diff options
author | uqs <uqs@FreeBSD.org> | 2012-10-19 22:21:01 +0000 |
---|---|---|
committer | uqs <uqs@FreeBSD.org> | 2012-10-19 22:21:01 +0000 |
commit | bdec3cb5a747bba9c264cfc079075a9cdd270b9b (patch) | |
tree | f3e4c243809ab9802585681d5a07885f772eb5b0 /contrib/mdocml/mandoc.3 | |
parent | 3362252a56bf0d1c15907a461e1692760af910c7 (diff) | |
parent | c2dfbbd38125b2ba3608eb48ca3b5e2e23f819df (diff) | |
download | FreeBSD-src-bdec3cb5a747bba9c264cfc079075a9cdd270b9b.zip FreeBSD-src-bdec3cb5a747bba9c264cfc079075a9cdd270b9b.tar.gz |
Merge mandoc from vendor into contrib and provide the necessary Makefile glue.
It's not yet connected to the build.
Diffstat (limited to 'contrib/mdocml/mandoc.3')
-rw-r--r-- | contrib/mdocml/mandoc.3 | 600 |
1 files changed, 600 insertions, 0 deletions
diff --git a/contrib/mdocml/mandoc.3 b/contrib/mdocml/mandoc.3 new file mode 100644 index 0000000..4d0b20d --- /dev/null +++ b/contrib/mdocml/mandoc.3 @@ -0,0 +1,600 @@ +.\" $Id: mandoc.3,v 1.17 2012/01/13 15:27:14 joerg Exp $ +.\" +.\" Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> +.\" Copyright (c) 2010 Ingo Schwarze <schwarze@openbsd.org> +.\" +.\" Permission to use, copy, modify, and distribute this software for any +.\" purpose with or without fee is hereby granted, provided that the above +.\" copyright notice and this permission notice appear in all copies. +.\" +.\" THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES +.\" WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF +.\" MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR +.\" ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES +.\" WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN +.\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF +.\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. +.\" +.Dd $Mdocdate: January 13 2012 $ +.Dt MANDOC 3 +.Os +.Sh NAME +.Nm mandoc , +.Nm mandoc_escape , +.Nm man_meta , +.Nm man_mparse , +.Nm man_node , +.Nm mchars_alloc , +.Nm mchars_free , +.Nm mchars_num2char , +.Nm mchars_num2uc , +.Nm mchars_spec2cp , +.Nm mchars_spec2str , +.Nm mdoc_meta , +.Nm mdoc_node , +.Nm mparse_alloc , +.Nm mparse_free , +.Nm mparse_getkeep , +.Nm mparse_keep , +.Nm mparse_readfd , +.Nm mparse_reset , +.Nm mparse_result , +.Nm mparse_strerror , +.Nm mparse_strlevel +.Nd mandoc macro compiler library +.Sh LIBRARY +.Lb mandoc +.Sh SYNOPSIS +.In man.h +.In mdoc.h +.In mandoc.h +.Ft "enum mandoc_esc" +.Fo mandoc_escape +.Fa "const char **end" +.Fa "const char **start" +.Fa "int *sz" +.Fc +.Ft "const struct man_meta *" +.Fo man_meta +.Fa "const struct man *man" +.Fc +.Ft "const struct mparse *" +.Fo man_mparse +.Fa "const struct man *man" +.Fc +.Ft "const struct man_node *" +.Fo man_node +.Fa "const struct man *man" +.Fc +.Ft "struct mchars *" +.Fn mchars_alloc +.Ft void +.Fn mchars_free "struct mchars *p" +.Ft char +.Fn mchars_num2char "const char *cp" "size_t sz" +.Ft int +.Fn mchars_num2uc "const char *cp" "size_t sz" +.Ft "const char *" +.Fo mchars_spec2str +.Fa "const struct mchars *p" +.Fa "const char *cp" +.Fa "size_t sz" +.Fa "size_t *rsz" +.Fc +.Ft int +.Fo mchars_spec2cp +.Fa "const struct mchars *p" +.Fa "const char *cp" +.Fa "size_t sz" +.Ft "const char *" +.Fc +.Ft "const struct mdoc_meta *" +.Fo mdoc_meta +.Fa "const struct mdoc *mdoc" +.Fc +.Ft "const struct mdoc_node *" +.Fo mdoc_node +.Fa "const struct mdoc *mdoc" +.Fc +.Ft void +.Fo mparse_alloc +.Fa "enum mparset type" +.Fa "enum mandoclevel wlevel" +.Fa "mandocmsg msg" +.Fa "void *msgarg" +.Fc +.Ft void +.Fo mparse_free +.Fa "struct mparse *parse" +.Fc +.Ft void +.Fo mparse_getkeep +.Fa "const struct mparse *parse" +.Fc +.Ft void +.Fo mparse_keep +.Fa "struct mparse *parse" +.Fc +.Ft "enum mandoclevel" +.Fo mparse_readfd +.Fa "struct mparse *parse" +.Fa "int fd" +.Fa "const char *fname" +.Fc +.Ft void +.Fo mparse_reset +.Fa "struct mparse *parse" +.Fc +.Ft void +.Fo mparse_result +.Fa "struct mparse *parse" +.Fa "struct mdoc **mdoc" +.Fa "struct man **man" +.Fc +.Ft "const char *" +.Fo mparse_strerror +.Fa "enum mandocerr" +.Fc +.Ft "const char *" +.Fo mparse_strlevel +.Fa "enum mandoclevel" +.Fc +.Vt extern const char * const * man_macronames; +.Vt extern const char * const * mdoc_argnames; +.Vt extern const char * const * mdoc_macronames; +.Fd "#define ASCII_NBRSP" +.Fd "#define ASCII_HYPH" +.Sh DESCRIPTION +The +.Nm mandoc +library parses a +.Ux +manual into an abstract syntax tree (AST). +.Ux +manuals are composed of +.Xr mdoc 7 +or +.Xr man 7 , +and may be mixed with +.Xr roff 7 , +.Xr tbl 7 , +and +.Xr eqn 7 +invocations. +.Pp +The following describes a general parse sequence: +.Bl -enum +.It +initiate a parsing sequence with +.Fn mparse_alloc ; +.It +parse files or file descriptors with +.Fn mparse_readfd ; +.It +retrieve a parsed syntax tree, if the parse was successful, with +.Fn mparse_result ; +.It +iterate over parse nodes with +.Fn mdoc_node +or +.Fn man_node ; +.It +free all allocated memory with +.Fn mparse_free , +or invoke +.Fn mparse_reset +and parse new files. +.El +.Pp +The +.Nm +library also contains routines for translating character strings into glyphs +.Pq see Fn mchars_alloc +and parsing escape sequences from strings +.Pq see Fn mandoc_escape . +.Sh REFERENCE +This section documents the functions, types, and variables available +via +.In mandoc.h . +.Ss Types +.Bl -ohang +.It Vt "enum mandoc_esc" +An escape sequence classification. +.It Vt "enum mandocerr" +A fatal error, error, or warning message during parsing. +.It Vt "enum mandoclevel" +A classification of an +.Vt "enum mandoclevel" +as regards system operation. +.It Vt "struct mchars" +An opaque pointer to an object allowing for translation between +character strings and glyphs. +See +.Fn mchars_alloc . +.It Vt "enum mparset" +The type of parser when reading input. +This should usually be +.Dv MPARSE_AUTO +for auto-detection. +.It Vt "struct mparse" +An opaque pointer to a running parse sequence. +Created with +.Fn mparse_alloc +and freed with +.Fn mparse_free . +This may be used across parsed input if +.Fn mparse_reset +is called between parses. +.It Vt "mandocmsg" +A prototype for a function to handle fatal error, error, and warning +messages emitted by the parser. +.El +.Ss Functions +.Bl -ohang +.It Fn mandoc_escape +Scan an escape sequence, i.e., a character string beginning with +.Sq \e . +Pass a pointer to the character after the +.Sq \e +as +.Va end ; +it will be set to the supremum of the parsed escape sequence unless +returning +.Dv ESCAPE_ERROR , +in which case the string is bogus and should be +thrown away. +If not +.Dv ESCAPE_ERROR +or +.Dv ESCAPE_IGNORE , +.Va start +is set to the first relevant character of the substring (font, glyph, +whatever) of length +.Va sz . +Both +.Va start +and +.Va sz +may be +.Dv NULL . +.It Fn man_meta +Obtain the meta-data of a successful parse. +This may only be used on a pointer returned by +.Fn mparse_result . +.It Fn man_mparse +Get the parser used for the current output. +.It Fn man_node +Obtain the root node of a successful parse. +This may only be used on a pointer returned by +.Fn mparse_result . +.It Fn mchars_alloc +Allocate an +.Vt "struct mchars *" +object for translating special characters into glyphs. +See +.Xr mandoc_char 7 +for an overview of special characters. +The object must be freed with +.Fn mchars_free . +.It Fn mchars_free +Free an object created with +.Fn mchars_alloc . +.It Fn mchars_num2char +Convert a character index (e.g., the \eN\(aq\(aq escape) into a +printable ASCII character. +Returns \e0 (the nil character) if the input sequence is malformed. +.It Fn mchars_num2uc +Convert a hexadecimal character index (e.g., the \e[uNNNN] escape) into +a Unicode codepoint. +Returns \e0 (the nil character) if the input sequence is malformed. +.It Fn mchars_spec2cp +Convert a special character into a valid Unicode codepoint. +Returns \-1 on failure or a non-zero Unicode codepoint on success. +.It Fn mchars_spec2str +Convert a special character into an ASCII string. +Returns +.Dv NULL +on failure. +.It Fn mdoc_meta +Obtain the meta-data of a successful parse. +This may only be used on a pointer returned by +.Fn mparse_result . +.It Fn mdoc_node +Obtain the root node of a successful parse. +This may only be used on a pointer returned by +.Fn mparse_result . +.It Fn mparse_alloc +Allocate a parser. +The same parser may be used for multiple files so long as +.Fn mparse_reset +is called between parses. +.Fn mparse_free +must be called to free the memory allocated by this function. +.It Fn mparse_free +Free all memory allocated by +.Fn mparse_alloc . +.It Fn mparse_getkeep +Acquire the keep buffer. +Must follow a call of +.Fn mparse_keep . +.It Fn mparse_keep +Instruct the parser to retain a copy of its parsed input. +This can be acquired with subsequent +.Fn mparse_getkeep +calls. +.It Fn mparse_readfd +Parse a file or file descriptor. +If +.Va fd +is -1, +.Va fname +is opened for reading. +Otherwise, +.Va fname +is assumed to be the name associated with +.Va fd . +This may be called multiple times with different parameters; however, +.Fn mparse_reset +should be invoked between parses. +.It Fn mparse_reset +Reset a parser so that +.Fn mparse_readfd +may be used again. +.It Fn mparse_result +Obtain the result of a parse. +Only successful parses +.Po +i.e., those where +.Fn mparse_readfd +returned less than MANDOCLEVEL_FATAL +.Pc +should invoke this function, in which case one of the two pointers will +be filled in. +.It Fn mparse_strerror +Return a statically-allocated string representation of an error code. +.It Fn mparse_strlevel +Return a statically-allocated string representation of a level code. +.El +.Ss Variables +.Bl -ohang +.It Va man_macronames +The string representation of a man macro as indexed by +.Vt "enum mant" . +.It Va mdoc_argnames +The string representation of a mdoc macro argument as indexed by +.Vt "enum mdocargt" . +.It Va mdoc_macronames +The string representation of a mdoc macro as indexed by +.Vt "enum mdoct" . +.El +.Sh IMPLEMENTATION NOTES +This section consists of structural documentation for +.Xr mdoc 7 +and +.Xr man 7 +syntax trees and strings. +.Ss Man and Mdoc Strings +Strings may be extracted from mdoc and man meta-data, or from text +nodes (MDOC_TEXT and MAN_TEXT, respectively). +These strings have special non-printing formatting cues embedded in the +text itself, as well as +.Xr roff 7 +escapes preserved from input. +Implementing systems will need to handle both situations to produce +human-readable text. +In general, strings may be assumed to consist of 7-bit ASCII characters. +.Pp +The following non-printing characters may be embedded in text strings: +.Bl -tag -width Ds +.It Dv ASCII_NBRSP +A non-breaking space character. +.It Dv ASCII_HYPH +A soft hyphen. +.El +.Pp +Escape characters are also passed verbatim into text strings. +An escape character is a sequence of characters beginning with the +backslash +.Pq Sq \e . +To construct human-readable text, these should be intercepted with +.Fn mandoc_escape +and converted with one of +.Fn mchars_num2char , +.Fn mchars_spec2str , +and so on. +.Ss Man Abstract Syntax Tree +This AST is governed by the ontological rules dictated in +.Xr man 7 +and derives its terminology accordingly. +.Pp +The AST is composed of +.Vt struct man_node +nodes with element, root and text types as declared by the +.Va type +field. +Each node also provides its parse point (the +.Va line , +.Va sec , +and +.Va pos +fields), its position in the tree (the +.Va parent , +.Va child , +.Va next +and +.Va prev +fields) and some type-specific data. +.Pp +The tree itself is arranged according to the following normal form, +where capitalised non-terminals represent nodes. +.Pp +.Bl -tag -width "ELEMENTXX" -compact +.It ROOT +\(<- mnode+ +.It mnode +\(<- ELEMENT | TEXT | BLOCK +.It BLOCK +\(<- HEAD BODY +.It HEAD +\(<- mnode* +.It BODY +\(<- mnode* +.It ELEMENT +\(<- ELEMENT | TEXT* +.It TEXT +\(<- [[:ascii:]]* +.El +.Pp +The only elements capable of nesting other elements are those with +next-lint scope as documented in +.Xr man 7 . +.Ss Mdoc Abstract Syntax Tree +This AST is governed by the ontological +rules dictated in +.Xr mdoc 7 +and derives its terminology accordingly. +.Qq In-line +elements described in +.Xr mdoc 7 +are described simply as +.Qq elements . +.Pp +The AST is composed of +.Vt struct mdoc_node +nodes with block, head, body, element, root and text types as declared +by the +.Va type +field. +Each node also provides its parse point (the +.Va line , +.Va sec , +and +.Va pos +fields), its position in the tree (the +.Va parent , +.Va child , +.Va nchild , +.Va next +and +.Va prev +fields) and some type-specific data, in particular, for nodes generated +from macros, the generating macro in the +.Va tok +field. +.Pp +The tree itself is arranged according to the following normal form, +where capitalised non-terminals represent nodes. +.Pp +.Bl -tag -width "ELEMENTXX" -compact +.It ROOT +\(<- mnode+ +.It mnode +\(<- BLOCK | ELEMENT | TEXT +.It BLOCK +\(<- HEAD [TEXT] (BODY [TEXT])+ [TAIL [TEXT]] +.It ELEMENT +\(<- TEXT* +.It HEAD +\(<- mnode* +.It BODY +\(<- mnode* [ENDBODY mnode*] +.It TAIL +\(<- mnode* +.It TEXT +\(<- [[:ascii:]]* +.El +.Pp +Of note are the TEXT nodes following the HEAD, BODY and TAIL nodes of +the BLOCK production: these refer to punctuation marks. +Furthermore, although a TEXT node will generally have a non-zero-length +string, in the specific case of +.Sq \&.Bd \-literal , +an empty line will produce a zero-length string. +Multiple body parts are only found in invocations of +.Sq \&Bl \-column , +where a new body introduces a new phrase. +.Pp +The +.Xr mdoc 7 +syntax tree accommodates for broken block structures as well. +The ENDBODY node is available to end the formatting associated +with a given block before the physical end of that block. +It has a non-null +.Va end +field, is of the BODY +.Va type , +has the same +.Va tok +as the BLOCK it is ending, and has a +.Va pending +field pointing to that BLOCK's BODY node. +It is an indirect child of that BODY node +and has no children of its own. +.Pp +An ENDBODY node is generated when a block ends while one of its child +blocks is still open, like in the following example: +.Bd -literal -offset indent +\&.Ao ao +\&.Bo bo ac +\&.Ac bc +\&.Bc end +.Ed +.Pp +This example results in the following block structure: +.Bd -literal -offset indent +BLOCK Ao + HEAD Ao + BODY Ao + TEXT ao + BLOCK Bo, pending -> Ao + HEAD Bo + BODY Bo + TEXT bo + TEXT ac + ENDBODY Ao, pending -> Ao + TEXT bc +TEXT end +.Ed +.Pp +Here, the formatting of the +.Sq \&Ao +block extends from TEXT ao to TEXT ac, +while the formatting of the +.Sq \&Bo +block extends from TEXT bo to TEXT bc. +It renders as follows in +.Fl T Ns Cm ascii +mode: +.Pp +.Dl <ao [bo ac> bc] end +.Pp +Support for badly-nested blocks is only provided for backward +compatibility with some older +.Xr mdoc 7 +implementations. +Using badly-nested blocks is +.Em strongly discouraged ; +for example, the +.Fl T Ns Cm html +and +.Fl T Ns Cm xhtml +front-ends to +.Xr mandoc 1 +are unable to render them in any meaningful way. +Furthermore, behaviour when encountering badly-nested blocks is not +consistent across troff implementations, especially when using multiple +levels of badly-nested blocks. +.Sh SEE ALSO +.Xr mandoc 1 , +.Xr eqn 7 , +.Xr man 7 , +.Xr mandoc_char 7 , +.Xr mdoc 7 , +.Xr roff 7 , +.Xr tbl 7 +.Sh AUTHORS +The +.Nm +library was written by +.An Kristaps Dzonsons , +.Mt kristaps@bsd.lv . |