Lib/sre.py

   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.
  33     "*"      Matches 0 or more (greedy) repetitions of the preceding RE.
  34              Greedy means that it will match as many repetitions as possible.
  35     "+"      Matches 1 or more (greedy) repetitions of the preceding RE.
  36     "?"      Matches 0 or 1 (greedy) of the preceding RE.
  37     *?,+?,?? Non-greedy versions of the previous three special characters.
  38     {m,n}    Matches from m to n repetitions of the preceding RE.
  39     {m,n}?   Non-greedy version of the above.
  40     "\\"      Either escapes special characters or signals a special sequence.
  41     []       Indicates a set of characters.
  42              A "^" as the first character indicates a complementing set.
  43     "|"      A|B, creates an RE that will match either A or B.
  44     (...)    Matches the RE inside the parentheses.
  45              The contents can be retrieved or matched later in the string.
  46     (?iLmsux) Set the I, L, M, S, U, or X flag for the RE (see below).
  47     (?:...)  Non-grouping version of regular parentheses.
  48     (?P<name>...) The substring matched by the group is accessible by name.
  49     (?P=name)     Matches the text matched earlier by the group named name.
  50     (?#...)  A comment; ignored.
  51     (?=...)  Matches if ... matches next, but doesn't consume the string.
  52     (?!...)  Matches if ... doesn't match next.
  53
  54 The special sequences consist of "\\" and a character from the list
  55 below.  If the ordinary character is not on the list, then the
  56 resulting RE will match the second character.
  57     \number  Matches the contents of the group of the same number.
  58     \A       Matches only at the start of the string.
  59     \Z       Matches only at the end of the string.
  60     \b       Matches the empty string, but only at the start or end of a word.
  61     \B       Matches the empty string, but not at the start or end of a word.
  62     \d       Matches any decimal digit; equivalent to the set [0-9].
  63     \D       Matches any non-digit character; equivalent to the set [^0-9].
  64     \s       Matches any whitespace character; equivalent to [ \t\n\r\f\v].
  65     \S       Matches any non-whitespace character; equiv. to [^ \t\n\r\f\v].
  66     \w       Matches any alphanumeric character; equivalent to [a-zA-Z0-9_].
  67              With LOCALE, it will match the set [0-9_] plus characters defined
  68              as letters for the current locale.
  69     \W       Matches the complement of \w.
  70     \\       Matches a literal backslash.
  71
  72 This module exports the following functions:
  73     match    Match a regular expression pattern to the beginning of a string.
  74     search   Search a string for the presence of a pattern.
  75     sub      Substitute occurrences of a pattern found in a string.
  76     subn     Same as sub, but also return the number of substitutions made.
  77     split    Split a string by the occurrences of a pattern.
  78     findall  Find all occurrences of a pattern in a string.
  79     compile  Compile a pattern into a RegexObject.
  80     purge    Clear the regular expression cache.
  81     escape   Backslash all non-alphanumerics in a string.
  82
  83 Some of the functions in this module takes flags as optional parameters:
  84     I  IGNORECASE  Perform case-insensitive matching.
  85     L  LOCALE      Make \w, \W, \b, \B, dependent on the current locale.
  86     M  MULTILINE   "^" matches the beginning of lines as well as the string.
  87                    "$" matches the end of lines as well as the string.
  88     S  DOTALL      "." matches any character at all, including the newline.
  89     X  VERBOSE     Ignore whitespace and comments for nicer looking RE's.
  90     U  UNICODE     Make \w, \W, \b, \B, dependent on the Unicode locale.
  91
  92 This module also defines an exception 'error'.
  93
  94 """
  95
  96 import sys
  97 import sre_compile
  98 import sre_parse
  99
 100 # public symbols
 101 __all__ = [ "match", "search", "sub", "subn", "split", "findall",
 102     "compile", "purge", "template", "escape", "I", "L", "M", "S", "X",
 103     "U", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE",
 104     "UNICODE", "error" ]
 105
 106 __version__ = "2.2.1"
 107
 108 # this module works under 1.5.2 and later.  don't use string methods
 109 import string
 110
 111 # flags
 112 I = IGNORECASE = sre_compile.SRE_FLAG_IGNORECASE # ignore case
 113 L = LOCALE = sre_compile.SRE_FLAG_LOCALE # assume current 8-bit locale
 114 U = UNICODE = sre_compile.SRE_FLAG_UNICODE # assume unicode locale
 115 M = MULTILINE = sre_compile.SRE_FLAG_MULTILINE # make anchors look for newline
 116 S = DOTALL = sre_compile.SRE_FLAG_DOTALL # make dot match newline
 117 X = VERBOSE = sre_compile.SRE_FLAG_VERBOSE # ignore whitespace and comments
 118
 119 # sre extensions (experimental, don't rely on these)
 120 T = TEMPLATE = sre_compile.SRE_FLAG_TEMPLATE # disable backtracking
 121 DEBUG = sre_compile.SRE_FLAG_DEBUG # dump pattern after compilation
 122
 123 # sre exception
 124 error = sre_compile.error
 125
 126 # --------------------------------------------------------------------
 127 # public interface
 128
 129 def match(pattern, string, flags=0):
 130     """Try to apply the pattern at the start of the string, returning
 131     a match object, or None if no match was found."""
 132     return _compile(pattern, flags).match(string)
 133
 134 def search(pattern, string, flags=0):
 135     """Scan through string looking for a match to the pattern, returning
 136     a match object, or None if no match was found."""
 137     return _compile(pattern, flags).search(string)
 138
 139 def sub(pattern, repl, string, count=0):
 140     """Return the string obtained by replacing the leftmost
 141     non-overlapping occurrences of the pattern in string by the
 142     replacement repl"""
 143     return _compile(pattern, 0).sub(repl, string, count)
 144
 145 def subn(pattern, repl, string, count=0):
 146     """Return a 2-tuple containing (new_string, number).
 147     new_string is the string obtained by replacing the leftmost
 148     non-overlapping occurrences of the pattern in the source
 149     string by the replacement repl.  number is the number of
 150     substitutions that were made."""
 151     return _compile(pattern, 0).subn(repl, string, count)
 152
 153 def split(pattern, string, maxsplit=0):
 154     """Split the source string by the occurrences of the pattern,
 155     returning a list containing the resulting substrings."""
 156     return _compile(pattern, 0).split(string, maxsplit)
 157
 158 def findall(pattern, string):
 159     """Return a list of all non-overlapping matches in the string.
 160
 161     If one or more groups are present in the pattern, return a
 162     list of groups; this will be a list of tuples if the pattern
 163     has more than one group.
 164
 165     Empty matches are included in the result."""
 166     return _compile(pattern, 0).findall(string)
 167
 168 if sys.hexversion >= 0x02020000:
 169     __all__.append("finditer")
 170     def finditer(pattern, string):
 171         """Return an iterator over all non-overlapping matches in the
 172         string.  For each match, the iterator returns a match object.
 173
 174         Empty matches are included in the result."""
 175         return _compile(pattern, 0).finditer(string)
 176
 177 def compile(pattern, flags=0):
 178     "Compile a regular expression pattern, returning a pattern object."
 179     return _compile(pattern, flags)
 180
 181 def purge():
 182     "Clear the regular expression cache"
 183     _cache.clear()
 184     _cache_repl.clear()
 185
 186 def template(pattern, flags=0):
 187     "Compile a template pattern, returning a pattern object"
 188     return _compile(pattern, flags|T)
 189
 190 def escape(pattern):
 191     "Escape all non-alphanumeric characters in pattern."
 192     s = list(pattern)
 193     for i in range(len(pattern)):
 194         c = pattern[i]
 195         if not ("a" <= c <= "z" or "A" <= c <= "Z" or "0" <= c <= "9"):
 196             if c == "\000":
 197                 s[i] = "\\000"
 198             else:
 199                 s[i] = "\\" + c
 200     return _join(s, pattern)
 201
 202 # --------------------------------------------------------------------
 203 # internals
 204
 205 _cache = {}
 206 _cache_repl = {}
 207
 208 _pattern_type = type(sre_compile.compile("", 0))
 209
 210 _MAXCACHE = 100
 211
 212 def _join(seq, sep):
 213     # internal: join into string having the same type as sep
 214     return string.join(seq, sep[:0])
 215
 216 def _compile(*key):
 217     # internal: compile pattern
 218     p = _cache.get(key)
 219     if p is not None:
 220         return p
 221     pattern, flags = key
 222     if type(pattern) is _pattern_type:
 223         return pattern
 224     if type(pattern) not in sre_compile.STRING_TYPES:
 225         raise TypeError, "first argument must be string or compiled pattern"
 226     try:
 227         p = sre_compile.compile(pattern, flags)
 228     except error, v:
 229         raise error, v # invalid expression
 230     if len(_cache) >= _MAXCACHE:
 231         _cache.clear()
 232     _cache[key] = p
 233     return p
 234
 235 def _compile_repl(*key):
 236     # internal: compile replacement pattern
 237     p = _cache_repl.get(key)
 238     if p is not None:
 239         return p
 240     repl, pattern = key
 241     try:
 242         p = sre_parse.parse_template(repl, pattern)
 243     except error, v:
 244         raise error, v # invalid expression
 245     if len(_cache_repl) >= _MAXCACHE:
 246         _cache_repl.clear()
 247     _cache_repl[key] = p
 248     return p
 249
 250 def _expand(pattern, match, template):
 251     # internal: match.expand implementation hook
 252     template = sre_parse.parse_template(template, pattern)
 253     return sre_parse.expand_template(template, match)
 254
 255 def _subx(pattern, template):
 256     # internal: pattern.sub/subn implementation helper
 257     template = _compile_repl(template, pattern)
 258     if not template[0] and len(template[1]) == 1:
 259         # literal replacement
 260         return template[1][0]
 261     def filter(match, template=template):
 262         return sre_parse.expand_template(template, match)
 263     return filter
 264
 265 # register myself for pickling
 266
 267 import copy_reg
 268
 269 def _pickle(p):
 270     return _compile, (p.pattern, p.flags)
 271
 272 copy_reg.pickle(_pattern_type, _pickle, _compile)
 273
 274 # --------------------------------------------------------------------
 275 # experimental stuff (see python-dev discussions for details)
 276
 277 class Scanner:
 278     def __init__(self, lexicon, flags=0):
 279         from sre_constants import BRANCH, SUBPATTERN
 280         self.lexicon = lexicon
 281         # combine phrases into a compound pattern
 282         p = []
 283         s = sre_parse.Pattern()
 284         s.flags = flags
 285         for phrase, action in lexicon:
 286             p.append(sre_parse.SubPattern(s, [
 287                 (SUBPATTERN, (len(p)+1, sre_parse.parse(phrase, flags))),
 288                 ]))
 289         p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
 290         s.groups = len(p)
 291         self.scanner = sre_compile.compile(p)
 292     def scan(self, string):
 293         result = []
 294         append = result.append
 295         match = self.scanner.scanner(string).match
 296         i = 0
 297         while 1:
 298             m = match()
 299             if not m:
 300                 break
 301             j = m.end()
 302             if i == j:
 303                 break
 304             action = self.lexicon[m.lastindex-1][1]
 305             if callable(action):
 306                 self.match = m
 307                 action = action(self, m.group())
 308             if action is not None:
 309                 append(action)
 310             i = j
 311         return result, string[i:]