|
1 # |
|
2 # Secret Labs' Regular Expression Engine |
|
3 # |
|
4 # re-compatible interface for the sre matching engine |
|
5 # |
|
6 # Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved. |
|
7 # |
|
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). |
|
11 # |
|
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. |
|
15 # |
|
16 |
|
17 r"""Support for regular expressions (RE). |
|
18 |
|
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. |
|
23 |
|
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'. |
|
28 |
|
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. |
|
58 |
|
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. |
|
76 |
|
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. |
|
88 |
|
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. |
|
99 |
|
100 This module also defines an exception 'error'. |
|
101 |
|
102 """ |
|
103 |
|
104 import sys |
|
105 import sre_compile |
|
106 import sre_parse |
|
107 |
|
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" ] |
|
113 |
|
114 __version__ = "2.2.1" |
|
115 |
|
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 |
|
123 |
|
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 |
|
127 |
|
128 # sre exception |
|
129 error = sre_compile.error |
|
130 |
|
131 # -------------------------------------------------------------------- |
|
132 # public interface |
|
133 |
|
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) |
|
138 |
|
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) |
|
143 |
|
144 def sub(pattern, repl, string, count=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 callable, it's passed the match object and must return |
|
149 a replacement string to be used.""" |
|
150 return _compile(pattern, 0).sub(repl, string, count) |
|
151 |
|
152 def subn(pattern, repl, string, count=0): |
|
153 """Return a 2-tuple containing (new_string, number). |
|
154 new_string is the string obtained by replacing the leftmost |
|
155 non-overlapping occurrences of the pattern in the source |
|
156 string by the replacement repl. number is the number of |
|
157 substitutions that were made. repl can be either a string or a |
|
158 callable; if a callable, it's passed the match object and must |
|
159 return a replacement string to be used.""" |
|
160 return _compile(pattern, 0).subn(repl, string, count) |
|
161 |
|
162 def split(pattern, string, maxsplit=0): |
|
163 """Split the source string by the occurrences of the pattern, |
|
164 returning a list containing the resulting substrings.""" |
|
165 return _compile(pattern, 0).split(string, maxsplit) |
|
166 |
|
167 def findall(pattern, string, flags=0): |
|
168 """Return a list of all non-overlapping matches in the string. |
|
169 |
|
170 If one or more groups are present in the pattern, return a |
|
171 list of groups; this will be a list of tuples if the pattern |
|
172 has more than one group. |
|
173 |
|
174 Empty matches are included in the result.""" |
|
175 return _compile(pattern, flags).findall(string) |
|
176 |
|
177 if sys.hexversion >= 0x02020000: |
|
178 __all__.append("finditer") |
|
179 def finditer(pattern, string, flags=0): |
|
180 """Return an iterator over all non-overlapping matches in the |
|
181 string. For each match, the iterator returns a match object. |
|
182 |
|
183 Empty matches are included in the result.""" |
|
184 return _compile(pattern, flags).finditer(string) |
|
185 |
|
186 def compile(pattern, flags=0): |
|
187 "Compile a regular expression pattern, returning a pattern object." |
|
188 return _compile(pattern, flags) |
|
189 |
|
190 def purge(): |
|
191 "Clear the regular expression cache" |
|
192 _cache.clear() |
|
193 _cache_repl.clear() |
|
194 |
|
195 def template(pattern, flags=0): |
|
196 "Compile a template pattern, returning a pattern object" |
|
197 return _compile(pattern, flags|T) |
|
198 |
|
199 _alphanum = {} |
|
200 for c in 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890': |
|
201 _alphanum[c] = 1 |
|
202 del c |
|
203 |
|
204 def escape(pattern): |
|
205 "Escape all non-alphanumeric characters in pattern." |
|
206 s = list(pattern) |
|
207 alphanum = _alphanum |
|
208 for i in range(len(pattern)): |
|
209 c = pattern[i] |
|
210 if c not in alphanum: |
|
211 if c == "\000": |
|
212 s[i] = "\\000" |
|
213 else: |
|
214 s[i] = "\\" + c |
|
215 return pattern[:0].join(s) |
|
216 |
|
217 # -------------------------------------------------------------------- |
|
218 # internals |
|
219 |
|
220 _cache = {} |
|
221 _cache_repl = {} |
|
222 |
|
223 _pattern_type = type(sre_compile.compile("", 0)) |
|
224 |
|
225 _MAXCACHE = 100 |
|
226 |
|
227 def _compile(*key): |
|
228 # internal: compile pattern |
|
229 cachekey = (type(key[0]),) + key |
|
230 p = _cache.get(cachekey) |
|
231 if p is not None: |
|
232 return p |
|
233 pattern, flags = key |
|
234 if isinstance(pattern, _pattern_type): |
|
235 if flags: |
|
236 raise ValueError('Cannot process flags argument with a compiled pattern') |
|
237 return pattern |
|
238 if not sre_compile.isstring(pattern): |
|
239 raise TypeError, "first argument must be string or compiled pattern" |
|
240 try: |
|
241 p = sre_compile.compile(pattern, flags) |
|
242 except error, v: |
|
243 raise error, v # invalid expression |
|
244 if len(_cache) >= _MAXCACHE: |
|
245 _cache.clear() |
|
246 _cache[cachekey] = p |
|
247 return p |
|
248 |
|
249 def _compile_repl(*key): |
|
250 # internal: compile replacement pattern |
|
251 p = _cache_repl.get(key) |
|
252 if p is not None: |
|
253 return p |
|
254 repl, pattern = key |
|
255 try: |
|
256 p = sre_parse.parse_template(repl, pattern) |
|
257 except error, v: |
|
258 raise error, v # invalid expression |
|
259 if len(_cache_repl) >= _MAXCACHE: |
|
260 _cache_repl.clear() |
|
261 _cache_repl[key] = p |
|
262 return p |
|
263 |
|
264 def _expand(pattern, match, template): |
|
265 # internal: match.expand implementation hook |
|
266 template = sre_parse.parse_template(template, pattern) |
|
267 return sre_parse.expand_template(template, match) |
|
268 |
|
269 def _subx(pattern, template): |
|
270 # internal: pattern.sub/subn implementation helper |
|
271 template = _compile_repl(template, pattern) |
|
272 if not template[0] and len(template[1]) == 1: |
|
273 # literal replacement |
|
274 return template[1][0] |
|
275 def filter(match, template=template): |
|
276 return sre_parse.expand_template(template, match) |
|
277 return filter |
|
278 |
|
279 # register myself for pickling |
|
280 |
|
281 import copy_reg |
|
282 |
|
283 def _pickle(p): |
|
284 return _compile, (p.pattern, p.flags) |
|
285 |
|
286 copy_reg.pickle(_pattern_type, _pickle, _compile) |
|
287 |
|
288 # -------------------------------------------------------------------- |
|
289 # experimental stuff (see python-dev discussions for details) |
|
290 |
|
291 class Scanner: |
|
292 def __init__(self, lexicon, flags=0): |
|
293 from sre_constants import BRANCH, SUBPATTERN |
|
294 self.lexicon = lexicon |
|
295 # combine phrases into a compound pattern |
|
296 p = [] |
|
297 s = sre_parse.Pattern() |
|
298 s.flags = flags |
|
299 for phrase, action in lexicon: |
|
300 p.append(sre_parse.SubPattern(s, [ |
|
301 (SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))), |
|
302 ])) |
|
303 s.groups = len(p)+1 |
|
304 p = sre_parse.SubPattern(s, [(BRANCH, (None, p))]) |
|
305 self.scanner = sre_compile.compile(p) |
|
306 def scan(self, string): |
|
307 result = [] |
|
308 append = result.append |
|
309 match = self.scanner.scanner(string).match |
|
310 i = 0 |
|
311 while 1: |
|
312 m = match() |
|
313 if not m: |
|
314 break |
|
315 j = m.end() |
|
316 if i == j: |
|
317 break |
|
318 action = self.lexicon[m.lastindex-1][1] |
|
319 if hasattr(action, '__call__'): |
|
320 self.match = m |
|
321 action = action(self, m.group()) |
|
322 if action is not None: |
|
323 append(action) |
|
324 i = j |
|
325 return result, string[i:] |