Issue #1515: Enable use of deepcopy() with instance methods. Patch by Robert Collins.
[python.git] / Lib / re.py
blob955b6b525f266ad1773e67c6e9d0a6cb266d7a0c
2 # Secret Labs' Regular Expression Engine
4 # re-compatible interface for the sre matching engine
6 # Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved.
8 # This version of the SRE library can be redistributed under CNRI's
9 # Python 1.6 license. For any other use, please contact Secret Labs
10 # AB (info@pythonware.com).
12 # Portions of this engine have been developed in cooperation with
13 # CNRI. Hewlett-Packard provided funding for 1.6 integration and
14 # other compatibility work.
17 r"""Support for regular expressions (RE).
19 This module provides regular expression matching operations similar to
20 those found in Perl. It supports both 8-bit and Unicode strings; both
21 the pattern and the strings being processed can contain null bytes and
22 characters outside the US ASCII range.
24 Regular expressions can contain both special and ordinary characters.
25 Most ordinary characters, like "A", "a", or "0", are the simplest
26 regular expressions; they simply match themselves. You can
27 concatenate ordinary characters, so last matches the string 'last'.
29 The special characters are:
30 "." Matches any character except a newline.
31 "^" Matches the start of the string.
32 "$" Matches the end of the string or just before the newline at
33 the end of the string.
34 "*" Matches 0 or more (greedy) repetitions of the preceding RE.
35 Greedy means that it will match as many repetitions as possible.
36 "+" Matches 1 or more (greedy) repetitions of the preceding RE.
37 "?" Matches 0 or 1 (greedy) of the preceding RE.
38 *?,+?,?? Non-greedy versions of the previous three special characters.
39 {m,n} Matches from m to n repetitions of the preceding RE.
40 {m,n}? Non-greedy version of the above.
41 "\\" Either escapes special characters or signals a special sequence.
42 [] Indicates a set of characters.
43 A "^" as the first character indicates a complementing set.
44 "|" A|B, creates an RE that will match either A or B.
45 (...) Matches the RE inside the parentheses.
46 The contents can be retrieved or matched later in the string.
47 (?iLmsux) Set the I, L, M, S, U, or X flag for the RE (see below).
48 (?:...) Non-grouping version of regular parentheses.
49 (?P<name>...) The substring matched by the group is accessible by name.
50 (?P=name) Matches the text matched earlier by the group named name.
51 (?#...) A comment; ignored.
52 (?=...) Matches if ... matches next, but doesn't consume the string.
53 (?!...) Matches if ... doesn't match next.
54 (?<=...) Matches if preceded by ... (must be fixed length).
55 (?<!...) Matches if not preceded by ... (must be fixed length).
56 (?(id/name)yes|no) Matches yes pattern if the group with id/name matched,
57 the (optional) no pattern otherwise.
59 The special sequences consist of "\\" and a character from the list
60 below. If the ordinary character is not on the list, then the
61 resulting RE will match the second character.
62 \number Matches the contents of the group of the same number.
63 \A Matches only at the start of the string.
64 \Z Matches only at the end of the string.
65 \b Matches the empty string, but only at the start or end of a word.
66 \B Matches the empty string, but not at the start or end of a word.
67 \d Matches any decimal digit; equivalent to the set [0-9].
68 \D Matches any non-digit character; equivalent to the set [^0-9].
69 \s Matches any whitespace character; equivalent to [ \t\n\r\f\v].
70 \S Matches any non-whitespace character; equiv. to [^ \t\n\r\f\v].
71 \w Matches any alphanumeric character; equivalent to [a-zA-Z0-9_].
72 With LOCALE, it will match the set [0-9_] plus characters defined
73 as letters for the current locale.
74 \W Matches the complement of \w.
75 \\ Matches a literal backslash.
77 This module exports the following functions:
78 match Match a regular expression pattern to the beginning of a string.
79 search Search a string for the presence of a pattern.
80 sub Substitute occurrences of a pattern found in a string.
81 subn Same as sub, but also return the number of substitutions made.
82 split Split a string by the occurrences of a pattern.
83 findall Find all occurrences of a pattern in a string.
84 finditer Return an iterator yielding a match object for each match.
85 compile Compile a pattern into a RegexObject.
86 purge Clear the regular expression cache.
87 escape Backslash all non-alphanumerics in a string.
89 Some of the functions in this module takes flags as optional parameters:
90 I IGNORECASE Perform case-insensitive matching.
91 L LOCALE Make \w, \W, \b, \B, dependent on the current locale.
92 M MULTILINE "^" matches the beginning of lines (after a newline)
93 as well as the string.
94 "$" matches the end of lines (before a newline) as well
95 as the end of the string.
96 S DOTALL "." matches any character at all, including the newline.
97 X VERBOSE Ignore whitespace and comments for nicer looking RE's.
98 U UNICODE Make \w, \W, \b, \B, dependent on the Unicode locale.
100 This module also defines an exception 'error'.
104 import sys
105 import sre_compile
106 import sre_parse
108 # public symbols
109 __all__ = [ "match", "search", "sub", "subn", "split", "findall",
110 "compile", "purge", "template", "escape", "I", "L", "M", "S", "X",
111 "U", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE",
112 "UNICODE", "error" ]
114 __version__ = "2.2.1"
116 # flags
117 I = IGNORECASE = sre_compile.SRE_FLAG_IGNORECASE # ignore case
118 L = LOCALE = sre_compile.SRE_FLAG_LOCALE # assume current 8-bit locale
119 U = UNICODE = sre_compile.SRE_FLAG_UNICODE # assume unicode locale
120 M = MULTILINE = sre_compile.SRE_FLAG_MULTILINE # make anchors look for newline
121 S = DOTALL = sre_compile.SRE_FLAG_DOTALL # make dot match newline
122 X = VERBOSE = sre_compile.SRE_FLAG_VERBOSE # ignore whitespace and comments
124 # sre extensions (experimental, don't rely on these)
125 T = TEMPLATE = sre_compile.SRE_FLAG_TEMPLATE # disable backtracking
126 DEBUG = sre_compile.SRE_FLAG_DEBUG # dump pattern after compilation
128 # sre exception
129 error = sre_compile.error
131 # --------------------------------------------------------------------
132 # public interface
134 def match(pattern, string, flags=0):
135 """Try to apply the pattern at the start of the string, returning
136 a match object, or None if no match was found."""
137 return _compile(pattern, flags).match(string)
139 def search(pattern, string, flags=0):
140 """Scan through string looking for a match to the pattern, returning
141 a match object, or None if no match was found."""
142 return _compile(pattern, flags).search(string)
144 def sub(pattern, repl, string, count=0, flags=0):
145 """Return the string obtained by replacing the leftmost
146 non-overlapping occurrences of the pattern in string by the
147 replacement repl. repl can be either a string or a callable;
148 if a string, backslash escapes in it are processed. If it is
149 a callable, it's passed the match object and must return
150 a replacement string to be used."""
151 return _compile(pattern, flags).sub(repl, string, count)
153 def subn(pattern, repl, string, count=0, flags=0):
154 """Return a 2-tuple containing (new_string, number).
155 new_string is the string obtained by replacing the leftmost
156 non-overlapping occurrences of the pattern in the source
157 string by the replacement repl. number is the number of
158 substitutions that were made. repl can be either a string or a
159 callable; if a string, backslash escapes in it are processed.
160 If it is a callable, it's passed the match object and must
161 return a replacement string to be used."""
162 return _compile(pattern, flags).subn(repl, string, count)
164 def split(pattern, string, maxsplit=0, flags=0):
165 """Split the source string by the occurrences of the pattern,
166 returning a list containing the resulting substrings."""
167 return _compile(pattern, flags).split(string, maxsplit)
169 def findall(pattern, string, flags=0):
170 """Return a list of all non-overlapping matches in the string.
172 If one or more groups are present in the pattern, return a
173 list of groups; this will be a list of tuples if the pattern
174 has more than one group.
176 Empty matches are included in the result."""
177 return _compile(pattern, flags).findall(string)
179 if sys.hexversion >= 0x02020000:
180 __all__.append("finditer")
181 def finditer(pattern, string, flags=0):
182 """Return an iterator over all non-overlapping matches in the
183 string. For each match, the iterator returns a match object.
185 Empty matches are included in the result."""
186 return _compile(pattern, flags).finditer(string)
188 def compile(pattern, flags=0):
189 "Compile a regular expression pattern, returning a pattern object."
190 return _compile(pattern, flags)
192 def purge():
193 "Clear the regular expression cache"
194 _cache.clear()
195 _cache_repl.clear()
197 def template(pattern, flags=0):
198 "Compile a template pattern, returning a pattern object"
199 return _compile(pattern, flags|T)
201 _alphanum = {}
202 for c in 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890':
203 _alphanum[c] = 1
204 del c
206 def escape(pattern):
207 "Escape all non-alphanumeric characters in pattern."
208 s = list(pattern)
209 alphanum = _alphanum
210 for i in range(len(pattern)):
211 c = pattern[i]
212 if c not in alphanum:
213 if c == "\000":
214 s[i] = "\\000"
215 else:
216 s[i] = "\\" + c
217 return pattern[:0].join(s)
219 # --------------------------------------------------------------------
220 # internals
222 _cache = {}
223 _cache_repl = {}
225 _pattern_type = type(sre_compile.compile("", 0))
227 _MAXCACHE = 100
229 def _compile(*key):
230 # internal: compile pattern
231 cachekey = (type(key[0]),) + key
232 p = _cache.get(cachekey)
233 if p is not None:
234 return p
235 pattern, flags = key
236 if isinstance(pattern, _pattern_type):
237 if flags:
238 raise ValueError('Cannot process flags argument with a compiled pattern')
239 return pattern
240 if not sre_compile.isstring(pattern):
241 raise TypeError, "first argument must be string or compiled pattern"
242 try:
243 p = sre_compile.compile(pattern, flags)
244 except error, v:
245 raise error, v # invalid expression
246 if len(_cache) >= _MAXCACHE:
247 _cache.clear()
248 _cache[cachekey] = p
249 return p
251 def _compile_repl(*key):
252 # internal: compile replacement pattern
253 p = _cache_repl.get(key)
254 if p is not None:
255 return p
256 repl, pattern = key
257 try:
258 p = sre_parse.parse_template(repl, pattern)
259 except error, v:
260 raise error, v # invalid expression
261 if len(_cache_repl) >= _MAXCACHE:
262 _cache_repl.clear()
263 _cache_repl[key] = p
264 return p
266 def _expand(pattern, match, template):
267 # internal: match.expand implementation hook
268 template = sre_parse.parse_template(template, pattern)
269 return sre_parse.expand_template(template, match)
271 def _subx(pattern, template):
272 # internal: pattern.sub/subn implementation helper
273 template = _compile_repl(template, pattern)
274 if not template[0] and len(template[1]) == 1:
275 # literal replacement
276 return template[1][0]
277 def filter(match, template=template):
278 return sre_parse.expand_template(template, match)
279 return filter
281 # register myself for pickling
283 import copy_reg
285 def _pickle(p):
286 return _compile, (p.pattern, p.flags)
288 copy_reg.pickle(_pattern_type, _pickle, _compile)
290 # --------------------------------------------------------------------
291 # experimental stuff (see python-dev discussions for details)
293 class Scanner:
294 def __init__(self, lexicon, flags=0):
295 from sre_constants import BRANCH, SUBPATTERN
296 self.lexicon = lexicon
297 # combine phrases into a compound pattern
298 p = []
299 s = sre_parse.Pattern()
300 s.flags = flags
301 for phrase, action in lexicon:
302 p.append(sre_parse.SubPattern(s, [
303 (SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))),
305 s.groups = len(p)+1
306 p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
307 self.scanner = sre_compile.compile(p)
308 def scan(self, string):
309 result = []
310 append = result.append
311 match = self.scanner.scanner(string).match
312 i = 0
313 while 1:
314 m = match()
315 if not m:
316 break
317 j = m.end()
318 if i == j:
319 break
320 action = self.lexicon[m.lastindex-1][1]
321 if hasattr(action, '__call__'):
322 self.match = m
323 action = action(self, m.group())
324 if action is not None:
325 append(action)
326 i = j
327 return result, string[i:]