Virgin import of a trimmed down GNU Grep 2.4a.

9 files changed, 143 insertions, 39 deletions

diff --git a/gnu/usr.bin/grep/ChangeLog b/gnu/usr.bin/grep/ChangeLog
index 3855810..8106528 100644
--- a/gnu/usr.bin/grep/ChangeLog
+++ b/gnu/usr.bin/grep/ChangeLog
@@ -1,3 +1,22 @@
+2000-01-04  Paul Eggert
+
+	Inititial patch from David O'Brien.
+
+	Add --binary-files option.
+	* NEWS, doc/grep.1, doc/grep.texi: Document it.
+	* src/grep.c (BINARY_FILES_OPTION): New constant.
+	(long_options, grep, usage, main): New --binary-files option.
+	(binary_files): New var.
+	* src/system.h (TYPE_SIGNED, TYPE_MINIMUM, TYPE_MAXIMUM, CHAR_MAX):
+	New macros.
+	(INT_MAX, UCHAR_MAX): Define in terms of TYPE_MAXIMUM.
+
+2000-01-04  Paul Eggert
+
+	* savedir.c (savedir): Don't store past the end of an array if
+	name_size is zero and the directory is empty.
+	Reported by Dima Barsky <dima@pwd.hp.com>.
+
 1999-11-18  Paul Eggert
 
 	* m4/largefile.m4 (AC_SYS_LARGEFILE_FLAGS): Work around a
@@ -46,8 +65,8 @@
 	* configure.in: drop support for --without-included-regex.
 	This was generating bogus bug reports, since many GNU/Linux
 	users have different version of glibc.  And glibc maintainers
-	decided to drop k&r support. 
-	
+	decided to drop k&r support.
+
 1999-11-01 Arnold D. Robbins
 
 	* regex.c (init_syntax_once): move below definition of
@@ -302,7 +321,7 @@ axes.)
 
 1999-06-15 Alain Magloire
 
-	* src/grep.c, doc/grep{1,texi} : 
+	* src/grep.c, doc/grep{1,texi} :
 	--revert-match should be --invert-match.
 	Correction proposed by Karl Berry.
 
@@ -337,7 +356,7 @@ axes.)
 1999-03-05  Eli Zaretskii
 
 	* src/grep.c (main): Print the name of the default matcher instead
-	of just "grep".                                                        
+	of just "grep".
 
 1999-02-06 Alain Magloire
 
@@ -349,7 +368,7 @@ axes.)
 	the input is drained, like this:
 	status=`echo 'check' | { ${GREP} -E -e pattern >/dev/null 2>&1;
 	echo $?; cat >/dev/null; }`; if test $status -ne $errnu then ... fi
-	Excerpt email from Andreas Schwab.                              
+	Excerpt email from Andreas Schwab.
 
 1999-02-23 Alain Magloire
 
@@ -470,7 +489,7 @@ axes.)
 	* PATCHES-AM: New file. A small patch for automake-1.4, use $(sep)
 	as the path separator base on @SEP@.
 	* PATCHES-AC configure.in : updated for autoconf-13.
- 
+
 1999-01-27 Volker Borchert
 
 	* grep.c: fgrep -NUM not working correctly.
diff --git a/gnu/usr.bin/grep/NEWS b/gnu/usr.bin/grep/NEWS
index efeaf41..88701af 100644
--- a/gnu/usr.bin/grep/NEWS
+++ b/gnu/usr.bin/grep/NEWS
@@ -1,3 +1,10 @@
+  - The new option --binary-files=TYPE makes grep assume that a binary input
+    file is of type TYPE.
+    --binary-files='binary' (the default) outputs a 1-line summary of matches.
+    --binary-files='without-match' assumes binary files do not match.
+    --binary-files='text' treats binary files as text
+	(equivalent to -a or --text).
+
 Version 2.4:
 
   - egrep is now equivalent to `grep -E' as required by POSIX,
diff --git a/gnu/usr.bin/grep/THANKS b/gnu/usr.bin/grep/THANKS
index 924b6cf..75ecc46 100644
--- a/gnu/usr.bin/grep/THANKS
+++ b/gnu/usr.bin/grep/THANKS
@@ -4,6 +4,7 @@ Andreas Schwab        <schwab@suse.de>
 Andreas Ley           <andy@rz.uni-karlsruhe.de>
 Ben Elliston          <bje@cygnus.com>
 David J MacKenzie     <djm@catapult.va.pubnix.com>
+David O'Brien         <obrien@freebsd.org>
 Eli Zaretskii         <eliz@is.elta.co.il>
 Florian La Roche      <florian@knorke.saar.de>
 Franc,ois Pinard      <pinard@IRO.UMontreal.CA>
diff --git a/gnu/usr.bin/grep/doc/grep.texi b/gnu/usr.bin/grep/doc/grep.texi
index 50a6938..d71f2c1 100644
--- a/gnu/usr.bin/grep/doc/grep.texi
+++ b/gnu/usr.bin/grep/doc/grep.texi
@@ -275,6 +275,21 @@ This version number should be included in all bug reports.
 Print a usage message briefly summarizing these command-line options
 and the bug-reporting address, then exit.
 
+@itemx --binary-files=@var{type}
+@opindex --binary-files
+@cindex binary files
+If the first few bytes of a file indicate that the file contains binary
+data, assume that the file is of type @var{type}.  By default,
+@var{type} is @samp{binary}, and @command{grep} normally outputs either
+a one-line message saying that a binary file matches, or no message if
+there is no match.  If @var{type} is @samp{without-match},
+@command{grep} assumes that a binary file does not match.  If @var{type}
+is @samp{text}, @command{grep} processes a binary file as if it were
+text; this is equivalent to the @samp{-a} or @samp{--text} option.
+@emph{Warning:} @samp{--binary-files=text} might output binary garbage,
+which can have nasty side effects if the output is a terminal and if the
+terminal driver interprets some of it as commands.
+
 @item -b
 @itemx --byte-offset
 @opindex -b
@@ -329,16 +344,8 @@ The scanning of every file will stop on the first match.
 @opindex --text
 @cindex suppress binary data
 @cindex binary files
-Do not suppress output lines that contain binary data.
-Normally, if the first few bytes of a file indicate
-that the file contains binary data, grep outputs only a
-message saying that the file matches the pattern.  This
-option causes grep to act as if the file is a text
-file, even if it would otherwise be treated as binary.
-@emph{Warning:} the result might be binary garbage
-printed to the terminal, which can have nasty
-side-effects if the terminal driver interprets some of
-it as commands.
+Process a binary file as if it were text; this is equivalent to the
+@samp{--binary-files=text} option.
 
 @item -w
 @itemx --word-regexp
diff --git a/gnu/usr.bin/grep/doc/version.texi b/gnu/usr.bin/grep/doc/version.texi
index 2c6880e..2deace2 100644
--- a/gnu/usr.bin/grep/doc/version.texi
+++ b/gnu/usr.bin/grep/doc/version.texi
@@ -1,3 +1,3 @@
-@set UPDATED 13 November 1999
-@set EDITION 2.4
-@set VERSION 2.4
+@set UPDATED 16 January 2000
+@set EDITION 2.4a
+@set VERSION 2.4a
diff --git a/gnu/usr.bin/grep/grep.1 b/gnu/usr.bin/grep/grep.1
index 0cee267..f6f5485 100644
--- a/gnu/usr.bin/grep/grep.1
+++ b/gnu/usr.bin/grep/grep.1
@@ -12,7 +12,7 @@
 .de Id
 .ds Dt \\$4
 ..
-.Id $Id: grep.1,v 1.7 1999/10/12 20:41:01 alainm Exp $
+.Id $Id: grep.1,v 1.8 2000/01/17 00:55:06 alainm Exp $
 .TH GREP 1 \*(Dt "GNU Project"
 .SH NAME
 grep, egrep, fgrep \- print lines matching a pattern
@@ -28,6 +28,7 @@ grep, egrep, fgrep \- print lines matching a pattern
 .IR FILE ]
 .RB [ \-d
 .IR ACTION ]
+.RB [ \-\^\-binary-files=\fITYPE\fP ]
 .RB [ \-\^\-directories=\fIACTION\fP ]
 .RB [ \-\^\-extended-regexp ]
 .RB [ \-\^\-fixed-strings ]
@@ -143,6 +144,41 @@ Print the version number of
 to standard error.  This version number should
 be included in all bug reports (see below).
 .TP
+.BI \-\^\-binary-files= TYPE
+If the first few bytes of a file indicate that the file contains binary
+data, assume that the file is of type
+.IR TYPE .
+By default,
+.I TYPE
+is
+.BR binary ,
+and
+.B grep
+normally outputs either
+a one-line message saying that a binary file matches, or no message if
+there is no match.
+If
+.I TYPE
+is
+.BR without-match ,
+.B grep
+assumes that a binary file does not match.
+If
+.I TYPE
+is
+.BR text ,
+.B grep
+processes a binary file as if it were text; this is equivalent to the
+.B \-a
+or
+.B \-\^\-text
+option.
+.I Warning:
+.B "grep \-\^\-binary-files=text"
+might output binary garbage,
+which can have nasty side effects if the output is a terminal and if the
+terminal driver interprets some of it as commands.
+.TP
 .BR \-b ", " \-\^\-byte-offset
 Print the byte offset within the input file before
 each line of output.
@@ -257,15 +293,9 @@ and
 and should redirect output to /dev/null instead.
 .TP
 .BR \-a ", " \-\^\-text
-Do not suppress output lines that contain binary data.
-Normally, if the first few bytes of a file indicate that
-the file contains binary data,
-.B grep
-outputs only a message saying that the file matches the pattern.
-This option causes
-.B grep
-to act as if the file is a text file,
-even if it would otherwise be treated as binary.
+Process a binary file as if it were text; this is equivalent to the
+.B \-\^\-binary-files=text
+option.
 .TP
 .BR \-v ", " \-\^\-invert-match
 Invert the sense of matching, to select non-matching lines.
@@ -323,9 +353,9 @@ system call to read input, instead of
 the default
 .BR read (2)
 system call.  In some situations,
-.B -\^-mmap
+.B \-\^\-mmap
 yields better performance.  However,
-.B -\^-mmap
+.B \-\^\-mmap
 can cause undefined behavior (including core dumps)
 if an input file shrinks while
 .B grep
diff --git a/gnu/usr.bin/grep/grep.c b/gnu/usr.bin/grep/grep.c
index 445eeca..80f7470 100644
--- a/gnu/usr.bin/grep/grep.c
+++ b/gnu/usr.bin/grep/grep.c
@@ -62,12 +62,19 @@ static int mmap_option;
 static char const short_options[] =
 "0123456789A:B:C::EFGHUVX:abcd:e:f:hiLlnqrsuvwxyZz";
 
+/* Non-boolean long options that have no corresponding short equivalents.  */
+enum
+{
+  BINARY_FILES_OPTION = CHAR_MAX + 1
+};
+
 /* Long options equivalences. */
 static struct option long_options[] =
 {
   {"after-context", required_argument, NULL, 'A'},
   {"basic-regexp", no_argument, NULL, 'G'},
   {"before-context", required_argument, NULL, 'B'},
+  {"binary-files", required_argument, NULL, BINARY_FILES_OPTION},
   {"byte-offset", no_argument, NULL, 'b'},
   {"context", optional_argument, NULL, 'C'},
   {"count", no_argument, NULL, 'c'},
@@ -476,7 +483,12 @@ fillbuf (save, stats)
 }
 
 /* Flags controlling the style of output. */
-static int always_text;		/* Assume the input is always text. */
+static enum
+  {
+    BINARY_BINARY_FILES,
+    TEXT_BINARY_FILES,
+    WITHOUT_MATCH_BINARY_FILES
+  } binary_files;		/* How to handle binary files.  */
 static int filename_mask;	/* If zero, output nulls after filenames.  */
 static int out_quiet;		/* Suppress all normal output. */
 static int out_invert;		/* Print nonmatching stuff. */
@@ -729,11 +741,14 @@ grep (fd, file, stats)
     {
       if (! (is_EISDIR (errno, file) && suppress_errors))
 	error (filename, errno);
-      return nlines;
+      return 0;
     }
 
-  not_text = (! (always_text | out_quiet)
+  not_text = (((binary_files == BINARY_BINARY_FILES && !out_quiet)
+	       || binary_files == WITHOUT_MATCH_BINARY_FILES)
 	      && memchr (bufbeg, eol ? '\0' : '\200', buflim - bufbeg));
+  if (not_text && binary_files == WITHOUT_MATCH_BINARY_FILES)
+    return 0;
   done_on_match += not_text;
   out_quiet += not_text;
 
@@ -993,7 +1008,9 @@ Output control:\n\
   -H, --with-filename       print the filename for each match\n\
   -h, --no-filename         suppress the prefixing filename on output\n\
   -q, --quiet, --silent     suppress all normal output\n\
-  -a, --text                do not suppress binary output\n\
+  -a, --text                equivalent to --binary-files=text\n\
+      --binary-files=TYPE   assume that binary files are TYPE\n\
+                            TYPE is 'binary', 'text', or 'without-match'.\n\
   -d, --directories=ACTION  how to handle directories\n\
                             ACTION is 'read', 'recurse', or 'skip'.\n\
   -r, --recursive           equivalent to --directories=recurse.\n\
@@ -1276,7 +1293,7 @@ main (argc, argv)
 	setmatcher (optarg);
 	break;
       case 'a':
-	always_text = 1;
+	binary_files = TEXT_BINARY_FILES;
 	break;
       case 'b':
 	out_byte = 1;
@@ -1370,6 +1387,16 @@ main (argc, argv)
       case 'z':
 	eolbyte = '\0';
 	break;
+      case BINARY_FILES_OPTION:
+	if (strcmp (optarg, "binary") == 0)
+	  binary_files = BINARY_BINARY_FILES;
+	else if (strcmp (optarg, "text") == 0)
+	  binary_files = TEXT_BINARY_FILES;
+	else if (strcmp (optarg, "without-match") == 0)
+	  binary_files = WITHOUT_MATCH_BINARY_FILES;
+	else
+	  fatal (_("unknown binary-files type"), 0);
+	break;
       case 0:
 	/* long options */
 	break;
diff --git a/gnu/usr.bin/grep/savedir.c b/gnu/usr.bin/grep/savedir.c
index 5a9c339..e329717 100644
--- a/gnu/usr.bin/grep/savedir.c
+++ b/gnu/usr.bin/grep/savedir.c
@@ -1,5 +1,5 @@
 /* savedir.c -- save the list of files in a directory in a string
-   Copyright (C) 1990, 1997, 1998 Free Software Foundation, Inc.
+   Copyright (C) 1990, 1997, 1998, 1999, 2000 Free Software Foundation, Inc.
 
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -89,6 +89,10 @@ savedir (dir, name_size)
   if (dirp == NULL)
     return NULL;
 
+  /* Be sure name_size is at least `1' so there's room for
+     the final NUL byte.  */
+  name_size += !name_size;
+
   name_space = (char *) malloc (name_size);
   if (name_space == NULL)
     {
diff --git a/gnu/usr.bin/grep/system.h b/gnu/usr.bin/grep/system.h
index a6966e4..3cd9b56 100644
--- a/gnu/usr.bin/grep/system.h
+++ b/gnu/usr.bin/grep/system.h
@@ -127,11 +127,20 @@ void free();
 #ifndef CHAR_BIT
 # define CHAR_BIT 8
 #endif
+/* The extra casts work around common compiler bugs.  */
+#define TYPE_SIGNED(t) (! ((t) 0 < (t) -1))
+#define TYPE_MINIMUM(t) ((t) (TYPE_SIGNED (t) \
+			      ? ~ (t) 0 << (sizeof (t) * CHAR_BIT - 1) \
+			      : (t) 0))
+#define TYPE_MAXIMUM(t) ((t) (~ (t) 0 - TYPE_MINIMUM (t)))
+#ifndef CHAR_MAX
+# define CHAR_MAX TYPE_MAXIMUM (char)
+#endif
 #ifndef INT_MAX
-# define INT_MAX 2147483647
+# define INT_MAX TYPE_MAXIMUM (int)
 #endif
 #ifndef UCHAR_MAX
-# define UCHAR_MAX 255
+# define UCHAR_MAX TYPE_MAXIMUM (unsigned char)
 #endif
 
 #if !defined(STDC_HEADERS) && defined(HAVE_STRING_H) && defined(HAVE_MEMORY_H)