annotate Modules/sre.h @ 79675:c0a2294de787 2.7

Issue #16199: Backport 2to3 typo fix from 3.2.
author Chris Jerdonek <chris.jerdonek@gmail.com>
date Thu, 11 Oct 2012 16:15:46 -0700
parents 2ab0394e6e49
children 10314c9b7c5a 83b2d07b475b
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
1 /*
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
2 * Secret Labs' Regular Expression Engine
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
3 *
13139
c2207d6c03a8 - fixed another split problem
Fredrik Lundh <fredrik@pythonware.com>
parents: 13136
diff changeset
4 * regular expression matching engine
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
5 *
18363
c0288670230e merged with pythonware's SRE 2.1.1 codebase
Fredrik Lundh <fredrik@pythonware.com>
parents: 18324
diff changeset
6 * Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved.
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
7 *
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
8 * See the _sre.c file for information on usage and redistribution.
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
9 */
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
10
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
11 #ifndef SRE_INCLUDED
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
12 #define SRE_INCLUDED
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
13
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
14 #include "sre_constants.h"
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
15
18324
3ba7a358ce02 use Py_UNICODE_WIDE instead of USE_UCS4_STORAGE and Py_UNICODE_SIZE
Fredrik Lundh <fredrik@pythonware.com>
parents: 18280
diff changeset
16 /* size of a code word (must be unsigned short or larger, and
3ba7a358ce02 use Py_UNICODE_WIDE instead of USE_UCS4_STORAGE and Py_UNICODE_SIZE
Fredrik Lundh <fredrik@pythonware.com>
parents: 18280
diff changeset
17 large enough to hold a Py_UNICODE character) */
3ba7a358ce02 use Py_UNICODE_WIDE instead of USE_UCS4_STORAGE and Py_UNICODE_SIZE
Fredrik Lundh <fredrik@pythonware.com>
parents: 18280
diff changeset
18 #ifdef Py_UNICODE_WIDE
32006
e2a0ef87d4d4 Fix _sre.CODESIZE on 64-bit machines in UCS-4 mode. Fixes #931848.
Martin v. Löwis <martin@v.loewis.de>
parents: 31525
diff changeset
19 #define SRE_CODE Py_UCS4
18280
0632dcd69ea3 experimental UCS-4 support: added USE_UCS4_STORAGE define to
Fredrik Lundh <fredrik@pythonware.com>
parents: 13829
diff changeset
20 #else
13117
26ec1b30efa9 towards 1.6b1
Fredrik Lundh <fredrik@pythonware.com>
parents: 12819
diff changeset
21 #define SRE_CODE unsigned short
18280
0632dcd69ea3 experimental UCS-4 support: added USE_UCS4_STORAGE define to
Fredrik Lundh <fredrik@pythonware.com>
parents: 13829
diff changeset
22 #endif
13117
26ec1b30efa9 towards 1.6b1
Fredrik Lundh <fredrik@pythonware.com>
parents: 12819
diff changeset
23
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
24 typedef struct {
13327
c155bccb7a22 - added lookbehind support (?<=pattern), (?<!pattern).
Fredrik Lundh <fredrik@pythonware.com>
parents: 13310
diff changeset
25 PyObject_VAR_HEAD
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
26 Py_ssize_t groups; /* must be first! */
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
27 PyObject* groupindex;
13310
3c35bf7b580b - experimental: added two new attributes to the match object:
Fredrik Lundh <fredrik@pythonware.com>
parents: 13308
diff changeset
28 PyObject* indexgroup;
12819
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
29 /* compatibility */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
30 PyObject* pattern; /* pattern source (or None) */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
31 int flags; /* flags used when compiling pattern source */
32160
aec9c98a47d2 Add weakref support to sockets and re pattern objects.
Raymond Hettinger <python@rcn.com>
parents: 32006
diff changeset
32 PyObject *weakreflist; /* List of weak references */
13327
c155bccb7a22 - added lookbehind support (?<=pattern), (?<!pattern).
Fredrik Lundh <fredrik@pythonware.com>
parents: 13310
diff changeset
33 /* pattern code */
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
34 Py_ssize_t codesize;
13327
c155bccb7a22 - added lookbehind support (?<=pattern), (?<!pattern).
Fredrik Lundh <fredrik@pythonware.com>
parents: 13310
diff changeset
35 SRE_CODE code[1];
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
36 } PatternObject;
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
37
13327
c155bccb7a22 - added lookbehind support (?<=pattern), (?<!pattern).
Fredrik Lundh <fredrik@pythonware.com>
parents: 13310
diff changeset
38 #define PatternObject_GetCode(o) (((PatternObject*)(o))->code)
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
39
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
40 typedef struct {
13327
c155bccb7a22 - added lookbehind support (?<=pattern), (?<!pattern).
Fredrik Lundh <fredrik@pythonware.com>
parents: 13310
diff changeset
41 PyObject_VAR_HEAD
18363
c0288670230e merged with pythonware's SRE 2.1.1 codebase
Fredrik Lundh <fredrik@pythonware.com>
parents: 18324
diff changeset
42 PyObject* string; /* link to the target string (must be first) */
13677
edb1a8e6b859 -- SRE 0.9.6 sync. this includes:
Fredrik Lundh <fredrik@pythonware.com>
parents: 13328
diff changeset
43 PyObject* regs; /* cached list of matching spans */
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
44 PatternObject* pattern; /* link to the regex (pattern) object */
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
45 Py_ssize_t pos, endpos; /* current target slice */
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
46 Py_ssize_t lastindex; /* last index marker seen by the engine (-1 if none) */
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
47 Py_ssize_t groups; /* number of groups (start/end marks) */
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
48 Py_ssize_t mark[1];
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
49 } MatchObject;
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
50
13117
26ec1b30efa9 towards 1.6b1
Fredrik Lundh <fredrik@pythonware.com>
parents: 12819
diff changeset
51 typedef unsigned int (*SRE_TOLOWER_HOOK)(unsigned int ch);
26ec1b30efa9 towards 1.6b1
Fredrik Lundh <fredrik@pythonware.com>
parents: 12819
diff changeset
52
13136
b6ed8fa2675c - fixed split
Fredrik Lundh <fredrik@pythonware.com>
parents: 13124
diff changeset
53 /* FIXME: <fl> shouldn't be a constant, really... */
b6ed8fa2675c - fixed split
Fredrik Lundh <fredrik@pythonware.com>
parents: 13124
diff changeset
54 #define SRE_MARK_SIZE 200
b6ed8fa2675c - fixed split
Fredrik Lundh <fredrik@pythonware.com>
parents: 13124
diff changeset
55
13789
4edd13eb759d SRE 0.9.8: passes the entire test suite
Fredrik Lundh <fredrik@pythonware.com>
parents: 13677
diff changeset
56 typedef struct SRE_REPEAT_T {
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
57 Py_ssize_t count;
13789
4edd13eb759d SRE 0.9.8: passes the entire test suite
Fredrik Lundh <fredrik@pythonware.com>
parents: 13677
diff changeset
58 SRE_CODE* pattern; /* points to REPEAT operator arguments */
30703
8282aa1f9343 Implemented non-recursive SRE matching.
Gustavo Niemeyer <gustavo@niemeyer.net>
parents: 22394
diff changeset
59 void* last_ptr; /* helper to check for infinite loops */
13789
4edd13eb759d SRE 0.9.8: passes the entire test suite
Fredrik Lundh <fredrik@pythonware.com>
parents: 13677
diff changeset
60 struct SRE_REPEAT_T *prev; /* points to previous repeat context */
4edd13eb759d SRE 0.9.8: passes the entire test suite
Fredrik Lundh <fredrik@pythonware.com>
parents: 13677
diff changeset
61 } SRE_REPEAT;
4edd13eb759d SRE 0.9.8: passes the entire test suite
Fredrik Lundh <fredrik@pythonware.com>
parents: 13677
diff changeset
62
12819
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
63 typedef struct {
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
64 /* string pointers */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
65 void* ptr; /* current position (also end of current slice) */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
66 void* beginning; /* start of original string */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
67 void* start; /* start of current slice */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
68 void* end; /* end of original string */
13677
edb1a8e6b859 -- SRE 0.9.6 sync. this includes:
Fredrik Lundh <fredrik@pythonware.com>
parents: 13328
diff changeset
69 /* attributes for the match object */
edb1a8e6b859 -- SRE 0.9.6 sync. this includes:
Fredrik Lundh <fredrik@pythonware.com>
parents: 13328
diff changeset
70 PyObject* string;
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
71 Py_ssize_t pos, endpos;
12819
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
72 /* character size */
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
73 int charsize;
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
74 /* registers */
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
75 Py_ssize_t lastindex;
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
76 Py_ssize_t lastmark;
13136
b6ed8fa2675c - fixed split
Fredrik Lundh <fredrik@pythonware.com>
parents: 13124
diff changeset
77 void* mark[SRE_MARK_SIZE];
13789
4edd13eb759d SRE 0.9.8: passes the entire test suite
Fredrik Lundh <fredrik@pythonware.com>
parents: 13677
diff changeset
78 /* dynamically allocated stuff */
30703
8282aa1f9343 Implemented non-recursive SRE matching.
Gustavo Niemeyer <gustavo@niemeyer.net>
parents: 22394
diff changeset
79 char* data_stack;
38770
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
80 size_t data_stack_size;
2ab0394e6e49 Impl ssize_t
Neal Norwitz <nnorwitz@gmail.com>
parents: 32160
diff changeset
81 size_t data_stack_base;
30703
8282aa1f9343 Implemented non-recursive SRE matching.
Gustavo Niemeyer <gustavo@niemeyer.net>
parents: 22394
diff changeset
82 /* current repeat context */
8282aa1f9343 Implemented non-recursive SRE matching.
Gustavo Niemeyer <gustavo@niemeyer.net>
parents: 22394
diff changeset
83 SRE_REPEAT *repeat;
13117
26ec1b30efa9 towards 1.6b1
Fredrik Lundh <fredrik@pythonware.com>
parents: 12819
diff changeset
84 /* hooks */
13124
5021db674019 - renamed "tolower" hook (it happened to work with
Fredrik Lundh <fredrik@pythonware.com>
parents: 13117
diff changeset
85 SRE_TOLOWER_HOOK lower;
12819
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
86 } SRE_STATE;
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
87
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
88 typedef struct {
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
89 PyObject_HEAD
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
90 PyObject* pattern;
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
91 SRE_STATE state;
13136
b6ed8fa2675c - fixed split
Fredrik Lundh <fredrik@pythonware.com>
parents: 13124
diff changeset
92 } ScannerObject;
12819
a24d9ad6786d Fredrik Lundh: here's the 96.6% version of SRE
Jeremy Hylton <jeremy@alum.mit.edu>
parents: 12176
diff changeset
93
12176
db83e63b384b Adding Fredrik Lundh's _sre.c module and its header files.
Guido van Rossum <guido@python.org>
parents:
diff changeset
94 #endif