forked from jwdj/EasyABC
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pyparsing.py
3668 lines (3205 loc) · 147 KB
/
pyparsing.py
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
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# module pyparsing.py
#
# Copyright (c) 2003-2013 Paul T. McGuire
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#
__doc__ = \
"""
pyparsing module - Classes and methods to define and execute parsing grammars
The pyparsing module is an alternative approach to creating and executing simple grammars,
vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you
don't need to learn a new syntax for defining grammars or matching expressions - the parsing module
provides a library of classes that you use to construct the grammar directly in Python.
Here is a program to parse "Hello, World!" (or any greeting of the form C{"<salutation>, <addressee>!"})::
from pyparsing import Word, alphas
# define grammar of a greeting
greet = Word( alphas ) + "," + Word( alphas ) + "!"
hello = "Hello, World!"
print (hello, "->", greet.parseString( hello ))
The program outputs the following::
Hello, World! -> ['Hello', ',', 'World', '!']
The Python representation of the grammar is quite readable, owing to the self-explanatory
class names, and the use of '+', '|' and '^' operators.
The parsed results returned from C{parseString()} can be accessed as a nested list, a dictionary, or an
object with named attributes.
The pyparsing module handles some of the problems that are typically vexing when writing text parsers:
- extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.)
- quoted strings
- embedded comments
"""
__version__ = "2.0.1"
__versionTime__ = "16 July 2013 22:22"
__author__ = "Paul McGuire <[email protected]>"
import string
from weakref import ref as wkref
import copy
import sys
import warnings
import re
import sre_constants
import collections
#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )
__all__ = [
'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty',
'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal',
'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or',
'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException',
'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException',
'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter', 'Upcase',
'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore',
'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col',
'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString',
'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums',
'htmlComment', 'javaStyleComment', 'keepOriginalText', 'line', 'lineEnd', 'lineStart', 'lineno',
'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral',
'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables',
'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity',
'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd',
'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute',
'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation',
]
PY_3 = sys.version.startswith('3')
if PY_3:
_MAX_INT = sys.maxsize
basestring = str
unichr = chr
_ustr = str
# build list of single arg builtins, that can be used as parse actions
singleArgBuiltins = [sum, len, sorted, reversed, list, tuple, set, any, all, min, max]
else:
_MAX_INT = sys.maxint
range = xrange
def _ustr(obj):
"""Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries
str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It
then < returns the unicode object | encodes it with the default encoding | ... >.
"""
if isinstance(obj,unicode):
return obj
try:
# If this works, then _ustr(obj) has the same behaviour as str(obj), so
# it won't break any existing code.
return str(obj)
except UnicodeEncodeError:
# The Python docs (http://docs.python.org/ref/customization.html#l2h-182)
# state that "The return value must be a string object". However, does a
# unicode object (being a subclass of basestring) count as a "string
# object"?
# If so, then return a unicode object:
return unicode(obj)
# Else encode it... but how? There are many choices... :)
# Replace unprintables with escape codes?
#return unicode(obj).encode(sys.getdefaultencoding(), 'backslashreplace_errors')
# Replace unprintables with question marks?
#return unicode(obj).encode(sys.getdefaultencoding(), 'replace')
# ...
# build list of single arg builtins, tolerant of Python version, that can be used as parse actions
singleArgBuiltins = []
import __builtin__
for fname in "sum len sorted reversed list tuple set any all min max".split():
try:
singleArgBuiltins.append(getattr(__builtin__,fname))
except AttributeError:
continue
def _xml_escape(data):
"""Escape &, <, >, ", ', etc. in a string of data."""
# ampersand must be replaced first
from_symbols = '&><"\''
to_symbols = ('&'+s+';' for s in "amp gt lt quot apos".split())
for from_,to_ in zip(from_symbols, to_symbols):
data = data.replace(from_, to_)
return data
class _Constants(object):
pass
alphas = string.ascii_lowercase + string.ascii_uppercase
nums = "0123456789"
hexnums = nums + "ABCDEFabcdef"
alphanums = alphas + nums
_bslash = chr(92)
printables = "".join(c for c in string.printable if c not in string.whitespace)
class ParseBaseException(Exception):
"""base exception class for all parsing runtime exceptions"""
# Performance tuning: we construct a *lot* of these, so keep this
# constructor as small and fast as possible
def __init__( self, pstr, loc=0, msg=None, elem=None ):
self.loc = loc
if msg is None:
self.msg = pstr
self.pstr = ""
else:
self.msg = msg
self.pstr = pstr
self.parserElement = elem
def __getattr__( self, aname ):
"""supported attributes by name are:
- lineno - returns the line number of the exception text
- col - returns the column number of the exception text
- line - returns the line containing the exception text
"""
if( aname == "lineno" ):
return lineno( self.loc, self.pstr )
elif( aname in ("col", "column") ):
return col( self.loc, self.pstr )
elif( aname == "line" ):
return line( self.loc, self.pstr )
else:
raise AttributeError(aname)
def __str__( self ):
return "%s (at char %d), (line:%d, col:%d)" % \
( self.msg, self.loc, self.lineno, self.column )
def __repr__( self ):
return _ustr(self)
def markInputline( self, markerString = ">!<" ):
"""Extracts the exception line from the input string, and marks
the location of the exception with a special symbol.
"""
line_str = self.line
line_column = self.column - 1
if markerString:
line_str = "".join(line_str[:line_column],
markerString, line_str[line_column:])
return line_str.strip()
def __dir__(self):
return "loc msg pstr parserElement lineno col line " \
"markInputline __str__ __repr__".split()
class ParseException(ParseBaseException):
"""exception thrown when parse expressions don't match class;
supported attributes by name are:
- lineno - returns the line number of the exception text
- col - returns the column number of the exception text
- line - returns the line containing the exception text
"""
pass
class ParseFatalException(ParseBaseException):
"""user-throwable exception thrown when inconsistent parse content
is found; stops all parsing immediately"""
pass
class ParseSyntaxException(ParseFatalException):
"""just like C{L{ParseFatalException}}, but thrown internally when an
C{L{ErrorStop<And._ErrorStop>}} ('-' operator) indicates that parsing is to stop immediately because
an unbacktrackable syntax error has been found"""
def __init__(self, pe):
super(ParseSyntaxException, self).__init__(
pe.pstr, pe.loc, pe.msg, pe.parserElement)
#~ class ReparseException(ParseBaseException):
#~ """Experimental class - parse actions can raise this exception to cause
#~ pyparsing to reparse the input string:
#~ - with a modified input string, and/or
#~ - with a modified start location
#~ Set the values of the ReparseException in the constructor, and raise the
#~ exception in a parse action to cause pyparsing to use the new string/location.
#~ Setting the values as None causes no change to be made.
#~ """
#~ def __init_( self, newstring, restartLoc ):
#~ self.newParseText = newstring
#~ self.reparseLoc = restartLoc
class RecursiveGrammarException(Exception):
"""exception thrown by C{validate()} if the grammar could be improperly recursive"""
def __init__( self, parseElementList ):
self.parseElementTrace = parseElementList
def __str__( self ):
return "RecursiveGrammarException: %s" % self.parseElementTrace
class _ParseResultsWithOffset(object):
def __init__(self,p1,p2):
self.tup = (p1,p2)
def __getitem__(self,i):
return self.tup[i]
def __repr__(self):
return repr(self.tup)
def setOffset(self,i):
self.tup = (self.tup[0],i)
class ParseResults(object):
"""Structured parse results, to provide multiple means of access to the parsed data:
- as a list (C{len(results)})
- by list index (C{results[0], results[1]}, etc.)
- by attribute (C{results.<resultsName>})
"""
#~ __slots__ = ( "__toklist", "__tokdict", "__doinit", "__name", "__parent", "__accumNames", "__weakref__" )
def __new__(cls, toklist, name=None, asList=True, modal=True ):
if isinstance(toklist, cls):
return toklist
retobj = object.__new__(cls)
retobj.__doinit = True
return retobj
# Performance tuning: we construct a *lot* of these, so keep this
# constructor as small and fast as possible
def __init__( self, toklist, name=None, asList=True, modal=True, isinstance=isinstance ):
if self.__doinit:
self.__doinit = False
self.__name = None
self.__parent = None
self.__accumNames = {}
if isinstance(toklist, list):
self.__toklist = toklist[:]
else:
self.__toklist = [toklist]
self.__tokdict = dict()
if name is not None and name:
if not modal:
self.__accumNames[name] = 0
if isinstance(name,int):
name = _ustr(name) # will always return a str, but use _ustr for consistency
self.__name = name
if not toklist in (None,'',[]):
if isinstance(toklist,basestring):
toklist = [ toklist ]
if asList:
if isinstance(toklist,ParseResults):
self[name] = _ParseResultsWithOffset(toklist.copy(),0)
else:
self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0)
self[name].__name = name
else:
try:
self[name] = toklist[0]
except (KeyError,TypeError,IndexError):
self[name] = toklist
def __getitem__( self, i ):
if isinstance( i, (int,slice) ):
return self.__toklist[i]
else:
if i not in self.__accumNames:
return self.__tokdict[i][-1][0]
else:
return ParseResults([ v[0] for v in self.__tokdict[i] ])
def __setitem__( self, k, v, isinstance=isinstance ):
if isinstance(v,_ParseResultsWithOffset):
self.__tokdict[k] = self.__tokdict.get(k,list()) + [v]
sub = v[0]
elif isinstance(k,int):
self.__toklist[k] = v
sub = v
else:
self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)]
sub = v
if isinstance(sub,ParseResults):
sub.__parent = wkref(self)
def __delitem__( self, i ):
if isinstance(i,(int,slice)):
mylen = len( self.__toklist )
del self.__toklist[i]
# convert int to slice
if isinstance(i, int):
if i < 0:
i += mylen
i = slice(i, i+1)
# get removed indices
removed = list(range(*i.indices(mylen)))
removed.reverse()
# fixup indices in token dictionary
for name in self.__tokdict:
occurrences = self.__tokdict[name]
for j in removed:
for k, (value, position) in enumerate(occurrences):
occurrences[k] = _ParseResultsWithOffset(value, position - (position > j))
else:
del self.__tokdict[i]
def __contains__( self, k ):
return k in self.__tokdict
def __len__( self ): return len( self.__toklist )
def __bool__(self): return len( self.__toklist ) > 0
__nonzero__ = __bool__
def __iter__( self ): return iter( self.__toklist )
def __reversed__( self ): return iter( self.__toklist[::-1] )
def keys( self ):
"""Returns all named result keys."""
return self.__tokdict.keys()
def pop( self, index=-1 ):
"""Removes and returns item at specified index (default=last).
Will work with either numeric indices or dict-key indicies."""
ret = self[index]
del self[index]
return ret
def get(self, key, defaultValue=None):
"""Returns named result matching the given key, or if there is no
such name, then returns the given C{defaultValue} or C{None} if no
C{defaultValue} is specified."""
if key in self:
return self[key]
else:
return defaultValue
def insert( self, index, insStr ):
"""Inserts new element at location index in the list of parsed tokens."""
self.__toklist.insert(index, insStr)
# fixup indices in token dictionary
for name in self.__tokdict:
occurrences = self.__tokdict[name]
for k, (value, position) in enumerate(occurrences):
occurrences[k] = _ParseResultsWithOffset(value, position + (position > index))
def items( self ):
"""Returns all named result keys and values as a list of tuples."""
return [(k,self[k]) for k in self.__tokdict]
def values( self ):
"""Returns all named result values."""
return [ v[-1][0] for v in self.__tokdict.values() ]
def __getattr__( self, name ):
if True: #name not in self.__slots__:
if name in self.__tokdict:
if name not in self.__accumNames:
return self.__tokdict[name][-1][0]
else:
return ParseResults([ v[0] for v in self.__tokdict[name] ])
else:
return ""
return None
def __add__( self, other ):
ret = self.copy()
ret += other
return ret
def __iadd__( self, other ):
if other.__tokdict:
offset = len(self.__toklist)
addoffset = ( lambda a: (a<0 and offset) or (a+offset) )
otheritems = other.__tokdict.items()
otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) )
for (k,vlist) in otheritems for v in vlist]
for k,v in otherdictitems:
self[k] = v
if isinstance(v[0],ParseResults):
v[0].__parent = wkref(self)
self.__toklist += other.__toklist
self.__accumNames.update( other.__accumNames )
return self
def __radd__(self, other):
if isinstance(other,int) and other == 0:
return self.copy()
def __repr__( self ):
return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) )
def __str__( self ):
out = []
for i in self.__toklist:
if isinstance(i, ParseResults):
out.append(_ustr(i))
else:
out.append(repr(i))
return '[' + ', '.join(out) + ']'
def _asStringList( self, sep='' ):
out = []
for item in self.__toklist:
if out and sep:
out.append(sep)
if isinstance( item, ParseResults ):
out += item._asStringList()
else:
out.append( _ustr(item) )
return out
def asList( self ):
"""Returns the parse results as a nested list of matching tokens, all converted to strings."""
out = []
for res in self.__toklist:
if isinstance(res,ParseResults):
out.append( res.asList() )
else:
out.append( res )
return out
def asDict( self ):
"""Returns the named parse results as dictionary."""
return dict( self.items() )
def copy( self ):
"""Returns a new copy of a C{ParseResults} object."""
ret = ParseResults( self.__toklist )
ret.__tokdict = self.__tokdict.copy()
ret.__parent = self.__parent
ret.__accumNames.update( self.__accumNames )
ret.__name = self.__name
return ret
def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ):
"""Returns the parse results as XML. Tags are created for tokens and lists that have defined results names."""
nl = "\n"
out = []
namedItems = dict((v[1],k) for (k,vlist) in self.__tokdict.items()
for v in vlist)
nextLevelIndent = indent + " "
# collapse out indents if formatting is not desired
if not formatted:
indent = ""
nextLevelIndent = ""
nl = ""
selfTag = None
if doctag is not None:
selfTag = doctag
else:
if self.__name:
selfTag = self.__name
if not selfTag:
if namedItemsOnly:
return ""
else:
selfTag = "ITEM"
out += [ nl, indent, "<", selfTag, ">" ]
worklist = self.__toklist
for i,res in enumerate(worklist):
if isinstance(res,ParseResults):
if i in namedItems:
out += [ res.asXML(namedItems[i],
namedItemsOnly and doctag is None,
nextLevelIndent,
formatted)]
else:
out += [ res.asXML(None,
namedItemsOnly and doctag is None,
nextLevelIndent,
formatted)]
else:
# individual token, see if there is a name for it
resTag = None
if i in namedItems:
resTag = namedItems[i]
if not resTag:
if namedItemsOnly:
continue
else:
resTag = "ITEM"
xmlBodyText = _xml_escape(_ustr(res))
out += [ nl, nextLevelIndent, "<", resTag, ">",
xmlBodyText,
"</", resTag, ">" ]
out += [ nl, indent, "</", selfTag, ">" ]
return "".join(out)
def __lookup(self,sub):
for k,vlist in self.__tokdict.items():
for v,loc in vlist:
if sub is v:
return k
return None
def getName(self):
"""Returns the results name for this token expression."""
if self.__name:
return self.__name
elif self.__parent:
par = self.__parent()
if par:
return par.__lookup(self)
else:
return None
elif (len(self) == 1 and
len(self.__tokdict) == 1 and
list(self.__tokdict.values())[0][0][1] in (0,-1)):
return list(self.__tokdict.keys())[0]
else:
return None
def dump(self,indent='',depth=0):
"""Diagnostic method for listing out the contents of a C{ParseResults}.
Accepts an optional C{indent} argument so that this string can be embedded
in a nested display of other data."""
out = []
out.append( indent+_ustr(self.asList()) )
keys = self.items()
keys.sort()
for k,v in keys:
if out:
out.append('\n')
out.append( "%s%s- %s: " % (indent,(' '*depth), k) )
if isinstance(v,ParseResults):
if v.keys():
out.append( v.dump(indent,depth+1) )
else:
out.append(_ustr(v))
else:
out.append(_ustr(v))
return "".join(out)
# add support for pickle protocol
def __getstate__(self):
return ( self.__toklist,
( self.__tokdict.copy(),
self.__parent is not None and self.__parent() or None,
self.__accumNames,
self.__name ) )
def __setstate__(self,state):
self.__toklist = state[0]
(self.__tokdict,
par,
inAccumNames,
self.__name) = state[1]
self.__accumNames = {}
self.__accumNames.update(inAccumNames)
if par is not None:
self.__parent = wkref(par)
else:
self.__parent = None
def __dir__(self):
return dir(super(ParseResults,self)) + list(self.keys())
collections.MutableMapping.register(ParseResults)
def col (loc,strg):
"""Returns current column within a string, counting newlines as line separators.
The first column is number 1.
Note: the default parsing behavior is to expand tabs in the input string
before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
consistent view of the parsed string, the parse location, and line and column
positions within the parsed string.
"""
return (loc<len(strg) and strg[loc] == '\n') and 1 or loc - strg.rfind("\n", 0, loc)
def lineno(loc,strg):
"""Returns current line number within a string, counting newlines as line separators.
The first line is number 1.
Note: the default parsing behavior is to expand tabs in the input string
before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
consistent view of the parsed string, the parse location, and line and column
positions within the parsed string.
"""
return strg.count("\n",0,loc) + 1
def line( loc, strg ):
"""Returns the line of text containing loc within a string, counting newlines as line separators.
"""
lastCR = strg.rfind("\n", 0, loc)
nextCR = strg.find("\n", loc)
if nextCR >= 0:
return strg[lastCR+1:nextCR]
else:
return strg[lastCR+1:]
def _defaultStartDebugAction( instring, loc, expr ):
print ("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) ))
def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ):
print ("Matched " + _ustr(expr) + " -> " + str(toks.asList()))
def _defaultExceptionDebugAction( instring, loc, expr, exc ):
print ("Exception raised:" + _ustr(exc))
def nullDebugAction(*args):
"""'Do-nothing' debug action, to suppress debugging output during parsing."""
pass
# Only works on Python 3.x - nonlocal is toxic to Python 2 installs
#~ 'decorator to trim function calls to match the arity of the target'
#~ def _trim_arity(func, maxargs=3):
#~ if func in singleArgBuiltins:
#~ return lambda s,l,t: func(t)
#~ limit = 0
#~ foundArity = False
#~ def wrapper(*args):
#~ nonlocal limit,foundArity
#~ while 1:
#~ try:
#~ ret = func(*args[limit:])
#~ foundArity = True
#~ return ret
#~ except TypeError:
#~ if limit == maxargs or foundArity:
#~ raise
#~ limit += 1
#~ continue
#~ return wrapper
# this version is Python 2.x-3.x cross-compatible
'decorator to trim function calls to match the arity of the target'
def _trim_arity(func, maxargs=2):
if func in singleArgBuiltins:
return lambda s,l,t: func(t)
limit = [0]
foundArity = [False]
def wrapper(*args):
while 1:
try:
ret = func(*args[limit[0]:])
foundArity[0] = True
return ret
except TypeError:
if limit[0] <= maxargs and not foundArity[0]:
limit[0] += 1
continue
raise
return wrapper
class ParserElement(object):
"""Abstract base level parser element class."""
DEFAULT_WHITE_CHARS = " \n\t\r"
verbose_stacktrace = False
def setDefaultWhitespaceChars( chars ):
"""Overrides the default whitespace chars
"""
ParserElement.DEFAULT_WHITE_CHARS = chars
setDefaultWhitespaceChars = staticmethod(setDefaultWhitespaceChars)
def inlineLiteralsUsing(cls):
"""
Set class to be used for inclusion of string literals into a parser.
"""
ParserElement.literalStringClass = cls
inlineLiteralsUsing = staticmethod(inlineLiteralsUsing)
def __init__( self, savelist=False ):
self.parseAction = list()
self.failAction = None
#~ self.name = "<unknown>" # don't define self.name, let subclasses try/except upcall
self.strRepr = None
self.resultsName = None
self.saveAsList = savelist
self.skipWhitespace = True
self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
self.copyDefaultWhiteChars = True
self.mayReturnEmpty = False # used when checking for left-recursion
self.keepTabs = False
self.ignoreExprs = list()
self.debug = False
self.streamlined = False
self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index
self.errmsg = ""
self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all)
self.debugActions = ( None, None, None ) #custom debug actions
self.re = None
self.callPreparse = True # used to avoid redundant calls to preParse
self.callDuringTry = False
def copy( self ):
"""Make a copy of this C{ParserElement}. Useful for defining different parse actions
for the same parsing pattern, using copies of the original parse element."""
cpy = copy.copy( self )
cpy.parseAction = self.parseAction[:]
cpy.ignoreExprs = self.ignoreExprs[:]
if self.copyDefaultWhiteChars:
cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
return cpy
def setName( self, name ):
"""Define name for this expression, for use in debugging."""
self.name = name
self.errmsg = "Expected " + self.name
if hasattr(self,"exception"):
self.exception.msg = self.errmsg
return self
def setResultsName( self, name, listAllMatches=False ):
"""Define name for referencing matching tokens as a nested attribute
of the returned parse results.
NOTE: this returns a *copy* of the original C{ParserElement} object;
this is so that the client can define a basic element, such as an
integer, and reference it in multiple places with different names.
You can also set results names using the abbreviated syntax,
C{expr("name")} in place of C{expr.setResultsName("name")} -
see L{I{__call__}<__call__>}.
"""
newself = self.copy()
if name.endswith("*"):
name = name[:-1]
listAllMatches=True
newself.resultsName = name
newself.modalResults = not listAllMatches
return newself
def setBreak(self,breakFlag = True):
"""Method to invoke the Python pdb debugger when this element is
about to be parsed. Set C{breakFlag} to True to enable, False to
disable.
"""
if breakFlag:
_parseMethod = self._parse
def breaker(instring, loc, doActions=True, callPreParse=True):
import pdb
pdb.set_trace()
return _parseMethod( instring, loc, doActions, callPreParse )
breaker._originalParseMethod = _parseMethod
self._parse = breaker
else:
if hasattr(self._parse,"_originalParseMethod"):
self._parse = self._parse._originalParseMethod
return self
def setParseAction( self, *fns, **kwargs ):
"""Define action to perform when successfully matching parse element definition.
Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)},
C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where:
- s = the original string being parsed (see note below)
- loc = the location of the matching substring
- toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object
If the functions in fns modify the tokens, they can return them as the return
value from fn, and the modified list of tokens will replace the original.
Otherwise, fn does not need to return any value.
Note: the default parsing behavior is to expand tabs in the input string
before starting the parsing process. See L{I{parseString}<parseString>} for more information
on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
consistent view of the parsed string, the parse location, and line and column
positions within the parsed string.
"""
self.parseAction = list(map(_trim_arity, list(fns)))
self.callDuringTry = ("callDuringTry" in kwargs and kwargs["callDuringTry"])
return self
def addParseAction( self, *fns, **kwargs ):
"""Add parse action to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}."""
self.parseAction += list(map(_trim_arity, list(fns)))
self.callDuringTry = self.callDuringTry or ("callDuringTry" in kwargs and kwargs["callDuringTry"])
return self
def setFailAction( self, fn ):
"""Define action to perform if parsing fails at this expression.
Fail acton fn is a callable function that takes the arguments
C{fn(s,loc,expr,err)} where:
- s = string being parsed
- loc = location where expression match was attempted and failed
- expr = the parse expression that failed
- err = the exception thrown
The function returns no value. It may throw C{L{ParseFatalException}}
if it is desired to stop parsing immediately."""
self.failAction = fn
return self
def _skipIgnorables( self, instring, loc ):
exprsFound = True
while exprsFound:
exprsFound = False
for e in self.ignoreExprs:
try:
while 1:
loc,dummy = e._parse( instring, loc )
exprsFound = True
except ParseException:
pass
return loc
def preParse( self, instring, loc ):
if self.ignoreExprs:
loc = self._skipIgnorables( instring, loc )
if self.skipWhitespace:
wt = self.whiteChars
instrlen = len(instring)
while loc < instrlen and instring[loc] in wt:
loc += 1
return loc
def parseImpl( self, instring, loc, doActions=True ):
return loc, []
def postParse( self, instring, loc, tokenlist ):
return tokenlist
#~ @profile
def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ):
debugging = ( self.debug ) #and doActions )
if debugging or self.failAction:
#~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) ))
if (self.debugActions[0] ):
self.debugActions[0]( instring, loc, self )
if callPreParse and self.callPreparse:
preloc = self.preParse( instring, loc )
else:
preloc = loc
tokensStart = preloc
try:
try:
loc,tokens = self.parseImpl( instring, preloc, doActions )
except IndexError:
raise ParseException( instring, len(instring), self.errmsg, self )
except ParseBaseException as err:
#~ print ("Exception raised:", err)
if self.debugActions[2]:
self.debugActions[2]( instring, tokensStart, self, err )
if self.failAction:
self.failAction( instring, tokensStart, self, err )
raise
else:
if callPreParse and self.callPreparse:
preloc = self.preParse( instring, loc )
else:
preloc = loc
tokensStart = preloc
if self.mayIndexError or loc >= len(instring):
try:
loc,tokens = self.parseImpl( instring, preloc, doActions )
except IndexError:
raise ParseException( instring, len(instring), self.errmsg, self )
else:
loc,tokens = self.parseImpl( instring, preloc, doActions )
tokens = self.postParse( instring, loc, tokens )
retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults )
if self.parseAction and (doActions or self.callDuringTry):
if debugging:
try:
for fn in self.parseAction:
tokens = fn( instring, tokensStart, retTokens )
if tokens is not None:
retTokens = ParseResults( tokens,
self.resultsName,
asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
modal=self.modalResults )
except ParseBaseException as err:
#~ print "Exception raised in user parse action:", err
if (self.debugActions[2] ):
self.debugActions[2]( instring, tokensStart, self, err )
raise
else:
for fn in self.parseAction:
tokens = fn( instring, tokensStart, retTokens )
if tokens is not None:
retTokens = ParseResults( tokens,
self.resultsName,
asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
modal=self.modalResults )
if debugging:
#~ print ("Matched",self,"->",retTokens.asList())
if (self.debugActions[1] ):
self.debugActions[1]( instring, tokensStart, loc, self, retTokens )
return loc, retTokens
def tryParse( self, instring, loc ):
try:
return self._parse( instring, loc, doActions=False )[0]
except ParseFatalException:
raise ParseException( instring, loc, self.errmsg, self)
# this method gets repeatedly called during backtracking with the same arguments -
# we can cache these arguments and save ourselves the trouble of re-parsing the contained expression
def _parseCache( self, instring, loc, doActions=True, callPreParse=True ):
lookup = (self,instring,loc,callPreParse,doActions)
if lookup in ParserElement._exprArgCache:
value = ParserElement._exprArgCache[ lookup ]
if isinstance(value, Exception):
raise value
return (value[0],value[1].copy())
else:
try:
value = self._parseNoCache( instring, loc, doActions, callPreParse )
ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy())
return value
except ParseBaseException as pe:
pe.__traceback__ = None
ParserElement._exprArgCache[ lookup ] = pe
raise
_parse = _parseNoCache
# argument cache for optimizing repeated calls when backtracking through recursive expressions
_exprArgCache = {}
def resetCache():
ParserElement._exprArgCache.clear()
resetCache = staticmethod(resetCache)
_packratEnabled = False
def enablePackrat():
"""Enables "packrat" parsing, which adds memoizing to the parsing logic.
Repeated parse attempts at the same string location (which happens
often in many complex grammars) can immediately return a cached value,
instead of re-executing parsing/validating code. Memoizing is done of
both valid results and parsing exceptions.
This speedup may break existing programs that use parse actions that
have side-effects. For this reason, packrat parsing is disabled when
you first import pyparsing. To activate the packrat feature, your
program must call the class method C{ParserElement.enablePackrat()}. If
your program uses C{psyco} to "compile as you go", you must call
C{enablePackrat} before calling C{psyco.full()}. If you do not do this,
Python will crash. For best results, call C{enablePackrat()} immediately
after importing pyparsing.
"""
if not ParserElement._packratEnabled:
ParserElement._packratEnabled = True
ParserElement._parse = ParserElement._parseCache
enablePackrat = staticmethod(enablePackrat)
def parseString( self, instring, parseAll=False ):