File: GroupLexer.py

package info (click to toggle)
python-stringtemplate3 3.1-4
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 1,392 kB
  • sloc: python: 8,819; makefile: 20
file content (667 lines) | stat: -rw-r--r-- 22,588 bytes parent folder | download | duplicates (2)
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
### $ANTLR 2.7.7 (2006-11-01): "group.g" -> "GroupLexer.py"$
### import antlr and other modules ..
import sys
import antlr

### header action >>> 
from ASTExpr import *
import stringtemplate3
import traceback
### header action <<< 
### preamble action >>> 

### preamble action <<< 
### >>>The Literals<<<
literals = {}
literals[u"default"] = 21
literals[u"group"] = 4
literals[u"implements"] = 7


### import antlr.Token 
from antlr import Token
### >>>The Known Token Types <<<
SKIP                = antlr.SKIP
INVALID_TYPE        = antlr.INVALID_TYPE
EOF_TYPE            = antlr.EOF_TYPE
EOF                 = antlr.EOF
NULL_TREE_LOOKAHEAD = antlr.NULL_TREE_LOOKAHEAD
MIN_USER_TYPE       = antlr.MIN_USER_TYPE
LITERAL_group = 4
ID = 5
COLON = 6
LITERAL_implements = 7
COMMA = 8
SEMI = 9
AT = 10
DOT = 11
LPAREN = 12
RPAREN = 13
DEFINED_TO_BE = 14
STRING = 15
BIGSTRING = 16
ASSIGN = 17
ANONYMOUS_TEMPLATE = 18
LBRACK = 19
RBRACK = 20
LITERAL_default = 21
STAR = 22
PLUS = 23
OPTIONAL = 24
SL_COMMENT = 25
ML_COMMENT = 26
NL = 27
WS = 28

class Lexer(antlr.CharScanner) :
    ### user action >>>
    ### user action <<<
    def __init__(self, *argv, **kwargs) :
        antlr.CharScanner.__init__(self, *argv, **kwargs)
        self.caseSensitiveLiterals = True
        self.setCaseSensitive(True)
        self.literals = literals
    
    def nextToken(self):
        while True:
            try: ### try again ..
                while True:
                    _token = None
                    _ttype = INVALID_TYPE
                    self.resetText()
                    try: ## for char stream error handling
                        try: ##for lexical error handling
                            la1 = self.LA(1)
                            if False:
                                pass
                            elif la1 and la1 in u'ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz':
                                pass
                                self.mID(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'"':
                                pass
                                self.mSTRING(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'<':
                                pass
                                self.mBIGSTRING(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'{':
                                pass
                                self.mANONYMOUS_TEMPLATE(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'@':
                                pass
                                self.mAT(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'(':
                                pass
                                self.mLPAREN(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u')':
                                pass
                                self.mRPAREN(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'[':
                                pass
                                self.mLBRACK(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u']':
                                pass
                                self.mRBRACK(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u',':
                                pass
                                self.mCOMMA(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'.':
                                pass
                                self.mDOT(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u';':
                                pass
                                self.mSEMI(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'*':
                                pass
                                self.mSTAR(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'+':
                                pass
                                self.mPLUS(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'=':
                                pass
                                self.mASSIGN(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'?':
                                pass
                                self.mOPTIONAL(True)
                                theRetToken = self._returnToken
                            elif la1 and la1 in u'\t\n\u000c\r ':
                                pass
                                self.mWS(True)
                                theRetToken = self._returnToken
                            else:
                                if (self.LA(1)==u':') and (self.LA(2)==u':'):
                                    pass
                                    self.mDEFINED_TO_BE(True)
                                    theRetToken = self._returnToken
                                elif (self.LA(1)==u'/') and (self.LA(2)==u'/'):
                                    pass
                                    self.mSL_COMMENT(True)
                                    theRetToken = self._returnToken
                                elif (self.LA(1)==u'/') and (self.LA(2)==u'*'):
                                    pass
                                    self.mML_COMMENT(True)
                                    theRetToken = self._returnToken
                                elif (self.LA(1)==u':') and (True):
                                    pass
                                    self.mCOLON(True)
                                    theRetToken = self._returnToken
                                else:
                                    self.default(self.LA(1))
                                
                            if not self._returnToken:
                                raise antlr.TryAgain ### found SKIP token
                            ### return token to caller
                            return self._returnToken
                        ### handle lexical errors ....
                        except antlr.RecognitionException as e:
                            raise antlr.TokenStreamRecognitionException(e)
                    ### handle char stream errors ...
                    except antlr.CharStreamException as cse:
                        if isinstance(cse, antlr.CharStreamIOException):
                            raise antlr.TokenStreamIOException(cse.io)
                        else:
                            raise antlr.TokenStreamException(str(cse))
            except antlr.TryAgain:
                pass
        
    def mID(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = ID
        _saveIndex = 0
        pass
        la1 = self.LA(1)
        if False:
            pass
        elif la1 and la1 in u'abcdefghijklmnopqrstuvwxyz':
            pass
            self.matchRange(u'a', u'z')
        elif la1 and la1 in u'ABCDEFGHIJKLMNOPQRSTUVWXYZ':
            pass
            self.matchRange(u'A', u'Z')
        elif la1 and la1 in u'_':
            pass
            self.match('_')
        else:
                self.raise_NoViableAlt(self.LA(1))
            
        while True:
            la1 = self.LA(1)
            if False:
                pass
            elif la1 and la1 in u'abcdefghijklmnopqrstuvwxyz':
                pass
                self.matchRange(u'a', u'z')
            elif la1 and la1 in u'ABCDEFGHIJKLMNOPQRSTUVWXYZ':
                pass
                self.matchRange(u'A', u'Z')
            elif la1 and la1 in u'0123456789':
                pass
                self.matchRange(u'0', u'9')
            elif la1 and la1 in u'-':
                pass
                self.match('-')
            elif la1 and la1 in u'_':
                pass
                self.match('_')
            else:
                    break
                
        ### option { testLiterals=true } 
        _ttype = self.testLiteralsTable(_ttype)
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mSTRING(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = STRING
        _saveIndex = 0
        pass
        _saveIndex = self.text.length()
        self.match('"')
        self.text.setLength(_saveIndex)
        while True:
            if (self.LA(1)==u'\\') and (self.LA(2)==u'"'):
                pass
                _saveIndex = self.text.length()
                self.match('\\')
                self.text.setLength(_saveIndex)
                self.match('"')
            elif (self.LA(1)==u'\\') and (_tokenSet_0.member(self.LA(2))):
                pass
                self.match('\\')
                self.matchNot('"')
            elif (_tokenSet_1.member(self.LA(1))):
                pass
                self.matchNot('"')
            else:
                break
            
        _saveIndex = self.text.length()
        self.match('"')
        self.text.setLength(_saveIndex)
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mBIGSTRING(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = BIGSTRING
        _saveIndex = 0
        pass
        _saveIndex = self.text.length()
        self.match("<<")
        self.text.setLength(_saveIndex)
        if (self.LA(1)==u'\n' or self.LA(1)==u'\r') and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
            pass
            _saveIndex = self.text.length()
            self.mNL(False)
            self.text.setLength(_saveIndex)
            self.newline()
        elif ((self.LA(1) >= u'\u0000' and self.LA(1) <= u'\ufffe')) and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
            pass
        else:
            self.raise_NoViableAlt(self.LA(1))
        
        while True:
            ###  nongreedy exit test
            if ((self.LA(1)==u'>') and (self.LA(2)==u'>')):
                break
            if ((self.LA(1)==u'\r') and (self.LA(2)==u'\n') and ( self.LA(3) == '>' and self.LA(4) == '>' )):
                pass
                _saveIndex = self.text.length()
                self.match('\r')
                self.text.setLength(_saveIndex)
                _saveIndex = self.text.length()
                self.match('\n')
                self.text.setLength(_saveIndex)
                self.newline()
            elif ((self.LA(1)==u'\n') and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')) and ( self.LA(2) == '>' and self.LA(3) == '>' )):
                pass
                _saveIndex = self.text.length()
                self.match('\n')
                self.text.setLength(_saveIndex)
                self.newline()
            elif ((self.LA(1)==u'\r') and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')) and ( self.LA(2) == '>' and self.LA(3) == '>' )):
                pass
                _saveIndex = self.text.length()
                self.match('\r')
                self.text.setLength(_saveIndex)
                self.newline()
            elif (self.LA(1)==u'\n' or self.LA(1)==u'\r') and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
                pass
                self.mNL(False)
                self.newline()
            elif (self.LA(1)==u'\\') and (self.LA(2)==u'>'):
                pass
                _saveIndex = self.text.length()
                self.match('\\')
                self.text.setLength(_saveIndex)
                self.match('>')
            elif ((self.LA(1) >= u'\u0000' and self.LA(1) <= u'\ufffe')) and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
                pass
                self.matchNot(antlr.EOF_CHAR)
            else:
                break
            
        _saveIndex = self.text.length()
        self.match(">>")
        self.text.setLength(_saveIndex)
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mNL(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = NL
        _saveIndex = 0
        if (self.LA(1)==u'\r') and (self.LA(2)==u'\n'):
            pass
            self.match('\r')
            self.match('\n')
        elif (self.LA(1)==u'\r') and (True):
            pass
            self.match('\r')
        elif (self.LA(1)==u'\n'):
            pass
            self.match('\n')
        else:
            self.raise_NoViableAlt(self.LA(1))
        
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mANONYMOUS_TEMPLATE(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = ANONYMOUS_TEMPLATE
        _saveIndex = 0
        args = None
        t = None
        pass
        _saveIndex = self.text.length()
        self.match('{')
        self.text.setLength(_saveIndex)
        while True:
            ###  nongreedy exit test
            if ((self.LA(1)==u'}') and (True)):
                break
            if (self.LA(1)==u'\n' or self.LA(1)==u'\r') and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
                pass
                la1 = self.LA(1)
                if False:
                    pass
                elif la1 and la1 in u'\r':
                    pass
                    self.match('\r')
                elif la1 and la1 in u'\n':
                    pass
                else:
                        self.raise_NoViableAlt(self.LA(1))
                    
                self.match('\n')
                self.newline()
            elif (self.LA(1)==u'\\') and (self.LA(2)==u'>'):
                pass
                _saveIndex = self.text.length()
                self.match('\\')
                self.text.setLength(_saveIndex)
                self.match('>')
            elif ((self.LA(1) >= u'\u0000' and self.LA(1) <= u'\ufffe')) and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
                pass
                self.matchNot(antlr.EOF_CHAR)
            else:
                break
            
        _saveIndex = self.text.length()
        self.match('}')
        self.text.setLength(_saveIndex)
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mAT(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = AT
        _saveIndex = 0
        pass
        self.match('@')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mLPAREN(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = LPAREN
        _saveIndex = 0
        pass
        self.match('(')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mRPAREN(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = RPAREN
        _saveIndex = 0
        pass
        self.match(')')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mLBRACK(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = LBRACK
        _saveIndex = 0
        pass
        self.match('[')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mRBRACK(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = RBRACK
        _saveIndex = 0
        pass
        self.match(']')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mCOMMA(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = COMMA
        _saveIndex = 0
        pass
        self.match(',')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mDOT(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = DOT
        _saveIndex = 0
        pass
        self.match('.')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mDEFINED_TO_BE(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = DEFINED_TO_BE
        _saveIndex = 0
        pass
        self.match("::=")
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mSEMI(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = SEMI
        _saveIndex = 0
        pass
        self.match(';')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mCOLON(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = COLON
        _saveIndex = 0
        pass
        self.match(':')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mSTAR(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = STAR
        _saveIndex = 0
        pass
        self.match('*')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mPLUS(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = PLUS
        _saveIndex = 0
        pass
        self.match('+')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mASSIGN(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = ASSIGN
        _saveIndex = 0
        pass
        self.match('=')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mOPTIONAL(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = OPTIONAL
        _saveIndex = 0
        pass
        self.match('?')
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mSL_COMMENT(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = SL_COMMENT
        _saveIndex = 0
        pass
        self.match("//")
        while True:
            if (_tokenSet_2.member(self.LA(1))):
                pass
                self.match(_tokenSet_2)
            else:
                break
            
        if (self.LA(1)==u'\n' or self.LA(1)==u'\r'):
            pass
            self.mNL(False)
        else: ## <m4>
                pass
            
        _ttype = SKIP; self.newline()
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mML_COMMENT(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = ML_COMMENT
        _saveIndex = 0
        pass
        self.match("/*")
        while True:
            ###  nongreedy exit test
            if ((self.LA(1)==u'*') and (self.LA(2)==u'/')):
                break
            if (self.LA(1)==u'\n' or self.LA(1)==u'\r') and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
                pass
                self.mNL(False)
                self.newline()
            elif ((self.LA(1) >= u'\u0000' and self.LA(1) <= u'\ufffe')) and ((self.LA(2) >= u'\u0000' and self.LA(2) <= u'\ufffe')):
                pass
                self.matchNot(antlr.EOF_CHAR)
            else:
                break
            
        self.match("*/")
        _ttype = SKIP
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    def mWS(self, _createToken):    
        _ttype = 0
        _token = None
        _begin = self.text.length()
        _ttype = WS
        _saveIndex = 0
        pass
        _cnt66= 0
        while True:
            la1 = self.LA(1)
            if False:
                pass
            elif la1 and la1 in u' ':
                pass
                self.match(' ')
            elif la1 and la1 in u'\t':
                pass
                self.match('\t')
            elif la1 and la1 in u'\u000c':
                pass
                self.match('\f')
            elif la1 and la1 in u'\n\r':
                pass
                self.mNL(False)
                self.newline()
            else:
                    break
                
            _cnt66 += 1
        if _cnt66 < 1:
            self.raise_NoViableAlt(self.LA(1))
        _ttype = SKIP
        self.set_return_token(_createToken, _token, _ttype, _begin)
    
    

### generate bit set
def mk_tokenSet_0(): 
    data = [0] * 2048 ### init list
    data[0] =-17179869185
    for x in range(1, 1023):
        data[x] = -1
    data[1023] =9223372036854775807
    return data
_tokenSet_0 = antlr.BitSet(mk_tokenSet_0())

### generate bit set
def mk_tokenSet_1(): 
    data = [0] * 2048 ### init list
    data[0] =-17179869185
    data[1] =-268435457
    for x in range(2, 1023):
        data[x] = -1
    data[1023] =9223372036854775807
    return data
_tokenSet_1 = antlr.BitSet(mk_tokenSet_1())

### generate bit set
def mk_tokenSet_2(): 
    data = [0] * 2048 ### init list
    data[0] =-9217
    for x in range(1, 1023):
        data[x] = -1
    data[1023] =9223372036854775807
    return data
_tokenSet_2 = antlr.BitSet(mk_tokenSet_2())
    
### __main__ header action >>> 
if __name__ == '__main__' :
    import sys
    import antlr
    import GroupLexer
    
    ### create lexer - shall read from stdin
    try:
        for token in GroupLexer.Lexer():
            print(token)
            
    except antlr.TokenStreamException as e:
        print("error: exception caught while lexing")
### __main__ header action <<<