From 32eddc1bbc47479a3639b9191ffc82a52903c5f4 Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Sat, 23 Nov 2013 23:20:30 +0200 Subject: Issue #16203: Add re.fullmatch() function and regex.fullmatch() method, which anchor the pattern at both ends of the string to match. Original patch by Matthew Barnett. --- Doc/library/re.rst | 30 +++++++++++++++++++- Doc/whatsnew/3.4.rst | 7 +++++ Lib/re.py | 28 +++++++++++-------- Lib/test/test_re.py | 30 ++++++++++++++++++++ Misc/NEWS | 4 +++ Modules/_sre.c | 77 ++++++++++++++++++++++++++++++++++++++++------------ Modules/sre.h | 1 + Modules/sre_lib.h | 28 ++++++++++++++----- 8 files changed, 168 insertions(+), 37 deletions(-) diff --git a/Doc/library/re.rst b/Doc/library/re.rst index 220ce86..fa6a9ce 100644 --- a/Doc/library/re.rst +++ b/Doc/library/re.rst @@ -481,7 +481,7 @@ form. .. note:: The compiled versions of the most recent patterns passed to - :func:`re.match`, :func:`re.search` or :func:`re.compile` are cached, so + :func:`re.compile` and the module-level matching functions are cached, so programs that use only a few regular expressions at a time needn't worry about compiling regular expressions. @@ -584,6 +584,16 @@ form. instead (see also :ref:`search-vs-match`). +.. function:: fullmatch(pattern, string, flags=0) + + If the whole *string* matches the regular expression *pattern*, return a + corresponding :ref:`match object `. Return ``None`` if the + string does not match the pattern; note that this is different from a + zero-length match. + + .. versionadded:: 3.4 + + .. function:: split(pattern, string, maxsplit=0, flags=0) Split *string* by the occurrences of *pattern*. If capturing parentheses are @@ -778,6 +788,24 @@ attributes: :meth:`~regex.search` instead (see also :ref:`search-vs-match`). +.. method:: regex.fullmatch(string[, pos[, endpos]]) + + If the whole *string* matches this regular expression, return a corresponding + :ref:`match object `. Return ``None`` if the string does not + match the pattern; note that this is different from a zero-length match. + + The optional *pos* and *endpos* parameters have the same meaning as for the + :meth:`~regex.search` method. + + >>> pattern = re.compile("o[gh]") + >>> pattern.fullmatch("dog") # No match as "o" is not at the start of "dog". + >>> pattern.fullmatch("ogre") # No match as not the full string matches. + >>> pattern.fullmatch("doggie", 1, 3) # Matches within given limits. + <_sre.SRE_Match object at ...> + + .. versionadded:: 3.4 + + .. method:: regex.split(string, maxsplit=0) Identical to the :func:`split` function, using the compiled pattern. diff --git a/Doc/whatsnew/3.4.rst b/Doc/whatsnew/3.4.rst index 31f7cbd..435d582 100644 --- a/Doc/whatsnew/3.4.rst +++ b/Doc/whatsnew/3.4.rst @@ -647,6 +647,13 @@ behaviours has been improved substantially by the underlying changes in the :mod:`inspect` module. +re +-- + +Added :func:`re.fullmatch` function and :meth:`regex.fullmatch` method, +which anchor the pattern at both ends of the string to match. +(Contributed by Matthew Barnett in :issue:`16203`.) + resource -------- diff --git a/Lib/re.py b/Lib/re.py index b41aab0..77f5e3f 100644 --- a/Lib/re.py +++ b/Lib/re.py @@ -85,16 +85,17 @@ resulting RE will match the second character. \\ Matches a literal backslash. This module exports the following functions: - match Match a regular expression pattern to the beginning of a string. - search Search a string for the presence of a pattern. - sub Substitute occurrences of a pattern found in a string. - subn Same as sub, but also return the number of substitutions made. - split Split a string by the occurrences of a pattern. - findall Find all occurrences of a pattern in a string. - finditer Return an iterator yielding a match object for each match. - compile Compile a pattern into a RegexObject. - purge Clear the regular expression cache. - escape Backslash all non-alphanumerics in a string. + match Match a regular expression pattern to the beginning of a string. + fullmatch Match a regular expression pattern to all of a string. + search Search a string for the presence of a pattern. + sub Substitute occurrences of a pattern found in a string. + subn Same as sub, but also return the number of substitutions made. + split Split a string by the occurrences of a pattern. + findall Find all occurrences of a pattern in a string. + finditer Return an iterator yielding a match object for each match. + compile Compile a pattern into a RegexObject. + purge Clear the regular expression cache. + escape Backslash all non-alphanumerics in a string. Some of the functions in this module takes flags as optional parameters: A ASCII For string patterns, make \w, \W, \b, \B, \d, \D @@ -123,7 +124,7 @@ import sre_compile import sre_parse # public symbols -__all__ = [ "match", "search", "sub", "subn", "split", "findall", +__all__ = [ "match", "fullmatch", "search", "sub", "subn", "split", "findall", "compile", "purge", "template", "escape", "A", "I", "L", "M", "S", "X", "U", "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE", "UNICODE", "error" ] @@ -154,6 +155,11 @@ def match(pattern, string, flags=0): a match object, or None if no match was found.""" return _compile(pattern, flags).match(string) +def fullmatch(pattern, string, flags=0): + """Try to apply the pattern to all of the string, returning + a match object, or None if no match was found.""" + return _compile(pattern, flags).fullmatch(string) + def search(pattern, string, flags=0): """Scan through string looking for a match to the pattern, returning a match object, or None if no match was found.""" diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py index 1ef68b8..a4e11c6 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -349,6 +349,36 @@ class ReTests(unittest.TestCase): (None, 'b', None)) self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c')) + def test_re_fullmatch(self): + # Issue 16203: Proposal: add re.fullmatch() method. + self.assertEqual(re.fullmatch(r"a", "a").span(), (0, 1)) + for string in "ab", S("ab"): + self.assertEqual(re.fullmatch(r"a|ab", string).span(), (0, 2)) + for string in b"ab", B(b"ab"), bytearray(b"ab"), memoryview(b"ab"): + self.assertEqual(re.fullmatch(br"a|ab", string).span(), (0, 2)) + for a, b in "\xe0\xdf", "\u0430\u0431", "\U0001d49c\U0001d49e": + r = r"%s|%s" % (a, a + b) + self.assertEqual(re.fullmatch(r, a + b).span(), (0, 2)) + self.assertEqual(re.fullmatch(r".*?$", "abc").span(), (0, 3)) + self.assertEqual(re.fullmatch(r".*?", "abc").span(), (0, 3)) + self.assertEqual(re.fullmatch(r"a.*?b", "ab").span(), (0, 2)) + self.assertEqual(re.fullmatch(r"a.*?b", "abb").span(), (0, 3)) + self.assertEqual(re.fullmatch(r"a.*?b", "axxb").span(), (0, 4)) + self.assertIsNone(re.fullmatch(r"a+", "ab")) + self.assertIsNone(re.fullmatch(r"abc$", "abc\n")) + self.assertIsNone(re.fullmatch(r"abc\Z", "abc\n")) + self.assertIsNone(re.fullmatch(r"(?m)abc$", "abc\n")) + self.assertEqual(re.fullmatch(r"ab(?=c)cd", "abcd").span(), (0, 4)) + self.assertEqual(re.fullmatch(r"ab(?<=b)cd", "abcd").span(), (0, 4)) + self.assertEqual(re.fullmatch(r"(?=a|ab)ab", "ab").span(), (0, 2)) + + self.assertEqual( + re.compile(r"bc").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3)) + self.assertEqual( + re.compile(r".*?$").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3)) + self.assertEqual( + re.compile(r".*?").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3)) + def test_re_groupref_exists(self): self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(), ('(', 'a')) diff --git a/Misc/NEWS b/Misc/NEWS index a2db433..22d2c77 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -68,6 +68,10 @@ Core and Builtins Library ------- +- Issue #16203: Add re.fullmatch() function and regex.fullmatch() method, + which anchor the pattern at both ends of the string to match. + Original patch by Matthew Barnett. + - Issue #13592: Improved the repr for regular expression pattern objects. Based on patch by Hugo Lopes Tavares. diff --git a/Modules/_sre.c b/Modules/_sre.c index 3a92db9..55a86c2 100644 --- a/Modules/_sre.c +++ b/Modules/_sre.c @@ -4,24 +4,25 @@ * regular expression matching engine * * partial history: - * 1999-10-24 fl created (based on existing template matcher code) - * 2000-03-06 fl first alpha, sort of - * 2000-08-01 fl fixes for 1.6b1 - * 2000-08-07 fl use PyOS_CheckStack() if available - * 2000-09-20 fl added expand method - * 2001-03-20 fl lots of fixes for 2.1b2 - * 2001-04-15 fl export copyright as Python attribute, not global - * 2001-04-28 fl added __copy__ methods (work in progress) - * 2001-05-14 fl fixes for 1.5.2 compatibility - * 2001-07-01 fl added BIGCHARSET support (from Martin von Loewis) - * 2001-10-18 fl fixed group reset issue (from Matthew Mueller) - * 2001-10-20 fl added split primitive; reenable unicode for 1.6/2.0/2.1 - * 2001-10-21 fl added sub/subn primitive - * 2001-10-24 fl added finditer primitive (for 2.2 only) - * 2001-12-07 fl fixed memory leak in sub/subn (Guido van Rossum) - * 2002-11-09 fl fixed empty sub/subn return type - * 2003-04-18 mvl fully support 4-byte codes - * 2003-10-17 gn implemented non recursive scheme + * 1999-10-24 fl created (based on existing template matcher code) + * 2000-03-06 fl first alpha, sort of + * 2000-08-01 fl fixes for 1.6b1 + * 2000-08-07 fl use PyOS_CheckStack() if available + * 2000-09-20 fl added expand method + * 2001-03-20 fl lots of fixes for 2.1b2 + * 2001-04-15 fl export copyright as Python attribute, not global + * 2001-04-28 fl added __copy__ methods (work in progress) + * 2001-05-14 fl fixes for 1.5.2 compatibility + * 2001-07-01 fl added BIGCHARSET support (from Martin von Loewis) + * 2001-10-18 fl fixed group reset issue (from Matthew Mueller) + * 2001-10-20 fl added split primitive; reenable unicode for 1.6/2.0/2.1 + * 2001-10-21 fl added sub/subn primitive + * 2001-10-24 fl added finditer primitive (for 2.2 only) + * 2001-12-07 fl fixed memory leak in sub/subn (Guido van Rossum) + * 2002-11-09 fl fixed empty sub/subn return type + * 2003-04-18 mvl fully support 4-byte codes + * 2003-10-17 gn implemented non recursive scheme + * 2013-02-04 mrab added fullmatch primitive * * Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved. * @@ -559,6 +560,40 @@ pattern_match(PatternObject* self, PyObject* args, PyObject* kw) } static PyObject* +pattern_fullmatch(PatternObject* self, PyObject* args, PyObject* kw) +{ + SRE_STATE state; + Py_ssize_t status; + + PyObject* string; + Py_ssize_t start = 0; + Py_ssize_t end = PY_SSIZE_T_MAX; + static char* kwlist[] = { "pattern", "pos", "endpos", NULL }; + if (!PyArg_ParseTupleAndKeywords(args, kw, "O|nn:fullmatch", kwlist, + &string, &start, &end)) + return NULL; + + string = state_init(&state, self, string, start, end); + if (!string) + return NULL; + + state.match_all = 1; + state.ptr = state.start; + + TRACE(("|%p|%p|FULLMATCH\n", PatternObject_GetCode(self), state.ptr)); + + status = sre_match(&state, PatternObject_GetCode(self)); + + TRACE(("|%p|%p|END\n", PatternObject_GetCode(self), state.ptr)); + if (PyErr_Occurred()) + return NULL; + + state_fini(&state); + + return pattern_new_match(self, &state, status); +} + +static PyObject* pattern_search(PatternObject* self, PyObject* args, PyObject* kw) { SRE_STATE state; @@ -1223,6 +1258,10 @@ PyDoc_STRVAR(pattern_match_doc, "match(string[, pos[, endpos]]) -> match object or None.\n\ Matches zero or more characters at the beginning of the string"); +PyDoc_STRVAR(pattern_fullmatch_doc, +"fullmatch(string[, pos[, endpos]]) -> match object or None.\n\ + Matches against all of the string"); + PyDoc_STRVAR(pattern_search_doc, "search(string[, pos[, endpos]]) -> match object or None.\n\ Scan through string looking for a match, and return a corresponding\n\ @@ -1258,6 +1297,8 @@ PyDoc_STRVAR(pattern_doc, "Compiled regular expression objects"); static PyMethodDef pattern_methods[] = { {"match", (PyCFunction) pattern_match, METH_VARARGS|METH_KEYWORDS, pattern_match_doc}, + {"fullmatch", (PyCFunction) pattern_fullmatch, METH_VARARGS|METH_KEYWORDS, + pattern_fullmatch_doc}, {"search", (PyCFunction) pattern_search, METH_VARARGS|METH_KEYWORDS, pattern_search_doc}, {"sub", (PyCFunction) pattern_sub, METH_VARARGS|METH_KEYWORDS, diff --git a/Modules/sre.h b/Modules/sre.h index 42fe28d..621e2d8 100644 --- a/Modules/sre.h +++ b/Modules/sre.h @@ -86,6 +86,7 @@ typedef struct { SRE_REPEAT *repeat; /* hooks */ SRE_TOLOWER_HOOK lower; + int match_all; } SRE_STATE; typedef struct { diff --git a/Modules/sre_lib.h b/Modules/sre_lib.h index 214c22a..df86697 100644 --- a/Modules/sre_lib.h +++ b/Modules/sre_lib.h @@ -454,17 +454,24 @@ do { \ #define JUMP_ASSERT 12 #define JUMP_ASSERT_NOT 13 -#define DO_JUMP(jumpvalue, jumplabel, nextpattern) \ +#define DO_JUMPX(jumpvalue, jumplabel, nextpattern, matchall) \ DATA_ALLOC(SRE(match_context), nextctx); \ nextctx->last_ctx_pos = ctx_pos; \ nextctx->jump = jumpvalue; \ nextctx->pattern = nextpattern; \ + nextctx->match_all = matchall; \ ctx_pos = alloc_pos; \ ctx = nextctx; \ goto entrance; \ jumplabel: \ while (0) /* gcc doesn't like labels at end of scopes */ \ +#define DO_JUMP(jumpvalue, jumplabel, nextpattern) \ + DO_JUMPX(jumpvalue, jumplabel, nextpattern, ctx->match_all) + +#define DO_JUMP0(jumpvalue, jumplabel, nextpattern) \ + DO_JUMPX(jumpvalue, jumplabel, nextpattern, 0) + typedef struct { Py_ssize_t last_ctx_pos; Py_ssize_t jump; @@ -477,6 +484,7 @@ typedef struct { SRE_CODE chr; SRE_REPEAT* rep; } u; + int match_all; } SRE(match_context); /* check if string matches the given pattern. returns <0 for @@ -499,6 +507,7 @@ SRE(match)(SRE_STATE* state, SRE_CODE* pattern) ctx->last_ctx_pos = -1; ctx->jump = JUMP_NONE; ctx->pattern = pattern; + ctx->match_all = state->match_all; ctx_pos = alloc_pos; entrance: @@ -571,8 +580,11 @@ entrance: case SRE_OP_SUCCESS: /* end of pattern */ TRACE(("|%p|%p|SUCCESS\n", ctx->pattern, ctx->ptr)); - state->ptr = ctx->ptr; - RETURN_SUCCESS; + if (!ctx->match_all || ctx->ptr == state->end) { + state->ptr = ctx->ptr; + RETURN_SUCCESS; + } + RETURN_FAILURE; case SRE_OP_AT: /* match at given position */ @@ -726,7 +738,8 @@ entrance: if (ctx->count < (Py_ssize_t) ctx->pattern[1]) RETURN_FAILURE; - if (ctx->pattern[ctx->pattern[0]] == SRE_OP_SUCCESS) { + if (ctx->pattern[ctx->pattern[0]] == SRE_OP_SUCCESS && + (!ctx->match_all || ctx->ptr == state->end)) { /* tail is empty. we're finished */ state->ptr = ctx->ptr; RETURN_SUCCESS; @@ -810,7 +823,8 @@ entrance: ctx->ptr += ctx->count; } - if (ctx->pattern[ctx->pattern[0]] == SRE_OP_SUCCESS) { + if (ctx->pattern[ctx->pattern[0]] == SRE_OP_SUCCESS && + (!ctx->match_all || ctx->ptr == state->end)) { /* tail is empty. we're finished */ state->ptr = ctx->ptr; RETURN_SUCCESS; @@ -1082,7 +1096,7 @@ entrance: state->ptr = ctx->ptr - ctx->pattern[1]; if (state->ptr < state->beginning) RETURN_FAILURE; - DO_JUMP(JUMP_ASSERT, jump_assert, ctx->pattern+2); + DO_JUMP0(JUMP_ASSERT, jump_assert, ctx->pattern+2); RETURN_ON_FAILURE(ret); ctx->pattern += ctx->pattern[0]; break; @@ -1094,7 +1108,7 @@ entrance: ctx->ptr, ctx->pattern[1])); state->ptr = ctx->ptr - ctx->pattern[1]; if (state->ptr >= state->beginning) { - DO_JUMP(JUMP_ASSERT_NOT, jump_assert_not, ctx->pattern+2); + DO_JUMP0(JUMP_ASSERT_NOT, jump_assert_not, ctx->pattern+2); if (ret) { RETURN_ON_ERROR(ret); RETURN_FAILURE; -- cgit v0.12