annotate lib/regex.h @ 16846:a80d21de5373

system-quote, execute, spawn-pipe: Escape '?' on Windows. * lib/system-quote.c (SHELL_SPECIAL_CHARS, CMD_SPECIAL_CHARS): Add the '?' character. * lib/w32spawn.h (SHELL_SPECIAL_CHARS): Likewise. * tests/test-system-quote-main.c (check_all): Check also strings like "??????????". Reported by Eli Zaretskii <eliz@gnu.org>.
author Bruno Haible <bruno@clisp.org>
date Fri, 11 May 2012 01:39:04 +0200 (2012-05-10)
parents e011e0a7ab5a
children b6b08f30c630
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
1 /* Definitions for data structures and routines for the regular
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
2 expression library.
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
3 Copyright (C) 1985, 1989-1993, 1995-1998, 2000-2003, 2005-2012
14079
97fc9a21a8fb maint: update almost all copyright ranges to include 2011
Jim Meyering <meyering@redhat.com>
parents: 13647
diff changeset
4 Free Software Foundation, Inc.
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
5 This file is part of the GNU C Library.
1283
1630d40799c0 update from libc/copies
Jim Meyering <jim@meyering.net>
parents: 988
diff changeset
6
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
7 This program is free software; you can redistribute it and/or modify
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
8 it under the terms of the GNU General Public License as published by
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
9 the Free Software Foundation; either version 2, or (at your option)
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
10 any later version.
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
11
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
12 This program is distributed in the hope that it will be useful,
1283
1630d40799c0 update from libc/copies
Jim Meyering <jim@meyering.net>
parents: 988
diff changeset
13 but WITHOUT ANY WARRANTY; without even the implied warranty of
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
14 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
15 GNU General Public License for more details.
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
16
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
17 You should have received a copy of the GNU General Public License along
16366
bb182ee4a09d maint: replace FSF snail-mail addresses with URLs
Paul Eggert <eggert@cs.ucla.edu>
parents: 16361
diff changeset
18 with this program; if not, see <http://www.gnu.org/licenses/>. */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
19
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
20 #ifndef _REGEX_H
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
21 #define _REGEX_H 1
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
22
4304
70e590c93c06 update from libc
Karl Berry <karl@freefriends.org>
parents: 4020
diff changeset
23 #include <sys/types.h>
70e590c93c06 update from libc
Karl Berry <karl@freefriends.org>
parents: 4020
diff changeset
24
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
25 /* Allow the use in C++ code. */
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
26 #ifdef __cplusplus
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
27 extern "C" {
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
28 #endif
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
29
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
30 /* Define __USE_GNU to declare GNU extensions that violate the
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
31 POSIX name space rules. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
32 #ifdef _GNU_SOURCE
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
33 # define __USE_GNU 1
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
34 #endif
389
1abea4b3d539 update from FSF
Jim Meyering <jim@meyering.net>
parents: 14
diff changeset
35
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
36 #ifdef _REGEX_LARGE_OFFSETS
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
37
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
38 /* Use types and values that are wide enough to represent signed and
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
39 unsigned byte offsets in memory. This currently works only when
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
40 the regex code is used outside of the GNU C library; it is not yet
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
41 supported within glibc itself, and glibc users should not define
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
42 _REGEX_LARGE_OFFSETS. */
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
43
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
44 /* The type of nonnegative object indexes. Traditionally, GNU regex
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
45 uses 'int' for these. Code that uses __re_idx_t should work
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
46 regardless of whether the type is signed. */
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
47 typedef size_t __re_idx_t;
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
48
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
49 /* The type of object sizes. */
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
50 typedef size_t __re_size_t;
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
51
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
52 /* The type of object sizes, in places where the traditional code
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
53 uses unsigned long int. */
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
54 typedef size_t __re_long_size_t;
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
55
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
56 #else
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
57
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
58 /* The traditional GNU regex implementation mishandles strings longer
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
59 than INT_MAX. */
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
60 typedef int __re_idx_t;
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
61 typedef unsigned int __re_size_t;
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
62 typedef unsigned long int __re_long_size_t;
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
63
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
64 #endif
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
65
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
66 /* The following two types have to be signed and unsigned integer type
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
67 wide enough to hold a value of a pointer. For most ANSI compilers
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
68 ptrdiff_t and size_t should be likely OK. Still size of these two
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
69 types is 2 for Microsoft C. Ugh... */
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
70 typedef long int s_reg_t;
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
71 typedef unsigned long int active_reg_t;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
72
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
73 /* The following bits are used to determine the regexp syntax we
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
74 recognize. The set/not-set meanings are chosen so that Emacs syntax
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
75 remains the value 0. The bits are given in alphabetical order, and
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
76 the definitions shifted by one from the previous bit; thus, when we
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
77 add or remove a bit, only one other definition need change. */
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
78 typedef unsigned long int reg_syntax_t;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
79
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
80 #ifdef __USE_GNU
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
81 /* If this bit is not set, then \ inside a bracket expression is literal.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
82 If set, then such a \ quotes the following character. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
83 # define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
84
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
85 /* If this bit is not set, then + and ? are operators, and \+ and \? are
649
89f4c1937ac7 update FSF address in copyright and remove any trailing blanks
Jim Meyering <jim@meyering.net>
parents: 502
diff changeset
86 literals.
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
87 If set, then \+ and \? are operators and + and ? are literals. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
88 # define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
89
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
90 /* If this bit is set, then character classes are supported. They are:
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
91 [:alpha:], [:upper:], [:lower:], [:digit:], [:alnum:], [:xdigit:],
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
92 [:space:], [:print:], [:punct:], [:graph:], and [:cntrl:].
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
93 If not set, then character classes are not supported. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
94 # define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
95
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
96 /* If this bit is set, then ^ and $ are always anchors (outside bracket
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
97 expressions, of course).
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
98 If this bit is not set, then it depends:
13647
e5c0e28232bc regex documentation update from Reuben Thomas <rrt@sc3d.org>, 20 Aug 2010 12:04:39 +0100
Karl Berry <karl@freefriends.org>
parents: 12559
diff changeset
99 ^ is an anchor if it is at the beginning of a regular
e5c0e28232bc regex documentation update from Reuben Thomas <rrt@sc3d.org>, 20 Aug 2010 12:04:39 +0100
Karl Berry <karl@freefriends.org>
parents: 12559
diff changeset
100 expression or after an open-group or an alternation operator;
e5c0e28232bc regex documentation update from Reuben Thomas <rrt@sc3d.org>, 20 Aug 2010 12:04:39 +0100
Karl Berry <karl@freefriends.org>
parents: 12559
diff changeset
101 $ is an anchor if it is at the end of a regular expression, or
e5c0e28232bc regex documentation update from Reuben Thomas <rrt@sc3d.org>, 20 Aug 2010 12:04:39 +0100
Karl Berry <karl@freefriends.org>
parents: 12559
diff changeset
102 before a close-group or an alternation operator.
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
103
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
104 This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
105 POSIX draft 11.2 says that * etc. in leading positions is undefined.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
106 We already implemented a previous draft which made those constructs
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
107 invalid, though, so we haven't changed the code back. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
108 # define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
109
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
110 /* If this bit is set, then special characters are always special
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
111 regardless of where they are in the pattern.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
112 If this bit is not set, then special characters are special only in
649
89f4c1937ac7 update FSF address in copyright and remove any trailing blanks
Jim Meyering <jim@meyering.net>
parents: 502
diff changeset
113 some contexts; otherwise they are ordinary. Specifically,
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
114 * + ? and intervals are only special when not after the beginning,
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
115 open-group, or alternation operator. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
116 # define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
117
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
118 /* If this bit is set, then *, +, ?, and { cannot be first in an re or
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
119 immediately after an alternation or begin-group operator. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
120 # define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
121
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
122 /* If this bit is set, then . matches newline.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
123 If not set, then it doesn't. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
124 # define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
125
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
126 /* If this bit is set, then . doesn't match NUL.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
127 If not set, then it does. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
128 # define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
129
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
130 /* If this bit is set, nonmatching lists [^...] do not match newline.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
131 If not set, they do. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
132 # define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
133
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
134 /* If this bit is set, either \{...\} or {...} defines an
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
135 interval, depending on RE_NO_BK_BRACES.
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
136 If not set, \{, \}, {, and } are literals. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
137 # define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
138
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
139 /* If this bit is set, +, ? and | aren't recognized as operators.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
140 If not set, they are. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
141 # define RE_LIMITED_OPS (RE_INTERVALS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
142
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
143 /* If this bit is set, newline is an alternation operator.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
144 If not set, newline is literal. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
145 # define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
146
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
147 /* If this bit is set, then '{...}' defines an interval, and \{ and \}
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
148 are literals.
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
149 If not set, then '\{...\}' defines an interval. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
150 # define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
151
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
152 /* If this bit is set, (...) defines a group, and \( and \) are literals.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
153 If not set, \(...\) defines a group, and ( and ) are literals. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
154 # define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
155
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
156 /* If this bit is set, then \<digit> matches <digit>.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
157 If not set, then \<digit> is a back-reference. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
158 # define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
159
649
89f4c1937ac7 update FSF address in copyright and remove any trailing blanks
Jim Meyering <jim@meyering.net>
parents: 502
diff changeset
160 /* If this bit is set, then | is an alternation operator, and \| is literal.
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
161 If not set, then \| is an alternation operator, and | is literal. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
162 # define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
163
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
164 /* If this bit is set, then an ending range point collating higher
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
165 than the starting range point, as in [z-a], is invalid.
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
166 If not set, then when ending range point collates higher than the
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
167 starting range point, the range is ignored. */
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
168 # define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
169
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
170 /* If this bit is set, then an unmatched ) is ordinary.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
171 If not set, then an unmatched ) is invalid. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
172 # define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
173
389
1abea4b3d539 update from FSF
Jim Meyering <jim@meyering.net>
parents: 14
diff changeset
174 /* If this bit is set, succeed as soon as we match the whole pattern,
1abea4b3d539 update from FSF
Jim Meyering <jim@meyering.net>
parents: 14
diff changeset
175 without further backtracking. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
176 # define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1)
389
1abea4b3d539 update from FSF
Jim Meyering <jim@meyering.net>
parents: 14
diff changeset
177
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
178 /* If this bit is set, do not process the GNU regex operators.
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
179 If not set, then the GNU regex operators are recognized. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
180 # define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1)
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
181
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
182 /* If this bit is set, turn on internal regex debugging.
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
183 If not set, and debugging was on, turn it off.
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
184 This only works if regex.c is compiled -DDEBUG.
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
185 We define this bit always, so that all that's needed to turn on
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
186 debugging is to recompile regex.c; the calling code can always have
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
187 this bit set, and it won't affect anything in the normal case. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
188 # define RE_DEBUG (RE_NO_GNU_OPS << 1)
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
189
3227
255cd439f908 Update from GNU libc.
Jim Meyering <jim@meyering.net>
parents: 2940
diff changeset
190 /* If this bit is set, a syntactically invalid interval is treated as
255cd439f908 Update from GNU libc.
Jim Meyering <jim@meyering.net>
parents: 2940
diff changeset
191 a string of ordinary characters. For example, the ERE 'a{1' is
255cd439f908 Update from GNU libc.
Jim Meyering <jim@meyering.net>
parents: 2940
diff changeset
192 treated as 'a\{1'. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
193 # define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1)
3227
255cd439f908 Update from GNU libc.
Jim Meyering <jim@meyering.net>
parents: 2940
diff changeset
194
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
195 /* If this bit is set, then ignore case when matching.
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
196 If not set, then case is significant. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
197 # define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1)
4020
7158a1db8695 change license to gpl.
Karl Berry <karl@freefriends.org>
parents: 3684
diff changeset
198
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
199 /* This bit is used internally like RE_CONTEXT_INDEP_ANCHORS but only
5968
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
200 for ^, because it is difficult to scan the regex backwards to find
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
201 whether ^ should be special. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
202 # define RE_CARET_ANCHORS_HERE (RE_ICASE << 1)
5968
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
203
13647
e5c0e28232bc regex documentation update from Reuben Thomas <rrt@sc3d.org>, 20 Aug 2010 12:04:39 +0100
Karl Berry <karl@freefriends.org>
parents: 12559
diff changeset
204 /* If this bit is set, then \{ cannot be first in a regex or
e5c0e28232bc regex documentation update from Reuben Thomas <rrt@sc3d.org>, 20 Aug 2010 12:04:39 +0100
Karl Berry <karl@freefriends.org>
parents: 12559
diff changeset
205 immediately after an alternation, open-group or \} operator. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
206 # define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1)
5968
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
207
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
208 /* If this bit is set, then no_sub will be set to 1 during
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
209 re_compile_pattern. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
210 # define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1)
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
211 #endif
5968
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
212
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
213 /* This global variable defines the particular regexp syntax to use (for
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
214 some interfaces). When a regexp is compiled, the syntax used is
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
215 stored in the pattern buffer, so changing this does not affect
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
216 already-compiled regexps. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
217 extern reg_syntax_t re_syntax_options;
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
218
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
219 #ifdef __USE_GNU
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
220 /* Define combinations of the above bits for the standard possibilities.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
221 (The [[[ comments delimit what gets put into the Texinfo file, so
649
89f4c1937ac7 update FSF address in copyright and remove any trailing blanks
Jim Meyering <jim@meyering.net>
parents: 502
diff changeset
222 don't delete them!) */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
223 /* [[[begin syntaxes]]] */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
224 # define RE_SYNTAX_EMACS 0
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
225
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
226 # define RE_SYNTAX_AWK \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
227 (RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DOT_NOT_NULL \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
228 | RE_NO_BK_PARENS | RE_NO_BK_REFS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
229 | RE_NO_BK_VBAR | RE_NO_EMPTY_RANGES \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
230 | RE_DOT_NEWLINE | RE_CONTEXT_INDEP_ANCHORS \
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
231 | RE_CHAR_CLASSES \
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
232 | RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS)
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
233
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
234 # define RE_SYNTAX_GNU_AWK \
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
235 ((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
236 | RE_INVALID_INTERVAL_ORD) \
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
237 & ~(RE_DOT_NOT_NULL | RE_CONTEXT_INDEP_OPS \
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
238 | RE_CONTEXT_INVALID_OPS ))
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
239
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
240 # define RE_SYNTAX_POSIX_AWK \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
241 (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
242 | RE_INTERVALS | RE_NO_GNU_OPS \
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
243 | RE_INVALID_INTERVAL_ORD)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
244
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
245 # define RE_SYNTAX_GREP \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
246 (RE_BK_PLUS_QM | RE_CHAR_CLASSES \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
247 | RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
248 | RE_NEWLINE_ALT)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
249
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
250 # define RE_SYNTAX_EGREP \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
251 (RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
252 | RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
253 | RE_NEWLINE_ALT | RE_NO_BK_PARENS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
254 | RE_NO_BK_VBAR)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
255
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
256 # define RE_SYNTAX_POSIX_EGREP \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
257 (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
258 | RE_INVALID_INTERVAL_ORD)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
259
389
1abea4b3d539 update from FSF
Jim Meyering <jim@meyering.net>
parents: 14
diff changeset
260 /* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
261 # define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC
389
1abea4b3d539 update from FSF
Jim Meyering <jim@meyering.net>
parents: 14
diff changeset
262
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
263 # define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
264
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
265 /* Syntax bits common to both basic and extended POSIX regex syntax. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
266 # define _RE_SYNTAX_POSIX_COMMON \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
267 (RE_CHAR_CLASSES | RE_DOT_NEWLINE | RE_DOT_NOT_NULL \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
268 | RE_INTERVALS | RE_NO_EMPTY_RANGES)
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
269
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
270 # define RE_SYNTAX_POSIX_BASIC \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
271 (_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM | RE_CONTEXT_INVALID_DUP)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
272
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
273 /* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
274 RE_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
275 isn't minimal, since other operators, such as \`, aren't disabled. */
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
276 # define RE_SYNTAX_POSIX_MINIMAL_BASIC \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
277 (_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
278
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
279 # define RE_SYNTAX_POSIX_EXTENDED \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
280 (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
281 | RE_CONTEXT_INDEP_OPS | RE_NO_BK_BRACES \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
282 | RE_NO_BK_PARENS | RE_NO_BK_VBAR \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
283 | RE_CONTEXT_INVALID_OPS | RE_UNMATCHED_RIGHT_PAREN_ORD)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
284
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
285 /* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INDEP_OPS is
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
286 removed and RE_NO_BK_REFS is added. */
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
287 # define RE_SYNTAX_POSIX_MINIMAL_EXTENDED \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
288 (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
289 | RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
290 | RE_NO_BK_PARENS | RE_NO_BK_REFS \
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
291 | RE_NO_BK_VBAR | RE_UNMATCHED_RIGHT_PAREN_ORD)
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
292 /* [[[end syntaxes]]] */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
293
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
294 /* Maximum number of duplicates an interval can allow. POSIX-conforming
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
295 systems might define this in <limits.h>, but we want our
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
296 value, so remove any previous define. */
16650
8ad751eaba31 regex: allow inclusion of <regex.h> before <limits.h>
Paul Eggert <eggert@cs.ucla.edu>
parents: 16366
diff changeset
297 # ifdef _REGEX_INCLUDE_LIMITS_H
8ad751eaba31 regex: allow inclusion of <regex.h> before <limits.h>
Paul Eggert <eggert@cs.ucla.edu>
parents: 16366
diff changeset
298 # include <limits.h>
8ad751eaba31 regex: allow inclusion of <regex.h> before <limits.h>
Paul Eggert <eggert@cs.ucla.edu>
parents: 16366
diff changeset
299 # endif
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
300 # ifdef RE_DUP_MAX
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
301 # undef RE_DUP_MAX
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
302 # endif
6733
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
303
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
304 /* RE_DUP_MAX is 2**15 - 1 because an earlier implementation stored
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
305 the counter as a 2-byte signed integer. This is no longer true, so
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
306 RE_DUP_MAX could be increased to (INT_MAX / 10 - 1), or to
16705
54b750a813cb regex: diagnose too-large repeat counts in EREs
Paul Eggert <eggert@cs.ucla.edu>
parents: 16650
diff changeset
307 ((SIZE_MAX - 9) / 10) if _REGEX_LARGE_OFFSETS is defined.
6733
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
308 However, there would be a huge performance problem if someone
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
309 actually used a pattern like a\{214748363\}, so RE_DUP_MAX retains
1c9a307d93bd * regcomp.c (init_dfa): Don't use wchar_t or wctype_t if RE_ENABLE_I18N
Paul Eggert <eggert@cs.ucla.edu>
parents: 6726
diff changeset
310 its historical value. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
311 # define RE_DUP_MAX (0x7fff)
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
312 #endif
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
313
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
314
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
315 /* POSIX 'cflags' bits (i.e., information for 'regcomp'). */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
316
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
317 /* If this bit is set, then use extended regular expression syntax.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
318 If not set, then use basic regular expression syntax. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
319 #define REG_EXTENDED 1
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
320
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
321 /* If this bit is set, then ignore case when matching.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
322 If not set, then case is significant. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
323 #define REG_ICASE (1 << 1)
649
89f4c1937ac7 update FSF address in copyright and remove any trailing blanks
Jim Meyering <jim@meyering.net>
parents: 502
diff changeset
324
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
325 /* If this bit is set, then anchors do not match at newline
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
326 characters in the string.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
327 If not set, then anchors do match at newlines. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
328 #define REG_NEWLINE (1 << 2)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
329
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
330 /* If this bit is set, then report only success or fail in regexec.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
331 If not set, then returns differ between not matching and errors. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
332 #define REG_NOSUB (1 << 3)
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
333
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
334
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
335 /* POSIX 'eflags' bits (i.e., information for regexec). */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
336
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
337 /* If this bit is set, then the beginning-of-line operator doesn't match
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
338 the beginning of the string (presumably because it's not the
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
339 beginning of a line).
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
340 If not set, then the beginning-of-line operator does match the
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
341 beginning of the string. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
342 #define REG_NOTBOL 1
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
343
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
344 /* Like REG_NOTBOL, except for the end-of-line. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
345 #define REG_NOTEOL (1 << 1)
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
346
5968
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
347 /* Use PMATCH[0] to delimit the start and end of the search in the
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
348 buffer. */
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
349 #define REG_STARTEND (1 << 2)
541fed6ae301 * modules/regex (Files): Add lib/regex_internal.c,
Paul Eggert <eggert@cs.ucla.edu>
parents: 5851
diff changeset
350
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
351
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
352 /* If any error codes are removed, changed, or added, update the
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
353 '__re_error_msgid' table in regcomp.c. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
354
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
355 typedef enum
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
356 {
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
357 _REG_ENOSYS = -1, /* This will never happen for this implementation. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
358 _REG_NOERROR = 0, /* Success. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
359 _REG_NOMATCH, /* Didn't find a match (for regexec). */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
360
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
361 /* POSIX regcomp return error codes. (In the order listed in the
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
362 standard.) */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
363 _REG_BADPAT, /* Invalid pattern. */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
364 _REG_ECOLLATE, /* Invalid collating element. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
365 _REG_ECTYPE, /* Invalid character class name. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
366 _REG_EESCAPE, /* Trailing backslash. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
367 _REG_ESUBREG, /* Invalid back reference. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
368 _REG_EBRACK, /* Unmatched left bracket. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
369 _REG_EPAREN, /* Parenthesis imbalance. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
370 _REG_EBRACE, /* Unmatched \{. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
371 _REG_BADBR, /* Invalid contents of \{\}. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
372 _REG_ERANGE, /* Invalid range end. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
373 _REG_ESPACE, /* Ran out of memory. */
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
374 _REG_BADRPT, /* No preceding re for repetition op. */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
375
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
376 /* Error codes we've added. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
377 _REG_EEND, /* Premature end. */
16705
54b750a813cb regex: diagnose too-large repeat counts in EREs
Paul Eggert <eggert@cs.ucla.edu>
parents: 16650
diff changeset
378 _REG_ESIZE, /* Too large (e.g., repeat count too large). */
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
379 _REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
380 } reg_errcode_t;
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
381
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
382 #if defined _XOPEN_SOURCE || defined __USE_XOPEN2K
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
383 # define REG_ENOSYS _REG_ENOSYS
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
384 #endif
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
385 #define REG_NOERROR _REG_NOERROR
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
386 #define REG_NOMATCH _REG_NOMATCH
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
387 #define REG_BADPAT _REG_BADPAT
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
388 #define REG_ECOLLATE _REG_ECOLLATE
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
389 #define REG_ECTYPE _REG_ECTYPE
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
390 #define REG_EESCAPE _REG_EESCAPE
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
391 #define REG_ESUBREG _REG_ESUBREG
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
392 #define REG_EBRACK _REG_EBRACK
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
393 #define REG_EPAREN _REG_EPAREN
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
394 #define REG_EBRACE _REG_EBRACE
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
395 #define REG_BADBR _REG_BADBR
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
396 #define REG_ERANGE _REG_ERANGE
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
397 #define REG_ESPACE _REG_ESPACE
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
398 #define REG_BADRPT _REG_BADRPT
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
399 #define REG_EEND _REG_EEND
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
400 #define REG_ESIZE _REG_ESIZE
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
401 #define REG_ERPAREN _REG_ERPAREN
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
402
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
403 /* This data structure represents a compiled pattern. Before calling
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
404 the pattern compiler, the fields 'buffer', 'allocated', 'fastmap',
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
405 and 'translate' can be set. After the pattern has been compiled,
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
406 the fields 're_nsub', 'not_bol' and 'not_eol' are available. All
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
407 other fields are private to the regex routines. */
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
408
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
409 #ifndef RE_TRANSLATE_TYPE
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
410 # define __RE_TRANSLATE_TYPE unsigned char *
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
411 # ifdef __USE_GNU
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
412 # define RE_TRANSLATE_TYPE __RE_TRANSLATE_TYPE
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
413 # endif
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
414 #endif
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
415
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
416 #ifdef __USE_GNU
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
417 # define __REPB_PREFIX(name) name
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
418 #else
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
419 # define __REPB_PREFIX(name) __##name
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
420 #endif
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
421
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
422 struct re_pattern_buffer
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
423 {
16770
e011e0a7ab5a regex: remove unnecessary type punning
Paul Eggert <eggert@cs.ucla.edu>
parents: 16705
diff changeset
424 /* Space that holds the compiled pattern. The type
e011e0a7ab5a regex: remove unnecessary type punning
Paul Eggert <eggert@cs.ucla.edu>
parents: 16705
diff changeset
425 'struct re_dfa_t' is private and is not declared here. */
e011e0a7ab5a regex: remove unnecessary type punning
Paul Eggert <eggert@cs.ucla.edu>
parents: 16705
diff changeset
426 struct re_dfa_t *__REPB_PREFIX(buffer);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
427
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
428 /* Number of bytes to which 'buffer' points. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
429 __re_long_size_t __REPB_PREFIX(allocated);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
430
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
431 /* Number of bytes actually used in 'buffer'. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
432 __re_long_size_t __REPB_PREFIX(used);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
433
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
434 /* Syntax setting with which the pattern was compiled. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
435 reg_syntax_t __REPB_PREFIX(syntax);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
436
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
437 /* Pointer to a fastmap, if any, otherwise zero. re_search uses the
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
438 fastmap, if there is one, to skip over impossible starting points
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
439 for matches. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
440 char *__REPB_PREFIX(fastmap);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
441
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
442 /* Either a translate table to apply to all characters before
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
443 comparing them, or zero for no translation. The translation is
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
444 applied to a pattern when it is compiled and to a string when it
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
445 is matched. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
446 __RE_TRANSLATE_TYPE __REPB_PREFIX(translate);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
447
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
448 /* Number of subexpressions found by the compiler. */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
449 size_t re_nsub;
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
450
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
451 /* Zero if this pattern cannot match the empty string, one else.
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
452 Well, in truth it's used only in 're_search_2', to see whether or
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
453 not we should use the fastmap, so we don't set this absolutely
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
454 perfectly; see 're_compile_fastmap' (the "duplicate" case). */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
455 unsigned __REPB_PREFIX(can_be_null) : 1;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
456
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
457 /* If REGS_UNALLOCATED, allocate space in the 'regs' structure
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
458 for 'max (RE_NREGS, re_nsub + 1)' groups.
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
459 If REGS_REALLOCATE, reallocate space if necessary.
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
460 If REGS_FIXED, use what's there. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
461 #ifdef __USE_GNU
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
462 # define REGS_UNALLOCATED 0
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
463 # define REGS_REALLOCATE 1
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
464 # define REGS_FIXED 2
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
465 #endif
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
466 unsigned __REPB_PREFIX(regs_allocated) : 2;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
467
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
468 /* Set to zero when 're_compile_pattern' compiles a pattern; set to
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
469 one by 're_compile_fastmap' if it updates the fastmap. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
470 unsigned __REPB_PREFIX(fastmap_accurate) : 1;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
471
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
472 /* If set, 're_match_2' does not return information about
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
473 subexpressions. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
474 unsigned __REPB_PREFIX(no_sub) : 1;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
475
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
476 /* If set, a beginning-of-line anchor doesn't match at the beginning
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
477 of the string. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
478 unsigned __REPB_PREFIX(not_bol) : 1;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
479
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
480 /* Similarly for an end-of-line anchor. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
481 unsigned __REPB_PREFIX(not_eol) : 1;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
482
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
483 /* If true, an anchor at a newline matches. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
484 unsigned __REPB_PREFIX(newline_anchor) : 1;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
485 };
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
486
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
487 typedef struct re_pattern_buffer regex_t;
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
488
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
489 /* Type for byte offsets within the string. POSIX mandates this. */
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
490 #ifdef _REGEX_LARGE_OFFSETS
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
491 /* POSIX 1003.1-2008 requires that regoff_t be at least as wide as
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
492 ptrdiff_t and ssize_t. We don't know of any hosts where ptrdiff_t
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
493 is wider than ssize_t, so ssize_t is safe. */
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
494 typedef ssize_t regoff_t;
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
495 #else
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
496 /* The traditional GNU regex implementation mishandles strings longer
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
497 than INT_MAX. */
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
498 typedef int regoff_t;
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
499 #endif
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
500
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
501
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
502 #ifdef __USE_GNU
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
503 /* This is the structure we store register match data in. See
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
504 regex.texinfo for a full description of what registers match. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
505 struct re_registers
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
506 {
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
507 __re_size_t num_regs;
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
508 regoff_t *start;
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
509 regoff_t *end;
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
510 };
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
511
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
512
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
513 /* If 'regs_allocated' is REGS_UNALLOCATED in the pattern buffer,
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
514 're_match_2' returns information about at least this many registers
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
515 the first time a 'regs' structure is passed. */
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
516 # ifndef RE_NREGS
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
517 # define RE_NREGS 30
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
518 # endif
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
519 #endif
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
520
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
521
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
522 /* POSIX specification for registers. Aside from the different names than
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
523 're_registers', POSIX uses an array of structures, instead of a
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
524 structure of arrays. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
525 typedef struct
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
526 {
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
527 regoff_t rm_so; /* Byte offset from string's start to substring's start. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
528 regoff_t rm_eo; /* Byte offset from string's start to substring's end. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
529 } regmatch_t;
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
530
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
531 /* Declarations for routines. */
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
532
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
533 #ifdef __USE_GNU
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
534 /* Sets the current default syntax to SYNTAX, and return the old syntax.
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
535 You can also simply assign to the 're_syntax_options' variable. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
536 extern reg_syntax_t re_set_syntax (reg_syntax_t __syntax);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
537
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
538 /* Compile the regular expression PATTERN, with length LENGTH
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
539 and syntax given by the global 're_syntax_options', into the buffer
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
540 BUFFER. Return NULL if successful, and an error string if not.
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
541
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
542 To free the allocated storage, you must call 'regfree' on BUFFER.
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
543 Note that the translate table must either have been initialised by
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
544 'regcomp', with a malloc'ed value, or set to NULL before calling
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
545 'regfree'. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
546 extern const char *re_compile_pattern (const char *__pattern, size_t __length,
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
547 struct re_pattern_buffer *__buffer);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
548
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
549
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
550 /* Compile a fastmap for the compiled pattern in BUFFER; used to
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
551 accelerate searches. Return 0 if successful and -2 if was an
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
552 internal error. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
553 extern int re_compile_fastmap (struct re_pattern_buffer *__buffer);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
554
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
555
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
556 /* Search in the string STRING (with length LENGTH) for the pattern
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
557 compiled into BUFFER. Start searching at position START, for RANGE
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
558 characters. Return the starting position of the match, -1 for no
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
559 match, or -2 for an internal error. Also return register
6726
af9abbcedfbd Merge regex changes from libc, removing some of our
Paul Eggert <eggert@cs.ucla.edu>
parents: 6707
diff changeset
560 information in REGS (if REGS and BUFFER->no_sub are nonzero). */
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
561 extern regoff_t re_search (struct re_pattern_buffer *__buffer,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
562 const char *__string, __re_idx_t __length,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
563 __re_idx_t __start, regoff_t __range,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
564 struct re_registers *__regs);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
565
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
566
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
567 /* Like 're_search', but search in the concatenation of STRING1 and
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
568 STRING2. Also, stop searching at index START + STOP. */
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
569 extern regoff_t re_search_2 (struct re_pattern_buffer *__buffer,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
570 const char *__string1, __re_idx_t __length1,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
571 const char *__string2, __re_idx_t __length2,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
572 __re_idx_t __start, regoff_t __range,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
573 struct re_registers *__regs,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
574 __re_idx_t __stop);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
575
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
576
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
577 /* Like 're_search', but return how many characters in STRING the regexp
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
578 in BUFFER matched, starting at position START. */
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
579 extern regoff_t re_match (struct re_pattern_buffer *__buffer,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
580 const char *__string, __re_idx_t __length,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
581 __re_idx_t __start, struct re_registers *__regs);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
582
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
583
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
584 /* Relates to 're_match' as 're_search_2' relates to 're_search'. */
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
585 extern regoff_t re_match_2 (struct re_pattern_buffer *__buffer,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
586 const char *__string1, __re_idx_t __length1,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
587 const char *__string2, __re_idx_t __length2,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
588 __re_idx_t __start, struct re_registers *__regs,
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
589 __re_idx_t __stop);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
590
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
591
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
592 /* Set REGS to hold NUM_REGS registers, storing them in STARTS and
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
593 ENDS. Subsequent matches using BUFFER and REGS will use this memory
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
594 for recording register information. STARTS and ENDS must be
16235
18a38c9615f0 In commentary, do not use ` to quote.
Paul Eggert <eggert@cs.ucla.edu>
parents: 16201
diff changeset
595 allocated with malloc, and must each be at least 'NUM_REGS * sizeof
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
596 (regoff_t)' bytes long.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
597
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
598 If NUM_REGS == 0, then subsequent matches should allocate their own
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
599 register data.
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
600
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
601 Unless this function is called, the first search or match using
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
602 BUFFER will allocate its own register data, without
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
603 freeing the old data. */
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
604 extern void re_set_registers (struct re_pattern_buffer *__buffer,
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
605 struct re_registers *__regs,
6184
f1728546eca4 On 64-bit hosts (where size_t is 64 bits and int is 32 bits), the
Paul Eggert <eggert@cs.ucla.edu>
parents: 6104
diff changeset
606 __re_size_t __num_regs,
6099
cfc20c5f63f0 * config/srclist.txt:
Paul Eggert <eggert@cs.ucla.edu>
parents: 6086
diff changeset
607 regoff_t *__starts, regoff_t *__ends);
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
608 #endif /* Use GNU */
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
609
16361
ab59b5080051 regex: merge glibc changes
Paul Eggert <eggert@cs.ucla.edu>
parents: 16235
diff changeset
610 #if defined _REGEX_RE_COMP || (defined _LIBC && defined __USE_BSD)
1283
1630d40799c0 update from libc/copies
Jim Meyering <jim@meyering.net>
parents: 988
diff changeset
611 # ifndef _CRAY
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
612 /* 4.2 bsd compatibility. */
6076
e2dd51f6e259 * config/srclist.txt: Add glibc bugs 1220, 1221, 1222.
Paul Eggert <eggert@cs.ucla.edu>
parents: 6059
diff changeset
613 extern char *re_comp (const char *);
e2dd51f6e259 * config/srclist.txt: Add glibc bugs 1220, 1221, 1222.
Paul Eggert <eggert@cs.ucla.edu>
parents: 6059
diff changeset
614 extern int re_exec (const char *);
1283
1630d40799c0 update from libc/copies
Jim Meyering <jim@meyering.net>
parents: 988
diff changeset
615 # endif
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
616 #endif
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
617
2927
9065aac1a5e8 Update from libc.
Jim Meyering <jim@meyering.net>
parents: 2472
diff changeset
618 /* GCC 2.95 and later have "__restrict"; C99 compilers have
8045
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
619 "restrict", and "configure" may have defined "restrict".
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
620 Other compilers use __restrict, __restrict__, and _Restrict, and
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
621 'configure' might #define 'restrict' to those words, so pick a
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
622 different name. */
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
623 #ifndef _Restrict_
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
624 # if 199901L <= __STDC_VERSION__
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
625 # define _Restrict_ restrict
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
626 # elif 2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
627 # define _Restrict_ __restrict
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
628 # else
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
629 # define _Restrict_
2927
9065aac1a5e8 Update from libc.
Jim Meyering <jim@meyering.net>
parents: 2472
diff changeset
630 # endif
2940
c7143052abca (__restrict_arr): Move definition out of #ifndef block.
Jim Meyering <jim@meyering.net>
parents: 2927
diff changeset
631 #endif
7689
b4806b1ec9e4 Fix some incompatibilities with gcc -ansi -pedantic.
Paul Eggert <eggert@cs.ucla.edu>
parents: 7110
diff changeset
632 /* gcc 3.1 and up support the [restrict] syntax. Don't trust
b4806b1ec9e4 Fix some incompatibilities with gcc -ansi -pedantic.
Paul Eggert <eggert@cs.ucla.edu>
parents: 7110
diff changeset
633 sys/cdefs.h's definition of __restrict_arr, though, as it
b4806b1ec9e4 Fix some incompatibilities with gcc -ansi -pedantic.
Paul Eggert <eggert@cs.ucla.edu>
parents: 7110
diff changeset
634 mishandles gcc -ansi -pedantic. */
8045
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
635 #ifndef _Restrict_arr_
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
636 # if ((199901L <= __STDC_VERSION__ \
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
637 || ((3 < __GNUC__ || (3 == __GNUC__ && 1 <= __GNUC_MINOR__)) \
15962
cfa1d5dbe78c Support for old NeXTstep 3.3 gcc.
Daniel Richard G <skunk@iskunk.org>
parents: 14079
diff changeset
638 && !defined __STRICT_ANSI__)) \
8045
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
639 && !defined __GNUG__)
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
640 # define _Restrict_arr_ _Restrict_
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
641 # else
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
642 # define _Restrict_arr_
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
643 # endif
3684
c8ed84e015e6 (__restrict_arr): Update from libc.
Jim Meyering <jim@meyering.net>
parents: 3336
diff changeset
644 #endif
2927
9065aac1a5e8 Update from libc.
Jim Meyering <jim@meyering.net>
parents: 2472
diff changeset
645
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
646 /* POSIX compatibility. */
8045
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
647 extern int regcomp (regex_t *_Restrict_ __preg,
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
648 const char *_Restrict_ __pattern,
6076
e2dd51f6e259 * config/srclist.txt: Add glibc bugs 1220, 1221, 1222.
Paul Eggert <eggert@cs.ucla.edu>
parents: 6059
diff changeset
649 int __cflags);
1466
6edda82f9fd9 update from glibc
Jim Meyering <jim@meyering.net>
parents: 1283
diff changeset
650
8045
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
651 extern int regexec (const regex_t *_Restrict_ __preg,
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
652 const char *_Restrict_ __string, size_t __nmatch,
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
653 regmatch_t __pmatch[_Restrict_arr_],
6076
e2dd51f6e259 * config/srclist.txt: Add glibc bugs 1220, 1221, 1222.
Paul Eggert <eggert@cs.ucla.edu>
parents: 6059
diff changeset
654 int __eflags);
1466
6edda82f9fd9 update from glibc
Jim Meyering <jim@meyering.net>
parents: 1283
diff changeset
655
8045
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
656 extern size_t regerror (int __errcode, const regex_t *_Restrict_ __preg,
7dcf8a1f2f5e * lib/regex.h (_Restrict_): Renamed from __restrict, to avoid
Paul Eggert <eggert@cs.ucla.edu>
parents: 7692
diff changeset
657 char *_Restrict_ __errbuf, size_t __errbuf_size);
1466
6edda82f9fd9 update from glibc
Jim Meyering <jim@meyering.net>
parents: 1283
diff changeset
658
6076
e2dd51f6e259 * config/srclist.txt: Add glibc bugs 1220, 1221, 1222.
Paul Eggert <eggert@cs.ucla.edu>
parents: 6059
diff changeset
659 extern void regfree (regex_t *__preg);
14
3eda3e12f7ba Initial revision
Jim Meyering <jim@meyering.net>
parents:
diff changeset
660
988
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
661
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
662 #ifdef __cplusplus
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
663 }
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
664 #endif /* C++ */
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
665
ba13cef00d11 replace with new version from libc
Jim Meyering <jim@meyering.net>
parents: 649
diff changeset
666 #endif /* regex.h */