summaryrefslogtreecommitdiffstats
path: root/Lib/sre_parse.py
blob: fc3c4928bce772f19e00131ec4180614c3cd57bd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
#
# Secret Labs' Regular Expression Engine
#
# convert re-style regular expression to sre pattern
#
# Copyright (c) 1998-2001 by Secret Labs AB.  All rights reserved.
#
# See the sre.py file for information on usage and redistribution.
#

# XXX: show string offset and offending character for all errors

import sys

from sre_constants import *

__all__ = ["Pattern","SubPattern","Tokenizer","parse","parse_template",
           "expand_template"]

SPECIAL_CHARS = ".\\[{()*+?^$|"
REPEAT_CHARS = "*+?{"

DIGITS = tuple("0123456789")

OCTDIGITS = tuple("01234567")
HEXDIGITS = tuple("0123456789abcdefABCDEF")

WHITESPACE = tuple(" \t\n\r\v\f")

ESCAPES = {
    r"\a": (LITERAL, 7),
    r"\b": (LITERAL, 8),
    r"\f": (LITERAL, 12),
    r"\n": (LITERAL, 10),
    r"\r": (LITERAL, 13),
    r"\t": (LITERAL, 9),
    r"\v": (LITERAL, 11),
    r"\\": (LITERAL, ord("\\"))
}

CATEGORIES = {
    r"\A": (AT, AT_BEGINNING_STRING), # start of string
    r"\b": (AT, AT_BOUNDARY),
    r"\B": (AT, AT_NON_BOUNDARY),
    r"\d": (IN, [(CATEGORY, CATEGORY_DIGIT)]),
    r"\D": (IN, [(CATEGORY, CATEGORY_NOT_DIGIT)]),
    r"\s": (IN, [(CATEGORY, CATEGORY_SPACE)]),
    r"\S": (IN, [(CATEGORY, CATEGORY_NOT_SPACE)]),
    r"\w": (IN, [(CATEGORY, CATEGORY_WORD)]),
    r"\W": (IN, [(CATEGORY, CATEGORY_NOT_WORD)]),
    r"\Z": (AT, AT_END_STRING), # end of string
}

FLAGS = {
    # standard flags
    "i": SRE_FLAG_IGNORECASE,
    "L": SRE_FLAG_LOCALE,
    "m": SRE_FLAG_MULTILINE,
    "s": SRE_FLAG_DOTALL,
    "x": SRE_FLAG_VERBOSE,
    # extensions
    "t": SRE_FLAG_TEMPLATE,
    "u": SRE_FLAG_UNICODE,
}

class Pattern:
    # master pattern object.  keeps track of global attributes
    def __init__(self):
        self.flags = 0
        self.open = []
        self.groups = 1
        self.groupdict = {}
    def opengroup(self, name=None):
        gid = self.groups
        self.groups = gid + 1
        if name:
            self.groupdict[name] = gid
        self.open.append(gid)
        return gid
    def closegroup(self, gid):
        self.open.remove(gid)
    def checkgroup(self, gid):
        return gid < self.groups and gid not in self.open

class SubPattern:
    # a subpattern, in intermediate form
    def __init__(self, pattern, data=None):
        self.pattern = pattern
        if not data:
            data = []
        self.data = data
        self.width = None
    def dump(self, level=0):
        nl = 1
        for op, av in self.data:
            print level*"  " + op,; nl = 0
            if op == "in":
                # member sublanguage
                print; nl = 1
                for op, a in av:
                    print (level+1)*"  " + op, a
            elif op == "branch":
                print; nl = 1
                i = 0
                for a in av[1]:
                    if i > 0:
                        print level*"  " + "or"
                    a.dump(level+1); nl = 1
                    i = i + 1
            elif type(av) in (type(()), type([])):
                for a in av:
                    if isinstance(a, SubPattern):
                        if not nl: print
                        a.dump(level+1); nl = 1
                    else:
                        print a, ; nl = 0
            else:
                print av, ; nl = 0
            if not nl: print
    def __repr__(self):
        return repr(self.data)
    def __len__(self):
        return len(self.data)
    def __delitem__(self, index):
        del self.data[index]
    def __getitem__(self, index):
        return self.data[index]
    def __setitem__(self, index, code):
        self.data[index] = code
    def __getslice__(self, start, stop):
        return SubPattern(self.pattern, self.data[start:stop])
    def insert(self, index, code):
        self.data.insert(index, code)
    def append(self, code):
        self.data.append(code)
    def getwidth(self):
        # determine the width (min, max) for this subpattern
        if self.width:
            return self.width
        lo = hi = 0L
        for op, av in self.data:
            if op is BRANCH:
                i = sys.maxint
                j = 0
                for av in av[1]:
                    l, h = av.getwidth()
                    i = min(i, l)
                    j = max(j, h)
                lo = lo + i
                hi = hi + j
            elif op is CALL:
                i, j = av.getwidth()
                lo = lo + i
                hi = hi + j
            elif op is SUBPATTERN:
                i, j = av[1].getwidth()
                lo = lo + i
                hi = hi + j
            elif op in (MIN_REPEAT, MAX_REPEAT):
                i, j = av[2].getwidth()
                lo = lo + long(i) * av[0]
                hi = hi + long(j) * av[1]
            elif op in (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY):
                lo = lo + 1
                hi = hi + 1
            elif op == SUCCESS:
                break
        self.width = int(min(lo, sys.maxint)), int(min(hi, sys.maxint))
        return self.width

class Tokenizer:
    def __init__(self, string):
        self.string = string
        self.index = 0
        self.__next()
    def __next(self):
        if self.index >= len(self.string):
            self.next = None
            return
        char = self.string[self.index]
        if char[0] == "\\":
            try:
                c = self.string[self.index + 1]
            except IndexError:
                raise error, "bogus escape"
            char = char + c
        self.index = self.index + len(char)
        self.next = char
    def match(self, char, skip=1):
        if char == self.next:
            if skip:
                self.__next()
            return 1
        return 0
    def get(self):
        this = self.next
        self.__next()
        return this
    def tell(self):
        return self.index, self.next
    def seek(self, index):
        self.index, self.next = index

def isident(char):
    return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"

def isdigit(char):
    return "0" <= char <= "9"

def isname(name):
    # check that group name is a valid string
    if not isident(name[0]):
        return 0
    for char in name:
        if not isident(char) and not isdigit(char):
            return 0
    return 1

def _group(escape, groups):
    # check if the escape string represents a valid group
    try:
        gid = int(escape[1:])
        if gid and gid < groups:
            return gid
    except ValueError:
        pass
    return None # not a valid group

def _class_escape(source, escape):
    # handle escape code inside character class
    code = ESCAPES.get(escape)
    if code:
        return code
    code = CATEGORIES.get(escape)
    if code:
        return code
    try:
        if escape[1:2] == "x":
            # hexadecimal escape (exactly two digits)
            while source.next in HEXDIGITS and len(escape) < 4:
                escape = escape + source.get()
            escape = escape[2:]
            if len(escape) != 2:
                raise error, "bogus escape: %s" % repr("\\" + escape)
            return LITERAL, int(escape, 16) & 0xff
        elif str(escape[1:2]) in OCTDIGITS:
            # octal escape (up to three digits)
            while source.next in OCTDIGITS and len(escape) < 5:
                escape = escape + source.get()
            escape = escape[1:]
            return LITERAL, int(escape, 8) & 0xff
        if len(escape) == 2:
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise error, "bogus escape: %s" % repr(escape)

def _escape(source, escape, state):
    # handle escape code in expression
    code = CATEGORIES.get(escape)
    if code:
        return code
    code = ESCAPES.get(escape)
    if code:
        return code
    try:
        if escape[1:2] == "x":
            # hexadecimal escape
            while source.next in HEXDIGITS and len(escape) < 4:
                escape = escape + source.get()
            if len(escape) != 4:
                raise ValueError
            return LITERAL, int(escape[2:], 16) & 0xff
        elif escape[1:2] == "0":
            # octal escape
            while source.next in OCTDIGITS and len(escape) < 4:
                escape = escape + source.get()
            return LITERAL, int(escape[1:], 8) & 0xff
        elif escape[1:2] in DIGITS:
            # octal escape *or* decimal group reference (sigh)
            here = source.tell()
            if source.next in DIGITS:
                escape = escape + source.get()
                if (escape[1] in OCTDIGITS and escape[2] in OCTDIGITS and
                    source.next in OCTDIGITS):
                    # got three octal digits; this is an octal escape
                    escape = escape + source.get()
                    return LITERAL, int(escape[1:], 8) & 0xff
            # got at least one decimal digit; this is a group reference
            group = _group(escape, state.groups)
            if group:
                if not state.checkgroup(group):
                    raise error, "cannot refer to open group"
                return GROUPREF, group
            raise ValueError
        if len(escape) == 2:
            return LITERAL, ord(escape[1])
    except ValueError:
        pass
    raise error, "bogus escape: %s" % repr(escape)

def _parse_sub(source, state, nested=1):
    # parse an alternation: a|b|c

    items = []
    while 1:
        items.append(_parse(source, state))
        if source.match("|"):
            continue
        if not nested:
            break
        if not source.next or source.match(")", 0):
            break
        else:
            raise error, "pattern not properly closed"

    if len(items) == 1:
        return items[0]

    subpattern = SubPattern(state)

    # check if all items share a common prefix
    while 1:
        prefix = None
        for item in items:
            if not item:
                break
            if prefix is None:
                prefix = item[0]
            elif item[0] != prefix:
                break
        else:
            # all subitems start with a common "prefix".
            # move it out of the branch
            for item in items:
                del item[0]
            subpattern.append(prefix)
            continue # check next one
        break

    # check if the branch can be replaced by a character set
    for item in items:
        if len(item) != 1 or item[0][0] != LITERAL:
            break
    else:
        # we can store this as a character set instead of a
        # branch (the compiler may optimize this even more)
        set = []
        for item in items:
            set.append(item[0])
        subpattern.append((IN, set))
        return subpattern

    subpattern.append((BRANCH, (None, items)))
    return subpattern

def _parse(source, state):
    # parse a simple pattern

    subpattern = SubPattern(state)

    while 1:

        if source.next in ("|", ")"):
            break # end of subpattern
        this = source.get()
        if this is None:
            break # end of pattern

        if state.flags & SRE_FLAG_VERBOSE:
            # skip whitespace and comments
            if this in WHITESPACE:
                continue
            if this == "#":
                while 1:
                    this = source.get()
                    if this in (None, "\n"):
                        break
                continue

        if this and this[0] not in SPECIAL_CHARS:
            subpattern.append((LITERAL, ord(this)))

        elif this == "[":
            # character set
            set = []
##          if source.match(":"):
##              pass # handle character classes
            if source.match("^"):
                set.append((NEGATE, None))
            # check remaining characters
            start = set[:]
            while 1:
                this = source.get()
                if this == "]" and set != start:
                    break
                elif this and this[0] == "\\":
                    code1 = _class_escape(source, this)
                elif this:
                    code1 = LITERAL, ord(this)
                else:
                    raise error, "unexpected end of regular expression"
                if source.match("-"):
                    # potential range
                    this = source.get()
                    if this == "]":
                        if code1[0] is IN:
                            code1 = code1[1][0]
                        set.append(code1)
                        set.append((LITERAL, ord("-")))
                        break
                    else:
                        if this[0] == "\\":
                            code2 = _class_escape(source, this)
                        else:
                            code2 = LITERAL, ord(this)
                        if code1[0] != LITERAL or code2[0] != LITERAL:
                            raise error, "bad character range"
                        lo = code1[1]
                        hi = code2[1]
                        if hi < lo:
                            raise error, "bad character range"
                        set.append((RANGE, (lo, hi)))
                else:
                    if code1[0] is IN:
                        code1 = code1[1][0]
                    set.append(code1)

            # XXX: <fl> should move set optimization to compiler!
            if len(set)==1 and set[0][0] is LITERAL:
                subpattern.append(set[0]) # optimization
            elif len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL:
                subpattern.append((NOT_LITERAL, set[1][1])) # optimization
            else:
                # XXX: <fl> should add charmap optimization here
                subpattern.append((IN, set))

        elif this and this[0] in REPEAT_CHARS:
            # repeat previous item
            if this == "?":
                min, max = 0, 1
            elif this == "*":
                min, max = 0, MAXREPEAT
            elif this == "+":
                min, max = 1, MAXREPEAT
            elif this == "{":
                here = source.tell()
                min, max = 0, MAXREPEAT
                lo = hi = ""
                while source.next in DIGITS:
                    lo = lo + source.get()
                if source.match(","):
                    while source.next in DIGITS:
                        hi = hi + source.get()
                else:
                    hi = lo
                if not source.match("}"):
                    subpattern.append((LITERAL, ord(this)))
                    source.seek(here)
                    continue
                if lo:
                    min = int(lo)
                if hi:
                    max = int(hi)
                if max < min:
                    raise error, "bad repeat interval"
            else:
                raise error, "not supported"
            # figure out which item to repeat
            if subpattern:
                item = subpattern[-1:]
            else:
                raise error, "nothing to repeat"
            if item[0][0] in (MIN_REPEAT, MAX_REPEAT):
                raise error, "multiple repeat"
            if source.match("?"):
                subpattern[-1] = (MIN_REPEAT, (min, max, item))
            else:
                subpattern[-1] = (MAX_REPEAT, (min, max, item))

        elif this == ".":
            subpattern.append((ANY, None))

        elif this == "(":
            group = 1
            name = None
            if source.match("?"):
                group = 0
                # options
                if source.match("P"):
                    # python extensions
                    if source.match("<"):
                        # named group: skip forward to end of name
                        name = ""
                        while 1:
                            char = source.get()
                            if char is None:
                                raise error, "unterminated name"
                            if char == ">":
                                break
                            name = name + char
                        group = 1
                        if not isname(name):
                            raise error, "bad character in group name"
                    elif source.match("="):
                        # named backreference
                        name = ""
                        while 1:
                            char = source.get()
                            if char is None:
                                raise error, "unterminated name"
                            if char == ")":
                                break
                            name = name + char
                        if not isname(name):
                            raise error, "bad character in group name"
                        gid = state.groupdict.get(name)
                        if gid is None:
                            raise error, "unknown group name"
                        subpattern.append((GROUPREF, gid))
                        continue
                    else:
                        char = source.get()
                        if char is None:
                            raise error, "unexpected end of pattern"
                        raise error, "unknown specifier: ?P%s" % char
                elif source.match(":"):
                    # non-capturing group
                    group = 2
                elif source.match("#"):
                    # comment
                    while 1:
                        if source.next is None or source.next == ")":
                            break
                        source.get()
                    if not source.match(")"):
                        raise error, "unbalanced parenthesis"
                    continue
                elif source.next in ("=", "!", "<"):
                    # lookahead assertions
                    char = source.get()
                    dir = 1
                    if char == "<":
                        if source.next not in ("=", "!"):
                            raise error, "syntax error"
                        dir = -1 # lookbehind
                        char = source.get()
                    p = _parse_sub(source, state)
                    if not source.match(")"):
                        raise error, "unbalanced parenthesis"
                    if char == "=":
                        subpattern.append((ASSERT, (dir, p)))
                    else:
                        subpattern.append((ASSERT_NOT, (dir, p)))
                    continue
                else:
                    # flags
                    if not FLAGS.has_key(source.next):
                        raise error, "unexpected end of pattern"
                    while FLAGS.has_key(source.next):
                        state.flags = state.flags | FLAGS[source.get()]
            if group:
                # parse group contents
                if group == 2:
                    # anonymous group
                    group = None
                else:
                    group = state.opengroup(name)
                p = _parse_sub(source, state)
                if not source.match(")"):
                    raise error, "unbalanced parenthesis"
                if group is not None:
                    state.closegroup(group)
                subpattern.append((SUBPATTERN, (group, p)))
            else:
                while 1:
                    char = source.get()
                    if char is None:
                        raise error, "unexpected end of pattern"
                    if char == ")":
                        break
                    raise error, "unknown extension"

        elif this == "^":
            subpattern.append((AT, AT_BEGINNING))

        elif this == "$":
            subpattern.append((AT, AT_END))

        elif this and this[0] == "\\":
            code = _escape(source, this, state)
            subpattern.append(code)

        else:
            raise error, "parser error"

    return subpattern

def parse(str, flags=0, pattern=None):
    # parse 're' pattern into list of (opcode, argument) tuples

    source = Tokenizer(str)

    if pattern is None:
        pattern = Pattern()
    pattern.flags = flags
    pattern.str = str

    p = _parse_sub(source, pattern, 0)

    tail = source.get()
    if tail == ")":
        raise error, "unbalanced parenthesis"
    elif tail:
        raise error, "bogus characters at end of regular expression"

    if flags & SRE_FLAG_DEBUG:
        p.dump()

    if not (flags & SRE_FLAG_VERBOSE) and p.pattern.flags & SRE_FLAG_VERBOSE:
        # the VERBOSE flag was switched on inside the pattern.  to be
        # on the safe side, we'll parse the whole thing again...
        return parse(str, p.pattern.flags)

    return p

def parse_template(source, pattern):
    # parse 're' replacement string into list of literals and
    # group references
    s = Tokenizer(source)
    p = []
    a = p.append
    while 1:
        this = s.get()
        if this is None:
            break # end of replacement string
        if this and this[0] == "\\":
            # group
            if this == "\\g":
                name = ""
                if s.match("<"):
                    while 1:
                        char = s.get()
                        if char is None:
                            raise error, "unterminated group name"
                        if char == ">":
                            break
                        name = name + char
                if not name:
                    raise error, "bad group name"
                try:
                    index = int(name)
                except ValueError:
                    if not isname(name):
                        raise error, "bad character in group name"
                    try:
                        index = pattern.groupindex[name]
                    except KeyError:
                        raise IndexError, "unknown group name"
                a((MARK, index))
            elif len(this) > 1 and this[1] in DIGITS:
                code = None
                while 1:
                    group = _group(this, pattern.groups+1)
                    if group:
                        if (s.next not in DIGITS or
                            not _group(this + s.next, pattern.groups+1)):
                            code = MARK, group
                            break
                    elif s.next in OCTDIGITS:
                        this = this + s.get()
                    else:
                        break
                if not code:
                    this = this[1:]
                    code = LITERAL, int(this[-6:], 8) & 0xff
                a(code)
            else:
                try:
                    a(ESCAPES[this])
                except KeyError:
                    for c in this:
                        a((LITERAL, ord(c)))
        else:
            a((LITERAL, ord(this)))
    return p

def expand_template(template, match):
    # XXX: <fl> this is sooooo slow.  drop in the slicelist code instead
    p = []
    a = p.append
    sep = match.string[:0]
    if type(sep) is type(""):
        char = chr
    else:
        char = unichr
    for c, s in template:
        if c is LITERAL:
            a(char(s))
        elif c is MARK:
            s = match.group(s)
            if s is None:
                raise error, "empty group"
            a(s)
    return sep.join(p)