member must be userData so that the XML_GetUserData + macro works. */ + void *m_userData; + void *m_handlerArg; + char *m_buffer; + const XML_Memory_Handling_Suite m_mem; + /* first character to be parsed */ + const char *m_bufferPtr; + /* past last character to be parsed */ + char *m_bufferEnd; + /* allocated end of buffer */ + const char *m_bufferLim; + XML_Index m_parseEndByteIndex; + const char *m_parseEndPtr; + XML_Char *m_dataBuf; + XML_Char *m_dataBufEnd; + XML_StartElementHandler m_startElementHandler; + XML_EndElementHandler m_endElementHandler; + XML_CharacterDataHandler m_characterDataHandler; + XML_ProcessingInstructionHandler m_processingInstructionHandler; + XML_CommentHandler m_commentHandler; + XML_StartCdataSectionHandler m_startCdataSectionHandler; + XML_EndCdataSectionHandler m_endCdataSectionHandler; + XML_DefaultHandler m_defaultHandler; + XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler; + XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler; + XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler; + XML_NotationDeclHandler m_notationDeclHandler; + XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler; + XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler; + XML_NotStandaloneHandler m_notStandaloneHandler; + XML_ExternalEntityRefHandler m_externalEntityRefHandler; + XML_Parser m_externalEntityRefHandlerArg; + XML_SkippedEntityHandler m_skippedEntityHandler; + XML_UnknownEncodingHandler m_unknownEncodingHandler; + XML_ElementDeclHandler m_elementDeclHandler; + XML_AttlistDeclHandler m_attlistDeclHandler; + XML_EntityDeclHandler m_entityDeclHandler; + XML_XmlDeclHandler m_xmlDeclHandler; + const ENCODING *m_encoding; + INIT_ENCODING m_initEncoding; + const ENCODING *m_internalEncoding; + const XML_Char *m_protocolEncodingName; + XML_Bool m_ns; + XML_Bool m_ns_triplets; + void *m_unknownEncodingMem; + void *m_unknownEncodingData; + void *m_unknownEncodingHandlerData; + void (XMLCALL *m_unknownEncodingRelease)(void *); + PROLOG_STATE m_prologState; + Processor *m_processor; + enum XML_Error m_errorCode; + const char *m_eventPtr; + const char *m_eventEndPtr; + const char *m_positionPtr; + OPEN_INTERNAL_ENTITY *m_openInternalEntities; + OPEN_INTERNAL_ENTITY *m_freeInternalEntities; + XML_Bool m_defaultExpandInternalEntities; + int m_tagLevel; + ENTITY *m_declEntity; + const XML_Char *m_doctypeName; + const XML_Char *m_doctypeSysid; + const XML_Char *m_doctypePubid; + const XML_Char *m_declAttributeType; + const XML_Char *m_declNotationName; + const XML_Char *m_declNotationPublicId; + ELEMENT_TYPE *m_declElementType; + ATTRIBUTE_ID *m_declAttributeId; + XML_Bool m_declAttributeIsCdata; + XML_Bool m_declAttributeIsId; + DTD *m_dtd; + const XML_Char *m_curBase; + TAG *m_tagStack; + TAG *m_freeTagList; + BINDING *m_inheritedBindings; + BINDING *m_freeBindingList; + int m_attsSize; + int m_nSpecifiedAtts; + int m_idAttIndex; + ATTRIBUTE *m_atts; + NS_ATT *m_nsAtts; + unsigned long m_nsAttsVersion; + unsigned char m_nsAttsPower; +#ifdef XML_ATTR_INFO + XML_AttrInfo *m_attInfo; +#endif + POSITION m_position; + STRING_POOL m_tempPool; + STRING_POOL m_temp2Pool; + char *m_groupConnector; + unsigned int m_groupSize; + XML_Char m_namespaceSeparator; + XML_Parser m_parentParser; + XML_ParsingStatus m_parsingStatus; +#ifdef XML_DTD + XML_Bool m_isParamEntity; + XML_Bool m_useForeignDTD; + enum XML_ParamEntityParsing m_paramEntityParsing; +#endif + unsigned long m_hash_secret_salt; +}; + +#define MALLOC(s) (parser->m_mem.malloc_fcn((s))) +#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s))) +#define FREE(p) (parser->m_mem.free_fcn((p))) + +#define userData (parser->m_userData) +#define handlerArg (parser->m_handlerArg) +#define startElementHandler (parser->m_startElementHandler) +#define endElementHandler (parser->m_endElementHandler) +#define characterDataHandler (parser->m_characterDataHandler) +#define processingInstructionHandler \ + (parser->m_processingInstructionHandler) +#define commentHandler (parser->m_commentHandler) +#define startCdataSectionHandler \ + (parser->m_startCdataSectionHandler) +#define endCdataSectionHandler (parser->m_endCdataSectionHandler) +#define defaultHandler (parser->m_defaultHandler) +#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler) +#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler) +#define unparsedEntityDeclHandler \ + (parser->m_unparsedEntityDeclHandler) +#define notationDeclHandler (parser->m_notationDeclHandler) +#define startNamespaceDeclHandler \ + (parser->m_startNamespaceDeclHandler) +#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler) +#define notStandaloneHandler (parser->m_notStandaloneHandler) +#define externalEntityRefHandler \ + (parser->m_externalEntityRefHandler) +#define externalEntityRefHandlerArg \ + (parser->m_externalEntityRefHandlerArg) +#define internalEntityRefHandler \ + (parser->m_internalEntityRefHandler) +#define skippedEntityHandler (parser->m_skippedEntityHandler) +#define unknownEncodingHandler (parser->m_unknownEncodingHandler) +#define elementDeclHandler (parser->m_elementDeclHandler) +#define attlistDeclHandler (parser->m_attlistDeclHandler) +#define entityDeclHandler (parser->m_entityDeclHandler) +#define xmlDeclHandler (parser->m_xmlDeclHandler) +#define encoding (parser->m_encoding) +#define initEncoding (parser->m_initEncoding) +#define internalEncoding (parser->m_internalEncoding) +#define unknownEncodingMem (parser->m_unknownEncodingMem) +#define unknownEncodingData (parser->m_unknownEncodingData) +#define unknownEncodingHandlerData \ + (parser->m_unknownEncodingHandlerData) +#define unknownEncodingRelease (parser->m_unknownEncodingRelease) +#define protocolEncodingName (parser->m_protocolEncodingName) +#define ns (parser->m_ns) +#define ns_triplets (parser->m_ns_triplets) +#define prologState (parser->m_prologState) +#define processor (parser->m_processor) +#define errorCode (parser->m_errorCode) +#define eventPtr (parser->m_eventPtr) +#define eventEndPtr (parser->m_eventEndPtr) +#define positionPtr (parser->m_positionPtr) +#define position (parser->m_position) +#define openInternalEntities (parser->m_openInternalEntities) +#define freeInternalEntities (parser->m_freeInternalEntities) +#define defaultExpandInternalEntities \ + (parser->m_defaultExpandInternalEntities) +#define tagLevel (parser->m_tagLevel) +#define buffer (parser->m_buffer) +#define bufferPtr (parser->m_bufferPtr) +#define bufferEnd (parser->m_bufferEnd) +#define parseEndByteIndex (parser->m_parseEndByteIndex) +#define parseEndPtr (parser->m_parseEndPtr) +#define bufferLim (parser->m_bufferLim) +#define dataBuf (parser->m_dataBuf) +#define dataBufEnd (parser->m_dataBufEnd) +#define _dtd (parser->m_dtd) +#define curBase (parser->m_curBase) +#define declEntity (parser->m_declEntity) +#define doctypeName (parser->m_doctypeName) +#define doctypeSysid (parser->m_doctypeSysid) +#define doctypePubid (parser->m_doctypePubid) +#define declAttributeType (parser->m_declAttributeType) +#define declNotationName (parser->m_declNotationName) +#define declNotationPublicId (parser->m_declNotationPublicId) +#define declElementType (parser->m_declElementType) +#define declAttributeId (parser->m_declAttributeId) +#define declAttributeIsCdata (parser->m_declAttributeIsCdata) +#define declAttributeIsId (parser->m_declAttributeIsId) +#define freeTagList (parser->m_freeTagList) +#define freeBindingList (parser->m_freeBindingList) +#define inheritedBindings (parser->m_inheritedBindings) +#define tagStack (parser->m_tagStack) +#define atts (parser->m_atts) +#define attsSize (parser->m_attsSize) +#define nSpecifiedAtts (parser->m_nSpecifiedAtts) +#define idAttIndex (parser->m_idAttIndex) +#define nsAtts (parser->m_nsAtts) +#define nsAttsVersion (parser->m_nsAttsVersion) +#define nsAttsPower (parser->m_nsAttsPower) +#define attInfo (parser->m_attInfo) +#define tempPool (parser->m_tempPool) +#define temp2Pool (parser->m_temp2Pool) +#define groupConnector (parser->m_groupConnector) +#define groupSize (parser->m_groupSize) +#define namespaceSeparator (parser->m_namespaceSeparator) +#define parentParser (parser->m_parentParser) +#define ps_parsing (parser->m_parsingStatus.parsing) +#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer) +#ifdef XML_DTD +#define isParamEntity (parser->m_isParamEntity) +#define useForeignDTD (parser->m_useForeignDTD) +#define paramEntityParsing (parser->m_paramEntityParsing) +#endif /* XML_DTD */ +#define hash_secret_salt (parser->m_hash_secret_salt) + +XML_Parser XMLCALL +XML_ParserCreate(const XML_Char *encodingName) +{ + return XML_ParserCreate_MM(encodingName, NULL, NULL); +} + +XML_Parser XMLCALL +XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) +{ + XML_Char tmp[2]; + *tmp = nsSep; + return XML_ParserCreate_MM(encodingName, NULL, tmp); +} + +static const XML_Char implicitContext[] = { + ASCII_x, ASCII_m, ASCII_l, ASCII_EQUALS, ASCII_h, ASCII_t, ASCII_t, ASCII_p, + ASCII_COLON, ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, + ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, ASCII_g, + ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, ASCII_SLASH, ASCII_1, ASCII_9, + ASCII_9, ASCII_8, ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, ASCII_e, + ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, '\0' +}; + +static unsigned long +generate_hash_secret_salt(void) +{ + unsigned int seed = time(NULL) % UINT_MAX; + srand(seed); + return rand(); +} + +static XML_Bool /* only valid for root parser */ +startParsing(XML_Parser parser) +{ + /* hash functions must be initialized before setContext() is called */ + if (hash_secret_salt == 0) + hash_secret_salt = generate_hash_secret_salt(); + if (ns) { + /* implicit context only set for root parser, since child + parsers (i.e. external entity parsers) will inherit it + */ + return setContext(parser, implicitContext); + } + return XML_TRUE; +} + +XML_Parser XMLCALL +XML_ParserCreate_MM(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep) +{ + return parserCreate(encodingName, memsuite, nameSep, NULL); +} + +static XML_Parser +parserCreate(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep, + DTD *dtd) +{ + XML_Parser parser; + + if (memsuite) { + XML_Memory_Handling_Suite *mtemp; + parser = (XML_Parser) + memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); + if (parser != NULL) { + mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); + mtemp->malloc_fcn = memsuite->malloc_fcn; + mtemp->realloc_fcn = memsuite->realloc_fcn; + mtemp->free_fcn = memsuite->free_fcn; + } + } + else { + XML_Memory_Handling_Suite *mtemp; + parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct)); + if (parser != NULL) { + mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); + mtemp->malloc_fcn = malloc; + mtemp->realloc_fcn = realloc; + mtemp->free_fcn = free; + } + } + + if (!parser) + return parser; + + buffer = NULL; + bufferLim = NULL; + + attsSize = INIT_ATTS_SIZE; + atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE)); + if (atts == NULL) { + FREE(parser); + return NULL; + } +#ifdef XML_ATTR_INFO + attInfo = (XML_AttrInfo*)MALLOC(attsSize * sizeof(XML_AttrInfo)); + if (attInfo == NULL) { + FREE(atts); + FREE(parser); + return NULL; + } +#endif + dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char)); + if (dataBuf == NULL) { + FREE(atts); +#ifdef XML_ATTR_INFO + FREE(attInfo); +#endif + FREE(parser); + return NULL; + } + dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE; + + if (dtd) + _dtd = dtd; + else { + _dtd = dtdCreate(&parser->m_mem); + if (_dtd == NULL) { + FREE(dataBuf); + FREE(atts); +#ifdef XML_ATTR_INFO + FREE(attInfo); +#endif + FREE(parser); + return NULL; + } + } + + freeBindingList = NULL; + freeTagList = NULL; + freeInternalEntities = NULL; + + groupSize = 0; + groupConnector = NULL; + + unknownEncodingHandler = NULL; + unknownEncodingHandlerData = NULL; + + namespaceSeparator = ASCII_EXCL; + ns = XML_FALSE; + ns_triplets = XML_FALSE; + + nsAtts = NULL; + nsAttsVersion = 0; + nsAttsPower = 0; + + poolInit(&tempPool, &(parser->m_mem)); + poolInit(&temp2Pool, &(parser->m_mem)); + parserInit(parser, encodingName); + + if (encodingName && !protocolEncodingName) { + XML_ParserFree(parser); + return NULL; + } + + if (nameSep) { + ns = XML_TRUE; + internalEncoding = XmlGetInternalEncodingNS(); + namespaceSeparator = *nameSep; + } + else { + internalEncoding = XmlGetInternalEncoding(); + } + + return parser; +} + +static void +parserInit(XML_Parser parser, const XML_Char *encodingName) +{ + processor = prologInitProcessor; + XmlPrologStateInit(&prologState); + protocolEncodingName = (encodingName != NULL + ? poolCopyString(&tempPool, encodingName) + : NULL); + curBase = NULL; + XmlInitEncoding(&initEncoding, &encoding, 0); + userData = NULL; + handlerArg = NULL; + startElementHandler = NULL; + endElementHandler = NULL; + characterDataHandler = NULL; + processingInstructionHandler = NULL; + commentHandler = NULL; + startCdataSectionHandler = NULL; + endCdataSectionHandler = NULL; + defaultHandler = NULL; + startDoctypeDeclHandler = NULL; + endDoctypeDeclHandler = NULL; + unparsedEntityDeclHandler = NULL; + notationDeclHandler = NULL; + startNamespaceDeclHandler = NULL; + endNamespaceDeclHandler = NULL; + notStandaloneHandler = NULL; + externalEntityRefHandler = NULL; + externalEntityRefHandlerArg = parser; + skippedEntityHandler = NULL; + elementDeclHandler = NULL; + attlistDeclHandler = NULL; + entityDeclHandler = NULL; + xmlDeclHandler = NULL; + bufferPtr = buffer; + bufferEnd = buffer; + parseEndByteIndex = 0; + parseEndPtr = NULL; + declElementType = NULL; + declAttributeId = NULL; + declEntity = NULL; + doctypeName = NULL; + doctypeSysid = NULL; + doctypePubid = NULL; + declAttributeType = NULL; + declNotationName = NULL; + declNotationPublicId = NULL; + declAttributeIsCdata = XML_FALSE; + declAttributeIsId = XML_FALSE; + memset(&position, 0, sizeof(POSITION)); + errorCode = XML_ERROR_NONE; + eventPtr = NULL; + eventEndPtr = NULL; + positionPtr = NULL; + openInternalEntities = NULL; + defaultExpandInternalEntities = XML_TRUE; + tagLevel = 0; + tagStack = NULL; + inheritedBindings = NULL; + nSpecifiedAtts = 0; + unknownEncodingMem = NULL; + unknownEncodingRelease = NULL; + unknownEncodingData = NULL; + parentParser = NULL; + ps_parsing = XML_INITIALIZED; +#ifdef XML_DTD + isParamEntity = XML_FALSE; + useForeignDTD = XML_FALSE; + paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; +#endif + hash_secret_salt = 0; +} + +/* moves list of bindings to freeBindingList */ +static void FASTCALL +moveToFreeBindingList(XML_Parser parser, BINDING *bindings) +{ + while (bindings) { + BINDING *b = bindings; + bindings = bindings->nextTagBinding; + b->nextTagBinding = freeBindingList; + freeBindingList = b; + } +} + +XML_Bool XMLCALL +XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) +{ + TAG *tStk; + OPEN_INTERNAL_ENTITY *openEntityList; + if (parentParser) + return XML_FALSE; + /* move tagStack to freeTagList */ + tStk = tagStack; + while (tStk) { + TAG *tag = tStk; + tStk = tStk->parent; + tag->parent = freeTagList; + moveToFreeBindingList(parser, tag->bindings); + tag->bindings = NULL; + freeTagList = tag; + } + /* move openInternalEntities to freeInternalEntities */ + openEntityList = openInternalEntities; + while (openEntityList) { + OPEN_INTERNAL_ENTITY *openEntity = openEntityList; + openEntityList = openEntity->next; + openEntity->next = freeInternalEntities; + freeInternalEntities = openEntity; + } + moveToFreeBindingList(parser, inheritedBindings); + FREE(unknownEncodingMem); + if (unknownEncodingRelease) + unknownEncodingRelease(unknownEncodingData); + poolClear(&tempPool); + poolClear(&temp2Pool); + parserInit(parser, encodingName); + dtdReset(_dtd, &parser->m_mem); + return XML_TRUE; +} + +enum XML_Status XMLCALL +XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) +{ + /* Block after XML_Parse()/XML_ParseBuffer() has been called. + XXX There's no way for the caller to determine which of the + XXX possible error cases caused the XML_STATUS_ERROR return. + */ + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + return XML_STATUS_ERROR; + if (encodingName == NULL) + protocolEncodingName = NULL; + else { + protocolEncodingName = poolCopyString(&tempPool, encodingName); + if (!protocolEncodingName) + return XML_STATUS_ERROR; + } + return XML_STATUS_OK; +} + +XML_Parser XMLCALL +XML_ExternalEntityParserCreate(XML_Parser oldParser, + const XML_Char *context, + const XML_Char *encodingName) +{ + XML_Parser parser = oldParser; + DTD *newDtd = NULL; + DTD *oldDtd = _dtd; + XML_StartElementHandler oldStartElementHandler = startElementHandler; + XML_EndElementHandler oldEndElementHandler = endElementHandler; + XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler; + XML_ProcessingInstructionHandler oldProcessingInstructionHandler + = processingInstructionHandler; + XML_CommentHandler oldCommentHandler = commentHandler; + XML_StartCdataSectionHandler oldStartCdataSectionHandler + = startCdataSectionHandler; + XML_EndCdataSectionHandler oldEndCdataSectionHandler + = endCdataSectionHandler; + XML_DefaultHandler oldDefaultHandler = defaultHandler; + XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler + = unparsedEntityDeclHandler; + XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler; + XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler + = startNamespaceDeclHandler; + XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler + = endNamespaceDeclHandler; + XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler; + XML_ExternalEntityRefHandler oldExternalEntityRefHandler + = externalEntityRefHandler; + XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler; + XML_UnknownEncodingHandler oldUnknownEncodingHandler + = unknownEncodingHandler; + XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler; + XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler; + XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler; + XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler; + ELEMENT_TYPE * oldDeclElementType = declElementType; + + void *oldUserData = userData; + void *oldHandlerArg = handlerArg; + XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities; + XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg; +#ifdef XML_DTD + enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing; + int oldInEntityValue = prologState.inEntityValue; +#endif + XML_Bool oldns_triplets = ns_triplets; + /* Note that the new parser shares the same hash secret as the old + parser, so that dtdCopy and copyEntityTable can lookup values + from hash tables associated with either parser without us having + to worry which hash secrets each table has. + */ + unsigned long oldhash_secret_salt = hash_secret_salt; + +#ifdef XML_DTD + if (!context) + newDtd = oldDtd; +#endif /* XML_DTD */ + + /* Note that the magical uses of the pre-processor to make field + access look more like C++ require that `parser' be overwritten + here. This makes this function more painful to follow than it + would be otherwise. + */ + if (ns) { + XML_Char tmp[2]; + *tmp = namespaceSeparator; + parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd); + } + else { + parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd); + } + + if (!parser) + return NULL; + + startElementHandler = oldStartElementHandler; + endElementHandler = oldEndElementHandler; + characterDataHandler = oldCharacterDataHandler; + processingInstructionHandler = oldProcessingInstructionHandler; + commentHandler = oldCommentHandler; + startCdataSectionHandler = oldStartCdataSectionHandler; + endCdataSectionHandler = oldEndCdataSectionHandler; + defaultHandler = oldDefaultHandler; + unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler; + notationDeclHandler = oldNotationDeclHandler; + startNamespaceDeclHandler = oldStartNamespaceDeclHandler; + endNamespaceDeclHandler = oldEndNamespaceDeclHandler; + notStandaloneHandler = oldNotStandaloneHandler; + externalEntityRefHandler = oldExternalEntityRefHandler; + skippedEntityHandler = oldSkippedEntityHandler; + unknownEncodingHandler = oldUnknownEncodingHandler; + elementDeclHandler = oldElementDeclHandler; + attlistDeclHandler = oldAttlistDeclHandler; + entityDeclHandler = oldEntityDeclHandler; + xmlDeclHandler = oldXmlDeclHandler; + declElementType = oldDeclElementType; + userData = oldUserData; + if (oldUserData == oldHandlerArg) + handlerArg = userData; + else + handlerArg = parser; + if (oldExternalEntityRefHandlerArg != oldParser) + externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg; + defaultExpandInternalEntities = oldDefaultExpandInternalEntities; + ns_triplets = oldns_triplets; + hash_secret_salt = oldhash_secret_salt; + parentParser = oldParser; +#ifdef XML_DTD + paramEntityParsing = oldParamEntityParsing; + prologState.inEntityValue = oldInEntityValue; + if (context) { +#endif /* XML_DTD */ + if (!dtdCopy(oldParser, _dtd, oldDtd, &parser->m_mem) + || !setContext(parser, context)) { + XML_ParserFree(parser); + return NULL; + } + processor = externalEntityInitProcessor; +#ifdef XML_DTD + } + else { + /* The DTD instance referenced by _dtd is shared between the document's + root parser and external PE parsers, therefore one does not need to + call setContext. In addition, one also *must* not call setContext, + because this would overwrite existing prefix->binding pointers in + _dtd with ones that get destroyed with the external PE parser. + This would leave those prefixes with dangling pointers. + */ + isParamEntity = XML_TRUE; + XmlPrologStateInitExternalEntity(&prologState); + processor = externalParEntInitProcessor; + } +#endif /* XML_DTD */ + return parser; +} + +static void FASTCALL +destroyBindings(BINDING *bindings, XML_Parser parser) +{ + for (;;) { + BINDING *b = bindings; + if (!b) + break; + bindings = b->nextTagBinding; + FREE(b->uri); + FREE(b); + } +} + +void XMLCALL +XML_ParserFree(XML_Parser parser) +{ + TAG *tagList; + OPEN_INTERNAL_ENTITY *entityList; + if (parser == NULL) + return; + /* free tagStack and freeTagList */ + tagList = tagStack; + for (;;) { + TAG *p; + if (tagList == NULL) { + if (freeTagList == NULL) + break; + tagList = freeTagList; + freeTagList = NULL; + } + p = tagList; + tagList = tagList->parent; + FREE(p->buf); + destroyBindings(p->bindings, parser); + FREE(p); + } + /* free openInternalEntities and freeInternalEntities */ + entityList = openInternalEntities; + for (;;) { + OPEN_INTERNAL_ENTITY *openEntity; + if (entityList == NULL) { + if (freeInternalEntities == NULL) + break; + entityList = freeInternalEntities; + freeInternalEntities = NULL; + } + openEntity = entityList; + entityList = entityList->next; + FREE(openEntity); + } + + destroyBindings(freeBindingList, parser); + destroyBindings(inheritedBindings, parser); + poolDestroy(&tempPool); + poolDestroy(&temp2Pool); +#ifdef XML_DTD + /* external parameter entity parsers share the DTD structure + parser->m_dtd with the root parser, so we must not destroy it + */ + if (!isParamEntity && _dtd) +#else + if (_dtd) +#endif /* XML_DTD */ + dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem); + FREE((void *)atts); +#ifdef XML_ATTR_INFO + FREE((void *)attInfo); +#endif + FREE(groupConnector); + FREE(buffer); + FREE(dataBuf); + FREE(nsAtts); + FREE(unknownEncodingMem); + if (unknownEncodingRelease) + unknownEncodingRelease(unknownEncodingData); + FREE(parser); +} + +void XMLCALL +XML_UseParserAsHandlerArg(XML_Parser parser) +{ + handlerArg = parser; +} + +enum XML_Error XMLCALL +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) +{ +#ifdef XML_DTD + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; + useForeignDTD = useDTD; + return XML_ERROR_NONE; +#else + return XML_ERROR_FEATURE_REQUIRES_XML_DTD; +#endif +} + +void XMLCALL +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) +{ + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + return; + ns_triplets = do_nst ? XML_TRUE : XML_FALSE; +} + +void XMLCALL +XML_SetUserData(XML_Parser parser, void *p) +{ + if (handlerArg == userData) + handlerArg = userData = p; + else + userData = p; +} + +enum XML_Status XMLCALL +XML_SetBase(XML_Parser parser, const XML_Char *p) +{ + if (p) { + p = poolCopyString(&_dtd->pool, p); + if (!p) + return XML_STATUS_ERROR; + curBase = p; + } + else + curBase = NULL; + return XML_STATUS_OK; +} + +const XML_Char * XMLCALL +XML_GetBase(XML_Parser parser) +{ + return curBase; +} + +int XMLCALL +XML_GetSpecifiedAttributeCount(XML_Parser parser) +{ + return nSpecifiedAtts; +} + +int XMLCALL +XML_GetIdAttributeIndex(XML_Parser parser) +{ + return idAttIndex; +} + +#ifdef XML_ATTR_INFO +const XML_AttrInfo * XMLCALL +XML_GetAttributeInfo(XML_Parser parser) +{ + return attInfo; +} +#endif + +void XMLCALL +XML_SetElementHandler(XML_Parser parser, + XML_StartElementHandler start, + XML_EndElementHandler end) +{ + startElementHandler = start; + endElementHandler = end; +} + +void XMLCALL +XML_SetStartElementHandler(XML_Parser parser, + XML_StartElementHandler start) { + startElementHandler = start; +} + +void XMLCALL +XML_SetEndElementHandler(XML_Parser parser, + XML_EndElementHandler end) { + endElementHandler = end; +} + +void XMLCALL +XML_SetCharacterDataHandler(XML_Parser parser, + XML_CharacterDataHandler handler) +{ + characterDataHandler = handler; +} + +void XMLCALL +XML_SetProcessingInstructionHandler(XML_Parser parser, + XML_ProcessingInstructionHandler handler) +{ + processingInstructionHandler = handler; +} + +void XMLCALL +XML_SetCommentHandler(XML_Parser parser, + XML_CommentHandler handler) +{ + commentHandler = handler; +} + +void XMLCALL +XML_SetCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end) +{ + startCdataSectionHandler = start; + endCdataSectionHandler = end; +} + +void XMLCALL +XML_SetStartCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start) { + startCdataSectionHandler = start; +} + +void XMLCALL +XML_SetEndCdataSectionHandler(XML_Parser parser, + XML_EndCdataSectionHandler end) { + endCdataSectionHandler = end; +} + +void XMLCALL +XML_SetDefaultHandler(XML_Parser parser, + XML_DefaultHandler handler) +{ + defaultHandler = handler; + defaultExpandInternalEntities = XML_FALSE; +} + +void XMLCALL +XML_SetDefaultHandlerExpand(XML_Parser parser, + XML_DefaultHandler handler) +{ + defaultHandler = handler; + defaultExpandInternalEntities = XML_TRUE; +} + +void XMLCALL +XML_SetDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end) +{ + startDoctypeDeclHandler = start; + endDoctypeDeclHandler = end; +} + +void XMLCALL +XML_SetStartDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start) { + startDoctypeDeclHandler = start; +} + +void XMLCALL +XML_SetEndDoctypeDeclHandler(XML_Parser parser, + XML_EndDoctypeDeclHandler end) { + endDoctypeDeclHandler = end; +} + +void XMLCALL +XML_SetUnparsedEntityDeclHandler(XML_Parser parser, + XML_UnparsedEntityDeclHandler handler) +{ + unparsedEntityDeclHandler = handler; +} + +void XMLCALL +XML_SetNotationDeclHandler(XML_Parser parser, + XML_NotationDeclHandler handler) +{ + notationDeclHandler = handler; +} + +void XMLCALL +XML_SetNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end) +{ + startNamespaceDeclHandler = start; + endNamespaceDeclHandler = end; +} + +void XMLCALL +XML_SetStartNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start) { + startNamespaceDeclHandler = start; +} + +void XMLCALL +XML_SetEndNamespaceDeclHandler(XML_Parser parser, + XML_EndNamespaceDeclHandler end) { + endNamespaceDeclHandler = end; +} + +void XMLCALL +XML_SetNotStandaloneHandler(XML_Parser parser, + XML_NotStandaloneHandler handler) +{ + notStandaloneHandler = handler; +} + +void XMLCALL +XML_SetExternalEntityRefHandler(XML_Parser parser, + XML_ExternalEntityRefHandler handler) +{ + externalEntityRefHandler = handler; +} + +void XMLCALL +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) +{ + if (arg) + externalEntityRefHandlerArg = (XML_Parser)arg; + else + externalEntityRefHandlerArg = parser; +} + +void XMLCALL +XML_SetSkippedEntityHandler(XML_Parser parser, + XML_SkippedEntityHandler handler) +{ + skippedEntityHandler = handler; +} + +void XMLCALL +XML_SetUnknownEncodingHandler(XML_Parser parser, + XML_UnknownEncodingHandler handler, + void *data) +{ + unknownEncodingHandler = handler; + unknownEncodingHandlerData = data; +} + +void XMLCALL +XML_SetElementDeclHandler(XML_Parser parser, + XML_ElementDeclHandler eldecl) +{ + elementDeclHandler = eldecl; +} + +void XMLCALL +XML_SetAttlistDeclHandler(XML_Parser parser, + XML_AttlistDeclHandler attdecl) +{ + attlistDeclHandler = attdecl; +} + +void XMLCALL +XML_SetEntityDeclHandler(XML_Parser parser, + XML_EntityDeclHandler handler) +{ + entityDeclHandler = handler; +} + +void XMLCALL +XML_SetXmlDeclHandler(XML_Parser parser, + XML_XmlDeclHandler handler) { + xmlDeclHandler = handler; +} + +int XMLCALL +XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing peParsing) +{ + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + return 0; +#ifdef XML_DTD + paramEntityParsing = peParsing; + return 1; +#else + return peParsing == XML_PARAM_ENTITY_PARSING_NEVER; +#endif +} + +int XMLCALL +XML_SetHashSalt(XML_Parser parser, + unsigned long hash_salt) +{ + /* block after XML_Parse()/XML_ParseBuffer() has been called */ + if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + return 0; + hash_secret_salt = hash_salt; + return 1; +} + +enum XML_Status XMLCALL +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) +{ + switch (ps_parsing) { + case XML_SUSPENDED: + errorCode = XML_ERROR_SUSPENDED; + return XML_STATUS_ERROR; + case XML_FINISHED: + errorCode = XML_ERROR_FINISHED; + return XML_STATUS_ERROR; + case XML_INITIALIZED: + if (parentParser == NULL && !startParsing(parser)) { + errorCode = XML_ERROR_NO_MEMORY; + return XML_STATUS_ERROR; + } + default: + ps_parsing = XML_PARSING; + } + + if (len == 0) { + ps_finalBuffer = (XML_Bool)isFinal; + if (!isFinal) + return XML_STATUS_OK; + positionPtr = bufferPtr; + parseEndPtr = bufferEnd; + + /* If data are left over from last buffer, and we now know that these + data are the final chunk of input, then we have to check them again + to detect errors based on that fact. + */ + errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); + + if (errorCode == XML_ERROR_NONE) { + switch (ps_parsing) { + case XML_SUSPENDED: + XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); + positionPtr = bufferPtr; + return XML_STATUS_SUSPENDED; + case XML_INITIALIZED: + case XML_PARSING: + ps_parsing = XML_FINISHED; + /* fall through */ + default: + return XML_STATUS_OK; + } + } + eventEndPtr = eventPtr; + processor = errorProcessor; + return XML_STATUS_ERROR; + } +#ifndef XML_CONTEXT_BYTES + else if (bufferPtr == bufferEnd) { + const char *end; + int nLeftOver; + enum XML_Error result; + parseEndByteIndex += len; + positionPtr = s; + ps_finalBuffer = (XML_Bool)isFinal; + + errorCode = processor(parser, s, parseEndPtr = s + len, &end); + + if (errorCode != XML_ERROR_NONE) { + eventEndPtr = eventPtr; + processor = errorProcessor; + return XML_STATUS_ERROR; + } + else { + switch (ps_parsing) { + case XML_SUSPENDED: + result = XML_STATUS_SUSPENDED; + break; + case XML_INITIALIZED: + case XML_PARSING: + if (isFinal) { + ps_parsing = XML_FINISHED; + return XML_STATUS_OK; + } + /* fall through */ + default: + result = XML_STATUS_OK; + } + } + + XmlUpdatePosition(encoding, positionPtr, end, &position); + nLeftOver = s + len - end; + if (nLeftOver) { + if (buffer == NULL || nLeftOver > bufferLim - buffer) { + /* FIXME avoid integer overflow */ + char *temp; + temp = (buffer == NULL + ? (char *)MALLOC(len * 2) + : (char *)REALLOC(buffer, len * 2)); + if (temp == NULL) { + errorCode = XML_ERROR_NO_MEMORY; + eventPtr = eventEndPtr = NULL; + processor = errorProcessor; + return XML_STATUS_ERROR; + } + buffer = temp; + bufferLim = buffer + len * 2; + } + memcpy(buffer, end, nLeftOver); + } + bufferPtr = buffer; + bufferEnd = buffer + nLeftOver; + positionPtr = bufferPtr; + parseEndPtr = bufferEnd; + eventPtr = bufferPtr; + eventEndPtr = bufferPtr; + return result; + } +#endif /* not defined XML_CONTEXT_BYTES */ + else { + void *buff = XML_GetBuffer(parser, len); + if (buff == NULL) + return XML_STATUS_ERROR; + else { + memcpy(buff, s, len); + return XML_ParseBuffer(parser, len, isFinal); + } + } +} + +enum XML_Status XMLCALL +XML_ParseBuffer(XML_Parser parser, int len, int isFinal) +{ + const char *start; + enum XML_Status result = XML_STATUS_OK; + + switch (ps_parsing) { + case XML_SUSPENDED: + errorCode = XML_ERROR_SUSPENDED; + return XML_STATUS_ERROR; + case XML_FINISHED: + errorCode = XML_ERROR_FINISHED; + return XML_STATUS_ERROR; + case XML_INITIALIZED: + if (parentParser == NULL && !startParsing(parser)) { + errorCode = XML_ERROR_NO_MEMORY; + return XML_STATUS_ERROR; + } + default: + ps_parsing = XML_PARSING; + } + + start = bufferPtr; + positionPtr = start; + bufferEnd += len; + parseEndPtr = bufferEnd; + parseEndByteIndex += len; + ps_finalBuffer = (XML_Bool)isFinal; + + errorCode = processor(parser, start, parseEndPtr, &bufferPtr); + + if (errorCode != XML_ERROR_NONE) { + eventEndPtr = eventPtr; + processor = errorProcessor; + return XML_STATUS_ERROR; + } + else { + switch (ps_parsing) { + case XML_SUSPENDED: + result = XML_STATUS_SUSPENDED; + break; + case XML_INITIALIZED: + case XML_PARSING: + if (isFinal) { + ps_parsing = XML_FINISHED; + return result; + } + default: ; /* should not happen */ + } + } + + XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); + positionPtr = bufferPtr; + return result; +} + +void * XMLCALL +XML_GetBuffer(XML_Parser parser, int len) +{ + switch (ps_parsing) { + case XML_SUSPENDED: + errorCode = XML_ERROR_SUSPENDED; + return NULL; + case XML_FINISHED: + errorCode = XML_ERROR_FINISHED; + return NULL; + default: ; + } + + if (len > bufferLim - bufferEnd) { + /* FIXME avoid integer overflow */ + int neededSize = len + (int)(bufferEnd - bufferPtr); +#ifdef XML_CONTEXT_BYTES + int keep = (int)(bufferPtr - buffer); + + if (keep > XML_CONTEXT_BYTES) + keep = XML_CONTEXT_BYTES; + neededSize += keep; +#endif /* defined XML_CONTEXT_BYTES */ + if (neededSize <= bufferLim - buffer) { +#ifdef XML_CONTEXT_BYTES + if (keep < bufferPtr - buffer) { + int offset = (int)(bufferPtr - buffer) - keep; + memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep); + bufferEnd -= offset; + bufferPtr -= offset; + } +#else + memmove(buffer, bufferPtr, bufferEnd - bufferPtr); + bufferEnd = buffer + (bufferEnd - bufferPtr); + bufferPtr = buffer; +#endif /* not defined XML_CONTEXT_BYTES */ + } + else { + char *newBuf; + int bufferSize = (int)(bufferLim - bufferPtr); + if (bufferSize == 0) + bufferSize = INIT_BUFFER_SIZE; + do { + bufferSize *= 2; + } while (bufferSize < neededSize); + newBuf = (char *)MALLOC(bufferSize); + if (newBuf == 0) { + errorCode = XML_ERROR_NO_MEMORY; + return NULL; + } + bufferLim = newBuf + bufferSize; +#ifdef XML_CONTEXT_BYTES + if (bufferPtr) { + int keep = (int)(bufferPtr - buffer); + if (keep > XML_CONTEXT_BYTES) + keep = XML_CONTEXT_BYTES; + memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep); + FREE(buffer); + buffer = newBuf; + bufferEnd = buffer + (bufferEnd - bufferPtr) + keep; + bufferPtr = buffer + keep; + } + else { + bufferEnd = newBuf + (bufferEnd - bufferPtr); + bufferPtr = buffer = newBuf; + } +#else + if (bufferPtr) { + memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr); + FREE(buffer); + } + bufferEnd = newBuf + (bufferEnd - bufferPtr); + bufferPtr = buffer = newBuf; +#endif /* not defined XML_CONTEXT_BYTES */ + } + eventPtr = eventEndPtr = NULL; + positionPtr = NULL; + } + return bufferEnd; +} + +enum XML_Status XMLCALL +XML_StopParser(XML_Parser parser, XML_Bool resumable) +{ + switch (ps_parsing) { + case XML_SUSPENDED: + if (resumable) { + errorCode = XML_ERROR_SUSPENDED; + return XML_STATUS_ERROR; + } + ps_parsing = XML_FINISHED; + break; + case XML_FINISHED: + errorCode = XML_ERROR_FINISHED; + return XML_STATUS_ERROR; + default: + if (resumable) { +#ifdef XML_DTD + if (isParamEntity) { + errorCode = XML_ERROR_SUSPEND_PE; + return XML_STATUS_ERROR; + } +#endif + ps_parsing = XML_SUSPENDED; + } + else + ps_parsing = XML_FINISHED; + } + return XML_STATUS_OK; +} + +enum XML_Status XMLCALL +XML_ResumeParser(XML_Parser parser) +{ + enum XML_Status result = XML_STATUS_OK; + + if (ps_parsing != XML_SUSPENDED) { + errorCode = XML_ERROR_NOT_SUSPENDED; + return XML_STATUS_ERROR; + } + ps_parsing = XML_PARSING; + + errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); + + if (errorCode != XML_ERROR_NONE) { + eventEndPtr = eventPtr; + processor = errorProcessor; + return XML_STATUS_ERROR; + } + else { + switch (ps_parsing) { + case XML_SUSPENDED: + result = XML_STATUS_SUSPENDED; + break; + case XML_INITIALIZED: + case XML_PARSING: + if (ps_finalBuffer) { + ps_parsing = XML_FINISHED; + return result; + } + default: ; + } + } + + XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); + positionPtr = bufferPtr; + return result; +} + +void XMLCALL +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) +{ + assert(status != NULL); + *status = parser->m_parsingStatus; +} + +enum XML_Error XMLCALL +XML_GetErrorCode(XML_Parser parser) +{ + return errorCode; +} + +XML_Index XMLCALL +XML_GetCurrentByteIndex(XML_Parser parser) +{ + if (eventPtr) + return parseEndByteIndex - (parseEndPtr - eventPtr); + return -1; +} + +int XMLCALL +XML_GetCurrentByteCount(XML_Parser parser) +{ + if (eventEndPtr && eventPtr) + return (int)(eventEndPtr - eventPtr); + return 0; +} + +const char * XMLCALL +XML_GetInputContext(XML_Parser parser, int *offset, int *size) +{ +#ifdef XML_CONTEXT_BYTES + if (eventPtr && buffer) { + *offset = (int)(eventPtr - buffer); + *size = (int)(bufferEnd - buffer); + return buffer; + } +#endif /* defined XML_CONTEXT_BYTES */ + return (char *) 0; +} + +XML_Size XMLCALL +XML_GetCurrentLineNumber(XML_Parser parser) +{ + if (eventPtr && eventPtr >= positionPtr) { + XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); + positionPtr = eventPtr; + } + return position.lineNumber + 1; +} + +XML_Size XMLCALL +XML_GetCurrentColumnNumber(XML_Parser parser) +{ + if (eventPtr && eventPtr >= positionPtr) { + XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); + positionPtr = eventPtr; + } + return position.columnNumber; +} + +void XMLCALL +XML_FreeContentModel(XML_Parser parser, XML_Content *model) +{ + FREE(model); +} + +void * XMLCALL +XML_MemMalloc(XML_Parser parser, size_t size) +{ + return MALLOC(size); +} + +void * XMLCALL +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) +{ + return REALLOC(ptr, size); +} + +void XMLCALL +XML_MemFree(XML_Parser parser, void *ptr) +{ + FREE(ptr); +} + +void XMLCALL +XML_DefaultCurrent(XML_Parser parser) +{ + if (defaultHandler) { + if (openInternalEntities) + reportDefault(parser, + internalEncoding, + openInternalEntities->internalEventPtr, + openInternalEntities->internalEventEndPtr); + else + reportDefault(parser, encoding, eventPtr, eventEndPtr); + } +} + +const XML_LChar * XMLCALL +XML_ErrorString(enum XML_Error code) +{ + static const XML_LChar* const message[] = { + 0, + XML_L("out of memory"), + XML_L("syntax error"), + XML_L("no element found"), + XML_L("not well-formed (invalid token)"), + XML_L("unclosed token"), + XML_L("partial character"), + XML_L("mismatched tag"), + XML_L("duplicate attribute"), + XML_L("junk after document element"), + XML_L("illegal parameter entity reference"), + XML_L("undefined entity"), + XML_L("recursive entity reference"), + XML_L("asynchronous entity"), + XML_L("reference to invalid character number"), + XML_L("reference to binary entity"), + XML_L("reference to external entity in attribute"), + XML_L("XML or text declaration not at start of entity"), + XML_L("unknown encoding"), + XML_L("encoding specified in XML declaration is incorrect"), + XML_L("unclosed CDATA section"), + XML_L("error in processing external entity reference"), + XML_L("document is not standalone"), + XML_L("unexpected parser state - please send a bug report"), + XML_L("entity declared in parameter entity"), + XML_L("requested feature requires XML_DTD support in Expat"), + XML_L("cannot change setting once parsing has begun"), + XML_L("unbound prefix"), + XML_L("must not undeclare prefix"), + XML_L("incomplete markup in parameter entity"), + XML_L("XML declaration not well-formed"), + XML_L("text declaration not well-formed"), + XML_L("illegal character(s) in public id"), + XML_L("parser suspended"), + XML_L("parser not suspended"), + XML_L("parsing aborted"), + XML_L("parsing finished"), + XML_L("cannot suspend in external parameter entity"), + XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"), + XML_L("reserved prefix (xmlns) must not be declared or undeclared"), + XML_L("prefix must not be bound to one of the reserved namespace names") + }; + if (code > 0 && code < sizeof(message)/sizeof(message[0])) + return message[code]; + return NULL; +} + +const XML_LChar * XMLCALL +XML_ExpatVersion(void) { + + /* V1 is used to string-ize the version number. However, it would + string-ize the actual version macro *names* unless we get them + substituted before being passed to V1. CPP is defined to expand + a macro, then rescan for more expansions. Thus, we use V2 to expand + the version macros, then CPP will expand the resulting V1() macro + with the correct numerals. */ + /* ### I'm assuming cpp is portable in this respect... */ + +#define V1(a,b,c) XML_L(#a)XML_L(".")XML_L(#b)XML_L(".")XML_L(#c) +#define V2(a,b,c) XML_L("expat_")V1(a,b,c) + + return V2(XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION); + +#undef V1 +#undef V2 +} + +XML_Expat_Version XMLCALL +XML_ExpatVersionInfo(void) +{ + XML_Expat_Version version; + + version.major = XML_MAJOR_VERSION; + version.minor = XML_MINOR_VERSION; + version.micro = XML_MICRO_VERSION; + + return version; +} + +const XML_Feature * XMLCALL +XML_GetFeatureList(void) +{ + static const XML_Feature features[] = { + {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), + sizeof(XML_Char)}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), + sizeof(XML_LChar)}, +#ifdef XML_UNICODE + {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, +#endif +#ifdef XML_UNICODE_WCHAR_T + {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, +#endif +#ifdef XML_DTD + {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, +#endif +#ifdef XML_CONTEXT_BYTES + {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), + XML_CONTEXT_BYTES}, +#endif +#ifdef XML_MIN_SIZE + {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, +#endif +#ifdef XML_NS + {XML_FEATURE_NS, XML_L("XML_NS"), 0}, +#endif +#ifdef XML_LARGE_SIZE + {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, +#endif +#ifdef XML_ATTR_INFO + {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, +#endif + {XML_FEATURE_END, NULL, 0} + }; + + return features; +} + +/* Initially tag->rawName always points into the parse buffer; + for those TAG instances opened while the current parse buffer was + processed, and not yet closed, we need to store tag->rawName in a more + permanent location, since the parse buffer is about to be discarded. +*/ +static XML_Bool +storeRawNames(XML_Parser parser) +{ + TAG *tag = tagStack; + while (tag) { + int bufSize; + int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1); + char *rawNameBuf = tag->buf + nameLen; + /* Stop if already stored. Since tagStack is a stack, we can stop + at the first entry that has already been copied; everything + below it in the stack is already been accounted for in a + previous call to this function. + */ + if (tag->rawName == rawNameBuf) + break; + /* For re-use purposes we need to ensure that the + size of tag->buf is a multiple of sizeof(XML_Char). + */ + bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)); + if (bufSize > tag->bufEnd - tag->buf) { + char *temp = (char *)REALLOC(tag->buf, bufSize); + if (temp == NULL) + return XML_FALSE; + /* if tag->name.str points to tag->buf (only when namespace + processing is off) then we have to update it + */ + if (tag->name.str == (XML_Char *)tag->buf) + tag->name.str = (XML_Char *)temp; + /* if tag->name.localPart is set (when namespace processing is on) + then update it as well, since it will always point into tag->buf + */ + if (tag->name.localPart) + tag->name.localPart = (XML_Char *)temp + (tag->name.localPart - + (XML_Char *)tag->buf); + tag->buf = temp; + tag->bufEnd = temp + bufSize; + rawNameBuf = temp + nameLen; + } + memcpy(rawNameBuf, tag->rawName, tag->rawNameLength); + tag->rawName = rawNameBuf; + tag = tag->parent; + } + return XML_TRUE; +} + +static enum XML_Error PTRCALL +contentProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = doContent(parser, 0, encoding, start, end, + endPtr, (XML_Bool)!ps_finalBuffer); + if (result == XML_ERROR_NONE) { + if (!storeRawNames(parser)) + return XML_ERROR_NO_MEMORY; + } + return result; +} + +static enum XML_Error PTRCALL +externalEntityInitProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + processor = externalEntityInitProcessor2; + return externalEntityInitProcessor2(parser, start, end, endPtr); +} + +static enum XML_Error PTRCALL +externalEntityInitProcessor2(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + const char *next = start; /* XmlContentTok doesn't always set the last arg */ + int tok = XmlContentTok(encoding, start, end, &next); + switch (tok) { + case XML_TOK_BOM: + /* If we are at the end of the buffer, this would cause the next stage, + i.e. externalEntityInitProcessor3, to pass control directly to + doContent (by detecting XML_TOK_NONE) without processing any xml text + declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent. + */ + if (next == end && !ps_finalBuffer) { + *endPtr = next; + return XML_ERROR_NONE; + } + start = next; + break; + case XML_TOK_PARTIAL: + if (!ps_finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + eventPtr = start; + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (!ps_finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + eventPtr = start; + return XML_ERROR_PARTIAL_CHAR; + } + processor = externalEntityInitProcessor3; + return externalEntityInitProcessor3(parser, start, end, endPtr); +} + +static enum XML_Error PTRCALL +externalEntityInitProcessor3(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + int tok; + const char *next = start; /* XmlContentTok doesn't always set the last arg */ + eventPtr = start; + tok = XmlContentTok(encoding, start, end, &next); + eventEndPtr = next; + + switch (tok) { + case XML_TOK_XML_DECL: + { + enum XML_Error result; + result = processXmlDecl(parser, 1, start, next); + if (result != XML_ERROR_NONE) + return result; + switch (ps_parsing) { + case XML_SUSPENDED: + *endPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + start = next; + } + } + break; + case XML_TOK_PARTIAL: + if (!ps_finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (!ps_finalBuffer) { + *endPtr = start; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + } + processor = externalEntityContentProcessor; + tagLevel = 1; + return externalEntityContentProcessor(parser, start, end, endPtr); +} + +static enum XML_Error PTRCALL +externalEntityContentProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = doContent(parser, 1, encoding, start, end, + endPtr, (XML_Bool)!ps_finalBuffer); + if (result == XML_ERROR_NONE) { + if (!storeRawNames(parser)) + return XML_ERROR_NO_MEMORY; + } + return result; +} + +static enum XML_Error +doContent(XML_Parser parser, + int startTagLevel, + const ENCODING *enc, + const char *s, + const char *end, + const char **nextPtr, + XML_Bool haveMore) +{ + /* save one level of indirection */ + DTD * const dtd = _dtd; + + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + + for (;;) { + const char *next = s; /* XmlContentTok doesn't always set the last arg */ + int tok = XmlContentTok(enc, s, end, &next); + *eventEndPP = next; + switch (tok) { + case XML_TOK_TRAILING_CR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + *eventEndPP = end; + if (characterDataHandler) { + XML_Char c = 0xA; + characterDataHandler(handlerArg, &c, 1); + } + else if (defaultHandler) + reportDefault(parser, enc, s, end); + /* We are at the end of the final buffer, should we check for + XML_SUSPENDED, XML_FINISHED? + */ + if (startTagLevel == 0) + return XML_ERROR_NO_ELEMENTS; + if (tagLevel != startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + *nextPtr = end; + return XML_ERROR_NONE; + case XML_TOK_NONE: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + if (startTagLevel > 0) { + if (tagLevel != startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_NO_ELEMENTS; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_ENTITY_REF: + { + const XML_Char *name; + ENTITY *entity; + XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (ch) { + if (characterDataHandler) + characterDataHandler(handlerArg, &ch, 1); + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + name = poolStoreString(&dtd->pool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&dtd->pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal, + otherwise call the skipped entity or default handler. + */ + if (!dtd->hasParamEntityRefs || dtd->standalone) { + if (!entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (!entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } + else if (!entity) { + if (skippedEntityHandler) + skippedEntityHandler(handlerArg, name, 0); + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->notation) + return XML_ERROR_BINARY_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + if (!defaultExpandInternalEntities) { + if (skippedEntityHandler) + skippedEntityHandler(handlerArg, entity->name, 0); + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + result = processInternalEntity(parser, entity, XML_FALSE); + if (result != XML_ERROR_NONE) + return result; + } + else if (externalEntityRefHandler) { + const XML_Char *context; + entity->open = XML_TRUE; + context = getContext(parser); + entity->open = XML_FALSE; + if (!context) + return XML_ERROR_NO_MEMORY; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + context, + entity->base, + entity->systemId, + entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + poolDiscard(&tempPool); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + case XML_TOK_START_TAG_NO_ATTS: + /* fall through */ + case XML_TOK_START_TAG_WITH_ATTS: + { + TAG *tag; + enum XML_Error result; + XML_Char *toPtr; + if (freeTagList) { + tag = freeTagList; + freeTagList = freeTagList->parent; + } + else { + tag = (TAG *)MALLOC(sizeof(TAG)); + if (!tag) + return XML_ERROR_NO_MEMORY; + tag->buf = (char *)MALLOC(INIT_TAG_BUF_SIZE); + if (!tag->buf) { + FREE(tag); + return XML_ERROR_NO_MEMORY; + } + tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; + } + tag->bindings = NULL; + tag->parent = tagStack; + tagStack = tag; + tag->name.localPart = NULL; + tag->name.prefix = NULL; + tag->rawName = s + enc->minBytesPerChar; + tag->rawNameLength = XmlNameLength(enc, tag->rawName); + ++tagLevel; + { + const char *rawNameEnd = tag->rawName + tag->rawNameLength; + const char *fromPtr = tag->rawName; + toPtr = (XML_Char *)tag->buf; + for (;;) { + int bufSize; + int convLen; + XmlConvert(enc, + &fromPtr, rawNameEnd, + (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1); + convLen = (int)(toPtr - (XML_Char *)tag->buf); + if (fromPtr == rawNameEnd) { + tag->name.strLen = convLen; + break; + } + bufSize = (int)(tag->bufEnd - tag->buf) << 1; + { + char *temp = (char *)REALLOC(tag->buf, bufSize); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + tag->buf = temp; + tag->bufEnd = temp + bufSize; + toPtr = (XML_Char *)temp + convLen; + } + } + } + tag->name.str = (XML_Char *)tag->buf; + *toPtr = XML_T('\0'); + result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); + if (result) + return result; + if (startElementHandler) + startElementHandler(handlerArg, tag->name.str, + (const XML_Char **)atts); + else if (defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&tempPool); + break; + } + case XML_TOK_EMPTY_ELEMENT_NO_ATTS: + /* fall through */ + case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: + { + const char *rawName = s + enc->minBytesPerChar; + enum XML_Error result; + BINDING *bindings = NULL; + XML_Bool noElmHandlers = XML_TRUE; + TAG_NAME name; + name.str = poolStoreString(&tempPool, enc, rawName, + rawName + XmlNameLength(enc, rawName)); + if (!name.str) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + result = storeAtts(parser, enc, s, &name, &bindings); + if (result) + return result; + poolFinish(&tempPool); + if (startElementHandler) { + startElementHandler(handlerArg, name.str, (const XML_Char **)atts); + noElmHandlers = XML_FALSE; + } + if (endElementHandler) { + if (startElementHandler) + *eventPP = *eventEndPP; + endElementHandler(handlerArg, name.str); + noElmHandlers = XML_FALSE; + } + if (noElmHandlers && defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&tempPool); + while (bindings) { + BINDING *b = bindings; + if (endNamespaceDeclHandler) + endNamespaceDeclHandler(handlerArg, b->prefix->name); + bindings = bindings->nextTagBinding; + b->nextTagBinding = freeBindingList; + freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } + } + if (tagLevel == 0) + return epilogProcessor(parser, next, end, nextPtr); + break; + case XML_TOK_END_TAG: + if (tagLevel == startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + else { + int len; + const char *rawName; + TAG *tag = tagStack; + tagStack = tag->parent; + tag->parent = freeTagList; + freeTagList = tag; + rawName = s + enc->minBytesPerChar*2; + len = XmlNameLength(enc, rawName); + if (len != tag->rawNameLength + || memcmp(tag->rawName, rawName, len) != 0) { + *eventPP = rawName; + return XML_ERROR_TAG_MISMATCH; + } + --tagLevel; + if (endElementHandler) { + const XML_Char *localPart; + const XML_Char *prefix; + XML_Char *uri; + localPart = tag->name.localPart; + if (ns && localPart) { + /* localPart and prefix may have been overwritten in + tag->name.str, since this points to the binding->uri + buffer which gets re-used; so we have to add them again + */ + uri = (XML_Char *)tag->name.str + tag->name.uriLen; + /* don't need to check for space - already done in storeAtts() */ + while (*localPart) *uri++ = *localPart++; + prefix = (XML_Char *)tag->name.prefix; + if (ns_triplets && prefix) { + *uri++ = namespaceSeparator; + while (*prefix) *uri++ = *prefix++; + } + *uri = XML_T('\0'); + } + endElementHandler(handlerArg, tag->name.str); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + while (tag->bindings) { + BINDING *b = tag->bindings; + if (endNamespaceDeclHandler) + endNamespaceDeclHandler(handlerArg, b->prefix->name); + tag->bindings = tag->bindings->nextTagBinding; + b->nextTagBinding = freeBindingList; + freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } + if (tagLevel == 0) + return epilogProcessor(parser, next, end, nextPtr); + } + break; + case XML_TOK_CHAR_REF: + { + int n = XmlCharRefNumber(enc, s); + if (n < 0) + return XML_ERROR_BAD_CHAR_REF; + if (characterDataHandler) { + XML_Char buf[XML_ENCODE_MAX]; + characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf)); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + } + break; + case XML_TOK_XML_DECL: + return XML_ERROR_MISPLACED_XML_PI; + case XML_TOK_DATA_NEWLINE: + if (characterDataHandler) { + XML_Char c = 0xA; + characterDataHandler(handlerArg, &c, 1); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_CDATA_SECT_OPEN: + { + enum XML_Error result; + if (startCdataSectionHandler) + startCdataSectionHandler(handlerArg); +#if 0 + /* Suppose you doing a transformation on a document that involves + changing only the character data. You set up a defaultHandler + and a characterDataHandler. The defaultHandler simply copies + characters through. The characterDataHandler does the + transformation and writes the characters out escaping them as + necessary. This case will fail to work if we leave out the + following two lines (because & and < inside CDATA sections will + be incorrectly escaped). + + However, now we have a start/endCdataSectionHandler, so it seems + easier to let the user deal with this. + */ + else if (characterDataHandler) + characterDataHandler(handlerArg, dataBuf, 0); +#endif + else if (defaultHandler) + reportDefault(parser, enc, s, next); + result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (!next) { + processor = cdataSectionProcessor; + return result; + } + } + break; + case XML_TOK_TRAILING_RSQB: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + if (characterDataHandler) { + if (MUST_CONVERT(enc, s)) { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); + characterDataHandler(handlerArg, dataBuf, + (int)(dataPtr - (ICHAR *)dataBuf)); + } + else + characterDataHandler(handlerArg, + (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); + } + else if (defaultHandler) + reportDefault(parser, enc, s, end); + /* We are at the end of the final buffer, should we check for + XML_SUSPENDED, XML_FINISHED? + */ + if (startTagLevel == 0) { + *eventPP = end; + return XML_ERROR_NO_ELEMENTS; + } + if (tagLevel != startTagLevel) { + *eventPP = end; + return XML_ERROR_ASYNC_ENTITY; + } + *nextPtr = end; + return XML_ERROR_NONE; + case XML_TOK_DATA_CHARS: + { + XML_CharacterDataHandler charDataHandler = characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); + *eventEndPP = s; + charDataHandler(handlerArg, dataBuf, + (int)(dataPtr - (ICHAR *)dataBuf)); + if (s == next) + break; + *eventPP = s; + } + } + else + charDataHandler(handlerArg, + (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + } + break; + case XML_TOK_PI: + if (!reportProcessingInstruction(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (!reportComment(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + default: + if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + *eventPP = s = next; + switch (ps_parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: ; + } + } + /* not reached */ +} + +/* Precondition: all arguments must be non-NULL; + Purpose: + - normalize attributes + - check attributes for well-formedness + - generate namespace aware attribute names (URI, prefix) + - build list of attributes for startElementHandler + - default attributes + - process namespace declarations (check and report them) + - generate namespace aware element name (URI, prefix) +*/ +static enum XML_Error +storeAtts(XML_Parser parser, const ENCODING *enc, + const char *attStr, TAG_NAME *tagNamePtr, + BINDING **bindingsPtr) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + ELEMENT_TYPE *elementType; + int nDefaultAtts; + const XML_Char **appAtts; /* the attribute list for the application */ + int attIndex = 0; + int prefixLen; + int i; + int n; + XML_Char *uri; + int nPrefixes = 0; + BINDING *binding; + const XML_Char *localPart; + + /* lookup the element type name */ + elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str,0); + if (!elementType) { + const XML_Char *name = poolCopyString(&dtd->pool, tagNamePtr->str); + if (!name) + return XML_ERROR_NO_MEMORY; + elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, + sizeof(ELEMENT_TYPE)); + if (!elementType) + return XML_ERROR_NO_MEMORY; + if (ns && !setElementTypePrefix(parser, elementType)) + return XML_ERROR_NO_MEMORY; + } + nDefaultAtts = elementType->nDefaultAtts; + + /* get the attributes from the tokenizer */ + n = XmlGetAttributes(enc, attStr, attsSize, atts); + if (n + nDefaultAtts > attsSize) { + int oldAttsSize = attsSize; + ATTRIBUTE *temp; +#ifdef XML_ATTR_INFO + XML_AttrInfo *temp2; +#endif + attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; + temp = (ATTRIBUTE *)REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE)); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + atts = temp; +#ifdef XML_ATTR_INFO + temp2 = (XML_AttrInfo *)REALLOC((void *)attInfo, attsSize * sizeof(XML_AttrInfo)); + if (temp2 == NULL) + return XML_ERROR_NO_MEMORY; + attInfo = temp2; +#endif + if (n > oldAttsSize) + XmlGetAttributes(enc, attStr, n, atts); + } + + appAtts = (const XML_Char **)atts; + for (i = 0; i < n; i++) { + ATTRIBUTE *currAtt = &atts[i]; +#ifdef XML_ATTR_INFO + XML_AttrInfo *currAttInfo = &attInfo[i]; +#endif + /* add the name and value to the attribute list */ + ATTRIBUTE_ID *attId = getAttributeId(parser, enc, currAtt->name, + currAtt->name + + XmlNameLength(enc, currAtt->name)); + if (!attId) + return XML_ERROR_NO_MEMORY; +#ifdef XML_ATTR_INFO + currAttInfo->nameStart = parseEndByteIndex - (parseEndPtr - currAtt->name); + currAttInfo->nameEnd = currAttInfo->nameStart + + XmlNameLength(enc, currAtt->name); + currAttInfo->valueStart = parseEndByteIndex - + (parseEndPtr - currAtt->valuePtr); + currAttInfo->valueEnd = parseEndByteIndex - (parseEndPtr - currAtt->valueEnd); +#endif + /* Detect duplicate attributes by their QNames. This does not work when + namespace processing is turned on and different prefixes for the same + namespace are used. For this case we have a check further down. + */ + if ((attId->name)[-1]) { + if (enc == encoding) + eventPtr = atts[i].name; + return XML_ERROR_DUPLICATE_ATTRIBUTE; + } + (attId->name)[-1] = 1; + appAtts[attIndex++] = attId->name; + if (!atts[i].normalized) { + enum XML_Error result; + XML_Bool isCdata = XML_TRUE; + + /* figure out whether declared as other than CDATA */ + if (attId->maybeTokenized) { + int j; + for (j = 0; j < nDefaultAtts; j++) { + if (attId == elementType->defaultAtts[j].id) { + isCdata = elementType->defaultAtts[j].isCdata; + break; + } + } + } + + /* normalize the attribute value */ + result = storeAttributeValue(parser, enc, isCdata, + atts[i].valuePtr, atts[i].valueEnd, + &tempPool); + if (result) + return result; + appAtts[attIndex] = poolStart(&tempPool); + poolFinish(&tempPool); + } + else { + /* the value did not need normalizing */ + appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, + atts[i].valueEnd); + if (appAtts[attIndex] == 0) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + } + /* handle prefixed attribute names */ + if (attId->prefix) { + if (attId->xmlns) { + /* deal with namespace declarations here */ + enum XML_Error result = addBinding(parser, attId->prefix, attId, + appAtts[attIndex], bindingsPtr); + if (result) + return result; + --attIndex; + } + else { + /* deal with other prefixed names later */ + attIndex++; + nPrefixes++; + (attId->name)[-1] = 2; + } + } + else + attIndex++; + } + + /* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */ + nSpecifiedAtts = attIndex; + if (elementType->idAtt && (elementType->idAtt->name)[-1]) { + for (i = 0; i < attIndex; i += 2) + if (appAtts[i] == elementType->idAtt->name) { + idAttIndex = i; + break; + } + } + else + idAttIndex = -1; + + /* do attribute defaulting */ + for (i = 0; i < nDefaultAtts; i++) { + const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + i; + if (!(da->id->name)[-1] && da->value) { + if (da->id->prefix) { + if (da->id->xmlns) { + enum XML_Error result = addBinding(parser, da->id->prefix, da->id, + da->value, bindingsPtr); + if (result) + return result; + } + else { + (da->id->name)[-1] = 2; + nPrefixes++; + appAtts[attIndex++] = da->id->name; + appAtts[attIndex++] = da->value; + } + } + else { + (da->id->name)[-1] = 1; + appAtts[attIndex++] = da->id->name; + appAtts[attIndex++] = da->value; + } + } + } + appAtts[attIndex] = 0; + + /* expand prefixed attribute names, check for duplicates, + and clear flags that say whether attributes were specified */ + i = 0; + if (nPrefixes) { + int j; /* hash table index */ + unsigned long version = nsAttsVersion; + int nsAttsSize = (int)1 << nsAttsPower; + /* size of hash table must be at least 2 * (# of prefixed attributes) */ + if ((nPrefixes << 1) >> nsAttsPower) { /* true for nsAttsPower = 0 */ + NS_ATT *temp; + /* hash table size must also be a power of 2 and >= 8 */ + while (nPrefixes >> nsAttsPower++); + if (nsAttsPower < 3) + nsAttsPower = 3; + nsAttsSize = (int)1 << nsAttsPower; + temp = (NS_ATT *)REALLOC(nsAtts, nsAttsSize * sizeof(NS_ATT)); + if (!temp) + return XML_ERROR_NO_MEMORY; + nsAtts = temp; + version = 0; /* force re-initialization of nsAtts hash table */ + } + /* using a version flag saves us from initializing nsAtts every time */ + if (!version) { /* initialize version flags when version wraps around */ + version = INIT_ATTS_VERSION; + for (j = nsAttsSize; j != 0; ) + nsAtts[--j].version = version; + } + nsAttsVersion = --version; + + /* expand prefixed names and check for duplicates */ + for (; i < attIndex; i += 2) { + const XML_Char *s = appAtts[i]; + if (s[-1] == 2) { /* prefixed */ + ATTRIBUTE_ID *id; + const BINDING *b; + unsigned long uriHash = hash_secret_salt; + ((XML_Char *)s)[-1] = 0; /* clear flag */ + id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0); + b = id->prefix->binding; + if (!b) + return XML_ERROR_UNBOUND_PREFIX; + + /* as we expand the name we also calculate its hash value */ + for (j = 0; j < b->uriLen; j++) { + const XML_Char c = b->uri[j]; + if (!poolAppendChar(&tempPool, c)) + return XML_ERROR_NO_MEMORY; + uriHash = CHAR_HASH(uriHash, c); + } + while (*s++ != XML_T(ASCII_COLON)) + ; + do { /* copies null terminator */ + const XML_Char c = *s; + if (!poolAppendChar(&tempPool, *s)) + return XML_ERROR_NO_MEMORY; + uriHash = CHAR_HASH(uriHash, c); + } while (*s++); + + { /* Check hash table for duplicate of expanded name (uriName). + Derived from code in lookup(parser, HASH_TABLE *table, ...). + */ + unsigned char step = 0; + unsigned long mask = nsAttsSize - 1; + j = uriHash & mask; /* index into hash table */ + while (nsAtts[j].version == version) { + /* for speed we compare stored hash values first */ + if (uriHash == nsAtts[j].hash) { + const XML_Char *s1 = poolStart(&tempPool); + const XML_Char *s2 = nsAtts[j].uriName; + /* s1 is null terminated, but not s2 */ + for (; *s1 == *s2 && *s1 != 0; s1++, s2++); + if (*s1 == 0) + return XML_ERROR_DUPLICATE_ATTRIBUTE; + } + if (!step) + step = PROBE_STEP(uriHash, mask, nsAttsPower); + j < step ? (j += nsAttsSize - step) : (j -= step); + } + } + + if (ns_triplets) { /* append namespace separator and prefix */ + tempPool.ptr[-1] = namespaceSeparator; + s = b->prefix->name; + do { + if (!poolAppendChar(&tempPool, *s)) + return XML_ERROR_NO_MEMORY; + } while (*s++); + } + + /* store expanded name in attribute list */ + s = poolStart(&tempPool); + poolFinish(&tempPool); + appAtts[i] = s; + + /* fill empty slot with new version, uriName and hash value */ + nsAtts[j].version = version; + nsAtts[j].hash = uriHash; + nsAtts[j].uriName = s; + + if (!--nPrefixes) { + i += 2; + break; + } + } + else /* not prefixed */ + ((XML_Char *)s)[-1] = 0; /* clear flag */ + } + } + /* clear flags for the remaining attributes */ + for (; i < attIndex; i += 2) + ((XML_Char *)(appAtts[i]))[-1] = 0; + for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) + binding->attId->name[-1] = 0; + + if (!ns) + return XML_ERROR_NONE; + + /* expand the element type name */ + if (elementType->prefix) { + binding = elementType->prefix->binding; + if (!binding) + return XML_ERROR_UNBOUND_PREFIX; + localPart = tagNamePtr->str; + while (*localPart++ != XML_T(ASCII_COLON)) + ; + } + else if (dtd->defaultPrefix.binding) { + binding = dtd->defaultPrefix.binding; + localPart = tagNamePtr->str; + } + else + return XML_ERROR_NONE; + prefixLen = 0; + if (ns_triplets && binding->prefix->name) { + for (; binding->prefix->name[prefixLen++];) + ; /* prefixLen includes null terminator */ + } + tagNamePtr->localPart = localPart; + tagNamePtr->uriLen = binding->uriLen; + tagNamePtr->prefix = binding->prefix->name; + tagNamePtr->prefixLen = prefixLen; + for (i = 0; localPart[i++];) + ; /* i includes null terminator */ + n = i + binding->uriLen + prefixLen; + if (n > binding->uriAlloc) { + TAG *p; + uri = (XML_Char *)MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char)); + if (!uri) + return XML_ERROR_NO_MEMORY; + binding->uriAlloc = n + EXPAND_SPARE; + memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char)); + for (p = tagStack; p; p = p->parent) + if (p->name.str == binding->uri) + p->name.str = uri; + FREE(binding->uri); + binding->uri = uri; + } + /* if namespaceSeparator != '\0' then uri includes it already */ + uri = binding->uri + binding->uriLen; + memcpy(uri, localPart, i * sizeof(XML_Char)); + /* we always have a namespace separator between localPart and prefix */ + if (prefixLen) { + uri += i - 1; + *uri = namespaceSeparator; /* replace null terminator */ + memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); + } + tagNamePtr->str = binding->uri; + return XML_ERROR_NONE; +} + +/* addBinding() overwrites the value of prefix->binding without checking. + Therefore one must keep track of the old value outside of addBinding(). +*/ +static enum XML_Error +addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, + const XML_Char *uri, BINDING **bindingsPtr) +{ + static const XML_Char xmlNamespace[] = { + ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, + ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, + ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, + ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, ASCII_8, ASCII_SLASH, + ASCII_n, ASCII_a, ASCII_m, ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, + ASCII_e, '\0' + }; + static const int xmlLen = + (int)sizeof(xmlNamespace)/sizeof(XML_Char) - 1; + static const XML_Char xmlnsNamespace[] = { + ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, + ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, + ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_2, ASCII_0, ASCII_0, + ASCII_0, ASCII_SLASH, ASCII_x, ASCII_m, ASCII_l, ASCII_n, ASCII_s, + ASCII_SLASH, '\0' + }; + static const int xmlnsLen = + (int)sizeof(xmlnsNamespace)/sizeof(XML_Char) - 1; + + XML_Bool mustBeXML = XML_FALSE; + XML_Bool isXML = XML_TRUE; + XML_Bool isXMLNS = XML_TRUE; + + BINDING *b; + int len; + + /* empty URI is only valid for default namespace per XML NS 1.0 (not 1.1) */ + if (*uri == XML_T('\0') && prefix->name) + return XML_ERROR_UNDECLARING_PREFIX; + + if (prefix->name + && prefix->name[0] == XML_T(ASCII_x) + && prefix->name[1] == XML_T(ASCII_m) + && prefix->name[2] == XML_T(ASCII_l)) { + + /* Not allowed to bind xmlns */ + if (prefix->name[3] == XML_T(ASCII_n) + && prefix->name[4] == XML_T(ASCII_s) + && prefix->name[5] == XML_T('\0')) + return XML_ERROR_RESERVED_PREFIX_XMLNS; + + if (prefix->name[3] == XML_T('\0')) + mustBeXML = XML_TRUE; + } + + for (len = 0; uri[len]; len++) { + if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len])) + isXML = XML_FALSE; + + if (!mustBeXML && isXMLNS + && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) + isXMLNS = XML_FALSE; + } + isXML = isXML && len == xmlLen; + isXMLNS = isXMLNS && len == xmlnsLen; + + if (mustBeXML != isXML) + return mustBeXML ? XML_ERROR_RESERVED_PREFIX_XML + : XML_ERROR_RESERVED_NAMESPACE_URI; + + if (isXMLNS) + return XML_ERROR_RESERVED_NAMESPACE_URI; + + if (namespaceSeparator) + len++; + if (freeBindingList) { + b = freeBindingList; + if (len > b->uriAlloc) { + XML_Char *temp = (XML_Char *)REALLOC(b->uri, + sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + b->uri = temp; + b->uriAlloc = len + EXPAND_SPARE; + } + freeBindingList = b->nextTagBinding; + } + else { + b = (BINDING *)MALLOC(sizeof(BINDING)); + if (!b) + return XML_ERROR_NO_MEMORY; + b->uri = (XML_Char *)MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (!b->uri) { + FREE(b); + return XML_ERROR_NO_MEMORY; + } + b->uriAlloc = len + EXPAND_SPARE; + } + b->uriLen = len; + memcpy(b->uri, uri, len * sizeof(XML_Char)); + if (namespaceSeparator) + b->uri[len - 1] = namespaceSeparator; + b->prefix = prefix; + b->attId = attId; + b->prevPrefixBinding = prefix->binding; + /* NULL binding when default namespace undeclared */ + if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix) + prefix->binding = NULL; + else + prefix->binding = b; + b->nextTagBinding = *bindingsPtr; + *bindingsPtr = b; + /* if attId == NULL then we are not starting a namespace scope */ + if (attId && startNamespaceDeclHandler) + startNamespaceDeclHandler(handlerArg, prefix->name, + prefix->binding ? uri : 0); + return XML_ERROR_NONE; +} + +/* The idea here is to avoid using stack for each CDATA section when + the whole file is parsed with one call. +*/ +static enum XML_Error PTRCALL +cdataSectionProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = doCdataSection(parser, encoding, &start, end, + endPtr, (XML_Bool)!ps_finalBuffer); + if (result != XML_ERROR_NONE) + return result; + if (start) { + if (parentParser) { /* we are parsing an external entity */ + processor = externalEntityContentProcessor; + return externalEntityContentProcessor(parser, start, end, endPtr); + } + else { + processor = contentProcessor; + return contentProcessor(parser, start, end, endPtr); + } + } + return result; +} + +/* startPtr gets set to non-null if the section is closed, and to null if + the section is not yet closed. +*/ +static enum XML_Error +doCdataSection(XML_Parser parser, + const ENCODING *enc, + const char **startPtr, + const char *end, + const char **nextPtr, + XML_Bool haveMore) +{ + const char *s = *startPtr; + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + *eventPP = s; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + *startPtr = NULL; + + for (;;) { + const char *next; + int tok = XmlCdataSectionTok(enc, s, end, &next); + *eventEndPP = next; + switch (tok) { + case XML_TOK_CDATA_SECT_CLOSE: + if (endCdataSectionHandler) + endCdataSectionHandler(handlerArg); +#if 0 + /* see comment under XML_TOK_CDATA_SECT_OPEN */ + else if (characterDataHandler) + characterDataHandler(handlerArg, dataBuf, 0); +#endif + else if (defaultHandler) + reportDefault(parser, enc, s, next); + *startPtr = next; + *nextPtr = next; + if (ps_parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + else + return XML_ERROR_NONE; + case XML_TOK_DATA_NEWLINE: + if (characterDataHandler) { + XML_Char c = 0xA; + characterDataHandler(handlerArg, &c, 1); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_DATA_CHARS: + { + XML_CharacterDataHandler charDataHandler = characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); + *eventEndPP = next; + charDataHandler(handlerArg, dataBuf, + (int)(dataPtr - (ICHAR *)dataBuf)); + if (s == next) + break; + *eventPP = s; + } + } + else + charDataHandler(handlerArg, + (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + } + break; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_PARTIAL: + case XML_TOK_NONE: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_CDATA_SECTION; + default: + *eventPP = next; + return XML_ERROR_UNEXPECTED_STATE; + } + + *eventPP = s = next; + switch (ps_parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: ; + } + } + /* not reached */ +} + +#ifdef XML_DTD + +/* The idea here is to avoid using stack for each IGNORE section when + the whole file is parsed with one call. +*/ +static enum XML_Error PTRCALL +ignoreSectionProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = doIgnoreSection(parser, encoding, &start, end, + endPtr, (XML_Bool)!ps_finalBuffer); + if (result != XML_ERROR_NONE) + return result; + if (start) { + processor = prologProcessor; + return prologProcessor(parser, start, end, endPtr); + } + return result; +} + +/* startPtr gets set to non-null is the section is closed, and to null + if the section is not yet closed. +*/ +static enum XML_Error +doIgnoreSection(XML_Parser parser, + const ENCODING *enc, + const char **startPtr, + const char *end, + const char **nextPtr, + XML_Bool haveMore) +{ + const char *next; + int tok; + const char *s = *startPtr; + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + *eventPP = s; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + *startPtr = NULL; + tok = XmlIgnoreSectionTok(enc, s, end, &next); + *eventEndPP = next; + switch (tok) { + case XML_TOK_IGNORE_SECT: + if (defaultHandler) + reportDefault(parser, enc, s, next); + *startPtr = next; + *nextPtr = next; + if (ps_parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + else + return XML_ERROR_NONE; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_PARTIAL: + case XML_TOK_NONE: + if (haveMore) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */ + default: + *eventPP = next; + return XML_ERROR_UNEXPECTED_STATE; + } + /* not reached */ +} + +#endif /* XML_DTD */ + +static enum XML_Error +initializeEncoding(XML_Parser parser) +{ + const char *s; +#ifdef XML_UNICODE + char encodingBuf[128]; + if (!protocolEncodingName) + s = NULL; + else { + int i; + for (i = 0; protocolEncodingName[i]; i++) { + if (i == sizeof(encodingBuf) - 1 + || (protocolEncodingName[i] & ~0x7f) != 0) { + encodingBuf[0] = '\0'; + break; + } + encodingBuf[i] = (char)protocolEncodingName[i]; + } + encodingBuf[i] = '\0'; + s = encodingBuf; + } +#else + s = protocolEncodingName; +#endif + if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s)) + return XML_ERROR_NONE; + return handleUnknownEncoding(parser, protocolEncodingName); +} + +static enum XML_Error +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, + const char *s, const char *next) +{ + const char *encodingName = NULL; + const XML_Char *storedEncName = NULL; + const ENCODING *newEncoding = NULL; + const char *version = NULL; + const char *versionend; + const XML_Char *storedversion = NULL; + int standalone = -1; + if (!(ns + ? XmlParseXmlDeclNS + : XmlParseXmlDecl)(isGeneralTextEntity, + encoding, + s, + next, + &eventPtr, + &version, + &versionend, + &encodingName, + &newEncoding, + &standalone)) { + if (isGeneralTextEntity) + return XML_ERROR_TEXT_DECL; + else + return XML_ERROR_XML_DECL; + } + if (!isGeneralTextEntity && standalone == 1) { + _dtd->standalone = XML_TRUE; +#ifdef XML_DTD + if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) + paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; +#endif /* XML_DTD */ + } + if (xmlDeclHandler) { + if (encodingName != NULL) { + storedEncName = poolStoreString(&temp2Pool, + encoding, + encodingName, + encodingName + + XmlNameLength(encoding, encodingName)); + if (!storedEncName) + return XML_ERROR_NO_MEMORY; + poolFinish(&temp2Pool); + } + if (version) { + storedversion = poolStoreString(&temp2Pool, + encoding, + version, + versionend - encoding->minBytesPerChar); + if (!storedversion) + return XML_ERROR_NO_MEMORY; + } + xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone); + } + else if (defaultHandler) + reportDefault(parser, encoding, s, next); + if (protocolEncodingName == NULL) { + if (newEncoding) { + if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) { + eventPtr = encodingName; + return XML_ERROR_INCORRECT_ENCODING; + } + encoding = newEncoding; + } + else if (encodingName) { + enum XML_Error result; + if (!storedEncName) { + storedEncName = poolStoreString( + &temp2Pool, encoding, encodingName, + encodingName + XmlNameLength(encoding, encodingName)); + if (!storedEncName) + return XML_ERROR_NO_MEMORY; + } + result = handleUnknownEncoding(parser, storedEncName); + poolClear(&temp2Pool); + if (result == XML_ERROR_UNKNOWN_ENCODING) + eventPtr = encodingName; + return result; + } + } + + if (storedEncName || storedversion) + poolClear(&temp2Pool); + + return XML_ERROR_NONE; +} + +static enum XML_Error +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) +{ + if (unknownEncodingHandler) { + XML_Encoding info; + int i; + for (i = 0; i < 256; i++) + info.map[i] = -1; + info.convert = NULL; + info.data = NULL; + info.release = NULL; + if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName, + &info)) { + ENCODING *enc; + unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding()); + if (!unknownEncodingMem) { + if (info.release) + info.release(info.data); + return XML_ERROR_NO_MEMORY; + } + enc = (ns + ? XmlInitUnknownEncodingNS + : XmlInitUnknownEncoding)(unknownEncodingMem, + info.map, + info.convert, + info.data); + if (enc) { + unknownEncodingData = info.data; + unknownEncodingRelease = info.release; + encoding = enc; + return XML_ERROR_NONE; + } + } + if (info.release != NULL) + info.release(info.data); + } + return XML_ERROR_UNKNOWN_ENCODING; +} + +static enum XML_Error PTRCALL +prologInitProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + processor = prologProcessor; + return prologProcessor(parser, s, end, nextPtr); +} + +#ifdef XML_DTD + +static enum XML_Error PTRCALL +externalParEntInitProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + + /* we know now that XML_Parse(Buffer) has been called, + so we consider the external parameter entity read */ + _dtd->paramEntityRead = XML_TRUE; + + if (prologState.inEntityValue) { + processor = entityValueInitProcessor; + return entityValueInitProcessor(parser, s, end, nextPtr); + } + else { + processor = externalParEntProcessor; + return externalParEntProcessor(parser, s, end, nextPtr); + } +} + +static enum XML_Error PTRCALL +entityValueInitProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + int tok; + const char *start = s; + const char *next = start; + eventPtr = start; + + for (;;) { + tok = XmlPrologTok(encoding, start, end, &next); + eventEndPtr = next; + if (tok <= 0) { + if (!ps_finalBuffer && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: /* start == end */ + default: + break; + } + /* found end of entity value - can store it now */ + return storeEntityValue(parser, encoding, s, end); + } + else if (tok == XML_TOK_XML_DECL) { + enum XML_Error result; + result = processXmlDecl(parser, 0, start, next); + if (result != XML_ERROR_NONE) + return result; + switch (ps_parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + *nextPtr = next; + } + /* stop scanning for text declaration - we found one */ + processor = entityValueProcessor; + return entityValueProcessor(parser, next, end, nextPtr); + } + /* If we are at the end of the buffer, this would cause XmlPrologTok to + return XML_TOK_NONE on the next call, which would then cause the + function to exit with *nextPtr set to s - that is what we want for other + tokens, but not for the BOM - we would rather like to skip it; + then, when this routine is entered the next time, XmlPrologTok will + return XML_TOK_INVALID, since the BOM is still in the buffer + */ + else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) { + *nextPtr = next; + return XML_ERROR_NONE; + } + start = next; + eventPtr = start; + } +} + +static enum XML_Error PTRCALL +externalParEntProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + const char *next = s; + int tok; + + tok = XmlPrologTok(encoding, s, end, &next); + if (tok <= 0) { + if (!ps_finalBuffer && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: /* start == end */ + default: + break; + } + } + /* This would cause the next stage, i.e. doProlog to be passed XML_TOK_BOM. + However, when parsing an external subset, doProlog will not accept a BOM + as valid, and report a syntax error, so we have to skip the BOM + */ + else if (tok == XML_TOK_BOM) { + s = next; + tok = XmlPrologTok(encoding, s, end, &next); + } + + processor = prologProcessor; + return doProlog(parser, encoding, s, end, tok, next, + nextPtr, (XML_Bool)!ps_finalBuffer); +} + +static enum XML_Error PTRCALL +entityValueProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + const char *start = s; + const char *next = s; + const ENCODING *enc = encoding; + int tok; + + for (;;) { + tok = XmlPrologTok(enc, start, end, &next); + if (tok <= 0) { + if (!ps_finalBuffer && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: /* start == end */ + default: + break; + } + /* found end of entity value - can store it now */ + return storeEntityValue(parser, enc, s, end); + } + start = next; + } +} + +#endif /* XML_DTD */ + +static enum XML_Error PTRCALL +prologProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + const char *next = s; + int tok = XmlPrologTok(encoding, s, end, &next); + return doProlog(parser, encoding, s, end, tok, next, + nextPtr, (XML_Bool)!ps_finalBuffer); +} + +static enum XML_Error +doProlog(XML_Parser parser, + const ENCODING *enc, + const char *s, + const char *end, + int tok, + const char *next, + const char **nextPtr, + XML_Bool haveMore) +{ +#ifdef XML_DTD + static const XML_Char externalSubsetName[] = { ASCII_HASH , '\0' }; +#endif /* XML_DTD */ + static const XML_Char atypeCDATA[] = + { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; + static const XML_Char atypeID[] = { ASCII_I, ASCII_D, '\0' }; + static const XML_Char atypeIDREF[] = + { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; + static const XML_Char atypeIDREFS[] = + { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; + static const XML_Char atypeENTITY[] = + { ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; + static const XML_Char atypeENTITIES[] = { ASCII_E, ASCII_N, + ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, '\0' }; + static const XML_Char atypeNMTOKEN[] = { + ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; + static const XML_Char atypeNMTOKENS[] = { ASCII_N, ASCII_M, ASCII_T, + ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, '\0' }; + static const XML_Char notationPrefix[] = { ASCII_N, ASCII_O, ASCII_T, + ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0' }; + static const XML_Char enumValueSep[] = { ASCII_PIPE, '\0' }; + static const XML_Char enumValueStart[] = { ASCII_LPAREN, '\0' }; + + /* save one level of indirection */ + DTD * const dtd = _dtd; + + const char **eventPP; + const char **eventEndPP; + enum XML_Content_Quant quant; + + if (enc == encoding) { + eventPP = &eventPtr; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + + for (;;) { + int role; + XML_Bool handleDefault = XML_TRUE; + *eventPP = s; + *eventEndPP = next; + if (tok <= 0) { + if (haveMore && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case -XML_TOK_PROLOG_S: + tok = -tok; + break; + case XML_TOK_NONE: +#ifdef XML_DTD + /* for internal PE NOT referenced between declarations */ + if (enc != encoding && !openInternalEntities->betweenDecl) { + *nextPtr = s; + return XML_ERROR_NONE; + } + /* WFC: PE Between Declarations - must check that PE contains + complete markup, not only for external PEs, but also for + internal PEs if the reference occurs between declarations. + */ + if (isParamEntity || enc != encoding) { + if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc) + == XML_ROLE_ERROR) + return XML_ERROR_INCOMPLETE_PE; + *nextPtr = s; + return XML_ERROR_NONE; + } +#endif /* XML_DTD */ + return XML_ERROR_NO_ELEMENTS; + default: + tok = -tok; + next = end; + break; + } + } + role = XmlTokenRole(&prologState, tok, s, next, enc); + switch (role) { + case XML_ROLE_XML_DECL: + { + enum XML_Error result = processXmlDecl(parser, 0, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = encoding; + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_DOCTYPE_NAME: + if (startDoctypeDeclHandler) { + doctypeName = poolStoreString(&tempPool, enc, s, next); + if (!doctypeName) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + doctypePubid = NULL; + handleDefault = XML_FALSE; + } + doctypeSysid = NULL; /* always initialize to NULL */ + break; + case XML_ROLE_DOCTYPE_INTERNAL_SUBSET: + if (startDoctypeDeclHandler) { + startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid, + doctypePubid, 1); + doctypeName = NULL; + poolClear(&tempPool); + handleDefault = XML_FALSE; + } + break; +#ifdef XML_DTD + case XML_ROLE_TEXT_DECL: + { + enum XML_Error result = processXmlDecl(parser, 1, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = encoding; + handleDefault = XML_FALSE; + } + break; +#endif /* XML_DTD */ + case XML_ROLE_DOCTYPE_PUBLIC_ID: +#ifdef XML_DTD + useForeignDTD = XML_FALSE; + declEntity = (ENTITY *)lookup(parser, + &dtd->paramEntities, + externalSubsetName, + sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; +#endif /* XML_DTD */ + dtd->hasParamEntityRefs = XML_TRUE; + if (startDoctypeDeclHandler) { + XML_Char *pubId; + if (!XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_PUBLICID; + pubId = poolStoreString(&tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!pubId) + return XML_ERROR_NO_MEMORY; + normalizePublicId(pubId); + poolFinish(&tempPool); + doctypePubid = pubId; + handleDefault = XML_FALSE; + goto alreadyChecked; + } + /* fall through */ + case XML_ROLE_ENTITY_PUBLIC_ID: + if (!XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_PUBLICID; + alreadyChecked: + if (dtd->keepProcessing && declEntity) { + XML_Char *tem = poolStoreString(&dtd->pool, + enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!tem) + return XML_ERROR_NO_MEMORY; + normalizePublicId(tem); + declEntity->publicId = tem; + poolFinish(&dtd->pool); + if (entityDeclHandler) + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_DOCTYPE_CLOSE: + if (doctypeName) { + startDoctypeDeclHandler(handlerArg, doctypeName, + doctypeSysid, doctypePubid, 0); + poolClear(&tempPool); + handleDefault = XML_FALSE; + } + /* doctypeSysid will be non-NULL in the case of a previous + XML_ROLE_DOCTYPE_SYSTEM_ID, even if startDoctypeDeclHandler + was not set, indicating an external subset + */ +#ifdef XML_DTD + if (doctypeSysid || useForeignDTD) { + XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; + dtd->hasParamEntityRefs = XML_TRUE; + if (paramEntityParsing && externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(parser, + &dtd->paramEntities, + externalSubsetName, + sizeof(ENTITY)); + if (!entity) + return XML_ERROR_NO_MEMORY; + if (useForeignDTD) + entity->base = curBase; + dtd->paramEntityRead = XML_FALSE; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + 0, + entity->base, + entity->systemId, + entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + if (dtd->paramEntityRead) { + if (!dtd->standalone && + notStandaloneHandler && + !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + /* if we didn't read the foreign DTD then this means that there + is no external subset and we must reset dtd->hasParamEntityRefs + */ + else if (!doctypeSysid) + dtd->hasParamEntityRefs = hadParamEntityRefs; + /* end of DTD - no need to update dtd->keepProcessing */ + } + useForeignDTD = XML_FALSE; + } +#endif /* XML_DTD */ + if (endDoctypeDeclHandler) { + endDoctypeDeclHandler(handlerArg); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_INSTANCE_START: +#ifdef XML_DTD + /* if there is no DOCTYPE declaration then now is the + last chance to read the foreign DTD + */ + if (useForeignDTD) { + XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; + dtd->hasParamEntityRefs = XML_TRUE; + if (paramEntityParsing && externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, + externalSubsetName, + sizeof(ENTITY)); + if (!entity) + return XML_ERROR_NO_MEMORY; + entity->base = curBase; + dtd->paramEntityRead = XML_FALSE; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + 0, + entity->base, + entity->systemId, + entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + if (dtd->paramEntityRead) { + if (!dtd->standalone && + notStandaloneHandler && + !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + /* if we didn't read the foreign DTD then this means that there + is no external subset and we must reset dtd->hasParamEntityRefs + */ + else + dtd->hasParamEntityRefs = hadParamEntityRefs; + /* end of DTD - no need to update dtd->keepProcessing */ + } + } +#endif /* XML_DTD */ + processor = contentProcessor; + return contentProcessor(parser, s, end, nextPtr); + case XML_ROLE_ATTLIST_ELEMENT_NAME: + declElementType = getElementType(parser, enc, s, next); + if (!declElementType) + return XML_ERROR_NO_MEMORY; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_NAME: + declAttributeId = getAttributeId(parser, enc, s, next); + if (!declAttributeId) + return XML_ERROR_NO_MEMORY; + declAttributeIsCdata = XML_FALSE; + declAttributeType = NULL; + declAttributeIsId = XML_FALSE; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_CDATA: + declAttributeIsCdata = XML_TRUE; + declAttributeType = atypeCDATA; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_ID: + declAttributeIsId = XML_TRUE; + declAttributeType = atypeID; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_IDREF: + declAttributeType = atypeIDREF; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_IDREFS: + declAttributeType = atypeIDREFS; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_ENTITY: + declAttributeType = atypeENTITY; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES: + declAttributeType = atypeENTITIES; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN: + declAttributeType = atypeNMTOKEN; + goto checkAttListDeclHandler; + case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS: + declAttributeType = atypeNMTOKENS; + checkAttListDeclHandler: + if (dtd->keepProcessing && attlistDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ATTRIBUTE_ENUM_VALUE: + case XML_ROLE_ATTRIBUTE_NOTATION_VALUE: + if (dtd->keepProcessing && attlistDeclHandler) { + const XML_Char *prefix; + if (declAttributeType) { + prefix = enumValueSep; + } + else { + prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE + ? notationPrefix + : enumValueStart); + } + if (!poolAppendString(&tempPool, prefix)) + return XML_ERROR_NO_MEMORY; + if (!poolAppend(&tempPool, enc, s, next)) + return XML_ERROR_NO_MEMORY; + declAttributeType = tempPool.start; + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE: + case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: + if (dtd->keepProcessing) { + if (!defineAttribute(declElementType, declAttributeId, + declAttributeIsCdata, declAttributeIsId, + 0, parser)) + return XML_ERROR_NO_MEMORY; + if (attlistDeclHandler && declAttributeType) { + if (*declAttributeType == XML_T(ASCII_LPAREN) + || (*declAttributeType == XML_T(ASCII_N) + && declAttributeType[1] == XML_T(ASCII_O))) { + /* Enumerated or Notation type */ + if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN)) + || !poolAppendChar(&tempPool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + declAttributeType = tempPool.start; + poolFinish(&tempPool); + } + *eventEndPP = s; + attlistDeclHandler(handlerArg, declElementType->name, + declAttributeId->name, declAttributeType, + 0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); + poolClear(&tempPool); + handleDefault = XML_FALSE; + } + } + break; + case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE: + case XML_ROLE_FIXED_ATTRIBUTE_VALUE: + if (dtd->keepProcessing) { + const XML_Char *attVal; + enum XML_Error result = + storeAttributeValue(parser, enc, declAttributeIsCdata, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar, + &dtd->pool); + if (result) + return result; + attVal = poolStart(&dtd->pool); + poolFinish(&dtd->pool); + /* ID attributes aren't allowed to have a default */ + if (!defineAttribute(declElementType, declAttributeId, + declAttributeIsCdata, XML_FALSE, attVal, parser)) + return XML_ERROR_NO_MEMORY; + if (attlistDeclHandler && declAttributeType) { + if (*declAttributeType == XML_T(ASCII_LPAREN) + || (*declAttributeType == XML_T(ASCII_N) + && declAttributeType[1] == XML_T(ASCII_O))) { + /* Enumerated or Notation type */ + if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN)) + || !poolAppendChar(&tempPool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + declAttributeType = tempPool.start; + poolFinish(&tempPool); + } + *eventEndPP = s; + attlistDeclHandler(handlerArg, declElementType->name, + declAttributeId->name, declAttributeType, + attVal, + role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); + poolClear(&tempPool); + handleDefault = XML_FALSE; + } + } + break; + case XML_ROLE_ENTITY_VALUE: + if (dtd->keepProcessing) { + enum XML_Error result = storeEntityValue(parser, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (declEntity) { + declEntity->textPtr = poolStart(&dtd->entityValuePool); + declEntity->textLen = (int)(poolLength(&dtd->entityValuePool)); + poolFinish(&dtd->entityValuePool); + if (entityDeclHandler) { + *eventEndPP = s; + entityDeclHandler(handlerArg, + declEntity->name, + declEntity->is_param, + declEntity->textPtr, + declEntity->textLen, + curBase, 0, 0, 0); + handleDefault = XML_FALSE; + } + } + else + poolDiscard(&dtd->entityValuePool); + if (result != XML_ERROR_NONE) + return result; + } + break; + case XML_ROLE_DOCTYPE_SYSTEM_ID: +#ifdef XML_DTD + useForeignDTD = XML_FALSE; +#endif /* XML_DTD */ + dtd->hasParamEntityRefs = XML_TRUE; + if (startDoctypeDeclHandler) { + doctypeSysid = poolStoreString(&tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (doctypeSysid == NULL) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + handleDefault = XML_FALSE; + } +#ifdef XML_DTD + else + /* use externalSubsetName to make doctypeSysid non-NULL + for the case where no startDoctypeDeclHandler is set */ + doctypeSysid = externalSubsetName; +#endif /* XML_DTD */ + if (!dtd->standalone +#ifdef XML_DTD + && !paramEntityParsing +#endif /* XML_DTD */ + && notStandaloneHandler + && !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; +#ifndef XML_DTD + break; +#else /* XML_DTD */ + if (!declEntity) { + declEntity = (ENTITY *)lookup(parser, + &dtd->paramEntities, + externalSubsetName, + sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; + declEntity->publicId = NULL; + } + /* fall through */ +#endif /* XML_DTD */ + case XML_ROLE_ENTITY_SYSTEM_ID: + if (dtd->keepProcessing && declEntity) { + declEntity->systemId = poolStoreString(&dtd->pool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!declEntity->systemId) + return XML_ERROR_NO_MEMORY; + declEntity->base = curBase; + poolFinish(&dtd->pool); + if (entityDeclHandler) + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_ENTITY_COMPLETE: + if (dtd->keepProcessing && declEntity && entityDeclHandler) { + *eventEndPP = s; + entityDeclHandler(handlerArg, + declEntity->name, + declEntity->is_param, + 0,0, + declEntity->base, + declEntity->systemId, + declEntity->publicId, + 0); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_ENTITY_NOTATION_NAME: + if (dtd->keepProcessing && declEntity) { + declEntity->notation = poolStoreString(&dtd->pool, enc, s, next); + if (!declEntity->notation) + return XML_ERROR_NO_MEMORY; + poolFinish(&dtd->pool); + if (unparsedEntityDeclHandler) { + *eventEndPP = s; + unparsedEntityDeclHandler(handlerArg, + declEntity->name, + declEntity->base, + declEntity->systemId, + declEntity->publicId, + declEntity->notation); + handleDefault = XML_FALSE; + } + else if (entityDeclHandler) { + *eventEndPP = s; + entityDeclHandler(handlerArg, + declEntity->name, + 0,0,0, + declEntity->base, + declEntity->systemId, + declEntity->publicId, + declEntity->notation); + handleDefault = XML_FALSE; + } + } + break; + case XML_ROLE_GENERAL_ENTITY_NAME: + { + if (XmlPredefinedEntityName(enc, s, next)) { + declEntity = NULL; + break; + } + if (dtd->keepProcessing) { + const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); + if (!name) + return XML_ERROR_NO_MEMORY; + declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, + sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; + if (declEntity->name != name) { + poolDiscard(&dtd->pool); + declEntity = NULL; + } + else { + poolFinish(&dtd->pool); + declEntity->publicId = NULL; + declEntity->is_param = XML_FALSE; + /* if we have a parent parser or are reading an internal parameter + entity, then the entity declaration is not considered "internal" + */ + declEntity->is_internal = !(parentParser || openInternalEntities); + if (entityDeclHandler) + handleDefault = XML_FALSE; + } + } + else { + poolDiscard(&dtd->pool); + declEntity = NULL; + } + } + break; + case XML_ROLE_PARAM_ENTITY_NAME: +#ifdef XML_DTD + if (dtd->keepProcessing) { + const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); + if (!name) + return XML_ERROR_NO_MEMORY; + declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities, + name, sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; + if (declEntity->name != name) { + poolDiscard(&dtd->pool); + declEntity = NULL; + } + else { + poolFinish(&dtd->pool); + declEntity->publicId = NULL; + declEntity->is_param = XML_TRUE; + /* if we have a parent parser or are reading an internal parameter + entity, then the entity declaration is not considered "internal" + */ + declEntity->is_internal = !(parentParser || openInternalEntities); + if (entityDeclHandler) + handleDefault = XML_FALSE; + } + } + else { + poolDiscard(&dtd->pool); + declEntity = NULL; + } +#else /* not XML_DTD */ + declEntity = NULL; +#endif /* XML_DTD */ + break; + case XML_ROLE_NOTATION_NAME: + declNotationPublicId = NULL; + declNotationName = NULL; + if (notationDeclHandler) { + declNotationName = poolStoreString(&tempPool, enc, s, next); + if (!declNotationName) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_NOTATION_PUBLIC_ID: + if (!XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_PUBLICID; + if (declNotationName) { /* means notationDeclHandler != NULL */ + XML_Char *tem = poolStoreString(&tempPool, + enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!tem) + return XML_ERROR_NO_MEMORY; + normalizePublicId(tem); + declNotationPublicId = tem; + poolFinish(&tempPool); + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_NOTATION_SYSTEM_ID: + if (declNotationName && notationDeclHandler) { + const XML_Char *systemId + = poolStoreString(&tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!systemId) + return XML_ERROR_NO_MEMORY; + *eventEndPP = s; + notationDeclHandler(handlerArg, + declNotationName, + curBase, + systemId, + declNotationPublicId); + handleDefault = XML_FALSE; + } + poolClear(&tempPool); + break; + case XML_ROLE_NOTATION_NO_SYSTEM_ID: + if (declNotationPublicId && notationDeclHandler) { + *eventEndPP = s; + notationDeclHandler(handlerArg, + declNotationName, + curBase, + 0, + declNotationPublicId); + handleDefault = XML_FALSE; + } + poolClear(&tempPool); + break; + case XML_ROLE_ERROR: + switch (tok) { + case XML_TOK_PARAM_ENTITY_REF: + /* PE references in internal subset are + not allowed within declarations. */ + return XML_ERROR_PARAM_ENTITY_REF; + case XML_TOK_XML_DECL: + return XML_ERROR_MISPLACED_XML_PI; + default: + return XML_ERROR_SYNTAX; + } +#ifdef XML_DTD + case XML_ROLE_IGNORE_SECT: + { + enum XML_Error result; + if (defaultHandler) + reportDefault(parser, enc, s, next); + handleDefault = XML_FALSE; + result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (!next) { + processor = ignoreSectionProcessor; + return result; + } + } + break; +#endif /* XML_DTD */ + case XML_ROLE_GROUP_OPEN: + if (prologState.level >= groupSize) { + if (groupSize) { + char *temp = (char *)REALLOC(groupConnector, groupSize *= 2); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + groupConnector = temp; + if (dtd->scaffIndex) { + int *temp = (int *)REALLOC(dtd->scaffIndex, + groupSize * sizeof(int)); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + dtd->scaffIndex = temp; + } + } + else { + groupConnector = (char *)MALLOC(groupSize = 32); + if (!groupConnector) + return XML_ERROR_NO_MEMORY; + } + } + groupConnector[prologState.level] = 0; + if (dtd->in_eldecl) { + int myindex = nextScaffoldPart(parser); + if (myindex < 0) + return XML_ERROR_NO_MEMORY; + dtd->scaffIndex[dtd->scaffLevel] = myindex; + dtd->scaffLevel++; + dtd->scaffold[myindex].type = XML_CTYPE_SEQ; + if (elementDeclHandler) + handleDefault = XML_FALSE; + } + break; + case XML_ROLE_GROUP_SEQUENCE: + if (groupConnector[prologState.level] == ASCII_PIPE) + return XML_ERROR_SYNTAX; + groupConnector[prologState.level] = ASCII_COMMA; + if (dtd->in_eldecl && elementDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_GROUP_CHOICE: + if (groupConnector[prologState.level] == ASCII_COMMA) + return XML_ERROR_SYNTAX; + if (dtd->in_eldecl + && !groupConnector[prologState.level] + && (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type + != XML_CTYPE_MIXED) + ) { + dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type + = XML_CTYPE_CHOICE; + if (elementDeclHandler) + handleDefault = XML_FALSE; + } + groupConnector[prologState.level] = ASCII_PIPE; + break; + case XML_ROLE_PARAM_ENTITY_REF: +#ifdef XML_DTD + case XML_ROLE_INNER_PARAM_ENTITY_REF: + dtd->hasParamEntityRefs = XML_TRUE; + if (!paramEntityParsing) + dtd->keepProcessing = dtd->standalone; + else { + const XML_Char *name; + ENTITY *entity; + name = poolStoreString(&dtd->pool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); + poolDiscard(&dtd->pool); + /* first, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal, + otherwise call the skipped entity handler + */ + if (prologState.documentEntity && + (dtd->standalone + ? !openInternalEntities + : !dtd->hasParamEntityRefs)) { + if (!entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (!entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } + else if (!entity) { + dtd->keepProcessing = dtd->standalone; + /* cannot report skipped entities in declarations */ + if ((role == XML_ROLE_PARAM_ENTITY_REF) && skippedEntityHandler) { + skippedEntityHandler(handlerArg, name, 1); + handleDefault = XML_FALSE; + } + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + XML_Bool betweenDecl = + (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); + result = processInternalEntity(parser, entity, betweenDecl); + if (result != XML_ERROR_NONE) + return result; + handleDefault = XML_FALSE; + break; + } + if (externalEntityRefHandler) { + dtd->paramEntityRead = XML_FALSE; + entity->open = XML_TRUE; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + 0, + entity->base, + entity->systemId, + entity->publicId)) { + entity->open = XML_FALSE; + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + } + entity->open = XML_FALSE; + handleDefault = XML_FALSE; + if (!dtd->paramEntityRead) { + dtd->keepProcessing = dtd->standalone; + break; + } + } + else { + dtd->keepProcessing = dtd->standalone; + break; + } + } +#endif /* XML_DTD */ + if (!dtd->standalone && + notStandaloneHandler && + !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + break; + + /* Element declaration stuff */ + + case XML_ROLE_ELEMENT_NAME: + if (elementDeclHandler) { + declElementType = getElementType(parser, enc, s, next); + if (!declElementType) + return XML_ERROR_NO_MEMORY; + dtd->scaffLevel = 0; + dtd->scaffCount = 0; + dtd->in_eldecl = XML_TRUE; + handleDefault = XML_FALSE; + } + break; + + case XML_ROLE_CONTENT_ANY: + case XML_ROLE_CONTENT_EMPTY: + if (dtd->in_eldecl) { + if (elementDeclHandler) { + XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content)); + if (!content) + return XML_ERROR_NO_MEMORY; + content->quant = XML_CQUANT_NONE; + content->name = NULL; + content->numchildren = 0; + content->children = NULL; + content->type = ((role == XML_ROLE_CONTENT_ANY) ? + XML_CTYPE_ANY : + XML_CTYPE_EMPTY); + *eventEndPP = s; + elementDeclHandler(handlerArg, declElementType->name, content); + handleDefault = XML_FALSE; + } + dtd->in_eldecl = XML_FALSE; + } + break; + + case XML_ROLE_CONTENT_PCDATA: + if (dtd->in_eldecl) { + dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type + = XML_CTYPE_MIXED; + if (elementDeclHandler) + handleDefault = XML_FALSE; + } + break; + + case XML_ROLE_CONTENT_ELEMENT: + quant = XML_CQUANT_NONE; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_OPT: + quant = XML_CQUANT_OPT; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_REP: + quant = XML_CQUANT_REP; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_PLUS: + quant = XML_CQUANT_PLUS; + elementContent: + if (dtd->in_eldecl) { + ELEMENT_TYPE *el; + const XML_Char *name; + int nameLen; + const char *nxt = (quant == XML_CQUANT_NONE + ? next + : next - enc->minBytesPerChar); + int myindex = nextScaffoldPart(parser); + if (myindex < 0) + return XML_ERROR_NO_MEMORY; + dtd->scaffold[myindex].type = XML_CTYPE_NAME; + dtd->scaffold[myindex].quant = quant; + el = getElementType(parser, enc, s, nxt); + if (!el) + return XML_ERROR_NO_MEMORY; + name = el->name; + dtd->scaffold[myindex].name = name; + nameLen = 0; + for (; name[nameLen++]; ); + dtd->contentStringLen += nameLen; + if (elementDeclHandler) + handleDefault = XML_FALSE; + } + break; + + case XML_ROLE_GROUP_CLOSE: + quant = XML_CQUANT_NONE; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_OPT: + quant = XML_CQUANT_OPT; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_REP: + quant = XML_CQUANT_REP; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_PLUS: + quant = XML_CQUANT_PLUS; + closeGroup: + if (dtd->in_eldecl) { + if (elementDeclHandler) + handleDefault = XML_FALSE; + dtd->scaffLevel--; + dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant; + if (dtd->scaffLevel == 0) { + if (!handleDefault) { + XML_Content *model = build_model(parser); + if (!model) + return XML_ERROR_NO_MEMORY; + *eventEndPP = s; + elementDeclHandler(handlerArg, declElementType->name, model); + } + dtd->in_eldecl = XML_FALSE; + dtd->contentStringLen = 0; + } + } + break; + /* End element declaration stuff */ + + case XML_ROLE_PI: + if (!reportProcessingInstruction(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + handleDefault = XML_FALSE; + break; + case XML_ROLE_COMMENT: + if (!reportComment(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + handleDefault = XML_FALSE; + break; + case XML_ROLE_NONE: + switch (tok) { + case XML_TOK_BOM: + handleDefault = XML_FALSE; + break; + } + break; + case XML_ROLE_DOCTYPE_NONE: + if (startDoctypeDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ENTITY_NONE: + if (dtd->keepProcessing && entityDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_NOTATION_NONE: + if (notationDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ATTLIST_NONE: + if (dtd->keepProcessing && attlistDeclHandler) + handleDefault = XML_FALSE; + break; + case XML_ROLE_ELEMENT_NONE: + if (elementDeclHandler) + handleDefault = XML_FALSE; + break; + } /* end of big switch */ + + if (handleDefault && defaultHandler) + reportDefault(parser, enc, s, next); + + switch (ps_parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + s = next; + tok = XmlPrologTok(enc, s, end, &next); + } + } + /* not reached */ +} + +static enum XML_Error PTRCALL +epilogProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + processor = epilogProcessor; + eventPtr = s; + for (;;) { + const char *next = NULL; + int tok = XmlPrologTok(encoding, s, end, &next); + eventEndPtr = next; + switch (tok) { + /* report partial linebreak - it might be the last token */ + case -XML_TOK_PROLOG_S: + if (defaultHandler) { + reportDefault(parser, encoding, s, next); + if (ps_parsing == XML_FINISHED) + return XML_ERROR_ABORTED; + } + *nextPtr = next; + return XML_ERROR_NONE; + case XML_TOK_NONE: + *nextPtr = s; + return XML_ERROR_NONE; + case XML_TOK_PROLOG_S: + if (defaultHandler) + reportDefault(parser, encoding, s, next); + break; + case XML_TOK_PI: + if (!reportProcessingInstruction(parser, encoding, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (!reportComment(parser, encoding, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_INVALID: + eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (!ps_finalBuffer) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (!ps_finalBuffer) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + default: + return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; + } + eventPtr = s = next; + switch (ps_parsing) { + case XML_SUSPENDED: + *nextPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: ; + } + } +} + +static enum XML_Error +processInternalEntity(XML_Parser parser, ENTITY *entity, + XML_Bool betweenDecl) +{ + const char *textStart, *textEnd; + const char *next; + enum XML_Error result; + OPEN_INTERNAL_ENTITY *openEntity; + + if (freeInternalEntities) { + openEntity = freeInternalEntities; + freeInternalEntities = openEntity->next; + } + else { + openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(sizeof(OPEN_INTERNAL_ENTITY)); + if (!openEntity) + return XML_ERROR_NO_MEMORY; + } + entity->open = XML_TRUE; + entity->processed = 0; + openEntity->next = openInternalEntities; + openInternalEntities = openEntity; + openEntity->entity = entity; + openEntity->startTagLevel = tagLevel; + openEntity->betweenDecl = betweenDecl; + openEntity->internalEventPtr = NULL; + openEntity->internalEventEndPtr = NULL; + textStart = (char *)entity->textPtr; + textEnd = (char *)(entity->textPtr + entity->textLen); + +#ifdef XML_DTD + if (entity->is_param) { + int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, internalEncoding, textStart, textEnd, tok, + next, &next, XML_FALSE); + } + else +#endif /* XML_DTD */ + result = doContent(parser, tagLevel, internalEncoding, textStart, + textEnd, &next, XML_FALSE); + + if (result == XML_ERROR_NONE) { + if (textEnd != next && ps_parsing == XML_SUSPENDED) { + entity->processed = (int)(next - textStart); + processor = internalEntityProcessor; + } + else { + entity->open = XML_FALSE; + openInternalEntities = openEntity->next; + /* put openEntity back in list of free instances */ + openEntity->next = freeInternalEntities; + freeInternalEntities = openEntity; + } + } + return result; +} + +static enum XML_Error PTRCALL +internalEntityProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + ENTITY *entity; + const char *textStart, *textEnd; + const char *next; + enum XML_Error result; + OPEN_INTERNAL_ENTITY *openEntity = openInternalEntities; + if (!openEntity) + return XML_ERROR_UNEXPECTED_STATE; + + entity = openEntity->entity; + textStart = ((char *)entity->textPtr) + entity->processed; + textEnd = (char *)(entity->textPtr + entity->textLen); + +#ifdef XML_DTD + if (entity->is_param) { + int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, internalEncoding, textStart, textEnd, tok, + next, &next, XML_FALSE); + } + else +#endif /* XML_DTD */ + result = doContent(parser, openEntity->startTagLevel, internalEncoding, + textStart, textEnd, &next, XML_FALSE); + + if (result != XML_ERROR_NONE) + return result; + else if (textEnd != next && ps_parsing == XML_SUSPENDED) { + entity->processed = (int)(next - (char *)entity->textPtr); + return result; + } + else { + entity->open = XML_FALSE; + openInternalEntities = openEntity->next; + /* put openEntity back in list of free instances */ + openEntity->next = freeInternalEntities; + freeInternalEntities = openEntity; + } + +#ifdef XML_DTD + if (entity->is_param) { + int tok; + processor = prologProcessor; + tok = XmlPrologTok(encoding, s, end, &next); + return doProlog(parser, encoding, s, end, tok, next, nextPtr, + (XML_Bool)!ps_finalBuffer); + } + else +#endif /* XML_DTD */ + { + processor = contentProcessor; + /* see externalEntityContentProcessor vs contentProcessor */ + return doContent(parser, parentParser ? 1 : 0, encoding, s, end, + nextPtr, (XML_Bool)!ps_finalBuffer); + } +} + +static enum XML_Error PTRCALL +errorProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + return errorCode; +} + +static enum XML_Error +storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, + const char *ptr, const char *end, + STRING_POOL *pool) +{ + enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, + end, pool); + if (result) + return result; + if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) + poolChop(pool); + if (!poolAppendChar(pool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + return XML_ERROR_NONE; +} + +static enum XML_Error +appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, + const char *ptr, const char *end, + STRING_POOL *pool) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + for (;;) { + const char *next; + int tok = XmlAttributeValueTok(enc, ptr, end, &next); + switch (tok) { + case XML_TOK_NONE: + return XML_ERROR_NONE; + case XML_TOK_INVALID: + if (enc == encoding) + eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_CHAR_REF: + { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, ptr); + if (n < 0) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; + } + if (!isCdata + && n == 0x20 /* space */ + && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + n = XmlEncode(n, (ICHAR *)buf); + if (!n) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; + } + for (i = 0; i < n; i++) { + if (!poolAppendChar(pool, buf[i])) + return XML_ERROR_NO_MEMORY; + } + } + break; + case XML_TOK_DATA_CHARS: + if (!poolAppend(pool, enc, ptr, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_TRAILING_CR: + next = ptr + enc->minBytesPerChar; + /* fall through */ + case XML_TOK_ATTRIBUTE_VALUE_S: + case XML_TOK_DATA_NEWLINE: + if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + if (!poolAppendChar(pool, 0x20)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_ENTITY_REF: + { + const XML_Char *name; + ENTITY *entity; + char checkEntityDecl; + XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (ch) { + if (!poolAppendChar(pool, ch)) + return XML_ERROR_NO_MEMORY; + break; + } + name = poolStoreString(&temp2Pool, enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&temp2Pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal. + */ + if (pool == &dtd->pool) /* are we called from prolog? */ + checkEntityDecl = +#ifdef XML_DTD + prologState.documentEntity && +#endif /* XML_DTD */ + (dtd->standalone + ? !openInternalEntities + : !dtd->hasParamEntityRefs); + else /* if (pool == &tempPool): we are called from content */ + checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone; + if (checkEntityDecl) { + if (!entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (!entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } + else if (!entity) { + /* Cannot report skipped entity here - see comments on + skippedEntityHandler. + if (skippedEntityHandler) + skippedEntityHandler(handlerArg, name, 0); + */ + /* Cannot call the default handler because this would be + out of sync with the call to the startElementHandler. + if ((pool == &tempPool) && defaultHandler) + reportDefault(parser, enc, ptr, next); + */ + break; + } + if (entity->open) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_RECURSIVE_ENTITY_REF; + } + if (entity->notation) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_BINARY_ENTITY_REF; + } + if (!entity->textPtr) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; + } + else { + enum XML_Error result; + const XML_Char *textEnd = entity->textPtr + entity->textLen; + entity->open = XML_TRUE; + result = appendAttributeValue(parser, internalEncoding, isCdata, + (char *)entity->textPtr, + (char *)textEnd, pool); + entity->open = XML_FALSE; + if (result) + return result; + } + } + break; + default: + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_UNEXPECTED_STATE; + } + ptr = next; + } + /* not reached */ +} + +static enum XML_Error +storeEntityValue(XML_Parser parser, + const ENCODING *enc, + const char *entityTextPtr, + const char *entityTextEnd) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + STRING_POOL *pool = &(dtd->entityValuePool); + enum XML_Error result = XML_ERROR_NONE; +#ifdef XML_DTD + int oldInEntityValue = prologState.inEntityValue; + prologState.inEntityValue = 1; +#endif /* XML_DTD */ + /* never return Null for the value argument in EntityDeclHandler, + since this would indicate an external entity; therefore we + have to make sure that entityValuePool.start is not null */ + if (!pool->blocks) { + if (!poolGrow(pool)) + return XML_ERROR_NO_MEMORY; + } + + for (;;) { + const char *next; + int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next); + switch (tok) { + case XML_TOK_PARAM_ENTITY_REF: +#ifdef XML_DTD + if (isParamEntity || enc != encoding) { + const XML_Char *name; + ENTITY *entity; + name = poolStoreString(&tempPool, enc, + entityTextPtr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); + poolDiscard(&tempPool); + if (!entity) { + /* not a well-formedness error - see XML 1.0: WFC Entity Declared */ + /* cannot report skipped entity here - see comments on + skippedEntityHandler + if (skippedEntityHandler) + skippedEntityHandler(handlerArg, name, 0); + */ + dtd->keepProcessing = dtd->standalone; + goto endEntityValue; + } + if (entity->open) { + if (enc == encoding) + eventPtr = entityTextPtr; + result = XML_ERROR_RECURSIVE_ENTITY_REF; + goto endEntityValue; + } + if (entity->systemId) { + if (externalEntityRefHandler) { + dtd->paramEntityRead = XML_FALSE; + entity->open = XML_TRUE; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + 0, + entity->base, + entity->systemId, + entity->publicId)) { + entity->open = XML_FALSE; + result = XML_ERROR_EXTERNAL_ENTITY_HANDLING; + goto endEntityValue; + } + entity->open = XML_FALSE; + if (!dtd->paramEntityRead) + dtd->keepProcessing = dtd->standalone; + } + else + dtd->keepProcessing = dtd->standalone; + } + else { + entity->open = XML_TRUE; + result = storeEntityValue(parser, + internalEncoding, + (char *)entity->textPtr, + (char *)(entity->textPtr + + entity->textLen)); + entity->open = XML_FALSE; + if (result) + goto endEntityValue; + } + break; + } +#endif /* XML_DTD */ + /* In the internal subset, PE references are not legal + within markup declarations, e.g entity values in this case. */ + eventPtr = entityTextPtr; + result = XML_ERROR_PARAM_ENTITY_REF; + goto endEntityValue; + case XML_TOK_NONE: + result = XML_ERROR_NONE; + goto endEntityValue; + case XML_TOK_ENTITY_REF: + case XML_TOK_DATA_CHARS: + if (!poolAppend(pool, enc, entityTextPtr, next)) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + break; + case XML_TOK_TRAILING_CR: + next = entityTextPtr + enc->minBytesPerChar; + /* fall through */ + case XML_TOK_DATA_NEWLINE: + if (pool->end == pool->ptr && !poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + *(pool->ptr)++ = 0xA; + break; + case XML_TOK_CHAR_REF: + { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, entityTextPtr); + if (n < 0) { + if (enc == encoding) + eventPtr = entityTextPtr; + result = XML_ERROR_BAD_CHAR_REF; + goto endEntityValue; + } + n = XmlEncode(n, (ICHAR *)buf); + if (!n) { + if (enc == encoding) + eventPtr = entityTextPtr; + result = XML_ERROR_BAD_CHAR_REF; + goto endEntityValue; + } + for (i = 0; i < n; i++) { + if (pool->end == pool->ptr && !poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; + goto endEntityValue; + } + *(pool->ptr)++ = buf[i]; + } + } + break; + case XML_TOK_PARTIAL: + if (enc == encoding) + eventPtr = entityTextPtr; + result = XML_ERROR_INVALID_TOKEN; + goto endEntityValue; + case XML_TOK_INVALID: + if (enc == encoding) + eventPtr = next; + result = XML_ERROR_INVALID_TOKEN; + goto endEntityValue; + default: + if (enc == encoding) + eventPtr = entityTextPtr; + result = XML_ERROR_UNEXPECTED_STATE; + goto endEntityValue; + } + entityTextPtr = next; + } +endEntityValue: +#ifdef XML_DTD + prologState.inEntityValue = oldInEntityValue; +#endif /* XML_DTD */ + return result; +} + +static void FASTCALL +normalizeLines(XML_Char *s) +{ + XML_Char *p; + for (;; s++) { + if (*s == XML_T('\0')) + return; + if (*s == 0xD) + break; + } + p = s; + do { + if (*s == 0xD) { + *p++ = 0xA; + if (*++s == 0xA) + s++; + } + else + *p++ = *s++; + } while (*s); + *p = XML_T('\0'); +} + +static int +reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end) +{ + const XML_Char *target; + XML_Char *data; + const char *tem; + if (!processingInstructionHandler) { + if (defaultHandler) + reportDefault(parser, enc, start, end); + return 1; + } + start += enc->minBytesPerChar * 2; + tem = start + XmlNameLength(enc, start); + target = poolStoreString(&tempPool, enc, start, tem); + if (!target) + return 0; + poolFinish(&tempPool); + data = poolStoreString(&tempPool, enc, + XmlSkipS(enc, tem), + end - enc->minBytesPerChar*2); + if (!data) + return 0; + normalizeLines(data); + processingInstructionHandler(handlerArg, target, data); + poolClear(&tempPool); + return 1; +} + +static int +reportComment(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end) +{ + XML_Char *data; + if (!commentHandler) { + if (defaultHandler) + reportDefault(parser, enc, start, end); + return 1; + } + data = poolStoreString(&tempPool, + enc, + start + enc->minBytesPerChar * 4, + end - enc->minBytesPerChar * 3); + if (!data) + return 0; + normalizeLines(data); + commentHandler(handlerArg, data); + poolClear(&tempPool); + return 1; +} + +static void +reportDefault(XML_Parser parser, const ENCODING *enc, + const char *s, const char *end) +{ + if (MUST_CONVERT(enc, s)) { + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + do { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); + *eventEndPP = s; + defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf)); + *eventPP = s; + } while (s != end); + } + else + defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s)); +} + + +static int +defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, + XML_Bool isId, const XML_Char *value, XML_Parser parser) +{ + DEFAULT_ATTRIBUTE *att; + if (value || isId) { + /* The handling of default attributes gets messed up if we have + a default which duplicates a non-default. */ + int i; + for (i = 0; i < type->nDefaultAtts; i++) + if (attId == type->defaultAtts[i].id) + return 1; + if (isId && !type->idAtt && !attId->xmlns) + type->idAtt = attId; + } + if (type->nDefaultAtts == type->allocDefaultAtts) { + if (type->allocDefaultAtts == 0) { + type->allocDefaultAtts = 8; + type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(type->allocDefaultAtts + * sizeof(DEFAULT_ATTRIBUTE)); + if (!type->defaultAtts) + return 0; + } + else { + DEFAULT_ATTRIBUTE *temp; + int count = type->allocDefaultAtts * 2; + temp = (DEFAULT_ATTRIBUTE *) + REALLOC(type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE))); + if (temp == NULL) + return 0; + type->allocDefaultAtts = count; + type->defaultAtts = temp; + } + } + att = type->defaultAtts + type->nDefaultAtts; + att->id = attId; + att->value = value; + att->isCdata = isCdata; + if (!isCdata) + attId->maybeTokenized = XML_TRUE; + type->nDefaultAtts += 1; + return 1; +} + +static int +setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + const XML_Char *name; + for (name = elementType->name; *name; name++) { + if (*name == XML_T(ASCII_COLON)) { + PREFIX *prefix; + const XML_Char *s; + for (s = elementType->name; s != name; s++) { + if (!poolAppendChar(&dtd->pool, *s)) + return 0; + } + if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + return 0; + prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), + sizeof(PREFIX)); + if (!prefix) + return 0; + if (prefix->name == poolStart(&dtd->pool)) + poolFinish(&dtd->pool); + else + poolDiscard(&dtd->pool); + elementType->prefix = prefix; + + } + } + return 1; +} + +static ATTRIBUTE_ID * +getAttributeId(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + ATTRIBUTE_ID *id; + const XML_Char *name; + if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + return NULL; + name = poolStoreString(&dtd->pool, enc, start, end); + if (!name) + return NULL; + /* skip quotation mark - its storage will be re-used (like in name[-1]) */ + ++name; + id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, sizeof(ATTRIBUTE_ID)); + if (!id) + return NULL; + if (id->name != name) + poolDiscard(&dtd->pool); + else { + poolFinish(&dtd->pool); + if (!ns) + ; + else if (name[0] == XML_T(ASCII_x) + && name[1] == XML_T(ASCII_m) + && name[2] == XML_T(ASCII_l) + && name[3] == XML_T(ASCII_n) + && name[4] == XML_T(ASCII_s) + && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { + if (name[5] == XML_T('\0')) + id->prefix = &dtd->defaultPrefix; + else + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, sizeof(PREFIX)); + id->xmlns = XML_TRUE; + } + else { + int i; + for (i = 0; name[i]; i++) { + /* attributes without prefix are *not* in the default namespace */ + if (name[i] == XML_T(ASCII_COLON)) { + int j; + for (j = 0; j < i; j++) { + if (!poolAppendChar(&dtd->pool, name[j])) + return NULL; + } + if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + return NULL; + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), + sizeof(PREFIX)); + if (id->prefix->name == poolStart(&dtd->pool)) + poolFinish(&dtd->pool); + else + poolDiscard(&dtd->pool); + break; + } + } + } + } + return id; +} + +#define CONTEXT_SEP XML_T(ASCII_FF) + +static const XML_Char * +getContext(XML_Parser parser) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + HASH_TABLE_ITER iter; + XML_Bool needSep = XML_FALSE; + + if (dtd->defaultPrefix.binding) { + int i; + int len; + if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS))) + return NULL; + len = dtd->defaultPrefix.binding->uriLen; + if (namespaceSeparator) + len--; + for (i = 0; i < len; i++) + if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i])) + return NULL; + needSep = XML_TRUE; + } + + hashTableIterInit(&iter, &(dtd->prefixes)); + for (;;) { + int i; + int len; + const XML_Char *s; + PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter); + if (!prefix) + break; + if (!prefix->binding) + continue; + if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) + return NULL; + for (s = prefix->name; *s; s++) + if (!poolAppendChar(&tempPool, *s)) + return NULL; + if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS))) + return NULL; + len = prefix->binding->uriLen; + if (namespaceSeparator) + len--; + for (i = 0; i < len; i++) + if (!poolAppendChar(&tempPool, prefix->binding->uri[i])) + return NULL; + needSep = XML_TRUE; + } + + + hashTableIterInit(&iter, &(dtd->generalEntities)); + for (;;) { + const XML_Char *s; + ENTITY *e = (ENTITY *)hashTableIterNext(&iter); + if (!e) + break; + if (!e->open) + continue; + if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) + return NULL; + for (s = e->name; *s; s++) + if (!poolAppendChar(&tempPool, *s)) + return 0; + needSep = XML_TRUE; + } + + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return NULL; + return tempPool.start; +} + +static XML_Bool +setContext(XML_Parser parser, const XML_Char *context) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + const XML_Char *s = context; + + while (*context != XML_T('\0')) { + if (*s == CONTEXT_SEP || *s == XML_T('\0')) { + ENTITY *e; + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return XML_FALSE; + e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&tempPool), 0); + if (e) + e->open = XML_TRUE; + if (*s != XML_T('\0')) + s++; + context = s; + poolDiscard(&tempPool); + } + else if (*s == XML_T(ASCII_EQUALS)) { + PREFIX *prefix; + if (poolLength(&tempPool) == 0) + prefix = &dtd->defaultPrefix; + else { + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return XML_FALSE; + prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&tempPool), + sizeof(PREFIX)); + if (!prefix) + return XML_FALSE; + if (prefix->name == poolStart(&tempPool)) { + prefix->name = poolCopyString(&dtd->pool, prefix->name); + if (!prefix->name) + return XML_FALSE; + } + poolDiscard(&tempPool); + } + for (context = s + 1; + *context != CONTEXT_SEP && *context != XML_T('\0'); + context++) + if (!poolAppendChar(&tempPool, *context)) + return XML_FALSE; + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return XML_FALSE; + if (addBinding(parser, prefix, NULL, poolStart(&tempPool), + &inheritedBindings) != XML_ERROR_NONE) + return XML_FALSE; + poolDiscard(&tempPool); + if (*context != XML_T('\0')) + ++context; + s = context; + } + else { + if (!poolAppendChar(&tempPool, *s)) + return XML_FALSE; + s++; + } + } + return XML_TRUE; +} + +static void FASTCALL +normalizePublicId(XML_Char *publicId) +{ + XML_Char *p = publicId; + XML_Char *s; + for (s = publicId; *s; s++) { + switch (*s) { + case 0x20: + case 0xD: + case 0xA: + if (p != publicId && p[-1] != 0x20) + *p++ = 0x20; + break; + default: + *p++ = *s; + } + } + if (p != publicId && p[-1] == 0x20) + --p; + *p = XML_T('\0'); +} + +static DTD * +dtdCreate(const XML_Memory_Handling_Suite *ms) +{ + DTD *p = (DTD *)ms->malloc_fcn(sizeof(DTD)); + if (p == NULL) + return p; + poolInit(&(p->pool), ms); + poolInit(&(p->entityValuePool), ms); + hashTableInit(&(p->generalEntities), ms); + hashTableInit(&(p->elementTypes), ms); + hashTableInit(&(p->attributeIds), ms); + hashTableInit(&(p->prefixes), ms); +#ifdef XML_DTD + p->paramEntityRead = XML_FALSE; + hashTableInit(&(p->paramEntities), ms); +#endif /* XML_DTD */ + p->defaultPrefix.name = NULL; + p->defaultPrefix.binding = NULL; + + p->in_eldecl = XML_FALSE; + p->scaffIndex = NULL; + p->scaffold = NULL; + p->scaffLevel = 0; + p->scaffSize = 0; + p->scaffCount = 0; + p->contentStringLen = 0; + + p->keepProcessing = XML_TRUE; + p->hasParamEntityRefs = XML_FALSE; + p->standalone = XML_FALSE; + return p; +} + +static void +dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) +{ + HASH_TABLE_ITER iter; + hashTableIterInit(&iter, &(p->elementTypes)); + for (;;) { + ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (!e) + break; + if (e->allocDefaultAtts != 0) + ms->free_fcn(e->defaultAtts); + } + hashTableClear(&(p->generalEntities)); +#ifdef XML_DTD + p->paramEntityRead = XML_FALSE; + hashTableClear(&(p->paramEntities)); +#endif /* XML_DTD */ + hashTableClear(&(p->elementTypes)); + hashTableClear(&(p->attributeIds)); + hashTableClear(&(p->prefixes)); + poolClear(&(p->pool)); + poolClear(&(p->entityValuePool)); + p->defaultPrefix.name = NULL; + p->defaultPrefix.binding = NULL; + + p->in_eldecl = XML_FALSE; + + ms->free_fcn(p->scaffIndex); + p->scaffIndex = NULL; + ms->free_fcn(p->scaffold); + p->scaffold = NULL; + + p->scaffLevel = 0; + p->scaffSize = 0; + p->scaffCount = 0; + p->contentStringLen = 0; + + p->keepProcessing = XML_TRUE; + p->hasParamEntityRefs = XML_FALSE; + p->standalone = XML_FALSE; +} + +static void +dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) +{ + HASH_TABLE_ITER iter; + hashTableIterInit(&iter, &(p->elementTypes)); + for (;;) { + ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (!e) + break; + if (e->allocDefaultAtts != 0) + ms->free_fcn(e->defaultAtts); + } + hashTableDestroy(&(p->generalEntities)); +#ifdef XML_DTD + hashTableDestroy(&(p->paramEntities)); +#endif /* XML_DTD */ + hashTableDestroy(&(p->elementTypes)); + hashTableDestroy(&(p->attributeIds)); + hashTableDestroy(&(p->prefixes)); + poolDestroy(&(p->pool)); + poolDestroy(&(p->entityValuePool)); + if (isDocEntity) { + ms->free_fcn(p->scaffIndex); + ms->free_fcn(p->scaffold); + } + ms->free_fcn(p); +} + +/* Do a deep copy of the DTD. Return 0 for out of memory, non-zero otherwise. + The new DTD has already been initialized. +*/ +static int +dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms) +{ + HASH_TABLE_ITER iter; + + /* Copy the prefix table. */ + + hashTableIterInit(&iter, &(oldDtd->prefixes)); + for (;;) { + const XML_Char *name; + const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter); + if (!oldP) + break; + name = poolCopyString(&(newDtd->pool), oldP->name); + if (!name) + return 0; + if (!lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) + return 0; + } + + hashTableIterInit(&iter, &(oldDtd->attributeIds)); + + /* Copy the attribute id table. */ + + for (;;) { + ATTRIBUTE_ID *newA; + const XML_Char *name; + const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter); + + if (!oldA) + break; + /* Remember to allocate the scratch byte before the name. */ + if (!poolAppendChar(&(newDtd->pool), XML_T('\0'))) + return 0; + name = poolCopyString(&(newDtd->pool), oldA->name); + if (!name) + return 0; + ++name; + newA = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), name, + sizeof(ATTRIBUTE_ID)); + if (!newA) + return 0; + newA->maybeTokenized = oldA->maybeTokenized; + if (oldA->prefix) { + newA->xmlns = oldA->xmlns; + if (oldA->prefix == &oldDtd->defaultPrefix) + newA->prefix = &newDtd->defaultPrefix; + else + newA->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), + oldA->prefix->name, 0); + } + } + + /* Copy the element type table. */ + + hashTableIterInit(&iter, &(oldDtd->elementTypes)); + + for (;;) { + int i; + ELEMENT_TYPE *newE; + const XML_Char *name; + const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (!oldE) + break; + name = poolCopyString(&(newDtd->pool), oldE->name); + if (!name) + return 0; + newE = (ELEMENT_TYPE *)lookup(oldParser, &(newDtd->elementTypes), name, + sizeof(ELEMENT_TYPE)); + if (!newE) + return 0; + if (oldE->nDefaultAtts) { + newE->defaultAtts = (DEFAULT_ATTRIBUTE *) + ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (!newE->defaultAtts) { + ms->free_fcn(newE); + return 0; + } + } + if (oldE->idAtt) + newE->idAtt = (ATTRIBUTE_ID *) + lookup(oldParser, &(newDtd->attributeIds), oldE->idAtt->name, 0); + newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts; + if (oldE->prefix) + newE->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), + oldE->prefix->name, 0); + for (i = 0; i < newE->nDefaultAtts; i++) { + newE->defaultAtts[i].id = (ATTRIBUTE_ID *) + lookup(oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); + newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata; + if (oldE->defaultAtts[i].value) { + newE->defaultAtts[i].value + = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value); + if (!newE->defaultAtts[i].value) + return 0; + } + else + newE->defaultAtts[i].value = NULL; + } + } + + /* Copy the entity tables. */ + if (!copyEntityTable(oldParser, + &(newDtd->generalEntities), + &(newDtd->pool), + &(oldDtd->generalEntities))) + return 0; + +#ifdef XML_DTD + if (!copyEntityTable(oldParser, + &(newDtd->paramEntities), + &(newDtd->pool), + &(oldDtd->paramEntities))) + return 0; + newDtd->paramEntityRead = oldDtd->paramEntityRead; +#endif /* XML_DTD */ + + newDtd->keepProcessing = oldDtd->keepProcessing; + newDtd->hasParamEntityRefs = oldDtd->hasParamEntityRefs; + newDtd->standalone = oldDtd->standalone; + + /* Don't want deep copying for scaffolding */ + newDtd->in_eldecl = oldDtd->in_eldecl; + newDtd->scaffold = oldDtd->scaffold; + newDtd->contentStringLen = oldDtd->contentStringLen; + newDtd->scaffSize = oldDtd->scaffSize; + newDtd->scaffLevel = oldDtd->scaffLevel; + newDtd->scaffIndex = oldDtd->scaffIndex; + + return 1; +} /* End dtdCopy */ + +static int +copyEntityTable(XML_Parser oldParser, + HASH_TABLE *newTable, + STRING_POOL *newPool, + const HASH_TABLE *oldTable) +{ + HASH_TABLE_ITER iter; + const XML_Char *cachedOldBase = NULL; + const XML_Char *cachedNewBase = NULL; + + hashTableIterInit(&iter, oldTable); + + for (;;) { + ENTITY *newE; + const XML_Char *name; + const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter); + if (!oldE) + break; + name = poolCopyString(newPool, oldE->name); + if (!name) + return 0; + newE = (ENTITY *)lookup(oldParser, newTable, name, sizeof(ENTITY)); + if (!newE) + return 0; + if (oldE->systemId) { + const XML_Char *tem = poolCopyString(newPool, oldE->systemId); + if (!tem) + return 0; + newE->systemId = tem; + if (oldE->base) { + if (oldE->base == cachedOldBase) + newE->base = cachedNewBase; + else { + cachedOldBase = oldE->base; + tem = poolCopyString(newPool, cachedOldBase); + if (!tem) + return 0; + cachedNewBase = newE->base = tem; + } + } + if (oldE->publicId) { + tem = poolCopyString(newPool, oldE->publicId); + if (!tem) + return 0; + newE->publicId = tem; + } + } + else { + const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr, + oldE->textLen); + if (!tem) + return 0; + newE->textPtr = tem; + newE->textLen = oldE->textLen; + } + if (oldE->notation) { + const XML_Char *tem = poolCopyString(newPool, oldE->notation); + if (!tem) + return 0; + newE->notation = tem; + } + newE->is_param = oldE->is_param; + newE->is_internal = oldE->is_internal; + } + return 1; +} + +#define INIT_POWER 6 + +static XML_Bool FASTCALL +keyeq(KEY s1, KEY s2) +{ + for (; *s1 == *s2; s1++, s2++) + if (*s1 == 0) + return XML_TRUE; + return XML_FALSE; +} + +static unsigned long FASTCALL +hash(XML_Parser parser, KEY s) +{ + unsigned long h = hash_secret_salt; + while (*s) + h = CHAR_HASH(h, *s++); + return h; +} + +static NAMED * +lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) +{ + size_t i; + if (table->size == 0) { + size_t tsize; + if (!createSize) + return NULL; + table->power = INIT_POWER; + /* table->size is a power of 2 */ + table->size = (size_t)1 << INIT_POWER; + tsize = table->size * sizeof(NAMED *); + table->v = (NAMED **)table->mem->malloc_fcn(tsize); + if (!table->v) { + table->size = 0; + return NULL; + } + memset(table->v, 0, tsize); + i = hash(parser, name) & ((unsigned long)table->size - 1); + } + else { + unsigned long h = hash(parser, name); + unsigned long mask = (unsigned long)table->size - 1; + unsigned char step = 0; + i = h & mask; + while (table->v[i]) { + if (keyeq(name, table->v[i]->name)) + return table->v[i]; + if (!step) + step = PROBE_STEP(h, mask, table->power); + i < step ? (i += table->size - step) : (i -= step); + } + if (!createSize) + return NULL; + + /* check for overflow (table is half full) */ + if (table->used >> (table->power - 1)) { + unsigned char newPower = table->power + 1; + size_t newSize = (size_t)1 << newPower; + unsigned long newMask = (unsigned long)newSize - 1; + size_t tsize = newSize * sizeof(NAMED *); + NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize); + if (!newV) + return NULL; + memset(newV, 0, tsize); + for (i = 0; i < table->size; i++) + if (table->v[i]) { + unsigned long newHash = hash(parser, table->v[i]->name); + size_t j = newHash & newMask; + step = 0; + while (newV[j]) { + if (!step) + step = PROBE_STEP(newHash, newMask, newPower); + j < step ? (j += newSize - step) : (j -= step); + } + newV[j] = table->v[i]; + } + table->mem->free_fcn(table->v); + table->v = newV; + table->power = newPower; + table->size = newSize; + i = h & newMask; + step = 0; + while (table->v[i]) { + if (!step) + step = PROBE_STEP(h, newMask, newPower); + i < step ? (i += newSize - step) : (i -= step); + } + } + } + table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize); + if (!table->v[i]) + return NULL; + memset(table->v[i], 0, createSize); + table->v[i]->name = name; + (table->used)++; + return table->v[i]; +} + +static void FASTCALL +hashTableClear(HASH_TABLE *table) +{ + size_t i; + for (i = 0; i < table->size; i++) { + table->mem->free_fcn(table->v[i]); + table->v[i] = NULL; + } + table->used = 0; +} + +static void FASTCALL +hashTableDestroy(HASH_TABLE *table) +{ + size_t i; + for (i = 0; i < table->size; i++) + table->mem->free_fcn(table->v[i]); + table->mem->free_fcn(table->v); +} + +static void FASTCALL +hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) +{ + p->power = 0; + p->size = 0; + p->used = 0; + p->v = NULL; + p->mem = ms; +} + +static void FASTCALL +hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) +{ + iter->p = table->v; + iter->end = iter->p + table->size; +} + +static NAMED * FASTCALL +hashTableIterNext(HASH_TABLE_ITER *iter) +{ + while (iter->p != iter->end) { + NAMED *tem = *(iter->p)++; + if (tem) + return tem; + } + return NULL; +} + +static void FASTCALL +poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) +{ + pool->blocks = NULL; + pool->freeBlocks = NULL; + pool->start = NULL; + pool->ptr = NULL; + pool->end = NULL; + pool->mem = ms; +} + +static void FASTCALL +poolClear(STRING_POOL *pool) +{ + if (!pool->freeBlocks) + pool->freeBlocks = pool->blocks; + else { + BLOCK *p = pool->blocks; + while (p) { + BLOCK *tem = p->next; + p->next = pool->freeBlocks; + pool->freeBlocks = p; + p = tem; + } + } + pool->blocks = NULL; + pool->start = NULL; + pool->ptr = NULL; + pool->end = NULL; +} + +static void FASTCALL +poolDestroy(STRING_POOL *pool) +{ + BLOCK *p = pool->blocks; + while (p) { + BLOCK *tem = p->next; + pool->mem->free_fcn(p); + p = tem; + } + p = pool->freeBlocks; + while (p) { + BLOCK *tem = p->next; + pool->mem->free_fcn(p); + p = tem; + } +} + +static XML_Char * +poolAppend(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end) +{ + if (!pool->ptr && !poolGrow(pool)) + return NULL; + for (;;) { + XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); + if (ptr == end) + break; + if (!poolGrow(pool)) + return NULL; + } + return pool->start; +} + +static const XML_Char * FASTCALL +poolCopyString(STRING_POOL *pool, const XML_Char *s) +{ + do { + if (!poolAppendChar(pool, *s)) + return NULL; + } while (*s++); + s = pool->start; + poolFinish(pool); + return s; +} + +static const XML_Char * +poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) +{ + if (!pool->ptr && !poolGrow(pool)) + return NULL; + for (; n > 0; --n, s++) { + if (!poolAppendChar(pool, *s)) + return NULL; + } + s = pool->start; + poolFinish(pool); + return s; +} + +static const XML_Char * FASTCALL +poolAppendString(STRING_POOL *pool, const XML_Char *s) +{ + while (*s) { + if (!poolAppendChar(pool, *s)) + return NULL; + s++; + } + return pool->start; +} + +static XML_Char * +poolStoreString(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end) +{ + if (!poolAppend(pool, enc, ptr, end)) + return NULL; + if (pool->ptr == pool->end && !poolGrow(pool)) + return NULL; + *(pool->ptr)++ = 0; + return pool->start; +} + +static XML_Bool FASTCALL +poolGrow(STRING_POOL *pool) +{ + if (pool->freeBlocks) { + if (pool->start == 0) { + pool->blocks = pool->freeBlocks; + pool->freeBlocks = pool->freeBlocks->next; + pool->blocks->next = NULL; + pool->start = pool->blocks->s; + pool->end = pool->start + pool->blocks->size; + pool->ptr = pool->start; + return XML_TRUE; + } + if (pool->end - pool->start < pool->freeBlocks->size) { + BLOCK *tem = pool->freeBlocks->next; + pool->freeBlocks->next = pool->blocks; + pool->blocks = pool->freeBlocks; + pool->freeBlocks = tem; + memcpy(pool->blocks->s, pool->start, + (pool->end - pool->start) * sizeof(XML_Char)); + pool->ptr = pool->blocks->s + (pool->ptr - pool->start); + pool->start = pool->blocks->s; + pool->end = pool->start + pool->blocks->size; + return XML_TRUE; + } + } + if (pool->blocks && pool->start == pool->blocks->s) { + int blockSize = (int)(pool->end - pool->start)*2; + BLOCK *temp = (BLOCK *) + pool->mem->realloc_fcn(pool->blocks, + (offsetof(BLOCK, s) + + blockSize * sizeof(XML_Char))); + if (temp == NULL) + return XML_FALSE; + pool->blocks = temp; + pool->blocks->size = blockSize; + pool->ptr = pool->blocks->s + (pool->ptr - pool->start); + pool->start = pool->blocks->s; + pool->end = pool->start + blockSize; + } + else { + BLOCK *tem; + int blockSize = (int)(pool->end - pool->start); + if (blockSize < INIT_BLOCK_SIZE) + blockSize = INIT_BLOCK_SIZE; + else + blockSize *= 2; + tem = (BLOCK *)pool->mem->malloc_fcn(offsetof(BLOCK, s) + + blockSize * sizeof(XML_Char)); + if (!tem) + return XML_FALSE; + tem->size = blockSize; + tem->next = pool->blocks; + pool->blocks = tem; + if (pool->ptr != pool->start) + memcpy(tem->s, pool->start, + (pool->ptr - pool->start) * sizeof(XML_Char)); + pool->ptr = tem->s + (pool->ptr - pool->start); + pool->start = tem->s; + pool->end = tem->s + blockSize; + } + return XML_TRUE; +} + +static int FASTCALL +nextScaffoldPart(XML_Parser parser) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + CONTENT_SCAFFOLD * me; + int next; + + if (!dtd->scaffIndex) { + dtd->scaffIndex = (int *)MALLOC(groupSize * sizeof(int)); + if (!dtd->scaffIndex) + return -1; + dtd->scaffIndex[0] = 0; + } + + if (dtd->scaffCount >= dtd->scaffSize) { + CONTENT_SCAFFOLD *temp; + if (dtd->scaffold) { + temp = (CONTENT_SCAFFOLD *) + REALLOC(dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); + if (temp == NULL) + return -1; + dtd->scaffSize *= 2; + } + else { + temp = (CONTENT_SCAFFOLD *)MALLOC(INIT_SCAFFOLD_ELEMENTS + * sizeof(CONTENT_SCAFFOLD)); + if (temp == NULL) + return -1; + dtd->scaffSize = INIT_SCAFFOLD_ELEMENTS; + } + dtd->scaffold = temp; + } + next = dtd->scaffCount++; + me = &dtd->scaffold[next]; + if (dtd->scaffLevel) { + CONTENT_SCAFFOLD *parent = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel-1]]; + if (parent->lastchild) { + dtd->scaffold[parent->lastchild].nextsib = next; + } + if (!parent->childcnt) + parent->firstchild = next; + parent->lastchild = next; + parent->childcnt++; + } + me->firstchild = me->lastchild = me->childcnt = me->nextsib = 0; + return next; +} + +static void +build_node(XML_Parser parser, + int src_node, + XML_Content *dest, + XML_Content **contpos, + XML_Char **strpos) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + dest->type = dtd->scaffold[src_node].type; + dest->quant = dtd->scaffold[src_node].quant; + if (dest->type == XML_CTYPE_NAME) { + const XML_Char *src; + dest->name = *strpos; + src = dtd->scaffold[src_node].name; + for (;;) { + *(*strpos)++ = *src; + if (!*src) + break; + src++; + } + dest->numchildren = 0; + dest->children = NULL; + } + else { + unsigned int i; + int cn; + dest->numchildren = dtd->scaffold[src_node].childcnt; + dest->children = *contpos; + *contpos += dest->numchildren; + for (i = 0, cn = dtd->scaffold[src_node].firstchild; + i < dest->numchildren; + i++, cn = dtd->scaffold[cn].nextsib) { + build_node(parser, cn, &(dest->children[i]), contpos, strpos); + } + dest->name = NULL; + } +} + +static XML_Content * +build_model (XML_Parser parser) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + XML_Content *ret; + XML_Content *cpos; + XML_Char * str; + int allocsize = (dtd->scaffCount * sizeof(XML_Content) + + (dtd->contentStringLen * sizeof(XML_Char))); + + ret = (XML_Content *)MALLOC(allocsize); + if (!ret) + return NULL; + + str = (XML_Char *) (&ret[dtd->scaffCount]); + cpos = &ret[1]; + + build_node(parser, 0, ret, &cpos, &str); + return ret; +} + +static ELEMENT_TYPE * +getElementType(XML_Parser parser, + const ENCODING *enc, + const char *ptr, + const char *end) +{ + DTD * const dtd = _dtd; /* save one level of indirection */ + const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end); + ELEMENT_TYPE *ret; + + if (!name) + return NULL; + ret = (ELEMENT_TYPE *) lookup(parser, &dtd->elementTypes, name, sizeof(ELEMENT_TYPE)); + if (!ret) + return NULL; + if (ret->name != name) + poolDiscard(&dtd->pool); + else { + poolFinish(&dtd->pool); + if (!setElementTypePrefix(parser, ret)) + return NULL; + } + return ret; +} diff --git a/contrib/expat/lib/xmlrole.c b/contrib/expat/lib/xmlrole.c new file mode 100644 index 0000000..44772e2 --- /dev/null +++ b/contrib/expat/lib/xmlrole.c @@ -0,0 +1,1336 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stddef.h> + +#ifdef COMPILED_FROM_DSP +#include "winconfig.h" +#elif defined(MACOS_CLASSIC) +#include "macconfig.h" +#elif defined(__amigaos__) +#include "amigaconfig.h" +#elif defined(__WATCOMC__) +#include "watcomconfig.h" +#else +#ifdef HAVE_EXPAT_CONFIG_H +#include <expat_config.h> +#endif +#endif /* ndef COMPILED_FROM_DSP */ + +#include "expat_external.h" +#include "internal.h" +#include "xmlrole.h" +#include "ascii.h" + +/* Doesn't check: + + that ,| are not mixed in a model group + content of literals + +*/ + +static const char KW_ANY[] = { + ASCII_A, ASCII_N, ASCII_Y, '\0' }; +static const char KW_ATTLIST[] = { + ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0' }; +static const char KW_CDATA[] = { + ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; +static const char KW_DOCTYPE[] = { + ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0' }; +static const char KW_ELEMENT[] = { + ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0' }; +static const char KW_EMPTY[] = { + ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0' }; +static const char KW_ENTITIES[] = { + ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, + '\0' }; +static const char KW_ENTITY[] = { + ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; +static const char KW_FIXED[] = { + ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0' }; +static const char KW_ID[] = { + ASCII_I, ASCII_D, '\0' }; +static const char KW_IDREF[] = { + ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; +static const char KW_IDREFS[] = { + ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; +#ifdef XML_DTD +static const char KW_IGNORE[] = { + ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0' }; +#endif +static const char KW_IMPLIED[] = { + ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0' }; +#ifdef XML_DTD +static const char KW_INCLUDE[] = { + ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0' }; +#endif +static const char KW_NDATA[] = { + ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; +static const char KW_NMTOKEN[] = { + ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; +static const char KW_NMTOKENS[] = { + ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, + '\0' }; +static const char KW_NOTATION[] = + { ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, + '\0' }; +static const char KW_PCDATA[] = { + ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; +static const char KW_PUBLIC[] = { + ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0' }; +static const char KW_REQUIRED[] = { + ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, ASCII_R, ASCII_E, ASCII_D, + '\0' }; +static const char KW_SYSTEM[] = { + ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0' }; + +#ifndef MIN_BYTES_PER_CHAR +#define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) +#endif + +#ifdef XML_DTD +#define setTopLevel(state) \ + ((state)->handler = ((state)->documentEntity \ + ? internalSubset \ + : externalSubset1)) +#else /* not XML_DTD */ +#define setTopLevel(state) ((state)->handler = internalSubset) +#endif /* not XML_DTD */ + +typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc); + +static PROLOG_HANDLER + prolog0, prolog1, prolog2, + doctype0, doctype1, doctype2, doctype3, doctype4, doctype5, + internalSubset, + entity0, entity1, entity2, entity3, entity4, entity5, entity6, + entity7, entity8, entity9, entity10, + notation0, notation1, notation2, notation3, notation4, + attlist0, attlist1, attlist2, attlist3, attlist4, attlist5, attlist6, + attlist7, attlist8, attlist9, + element0, element1, element2, element3, element4, element5, element6, + element7, +#ifdef XML_DTD + externalSubset0, externalSubset1, + condSect0, condSect1, condSect2, +#endif /* XML_DTD */ + declClose, + error; + +static int FASTCALL common(PROLOG_STATE *state, int tok); + +static int PTRCALL +prolog0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + state->handler = prolog1; + return XML_ROLE_NONE; + case XML_TOK_XML_DECL: + state->handler = prolog1; + return XML_ROLE_XML_DECL; + case XML_TOK_PI: + state->handler = prolog1; + return XML_ROLE_PI; + case XML_TOK_COMMENT: + state->handler = prolog1; + return XML_ROLE_COMMENT; + case XML_TOK_BOM: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (!XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_DOCTYPE)) + break; + state->handler = doctype0; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +prolog1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_BOM: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (!XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_DOCTYPE)) + break; + state->handler = doctype0; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +prolog2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +doctype0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = doctype1; + return XML_ROLE_DOCTYPE_NAME; + } + return common(state, tok); +} + +static int PTRCALL +doctype1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = internalSubset; + return XML_ROLE_DOCTYPE_INTERNAL_SUBSET; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = doctype3; + return XML_ROLE_DOCTYPE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = doctype2; + return XML_ROLE_DOCTYPE_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +doctype2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_LITERAL: + state->handler = doctype3; + return XML_ROLE_DOCTYPE_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +doctype3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_LITERAL: + state->handler = doctype4; + return XML_ROLE_DOCTYPE_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +doctype4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = internalSubset; + return XML_ROLE_DOCTYPE_INTERNAL_SUBSET; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static int PTRCALL +doctype5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static int PTRCALL +internalSubset(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ENTITY)) { + state->handler = entity0; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ATTLIST)) { + state->handler = attlist0; + return XML_ROLE_ATTLIST_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ELEMENT)) { + state->handler = element0; + return XML_ROLE_ELEMENT_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_NOTATION)) { + state->handler = notation0; + return XML_ROLE_NOTATION_NONE; + } + break; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_PARAM_ENTITY_REF: + return XML_ROLE_PARAM_ENTITY_REF; + case XML_TOK_CLOSE_BRACKET: + state->handler = doctype5; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_NONE: + return XML_ROLE_NONE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static int PTRCALL +externalSubset0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + state->handler = externalSubset1; + if (tok == XML_TOK_XML_DECL) + return XML_ROLE_TEXT_DECL; + return externalSubset1(state, tok, ptr, end, enc); +} + +static int PTRCALL +externalSubset1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_COND_SECT_OPEN: + state->handler = condSect0; + return XML_ROLE_NONE; + case XML_TOK_COND_SECT_CLOSE: + if (state->includeLevel == 0) + break; + state->includeLevel -= 1; + return XML_ROLE_NONE; + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_CLOSE_BRACKET: + break; + case XML_TOK_NONE: + if (state->includeLevel) + break; + return XML_ROLE_NONE; + default: + return internalSubset(state, tok, ptr, end, enc); + } + return common(state, tok); +} + +#endif /* XML_DTD */ + +static int PTRCALL +entity0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_PERCENT: + state->handler = entity1; + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = entity2; + return XML_ROLE_GENERAL_ENTITY_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = entity7; + return XML_ROLE_PARAM_ENTITY_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity4; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity3; + return XML_ROLE_ENTITY_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +entity3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity4; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity5; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ENTITY_COMPLETE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_NDATA)) { + state->handler = entity6; + return XML_ROLE_ENTITY_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +entity6(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_NOTATION_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity7(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity9; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity8; + return XML_ROLE_ENTITY_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +entity8(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity9; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity9(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity10; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity10(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ENTITY_COMPLETE; + } + return common(state, tok); +} + +static int PTRCALL +notation0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_NAME: + state->handler = notation1; + return XML_ROLE_NOTATION_NAME; + } + return common(state, tok); +} + +static int PTRCALL +notation1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = notation3; + return XML_ROLE_NOTATION_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = notation2; + return XML_ROLE_NOTATION_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +notation2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = notation4; + return XML_ROLE_NOTATION_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +notation3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_NOTATION_NONE; + return XML_ROLE_NOTATION_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +notation4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_NOTATION_NONE; + return XML_ROLE_NOTATION_SYSTEM_ID; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_NOTATION_NO_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +attlist0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist1; + return XML_ROLE_ATTLIST_ELEMENT_NAME; + } + return common(state, tok); +} + +static int PTRCALL +attlist1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist2; + return XML_ROLE_ATTRIBUTE_NAME; + } + return common(state, tok); +} + +static int PTRCALL +attlist2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + { + static const char * const types[] = { + KW_CDATA, + KW_ID, + KW_IDREF, + KW_IDREFS, + KW_ENTITY, + KW_ENTITIES, + KW_NMTOKEN, + KW_NMTOKENS, + }; + int i; + for (i = 0; i < (int)(sizeof(types)/sizeof(types[0])); i++) + if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { + state->handler = attlist8; + return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; + } + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_NOTATION)) { + state->handler = attlist5; + return XML_ROLE_ATTLIST_NONE; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = attlist3; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NMTOKEN: + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist4; + return XML_ROLE_ATTRIBUTE_ENUM_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OR: + state->handler = attlist3; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OPEN_PAREN: + state->handler = attlist6; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist6(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + state->handler = attlist7; + return XML_ROLE_ATTRIBUTE_NOTATION_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist7(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OR: + state->handler = attlist6; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +/* default value */ +static int PTRCALL +attlist8(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_POUND_NAME: + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_IMPLIED)) { + state->handler = attlist1; + return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE; + } + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_REQUIRED)) { + state->handler = attlist1; + return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE; + } + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_FIXED)) { + state->handler = attlist9; + return XML_ROLE_ATTLIST_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_DEFAULT_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist9(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_FIXED_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +element0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element1; + return XML_ROLE_ELEMENT_NAME; + } + return common(state, tok); +} + +static int PTRCALL +element1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_EMPTY)) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_CONTENT_EMPTY; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_ANY)) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_CONTENT_ANY; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = element2; + state->level = 1; + return XML_ROLE_GROUP_OPEN; + } + return common(state, tok); +} + +static int PTRCALL +element2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_POUND_NAME: + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_PCDATA)) { + state->handler = element3; + return XML_ROLE_CONTENT_PCDATA; + } + break; + case XML_TOK_OPEN_PAREN: + state->level = 2; + state->handler = element6; + return XML_ROLE_GROUP_OPEN; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT; + case XML_TOK_NAME_QUESTION: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_OPT; + case XML_TOK_NAME_ASTERISK: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_REP; + case XML_TOK_NAME_PLUS: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_PLUS; + } + return common(state, tok); +} + +static int PTRCALL +element3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_ELEMENT_NONE; + } + return common(state, tok); +} + +static int PTRCALL +element4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element5; + return XML_ROLE_CONTENT_ELEMENT; + } + return common(state, tok); +} + +static int PTRCALL +element5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_ELEMENT_NONE; + } + return common(state, tok); +} + +static int PTRCALL +element6(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_OPEN_PAREN: + state->level += 1; + return XML_ROLE_GROUP_OPEN; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT; + case XML_TOK_NAME_QUESTION: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_OPT; + case XML_TOK_NAME_ASTERISK: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_REP; + case XML_TOK_NAME_PLUS: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_PLUS; + } + return common(state, tok); +} + +static int PTRCALL +element7(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_CLOSE_PAREN_QUESTION: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_OPT; + case XML_TOK_CLOSE_PAREN_PLUS: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_PLUS; + case XML_TOK_COMMA: + state->handler = element6; + return XML_ROLE_GROUP_SEQUENCE; + case XML_TOK_OR: + state->handler = element6; + return XML_ROLE_GROUP_CHOICE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static int PTRCALL +condSect0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_INCLUDE)) { + state->handler = condSect1; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_IGNORE)) { + state->handler = condSect2; + return XML_ROLE_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +condSect1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = externalSubset1; + state->includeLevel += 1; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static int PTRCALL +condSect2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = externalSubset1; + return XML_ROLE_IGNORE_SECT; + } + return common(state, tok); +} + +#endif /* XML_DTD */ + +static int PTRCALL +declClose(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return state->role_none; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return state->role_none; + } + return common(state, tok); +} + +static int PTRCALL +error(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + return XML_ROLE_NONE; +} + +static int FASTCALL +common(PROLOG_STATE *state, int tok) +{ +#ifdef XML_DTD + if (!state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) + return XML_ROLE_INNER_PARAM_ENTITY_REF; +#endif + state->handler = error; + return XML_ROLE_ERROR; +} + +void +XmlPrologStateInit(PROLOG_STATE *state) +{ + state->handler = prolog0; +#ifdef XML_DTD + state->documentEntity = 1; + state->includeLevel = 0; + state->inEntityValue = 0; +#endif /* XML_DTD */ +} + +#ifdef XML_DTD + +void +XmlPrologStateInitExternalEntity(PROLOG_STATE *state) +{ + state->handler = externalSubset0; + state->documentEntity = 0; + state->includeLevel = 0; +} + +#endif /* XML_DTD */ diff --git a/contrib/expat/lib/xmlrole.h b/contrib/expat/lib/xmlrole.h new file mode 100644 index 0000000..4dd9f06 --- /dev/null +++ b/contrib/expat/lib/xmlrole.h @@ -0,0 +1,114 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef XmlRole_INCLUDED +#define XmlRole_INCLUDED 1 + +#ifdef __VMS +/* 0 1 2 3 0 1 2 3 + 1234567890123456789012345678901 1234567890123456789012345678901 */ +#define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt +#endif + +#include "xmltok.h" + +#ifdef __cplusplus +extern "C" { +#endif + +enum { + XML_ROLE_ERROR = -1, + XML_ROLE_NONE = 0, + XML_ROLE_XML_DECL, + XML_ROLE_INSTANCE_START, + XML_ROLE_DOCTYPE_NONE, + XML_ROLE_DOCTYPE_NAME, + XML_ROLE_DOCTYPE_SYSTEM_ID, + XML_ROLE_DOCTYPE_PUBLIC_ID, + XML_ROLE_DOCTYPE_INTERNAL_SUBSET, + XML_ROLE_DOCTYPE_CLOSE, + XML_ROLE_GENERAL_ENTITY_NAME, + XML_ROLE_PARAM_ENTITY_NAME, + XML_ROLE_ENTITY_NONE, + XML_ROLE_ENTITY_VALUE, + XML_ROLE_ENTITY_SYSTEM_ID, + XML_ROLE_ENTITY_PUBLIC_ID, + XML_ROLE_ENTITY_COMPLETE, + XML_ROLE_ENTITY_NOTATION_NAME, + XML_ROLE_NOTATION_NONE, + XML_ROLE_NOTATION_NAME, + XML_ROLE_NOTATION_SYSTEM_ID, + XML_ROLE_NOTATION_NO_SYSTEM_ID, + XML_ROLE_NOTATION_PUBLIC_ID, + XML_ROLE_ATTRIBUTE_NAME, + XML_ROLE_ATTRIBUTE_TYPE_CDATA, + XML_ROLE_ATTRIBUTE_TYPE_ID, + XML_ROLE_ATTRIBUTE_TYPE_IDREF, + XML_ROLE_ATTRIBUTE_TYPE_IDREFS, + XML_ROLE_ATTRIBUTE_TYPE_ENTITY, + XML_ROLE_ATTRIBUTE_TYPE_ENTITIES, + XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN, + XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS, + XML_ROLE_ATTRIBUTE_ENUM_VALUE, + XML_ROLE_ATTRIBUTE_NOTATION_VALUE, + XML_ROLE_ATTLIST_NONE, + XML_ROLE_ATTLIST_ELEMENT_NAME, + XML_ROLE_IMPLIED_ATTRIBUTE_VALUE, + XML_ROLE_REQUIRED_ATTRIBUTE_VALUE, + XML_ROLE_DEFAULT_ATTRIBUTE_VALUE, + XML_ROLE_FIXED_ATTRIBUTE_VALUE, + XML_ROLE_ELEMENT_NONE, + XML_ROLE_ELEMENT_NAME, + XML_ROLE_CONTENT_ANY, + XML_ROLE_CONTENT_EMPTY, + XML_ROLE_CONTENT_PCDATA, + XML_ROLE_GROUP_OPEN, + XML_ROLE_GROUP_CLOSE, + XML_ROLE_GROUP_CLOSE_REP, + XML_ROLE_GROUP_CLOSE_OPT, + XML_ROLE_GROUP_CLOSE_PLUS, + XML_ROLE_GROUP_CHOICE, + XML_ROLE_GROUP_SEQUENCE, + XML_ROLE_CONTENT_ELEMENT, + XML_ROLE_CONTENT_ELEMENT_REP, + XML_ROLE_CONTENT_ELEMENT_OPT, + XML_ROLE_CONTENT_ELEMENT_PLUS, + XML_ROLE_PI, + XML_ROLE_COMMENT, +#ifdef XML_DTD + XML_ROLE_TEXT_DECL, + XML_ROLE_IGNORE_SECT, + XML_ROLE_INNER_PARAM_ENTITY_REF, +#endif /* XML_DTD */ + XML_ROLE_PARAM_ENTITY_REF +}; + +typedef struct prolog_state { + int (PTRCALL *handler) (struct prolog_state *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc); + unsigned level; + int role_none; +#ifdef XML_DTD + unsigned includeLevel; + int documentEntity; + int inEntityValue; +#endif /* XML_DTD */ +} PROLOG_STATE; + +void XmlPrologStateInit(PROLOG_STATE *); +#ifdef XML_DTD +void XmlPrologStateInitExternalEntity(PROLOG_STATE *); +#endif /* XML_DTD */ + +#define XmlTokenRole(state, tok, ptr, end, enc) \ + (((state)->handler)(state, tok, ptr, end, enc)) + +#ifdef __cplusplus +} +#endif + +#endif /* not XmlRole_INCLUDED */ diff --git a/contrib/expat/lib/xmltok.c b/contrib/expat/lib/xmltok.c new file mode 100644 index 0000000..bf09dfc --- /dev/null +++ b/contrib/expat/lib/xmltok.c @@ -0,0 +1,1651 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stddef.h> + +#ifdef COMPILED_FROM_DSP +#include "winconfig.h" +#elif defined(MACOS_CLASSIC) +#include "macconfig.h" +#elif defined(__amigaos__) +#include "amigaconfig.h" +#elif defined(__WATCOMC__) +#include "watcomconfig.h" +#else +#ifdef HAVE_EXPAT_CONFIG_H +#include <expat_config.h> +#endif +#endif /* ndef COMPILED_FROM_DSP */ + +#include "expat_external.h" +#include "internal.h" +#include "xmltok.h" +#include "nametab.h" + +#ifdef XML_DTD +#define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) +#else +#define IGNORE_SECTION_TOK_VTABLE /* as nothing */ +#endif + +#define VTABLE1 \ + { PREFIX(prologTok), PREFIX(contentTok), \ + PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \ + { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \ + PREFIX(sameName), \ + PREFIX(nameMatchesAscii), \ + PREFIX(nameLength), \ + PREFIX(skipS), \ + PREFIX(getAtts), \ + PREFIX(charRefNumber), \ + PREFIX(predefinedEntityName), \ + PREFIX(updatePosition), \ + PREFIX(isPublicId) + +#define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16) + +#define UCS2_GET_NAMING(pages, hi, lo) \ + (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1 << ((lo) & 0x1F))) + +/* A 2 byte UTF-8 representation splits the characters 11 bits between + the bottom 5 and 6 bits of the bytes. We need 8 bits to index into + pages, 3 bits to add to that index and 5 bits to generate the mask. +*/ +#define UTF8_GET_NAMING2(pages, byte) \ + (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ + + ((((byte)[0]) & 3) << 1) \ + + ((((byte)[1]) >> 5) & 1)] \ + & (1 << (((byte)[1]) & 0x1F))) + +/* A 3 byte UTF-8 representation splits the characters 16 bits between + the bottom 4, 6 and 6 bits of the bytes. We need 8 bits to index + into pages, 3 bits to add to that index and 5 bits to generate the + mask. +*/ +#define UTF8_GET_NAMING3(pages, byte) \ + (namingBitmap[((pages)[((((byte)[0]) & 0xF) << 4) \ + + ((((byte)[1]) >> 2) & 0xF)] \ + << 3) \ + + ((((byte)[1]) & 3) << 1) \ + + ((((byte)[2]) >> 5) & 1)] \ + & (1 << (((byte)[2]) & 0x1F))) + +#define UTF8_GET_NAMING(pages, p, n) \ + ((n) == 2 \ + ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ + : ((n) == 3 \ + ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) \ + : 0)) + +/* Detection of invalid UTF-8 sequences is based on Table 3.1B + of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/ + with the additional restriction of not allowing the Unicode + code points 0xFFFF and 0xFFFE (sequences EF,BF,BF and EF,BF,BE). + Implementation details: + (A & 0x80) == 0 means A < 0x80 + and + (A & 0xC0) == 0xC0 means A > 0xBF +*/ + +#define UTF8_INVALID2(p) \ + ((*p) < 0xC2 || ((p)[1] & 0x80) == 0 || ((p)[1] & 0xC0) == 0xC0) + +#define UTF8_INVALID3(p) \ + (((p)[2] & 0x80) == 0 \ + || \ + ((*p) == 0xEF && (p)[1] == 0xBF \ + ? \ + (p)[2] > 0xBD \ + : \ + ((p)[2] & 0xC0) == 0xC0) \ + || \ + ((*p) == 0xE0 \ + ? \ + (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ + : \ + ((p)[1] & 0x80) == 0 \ + || \ + ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) + +#define UTF8_INVALID4(p) \ + (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 \ + || \ + ((p)[2] & 0x80) == 0 || ((p)[2] & 0xC0) == 0xC0 \ + || \ + ((*p) == 0xF0 \ + ? \ + (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ + : \ + ((p)[1] & 0x80) == 0 \ + || \ + ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) + +static int PTRFASTCALL +isNever(const ENCODING *enc, const char *p) +{ + return 0; +} + +static int PTRFASTCALL +utf8_isName2(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING2(namePages, (const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isName3(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING3(namePages, (const unsigned char *)p); +} + +#define utf8_isName4 isNever + +static int PTRFASTCALL +utf8_isNmstrt2(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isNmstrt3(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p); +} + +#define utf8_isNmstrt4 isNever + +static int PTRFASTCALL +utf8_isInvalid2(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID2((const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isInvalid3(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID3((const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isInvalid4(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID4((const unsigned char *)p); +} + +struct normal_encoding { + ENCODING enc; + unsigned char type[256]; +#ifdef XML_MIN_SIZE + int (PTRFASTCALL *byteType)(const ENCODING *, const char *); + int (PTRFASTCALL *isNameMin)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); + int (PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); + int (PTRCALL *charMatches)(const ENCODING *, const char *, int); +#endif /* XML_MIN_SIZE */ + int (PTRFASTCALL *isName2)(const ENCODING *, const char *); + int (PTRFASTCALL *isName3)(const ENCODING *, const char *); + int (PTRFASTCALL *isName4)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); + int (PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); + int (PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); + int (PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); +}; + +#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *) (enc)) + +#ifdef XML_MIN_SIZE + +#define STANDARD_VTABLE(E) \ + E ## byteType, \ + E ## isNameMin, \ + E ## isNmstrtMin, \ + E ## byteToAscii, \ + E ## charMatches, + +#else + +#define STANDARD_VTABLE(E) /* as nothing */ + +#endif + +#define NORMAL_VTABLE(E) \ + E ## isName2, \ + E ## isName3, \ + E ## isName4, \ + E ## isNmstrt2, \ + E ## isNmstrt3, \ + E ## isNmstrt4, \ + E ## isInvalid2, \ + E ## isInvalid3, \ + E ## isInvalid4 + +static int FASTCALL checkCharRefNumber(int); + +#include "xmltok_impl.h" +#include "ascii.h" + +#ifdef XML_MIN_SIZE +#define sb_isNameMin isNever +#define sb_isNmstrtMin isNever +#endif + +#ifdef XML_MIN_SIZE +#define MINBPC(enc) ((enc)->minBytesPerChar) +#else +/* minimum bytes per character */ +#define MINBPC(enc) 1 +#endif + +#define SB_BYTE_TYPE(enc, p) \ + (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) + +#ifdef XML_MIN_SIZE +static int PTRFASTCALL +sb_byteType(const ENCODING *enc, const char *p) +{ + return SB_BYTE_TYPE(enc, p); +} +#define BYTE_TYPE(enc, p) \ + (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) +#else +#define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) +#endif + +#ifdef XML_MIN_SIZE +#define BYTE_TO_ASCII(enc, p) \ + (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) +static int PTRFASTCALL +sb_byteToAscii(const ENCODING *enc, const char *p) +{ + return *p; +} +#else +#define BYTE_TO_ASCII(enc, p) (*(p)) +#endif + +#define IS_NAME_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isName ## n(enc, p)) +#define IS_NMSTRT_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isNmstrt ## n(enc, p)) +#define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid ## n(enc, p)) + +#ifdef XML_MIN_SIZE +#define IS_NAME_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) +#else +#define IS_NAME_CHAR_MINBPC(enc, p) (0) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) +#endif + +#ifdef XML_MIN_SIZE +#define CHAR_MATCHES(enc, p, c) \ + (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) +static int PTRCALL +sb_charMatches(const ENCODING *enc, const char *p, int c) +{ + return *p == c; +} +#else +/* c is an ASCII character */ +#define CHAR_MATCHES(enc, p, c) (*(p) == c) +#endif + +#define PREFIX(ident) normal_ ## ident +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ + UTF8_cval1 = 0x00, + UTF8_cval2 = 0xc0, + UTF8_cval3 = 0xe0, + UTF8_cval4 = 0xf0 +}; + +static void PTRCALL +utf8_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + char *to; + const char *from; + if (fromLim - *fromP > toLim - *toP) { + /* Avoid copying partial characters. */ + for (fromLim = *fromP + (toLim - *toP); fromLim > *fromP; fromLim--) + if (((unsigned char)fromLim[-1] & 0xc0) != 0x80) + break; + } + for (to = *toP, from = *fromP; from != fromLim; from++, to++) + *to = *from; + *fromP = from; + *toP = to; +} + +static void PTRCALL +utf8_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + unsigned short *to = *toP; + const char *from = *fromP; + while (from != fromLim && to != toLim) { + switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) { + case BT_LEAD2: + *to++ = (unsigned short)(((from[0] & 0x1f) << 6) | (from[1] & 0x3f)); + from += 2; + break; + case BT_LEAD3: + *to++ = (unsigned short)(((from[0] & 0xf) << 12) + | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f)); + from += 3; + break; + case BT_LEAD4: + { + unsigned long n; + if (to + 1 == toLim) + goto after; + n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) + | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); + n -= 0x10000; + to[0] = (unsigned short)((n >> 10) | 0xD800); + to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); + to += 2; + from += 4; + } + break; + default: + *to++ = *from++; + break; + } + } +after: + *fromP = from; + *toP = to; +} + +#ifdef XML_NS +static const struct normal_encoding utf8_encoding_ns = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#include "asciitab.h" +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; +#endif + +static const struct normal_encoding utf8_encoding = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; + +#ifdef XML_NS + +static const struct normal_encoding internal_utf8_encoding_ns = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#include "iasciitab.h" +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; + +#endif + +static const struct normal_encoding internal_utf8_encoding = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; + +static void PTRCALL +latin1_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + for (;;) { + unsigned char c; + if (*fromP == fromLim) + break; + c = (unsigned char)**fromP; + if (c & 0x80) { + if (toLim - *toP < 2) + break; + *(*toP)++ = (char)((c >> 6) | UTF8_cval2); + *(*toP)++ = (char)((c & 0x3f) | 0x80); + (*fromP)++; + } + else { + if (*toP == toLim) + break; + *(*toP)++ = *(*fromP)++; + } + } +} + +static void PTRCALL +latin1_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + while (*fromP != fromLim && *toP != toLim) + *(*toP)++ = (unsigned char)*(*fromP)++; +} + +#ifdef XML_NS + +static const struct normal_encoding latin1_encoding_ns = { + { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) +}; + +#endif + +static const struct normal_encoding latin1_encoding = { + { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) +}; + +static void PTRCALL +ascii_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + while (*fromP != fromLim && *toP != toLim) + *(*toP)++ = *(*fromP)++; +} + +#ifdef XML_NS + +static const struct normal_encoding ascii_encoding_ns = { + { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, + { +#include "asciitab.h" +/* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) +}; + +#endif + +static const struct normal_encoding ascii_encoding = { + { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +/* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) +}; + +static int PTRFASTCALL +unicode_byte_type(char hi, char lo) +{ + switch ((unsigned char)hi) { + case 0xD8: case 0xD9: case 0xDA: case 0xDB: + return BT_LEAD4; + case 0xDC: case 0xDD: case 0xDE: case 0xDF: + return BT_TRAIL; + case 0xFF: + switch ((unsigned char)lo) { + case 0xFF: + case 0xFE: + return BT_NONXML; + } + break; + } + return BT_NONASCII; +} + +#define DEFINE_UTF16_TO_UTF8(E) \ +static void PTRCALL \ +E ## toUtf8(const ENCODING *enc, \ + const char **fromP, const char *fromLim, \ + char **toP, const char *toLim) \ +{ \ + const char *from; \ + for (from = *fromP; from != fromLim; from += 2) { \ + int plane; \ + unsigned char lo2; \ + unsigned char lo = GET_LO(from); \ + unsigned char hi = GET_HI(from); \ + switch (hi) { \ + case 0: \ + if (lo < 0x80) { \ + if (*toP == toLim) { \ + *fromP = from; \ + return; \ + } \ + *(*toP)++ = lo; \ + break; \ + } \ + /* fall through */ \ + case 0x1: case 0x2: case 0x3: \ + case 0x4: case 0x5: case 0x6: case 0x7: \ + if (toLim - *toP < 2) { \ + *fromP = from; \ + return; \ + } \ + *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + default: \ + if (toLim - *toP < 3) { \ + *fromP = from; \ + return; \ + } \ + /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ + *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ + *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + case 0xD8: case 0xD9: case 0xDA: case 0xDB: \ + if (toLim - *toP < 4) { \ + *fromP = from; \ + return; \ + } \ + plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ + *(*toP)++ = ((plane >> 2) | UTF8_cval4); \ + *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ + from += 2; \ + lo2 = GET_LO(from); \ + *(*toP)++ = (((lo & 0x3) << 4) \ + | ((GET_HI(from) & 0x3) << 2) \ + | (lo2 >> 6) \ + | 0x80); \ + *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ + break; \ + } \ + } \ + *fromP = from; \ +} + +#define DEFINE_UTF16_TO_UTF16(E) \ +static void PTRCALL \ +E ## toUtf16(const ENCODING *enc, \ + const char **fromP, const char *fromLim, \ + unsigned short **toP, const unsigned short *toLim) \ +{ \ + /* Avoid copying first half only of surrogate */ \ + if (fromLim - *fromP > ((toLim - *toP) << 1) \ + && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) \ + fromLim -= 2; \ + for (; *fromP != fromLim && *toP != toLim; *fromP += 2) \ + *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ +} + +#define SET2(ptr, ch) \ + (((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8))) +#define GET_LO(ptr) ((unsigned char)(ptr)[0]) +#define GET_HI(ptr) ((unsigned char)(ptr)[1]) + +DEFINE_UTF16_TO_UTF8(little2_) +DEFINE_UTF16_TO_UTF16(little2_) + +#undef SET2 +#undef GET_LO +#undef GET_HI + +#define SET2(ptr, ch) \ + (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF))) +#define GET_LO(ptr) ((unsigned char)(ptr)[1]) +#define GET_HI(ptr) ((unsigned char)(ptr)[0]) + +DEFINE_UTF16_TO_UTF8(big2_) +DEFINE_UTF16_TO_UTF16(big2_) + +#undef SET2 +#undef GET_LO +#undef GET_HI + +#define LITTLE2_BYTE_TYPE(enc, p) \ + ((p)[1] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ + : unicode_byte_type((p)[1], (p)[0])) +#define LITTLE2_BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1) +#define LITTLE2_CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c) +#define LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) +#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0]) + +#ifdef XML_MIN_SIZE + +static int PTRFASTCALL +little2_byteType(const ENCODING *enc, const char *p) +{ + return LITTLE2_BYTE_TYPE(enc, p); +} + +static int PTRFASTCALL +little2_byteToAscii(const ENCODING *enc, const char *p) +{ + return LITTLE2_BYTE_TO_ASCII(enc, p); +} + +static int PTRCALL +little2_charMatches(const ENCODING *enc, const char *p, int c) +{ + return LITTLE2_CHAR_MATCHES(enc, p, c); +} + +static int PTRFASTCALL +little2_isNameMin(const ENCODING *enc, const char *p) +{ + return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p); +} + +static int PTRFASTCALL +little2_isNmstrtMin(const ENCODING *enc, const char *p) +{ + return LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p); +} + +#undef VTABLE +#define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 + +#else /* not XML_MIN_SIZE */ + +#undef PREFIX +#define PREFIX(ident) little2_ ## ident +#define MINBPC(enc) 2 +/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ +#define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) +#define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(enc, p) +#define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(enc, p, c) +#define IS_NAME_CHAR(enc, p, n) 0 +#define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) +#define IS_NMSTRT_CHAR(enc, p, n) (0) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) + +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +#endif /* not XML_MIN_SIZE */ + +#ifdef XML_NS + +static const struct normal_encoding little2_encoding_ns = { + { VTABLE, 2, 0, +#if BYTEORDER == 1234 + 1 +#else + 0 +#endif + }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) +}; + +#endif + +static const struct normal_encoding little2_encoding = { + { VTABLE, 2, 0, +#if BYTEORDER == 1234 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) +}; + +#if BYTEORDER != 4321 + +#ifdef XML_NS + +static const struct normal_encoding internal_little2_encoding_ns = { + { VTABLE, 2, 0, 1 }, + { +#include "iasciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) +}; + +#endif + +static const struct normal_encoding internal_little2_encoding = { + { VTABLE, 2, 0, 1 }, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) +}; + +#endif + + +#define BIG2_BYTE_TYPE(enc, p) \ + ((p)[0] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ + : unicode_byte_type((p)[0], (p)[1])) +#define BIG2_BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1) +#define BIG2_CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c) +#define BIG2_IS_NAME_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1]) +#define BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1]) + +#ifdef XML_MIN_SIZE + +static int PTRFASTCALL +big2_byteType(const ENCODING *enc, const char *p) +{ + return BIG2_BYTE_TYPE(enc, p); +} + +static int PTRFASTCALL +big2_byteToAscii(const ENCODING *enc, const char *p) +{ + return BIG2_BYTE_TO_ASCII(enc, p); +} + +static int PTRCALL +big2_charMatches(const ENCODING *enc, const char *p, int c) +{ + return BIG2_CHAR_MATCHES(enc, p, c); +} + +static int PTRFASTCALL +big2_isNameMin(const ENCODING *enc, const char *p) +{ + return BIG2_IS_NAME_CHAR_MINBPC(enc, p); +} + +static int PTRFASTCALL +big2_isNmstrtMin(const ENCODING *enc, const char *p) +{ + return BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p); +} + +#undef VTABLE +#define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 + +#else /* not XML_MIN_SIZE */ + +#undef PREFIX +#define PREFIX(ident) big2_ ## ident +#define MINBPC(enc) 2 +/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ +#define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) +#define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(enc, p) +#define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(enc, p, c) +#define IS_NAME_CHAR(enc, p, n) 0 +#define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(enc, p) +#define IS_NMSTRT_CHAR(enc, p, n) (0) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) + +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +#endif /* not XML_MIN_SIZE */ + +#ifdef XML_NS + +static const struct normal_encoding big2_encoding_ns = { + { VTABLE, 2, 0, +#if BYTEORDER == 4321 + 1 +#else + 0 +#endif + }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) +}; + +#endif + +static const struct normal_encoding big2_encoding = { + { VTABLE, 2, 0, +#if BYTEORDER == 4321 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) +}; + +#if BYTEORDER != 1234 + +#ifdef XML_NS + +static const struct normal_encoding internal_big2_encoding_ns = { + { VTABLE, 2, 0, 1 }, + { +#include "iasciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) +}; + +#endif + +static const struct normal_encoding internal_big2_encoding = { + { VTABLE, 2, 0, 1 }, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) +}; + +#endif + +#undef PREFIX + +static int FASTCALL +streqci(const char *s1, const char *s2) +{ + for (;;) { + char c1 = *s1++; + char c2 = *s2++; + if (ASCII_a <= c1 && c1 <= ASCII_z) + c1 += ASCII_A - ASCII_a; + if (ASCII_a <= c2 && c2 <= ASCII_z) + c2 += ASCII_A - ASCII_a; + if (c1 != c2) + return 0; + if (!c1) + break; + } + return 1; +} + +static void PTRCALL +initUpdatePosition(const ENCODING *enc, const char *ptr, + const char *end, POSITION *pos) +{ + normal_updatePosition(&utf8_encoding.enc, ptr, end, pos); +} + +static int +toAscii(const ENCODING *enc, const char *ptr, const char *end) +{ + char buf[1]; + char *p = buf; + XmlUtf8Convert(enc, &ptr, end, &p, p + 1); + if (p == buf) + return -1; + else + return buf[0]; +} + +static int FASTCALL +isSpace(int c) +{ + switch (c) { + case 0x20: + case 0xD: + case 0xA: + case 0x9: + return 1; + } + return 0; +} + +/* Return 1 if there's just optional white space or there's an S + followed by name=val. +*/ +static int +parsePseudoAttribute(const ENCODING *enc, + const char *ptr, + const char *end, + const char **namePtr, + const char **nameEndPtr, + const char **valPtr, + const char **nextTokPtr) +{ + int c; + char open; + if (ptr == end) { + *namePtr = NULL; + return 1; + } + if (!isSpace(toAscii(enc, ptr, end))) { + *nextTokPtr = ptr; + return 0; + } + do { + ptr += enc->minBytesPerChar; + } while (isSpace(toAscii(enc, ptr, end))); + if (ptr == end) { + *namePtr = NULL; + return 1; + } + *namePtr = ptr; + for (;;) { + c = toAscii(enc, ptr, end); + if (c == -1) { + *nextTokPtr = ptr; + return 0; + } + if (c == ASCII_EQUALS) { + *nameEndPtr = ptr; + break; + } + if (isSpace(c)) { + *nameEndPtr = ptr; + do { + ptr += enc->minBytesPerChar; + } while (isSpace(c = toAscii(enc, ptr, end))); + if (c != ASCII_EQUALS) { + *nextTokPtr = ptr; + return 0; + } + break; + } + ptr += enc->minBytesPerChar; + } + if (ptr == *namePtr) { + *nextTokPtr = ptr; + return 0; + } + ptr += enc->minBytesPerChar; + c = toAscii(enc, ptr, end); + while (isSpace(c)) { + ptr += enc->minBytesPerChar; + c = toAscii(enc, ptr, end); + } + if (c != ASCII_QUOT && c != ASCII_APOS) { + *nextTokPtr = ptr; + return 0; + } + open = (char)c; + ptr += enc->minBytesPerChar; + *valPtr = ptr; + for (;; ptr += enc->minBytesPerChar) { + c = toAscii(enc, ptr, end); + if (c == open) + break; + if (!(ASCII_a <= c && c <= ASCII_z) + && !(ASCII_A <= c && c <= ASCII_Z) + && !(ASCII_0 <= c && c <= ASCII_9) + && c != ASCII_PERIOD + && c != ASCII_MINUS + && c != ASCII_UNDERSCORE) { + *nextTokPtr = ptr; + return 0; + } + } + *nextTokPtr = ptr + enc->minBytesPerChar; + return 1; +} + +static const char KW_version[] = { + ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0' +}; + +static const char KW_encoding[] = { + ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, ASCII_i, ASCII_n, ASCII_g, '\0' +}; + +static const char KW_standalone[] = { + ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, ASCII_l, ASCII_o, + ASCII_n, ASCII_e, '\0' +}; + +static const char KW_yes[] = { + ASCII_y, ASCII_e, ASCII_s, '\0' +}; + +static const char KW_no[] = { + ASCII_n, ASCII_o, '\0' +}; + +static int +doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, + const char *, + const char *), + int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingName, + const ENCODING **encoding, + int *standalone) +{ + const char *val = NULL; + const char *name = NULL; + const char *nameEnd = NULL; + ptr += 5 * enc->minBytesPerChar; + end -= 2 * enc->minBytesPerChar; + if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) + || !name) { + *badPtr = ptr; + return 0; + } + if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { + if (!isGeneralTextEntity) { + *badPtr = name; + return 0; + } + } + else { + if (versionPtr) + *versionPtr = val; + if (versionEndPtr) + *versionEndPtr = ptr; + if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + *badPtr = ptr; + return 0; + } + if (!name) { + if (isGeneralTextEntity) { + /* a TextDecl must have an EncodingDecl */ + *badPtr = ptr; + return 0; + } + return 1; + } + } + if (XmlNameMatchesAscii(enc, name, nameEnd, KW_encoding)) { + int c = toAscii(enc, val, end); + if (!(ASCII_a <= c && c <= ASCII_z) && !(ASCII_A <= c && c <= ASCII_Z)) { + *badPtr = val; + return 0; + } + if (encodingName) + *encodingName = val; + if (encoding) + *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar); + if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + *badPtr = ptr; + return 0; + } + if (!name) + return 1; + } + if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) + || isGeneralTextEntity) { + *badPtr = name; + return 0; + } + if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_yes)) { + if (standalone) + *standalone = 1; + } + else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { + if (standalone) + *standalone = 0; + } + else { + *badPtr = val; + return 0; + } + while (isSpace(toAscii(enc, ptr, end))) + ptr += enc->minBytesPerChar; + if (ptr != end) { + *badPtr = ptr; + return 0; + } + return 1; +} + +static int FASTCALL +checkCharRefNumber(int result) +{ + switch (result >> 8) { + case 0xD8: case 0xD9: case 0xDA: case 0xDB: + case 0xDC: case 0xDD: case 0xDE: case 0xDF: + return -1; + case 0: + if (latin1_encoding.type[result] == BT_NONXML) + return -1; + break; + case 0xFF: + if (result == 0xFFFE || result == 0xFFFF) + return -1; + break; + } + return result; +} + +int FASTCALL +XmlUtf8Encode(int c, char *buf) +{ + enum { + /* minN is minimum legal resulting value for N byte sequence */ + min2 = 0x80, + min3 = 0x800, + min4 = 0x10000 + }; + + if (c < 0) + return 0; + if (c < min2) { + buf[0] = (char)(c | UTF8_cval1); + return 1; + } + if (c < min3) { + buf[0] = (char)((c >> 6) | UTF8_cval2); + buf[1] = (char)((c & 0x3f) | 0x80); + return 2; + } + if (c < min4) { + buf[0] = (char)((c >> 12) | UTF8_cval3); + buf[1] = (char)(((c >> 6) & 0x3f) | 0x80); + buf[2] = (char)((c & 0x3f) | 0x80); + return 3; + } + if (c < 0x110000) { + buf[0] = (char)((c >> 18) | UTF8_cval4); + buf[1] = (char)(((c >> 12) & 0x3f) | 0x80); + buf[2] = (char)(((c >> 6) & 0x3f) | 0x80); + buf[3] = (char)((c & 0x3f) | 0x80); + return 4; + } + return 0; +} + +int FASTCALL +XmlUtf16Encode(int charNum, unsigned short *buf) +{ + if (charNum < 0) + return 0; + if (charNum < 0x10000) { + buf[0] = (unsigned short)charNum; + return 1; + } + if (charNum < 0x110000) { + charNum -= 0x10000; + buf[0] = (unsigned short)((charNum >> 10) + 0xD800); + buf[1] = (unsigned short)((charNum & 0x3FF) + 0xDC00); + return 2; + } + return 0; +} + +struct unknown_encoding { + struct normal_encoding normal; + CONVERTER convert; + void *userData; + unsigned short utf16[256]; + char utf8[256][4]; +}; + +#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *) (enc)) + +int +XmlSizeOfUnknownEncoding(void) +{ + return sizeof(struct unknown_encoding); +} + +static int PTRFASTCALL +unknown_isName(const ENCODING *enc, const char *p) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(namePages, c >> 8, c & 0xFF); +} + +static int PTRFASTCALL +unknown_isNmstrt(const ENCODING *enc, const char *p) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xFF); +} + +static int PTRFASTCALL +unknown_isInvalid(const ENCODING *enc, const char *p) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + return (c & ~0xFFFF) || checkCharRefNumber(c) < 0; +} + +static void PTRCALL +unknown_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + char buf[XML_UTF8_ENCODE_MAX]; + for (;;) { + const char *utf8; + int n; + if (*fromP == fromLim) + break; + utf8 = uenc->utf8[(unsigned char)**fromP]; + n = *utf8++; + if (n == 0) { + int c = uenc->convert(uenc->userData, *fromP); + n = XmlUtf8Encode(c, buf); + if (n > toLim - *toP) + break; + utf8 = buf; + *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2)); + } + else { + if (n > toLim - *toP) + break; + (*fromP)++; + } + do { + *(*toP)++ = *utf8++; + } while (--n != 0); + } +} + +static void PTRCALL +unknown_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + while (*fromP != fromLim && *toP != toLim) { + unsigned short c = uenc->utf16[(unsigned char)**fromP]; + if (c == 0) { + c = (unsigned short) + uenc->convert(uenc->userData, *fromP); + *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2)); + } + else + (*fromP)++; + *(*toP)++ = c; + } +} + +ENCODING * +XmlInitUnknownEncoding(void *mem, + int *table, + CONVERTER convert, + void *userData) +{ + int i; + struct unknown_encoding *e = (struct unknown_encoding *)mem; + for (i = 0; i < (int)sizeof(struct normal_encoding); i++) + ((char *)mem)[i] = ((char *)&latin1_encoding)[i]; + for (i = 0; i < 128; i++) + if (latin1_encoding.type[i] != BT_OTHER + && latin1_encoding.type[i] != BT_NONXML + && table[i] != i) + return 0; + for (i = 0; i < 256; i++) { + int c = table[i]; + if (c == -1) { + e->normal.type[i] = BT_MALFORM; + /* This shouldn't really get used. */ + e->utf16[i] = 0xFFFF; + e->utf8[i][0] = 1; + e->utf8[i][1] = 0; + } + else if (c < 0) { + if (c < -4) + return 0; + e->normal.type[i] = (unsigned char)(BT_LEAD2 - (c + 2)); + e->utf8[i][0] = 0; + e->utf16[i] = 0; + } + else if (c < 0x80) { + if (latin1_encoding.type[c] != BT_OTHER + && latin1_encoding.type[c] != BT_NONXML + && c != i) + return 0; + e->normal.type[i] = latin1_encoding.type[c]; + e->utf8[i][0] = 1; + e->utf8[i][1] = (char)c; + e->utf16[i] = (unsigned short)(c == 0 ? 0xFFFF : c); + } + else if (checkCharRefNumber(c) < 0) { + e->normal.type[i] = BT_NONXML; + /* This shouldn't really get used. */ + e->utf16[i] = 0xFFFF; + e->utf8[i][0] = 1; + e->utf8[i][1] = 0; + } + else { + if (c > 0xFFFF) + return 0; + if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff)) + e->normal.type[i] = BT_NMSTRT; + else if (UCS2_GET_NAMING(namePages, c >> 8, c & 0xff)) + e->normal.type[i] = BT_NAME; + else + e->normal.type[i] = BT_OTHER; + e->utf8[i][0] = (char)XmlUtf8Encode(c, e->utf8[i] + 1); + e->utf16[i] = (unsigned short)c; + } + } + e->userData = userData; + e->convert = convert; + if (convert) { + e->normal.isName2 = unknown_isName; + e->normal.isName3 = unknown_isName; + e->normal.isName4 = unknown_isName; + e->normal.isNmstrt2 = unknown_isNmstrt; + e->normal.isNmstrt3 = unknown_isNmstrt; + e->normal.isNmstrt4 = unknown_isNmstrt; + e->normal.isInvalid2 = unknown_isInvalid; + e->normal.isInvalid3 = unknown_isInvalid; + e->normal.isInvalid4 = unknown_isInvalid; + } + e->normal.enc.utf8Convert = unknown_toUtf8; + e->normal.enc.utf16Convert = unknown_toUtf16; + return &(e->normal.enc); +} + +/* If this enumeration is changed, getEncodingIndex and encodings +must also be changed. */ +enum { + UNKNOWN_ENC = -1, + ISO_8859_1_ENC = 0, + US_ASCII_ENC, + UTF_8_ENC, + UTF_16_ENC, + UTF_16BE_ENC, + UTF_16LE_ENC, + /* must match encodingNames up to here */ + NO_ENC +}; + +static const char KW_ISO_8859_1[] = { + ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, ASCII_5, ASCII_9, + ASCII_MINUS, ASCII_1, '\0' +}; +static const char KW_US_ASCII[] = { + ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, ASCII_C, ASCII_I, ASCII_I, + '\0' +}; +static const char KW_UTF_8[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0' +}; +static const char KW_UTF_16[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0' +}; +static const char KW_UTF_16BE[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_B, ASCII_E, + '\0' +}; +static const char KW_UTF_16LE[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_L, ASCII_E, + '\0' +}; + +static int FASTCALL +getEncodingIndex(const char *name) +{ + static const char * const encodingNames[] = { + KW_ISO_8859_1, + KW_US_ASCII, + KW_UTF_8, + KW_UTF_16, + KW_UTF_16BE, + KW_UTF_16LE, + }; + int i; + if (name == NULL) + return NO_ENC; + for (i = 0; i < (int)(sizeof(encodingNames)/sizeof(encodingNames[0])); i++) + if (streqci(name, encodingNames[i])) + return i; + return UNKNOWN_ENC; +} + +/* For binary compatibility, we store the index of the encoding + specified at initialization in the isUtf16 member. +*/ + +#define INIT_ENC_INDEX(enc) ((int)(enc)->initEnc.isUtf16) +#define SET_INIT_ENC_INDEX(enc, i) ((enc)->initEnc.isUtf16 = (char)i) + +/* This is what detects the encoding. encodingTable maps from + encoding indices to encodings; INIT_ENC_INDEX(enc) is the index of + the external (protocol) specified encoding; state is + XML_CONTENT_STATE if we're parsing an external text entity, and + XML_PROLOG_STATE otherwise. +*/ + + +static int +initScan(const ENCODING * const *encodingTable, + const INIT_ENCODING *enc, + int state, + const char *ptr, + const char *end, + const char **nextTokPtr) +{ + const ENCODING **encPtr; + + if (ptr == end) + return XML_TOK_NONE; + encPtr = enc->encPtr; + if (ptr + 1 == end) { + /* only a single byte available for auto-detection */ +#ifndef XML_DTD /* FIXME */ + /* a well-formed document entity must have more than one byte */ + if (state != XML_CONTENT_STATE) + return XML_TOK_PARTIAL; +#endif + /* so we're parsing an external text entity... */ + /* if UTF-16 was externally specified, then we need at least 2 bytes */ + switch (INIT_ENC_INDEX(enc)) { + case UTF_16_ENC: + case UTF_16LE_ENC: + case UTF_16BE_ENC: + return XML_TOK_PARTIAL; + } + switch ((unsigned char)*ptr) { + case 0xFE: + case 0xFF: + case 0xEF: /* possibly first byte of UTF-8 BOM */ + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC + && state == XML_CONTENT_STATE) + break; + /* fall through */ + case 0x00: + case 0x3C: + return XML_TOK_PARTIAL; + } + } + else { + switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) { + case 0xFEFF: + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC + && state == XML_CONTENT_STATE) + break; + *nextTokPtr = ptr + 2; + *encPtr = encodingTable[UTF_16BE_ENC]; + return XML_TOK_BOM; + /* 00 3C is handled in the default case */ + case 0x3C00: + if ((INIT_ENC_INDEX(enc) == UTF_16BE_ENC + || INIT_ENC_INDEX(enc) == UTF_16_ENC) + && state == XML_CONTENT_STATE) + break; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + case 0xFFFE: + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC + && state == XML_CONTENT_STATE) + break; + *nextTokPtr = ptr + 2; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XML_TOK_BOM; + case 0xEFBB: + /* Maybe a UTF-8 BOM (EF BB BF) */ + /* If there's an explicitly specified (external) encoding + of ISO-8859-1 or some flavour of UTF-16 + and this is an external text entity, + don't look for the BOM, + because it might be a legal data. + */ + if (state == XML_CONTENT_STATE) { + int e = INIT_ENC_INDEX(enc); + if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC + || e == UTF_16LE_ENC || e == UTF_16_ENC) + break; + } + if (ptr + 2 == end) + return XML_TOK_PARTIAL; + if ((unsigned char)ptr[2] == 0xBF) { + *nextTokPtr = ptr + 3; + *encPtr = encodingTable[UTF_8_ENC]; + return XML_TOK_BOM; + } + break; + default: + if (ptr[0] == '\0') { + /* 0 isn't a legal data character. Furthermore a document + entity can only start with ASCII characters. So the only + way this can fail to be big-endian UTF-16 if it it's an + external parsed general entity that's labelled as + UTF-16LE. + */ + if (state == XML_CONTENT_STATE && INIT_ENC_INDEX(enc) == UTF_16LE_ENC) + break; + *encPtr = encodingTable[UTF_16BE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + } + else if (ptr[1] == '\0') { + /* We could recover here in the case: + - parsing an external entity + - second byte is 0 + - no externally specified encoding + - no encoding declaration + by assuming UTF-16LE. But we don't, because this would mean when + presented just with a single byte, we couldn't reliably determine + whether we needed further bytes. + */ + if (state == XML_CONTENT_STATE) + break; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + } + break; + } + } + *encPtr = encodingTable[INIT_ENC_INDEX(enc)]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); +} + + +#define NS(x) x +#define ns(x) x +#define XML_TOK_NS_C +#include "xmltok_ns.c" +#undef XML_TOK_NS_C +#undef NS +#undef ns + +#ifdef XML_NS + +#define NS(x) x ## NS +#define ns(x) x ## _ns + +#define XML_TOK_NS_C +#include "xmltok_ns.c" +#undef XML_TOK_NS_C + +#undef NS +#undef ns + +ENCODING * +XmlInitUnknownEncodingNS(void *mem, + int *table, + CONVERTER convert, + void *userData) +{ + ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData); + if (enc) + ((struct normal_encoding *)enc)->type[ASCII_COLON] = BT_COLON; + return enc; +} + +#endif /* XML_NS */ diff --git a/contrib/expat/lib/xmltok.h b/contrib/expat/lib/xmltok.h new file mode 100644 index 0000000..ca867aa --- /dev/null +++ b/contrib/expat/lib/xmltok.h @@ -0,0 +1,316 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef XmlTok_INCLUDED +#define XmlTok_INCLUDED 1 + +#ifdef __cplusplus +extern "C" { +#endif + +/* The following token may be returned by XmlContentTok */ +#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be + start of illegal ]]> sequence */ +/* The following tokens may be returned by both XmlPrologTok and + XmlContentTok. +*/ +#define XML_TOK_NONE -4 /* The string to be scanned is empty */ +#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan; + might be part of CRLF sequence */ +#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ +#define XML_TOK_PARTIAL -1 /* only part of a token */ +#define XML_TOK_INVALID 0 + +/* The following tokens are returned by XmlContentTok; some are also + returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok. +*/ +#define XML_TOK_START_TAG_WITH_ATTS 1 +#define XML_TOK_START_TAG_NO_ATTS 2 +#define XML_TOK_EMPTY_ELEMENT_WITH_ATTS 3 /* empty element tag <e/> */ +#define XML_TOK_EMPTY_ELEMENT_NO_ATTS 4 +#define XML_TOK_END_TAG 5 +#define XML_TOK_DATA_CHARS 6 +#define XML_TOK_DATA_NEWLINE 7 +#define XML_TOK_CDATA_SECT_OPEN 8 +#define XML_TOK_ENTITY_REF 9 +#define XML_TOK_CHAR_REF 10 /* numeric character reference */ + +/* The following tokens may be returned by both XmlPrologTok and + XmlContentTok. +*/ +#define XML_TOK_PI 11 /* processing instruction */ +#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ +#define XML_TOK_COMMENT 13 +#define XML_TOK_BOM 14 /* Byte order mark */ + +/* The following tokens are returned only by XmlPrologTok */ +#define XML_TOK_PROLOG_S 15 +#define XML_TOK_DECL_OPEN 16 /* <!foo */ +#define XML_TOK_DECL_CLOSE 17 /* > */ +#define XML_TOK_NAME 18 +#define XML_TOK_NMTOKEN 19 +#define XML_TOK_POUND_NAME 20 /* #name */ +#define XML_TOK_OR 21 /* | */ +#define XML_TOK_PERCENT 22 +#define XML_TOK_OPEN_PAREN 23 +#define XML_TOK_CLOSE_PAREN 24 +#define XML_TOK_OPEN_BRACKET 25 +#define XML_TOK_CLOSE_BRACKET 26 +#define XML_TOK_LITERAL 27 +#define XML_TOK_PARAM_ENTITY_REF 28 +#define XML_TOK_INSTANCE_START 29 + +/* The following occur only in element type declarations */ +#define XML_TOK_NAME_QUESTION 30 /* name? */ +#define XML_TOK_NAME_ASTERISK 31 /* name* */ +#define XML_TOK_NAME_PLUS 32 /* name+ */ +#define XML_TOK_COND_SECT_OPEN 33 /* <![ */ +#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */ +#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ +#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ +#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ +#define XML_TOK_COMMA 38 + +/* The following token is returned only by XmlAttributeValueTok */ +#define XML_TOK_ATTRIBUTE_VALUE_S 39 + +/* The following token is returned only by XmlCdataSectionTok */ +#define XML_TOK_CDATA_SECT_CLOSE 40 + +/* With namespace processing this is returned by XmlPrologTok for a + name with a colon. +*/ +#define XML_TOK_PREFIXED_NAME 41 + +#ifdef XML_DTD +#define XML_TOK_IGNORE_SECT 42 +#endif /* XML_DTD */ + +#ifdef XML_DTD +#define XML_N_STATES 4 +#else /* not XML_DTD */ +#define XML_N_STATES 3 +#endif /* not XML_DTD */ + +#define XML_PROLOG_STATE 0 +#define XML_CONTENT_STATE 1 +#define XML_CDATA_SECTION_STATE 2 +#ifdef XML_DTD +#define XML_IGNORE_SECTION_STATE 3 +#endif /* XML_DTD */ + +#define XML_N_LITERAL_TYPES 2 +#define XML_ATTRIBUTE_VALUE_LITERAL 0 +#define XML_ENTITY_VALUE_LITERAL 1 + +/* The size of the buffer passed to XmlUtf8Encode must be at least this. */ +#define XML_UTF8_ENCODE_MAX 4 +/* The size of the buffer passed to XmlUtf16Encode must be at least this. */ +#define XML_UTF16_ENCODE_MAX 2 + +typedef struct position { + /* first line and first column are 0 not 1 */ + XML_Size lineNumber; + XML_Size columnNumber; +} POSITION; + +typedef struct { + const char *name; + const char *valuePtr; + const char *valueEnd; + char normalized; +} ATTRIBUTE; + +struct encoding; +typedef struct encoding ENCODING; + +typedef int (PTRCALL *SCANNER)(const ENCODING *, + const char *, + const char *, + const char **); + +struct encoding { + SCANNER scanners[XML_N_STATES]; + SCANNER literalScanners[XML_N_LITERAL_TYPES]; + int (PTRCALL *sameName)(const ENCODING *, + const char *, + const char *); + int (PTRCALL *nameMatchesAscii)(const ENCODING *, + const char *, + const char *, + const char *); + int (PTRFASTCALL *nameLength)(const ENCODING *, const char *); + const char *(PTRFASTCALL *skipS)(const ENCODING *, const char *); + int (PTRCALL *getAtts)(const ENCODING *enc, + const char *ptr, + int attsMax, + ATTRIBUTE *atts); + int (PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); + int (PTRCALL *predefinedEntityName)(const ENCODING *, + const char *, + const char *); + void (PTRCALL *updatePosition)(const ENCODING *, + const char *ptr, + const char *end, + POSITION *); + int (PTRCALL *isPublicId)(const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr); + void (PTRCALL *utf8Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + char **toP, + const char *toLim); + void (PTRCALL *utf16Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + unsigned short **toP, + const unsigned short *toLim); + int minBytesPerChar; + char isUtf8; + char isUtf16; +}; + +/* Scan the string starting at ptr until the end of the next complete + token, but do not scan past eptr. Return an integer giving the + type of token. + + Return XML_TOK_NONE when ptr == eptr; nextTokPtr will not be set. + + Return XML_TOK_PARTIAL when the string does not contain a complete + token; nextTokPtr will not be set. + + Return XML_TOK_INVALID when the string does not start a valid + token; nextTokPtr will be set to point to the character which made + the token invalid. + + Otherwise the string starts with a valid token; nextTokPtr will be + set to point to the character following the end of that token. + + Each data character counts as a single token, but adjacent data + characters may be returned together. Similarly for characters in + the prolog outside literals, comments and processing instructions. +*/ + + +#define XmlTok(enc, state, ptr, end, nextTokPtr) \ + (((enc)->scanners[state])(enc, ptr, end, nextTokPtr)) + +#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) + +#define XmlContentTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) + +#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) + +#ifdef XML_DTD + +#define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) + +#endif /* XML_DTD */ + +/* This is used for performing a 2nd-level tokenization on the content + of a literal that has already been returned by XmlTok. +*/ +#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ + (((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr)) + +#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) + +#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) + +#define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2)) + +#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ + (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2)) + +#define XmlNameLength(enc, ptr) \ + (((enc)->nameLength)(enc, ptr)) + +#define XmlSkipS(enc, ptr) \ + (((enc)->skipS)(enc, ptr)) + +#define XmlGetAttributes(enc, ptr, attsMax, atts) \ + (((enc)->getAtts)(enc, ptr, attsMax, atts)) + +#define XmlCharRefNumber(enc, ptr) \ + (((enc)->charRefNumber)(enc, ptr)) + +#define XmlPredefinedEntityName(enc, ptr, end) \ + (((enc)->predefinedEntityName)(enc, ptr, end)) + +#define XmlUpdatePosition(enc, ptr, end, pos) \ + (((enc)->updatePosition)(enc, ptr, end, pos)) + +#define XmlIsPublicId(enc, ptr, end, badPtr) \ + (((enc)->isPublicId)(enc, ptr, end, badPtr)) + +#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ + (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim)) + +#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ + (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim)) + +typedef struct { + ENCODING initEnc; + const ENCODING **encPtr; +} INIT_ENCODING; + +int XmlParseXmlDecl(int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingNamePtr, + const ENCODING **namedEncodingPtr, + int *standalonePtr); + +int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); +const ENCODING *XmlGetUtf8InternalEncoding(void); +const ENCODING *XmlGetUtf16InternalEncoding(void); +int FASTCALL XmlUtf8Encode(int charNumber, char *buf); +int FASTCALL XmlUtf16Encode(int charNumber, unsigned short *buf); +int XmlSizeOfUnknownEncoding(void); + + +typedef int (XMLCALL *CONVERTER) (void *userData, const char *p); + +ENCODING * +XmlInitUnknownEncoding(void *mem, + int *table, + CONVERTER convert, + void *userData); + +int XmlParseXmlDeclNS(int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingNamePtr, + const ENCODING **namedEncodingPtr, + int *standalonePtr); + +int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name); +const ENCODING *XmlGetUtf8InternalEncodingNS(void); +const ENCODING *XmlGetUtf16InternalEncodingNS(void); +ENCODING * +XmlInitUnknownEncodingNS(void *mem, + int *table, + CONVERTER convert, + void *userData); +#ifdef __cplusplus +} +#endif + +#endif /* not XmlTok_INCLUDED */ diff --git a/contrib/expat/lib/xmltok_impl.c b/contrib/expat/lib/xmltok_impl.c new file mode 100644 index 0000000..9c2895b --- /dev/null +++ b/contrib/expat/lib/xmltok_impl.c @@ -0,0 +1,1783 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* This file is included! */ +#ifdef XML_TOK_IMPL_C + +#ifndef IS_INVALID_CHAR +#define IS_INVALID_CHAR(enc, ptr, n) (0) +#endif + +#define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +#define INVALID_CASES(ptr, nextTokPtr) \ + INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ + case BT_NONXML: \ + case BT_MALFORM: \ + case BT_TRAIL: \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; + +#define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (!IS_NAME_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +#define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (!IS_NAME_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + case BT_NMSTRT: \ + case BT_HEX: \ + case BT_DIGIT: \ + case BT_NAME: \ + case BT_MINUS: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) + +#define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (!IS_NMSTRT_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +#define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (!IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + case BT_NMSTRT: \ + case BT_HEX: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) + +#ifndef PREFIX +#define PREFIX(ident) ident +#endif + +/* ptr points to character following "<!-" */ + +static int PTRCALL +PREFIX(scanComment)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr != end) { + if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_MINUS: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COMMENT; + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "<!" */ + +static int PTRCALL +PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_MINUS: + return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LSQB: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COND_SECT_OPEN; + case BT_NMSTRT: + case BT_HEX: + ptr += MINBPC(enc); + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_PERCNT: + if (ptr + MINBPC(enc) == end) + return XML_TOK_PARTIAL; + /* don't allow <!ENTITY% foo "whatever"> */ + switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) { + case BT_S: case BT_CR: case BT_LF: case BT_PERCNT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + /* fall through */ + case BT_S: case BT_CR: case BT_LF: + *nextTokPtr = ptr; + return XML_TOK_DECL_OPEN; + case BT_NMSTRT: + case BT_HEX: + ptr += MINBPC(enc); + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, + const char *end, int *tokPtr) +{ + int upper = 0; + *tokPtr = XML_TOK_PI; + if (end - ptr != MINBPC(enc)*3) + return 1; + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_x: + break; + case ASCII_X: + upper = 1; + break; + default: + return 1; + } + ptr += MINBPC(enc); + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_m: + break; + case ASCII_M: + upper = 1; + break; + default: + return 1; + } + ptr += MINBPC(enc); + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_l: + break; + case ASCII_L: + upper = 1; + break; + default: + return 1; + } + if (upper) + return 0; + *tokPtr = XML_TOK_XML_DECL; + return 1; +} + +/* ptr points to character following "<?" */ + +static int PTRCALL +PREFIX(scanPi)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + int tok; + const char *target = ptr; + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_CR: case BT_LF: + if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_QUEST: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr + MINBPC(enc); + return tok; + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; + case BT_QUEST: + if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr + MINBPC(enc); + return tok; + } + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A, + ASCII_T, ASCII_A, ASCII_LSQB }; + int i; + /* CDATA[ */ + if (end - ptr < 6 * MINBPC(enc)) + return XML_TOK_PARTIAL; + for (i = 0; i < 6; i++, ptr += MINBPC(enc)) { + if (!CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + *nextTokPtr = ptr; + return XML_TOK_CDATA_SECT_OPEN; +} + +static int PTRCALL +PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_RSQB: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + break; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr -= MINBPC(enc); + break; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CDATA_SECT_CLOSE; + case BT_CR: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + case BT_LF: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + INVALID_CASES(ptr, nextTokPtr) + default: + ptr += MINBPC(enc); + break; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NONXML: + case BT_MALFORM: + case BT_TRAIL: + case BT_CR: + case BT_LF: + case BT_RSQB: + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +/* ptr points to character following "</" */ + +static int PTRCALL +PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_CR: case BT_LF: + for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: case BT_CR: case BT_LF: + break; + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_END_TAG; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +#ifdef XML_NS + case BT_COLON: + /* no need to check qname syntax here, + since end-tag must match exactly */ + ptr += MINBPC(enc); + break; +#endif + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_END_TAG; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&#X" */ + +static int PTRCALL +PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + break; + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CHAR_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&#" */ + +static int PTRCALL +PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr != end) { + if (CHAR_MATCHES(enc, ptr, ASCII_x)) + return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + break; + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CHAR_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&" */ + +static int PTRCALL +PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_NUM: + return PREFIX(scanCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_ENTITY_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following first character of attribute name */ + +static int PTRCALL +PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ +#ifdef XML_NS + int hadColon = 0; +#endif + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +#ifdef XML_NS + case BT_COLON: + if (hadColon) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + hadColon = 1; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; +#endif + case BT_S: case BT_CR: case BT_LF: + for (;;) { + int t; + + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + t = BYTE_TYPE(enc, ptr); + if (t == BT_EQUALS) + break; + switch (t) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + /* fall through */ + case BT_EQUALS: + { + int open; +#ifdef XML_NS + hadColon = 0; +#endif + for (;;) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + open = BYTE_TYPE(enc, ptr); + if (open == BT_QUOT || open == BT_APOS) + break; + switch (open) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + ptr += MINBPC(enc); + /* in attribute value */ + for (;;) { + int t; + if (ptr == end) + return XML_TOK_PARTIAL; + t = BYTE_TYPE(enc, ptr); + if (t == open) + break; + switch (t) { + INVALID_CASES(ptr, nextTokPtr) + case BT_AMP: + { + int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr); + if (tok <= 0) { + if (tok == XML_TOK_INVALID) + *nextTokPtr = ptr; + return tok; + } + break; + } + case BT_LT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + default: + ptr += MINBPC(enc); + break; + } + } + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_CR: + case BT_LF: + break; + case BT_SOL: + goto sol; + case BT_GT: + goto gt; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + /* ptr points to closing quote */ + for (;;) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_CR: case BT_LF: + continue; + case BT_GT: + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_WITH_ATTS; + case BT_SOL: + sol: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_WITH_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; + } + break; + } + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "<" */ + +static int PTRCALL +PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ +#ifdef XML_NS + int hadColon; +#endif + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_EXCL: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_MINUS: + return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LSQB: + return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), + end, nextTokPtr); + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_SOL: + return PREFIX(scanEndTag)(enc, ptr + MINBPC(enc), end, nextTokPtr); + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } +#ifdef XML_NS + hadColon = 0; +#endif + /* we have a start-tag */ + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +#ifdef XML_NS + case BT_COLON: + if (hadColon) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + hadColon = 1; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; +#endif + case BT_S: case BT_CR: case BT_LF: + { + ptr += MINBPC(enc); + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: + goto gt; + case BT_SOL: + goto sol; + case BT_S: case BT_CR: case BT_LF: + ptr += MINBPC(enc); + continue; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + return PREFIX(scanAtts)(enc, ptr, end, nextTokPtr); + } + return XML_TOK_PARTIAL; + } + case BT_GT: + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_NO_ATTS; + case BT_SOL: + sol: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_NO_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_LT: + return PREFIX(scanLt)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_AMP: + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_CR: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + case BT_LF: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + case BT_RSQB: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_RSQB; + if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + break; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_RSQB; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr -= MINBPC(enc); + break; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + INVALID_CASES(ptr, nextTokPtr) + default: + ptr += MINBPC(enc); + break; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_RSQB: + if (ptr + MINBPC(enc) != end) { + if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { + ptr += MINBPC(enc); + break; + } + if (ptr + 2*MINBPC(enc) != end) { + if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), ASCII_GT)) { + ptr += MINBPC(enc); + break; + } + *nextTokPtr = ptr + 2*MINBPC(enc); + return XML_TOK_INVALID; + } + } + /* fall through */ + case BT_AMP: + case BT_LT: + case BT_NONXML: + case BT_MALFORM: + case BT_TRAIL: + case BT_CR: + case BT_LF: + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +/* ptr points to character following "%" */ + +static int PTRCALL +PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_LF: case BT_CR: case BT_PERCNT: + *nextTokPtr = ptr; + return XML_TOK_PERCENT; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_PARAM_ENTITY_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_CR: case BT_LF: case BT_S: + case BT_RPAR: case BT_GT: case BT_PERCNT: case BT_VERBAR: + *nextTokPtr = ptr; + return XML_TOK_POUND_NAME; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return -XML_TOK_POUND_NAME; +} + +static int PTRCALL +PREFIX(scanLit)(int open, const ENCODING *enc, + const char *ptr, const char *end, + const char **nextTokPtr) +{ + while (ptr != end) { + int t = BYTE_TYPE(enc, ptr); + switch (t) { + INVALID_CASES(ptr, nextTokPtr) + case BT_QUOT: + case BT_APOS: + ptr += MINBPC(enc); + if (t != open) + break; + if (ptr == end) + return -XML_TOK_LITERAL; + *nextTokPtr = ptr; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: case BT_CR: case BT_LF: + case BT_GT: case BT_PERCNT: case BT_LSQB: + return XML_TOK_LITERAL; + default: + return XML_TOK_INVALID; + } + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + int tok; + if (ptr == end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_QUOT: + return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_APOS: + return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LT: + { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_EXCL: + return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_NMSTRT: + case BT_HEX: + case BT_NONASCII: + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + *nextTokPtr = ptr - MINBPC(enc); + return XML_TOK_INSTANCE_START; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + case BT_CR: + if (ptr + MINBPC(enc) == end) { + *nextTokPtr = end; + /* indicate that this might be part of a CR/LF pair */ + return -XML_TOK_PROLOG_S; + } + /* fall through */ + case BT_S: case BT_LF: + for (;;) { + ptr += MINBPC(enc); + if (ptr == end) + break; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: case BT_LF: + break; + case BT_CR: + /* don't split CR/LF pair */ + if (ptr + MINBPC(enc) != end) + break; + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_PROLOG_S; + } + } + *nextTokPtr = ptr; + return XML_TOK_PROLOG_S; + case BT_PERCNT: + return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_COMMA: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COMMA; + case BT_LSQB: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OPEN_BRACKET; + case BT_RSQB: + ptr += MINBPC(enc); + if (ptr == end) + return -XML_TOK_CLOSE_BRACKET; + if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { + if (ptr + MINBPC(enc) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) { + *nextTokPtr = ptr + 2*MINBPC(enc); + return XML_TOK_COND_SECT_CLOSE; + } + } + *nextTokPtr = ptr; + return XML_TOK_CLOSE_BRACKET; + case BT_LPAR: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OPEN_PAREN; + case BT_RPAR: + ptr += MINBPC(enc); + if (ptr == end) + return -XML_TOK_CLOSE_PAREN; + switch (BYTE_TYPE(enc, ptr)) { + case BT_AST: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_ASTERISK; + case BT_QUEST: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_QUESTION; + case BT_PLUS: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_PLUS; + case BT_CR: case BT_LF: case BT_S: + case BT_GT: case BT_COMMA: case BT_VERBAR: + case BT_RPAR: + *nextTokPtr = ptr; + return XML_TOK_CLOSE_PAREN; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_VERBAR: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OR; + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DECL_CLOSE; + case BT_NUM: + return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr); +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NAME; \ + break; \ + } \ + if (IS_NAME_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NMTOKEN; \ + break; \ + } \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NMSTRT: + case BT_HEX: + tok = XML_TOK_NAME; + ptr += MINBPC(enc); + break; + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: +#ifdef XML_NS + case BT_COLON: +#endif + tok = XML_TOK_NMTOKEN; + ptr += MINBPC(enc); + break; + case BT_NONASCII: + if (IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { + ptr += MINBPC(enc); + tok = XML_TOK_NAME; + break; + } + if (IS_NAME_CHAR_MINBPC(enc, ptr)) { + ptr += MINBPC(enc); + tok = XML_TOK_NMTOKEN; + break; + } + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: case BT_RPAR: case BT_COMMA: + case BT_VERBAR: case BT_LSQB: case BT_PERCNT: + case BT_S: case BT_CR: case BT_LF: + *nextTokPtr = ptr; + return tok; +#ifdef XML_NS + case BT_COLON: + ptr += MINBPC(enc); + switch (tok) { + case XML_TOK_NAME: + if (ptr == end) + return XML_TOK_PARTIAL; + tok = XML_TOK_PREFIXED_NAME; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + default: + tok = XML_TOK_NMTOKEN; + break; + } + break; + case XML_TOK_PREFIXED_NAME: + tok = XML_TOK_NMTOKEN; + break; + } + break; +#endif + case BT_PLUS: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_PLUS; + case BT_AST: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_ASTERISK; + case BT_QUEST: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_QUESTION; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return -tok; +} + +static int PTRCALL +PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + const char *start; + if (ptr == end) + return XML_TOK_NONE; + start = ptr; + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: ptr += n; break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_AMP: + if (ptr == start) + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_LT: + /* this is for inside entity references */ + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_LF: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_CR: + if (ptr == start) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_S: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_ATTRIBUTE_VALUE_S; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +static int PTRCALL +PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + const char *start; + if (ptr == end) + return XML_TOK_NONE; + start = ptr; + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: ptr += n; break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_AMP: + if (ptr == start) + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_PERCNT: + if (ptr == start) { + int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), + end, nextTokPtr); + return (tok == XML_TOK_PERCENT) ? XML_TOK_INVALID : tok; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_LF: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_CR: + if (ptr == start) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +#ifdef XML_DTD + +static int PTRCALL +PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + int level = 0; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + end = ptr + n; + } + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_LT: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_EXCL)) { + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_LSQB)) { + ++level; + ptr += MINBPC(enc); + } + } + break; + case BT_RSQB: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr += MINBPC(enc); + if (level == 0) { + *nextTokPtr = ptr; + return XML_TOK_IGNORE_SECT; + } + --level; + } + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; +} + +#endif /* XML_DTD */ + +static int PTRCALL +PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, + const char **badPtr) +{ + ptr += MINBPC(enc); + end -= MINBPC(enc); + for (; ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + case BT_MINUS: + case BT_APOS: + case BT_LPAR: + case BT_RPAR: + case BT_PLUS: + case BT_COMMA: + case BT_SOL: + case BT_EQUALS: + case BT_QUEST: + case BT_CR: + case BT_LF: + case BT_SEMI: + case BT_EXCL: + case BT_AST: + case BT_PERCNT: + case BT_NUM: +#ifdef XML_NS + case BT_COLON: +#endif + break; + case BT_S: + if (CHAR_MATCHES(enc, ptr, ASCII_TAB)) { + *badPtr = ptr; + return 0; + } + break; + case BT_NAME: + case BT_NMSTRT: + if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f)) + break; + default: + switch (BYTE_TO_ASCII(enc, ptr)) { + case 0x24: /* $ */ + case 0x40: /* @ */ + break; + default: + *badPtr = ptr; + return 0; + } + break; + } + } + return 1; +} + +/* This must only be called for a well-formed start-tag or empty + element tag. Returns the number of attributes. Pointers to the + first attsMax attributes are stored in atts. +*/ + +static int PTRCALL +PREFIX(getAtts)(const ENCODING *enc, const char *ptr, + int attsMax, ATTRIBUTE *atts) +{ + enum { other, inName, inValue } state = inName; + int nAtts = 0; + int open = 0; /* defined when state == inValue; + initialization just to shut up compilers */ + + for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { +#define START_NAME \ + if (state == other) { \ + if (nAtts < attsMax) { \ + atts[nAtts].name = ptr; \ + atts[nAtts].normalized = 1; \ + } \ + state = inName; \ + } +#define LEAD_CASE(n) \ + case BT_LEAD ## n: START_NAME ptr += (n - MINBPC(enc)); break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NONASCII: + case BT_NMSTRT: + case BT_HEX: + START_NAME + break; +#undef START_NAME + case BT_QUOT: + if (state != inValue) { + if (nAtts < attsMax) + atts[nAtts].valuePtr = ptr + MINBPC(enc); + state = inValue; + open = BT_QUOT; + } + else if (open == BT_QUOT) { + state = other; + if (nAtts < attsMax) + atts[nAtts].valueEnd = ptr; + nAtts++; + } + break; + case BT_APOS: + if (state != inValue) { + if (nAtts < attsMax) + atts[nAtts].valuePtr = ptr + MINBPC(enc); + state = inValue; + open = BT_APOS; + } + else if (open == BT_APOS) { + state = other; + if (nAtts < attsMax) + atts[nAtts].valueEnd = ptr; + nAtts++; + } + break; + case BT_AMP: + if (nAtts < attsMax) + atts[nAtts].normalized = 0; + break; + case BT_S: + if (state == inName) + state = other; + else if (state == inValue + && nAtts < attsMax + && atts[nAtts].normalized + && (ptr == atts[nAtts].valuePtr + || BYTE_TO_ASCII(enc, ptr) != ASCII_SPACE + || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ASCII_SPACE + || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open)) + atts[nAtts].normalized = 0; + break; + case BT_CR: case BT_LF: + /* This case ensures that the first attribute name is counted + Apart from that we could just change state on the quote. */ + if (state == inName) + state = other; + else if (state == inValue && nAtts < attsMax) + atts[nAtts].normalized = 0; + break; + case BT_GT: + case BT_SOL: + if (state != inValue) + return nAtts; + break; + default: + break; + } + } + /* not reached */ +} + +static int PTRFASTCALL +PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) +{ + int result = 0; + /* skip &# */ + ptr += 2*MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_x)) { + for (ptr += MINBPC(enc); + !CHAR_MATCHES(enc, ptr, ASCII_SEMI); + ptr += MINBPC(enc)) { + int c = BYTE_TO_ASCII(enc, ptr); + switch (c) { + case ASCII_0: case ASCII_1: case ASCII_2: case ASCII_3: case ASCII_4: + case ASCII_5: case ASCII_6: case ASCII_7: case ASCII_8: case ASCII_9: + result <<= 4; + result |= (c - ASCII_0); + break; + case ASCII_A: case ASCII_B: case ASCII_C: + case ASCII_D: case ASCII_E: case ASCII_F: + result <<= 4; + result += 10 + (c - ASCII_A); + break; + case ASCII_a: case ASCII_b: case ASCII_c: + case ASCII_d: case ASCII_e: case ASCII_f: + result <<= 4; + result += 10 + (c - ASCII_a); + break; + } + if (result >= 0x110000) + return -1; + } + } + else { + for (; !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { + int c = BYTE_TO_ASCII(enc, ptr); + result *= 10; + result += (c - ASCII_0); + if (result >= 0x110000) + return -1; + } + } + return checkCharRefNumber(result); +} + +static int PTRCALL +PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, + const char *end) +{ + switch ((end - ptr)/MINBPC(enc)) { + case 2: + if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_t)) { + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_l: + return ASCII_LT; + case ASCII_g: + return ASCII_GT; + } + } + break; + case 3: + if (CHAR_MATCHES(enc, ptr, ASCII_a)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_m)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_p)) + return ASCII_AMP; + } + } + break; + case 4: + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_q: + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_u)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_o)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_t)) + return ASCII_QUOT; + } + } + break; + case ASCII_a: + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_p)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_o)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_s)) + return ASCII_APOS; + } + } + break; + } + } + return 0; +} + +static int PTRCALL +PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2) +{ + for (;;) { + switch (BYTE_TYPE(enc, ptr1)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (*ptr1++ != *ptr2++) \ + return 0; + LEAD_CASE(4) LEAD_CASE(3) LEAD_CASE(2) +#undef LEAD_CASE + /* fall through */ + if (*ptr1++ != *ptr2++) + return 0; + break; + case BT_NONASCII: + case BT_NMSTRT: +#ifdef XML_NS + case BT_COLON: +#endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + if (*ptr2++ != *ptr1++) + return 0; + if (MINBPC(enc) > 1) { + if (*ptr2++ != *ptr1++) + return 0; + if (MINBPC(enc) > 2) { + if (*ptr2++ != *ptr1++) + return 0; + if (MINBPC(enc) > 3) { + if (*ptr2++ != *ptr1++) + return 0; + } + } + } + break; + default: + if (MINBPC(enc) == 1 && *ptr1 == *ptr2) + return 1; + switch (BYTE_TYPE(enc, ptr2)) { + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + case BT_NONASCII: + case BT_NMSTRT: +#ifdef XML_NS + case BT_COLON: +#endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + return 0; + default: + return 1; + } + } + } + /* not reached */ +} + +static int PTRCALL +PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, + const char *end1, const char *ptr2) +{ + for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) { + if (ptr1 == end1) + return 0; + if (!CHAR_MATCHES(enc, ptr1, *ptr2)) + return 0; + } + return ptr1 == end1; +} + +static int PTRFASTCALL +PREFIX(nameLength)(const ENCODING *enc, const char *ptr) +{ + const char *start = ptr; + for (;;) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: ptr += n; break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NONASCII: + case BT_NMSTRT: +#ifdef XML_NS + case BT_COLON: +#endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + ptr += MINBPC(enc); + break; + default: + return (int)(ptr - start); + } + } +} + +static const char * PTRFASTCALL +PREFIX(skipS)(const ENCODING *enc, const char *ptr) +{ + for (;;) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_LF: + case BT_CR: + case BT_S: + ptr += MINBPC(enc); + break; + default: + return ptr; + } + } +} + +static void PTRCALL +PREFIX(updatePosition)(const ENCODING *enc, + const char *ptr, + const char *end, + POSITION *pos) +{ + while (ptr < end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + ptr += n; \ + break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_LF: + pos->columnNumber = (XML_Size)-1; + pos->lineNumber++; + ptr += MINBPC(enc); + break; + case BT_CR: + pos->lineNumber++; + ptr += MINBPC(enc); + if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + pos->columnNumber = (XML_Size)-1; + break; + default: + ptr += MINBPC(enc); + break; + } + pos->columnNumber++; + } +} + +#undef DO_LEAD_CASE +#undef MULTIBYTE_CASES +#undef INVALID_CASES +#undef CHECK_NAME_CASE +#undef CHECK_NAME_CASES +#undef CHECK_NMSTRT_CASE +#undef CHECK_NMSTRT_CASES + +#endif /* XML_TOK_IMPL_C */ diff --git a/contrib/expat/lib/xmltok_impl.h b/contrib/expat/lib/xmltok_impl.h new file mode 100644 index 0000000..da0ea60 --- /dev/null +++ b/contrib/expat/lib/xmltok_impl.h @@ -0,0 +1,46 @@ +/* +Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +enum { + BT_NONXML, + BT_MALFORM, + BT_LT, + BT_AMP, + BT_RSQB, + BT_LEAD2, + BT_LEAD3, + BT_LEAD4, + BT_TRAIL, + BT_CR, + BT_LF, + BT_GT, + BT_QUOT, + BT_APOS, + BT_EQUALS, + BT_QUEST, + BT_EXCL, + BT_SOL, + BT_SEMI, + BT_NUM, + BT_LSQB, + BT_S, + BT_NMSTRT, + BT_COLON, + BT_HEX, + BT_DIGIT, + BT_NAME, + BT_MINUS, + BT_OTHER, /* known not to be a name or name start character */ + BT_NONASCII, /* might be a name or name start character */ + BT_PERCNT, + BT_LPAR, + BT_RPAR, + BT_AST, + BT_PLUS, + BT_COMMA, + BT_VERBAR +}; + +#include <stddef.h> diff --git a/contrib/expat/lib/xmltok_ns.c b/contrib/expat/lib/xmltok_ns.c new file mode 100644 index 0000000..c3b88fd --- /dev/null +++ b/contrib/expat/lib/xmltok_ns.c @@ -0,0 +1,115 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* This file is included! */ +#ifdef XML_TOK_NS_C + +const ENCODING * +NS(XmlGetUtf8InternalEncoding)(void) +{ + return &ns(internal_utf8_encoding).enc; +} + +const ENCODING * +NS(XmlGetUtf16InternalEncoding)(void) +{ +#if BYTEORDER == 1234 + return &ns(internal_little2_encoding).enc; +#elif BYTEORDER == 4321 + return &ns(internal_big2_encoding).enc; +#else + const short n = 1; + return (*(const char *)&n + ? &ns(internal_little2_encoding).enc + : &ns(internal_big2_encoding).enc); +#endif +} + +static const ENCODING * const NS(encodings)[] = { + &ns(latin1_encoding).enc, + &ns(ascii_encoding).enc, + &ns(utf8_encoding).enc, + &ns(big2_encoding).enc, + &ns(big2_encoding).enc, + &ns(little2_encoding).enc, + &ns(utf8_encoding).enc /* NO_ENC */ +}; + +static int PTRCALL +NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + return initScan(NS(encodings), (const INIT_ENCODING *)enc, + XML_PROLOG_STATE, ptr, end, nextTokPtr); +} + +static int PTRCALL +NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + return initScan(NS(encodings), (const INIT_ENCODING *)enc, + XML_CONTENT_STATE, ptr, end, nextTokPtr); +} + +int +NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, + const char *name) +{ + int i = getEncodingIndex(name); + if (i == UNKNOWN_ENC) + return 0; + SET_INIT_ENC_INDEX(p, i); + p->initEnc.scanners[XML_PROLOG_STATE] = NS(initScanProlog); + p->initEnc.scanners[XML_CONTENT_STATE] = NS(initScanContent); + p->initEnc.updatePosition = initUpdatePosition; + p->encPtr = encPtr; + *encPtr = &(p->initEnc); + return 1; +} + +static const ENCODING * +NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) +{ +#define ENCODING_MAX 128 + char buf[ENCODING_MAX]; + char *p = buf; + int i; + XmlUtf8Convert(enc, &ptr, end, &p, p + ENCODING_MAX - 1); + if (ptr != end) + return 0; + *p = 0; + if (streqci(buf, KW_UTF_16) && enc->minBytesPerChar == 2) + return enc; + i = getEncodingIndex(buf); + if (i == UNKNOWN_ENC) + return 0; + return NS(encodings)[i]; +} + +int +NS(XmlParseXmlDecl)(int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingName, + const ENCODING **encoding, + int *standalone) +{ + return doParseXmlDecl(NS(findEncoding), + isGeneralTextEntity, + enc, + ptr, + end, + badPtr, + versionPtr, + versionEndPtr, + encodingName, + encoding, + standalone); +} + +#endif /* XML_TOK_NS_C */ diff --git a/contrib/expat/tests/README.txt b/contrib/expat/tests/README.txt new file mode 100644 index 0000000..30e1d4d --- /dev/null +++ b/contrib/expat/tests/README.txt @@ -0,0 +1,13 @@ +This directory contains the (fledgling) test suite for Expat. The +tests provide general unit testing and regression coverage. The tests +are not expected to be useful examples of Expat usage; see the +examples/ directory for that. + +The Expat tests use a partial internal implementation of the "Check" +unit testing framework for C. More information on Check can be found at: + + http://check.sourceforge.net/ + +Expat must be built and, depending on platform, must be installed, before "make check" can be executed. + +This test suite can all change in a later version. diff --git a/contrib/expat/tests/benchmark/README.txt b/contrib/expat/tests/benchmark/README.txt new file mode 100644 index 0000000..7f9cca0 --- /dev/null +++ b/contrib/expat/tests/benchmark/README.txt @@ -0,0 +1,16 @@ +Use this benchmark command line utility as follows: + + benchmark [-n] <file name> <buffer size> <# iterations> + +The command line arguments are: + + -n ... optional; if supplied, namespace processing is turned on + <file name> ... name/path of test xml file + <buffer size> ... size of processing buffer; + the file is parsed in chunks of this size + <# iterations> ... how often will the file be parsed + +Returns: + + The time (in seconds) it takes to parse the test file, + averaged over the number of iterations.
\ No newline at end of file diff --git a/contrib/expat/tests/benchmark/benchmark.c b/contrib/expat/tests/benchmark/benchmark.c new file mode 100644 index 0000000..0f0fd18c --- /dev/null +++ b/contrib/expat/tests/benchmark/benchmark.c @@ -0,0 +1,114 @@ +#include <sys/stat.h> +#include <stdlib.h> +#include <stdio.h> +#include <time.h> +#include "expat.h" + +#if defined(__amigaos__) && defined(__USE_INLINE__) +#include <proto/expat.h> +#endif + +#ifdef XML_LARGE_SIZE +#define XML_FMT_INT_MOD "ll" +#else +#define XML_FMT_INT_MOD "l" +#endif + +static void +usage(const char *prog, int rc) +{ + fprintf(stderr, + "usage: %s [-n] filename bufferSize nr_of_loops\n", prog); + exit(rc); +} + +int main (int argc, char *argv[]) +{ + XML_Parser parser; + char *XMLBuf, *XMLBufEnd, *XMLBufPtr; + FILE *fd; + struct stat fileAttr; + int nrOfLoops, bufferSize, fileSize, i, isFinal; + int j = 0, ns = 0; + clock_t tstart, tend; + double cpuTime = 0.0; + + if (argc > 1) { + if (argv[1][0] == '-') { + if (argv[1][1] == 'n' && argv[1][2] == '\0') { + ns = 1; + j = 1; + } + else + usage(argv[0], 1); + } + } + + if (argc != j + 4) + usage(argv[0], 1); + + if (stat (argv[j + 1], &fileAttr) != 0) { + fprintf (stderr, "could not access file '%s'\n", argv[j + 1]); + return 2; + } + + fd = fopen (argv[j + 1], "r"); + if (!fd) { + fprintf (stderr, "could not open file '%s'\n", argv[j + 1]); + exit(2); + } + + bufferSize = atoi (argv[j + 2]); + nrOfLoops = atoi (argv[j + 3]); + if (bufferSize <= 0 || nrOfLoops <= 0) { + fprintf (stderr, + "buffer size and nr of loops must be greater than zero.\n"); + exit(3); + } + + XMLBuf = malloc (fileAttr.st_size); + fileSize = fread (XMLBuf, sizeof (char), fileAttr.st_size, fd); + fclose (fd); + + if (ns) + parser = XML_ParserCreateNS(NULL, '!'); + else + parser = XML_ParserCreate(NULL); + + i = 0; + XMLBufEnd = XMLBuf + fileSize; + while (i < nrOfLoops) { + XMLBufPtr = XMLBuf; + isFinal = 0; + tstart = clock(); + do { + int parseBufferSize = XMLBufEnd - XMLBufPtr; + if (parseBufferSize <= bufferSize) + isFinal = 1; + else + parseBufferSize = bufferSize; + if (!XML_Parse (parser, XMLBufPtr, parseBufferSize, isFinal)) { + fprintf (stderr, "error '%s' at line %" XML_FMT_INT_MOD \ + "u character %" XML_FMT_INT_MOD "u\n", + XML_ErrorString (XML_GetErrorCode (parser)), + XML_GetCurrentLineNumber (parser), + XML_GetCurrentColumnNumber (parser)); + free (XMLBuf); + XML_ParserFree (parser); + exit (4); + } + XMLBufPtr += bufferSize; + } while (!isFinal); + tend = clock(); + cpuTime += ((double) (tend - tstart)) / CLOCKS_PER_SEC; + XML_ParserReset(parser, NULL); + i++; + } + + XML_ParserFree (parser); + free (XMLBuf); + + printf ("%d loops, with buffer size %d. Average time per loop: %f\n", + nrOfLoops, bufferSize, cpuTime / (double) nrOfLoops); + return 0; +} diff --git a/contrib/expat/tests/chardata.c b/contrib/expat/tests/chardata.c new file mode 100644 index 0000000..5fb0299 --- /dev/null +++ b/contrib/expat/tests/chardata.c @@ -0,0 +1,131 @@ +/* Copyright (c) 1998-2003 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. + + chardata.c +*/ + +#ifdef HAVE_EXPAT_CONFIG_H +#include <expat_config.h> +#endif +#ifdef HAVE_CHECK_H +#include <check.h> +#else +#include "minicheck.h" +#endif + +#include <assert.h> +#include <stdio.h> +#include <string.h> + +#include "chardata.h" + + +static int +xmlstrlen(const XML_Char *s) +{ + int len = 0; + assert(s != NULL); + while (s[len] != 0) + ++len; + return len; +} + + +void +CharData_Init(CharData *storage) +{ + assert(storage != NULL); + storage->count = -1; +} + +void +CharData_AppendString(CharData *storage, const char *s) +{ + int maxchars = sizeof(storage->data) / sizeof(storage->data[0]); + int len; + + assert(s != NULL); + len = strlen(s); + if (storage->count < 0) + storage->count = 0; + if ((len + storage->count) > maxchars) { + len = (maxchars - storage->count); + } + if (len + storage->count < sizeof(storage->data)) { + memcpy(storage->data + storage->count, s, len); + storage->count += len; + } +} + +void +CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len) +{ + int maxchars; + + assert(storage != NULL); + assert(s != NULL); + maxchars = sizeof(storage->data) / sizeof(storage->data[0]); + if (storage->count < 0) + storage->count = 0; + if (len < 0) + len = xmlstrlen(s); + if ((len + storage->count) > maxchars) { + len = (maxchars - storage->count); + } + if (len + storage->count < sizeof(storage->data)) { + memcpy(storage->data + storage->count, s, + len * sizeof(storage->data[0])); + storage->count += len; + } +} + +int +CharData_CheckString(CharData *storage, const char *expected) +{ + char buffer[1280]; + int len; + int count; + + assert(storage != NULL); + assert(expected != NULL); + count = (storage->count < 0) ? 0 : storage->count; + len = strlen(expected); + if (len != count) { + if (sizeof(XML_Char) == 1) + sprintf(buffer, "wrong number of data characters:" + " got %d, expected %d:\n%s", count, len, storage->data); + else + sprintf(buffer, + "wrong number of data characters: got %d, expected %d", + count, len); + fail(buffer); + return 0; + } + if (memcmp(expected, storage->data, len) != 0) { + fail("got bad data bytes"); + return 0; + } + return 1; +} + +int +CharData_CheckXMLChars(CharData *storage, const XML_Char *expected) +{ + char buffer[1024]; + int len = xmlstrlen(expected); + int count; + + assert(storage != NULL); + count = (storage->count < 0) ? 0 : storage->count; + if (len != count) { + sprintf(buffer, "wrong number of data characters: got %d, expected %d", + count, len); + fail(buffer); + return 0; + } + if (memcmp(expected, storage->data, len * sizeof(storage->data[0])) != 0) { + fail("got bad data bytes"); + return 0; + } + return 1; +} diff --git a/contrib/expat/tests/chardata.h b/contrib/expat/tests/chardata.h new file mode 100644 index 0000000..e8dc4ce --- /dev/null +++ b/contrib/expat/tests/chardata.h @@ -0,0 +1,40 @@ +/* chardata.h + + Interface to some helper routines used to accumulate and check text + and attribute content. +*/ + +#ifdef __cplusplus +extern "C" { +#endif + +#ifndef XML_CHARDATA_H +#define XML_CHARDATA_H 1 + +#ifndef XML_VERSION +#include "expat.h" /* need XML_Char */ +#endif + + +typedef struct { + int count; /* # of chars, < 0 if not set */ + XML_Char data[1024]; +} CharData; + + +void CharData_Init(CharData *storage); + +void CharData_AppendString(CharData *storage, const char *s); + +void CharData_AppendXMLChars(CharData *storage, const XML_Char *s, int len); + +int CharData_CheckString(CharData *storage, const char *s); + +int CharData_CheckXMLChars(CharData *storage, const XML_Char *s); + + +#endif /* XML_CHARDATA_H */ + +#ifdef __cplusplus +} +#endif diff --git a/contrib/expat/tests/minicheck.c b/contrib/expat/tests/minicheck.c new file mode 100644 index 0000000..d2f4295 --- /dev/null +++ b/contrib/expat/tests/minicheck.c @@ -0,0 +1,182 @@ +/* Miniature re-implementation of the "check" library. + * + * This is intended to support just enough of check to run the Expat + * tests. This interface is based entirely on the portion of the + * check library being used. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <setjmp.h> +#include <assert.h> + +#include "minicheck.h" + +Suite * +suite_create(char *name) +{ + Suite *suite = (Suite *) calloc(1, sizeof(Suite)); + if (suite != NULL) { + suite->name = name; + } + return suite; +} + +TCase * +tcase_create(char *name) +{ + TCase *tc = (TCase *) calloc(1, sizeof(TCase)); + if (tc != NULL) { + tc->name = name; + } + return tc; +} + +void +suite_add_tcase(Suite *suite, TCase *tc) +{ + assert(suite != NULL); + assert(tc != NULL); + assert(tc->next_tcase == NULL); + + tc->next_tcase = suite->tests; + suite->tests = tc; +} + +void +tcase_add_checked_fixture(TCase *tc, + tcase_setup_function setup, + tcase_teardown_function teardown) +{ + assert(tc != NULL); + tc->setup = setup; + tc->teardown = teardown; +} + +void +tcase_add_test(TCase *tc, tcase_test_function test) +{ + assert(tc != NULL); + if (tc->allocated == tc->ntests) { + int nalloc = tc->allocated + 100; + size_t new_size = sizeof(tcase_test_function) * nalloc; + tcase_test_function *new_tests = realloc(tc->tests, new_size); + assert(new_tests != NULL); + if (new_tests != tc->tests) { + free(tc->tests); + tc->tests = new_tests; + } + tc->allocated = nalloc; + } + tc->tests[tc->ntests] = test; + tc->ntests++; +} + +SRunner * +srunner_create(Suite *suite) +{ + SRunner *runner = calloc(1, sizeof(SRunner)); + if (runner != NULL) { + runner->suite = suite; + } + return runner; +} + +static jmp_buf env; + +static char const *_check_current_function = NULL; +static int _check_current_lineno = -1; +static char const *_check_current_filename = NULL; + +void +_check_set_test_info(char const *function, char const *filename, int lineno) +{ + _check_current_function = function; + _check_current_lineno = lineno; + _check_current_filename = filename; +} + + +static void +add_failure(SRunner *runner, int verbosity) +{ + runner->nfailures++; + if (verbosity >= CK_VERBOSE) { + printf("%s:%d: %s\n", _check_current_filename, + _check_current_lineno, _check_current_function); + } +} + +void +srunner_run_all(SRunner *runner, int verbosity) +{ + Suite *suite; + TCase *tc; + assert(runner != NULL); + suite = runner->suite; + tc = suite->tests; + while (tc != NULL) { + int i; + for (i = 0; i < tc->ntests; ++i) { + runner->nchecks++; + + if (tc->setup != NULL) { + /* setup */ + if (setjmp(env)) { + add_failure(runner, verbosity); + continue; + } + tc->setup(); + } + /* test */ + if (setjmp(env)) { + add_failure(runner, verbosity); + continue; + } + (tc->tests[i])(); + + /* teardown */ + if (tc->teardown != NULL) { + if (setjmp(env)) { + add_failure(runner, verbosity); + continue; + } + tc->teardown(); + } + } + tc = tc->next_tcase; + } + if (verbosity) { + int passed = runner->nchecks - runner->nfailures; + double percentage = ((double) passed) / runner->nchecks; + int display = (int) (percentage * 100); + printf("%d%%: Checks: %d, Failed: %d\n", + display, runner->nchecks, runner->nfailures); + } +} + +void +_fail_unless(int condition, const char *file, int line, char *msg) +{ + /* Always print the error message so it isn't lost. In this case, + we have a failure, so there's no reason to be quiet about what + it is. + */ + if (msg != NULL) + printf("%s", msg); + longjmp(env, 1); +} + +int +srunner_ntests_failed(SRunner *runner) +{ + assert(runner != NULL); + return runner->nfailures; +} + +void +srunner_free(SRunner *runner) +{ + free(runner->suite); + free(runner); +} diff --git a/contrib/expat/tests/minicheck.h b/contrib/expat/tests/minicheck.h new file mode 100644 index 0000000..c917c02 --- /dev/null +++ b/contrib/expat/tests/minicheck.h @@ -0,0 +1,90 @@ +/* Miniature re-implementation of the "check" library. + * + * This is intended to support just enough of check to run the Expat + * tests. This interface is based entirely on the portion of the + * check library being used. + * + * This is *source* compatible, but not necessary *link* compatible. + */ + +#ifdef __cplusplus +extern "C" { +#endif + +#define CK_NOFORK 0 +#define CK_FORK 1 + +#define CK_SILENT 0 +#define CK_NORMAL 1 +#define CK_VERBOSE 2 + +/* Workaround for Microsoft's compiler and Tru64 Unix systems where the + C compiler has a working __func__, but the C++ compiler only has a + working __FUNCTION__. This could be fixed in configure.in, but it's + not worth it right now. */ +#if defined (_MSC_VER) || (defined(__osf__) && defined(__cplusplus)) +#define __func__ __FUNCTION__ +#endif + +#define START_TEST(testname) static void testname(void) { \ + _check_set_test_info(__func__, __FILE__, __LINE__); \ + { +#define END_TEST } } + +#define fail(msg) _fail_unless(0, __FILE__, __LINE__, msg) + +typedef void (*tcase_setup_function)(void); +typedef void (*tcase_teardown_function)(void); +typedef void (*tcase_test_function)(void); + +typedef struct SRunner SRunner; +typedef struct Suite Suite; +typedef struct TCase TCase; + +struct SRunner { + Suite *suite; + int nchecks; + int nfailures; +}; + +struct Suite { + char *name; + TCase *tests; +}; + +struct TCase { + char *name; + tcase_setup_function setup; + tcase_teardown_function teardown; + tcase_test_function *tests; + int ntests; + int allocated; + TCase *next_tcase; +}; + + +/* Internal helper. */ +void _check_set_test_info(char const *function, + char const *filename, int lineno); + + +/* + * Prototypes for the actual implementation. + */ + +void _fail_unless(int condition, const char *file, int line, char *msg); +Suite *suite_create(char *name); +TCase *tcase_create(char *name); +void suite_add_tcase(Suite *suite, TCase *tc); +void tcase_add_checked_fixture(TCase *, + tcase_setup_function, + tcase_teardown_function); +void tcase_add_test(TCase *tc, tcase_test_function test); +SRunner *srunner_create(Suite *suite); +void srunner_run_all(SRunner *runner, int verbosity); +int srunner_ntests_failed(SRunner *runner); +void srunner_free(SRunner *runner); + +#ifdef __cplusplus +} +#endif diff --git a/contrib/expat/tests/runtests.c b/contrib/expat/tests/runtests.c new file mode 100644 index 0000000..614d6b2 --- /dev/null +++ b/contrib/expat/tests/runtests.c @@ -0,0 +1,1515 @@ +/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. + + runtest.c : run the Expat test suite +*/ + +#ifdef HAVE_EXPAT_CONFIG_H +#include <expat_config.h> +#endif + +#include <assert.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <stdint.h> + +#include "expat.h" +#include "chardata.h" +#include "minicheck.h" + +#if defined(__amigaos__) && defined(__USE_INLINE__) +#include <proto/expat.h> +#endif + +#ifdef XML_LARGE_SIZE +#define XML_FMT_INT_MOD "ll" +#else +#define XML_FMT_INT_MOD "l" +#endif + +static XML_Parser parser; + + +static void +basic_setup(void) +{ + parser = XML_ParserCreate(NULL); + if (parser == NULL) + fail("Parser not created."); +} + +static void +basic_teardown(void) +{ + if (parser != NULL) + XML_ParserFree(parser); +} + +/* Generate a failure using the parser state to create an error message; + this should be used when the parser reports an error we weren't + expecting. +*/ +static void +_xml_failure(XML_Parser parser, const char *file, int line) +{ + char buffer[1024]; + enum XML_Error err = XML_GetErrorCode(parser); + sprintf(buffer, + " %d: %s (line %" XML_FMT_INT_MOD "u, offset %"\ + XML_FMT_INT_MOD "u)\n reported from %s, line %d\n", + err, + XML_ErrorString(err), + XML_GetCurrentLineNumber(parser), + XML_GetCurrentColumnNumber(parser), + file, line); + _fail_unless(0, file, line, buffer); +} + +#define xml_failure(parser) _xml_failure((parser), __FILE__, __LINE__) + +static void +_expect_failure(char *text, enum XML_Error errorCode, char *errorMessage, + char *file, int lineno) +{ + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_OK) + /* Hackish use of _fail_unless() macro, but let's us report + the right filename and line number. */ + _fail_unless(0, file, lineno, errorMessage); + if (XML_GetErrorCode(parser) != errorCode) + _xml_failure(parser, file, lineno); +} + +#define expect_failure(text, errorCode, errorMessage) \ + _expect_failure((text), (errorCode), (errorMessage), \ + __FILE__, __LINE__) + +/* Dummy handlers for when we need to set a handler to tickle a bug, + but it doesn't need to do anything. +*/ + +static void XMLCALL +dummy_start_doctype_handler(void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset) +{} + +static void XMLCALL +dummy_end_doctype_handler(void *userData) +{} + +static void XMLCALL +dummy_entity_decl_handler(void *userData, + const XML_Char *entityName, + int is_parameter_entity, + const XML_Char *value, + int value_length, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName) +{} + +static void XMLCALL +dummy_notation_decl_handler(void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{} + +static void XMLCALL +dummy_element_decl_handler(void *userData, + const XML_Char *name, + XML_Content *model) +{} + +static void XMLCALL +dummy_attlist_decl_handler(void *userData, + const XML_Char *elname, + const XML_Char *attname, + const XML_Char *att_type, + const XML_Char *dflt, + int isrequired) +{} + +static void XMLCALL +dummy_comment_handler(void *userData, const XML_Char *data) +{} + +static void XMLCALL +dummy_pi_handler(void *userData, const XML_Char *target, const XML_Char *data) +{} + +static void XMLCALL +dummy_start_element(void *userData, + const XML_Char *name, const XML_Char **atts) +{} + + +/* + * Character & encoding tests. + */ + +START_TEST(test_nul_byte) +{ + char text[] = "<doc>\0</doc>"; + + /* test that a NUL byte (in US-ASCII data) is an error */ + if (XML_Parse(parser, text, sizeof(text) - 1, XML_TRUE) == XML_STATUS_OK) + fail("Parser did not report error on NUL-byte."); + if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN) + xml_failure(parser); +} +END_TEST + + +START_TEST(test_u0000_char) +{ + /* test that a NUL byte (in US-ASCII data) is an error */ + expect_failure("<doc>�</doc>", + XML_ERROR_BAD_CHAR_REF, + "Parser did not report error on NUL-byte."); +} +END_TEST + +START_TEST(test_bom_utf8) +{ + /* This test is really just making sure we don't core on a UTF-8 BOM. */ + char *text = "\357\273\277<e/>"; + + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +START_TEST(test_bom_utf16_be) +{ + char text[] = "\376\377\0<\0e\0/\0>"; + + if (XML_Parse(parser, text, sizeof(text)-1, XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +START_TEST(test_bom_utf16_le) +{ + char text[] = "\377\376<\0e\0/\0>\0"; + + if (XML_Parse(parser, text, sizeof(text)-1, XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +static void XMLCALL +accumulate_characters(void *userData, const XML_Char *s, int len) +{ + CharData_AppendXMLChars((CharData *)userData, s, len); +} + +static void XMLCALL +accumulate_attribute(void *userData, const XML_Char *name, + const XML_Char **atts) +{ + CharData *storage = (CharData *)userData; + if (storage->count < 0 && atts != NULL && atts[0] != NULL) { + /* "accumulate" the value of the first attribute we see */ + CharData_AppendXMLChars(storage, atts[1], -1); + } +} + + +static void +_run_character_check(XML_Char *text, XML_Char *expected, + const char *file, int line) +{ + CharData storage; + + CharData_Init(&storage); + XML_SetUserData(parser, &storage); + XML_SetCharacterDataHandler(parser, accumulate_characters); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + _xml_failure(parser, file, line); + CharData_CheckXMLChars(&storage, expected); +} + +#define run_character_check(text, expected) \ + _run_character_check(text, expected, __FILE__, __LINE__) + +static void +_run_attribute_check(XML_Char *text, XML_Char *expected, + const char *file, int line) +{ + CharData storage; + + CharData_Init(&storage); + XML_SetUserData(parser, &storage); + XML_SetStartElementHandler(parser, accumulate_attribute); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + _xml_failure(parser, file, line); + CharData_CheckXMLChars(&storage, expected); +} + +#define run_attribute_check(text, expected) \ + _run_attribute_check(text, expected, __FILE__, __LINE__) + +/* Regression test for SF bug #491986. */ +START_TEST(test_danish_latin1) +{ + char *text = + "<?xml version='1.0' encoding='iso-8859-1'?>\n" + "<e>J\xF8rgen \xE6\xF8\xE5\xC6\xD8\xC5</e>"; + run_character_check(text, + "J\xC3\xB8rgen \xC3\xA6\xC3\xB8\xC3\xA5\xC3\x86\xC3\x98\xC3\x85"); +} +END_TEST + + +/* Regression test for SF bug #514281. */ +START_TEST(test_french_charref_hexidecimal) +{ + char *text = + "<?xml version='1.0' encoding='iso-8859-1'?>\n" + "<doc>éèàçêÈ</doc>"; + run_character_check(text, + "\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88"); +} +END_TEST + +START_TEST(test_french_charref_decimal) +{ + char *text = + "<?xml version='1.0' encoding='iso-8859-1'?>\n" + "<doc>éèàçêÈ</doc>"; + run_character_check(text, + "\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88"); +} +END_TEST + +START_TEST(test_french_latin1) +{ + char *text = + "<?xml version='1.0' encoding='iso-8859-1'?>\n" + "<doc>\xE9\xE8\xE0\xE7\xEa\xC8</doc>"; + run_character_check(text, + "\xC3\xA9\xC3\xA8\xC3\xA0\xC3\xA7\xC3\xAA\xC3\x88"); +} +END_TEST + +START_TEST(test_french_utf8) +{ + char *text = + "<?xml version='1.0' encoding='utf-8'?>\n" + "<doc>\xC3\xA9</doc>"; + run_character_check(text, "\xC3\xA9"); +} +END_TEST + +/* Regression test for SF bug #600479. + XXX There should be a test that exercises all legal XML Unicode + characters as PCDATA and attribute value content, and XML Name + characters as part of element and attribute names. +*/ +START_TEST(test_utf8_false_rejection) +{ + char *text = "<doc>\xEF\xBA\xBF</doc>"; + run_character_check(text, "\xEF\xBA\xBF"); +} +END_TEST + +/* Regression test for SF bug #477667. + This test assures that any 8-bit character followed by a 7-bit + character will not be mistakenly interpreted as a valid UTF-8 + sequence. +*/ +START_TEST(test_illegal_utf8) +{ + char text[100]; + int i; + + for (i = 128; i <= 255; ++i) { + sprintf(text, "<e>%ccd</e>", i); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_OK) { + sprintf(text, + "expected token error for '%c' (ordinal %d) in UTF-8 text", + i, i); + fail(text); + } + else if (XML_GetErrorCode(parser) != XML_ERROR_INVALID_TOKEN) + xml_failure(parser); + /* Reset the parser since we use the same parser repeatedly. */ + XML_ParserReset(parser, NULL); + } +} +END_TEST + +START_TEST(test_utf16) +{ + /* <?xml version="1.0" encoding="UTF-16"?> + <doc a='123'>some text</doc> + */ + char text[] = + "\000<\000?\000x\000m\000\154\000 \000v\000e\000r\000s\000i\000o" + "\000n\000=\000'\0001\000.\000\060\000'\000 \000e\000n\000c\000o" + "\000d\000i\000n\000g\000=\000'\000U\000T\000F\000-\0001\000\066" + "\000'\000?\000>\000\n" + "\000<\000d\000o\000c\000 \000a\000=\000'\0001\0002\0003\000'" + "\000>\000s\000o\000m\000e\000 \000t\000e\000x\000t\000<\000/" + "\000d\000o\000c\000>"; + if (XML_Parse(parser, text, sizeof(text)-1, XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +START_TEST(test_utf16_le_epilog_newline) +{ + unsigned int first_chunk_bytes = 17; + char text[] = + "\xFF\xFE" /* BOM */ + "<\000e\000/\000>\000" /* document element */ + "\r\000\n\000\r\000\n\000"; /* epilog */ + + if (first_chunk_bytes >= sizeof(text) - 1) + fail("bad value of first_chunk_bytes"); + if ( XML_Parse(parser, text, first_chunk_bytes, XML_FALSE) + == XML_STATUS_ERROR) + xml_failure(parser); + else { + enum XML_Status rc; + rc = XML_Parse(parser, text + first_chunk_bytes, + sizeof(text) - first_chunk_bytes - 1, XML_TRUE); + if (rc == XML_STATUS_ERROR) + xml_failure(parser); + } +} +END_TEST + +/* Regression test for SF bug #481609, #774028. */ +START_TEST(test_latin1_umlauts) +{ + char *text = + "<?xml version='1.0' encoding='iso-8859-1'?>\n" + "<e a='\xE4 \xF6 \xFC ä ö ü ä ö ü >'\n" + " >\xE4 \xF6 \xFC ä ö ü ä ö ü ></e>"; + char *utf8 = + "\xC3\xA4 \xC3\xB6 \xC3\xBC " + "\xC3\xA4 \xC3\xB6 \xC3\xBC " + "\xC3\xA4 \xC3\xB6 \xC3\xBC >"; + run_character_check(text, utf8); + XML_ParserReset(parser, NULL); + run_attribute_check(text, utf8); +} +END_TEST + +/* Regression test #1 for SF bug #653180. */ +START_TEST(test_line_number_after_parse) +{ + char *text = + "<tag>\n" + "\n" + "\n</tag>"; + XML_Size lineno; + + if (XML_Parse(parser, text, strlen(text), XML_FALSE) == XML_STATUS_ERROR) + xml_failure(parser); + lineno = XML_GetCurrentLineNumber(parser); + if (lineno != 4) { + char buffer[100]; + sprintf(buffer, + "expected 4 lines, saw %" XML_FMT_INT_MOD "u", lineno); + fail(buffer); + } +} +END_TEST + +/* Regression test #2 for SF bug #653180. */ +START_TEST(test_column_number_after_parse) +{ + char *text = "<tag></tag>"; + XML_Size colno; + + if (XML_Parse(parser, text, strlen(text), XML_FALSE) == XML_STATUS_ERROR) + xml_failure(parser); + colno = XML_GetCurrentColumnNumber(parser); + if (colno != 11) { + char buffer[100]; + sprintf(buffer, + "expected 11 columns, saw %" XML_FMT_INT_MOD "u", colno); + fail(buffer); + } +} +END_TEST + +static void XMLCALL +start_element_event_handler2(void *userData, const XML_Char *name, + const XML_Char **attr) +{ + CharData *storage = (CharData *) userData; + char buffer[100]; + + sprintf(buffer, + "<%s> at col:%" XML_FMT_INT_MOD "u line:%"\ + XML_FMT_INT_MOD "u\n", name, + XML_GetCurrentColumnNumber(parser), + XML_GetCurrentLineNumber(parser)); + CharData_AppendString(storage, buffer); +} + +static void XMLCALL +end_element_event_handler2(void *userData, const XML_Char *name) +{ + CharData *storage = (CharData *) userData; + char buffer[100]; + + sprintf(buffer, + "</%s> at col:%" XML_FMT_INT_MOD "u line:%"\ + XML_FMT_INT_MOD "u\n", name, + XML_GetCurrentColumnNumber(parser), + XML_GetCurrentLineNumber(parser)); + CharData_AppendString(storage, buffer); +} + +/* Regression test #3 for SF bug #653180. */ +START_TEST(test_line_and_column_numbers_inside_handlers) +{ + char *text = + "<a>\n" /* Unix end-of-line */ + " <b>\r\n" /* Windows end-of-line */ + " <c/>\r" /* Mac OS end-of-line */ + " </b>\n" + " <d>\n" + " <f/>\n" + " </d>\n" + "</a>"; + char *expected = + "<a> at col:0 line:1\n" + "<b> at col:2 line:2\n" + "<c> at col:4 line:3\n" + "</c> at col:8 line:3\n" + "</b> at col:2 line:4\n" + "<d> at col:2 line:5\n" + "<f> at col:4 line:6\n" + "</f> at col:8 line:6\n" + "</d> at col:2 line:7\n" + "</a> at col:0 line:8\n"; + CharData storage; + + CharData_Init(&storage); + XML_SetUserData(parser, &storage); + XML_SetStartElementHandler(parser, start_element_event_handler2); + XML_SetEndElementHandler(parser, end_element_event_handler2); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); + + CharData_CheckString(&storage, expected); +} +END_TEST + +/* Regression test #4 for SF bug #653180. */ +START_TEST(test_line_number_after_error) +{ + char *text = + "<a>\n" + " <b>\n" + " </a>"; /* missing </b> */ + XML_Size lineno; + if (XML_Parse(parser, text, strlen(text), XML_FALSE) != XML_STATUS_ERROR) + fail("Expected a parse error"); + + lineno = XML_GetCurrentLineNumber(parser); + if (lineno != 3) { + char buffer[100]; + sprintf(buffer, "expected 3 lines, saw %" XML_FMT_INT_MOD "u", lineno); + fail(buffer); + } +} +END_TEST + +/* Regression test #5 for SF bug #653180. */ +START_TEST(test_column_number_after_error) +{ + char *text = + "<a>\n" + " <b>\n" + " </a>"; /* missing </b> */ + XML_Size colno; + if (XML_Parse(parser, text, strlen(text), XML_FALSE) != XML_STATUS_ERROR) + fail("Expected a parse error"); + + colno = XML_GetCurrentColumnNumber(parser); + if (colno != 4) { + char buffer[100]; + sprintf(buffer, + "expected 4 columns, saw %" XML_FMT_INT_MOD "u", colno); + fail(buffer); + } +} +END_TEST + +/* Regression test for SF bug #478332. */ +START_TEST(test_really_long_lines) +{ + /* This parses an input line longer than INIT_DATA_BUF_SIZE + characters long (defined to be 1024 in xmlparse.c). We take a + really cheesy approach to building the input buffer, because + this avoids writing bugs in buffer-filling code. + */ + char *text = + "<e>" + /* 64 chars */ + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + /* until we have at least 1024 characters on the line: */ + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-+" + "</e>"; + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + + +/* + * Element event tests. + */ + +static void XMLCALL +end_element_event_handler(void *userData, const XML_Char *name) +{ + CharData *storage = (CharData *) userData; + CharData_AppendString(storage, "/"); + CharData_AppendXMLChars(storage, name, -1); +} + +START_TEST(test_end_element_events) +{ + char *text = "<a><b><c/></b><d><f/></d></a>"; + char *expected = "/c/b/f/d/a"; + CharData storage; + + CharData_Init(&storage); + XML_SetUserData(parser, &storage); + XML_SetEndElementHandler(parser, end_element_event_handler); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); + CharData_CheckString(&storage, expected); +} +END_TEST + + +/* + * Attribute tests. + */ + +/* Helpers used by the following test; this checks any "attr" and "refs" + attributes to make sure whitespace has been normalized. + + Return true if whitespace has been normalized in a string, using + the rules for attribute value normalization. The 'is_cdata' flag + is needed since CDATA attributes don't need to have multiple + whitespace characters collapsed to a single space, while other + attribute data types do. (Section 3.3.3 of the recommendation.) +*/ +static int +is_whitespace_normalized(const XML_Char *s, int is_cdata) +{ + int blanks = 0; + int at_start = 1; + while (*s) { + if (*s == ' ') + ++blanks; + else if (*s == '\t' || *s == '\n' || *s == '\r') + return 0; + else { + if (at_start) { + at_start = 0; + if (blanks && !is_cdata) + /* illegal leading blanks */ + return 0; + } + else if (blanks > 1 && !is_cdata) + return 0; + blanks = 0; + } + ++s; + } + if (blanks && !is_cdata) + return 0; + return 1; +} + +/* Check the attribute whitespace checker: */ +static void +testhelper_is_whitespace_normalized(void) +{ + assert(is_whitespace_normalized("abc", 0)); + assert(is_whitespace_normalized("abc", 1)); + assert(is_whitespace_normalized("abc def ghi", 0)); + assert(is_whitespace_normalized("abc def ghi", 1)); + assert(!is_whitespace_normalized(" abc def ghi", 0)); + assert(is_whitespace_normalized(" abc def ghi", 1)); + assert(!is_whitespace_normalized("abc def ghi", 0)); + assert(is_whitespace_normalized("abc def ghi", 1)); + assert(!is_whitespace_normalized("abc def ghi ", 0)); + assert(is_whitespace_normalized("abc def ghi ", 1)); + assert(!is_whitespace_normalized(" ", 0)); + assert(is_whitespace_normalized(" ", 1)); + assert(!is_whitespace_normalized("\t", 0)); + assert(!is_whitespace_normalized("\t", 1)); + assert(!is_whitespace_normalized("\n", 0)); + assert(!is_whitespace_normalized("\n", 1)); + assert(!is_whitespace_normalized("\r", 0)); + assert(!is_whitespace_normalized("\r", 1)); + assert(!is_whitespace_normalized("abc\t def", 1)); +} + +static void XMLCALL +check_attr_contains_normalized_whitespace(void *userData, + const XML_Char *name, + const XML_Char **atts) +{ + int i; + for (i = 0; atts[i] != NULL; i += 2) { + const XML_Char *attrname = atts[i]; + const XML_Char *value = atts[i + 1]; + if (strcmp("attr", attrname) == 0 + || strcmp("ents", attrname) == 0 + || strcmp("refs", attrname) == 0) { + if (!is_whitespace_normalized(value, 0)) { + char buffer[256]; + sprintf(buffer, "attribute value not normalized: %s='%s'", + attrname, value); + fail(buffer); + } + } + } +} + +START_TEST(test_attr_whitespace_normalization) +{ + char *text = + "<!DOCTYPE doc [\n" + " <!ATTLIST doc\n" + " attr NMTOKENS #REQUIRED\n" + " ents ENTITIES #REQUIRED\n" + " refs IDREFS #REQUIRED>\n" + "]>\n" + "<doc attr=' a b c\t\td\te\t' refs=' id-1 \t id-2\t\t' \n" + " ents=' ent-1 \t\r\n" + " ent-2 ' >\n" + " <e id='id-1'/>\n" + " <e id='id-2'/>\n" + "</doc>"; + + XML_SetStartElementHandler(parser, + check_attr_contains_normalized_whitespace); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + + +/* + * XML declaration tests. + */ + +START_TEST(test_xmldecl_misplaced) +{ + expect_failure("\n" + "<?xml version='1.0'?>\n" + "<a/>", + XML_ERROR_MISPLACED_XML_PI, + "failed to report misplaced XML declaration"); +} +END_TEST + +/* Regression test for SF bug #584832. */ +static int XMLCALL +UnknownEncodingHandler(void *data,const XML_Char *encoding,XML_Encoding *info) +{ + if (strcmp(encoding,"unsupported-encoding") == 0) { + int i; + for (i = 0; i < 256; ++i) + info->map[i] = i; + info->data = NULL; + info->convert = NULL; + info->release = NULL; + return XML_STATUS_OK; + } + return XML_STATUS_ERROR; +} + +START_TEST(test_unknown_encoding_internal_entity) +{ + char *text = + "<?xml version='1.0' encoding='unsupported-encoding'?>\n" + "<!DOCTYPE test [<!ENTITY foo 'bar'>]>\n" + "<test a='&foo;'/>"; + + XML_SetUnknownEncodingHandler(parser, UnknownEncodingHandler, NULL); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +/* Regression test for SF bug #620106. */ +static int XMLCALL +external_entity_loader_set_encoding(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + /* This text says it's an unsupported encoding, but it's really + UTF-8, which we tell Expat using XML_SetEncoding(). + */ + char *text = + "<?xml encoding='iso-8859-3'?>" + "\xC3\xA9"; + XML_Parser extparser; + + extparser = XML_ExternalEntityParserCreate(parser, context, NULL); + if (extparser == NULL) + fail("Could not create external entity parser."); + if (!XML_SetEncoding(extparser, "utf-8")) + fail("XML_SetEncoding() ignored for external entity"); + if ( XML_Parse(extparser, text, strlen(text), XML_TRUE) + == XML_STATUS_ERROR) { + xml_failure(parser); + return 0; + } + return 1; +} + +START_TEST(test_ext_entity_set_encoding) +{ + char *text = + "<!DOCTYPE doc [\n" + " <!ENTITY en SYSTEM 'http://xml.libexpat.org/dummy.ent'>\n" + "]>\n" + "<doc>&en;</doc>"; + + XML_SetExternalEntityRefHandler(parser, + external_entity_loader_set_encoding); + run_character_check(text, "\xC3\xA9"); +} +END_TEST + +/* Test that no error is reported for unknown entities if we don't + read an external subset. This was fixed in Expat 1.95.5. +*/ +START_TEST(test_wfc_undeclared_entity_unread_external_subset) { + char *text = + "<!DOCTYPE doc SYSTEM 'foo'>\n" + "<doc>&entity;</doc>"; + + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +/* Test that an error is reported for unknown entities if we don't + have an external subset. +*/ +START_TEST(test_wfc_undeclared_entity_no_external_subset) { + expect_failure("<doc>&entity;</doc>", + XML_ERROR_UNDEFINED_ENTITY, + "Parser did not report undefined entity w/out a DTD."); +} +END_TEST + +/* Test that an error is reported for unknown entities if we don't + read an external subset, but have been declared standalone. +*/ +START_TEST(test_wfc_undeclared_entity_standalone) { + char *text = + "<?xml version='1.0' encoding='us-ascii' standalone='yes'?>\n" + "<!DOCTYPE doc SYSTEM 'foo'>\n" + "<doc>&entity;</doc>"; + + expect_failure(text, + XML_ERROR_UNDEFINED_ENTITY, + "Parser did not report undefined entity (standalone)."); +} +END_TEST + +static int XMLCALL +external_entity_loader(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + char *text = (char *)XML_GetUserData(parser); + XML_Parser extparser; + + extparser = XML_ExternalEntityParserCreate(parser, context, NULL); + if (extparser == NULL) + fail("Could not create external entity parser."); + if ( XML_Parse(extparser, text, strlen(text), XML_TRUE) + == XML_STATUS_ERROR) { + xml_failure(parser); + return XML_STATUS_ERROR; + } + return XML_STATUS_OK; +} + +/* Test that an error is reported for unknown entities if we have read + an external subset, and standalone is true. +*/ +START_TEST(test_wfc_undeclared_entity_with_external_subset_standalone) { + char *text = + "<?xml version='1.0' encoding='us-ascii' standalone='yes'?>\n" + "<!DOCTYPE doc SYSTEM 'foo'>\n" + "<doc>&entity;</doc>"; + char *foo_text = + "<!ELEMENT doc (#PCDATA)*>"; + + XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS); + XML_SetUserData(parser, foo_text); + XML_SetExternalEntityRefHandler(parser, external_entity_loader); + expect_failure(text, + XML_ERROR_UNDEFINED_ENTITY, + "Parser did not report undefined entity (external DTD)."); +} +END_TEST + +/* Test that no error is reported for unknown entities if we have read + an external subset, and standalone is false. +*/ +START_TEST(test_wfc_undeclared_entity_with_external_subset) { + char *text = + "<?xml version='1.0' encoding='us-ascii'?>\n" + "<!DOCTYPE doc SYSTEM 'foo'>\n" + "<doc>&entity;</doc>"; + char *foo_text = + "<!ELEMENT doc (#PCDATA)*>"; + + XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS); + XML_SetUserData(parser, foo_text); + XML_SetExternalEntityRefHandler(parser, external_entity_loader); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +START_TEST(test_wfc_no_recursive_entity_refs) +{ + char *text = + "<!DOCTYPE doc [\n" + " <!ENTITY entity '&entity;'>\n" + "]>\n" + "<doc>&entity;</doc>"; + + expect_failure(text, + XML_ERROR_RECURSIVE_ENTITY_REF, + "Parser did not report recursive entity reference."); +} +END_TEST + +/* Regression test for SF bug #483514. */ +START_TEST(test_dtd_default_handling) +{ + char *text = + "<!DOCTYPE doc [\n" + "<!ENTITY e SYSTEM 'http://xml.libexpat.org/e'>\n" + "<!NOTATION n SYSTEM 'http://xml.libexpat.org/n'>\n" + "<!ELEMENT doc EMPTY>\n" + "<!ATTLIST doc a CDATA #IMPLIED>\n" + "<?pi in dtd?>\n" + "<!--comment in dtd-->\n" + "]><doc/>"; + + XML_SetDefaultHandler(parser, accumulate_characters); + XML_SetDoctypeDeclHandler(parser, + dummy_start_doctype_handler, + dummy_end_doctype_handler); + XML_SetEntityDeclHandler(parser, dummy_entity_decl_handler); + XML_SetNotationDeclHandler(parser, dummy_notation_decl_handler); + XML_SetElementDeclHandler(parser, dummy_element_decl_handler); + XML_SetAttlistDeclHandler(parser, dummy_attlist_decl_handler); + XML_SetProcessingInstructionHandler(parser, dummy_pi_handler); + XML_SetCommentHandler(parser, dummy_comment_handler); + run_character_check(text, "\n\n\n\n\n\n\n<doc/>"); +} +END_TEST + +/* See related SF bug #673791. + When namespace processing is enabled, setting the namespace URI for + a prefix is not allowed; this test ensures that it *is* allowed + when namespace processing is not enabled. + (See Namespaces in XML, section 2.) +*/ +START_TEST(test_empty_ns_without_namespaces) +{ + char *text = + "<doc xmlns:prefix='http://www.example.com/'>\n" + " <e xmlns:prefix=''/>\n" + "</doc>"; + + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +/* Regression test for SF bug #824420. + Checks that an xmlns:prefix attribute set in an attribute's default + value isn't misinterpreted. +*/ +START_TEST(test_ns_in_attribute_default_without_namespaces) +{ + char *text = + "<!DOCTYPE e:element [\n" + " <!ATTLIST e:element\n" + " xmlns:e CDATA 'http://example.com/'>\n" + " ]>\n" + "<e:element/>"; + + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +static char *long_character_data_text = + "<?xml version='1.0' encoding='iso-8859-1'?><s>" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "012345678901234567890123456789012345678901234567890123456789" + "</s>"; + +static XML_Bool resumable = XML_FALSE; + +static void +clearing_aborting_character_handler(void *userData, + const XML_Char *s, int len) +{ + XML_StopParser(parser, resumable); + XML_SetCharacterDataHandler(parser, NULL); +} + +/* Regression test for SF bug #1515266: missing check of stopped + parser in doContext() 'for' loop. */ +START_TEST(test_stop_parser_between_char_data_calls) +{ + /* The sample data must be big enough that there are two calls to + the character data handler from within the inner "for" loop of + the XML_TOK_DATA_CHARS case in doContent(), and the character + handler must stop the parser and clear the character data + handler. + */ + char *text = long_character_data_text; + + XML_SetCharacterDataHandler(parser, clearing_aborting_character_handler); + resumable = XML_FALSE; + if (XML_Parse(parser, text, strlen(text), XML_TRUE) != XML_STATUS_ERROR) + xml_failure(parser); + if (XML_GetErrorCode(parser) != XML_ERROR_ABORTED) + xml_failure(parser); +} +END_TEST + +/* Regression test for SF bug #1515266: missing check of stopped + parser in doContext() 'for' loop. */ +START_TEST(test_suspend_parser_between_char_data_calls) +{ + /* The sample data must be big enough that there are two calls to + the character data handler from within the inner "for" loop of + the XML_TOK_DATA_CHARS case in doContent(), and the character + handler must stop the parser and clear the character data + handler. + */ + char *text = long_character_data_text; + + XML_SetCharacterDataHandler(parser, clearing_aborting_character_handler); + resumable = XML_TRUE; + if (XML_Parse(parser, text, strlen(text), XML_TRUE) != XML_STATUS_SUSPENDED) + xml_failure(parser); + if (XML_GetErrorCode(parser) != XML_ERROR_NONE) + xml_failure(parser); +} +END_TEST + + +/* + * Namespaces tests. + */ + +static void +namespace_setup(void) +{ + parser = XML_ParserCreateNS(NULL, ' '); + if (parser == NULL) + fail("Parser not created."); +} + +static void +namespace_teardown(void) +{ + basic_teardown(); +} + +/* Check that an element name and attribute name match the expected values. + The expected values are passed as an array reference of string pointers + provided as the userData argument; the first is the expected + element name, and the second is the expected attribute name. +*/ +static void XMLCALL +triplet_start_checker(void *userData, const XML_Char *name, + const XML_Char **atts) +{ + char **elemstr = (char **)userData; + char buffer[1024]; + if (strcmp(elemstr[0], name) != 0) { + sprintf(buffer, "unexpected start string: '%s'", name); + fail(buffer); + } + if (strcmp(elemstr[1], atts[0]) != 0) { + sprintf(buffer, "unexpected attribute string: '%s'", atts[0]); + fail(buffer); + } +} + +/* Check that the element name passed to the end-element handler matches + the expected value. The expected value is passed as the first element + in an array of strings passed as the userData argument. +*/ +static void XMLCALL +triplet_end_checker(void *userData, const XML_Char *name) +{ + char **elemstr = (char **)userData; + if (strcmp(elemstr[0], name) != 0) { + char buffer[1024]; + sprintf(buffer, "unexpected end string: '%s'", name); + fail(buffer); + } +} + +START_TEST(test_return_ns_triplet) +{ + char *text = + "<foo:e xmlns:foo='http://expat.sf.net/' bar:a='12'\n" + " xmlns:bar='http://expat.sf.net/'></foo:e>"; + char *elemstr[] = { + "http://expat.sf.net/ e foo", + "http://expat.sf.net/ a bar" + }; + XML_SetReturnNSTriplet(parser, XML_TRUE); + XML_SetUserData(parser, elemstr); + XML_SetElementHandler(parser, triplet_start_checker, triplet_end_checker); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +static void XMLCALL +overwrite_start_checker(void *userData, const XML_Char *name, + const XML_Char **atts) +{ + CharData *storage = (CharData *) userData; + CharData_AppendString(storage, "start "); + CharData_AppendXMLChars(storage, name, -1); + while (*atts != NULL) { + CharData_AppendString(storage, "\nattribute "); + CharData_AppendXMLChars(storage, *atts, -1); + atts += 2; + } + CharData_AppendString(storage, "\n"); +} + +static void XMLCALL +overwrite_end_checker(void *userData, const XML_Char *name) +{ + CharData *storage = (CharData *) userData; + CharData_AppendString(storage, "end "); + CharData_AppendXMLChars(storage, name, -1); + CharData_AppendString(storage, "\n"); +} + +static void +run_ns_tagname_overwrite_test(char *text, char *result) +{ + CharData storage; + CharData_Init(&storage); + XML_SetUserData(parser, &storage); + XML_SetElementHandler(parser, + overwrite_start_checker, overwrite_end_checker); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); + CharData_CheckString(&storage, result); +} + +/* Regression test for SF bug #566334. */ +START_TEST(test_ns_tagname_overwrite) +{ + char *text = + "<n:e xmlns:n='http://xml.libexpat.org/'>\n" + " <n:f n:attr='foo'/>\n" + " <n:g n:attr2='bar'/>\n" + "</n:e>"; + char *result = + "start http://xml.libexpat.org/ e\n" + "start http://xml.libexpat.org/ f\n" + "attribute http://xml.libexpat.org/ attr\n" + "end http://xml.libexpat.org/ f\n" + "start http://xml.libexpat.org/ g\n" + "attribute http://xml.libexpat.org/ attr2\n" + "end http://xml.libexpat.org/ g\n" + "end http://xml.libexpat.org/ e\n"; + run_ns_tagname_overwrite_test(text, result); +} +END_TEST + +/* Regression test for SF bug #566334. */ +START_TEST(test_ns_tagname_overwrite_triplet) +{ + char *text = + "<n:e xmlns:n='http://xml.libexpat.org/'>\n" + " <n:f n:attr='foo'/>\n" + " <n:g n:attr2='bar'/>\n" + "</n:e>"; + char *result = + "start http://xml.libexpat.org/ e n\n" + "start http://xml.libexpat.org/ f n\n" + "attribute http://xml.libexpat.org/ attr n\n" + "end http://xml.libexpat.org/ f n\n" + "start http://xml.libexpat.org/ g n\n" + "attribute http://xml.libexpat.org/ attr2 n\n" + "end http://xml.libexpat.org/ g n\n" + "end http://xml.libexpat.org/ e n\n"; + XML_SetReturnNSTriplet(parser, XML_TRUE); + run_ns_tagname_overwrite_test(text, result); +} +END_TEST + + +/* Regression test for SF bug #620343. */ +static void XMLCALL +start_element_fail(void *userData, + const XML_Char *name, const XML_Char **atts) +{ + /* We should never get here. */ + fail("should never reach start_element_fail()"); +} + +static void XMLCALL +start_ns_clearing_start_element(void *userData, + const XML_Char *prefix, + const XML_Char *uri) +{ + XML_SetStartElementHandler((XML_Parser) userData, NULL); +} + +START_TEST(test_start_ns_clears_start_element) +{ + /* This needs to use separate start/end tags; using the empty tag + syntax doesn't cause the problematic path through Expat to be + taken. + */ + char *text = "<e xmlns='http://xml.libexpat.org/'></e>"; + + XML_SetStartElementHandler(parser, start_element_fail); + XML_SetStartNamespaceDeclHandler(parser, start_ns_clearing_start_element); + XML_UseParserAsHandlerArg(parser); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +/* Regression test for SF bug #616863. */ +static int XMLCALL +external_entity_handler(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + intptr_t callno = 1 + (intptr_t)XML_GetUserData(parser); + char *text; + XML_Parser p2; + + if (callno == 1) + text = ("<!ELEMENT doc (e+)>\n" + "<!ATTLIST doc xmlns CDATA #IMPLIED>\n" + "<!ELEMENT e EMPTY>\n"); + else + text = ("<?xml version='1.0' encoding='us-ascii'?>" + "<e/>"); + + XML_SetUserData(parser, (void *) callno); + p2 = XML_ExternalEntityParserCreate(parser, context, NULL); + if (XML_Parse(p2, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) { + xml_failure(p2); + return 0; + } + XML_ParserFree(p2); + return 1; +} + +START_TEST(test_default_ns_from_ext_subset_and_ext_ge) +{ + char *text = + "<?xml version='1.0'?>\n" + "<!DOCTYPE doc SYSTEM 'http://xml.libexpat.org/doc.dtd' [\n" + " <!ENTITY en SYSTEM 'http://xml.libexpat.org/entity.ent'>\n" + "]>\n" + "<doc xmlns='http://xml.libexpat.org/ns1'>\n" + "&en;\n" + "</doc>"; + + XML_SetParamEntityParsing(parser, XML_PARAM_ENTITY_PARSING_ALWAYS); + XML_SetExternalEntityRefHandler(parser, external_entity_handler); + /* We actually need to set this handler to tickle this bug. */ + XML_SetStartElementHandler(parser, dummy_start_element); + XML_SetUserData(parser, NULL); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +/* Regression test #1 for SF bug #673791. */ +START_TEST(test_ns_prefix_with_empty_uri_1) +{ + char *text = + "<doc xmlns:prefix='http://xml.libexpat.org/'>\n" + " <e xmlns:prefix=''/>\n" + "</doc>"; + + expect_failure(text, + XML_ERROR_UNDECLARING_PREFIX, + "Did not report re-setting namespace" + " URI with prefix to ''."); +} +END_TEST + +/* Regression test #2 for SF bug #673791. */ +START_TEST(test_ns_prefix_with_empty_uri_2) +{ + char *text = + "<?xml version='1.0'?>\n" + "<docelem xmlns:pre=''/>"; + + expect_failure(text, + XML_ERROR_UNDECLARING_PREFIX, + "Did not report setting namespace URI with prefix to ''."); +} +END_TEST + +/* Regression test #3 for SF bug #673791. */ +START_TEST(test_ns_prefix_with_empty_uri_3) +{ + char *text = + "<!DOCTYPE doc [\n" + " <!ELEMENT doc EMPTY>\n" + " <!ATTLIST doc\n" + " xmlns:prefix CDATA ''>\n" + "]>\n" + "<doc/>"; + + expect_failure(text, + XML_ERROR_UNDECLARING_PREFIX, + "Didn't report attr default setting NS w/ prefix to ''."); +} +END_TEST + +/* Regression test #4 for SF bug #673791. */ +START_TEST(test_ns_prefix_with_empty_uri_4) +{ + char *text = + "<!DOCTYPE doc [\n" + " <!ELEMENT prefix:doc EMPTY>\n" + " <!ATTLIST prefix:doc\n" + " xmlns:prefix CDATA 'http://xml.libexpat.org/'>\n" + "]>\n" + "<prefix:doc/>"; + /* Packaged info expected by the end element handler; + the weird structuring lets us re-use the triplet_end_checker() + function also used for another test. */ + char *elemstr[] = { + "http://xml.libexpat.org/ doc prefix" + }; + XML_SetReturnNSTriplet(parser, XML_TRUE); + XML_SetUserData(parser, elemstr); + XML_SetEndElementHandler(parser, triplet_end_checker); + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +START_TEST(test_ns_default_with_empty_uri) +{ + char *text = + "<doc xmlns='http://xml.libexpat.org/'>\n" + " <e xmlns=''/>\n" + "</doc>"; + if (XML_Parse(parser, text, strlen(text), XML_TRUE) == XML_STATUS_ERROR) + xml_failure(parser); +} +END_TEST + +/* Regression test for SF bug #692964: two prefixes for one namespace. */ +START_TEST(test_ns_duplicate_attrs_diff_prefixes) +{ + char *text = + "<doc xmlns:a='http://xml.libexpat.org/a'\n" + " xmlns:b='http://xml.libexpat.org/a'\n" + " a:a='v' b:a='v' />"; + expect_failure(text, + XML_ERROR_DUPLICATE_ATTRIBUTE, + "did not report multiple attributes with same URI+name"); +} +END_TEST + +/* Regression test for SF bug #695401: unbound prefix. */ +START_TEST(test_ns_unbound_prefix_on_attribute) +{ + char *text = "<doc a:attr=''/>"; + expect_failure(text, + XML_ERROR_UNBOUND_PREFIX, + "did not report unbound prefix on attribute"); +} +END_TEST + +/* Regression test for SF bug #695401: unbound prefix. */ +START_TEST(test_ns_unbound_prefix_on_element) +{ + char *text = "<a:doc/>"; + expect_failure(text, + XML_ERROR_UNBOUND_PREFIX, + "did not report unbound prefix on element"); +} +END_TEST + +static Suite * +make_suite(void) +{ + Suite *s = suite_create("basic"); + TCase *tc_basic = tcase_create("basic tests"); + TCase *tc_namespace = tcase_create("XML namespaces"); + + suite_add_tcase(s, tc_basic); + tcase_add_checked_fixture(tc_basic, basic_setup, basic_teardown); + tcase_add_test(tc_basic, test_nul_byte); + tcase_add_test(tc_basic, test_u0000_char); + tcase_add_test(tc_basic, test_bom_utf8); + tcase_add_test(tc_basic, test_bom_utf16_be); + tcase_add_test(tc_basic, test_bom_utf16_le); + tcase_add_test(tc_basic, test_illegal_utf8); + tcase_add_test(tc_basic, test_utf16); + tcase_add_test(tc_basic, test_utf16_le_epilog_newline); + tcase_add_test(tc_basic, test_latin1_umlauts); + /* Regression test for SF bug #491986. */ + tcase_add_test(tc_basic, test_danish_latin1); + /* Regression test for SF bug #514281. */ + tcase_add_test(tc_basic, test_french_charref_hexidecimal); + tcase_add_test(tc_basic, test_french_charref_decimal); + tcase_add_test(tc_basic, test_french_latin1); + tcase_add_test(tc_basic, test_french_utf8); + tcase_add_test(tc_basic, test_utf8_false_rejection); + tcase_add_test(tc_basic, test_line_number_after_parse); + tcase_add_test(tc_basic, test_column_number_after_parse); + tcase_add_test(tc_basic, test_line_and_column_numbers_inside_handlers); + tcase_add_test(tc_basic, test_line_number_after_error); + tcase_add_test(tc_basic, test_column_number_after_error); + tcase_add_test(tc_basic, test_really_long_lines); + tcase_add_test(tc_basic, test_end_element_events); + tcase_add_test(tc_basic, test_attr_whitespace_normalization); + tcase_add_test(tc_basic, test_xmldecl_misplaced); + tcase_add_test(tc_basic, test_unknown_encoding_internal_entity); + tcase_add_test(tc_basic, + test_wfc_undeclared_entity_unread_external_subset); + tcase_add_test(tc_basic, test_wfc_undeclared_entity_no_external_subset); + tcase_add_test(tc_basic, test_wfc_undeclared_entity_standalone); + tcase_add_test(tc_basic, test_wfc_undeclared_entity_with_external_subset); + tcase_add_test(tc_basic, + test_wfc_undeclared_entity_with_external_subset_standalone); + tcase_add_test(tc_basic, test_wfc_no_recursive_entity_refs); + tcase_add_test(tc_basic, test_ext_entity_set_encoding); + tcase_add_test(tc_basic, test_dtd_default_handling); + tcase_add_test(tc_basic, test_empty_ns_without_namespaces); + tcase_add_test(tc_basic, test_ns_in_attribute_default_without_namespaces); + tcase_add_test(tc_basic, test_stop_parser_between_char_data_calls); + tcase_add_test(tc_basic, test_suspend_parser_between_char_data_calls); + + suite_add_tcase(s, tc_namespace); + tcase_add_checked_fixture(tc_namespace, + namespace_setup, namespace_teardown); + tcase_add_test(tc_namespace, test_return_ns_triplet); + tcase_add_test(tc_namespace, test_ns_tagname_overwrite); + tcase_add_test(tc_namespace, test_ns_tagname_overwrite_triplet); + tcase_add_test(tc_namespace, test_start_ns_clears_start_element); + tcase_add_test(tc_namespace, test_default_ns_from_ext_subset_and_ext_ge); + tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_1); + tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_2); + tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_3); + tcase_add_test(tc_namespace, test_ns_prefix_with_empty_uri_4); + tcase_add_test(tc_namespace, test_ns_default_with_empty_uri); + tcase_add_test(tc_namespace, test_ns_duplicate_attrs_diff_prefixes); + tcase_add_test(tc_namespace, test_ns_unbound_prefix_on_attribute); + tcase_add_test(tc_namespace, test_ns_unbound_prefix_on_element); + + return s; +} + + +int +main(int argc, char *argv[]) +{ + int i, nf; + int verbosity = CK_NORMAL; + Suite *s = make_suite(); + SRunner *sr = srunner_create(s); + + /* run the tests for internal helper functions */ + testhelper_is_whitespace_normalized(); + + for (i = 1; i < argc; ++i) { + char *opt = argv[i]; + if (strcmp(opt, "-v") == 0 || strcmp(opt, "--verbose") == 0) + verbosity = CK_VERBOSE; + else if (strcmp(opt, "-q") == 0 || strcmp(opt, "--quiet") == 0) + verbosity = CK_SILENT; + else { + fprintf(stderr, "runtests: unknown option '%s'\n", opt); + return 2; + } + } + if (verbosity != CK_SILENT) + printf("Expat version: %s\n", XML_ExpatVersion()); + srunner_run_all(sr, verbosity); + nf = srunner_ntests_failed(sr); + srunner_free(sr); + + return (nf == 0) ? EXIT_SUCCESS : EXIT_FAILURE; +} diff --git a/contrib/expat/tests/runtestspp.cpp b/contrib/expat/tests/runtestspp.cpp new file mode 100644 index 0000000..c35dc58 --- /dev/null +++ b/contrib/expat/tests/runtestspp.cpp @@ -0,0 +1,6 @@ +// C++ compilation harness for the test suite. +// +// This is used to ensure the Expat headers can be included from C++ +// and have everything work as expected. +// +#include "runtests.c" diff --git a/contrib/expat/tests/xmltest.sh b/contrib/expat/tests/xmltest.sh new file mode 100755 index 0000000..793a5cc --- /dev/null +++ b/contrib/expat/tests/xmltest.sh @@ -0,0 +1,142 @@ +#! /bin/sh + +# EXPAT TEST SCRIPT FOR W3C XML TEST SUITE + +# This script can be used to exercise Expat against the +# w3c.org xml test suite, available from +# http://www.w3.org/XML/Test/xmlts20020606.zip. + +# To run this script, first set XMLWF below so that xmlwf can be +# found, then set the output directory with OUTPUT. + +# The script lists all test cases where Expat shows a discrepancy +# from the expected result. Test cases where only the canonical +# output differs are prefixed with "Output differs:", and a diff file +# is generated in the appropriate subdirectory under $OUTPUT. + +# If there are output files provided, the script will use +# output from xmlwf and compare the desired output against it. +# However, one has to take into account that the canonical output +# produced by xmlwf conforms to an older definition of canonical XML +# and does not generate notation declarations. + +MYDIR="`dirname \"$0\"`" +cd "$MYDIR" +MYDIR="`pwd`" +XMLWF="`dirname \"$MYDIR\"`/xmlwf/xmlwf" +# XMLWF=/usr/local/bin/xmlwf +TS="$MYDIR/XML-Test-Suite" +# OUTPUT must terminate with the directory separator. +OUTPUT="$TS/out/" +# OUTPUT=/home/tmp/xml-testsuite-out/ + + +# RunXmlwfNotWF file reldir +# reldir includes trailing slash +RunXmlwfNotWF() { + file="$1" + reldir="$2" + $XMLWF -p "$file" > outfile || return $? + read outdata < outfile + if test "$outdata" = "" ; then + echo "Expected not well-formed: $reldir$file" + return 1 + else + return 0 + fi +} + +# RunXmlwfWF file reldir +# reldir includes trailing slash +RunXmlwfWF() { + file="$1" + reldir="$2" + $XMLWF -p -d "$OUTPUT$reldir" "$file" > outfile || return $? + read outdata < outfile + if test "$outdata" = "" ; then + if [ -f "out/$file" ] ; then + diff -u "$OUTPUT$reldir$file" "out/$file" > outfile + if [ -s outfile ] ; then + cp outfile "$OUTPUT$reldir$file.diff" + echo "Output differs: $reldir$file" + return 1 + fi + fi + return 0 + else + echo "In $reldir: $outdata" + return 1 + fi +} + +SUCCESS=0 +ERROR=0 + +UpdateStatus() { + if [ "$1" -eq 0 ] ; then + SUCCESS=`expr $SUCCESS + 1` + else + ERROR=`expr $ERROR + 1` + fi +} + +########################## +# well-formed test cases # +########################## + +cd "$TS/xmlconf" +for xmldir in ibm/valid/P* \ + ibm/invalid/P* \ + xmltest/valid/ext-sa \ + xmltest/valid/not-sa \ + xmltest/invalid \ + xmltest/invalid/not-sa \ + xmltest/valid/sa \ + sun/valid \ + sun/invalid ; do + cd "$TS/xmlconf/$xmldir" + mkdir -p "$OUTPUT$xmldir" + for xmlfile in *.xml ; do + RunXmlwfWF "$xmlfile" "$xmldir/" + UpdateStatus $? + done + rm outfile +done + +cd "$TS/xmlconf/oasis" +mkdir -p "$OUTPUT"oasis +for xmlfile in *pass*.xml ; do + RunXmlwfWF "$xmlfile" "oasis/" + UpdateStatus $? +done +rm outfile + +############################## +# not well-formed test cases # +############################## + +cd "$TS/xmlconf" +for xmldir in ibm/not-wf/P* \ + ibm/not-wf/p28a \ + ibm/not-wf/misc \ + xmltest/not-wf/ext-sa \ + xmltest/not-wf/not-sa \ + xmltest/not-wf/sa \ + sun/not-wf ; do + cd "$TS/xmlconf/$xmldir" + for xmlfile in *.xml ; do + RunXmlwfNotWF "$xmlfile" "$xmldir/" + UpdateStatus $? + done + rm outfile +done + +cd "$TS/xmlconf/oasis" +for xmlfile in *fail*.xml ; do + RunXmlwfNotWF "$xmlfile" "oasis/" + UpdateStatus $? +done +rm outfile + +echo "Passed: $SUCCESS" +echo "Failed: $ERROR" diff --git a/contrib/expat/xmlwf/codepage.c b/contrib/expat/xmlwf/codepage.c new file mode 100644 index 0000000..57e48ff --- /dev/null +++ b/contrib/expat/xmlwf/codepage.c @@ -0,0 +1,68 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include "codepage.h" + +#if (defined(WIN32) || (defined(__WATCOMC__) && defined(__NT__))) +#define STRICT 1 +#define WIN32_LEAN_AND_MEAN 1 + +#include <windows.h> + +int +codepageMap(int cp, int *map) +{ + int i; + CPINFO info; + if (!GetCPInfo(cp, &info) || info.MaxCharSize > 2) + return 0; + for (i = 0; i < 256; i++) + map[i] = -1; + if (info.MaxCharSize > 1) { + for (i = 0; i < MAX_LEADBYTES; i+=2) { + int j, lim; + if (info.LeadByte[i] == 0 && info.LeadByte[i + 1] == 0) + break; + lim = info.LeadByte[i + 1]; + for (j = info.LeadByte[i]; j <= lim; j++) + map[j] = -2; + } + } + for (i = 0; i < 256; i++) { + if (map[i] == -1) { + char c = (char)i; + unsigned short n; + if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS, + &c, 1, &n, 1) == 1) + map[i] = n; + } + } + return 1; +} + +int +codepageConvert(int cp, const char *p) +{ + unsigned short c; + if (MultiByteToWideChar(cp, MB_PRECOMPOSED|MB_ERR_INVALID_CHARS, + p, 2, &c, 1) == 1) + return c; + return -1; +} + +#else /* not WIN32 */ + +int +codepageMap(int cp, int *map) +{ + return 0; +} + +int +codepageConvert(int cp, const char *p) +{ + return -1; +} + +#endif /* not WIN32 */ diff --git a/contrib/expat/xmlwf/codepage.h b/contrib/expat/xmlwf/codepage.h new file mode 100644 index 0000000..6a4df68 --- /dev/null +++ b/contrib/expat/xmlwf/codepage.h @@ -0,0 +1,6 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +int codepageMap(int cp, int *map); +int codepageConvert(int cp, const char *p); diff --git a/contrib/expat/xmlwf/ct.c b/contrib/expat/xmlwf/ct.c new file mode 100644 index 0000000..95903a3 --- /dev/null +++ b/contrib/expat/xmlwf/ct.c @@ -0,0 +1,147 @@ +#define CHARSET_MAX 41 + +static const char * +getTok(const char **pp) +{ + enum { inAtom, inString, init, inComment }; + int state = init; + const char *tokStart = 0; + for (;;) { + switch (**pp) { + case '\0': + return 0; + case ' ': + case '\r': + case '\t': + case '\n': + if (state == inAtom) + return tokStart; + break; + case '(': + if (state == inAtom) + return tokStart; + if (state != inString) + state++; + break; + case ')': + if (state > init) + --state; + else if (state != inString) + return 0; + break; + case ';': + case '/': + case '=': + if (state == inAtom) + return tokStart; + if (state == init) + return (*pp)++; + break; + case '\\': + ++*pp; + if (**pp == '\0') + return 0; + break; + case '"': + switch (state) { + case inString: + ++*pp; + return tokStart; + case inAtom: + return tokStart; + case init: + tokStart = *pp; + state = inString; + break; + } + break; + default: + if (state == init) { + tokStart = *pp; + state = inAtom; + } + break; + } + ++*pp; + } + /* not reached */ +} + +/* key must be lowercase ASCII */ + +static int +matchkey(const char *start, const char *end, const char *key) +{ + if (!start) + return 0; + for (; start != end; start++, key++) + if (*start != *key && *start != 'A' + (*key - 'a')) + return 0; + return *key == '\0'; +} + +void +getXMLCharset(const char *buf, char *charset) +{ + const char *next, *p; + + charset[0] = '\0'; + next = buf; + p = getTok(&next); + if (matchkey(p, next, "text")) + strcpy(charset, "us-ascii"); + else if (!matchkey(p, next, "application")) + return; + p = getTok(&next); + if (!p || *p != '/') + return; + p = getTok(&next); + if (matchkey(p, next, "xml")) + isXml = 1; + p = getTok(&next); + while (p) { + if (*p == ';') { + p = getTok(&next); + if (matchkey(p, next, "charset")) { + p = getTok(&next); + if (p && *p == '=') { + p = getTok(&next); + if (p) { + char *s = charset; + if (*p == '"') { + while (++p != next - 1) { + if (*p == '\\') + ++p; + if (s == charset + CHARSET_MAX - 1) { + charset[0] = '\0'; + break; + } + *s++ = *p; + } + *s++ = '\0'; + } + else { + if (next - p > CHARSET_MAX - 1) + break; + while (p != next) + *s++ = *p++; + *s = 0; + break; + } + } + } + } + } + else + p = getTok(&next); + } +} + +int +main(int argc, char **argv) +{ + char buf[CHARSET_MAX]; + getXMLCharset(argv[1], buf); + printf("charset = \"%s\"\n", buf); + return 0; +} diff --git a/contrib/expat/xmlwf/filemap.h b/contrib/expat/xmlwf/filemap.h new file mode 100644 index 0000000..814edec --- /dev/null +++ b/contrib/expat/xmlwf/filemap.h @@ -0,0 +1,17 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stddef.h> + +#ifdef XML_UNICODE +int filemap(const wchar_t *name, + void (*processor)(const void *, size_t, + const wchar_t *, void *arg), + void *arg); +#else +int filemap(const char *name, + void (*processor)(const void *, size_t, + const char *, void *arg), + void *arg); +#endif diff --git a/contrib/expat/xmlwf/readfilemap.c b/contrib/expat/xmlwf/readfilemap.c new file mode 100644 index 0000000..bd32b93 --- /dev/null +++ b/contrib/expat/xmlwf/readfilemap.c @@ -0,0 +1,100 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <stdlib.h> +#include <stdio.h> + +#ifdef __WATCOMC__ +#ifndef __LINUX__ +#include <io.h> +#else +#include <unistd.h> +#endif +#endif + +#ifdef __BEOS__ +#include <unistd.h> +#endif + +#ifndef S_ISREG +#ifndef S_IFREG +#define S_IFREG _S_IFREG +#endif +#ifndef S_IFMT +#define S_IFMT _S_IFMT +#endif +#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG) +#endif /* not S_ISREG */ + +#ifndef O_BINARY +#ifdef _O_BINARY +#define O_BINARY _O_BINARY +#else +#define O_BINARY 0 +#endif +#endif + +#include "filemap.h" + +int +filemap(const char *name, + void (*processor)(const void *, size_t, const char *, void *arg), + void *arg) +{ + size_t nbytes; + int fd; + int n; + struct stat sb; + void *p; + + fd = open(name, O_RDONLY|O_BINARY); + if (fd < 0) { + perror(name); + return 0; + } + if (fstat(fd, &sb) < 0) { + perror(name); + close(fd); + return 0; + } + if (!S_ISREG(sb.st_mode)) { + fprintf(stderr, "%s: not a regular file\n", name); + close(fd); + return 0; + } + nbytes = sb.st_size; + /* malloc will return NULL with nbytes == 0, handle files with size 0 */ + if (nbytes == 0) { + static const char c = '\0'; + processor(&c, 0, name, arg); + close(fd); + return 1; + } + p = malloc(nbytes); + if (!p) { + fprintf(stderr, "%s: out of memory\n", name); + close(fd); + return 0; + } + n = read(fd, p, nbytes); + if (n < 0) { + perror(name); + free(p); + close(fd); + return 0; + } + if (n != nbytes) { + fprintf(stderr, "%s: read unexpected number of bytes\n", name); + free(p); + close(fd); + return 0; + } + processor(p, nbytes, name, arg); + free(p); + close(fd); + return 1; +} diff --git a/contrib/expat/xmlwf/unixfilemap.c b/contrib/expat/xmlwf/unixfilemap.c new file mode 100644 index 0000000..93adce3 --- /dev/null +++ b/contrib/expat/xmlwf/unixfilemap.c @@ -0,0 +1,65 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <sys/types.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <errno.h> +#include <string.h> +#include <stdio.h> +#include <unistd.h> + +#ifndef MAP_FILE +#define MAP_FILE 0 +#endif + +#include "filemap.h" + +int +filemap(const char *name, + void (*processor)(const void *, size_t, const char *, void *arg), + void *arg) +{ + int fd; + size_t nbytes; + struct stat sb; + void *p; + + fd = open(name, O_RDONLY); + if (fd < 0) { + perror(name); + return 0; + } + if (fstat(fd, &sb) < 0) { + perror(name); + close(fd); + return 0; + } + if (!S_ISREG(sb.st_mode)) { + close(fd); + fprintf(stderr, "%s: not a regular file\n", name); + return 0; + } + + nbytes = sb.st_size; + /* mmap fails for zero length files */ + if (nbytes == 0) { + static const char c = '\0'; + processor(&c, 0, name, arg); + close(fd); + return 1; + } + p = (void *)mmap((caddr_t)0, (size_t)nbytes, PROT_READ, + MAP_FILE|MAP_PRIVATE, fd, (off_t)0); + if (p == (void *)-1) { + perror(name); + close(fd); + return 0; + } + processor(p, nbytes, name, arg); + munmap((caddr_t)p, nbytes); + close(fd); + return 1; +} diff --git a/contrib/expat/xmlwf/win32filemap.c b/contrib/expat/xmlwf/win32filemap.c new file mode 100644 index 0000000..41dc35b --- /dev/null +++ b/contrib/expat/xmlwf/win32filemap.c @@ -0,0 +1,96 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#define STRICT 1 +#define WIN32_LEAN_AND_MEAN 1 + +#ifdef XML_UNICODE_WCHAR_T +#ifndef XML_UNICODE +#define XML_UNICODE +#endif +#endif + +#ifdef XML_UNICODE +#define UNICODE +#define _UNICODE +#endif /* XML_UNICODE */ +#include <windows.h> +#include <stdio.h> +#include <tchar.h> +#include "filemap.h" + +static void win32perror(const TCHAR *); + +int +filemap(const TCHAR *name, + void (*processor)(const void *, size_t, const TCHAR *, void *arg), + void *arg) +{ + HANDLE f; + HANDLE m; + DWORD size; + DWORD sizeHi; + void *p; + + f = CreateFile(name, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, + FILE_FLAG_SEQUENTIAL_SCAN, NULL); + if (f == INVALID_HANDLE_VALUE) { + win32perror(name); + return 0; + } + size = GetFileSize(f, &sizeHi); + if (size == (DWORD)-1) { + win32perror(name); + return 0; + } + if (sizeHi) { + _ftprintf(stderr, _T("%s: bigger than 2Gb\n"), name); + return 0; + } + /* CreateFileMapping barfs on zero length files */ + if (size == 0) { + static const char c = '\0'; + processor(&c, 0, name, arg); + CloseHandle(f); + return 1; + } + m = CreateFileMapping(f, NULL, PAGE_READONLY, 0, 0, NULL); + if (m == NULL) { + win32perror(name); + CloseHandle(f); + return 0; + } + p = MapViewOfFile(m, FILE_MAP_READ, 0, 0, 0); + if (p == NULL) { + win32perror(name); + CloseHandle(m); + CloseHandle(f); + return 0; + } + processor(p, size, name, arg); + UnmapViewOfFile(p); + CloseHandle(m); + CloseHandle(f); + return 1; +} + +static void +win32perror(const TCHAR *s) +{ + LPVOID buf; + if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER + | FORMAT_MESSAGE_FROM_SYSTEM, + NULL, + GetLastError(), + MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), + (LPTSTR) &buf, + 0, + NULL)) { + _ftprintf(stderr, _T("%s: %s"), s, buf); + fflush(stderr); + LocalFree(buf); + } + else + _ftprintf(stderr, _T("%s: unknown Windows error\n"), s); +} diff --git a/contrib/expat/xmlwf/xmlfile.c b/contrib/expat/xmlwf/xmlfile.c new file mode 100644 index 0000000..99eeeaa --- /dev/null +++ b/contrib/expat/xmlwf/xmlfile.c @@ -0,0 +1,244 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stdio.h> +#include <stdlib.h> +#include <stddef.h> +#include <string.h> +#include <fcntl.h> + +#ifdef COMPILED_FROM_DSP +#include "winconfig.h" +#elif defined(MACOS_CLASSIC) +#include "macconfig.h" +#elif defined(__amigaos__) +#include "amigaconfig.h" +#elif defined(__WATCOMC__) +#include "watcomconfig.h" +#elif defined(HAVE_EXPAT_CONFIG_H) +#include <expat_config.h> +#endif /* ndef COMPILED_FROM_DSP */ + +#include "expat.h" +#include "xmlfile.h" +#include "xmltchar.h" +#include "filemap.h" + +#if (defined(_MSC_VER) || (defined(__WATCOMC__) && !defined(__LINUX__))) +#include <io.h> +#endif + +#if defined(__amigaos__) && defined(__USE_INLINE__) +#include <proto/expat.h> +#endif + +#ifdef HAVE_UNISTD_H +#include <unistd.h> +#endif + +#ifndef O_BINARY +#ifdef _O_BINARY +#define O_BINARY _O_BINARY +#else +#define O_BINARY 0 +#endif +#endif + +#ifdef _DEBUG +#define READ_SIZE 16 +#else +#define READ_SIZE (1024*8) +#endif + + +typedef struct { + XML_Parser parser; + int *retPtr; +} PROCESS_ARGS; + +static void +reportError(XML_Parser parser, const XML_Char *filename) +{ + enum XML_Error code = XML_GetErrorCode(parser); + const XML_Char *message = XML_ErrorString(code); + if (message) + ftprintf(stdout, T("%s:%" XML_FMT_INT_MOD "u:%" XML_FMT_INT_MOD "u: %s\n"), + filename, + XML_GetErrorLineNumber(parser), + XML_GetErrorColumnNumber(parser), + message); + else + ftprintf(stderr, T("%s: (unknown message %d)\n"), filename, code); +} + +/* This implementation will give problems on files larger than INT_MAX. */ +static void +processFile(const void *data, size_t size, + const XML_Char *filename, void *args) +{ + XML_Parser parser = ((PROCESS_ARGS *)args)->parser; + int *retPtr = ((PROCESS_ARGS *)args)->retPtr; + if (XML_Parse(parser, (const char *)data, (int)size, 1) == XML_STATUS_ERROR) { + reportError(parser, filename); + *retPtr = 0; + } + else + *retPtr = 1; +} + +#if (defined(WIN32) || defined(__WATCOMC__)) + +static int +isAsciiLetter(XML_Char c) +{ + return (T('a') <= c && c <= T('z')) || (T('A') <= c && c <= T('Z')); +} + +#endif /* WIN32 */ + +static const XML_Char * +resolveSystemId(const XML_Char *base, const XML_Char *systemId, + XML_Char **toFree) +{ + XML_Char *s; + *toFree = 0; + if (!base + || *systemId == T('/') +#if (defined(WIN32) || defined(__WATCOMC__)) + || *systemId == T('\\') + || (isAsciiLetter(systemId[0]) && systemId[1] == T(':')) +#endif + ) + return systemId; + *toFree = (XML_Char *)malloc((tcslen(base) + tcslen(systemId) + 2) + * sizeof(XML_Char)); + if (!*toFree) + return systemId; + tcscpy(*toFree, base); + s = *toFree; + if (tcsrchr(s, T('/'))) + s = tcsrchr(s, T('/')) + 1; +#if (defined(WIN32) || defined(__WATCOMC__)) + if (tcsrchr(s, T('\\'))) + s = tcsrchr(s, T('\\')) + 1; +#endif + tcscpy(s, systemId); + return *toFree; +} + +static int +externalEntityRefFilemap(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + int result; + XML_Char *s; + const XML_Char *filename; + XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0); + PROCESS_ARGS args; + args.retPtr = &result; + args.parser = entParser; + filename = resolveSystemId(base, systemId, &s); + XML_SetBase(entParser, filename); + if (!filemap(filename, processFile, &args)) + result = 0; + free(s); + XML_ParserFree(entParser); + return result; +} + +static int +processStream(const XML_Char *filename, XML_Parser parser) +{ + /* passing NULL for filename means read intput from stdin */ + int fd = 0; /* 0 is the fileno for stdin */ + + if (filename != NULL) { + fd = topen(filename, O_BINARY|O_RDONLY); + if (fd < 0) { + tperror(filename); + return 0; + } + } + for (;;) { + int nread; + char *buf = (char *)XML_GetBuffer(parser, READ_SIZE); + if (!buf) { + if (filename != NULL) + close(fd); + ftprintf(stderr, T("%s: out of memory\n"), + filename != NULL ? filename : "xmlwf"); + return 0; + } + nread = read(fd, buf, READ_SIZE); + if (nread < 0) { + tperror(filename != NULL ? filename : "STDIN"); + if (filename != NULL) + close(fd); + return 0; + } + if (XML_ParseBuffer(parser, nread, nread == 0) == XML_STATUS_ERROR) { + reportError(parser, filename != NULL ? filename : "STDIN"); + if (filename != NULL) + close(fd); + return 0; + } + if (nread == 0) { + if (filename != NULL) + close(fd); + break;; + } + } + return 1; +} + +static int +externalEntityRefStream(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + XML_Char *s; + const XML_Char *filename; + int ret; + XML_Parser entParser = XML_ExternalEntityParserCreate(parser, context, 0); + filename = resolveSystemId(base, systemId, &s); + XML_SetBase(entParser, filename); + ret = processStream(filename, entParser); + free(s); + XML_ParserFree(entParser); + return ret; +} + +int +XML_ProcessFile(XML_Parser parser, + const XML_Char *filename, + unsigned flags) +{ + int result; + + if (!XML_SetBase(parser, filename)) { + ftprintf(stderr, T("%s: out of memory"), filename); + exit(1); + } + + if (flags & XML_EXTERNAL_ENTITIES) + XML_SetExternalEntityRefHandler(parser, + (flags & XML_MAP_FILE) + ? externalEntityRefFilemap + : externalEntityRefStream); + if (flags & XML_MAP_FILE) { + PROCESS_ARGS args; + args.retPtr = &result; + args.parser = parser; + if (!filemap(filename, processFile, &args)) + result = 0; + } + else + result = processStream(filename, parser); + return result; +} diff --git a/contrib/expat/xmlwf/xmlfile.h b/contrib/expat/xmlwf/xmlfile.h new file mode 100644 index 0000000..d093ecc --- /dev/null +++ b/contrib/expat/xmlwf/xmlfile.h @@ -0,0 +1,20 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#define XML_MAP_FILE 01 +#define XML_EXTERNAL_ENTITIES 02 + +#ifdef XML_LARGE_SIZE +#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400 +#define XML_FMT_INT_MOD "I64" +#else +#define XML_FMT_INT_MOD "ll" +#endif +#else +#define XML_FMT_INT_MOD "l" +#endif + +extern int XML_ProcessFile(XML_Parser parser, + const XML_Char *filename, + unsigned flags); diff --git a/contrib/expat/xmlwf/xmlmime.c b/contrib/expat/xmlwf/xmlmime.c new file mode 100644 index 0000000..56a0e7f --- /dev/null +++ b/contrib/expat/xmlwf/xmlmime.c @@ -0,0 +1,163 @@ +#include <string.h> +#include "xmlmime.h" + +static const char * +getTok(const char **pp) +{ + /* inComment means one level of nesting; inComment+1 means two levels etc */ + enum { inAtom, inString, init, inComment }; + int state = init; + const char *tokStart = 0; + for (;;) { + switch (**pp) { + case '\0': + if (state == inAtom) + return tokStart; + return 0; + case ' ': + case '\r': + case '\t': + case '\n': + if (state == inAtom) + return tokStart; + break; + case '(': + if (state == inAtom) + return tokStart; + if (state != inString) + state++; + break; + case ')': + if (state > init) + --state; + else if (state != inString) + return 0; + break; + case ';': + case '/': + case '=': + if (state == inAtom) + return tokStart; + if (state == init) + return (*pp)++; + break; + case '\\': + ++*pp; + if (**pp == '\0') + return 0; + break; + case '"': + switch (state) { + case inString: + ++*pp; + return tokStart; + case inAtom: + return tokStart; + case init: + tokStart = *pp; + state = inString; + break; + } + break; + default: + if (state == init) { + tokStart = *pp; + state = inAtom; + } + break; + } + ++*pp; + } + /* not reached */ +} + +/* key must be lowercase ASCII */ + +static int +matchkey(const char *start, const char *end, const char *key) +{ + if (!start) + return 0; + for (; start != end; start++, key++) + if (*start != *key && *start != 'A' + (*key - 'a')) + return 0; + return *key == '\0'; +} + +void +getXMLCharset(const char *buf, char *charset) +{ + const char *next, *p; + + charset[0] = '\0'; + next = buf; + p = getTok(&next); + if (matchkey(p, next, "text")) + strcpy(charset, "us-ascii"); + else if (!matchkey(p, next, "application")) + return; + p = getTok(&next); + if (!p || *p != '/') + return; + p = getTok(&next); +#if 0 + if (!matchkey(p, next, "xml") && charset[0] == '\0') + return; +#endif + p = getTok(&next); + while (p) { + if (*p == ';') { + p = getTok(&next); + if (matchkey(p, next, "charset")) { + p = getTok(&next); + if (p && *p == '=') { + p = getTok(&next); + if (p) { + char *s = charset; + if (*p == '"') { + while (++p != next - 1) { + if (*p == '\\') + ++p; + if (s == charset + CHARSET_MAX - 1) { + charset[0] = '\0'; + break; + } + *s++ = *p; + } + *s++ = '\0'; + } + else { + if (next - p > CHARSET_MAX - 1) + break; + while (p != next) + *s++ = *p++; + *s = 0; + break; + } + } + } + break; + } + } + else + p = getTok(&next); + } +} + +#ifdef TEST + +#include <stdio.h> + +int +main(int argc, char *argv[]) +{ + char buf[CHARSET_MAX]; + if (argc <= 1) + return 1; + printf("%s\n", argv[1]); + getXMLCharset(argv[1], buf); + printf("charset=\"%s\"\n", buf); + return 0; +} + +#endif /* TEST */ diff --git a/contrib/expat/xmlwf/xmlmime.h b/contrib/expat/xmlwf/xmlmime.h new file mode 100644 index 0000000..bf0356d --- /dev/null +++ b/contrib/expat/xmlwf/xmlmime.h @@ -0,0 +1,19 @@ +#ifdef __cplusplus +extern "C" { +#endif + +/* Registered charset names are at most 40 characters long. */ + +#define CHARSET_MAX 41 + +/* Figure out the charset to use from the ContentType. + buf contains the body of the header field (the part after "Content-Type:"). + charset gets the charset to use. It must be at least CHARSET_MAX chars + long. charset will be empty if the default charset should be used. +*/ + +void getXMLCharset(const char *buf, char *charset); + +#ifdef __cplusplus +} +#endif diff --git a/contrib/expat/xmlwf/xmltchar.h b/contrib/expat/xmlwf/xmltchar.h new file mode 100644 index 0000000..1088575 --- /dev/null +++ b/contrib/expat/xmlwf/xmltchar.h @@ -0,0 +1,36 @@ +#ifdef XML_UNICODE +#ifndef XML_UNICODE_WCHAR_T +#error xmlwf requires a 16-bit Unicode-compatible wchar_t +#endif +#define T(x) L ## x +#define ftprintf fwprintf +#define tfopen _wfopen +#define fputts fputws +#define puttc putwc +#define tcscmp wcscmp +#define tcscpy wcscpy +#define tcscat wcscat +#define tcschr wcschr +#define tcsrchr wcsrchr +#define tcslen wcslen +#define tperror _wperror +#define topen _wopen +#define tmain wmain +#define tremove _wremove +#else /* not XML_UNICODE */ +#define T(x) x +#define ftprintf fprintf +#define tfopen fopen +#define fputts fputs +#define puttc putc +#define tcscmp strcmp +#define tcscpy strcpy +#define tcscat strcat +#define tcschr strchr +#define tcsrchr strrchr +#define tcslen strlen +#define tperror perror +#define topen open +#define tmain main +#define tremove remove +#endif /* not XML_UNICODE */ diff --git a/contrib/expat/xmlwf/xmlurl.h b/contrib/expat/xmlwf/xmlurl.h new file mode 100644 index 0000000..d329913 --- /dev/null +++ b/contrib/expat/xmlwf/xmlurl.h @@ -0,0 +1,13 @@ +#ifdef __cplusplus +extern "C" { +#endif + +int XML_URLInit(); +void XML_URLUninit(); +int XML_ProcessURL(XML_Parser parser, + const XML_Char *url, + unsigned flags); + +#ifdef __cplusplus +} +#endif diff --git a/contrib/expat/xmlwf/xmlwf.c b/contrib/expat/xmlwf/xmlwf.c new file mode 100644 index 0000000..4fc77da --- /dev/null +++ b/contrib/expat/xmlwf/xmlwf.c @@ -0,0 +1,861 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stdio.h> +#include <stdlib.h> +#include <stddef.h> +#include <string.h> + +#include "expat.h" +#include "codepage.h" +#include "xmlfile.h" +#include "xmltchar.h" + +#ifdef _MSC_VER +#include <crtdbg.h> +#endif + +#if defined(__amigaos__) && defined(__USE_INLINE__) +#include <proto/expat.h> +#endif + +/* This ensures proper sorting. */ + +#define NSSEP T('\001') + +static void XMLCALL +characterData(void *userData, const XML_Char *s, int len) +{ + FILE *fp = (FILE *)userData; + for (; len > 0; --len, ++s) { + switch (*s) { + case T('&'): + fputts(T("&"), fp); + break; + case T('<'): + fputts(T("<"), fp); + break; + case T('>'): + fputts(T(">"), fp); + break; +#ifdef W3C14N + case 13: + fputts(T("
"), fp); + break; +#else + case T('"'): + fputts(T("""), fp); + break; + case 9: + case 10: + case 13: + ftprintf(fp, T("&#%d;"), *s); + break; +#endif + default: + puttc(*s, fp); + break; + } + } +} + +static void +attributeValue(FILE *fp, const XML_Char *s) +{ + puttc(T('='), fp); + puttc(T('"'), fp); + for (;;) { + switch (*s) { + case 0: + case NSSEP: + puttc(T('"'), fp); + return; + case T('&'): + fputts(T("&"), fp); + break; + case T('<'): + fputts(T("<"), fp); + break; + case T('"'): + fputts(T("""), fp); + break; +#ifdef W3C14N + case 9: + fputts(T("	"), fp); + break; + case 10: + fputts(T("
"), fp); + break; + case 13: + fputts(T("
"), fp); + break; +#else + case T('>'): + fputts(T(">"), fp); + break; + case 9: + case 10: + case 13: + ftprintf(fp, T("&#%d;"), *s); + break; +#endif + default: + puttc(*s, fp); + break; + } + s++; + } +} + +/* Lexicographically comparing UTF-8 encoded attribute values, +is equivalent to lexicographically comparing based on the character number. */ + +static int +attcmp(const void *att1, const void *att2) +{ + return tcscmp(*(const XML_Char **)att1, *(const XML_Char **)att2); +} + +static void XMLCALL +startElement(void *userData, const XML_Char *name, const XML_Char **atts) +{ + int nAtts; + const XML_Char **p; + FILE *fp = (FILE *)userData; + puttc(T('<'), fp); + fputts(name, fp); + + p = atts; + while (*p) + ++p; + nAtts = (int)((p - atts) >> 1); + if (nAtts > 1) + qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, attcmp); + while (*atts) { + puttc(T(' '), fp); + fputts(*atts++, fp); + attributeValue(fp, *atts); + atts++; + } + puttc(T('>'), fp); +} + +static void XMLCALL +endElement(void *userData, const XML_Char *name) +{ + FILE *fp = (FILE *)userData; + puttc(T('<'), fp); + puttc(T('/'), fp); + fputts(name, fp); + puttc(T('>'), fp); +} + +static int +nsattcmp(const void *p1, const void *p2) +{ + const XML_Char *att1 = *(const XML_Char **)p1; + const XML_Char *att2 = *(const XML_Char **)p2; + int sep1 = (tcsrchr(att1, NSSEP) != 0); + int sep2 = (tcsrchr(att1, NSSEP) != 0); + if (sep1 != sep2) + return sep1 - sep2; + return tcscmp(att1, att2); +} + +static void XMLCALL +startElementNS(void *userData, const XML_Char *name, const XML_Char **atts) +{ + int nAtts; + int nsi; + const XML_Char **p; + FILE *fp = (FILE *)userData; + const XML_Char *sep; + puttc(T('<'), fp); + + sep = tcsrchr(name, NSSEP); + if (sep) { + fputts(T("n1:"), fp); + fputts(sep + 1, fp); + fputts(T(" xmlns:n1"), fp); + attributeValue(fp, name); + nsi = 2; + } + else { + fputts(name, fp); + nsi = 1; + } + + p = atts; + while (*p) + ++p; + nAtts = (int)((p - atts) >> 1); + if (nAtts > 1) + qsort((void *)atts, nAtts, sizeof(XML_Char *) * 2, nsattcmp); + while (*atts) { + name = *atts++; + sep = tcsrchr(name, NSSEP); + puttc(T(' '), fp); + if (sep) { + ftprintf(fp, T("n%d:"), nsi); + fputts(sep + 1, fp); + } + else + fputts(name, fp); + attributeValue(fp, *atts); + if (sep) { + ftprintf(fp, T(" xmlns:n%d"), nsi++); + attributeValue(fp, name); + } + atts++; + } + puttc(T('>'), fp); +} + +static void XMLCALL +endElementNS(void *userData, const XML_Char *name) +{ + FILE *fp = (FILE *)userData; + const XML_Char *sep; + puttc(T('<'), fp); + puttc(T('/'), fp); + sep = tcsrchr(name, NSSEP); + if (sep) { + fputts(T("n1:"), fp); + fputts(sep + 1, fp); + } + else + fputts(name, fp); + puttc(T('>'), fp); +} + +#ifndef W3C14N + +static void XMLCALL +processingInstruction(void *userData, const XML_Char *target, + const XML_Char *data) +{ + FILE *fp = (FILE *)userData; + puttc(T('<'), fp); + puttc(T('?'), fp); + fputts(target, fp); + puttc(T(' '), fp); + fputts(data, fp); + puttc(T('?'), fp); + puttc(T('>'), fp); +} + +#endif /* not W3C14N */ + +static void XMLCALL +defaultCharacterData(void *userData, const XML_Char *s, int len) +{ + XML_DefaultCurrent((XML_Parser) userData); +} + +static void XMLCALL +defaultStartElement(void *userData, const XML_Char *name, + const XML_Char **atts) +{ + XML_DefaultCurrent((XML_Parser) userData); +} + +static void XMLCALL +defaultEndElement(void *userData, const XML_Char *name) +{ + XML_DefaultCurrent((XML_Parser) userData); +} + +static void XMLCALL +defaultProcessingInstruction(void *userData, const XML_Char *target, + const XML_Char *data) +{ + XML_DefaultCurrent((XML_Parser) userData); +} + +static void XMLCALL +nopCharacterData(void *userData, const XML_Char *s, int len) +{ +} + +static void XMLCALL +nopStartElement(void *userData, const XML_Char *name, const XML_Char **atts) +{ +} + +static void XMLCALL +nopEndElement(void *userData, const XML_Char *name) +{ +} + +static void XMLCALL +nopProcessingInstruction(void *userData, const XML_Char *target, + const XML_Char *data) +{ +} + +static void XMLCALL +markup(void *userData, const XML_Char *s, int len) +{ + FILE *fp = (FILE *)XML_GetUserData((XML_Parser) userData); + for (; len > 0; --len, ++s) + puttc(*s, fp); +} + +static void +metaLocation(XML_Parser parser) +{ + const XML_Char *uri = XML_GetBase(parser); + if (uri) + ftprintf((FILE *)XML_GetUserData(parser), T(" uri=\"%s\""), uri); + ftprintf((FILE *)XML_GetUserData(parser), + T(" byte=\"%" XML_FMT_INT_MOD "d\" nbytes=\"%d\" \ + line=\"%" XML_FMT_INT_MOD "u\" col=\"%" XML_FMT_INT_MOD "u\""), + XML_GetCurrentByteIndex(parser), + XML_GetCurrentByteCount(parser), + XML_GetCurrentLineNumber(parser), + XML_GetCurrentColumnNumber(parser)); +} + +static void +metaStartDocument(void *userData) +{ + fputts(T("<document>\n"), (FILE *)XML_GetUserData((XML_Parser) userData)); +} + +static void +metaEndDocument(void *userData) +{ + fputts(T("</document>\n"), (FILE *)XML_GetUserData((XML_Parser) userData)); +} + +static void XMLCALL +metaStartElement(void *userData, const XML_Char *name, + const XML_Char **atts) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + const XML_Char **specifiedAttsEnd + = atts + XML_GetSpecifiedAttributeCount(parser); + const XML_Char **idAttPtr; + int idAttIndex = XML_GetIdAttributeIndex(parser); + if (idAttIndex < 0) + idAttPtr = 0; + else + idAttPtr = atts + idAttIndex; + + ftprintf(fp, T("<starttag name=\"%s\""), name); + metaLocation(parser); + if (*atts) { + fputts(T(">\n"), fp); + do { + ftprintf(fp, T("<attribute name=\"%s\" value=\""), atts[0]); + characterData(fp, atts[1], (int)tcslen(atts[1])); + if (atts >= specifiedAttsEnd) + fputts(T("\" defaulted=\"yes\"/>\n"), fp); + else if (atts == idAttPtr) + fputts(T("\" id=\"yes\"/>\n"), fp); + else + fputts(T("\"/>\n"), fp); + } while (*(atts += 2)); + fputts(T("</starttag>\n"), fp); + } + else + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaEndElement(void *userData, const XML_Char *name) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + ftprintf(fp, T("<endtag name=\"%s\""), name); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaProcessingInstruction(void *userData, const XML_Char *target, + const XML_Char *data) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + ftprintf(fp, T("<pi target=\"%s\" data=\""), target); + characterData(fp, data, (int)tcslen(data)); + puttc(T('"'), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaComment(void *userData, const XML_Char *data) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + fputts(T("<comment data=\""), fp); + characterData(fp, data, (int)tcslen(data)); + puttc(T('"'), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaStartCdataSection(void *userData) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + fputts(T("<startcdata"), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaEndCdataSection(void *userData) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + fputts(T("<endcdata"), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaCharacterData(void *userData, const XML_Char *s, int len) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + fputts(T("<chars str=\""), fp); + characterData(fp, s, len); + puttc(T('"'), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaStartDoctypeDecl(void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + ftprintf(fp, T("<startdoctype name=\"%s\""), doctypeName); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaEndDoctypeDecl(void *userData) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + fputts(T("<enddoctype"), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaNotationDecl(void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + ftprintf(fp, T("<notation name=\"%s\""), notationName); + if (publicId) + ftprintf(fp, T(" public=\"%s\""), publicId); + if (systemId) { + fputts(T(" system=\""), fp); + characterData(fp, systemId, (int)tcslen(systemId)); + puttc(T('"'), fp); + } + metaLocation(parser); + fputts(T("/>\n"), fp); +} + + +static void XMLCALL +metaEntityDecl(void *userData, + const XML_Char *entityName, + int is_param, + const XML_Char *value, + int value_length, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + + if (value) { + ftprintf(fp, T("<entity name=\"%s\""), entityName); + metaLocation(parser); + puttc(T('>'), fp); + characterData(fp, value, value_length); + fputts(T("</entity/>\n"), fp); + } + else if (notationName) { + ftprintf(fp, T("<entity name=\"%s\""), entityName); + if (publicId) + ftprintf(fp, T(" public=\"%s\""), publicId); + fputts(T(" system=\""), fp); + characterData(fp, systemId, (int)tcslen(systemId)); + puttc(T('"'), fp); + ftprintf(fp, T(" notation=\"%s\""), notationName); + metaLocation(parser); + fputts(T("/>\n"), fp); + } + else { + ftprintf(fp, T("<entity name=\"%s\""), entityName); + if (publicId) + ftprintf(fp, T(" public=\"%s\""), publicId); + fputts(T(" system=\""), fp); + characterData(fp, systemId, (int)tcslen(systemId)); + puttc(T('"'), fp); + metaLocation(parser); + fputts(T("/>\n"), fp); + } +} + +static void XMLCALL +metaStartNamespaceDecl(void *userData, + const XML_Char *prefix, + const XML_Char *uri) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + fputts(T("<startns"), fp); + if (prefix) + ftprintf(fp, T(" prefix=\"%s\""), prefix); + if (uri) { + fputts(T(" ns=\""), fp); + characterData(fp, uri, (int)tcslen(uri)); + fputts(T("\"/>\n"), fp); + } + else + fputts(T("/>\n"), fp); +} + +static void XMLCALL +metaEndNamespaceDecl(void *userData, const XML_Char *prefix) +{ + XML_Parser parser = (XML_Parser) userData; + FILE *fp = (FILE *)XML_GetUserData(parser); + if (!prefix) + fputts(T("<endns/>\n"), fp); + else + ftprintf(fp, T("<endns prefix=\"%s\"/>\n"), prefix); +} + +static int XMLCALL +unknownEncodingConvert(void *data, const char *p) +{ + return codepageConvert(*(int *)data, p); +} + +static int XMLCALL +unknownEncoding(void *userData, const XML_Char *name, XML_Encoding *info) +{ + int cp; + static const XML_Char prefixL[] = T("windows-"); + static const XML_Char prefixU[] = T("WINDOWS-"); + int i; + + for (i = 0; prefixU[i]; i++) + if (name[i] != prefixU[i] && name[i] != prefixL[i]) + return 0; + + cp = 0; + for (; name[i]; i++) { + static const XML_Char digits[] = T("0123456789"); + const XML_Char *s = tcschr(digits, name[i]); + if (!s) + return 0; + cp *= 10; + cp += (int)(s - digits); + if (cp >= 0x10000) + return 0; + } + if (!codepageMap(cp, info->map)) + return 0; + info->convert = unknownEncodingConvert; + /* We could just cast the code page integer to a void *, + and avoid the use of release. */ + info->release = free; + info->data = malloc(sizeof(int)); + if (!info->data) + return 0; + *(int *)info->data = cp; + return 1; +} + +static int XMLCALL +notStandalone(void *userData) +{ + return 0; +} + +static void +showVersion(XML_Char *prog) +{ + XML_Char *s = prog; + XML_Char ch; + const XML_Feature *features = XML_GetFeatureList(); + while ((ch = *s) != 0) { + if (ch == '/' +#if (defined(WIN32) || defined(__WATCOMC__)) + || ch == '\\' +#endif + ) + prog = s + 1; + ++s; + } + ftprintf(stdout, T("%s using %s\n"), prog, XML_ExpatVersion()); + if (features != NULL && features[0].feature != XML_FEATURE_END) { + int i = 1; + ftprintf(stdout, T("%s"), features[0].name); + if (features[0].value) + ftprintf(stdout, T("=%ld"), features[0].value); + while (features[i].feature != XML_FEATURE_END) { + ftprintf(stdout, T(", %s"), features[i].name); + if (features[i].value) + ftprintf(stdout, T("=%ld"), features[i].value); + ++i; + } + ftprintf(stdout, T("\n")); + } +} + +static void +usage(const XML_Char *prog, int rc) +{ + ftprintf(stderr, + T("usage: %s [-n] [-p] [-r] [-s] [-w] [-x] [-d output-dir] " + "[-e encoding] file ...\n"), prog); + exit(rc); +} + +int +tmain(int argc, XML_Char **argv) +{ + int i, j; + const XML_Char *outputDir = NULL; + const XML_Char *encoding = NULL; + unsigned processFlags = XML_MAP_FILE; + int windowsCodePages = 0; + int outputType = 0; + int useNamespaces = 0; + int requireStandalone = 0; + enum XML_ParamEntityParsing paramEntityParsing = + XML_PARAM_ENTITY_PARSING_NEVER; + int useStdin = 0; + +#ifdef _MSC_VER + _CrtSetDbgFlag(_CRTDBG_ALLOC_MEM_DF|_CRTDBG_LEAK_CHECK_DF); +#endif + + i = 1; + j = 0; + while (i < argc) { + if (j == 0) { + if (argv[i][0] != T('-')) + break; + if (argv[i][1] == T('-') && argv[i][2] == T('\0')) { + i++; + break; + } + j++; + } + switch (argv[i][j]) { + case T('r'): + processFlags &= ~XML_MAP_FILE; + j++; + break; + case T('s'): + requireStandalone = 1; + j++; + break; + case T('n'): + useNamespaces = 1; + j++; + break; + case T('p'): + paramEntityParsing = XML_PARAM_ENTITY_PARSING_ALWAYS; + /* fall through */ + case T('x'): + processFlags |= XML_EXTERNAL_ENTITIES; + j++; + break; + case T('w'): + windowsCodePages = 1; + j++; + break; + case T('m'): + outputType = 'm'; + j++; + break; + case T('c'): + outputType = 'c'; + useNamespaces = 0; + j++; + break; + case T('t'): + outputType = 't'; + j++; + break; + case T('d'): + if (argv[i][j + 1] == T('\0')) { + if (++i == argc) + usage(argv[0], 2); + outputDir = argv[i]; + } + else + outputDir = argv[i] + j + 1; + i++; + j = 0; + break; + case T('e'): + if (argv[i][j + 1] == T('\0')) { + if (++i == argc) + usage(argv[0], 2); + encoding = argv[i]; + } + else + encoding = argv[i] + j + 1; + i++; + j = 0; + break; + case T('h'): + usage(argv[0], 0); + return 0; + case T('v'): + showVersion(argv[0]); + return 0; + case T('\0'): + if (j > 1) { + i++; + j = 0; + break; + } + /* fall through */ + default: + usage(argv[0], 2); + } + } + if (i == argc) { + useStdin = 1; + processFlags &= ~XML_MAP_FILE; + i--; + } + for (; i < argc; i++) { + FILE *fp = 0; + XML_Char *outName = 0; + int result; + XML_Parser parser; + if (useNamespaces) + parser = XML_ParserCreateNS(encoding, NSSEP); + else + parser = XML_ParserCreate(encoding); + if (requireStandalone) + XML_SetNotStandaloneHandler(parser, notStandalone); + XML_SetParamEntityParsing(parser, paramEntityParsing); + if (outputType == 't') { + /* This is for doing timings; this gives a more realistic estimate of + the parsing time. */ + outputDir = 0; + XML_SetElementHandler(parser, nopStartElement, nopEndElement); + XML_SetCharacterDataHandler(parser, nopCharacterData); + XML_SetProcessingInstructionHandler(parser, nopProcessingInstruction); + } + else if (outputDir) { + const XML_Char * delim = T("/"); + const XML_Char *file = useStdin ? T("STDIN") : argv[i]; + if (!useStdin) { + /* Jump after last (back)slash */ + const XML_Char * lastDelim = tcsrchr(file, delim[0]); + if (lastDelim) + file = lastDelim + 1; +#if (defined(WIN32) || defined(__WATCOMC__)) + else { + const XML_Char * winDelim = T("\\"); + lastDelim = tcsrchr(file, winDelim[0]); + if (lastDelim) { + file = lastDelim + 1; + delim = winDelim; + } + } +#endif + } + outName = (XML_Char *)malloc((tcslen(outputDir) + tcslen(file) + 2) + * sizeof(XML_Char)); + tcscpy(outName, outputDir); + tcscat(outName, delim); + tcscat(outName, file); + fp = tfopen(outName, T("wb")); + if (!fp) { + tperror(outName); + exit(1); + } + setvbuf(fp, NULL, _IOFBF, 16384); +#ifdef XML_UNICODE + puttc(0xFEFF, fp); +#endif + XML_SetUserData(parser, fp); + switch (outputType) { + case 'm': + XML_UseParserAsHandlerArg(parser); + XML_SetElementHandler(parser, metaStartElement, metaEndElement); + XML_SetProcessingInstructionHandler(parser, metaProcessingInstruction); + XML_SetCommentHandler(parser, metaComment); + XML_SetCdataSectionHandler(parser, metaStartCdataSection, + metaEndCdataSection); + XML_SetCharacterDataHandler(parser, metaCharacterData); + XML_SetDoctypeDeclHandler(parser, metaStartDoctypeDecl, + metaEndDoctypeDecl); + XML_SetEntityDeclHandler(parser, metaEntityDecl); + XML_SetNotationDeclHandler(parser, metaNotationDecl); + XML_SetNamespaceDeclHandler(parser, metaStartNamespaceDecl, + metaEndNamespaceDecl); + metaStartDocument(parser); + break; + case 'c': + XML_UseParserAsHandlerArg(parser); + XML_SetDefaultHandler(parser, markup); + XML_SetElementHandler(parser, defaultStartElement, defaultEndElement); + XML_SetCharacterDataHandler(parser, defaultCharacterData); + XML_SetProcessingInstructionHandler(parser, + defaultProcessingInstruction); + break; + default: + if (useNamespaces) + XML_SetElementHandler(parser, startElementNS, endElementNS); + else + XML_SetElementHandler(parser, startElement, endElement); + XML_SetCharacterDataHandler(parser, characterData); +#ifndef W3C14N + XML_SetProcessingInstructionHandler(parser, processingInstruction); +#endif /* not W3C14N */ + break; + } + } + if (windowsCodePages) + XML_SetUnknownEncodingHandler(parser, unknownEncoding, 0); + result = XML_ProcessFile(parser, useStdin ? NULL : argv[i], processFlags); + if (outputDir) { + if (outputType == 'm') + metaEndDocument(parser); + fclose(fp); + if (!result) { + tremove(outName); + exit(2); + } + free(outName); + } + XML_ParserFree(parser); + } + return 0; +} diff --git a/contrib/expat/xmlwf/xmlwin32url.cxx b/contrib/expat/xmlwf/xmlwin32url.cxx new file mode 100644 index 0000000..bbfcce2 --- /dev/null +++ b/contrib/expat/xmlwf/xmlwin32url.cxx @@ -0,0 +1,395 @@ +#include "expat.h" +#ifdef XML_UNICODE +#define UNICODE +#endif +#include <windows.h> +#include <urlmon.h> +#include <wininet.h> +#include <stdio.h> +#include <tchar.h> +#include "xmlurl.h" +#include "xmlmime.h" + +static int +processURL(XML_Parser parser, IMoniker *baseMoniker, const XML_Char *url); + +typedef void (*StopHandler)(void *, HRESULT); + +class Callback : public IBindStatusCallback { +public: + // IUnknown methods + STDMETHODIMP QueryInterface(REFIID,void **); + STDMETHODIMP_(ULONG) AddRef(); + STDMETHODIMP_(ULONG) Release(); + // IBindStatusCallback methods + STDMETHODIMP OnStartBinding(DWORD, IBinding *); + STDMETHODIMP GetPriority(LONG *); + STDMETHODIMP OnLowResource(DWORD); + STDMETHODIMP OnProgress(ULONG, ULONG, ULONG, LPCWSTR); + STDMETHODIMP OnStopBinding(HRESULT, LPCWSTR); + STDMETHODIMP GetBindInfo(DWORD *, BINDINFO *); + STDMETHODIMP OnDataAvailable(DWORD, DWORD, FORMATETC *, STGMEDIUM *); + STDMETHODIMP OnObjectAvailable(REFIID, IUnknown *); + Callback(XML_Parser, IMoniker *, StopHandler, void *); + ~Callback(); + int externalEntityRef(const XML_Char *context, + const XML_Char *systemId, const XML_Char *publicId); +private: + XML_Parser parser_; + IMoniker *baseMoniker_; + DWORD totalRead_; + ULONG ref_; + IBinding *pBinding_; + StopHandler stopHandler_; + void *stopArg_; +}; + +STDMETHODIMP_(ULONG) +Callback::AddRef() +{ + return ref_++; +} + +STDMETHODIMP_(ULONG) +Callback::Release() +{ + if (--ref_ == 0) { + delete this; + return 0; + } + return ref_; +} + +STDMETHODIMP +Callback::QueryInterface(REFIID riid, void** ppv) +{ + if (IsEqualGUID(riid, IID_IUnknown)) + *ppv = (IUnknown *)this; + else if (IsEqualGUID(riid, IID_IBindStatusCallback)) + *ppv = (IBindStatusCallback *)this; + else + return E_NOINTERFACE; + ((LPUNKNOWN)*ppv)->AddRef(); + return S_OK; +} + +STDMETHODIMP +Callback::OnStartBinding(DWORD, IBinding* pBinding) +{ + pBinding_ = pBinding; + pBinding->AddRef(); + return S_OK; +} + +STDMETHODIMP +Callback::GetPriority(LONG *) +{ + return E_NOTIMPL; +} + +STDMETHODIMP +Callback::OnLowResource(DWORD) +{ + return E_NOTIMPL; +} + +STDMETHODIMP +Callback::OnProgress(ULONG, ULONG, ULONG, LPCWSTR) +{ + return S_OK; +} + +STDMETHODIMP +Callback::OnStopBinding(HRESULT hr, LPCWSTR szError) +{ + if (pBinding_) { + pBinding_->Release(); + pBinding_ = 0; + } + if (baseMoniker_) { + baseMoniker_->Release(); + baseMoniker_ = 0; + } + stopHandler_(stopArg_, hr); + return S_OK; +} + +STDMETHODIMP +Callback::GetBindInfo(DWORD* pgrfBINDF, BINDINFO* pbindinfo) +{ + *pgrfBINDF = BINDF_ASYNCHRONOUS; + return S_OK; +} + +static void +reportError(XML_Parser parser) +{ + int code = XML_GetErrorCode(parser); + const XML_Char *message = XML_ErrorString(code); + if (message) + _ftprintf(stderr, _T("%s:%d:%ld: %s\n"), + XML_GetBase(parser), + XML_GetErrorLineNumber(parser), + XML_GetErrorColumnNumber(parser), + message); + else + _ftprintf(stderr, _T("%s: (unknown message %d)\n"), + XML_GetBase(parser), code); +} + +STDMETHODIMP +Callback::OnDataAvailable(DWORD grfBSCF, + DWORD dwSize, + FORMATETC *pfmtetc, + STGMEDIUM* pstgmed) +{ + if (grfBSCF & BSCF_FIRSTDATANOTIFICATION) { + IWinInetHttpInfo *hp; + HRESULT hr = pBinding_->QueryInterface(IID_IWinInetHttpInfo, + (void **)&hp); + if (SUCCEEDED(hr)) { + char contentType[1024]; + DWORD bufSize = sizeof(contentType); + DWORD flags = 0; + contentType[0] = 0; + hr = hp->QueryInfo(HTTP_QUERY_CONTENT_TYPE, contentType, + &bufSize, 0, NULL); + if (SUCCEEDED(hr)) { + char charset[CHARSET_MAX]; + getXMLCharset(contentType, charset); + if (charset[0]) { +#ifdef XML_UNICODE + XML_Char wcharset[CHARSET_MAX]; + XML_Char *p1 = wcharset; + const char *p2 = charset; + while ((*p1++ = (unsigned char)*p2++) != 0) + ; + XML_SetEncoding(parser_, wcharset); +#else + XML_SetEncoding(parser_, charset); +#endif + } + } + hp->Release(); + } + } + if (!parser_) + return E_ABORT; + if (pstgmed->tymed == TYMED_ISTREAM) { + while (totalRead_ < dwSize) { +#define READ_MAX (64*1024) + DWORD nToRead = dwSize - totalRead_; + if (nToRead > READ_MAX) + nToRead = READ_MAX; + void *buf = XML_GetBuffer(parser_, nToRead); + if (!buf) { + _ftprintf(stderr, _T("out of memory\n")); + return E_ABORT; + } + DWORD nRead; + HRESULT hr = pstgmed->pstm->Read(buf, nToRead, &nRead); + if (SUCCEEDED(hr)) { + totalRead_ += nRead; + if (!XML_ParseBuffer(parser_, + nRead, + (grfBSCF & BSCF_LASTDATANOTIFICATION) != 0 + && totalRead_ == dwSize)) { + reportError(parser_); + return E_ABORT; + } + } + } + } + return S_OK; +} + +STDMETHODIMP +Callback::OnObjectAvailable(REFIID, IUnknown *) +{ + return S_OK; +} + +int +Callback::externalEntityRef(const XML_Char *context, + const XML_Char *systemId, + const XML_Char *publicId) +{ + XML_Parser entParser = XML_ExternalEntityParserCreate(parser_, context, 0); + XML_SetBase(entParser, systemId); + int ret = processURL(entParser, baseMoniker_, systemId); + XML_ParserFree(entParser); + return ret; +} + +Callback::Callback(XML_Parser parser, IMoniker *baseMoniker, + StopHandler stopHandler, void *stopArg) +: parser_(parser), + baseMoniker_(baseMoniker), + ref_(0), + pBinding_(0), + totalRead_(0), + stopHandler_(stopHandler), + stopArg_(stopArg) +{ + if (baseMoniker_) + baseMoniker_->AddRef(); +} + +Callback::~Callback() +{ + if (pBinding_) + pBinding_->Release(); + if (baseMoniker_) + baseMoniker_->Release(); +} + +static int +externalEntityRef(void *arg, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId) +{ + return ((Callback *)arg)->externalEntityRef(context, systemId, publicId); +} + + +static HRESULT +openStream(XML_Parser parser, + IMoniker *baseMoniker, + const XML_Char *uri, + StopHandler stopHandler, void *stopArg) +{ + if (!XML_SetBase(parser, uri)) + return E_OUTOFMEMORY; + HRESULT hr; + IMoniker *m; +#ifdef XML_UNICODE + hr = CreateURLMoniker(0, uri, &m); +#else + LPWSTR uriw = new wchar_t[strlen(uri) + 1]; + for (int i = 0;; i++) { + uriw[i] = uri[i]; + if (uriw[i] == 0) + break; + } + hr = CreateURLMoniker(baseMoniker, uriw, &m); + delete [] uriw; +#endif + if (FAILED(hr)) + return hr; + IBindStatusCallback *cb = new Callback(parser, m, stopHandler, stopArg); + XML_SetExternalEntityRefHandler(parser, externalEntityRef); + XML_SetExternalEntityRefHandlerArg(parser, cb); + cb->AddRef(); + IBindCtx *b; + if (FAILED(hr = CreateAsyncBindCtx(0, cb, 0, &b))) { + cb->Release(); + m->Release(); + return hr; + } + cb->Release(); + IStream *pStream; + hr = m->BindToStorage(b, 0, IID_IStream, (void **)&pStream); + if (SUCCEEDED(hr)) { + if (pStream) + pStream->Release(); + } + if (hr == MK_S_ASYNCHRONOUS) + hr = S_OK; + m->Release(); + b->Release(); + return hr; +} + +struct QuitInfo { + const XML_Char *url; + HRESULT hr; + int stop; +}; + +static void +winPerror(const XML_Char *url, HRESULT hr) +{ + LPVOID buf; + if (FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER + | FORMAT_MESSAGE_FROM_HMODULE, + GetModuleHandleA("urlmon.dll"), + hr, + MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), + (LPTSTR) &buf, + 0, + NULL) + || FormatMessage(FORMAT_MESSAGE_ALLOCATE_BUFFER + | FORMAT_MESSAGE_FROM_SYSTEM, + 0, + hr, + MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), + (LPTSTR) &buf, + 0, + NULL)) { + /* The system error messages seem to end with a newline. */ + _ftprintf(stderr, _T("%s: %s"), url, buf); + fflush(stderr); + LocalFree(buf); + } + else + _ftprintf(stderr, _T("%s: error %x\n"), url, hr); +} + +static void +threadQuit(void *p, HRESULT hr) +{ + QuitInfo *qi = (QuitInfo *)p; + qi->hr = hr; + qi->stop = 1; +} + +extern "C" +int +XML_URLInit(void) +{ + return SUCCEEDED(CoInitialize(0)); +} + +extern "C" +void +XML_URLUninit(void) +{ + CoUninitialize(); +} + +static int +processURL(XML_Parser parser, IMoniker *baseMoniker, + const XML_Char *url) +{ + QuitInfo qi; + qi.stop = 0; + qi.url = url; + + XML_SetBase(parser, url); + HRESULT hr = openStream(parser, baseMoniker, url, threadQuit, &qi); + if (FAILED(hr)) { + winPerror(url, hr); + return 0; + } + else if (FAILED(qi.hr)) { + winPerror(url, qi.hr); + return 0; + } + MSG msg; + while (!qi.stop && GetMessage (&msg, NULL, 0, 0)) { + TranslateMessage (&msg); + DispatchMessage (&msg); + } + return 1; +} + +extern "C" +int +XML_ProcessURL(XML_Parser parser, + const XML_Char *url, + unsigned flags) +{ + return processURL(parser, 0, url); +} |