-
Notifications
You must be signed in to change notification settings - Fork 11
/
stringStructs.py
906 lines (810 loc) · 41.8 KB
/
stringStructs.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
# CodeDog Program Maker
# This file is code to convert "string" style structures into 'struct' style structures.
import re
import progSpec
import codeDogParser
from progSpec import cdlog, cdErr
def codeDogTypeToString(classes, tags, field):
#print "FIELD:", field
S=''
fieldName=field['fieldName']
fieldType=progSpec.getFieldType(field)
fieldValue =field['value']
fieldOwner =field['owner']
if(fieldType == 'flag'):
if fieldValue!=None and fieldValue!=0 and fieldValue!='false':
S+='flag: ' + fieldName + ' <- true\n'
else: S+='flag: ' + fieldName +'\n'
elif fieldType=='mode':
if fieldValue!=None:
S+='mode ['+field['enumList']+']: ' + fieldName + ' <- '+fieldValue+'\n'
else: S+='mode ['+field['enumList']+']: ' + fieldName +'\n'
elif fieldOwner=='const':
#print 'const ', fieldType, ': ', fieldName, ' <- ',fieldValue
#S+='const '+fieldType+': ' + fieldName + ' <- '+fieldValue+'\n'
pass
elif fieldOwner=='const':
print("Finish This")
return S
rules=[]
constDefs=[]
EParserConsts=[]
ruleSet={} # Used to track duplicates
globalFieldCount=0
globalTempVarIdx=0
startSymbol=''
def genParserCode():
global rules
global constDefs
global EParserConsts
RuleList=''
for rule in rules:
if rule[1]=='term':
RuleList+=' addTerminalProd("' + rule[0] +'", ' + rule[2] + ', "' + str(rule[3]).replace('::','_') + '")\n'
elif rule[1]=='nonterm':
RuleList+=' addNon_TermProd("' + rule[0] +'", ' + rule[2] + ', ' + str(rule[3]).replace('::','_') + ')\n'
ConstList=''
for C in constDefs:
ConstList+=' const int: ' + C[0].replace('::','_') + ' <- ' + str(C[1]) + '\n'
EParserConstList=''
for C in EParserConsts:
EParserConstList+=' const int: ' + C[0].replace('::','_') + ' <- ' + str(C[1]) + '\n'
code= r"""
struct EGrammar{
#CONST_CODE_HERE
void: populateGrammar() <- {
startProduction <- """+startSymbol+"""
setQuickParse(false)
clear()
#GRAMMAR_CODE_HERE
preCalcNullability()
preCalcStreamPoints()
}
void: INIT() <- {populateGrammar()}
}
struct EParser{
#EP_CONST_CODE_HERE
#EXTRA_PARSER_FUNCS_HERE
}
"""
code=code.replace('#EXTRA_PARSER_FUNCS_HERE', parserFunctionAccumulator, 1)
code=code.replace('#CONST_CODE_HERE', ConstList, 1)
code=code.replace('#EP_CONST_CODE_HERE', EParserConstList, 1)
code=code.replace('#GRAMMAR_CODE_HERE', RuleList, 1)
return code
def writePositionalFetch(classes, tags, field):
fname=field['fieldName']
fieldType=str(progSpec.getFieldType(field))
S="""
me fetchResult: fetch_%s() <- {
if(%s_hasVal) {return (fetchOK)}
}
"""% (fname, fname)
return S
#print 'FIELD:', fname, field['owner'], '"'+fieldType+'"'
if(field['owner']=='const' and fieldType=='string'):
S+=' %s_hasLen <- true \n %s_span.len <- '% (fname, fname) + str(len(field['value']))
S+=" if(! %s_hasPos){pos <- pred.pos+pred.len}\n" % (fname)
S+=" if( %s_hasPos){\n" % (fname)
# Scoop Data
S+=' FieldTYpe("' + fieldType +'")\n'
if progSpec.isStruct(fieldType):
#print " Call stuct's fetch()"
pass
#elif fieldType=='':
# Set and propogate length
S+=" }\n"
S+=' }'
return S
def writePositionalSet(field):
return " // Positional Set() TBD\n";
def writeContextualGet(field):
return " // Contextual Get() TBD\n";
def writeContextualSet(field):
return " // Contextual Set() TBD\n";
def appendRule(ruleName, termOrNot, pFlags, prodData):
global rules
global constDefs
global EParserConsts
global ruleSet
# If rule already exists, return the name rather than recreate it
# is there a rule with the same term, flags, and prodData? (Only care about term+parseSEQ+data)
if (ruleName in ruleSet):
ruleSet[ruleName]+=1
else:
thisIDX=len(rules)
if not isinstance(ruleName, str):
ruleName="rule"+str(thisIDX)
constDefs.append([ruleName, str(thisIDX)])
if pFlags=='parseAUTO': EParserConsts.append([ruleName, str(thisIDX)])
#print "PRODDATA:", prodData
if isinstance(prodData, list):
prodData='['+(', '.join(map(str,prodData))) + ']'
rules.append([ruleName, termOrNot, pFlags, prodData])
ruleSet[ruleName]=0
return ruleName
definedRules={}
def populateBaseRules():
definedRulePairs=[['{','lBrace'], ['}','rBrace'], ['(','lParen'], [')','rParen'], ['[','lBrckt'], [']','rBrckt'], [' ','space'], [',','comma'],
['!','bang'], ['.','period'], ['/','slash'], ['?','question'], [':','colon'], ['`','quoteBack'], ["'",'quote1'], [r'\"','quote2'],
['-','minus'], ['+','plus'], ['=','equals'], ['*','star'], ['<','lessThan'], ['>','grtrThan'], ['@','atSign'], ['#','hashMark'], ['$','dollarSign'],
['%','percent'], ['^','carot'], ['~','tilde'], ['_','underscore'], ['|','bar'], [r'\\','backSlash'], [';','semiColon'] ]
for pair in definedRulePairs:
appendRule(pair[1], "term", "parseSEQ", pair[0])
definedRules[pair[0]]=pair[1]
# Define common string formats
appendRule('alphaSeq', 'term', 'parseAUTO', "an alphabetic string")
appendRule('uintSeq', 'term', 'parseAUTO', 'an unsigned integer')
appendRule('intSeq', 'term', 'parseAUTO', 'an integer')
appendRule('RdxSeq', 'term', 'parseAUTO', 'a number')
appendRule('alphaNumSeq', 'term', 'parseAUTO', "an alpha-numeric string")
appendRule('ws', 'term', 'parseAUTO', 'white space')
appendRule('wsc', 'term', 'parseAUTO', 'white space or C comment')
appendRule('quotedStr', 'term', 'parseAUTO', "a quoted string with single or double quotes and escapes")
appendRule('quotedStr1', 'term', 'parseAUTO', "a single quoted string with escapes")
appendRule('quotedStr2', 'term', 'parseAUTO', "a double quoted string with escapes")
appendRule('HexNum_str', 'term', 'parseAUTO', "a hexadecimal number")
appendRule('BinNum_str', 'term', 'parseAUTO', "a binary number")
appendRule('BigInt', 'term', 'parseAUTO', "an integer")
appendRule('FlexNum', 'term', 'parseAUTO', "a rational number")
appendRule('CID', 'term', 'parseAUTO', 'a C-like identifier')
appendRule('UniID', 'term', 'parseAUTO', 'a unicode identifier')
appendRule('printables', 'term', 'parseAUTO', "a seqence of printable chars")
appendRule('toEOL', 'term', 'parseAUTO', "read to End Of Line, including EOL.")
# TODO: delimited List, keyWord
nextParseNameID=0 # Global used to uniquify sub-seqs and sub-alts in a struct parse. E.g.: ruleName: parse_myStruct_sub1
def fetchOrWriteTerminalParseRule(modelName, field, logLvl):
global nextParseNameID
#print "FIELD_IN:", modelName, field
fieldName='N/A'
fieldValue=''
if 'value' in field: fieldValue =field['value']
typeSpec = field['typeSpec']
fieldType = progSpec.getFieldType(typeSpec)
fieldOwner = typeSpec['owner']
if 'fieldName' in field: fieldName =field['fieldName']
cdlog(logLvl, "WRITING PARSE RULE for: {}.{}".format(modelName, fieldName))
#print "WRITE PARSE RULE:", modelName, fieldName
nameIn=None
nameOut=None
if fieldOwner=='const':
if fieldType=='string':
if fieldValue in definedRules: nameOut=definedRules[fieldValue]
else: nameOut=appendRule(nameIn, "term", "parseSEQ", fieldValue)
elif fieldType[0:4]=='uint': nameOut=appendRule(nameIn, "term", "parseSEQ", fieldValue)
elif fieldType[0:3]=='int': nameOut=appendRule(nameIn, "term", "parseSEQ", fieldValue)
elif fieldType[0:6]=='double': nameOut=appendRule(nameIn, "term", "parseSEQ", fieldValue)
elif fieldType[0:4]=='char': nameOut=appendRule(nameIn, "term", "parseSEQ", fieldValue)
elif fieldType[0:4]=='bool': nameOut=appendRule(nameIn, "term", "parseSEQ", fieldValue)
else:
print("Unusable const type in fetchOrWriteTerminalParseRule():", fieldType); exit(2);
elif fieldOwner=='me' or fieldOwner=='their' or fieldOwner=='our':
if fieldType=='string': nameOut='quotedStr'
elif fieldType[0:4]=='uint': nameOut='uintSeq'
elif fieldType[0:3]=='int': nameOut='intSeq'
elif fieldType[0:6]=='double': nameOut='RdxSeq'
elif fieldType[0:4]=='char': nameOut=appendRule(nameIn, "term", "parseSEQ", None)
elif fieldType[0:4]=='bool': nameOut=appendRule(nameIn, "term", "parseSEQ", None)
elif progSpec.isStruct(fieldType):
objName=progSpec.fieldTypeKeyword(fieldType)
if (objName=='ws' or objName=='wsc' or objName=='quotedStr' or objName=='quotedStr1' or objName=='quotedStr2'
or objName=='CID' or objName=='UniID' or objName=='printables' or objName=='toEOL' or objName=='alphaNumSeq'
or progSpec.typeIsInteger(objName)):
nameOut=objName
else:
if objName=='[' or objName=='{': # This is an ALT or SEQ sub structure
print("ERROR: These should be handled in writeNonTermParseRule().\n")
exit(1)
else: nameOut=objName+'_str'
elif progSpec.isAlt(fieldType):
pass
elif progSpec.isCofactual(fieldType):
pass
else:
print("Unusable type in fetchOrWriteTerminalParseRule():", fieldType); exit(2);
else: print("Pointer types not yet handled in fetchOrWriteTerminalParseRule():", fieldType); exit(2);
if progSpec.isAContainer(typeSpec):
global rules
containerTypeSpec = progSpec.getContainerSpec(typeSpec)
idxType=''
if 'indexType' in containerTypeSpec:
idxType=containerTypeSpec['indexType']
if(isinstance(containerTypeSpec['datastructID'], str)):
datastructID = containerTypeSpec['datastructID']
else: # it's a parseResult
datastructID = containerTypeSpec['datastructID'][0]
if idxType[0:4]=='uint': pass
if(datastructID=='list'):
nameOut=appendRule(nameOut+'_REP', "nonterm", "parseREP", [nameOut, 0, 0])
elif datastructID=='opt':
nameOut=appendRule(nameOut+'_OPT', "nonterm", "parseREP", [nameOut, 0, 1])
#print("NAMEOUT:", nameOut)
field['parseRule']=nameOut
return nameOut
def writeNonTermParseRule(classes, tags, modelName, fields, SeqOrAlt, nameSuffix, logLvl):
global nextParseNameID
nameIn=modelName+nameSuffix
# Allocate or fetch a rule identifier for each '>' field.
partIndexes=[]
for field in fields:
fname=field['fieldName']
if fname==None: fname=''
else: fname='_'+fname
typeSpec =field['typeSpec']
if(field['isNext']==True): # means in the parse there was a '>' symbol, a sequence seperator
firstItm=progSpec.getFieldType(field['typeSpec'])[0]
if firstItm=='[' or firstItm=='{': # Handle an ALT or SEQ sub structure
cdlog(logLvl, "NonTERM: {} = {}".format(fname, firstItm))
nextParseNameID+=1
if firstItm=='[':
innerSeqOrAlt='parseALT'
newNameSuffix = nameSuffix+fname+'_ALT'+str(nextParseNameID)
else:
innerSeqOrAlt='parseSEQ'
newNameSuffix = nameSuffix+fname+'_SEQ'+str(nextParseNameID)
innerFields=field['innerDefs']
ruleIdxStr = writeNonTermParseRule(classes, tags, modelName, innerFields, innerSeqOrAlt, newNameSuffix, logLvl+1)
field['parseRule']=ruleIdxStr
if progSpec.isAContainer(typeSpec):
# anything with [] is a container: lists and optionals
global rules
containerTypeSpec = progSpec.getContainerSpec(typeSpec)
idxType=''
if 'indexType' in containerTypeSpec:
idxType=containerTypeSpec['indexType']
if(isinstance(containerTypeSpec['datastructID'], str)):
datastructID = containerTypeSpec['datastructID']
else: # it's a parseResult
datastructID = containerTypeSpec['datastructID'][0]
if idxType[0:4]=='uint': pass
if(datastructID=='list'):
ruleIdxStr=appendRule(ruleIdxStr+'_REP', "nonterm", "parseREP", [ruleIdxStr, 0, 0])
elif datastructID=='opt':
ruleIdxStr=appendRule(ruleIdxStr+'_OPT', "nonterm", "parseREP", [ruleIdxStr, 0, 1])
else:
ruleIdxStr = fetchOrWriteTerminalParseRule(modelName, field, logLvl)
partIndexes.append(ruleIdxStr)
else: pass; # These fields probably have corresponding cofactuals
nameOut=appendRule(nameIn, "nonterm", SeqOrAlt, partIndexes)
return nameOut
####################################################### E x t r a c t i o n F u n c t i o n s
def getFunctionName(fromName, toName):
if len(fromName)>=5 and fromName[-5:-3]=='::': fromName=fromName[:-5]
if len(toName)>=5 and toName[-5:-3]=='::': toName=toName[:-5]
S='Extract_'+fromName.replace('::', '_')+'_to_'+toName.replace('::', '_')
return S
def fetchMemVersion(classes, objName):
if objName=='[' or objName=='{': return [None, None]
memObj = progSpec.findSpecOf(classes[0], objName, 'struct')
if memObj==None: return [None, None]
return [memObj, objName]
def Write_ALT_Extracter(classes, parentStructName, fields, VarTagBase, VarTagSuffix, VarName, indent, level, logLvl):
# Structname should be the name of the structure being parsed. It will be converted to the mem version to get 'to' fields.
# Fields is the list of alternates.
# VarTag is a string used to create local variables.
# VarName is the LVAL variable name.
global globalFieldCount
cdlog(logLvl, "WRITING code to extract one of {} from parse tree...".format(parentStructName))
InnerMemObjFields = []
progSpec.populateCallableStructFields(InnerMemObjFields, classes, parentStructName)
if parentStructName.find('::') != -1: cdErr("TODO: Make string parsing work on derived classes. Probably just select the correct fields for the destination struct.")
S=""
# Code to fetch the ruleIDX of this ALT. If the parse was terminal (i.e., 'const'), it will be at a different place.
if(level==-1):
level=1
VarTag='SRec1'
VarTagSuffix='0'
RHS = VarTagBase+VarTagSuffix
else:
globalFieldCount+=1
VarTag=VarTagBase+str(level)
RHS= 'getChildStateRec('+ VarTagBase + str(level-1)+', EP)'+VarTagSuffix
indent2 = indent+' '
S+='\n'+indent+'{\n'
S+='\n'+indent2+'our stateRec: '+VarTag+' <- '+RHS+'\n' # shared_ptr<stateRec > SRec1 = SRec0->child;
loopVarName = "ruleIDX"+str(globalFieldCount)
S+=indent2+'me int: '+loopVarName+' <- getChildStateRec('+VarTag+', EP).productionID\n'
#print "RULEIDX:", indent, parentStructName, VarName
if VarName!='memStruct':
S+=indent2 + 'me string: '+VarName+'\n'
count=0
S+= indent2+"switch("+loopVarName+"){\n"
for altField in fields:
if(altField['isNext']!=True): continue; # This field isn't in the parse stream.
cdlog(logLvl+1, "ALT: {}".format(altField['parseRule']))
if not 'parseRule' in altField: print("Error: Is syntax missing a '>'?"); exit(2);
S+=indent2+" case " + altField['parseRule'] + ":{\n"
coFactualCode=''
if 'coFactuals' in altField:
#Extract field and cofactsList
for coFact in altField['coFactuals']:
coFactualCode+= indent2 +' ' + VarName + '.' + coFact[0] + ' <- ' + coFact[2] + "\n"
cdlog(logLvl+2, "Cofactual: "+coFactualCode)
S+=coFactualCode
S+=Write_fieldExtracter(classes, parentStructName, altField, InnerMemObjFields, VarTagBase, VarName, False, coFactualCode, indent2+' ', level, logLvl+1)
S+=indent2+" }\n"
count+=1
S+=indent2+"}"
S+=indent+"}"
return S
def CodeRValExpr(toFieldType, VarTag, suffix):
if toFieldType=='string': CODE_RVAL='makeStr('+VarTag+'.child.next'+suffix+', EP)'+"\n"
elif toFieldType[0:4]=='uint': CODE_RVAL='makeInt('+VarTag+'.child.next'+suffix+', EP)'+"\n"
elif toFieldType[0:3]=='int': CODE_RVAL='makeInt('+VarTag+'.child.next'+suffix+', EP)'+"\n"
elif toFieldType[0:6]=='double': CODE_RVAL='makeDblFromStr('+VarTag+'.child.next'+suffix+')'+"\n"
elif toFieldType[0:4]=='char': CODE_RVAL="crntStr[0]"+"\n"
elif toFieldType[0:4]=='bool': CODE_RVAL='crntStr=="true"'+"\n"
elif toFieldType[0:4]=='flag': CODE_RVAL=''
else: print("TOFIELDTYPE:", toFieldType); exit(2);
return CODE_RVAL
postParseFunctionsByClassName={}
def getPostParseFunctionName(classes, structName):
if structName in postParseFunctionsByClassName:
return postParseFunctionsByClassName[structName]
if progSpec.doesClassContainFunc(classes, structName, 'postParseProcessing'):
postParseFunctionsByClassName[structName]='postParseProcessing'
return 'postParseProcessing'
elif progSpec.doesClassContainFunc(classes, structName, 'postParseProcessingEtc'):
postParseFunctionsByClassName[structName]='EP.postParseProcessingEtc'
return 'EP.postParseProcessingEtc'
return None
def Write_fieldExtracter(classes, ToStructName, field, memObjFields, VarTagBase, VarName, advancePtr, coFactualCode, indent, level, logLvl):
debugTmp=False # Erase this line
VarTag=VarTagBase+str(level)
################### G a t h e r N e e d e d I n f o r m a t i o n
global globalFieldCount
global globalTempVarIdx
S=''
fieldName = field['fieldName']
fieldIsNext= field['isNext']
fieldValue = field['value']
typeSpec = field['typeSpec']
fieldType = progSpec.getFieldType(typeSpec)
fieldOwner =typeSpec['owner']
fromIsEmbeddedAlt = (not isinstance(fieldType, str) and fieldType[0]=='[')
fromIsEmbeddedSeq = (not isinstance(fieldType, str) and fieldType[0]=='{')
fromIsEmbedded = fromIsEmbeddedAlt or fromIsEmbeddedSeq
if(fieldIsNext!=True): return '' # This field isn't in the parse stream.
[memObj, memVersionName]=fetchMemVersion(classes, ToStructName)
toField = progSpec.fetchFieldByName(memObjFields, fieldName)
if(toField==None):
#print " TOFIELD == None", fieldName
# Even tho there is no LVAL, we need to move the cursor. Also, there could be a co-factual.
toFieldType = progSpec.TypeSpecsMinimumBaseType(classes, typeSpec)
toTypeSpec=typeSpec
toFieldOwner="me"
else:
toTypeSpec = toField['typeSpec']
if progSpec.isNewContainerTempFunc(toTypeSpec):
toFieldType = progSpec.getNewContainerFirstElementTypeTempFunc2(toTypeSpec)
toFieldOwner = progSpec.getNewContainerFirstElementOwnerTempFunc(toTypeSpec)
else:
toFieldType = progSpec.getFieldType(toTypeSpec)
toFieldOwner = progSpec.getContainerFirstElementOwner(toTypeSpec)
if debugTmp:
print(' toFieldType:', toFieldType)
fTypeKW = progSpec.fieldTypeKeyword(fieldType)
toFTypeKW = progSpec.fieldTypeKeyword(toFieldType)
LHS_IsPointer = progSpec.typeIsPointer(toTypeSpec)
# print " CONVERTING:", fieldName, str(toFieldType)[:100]+'... ', str(typeSpec)[:100]+'... '
# print " TOFieldTYPE1:", str(toField)[:100]
# print " TOFieldTYPE :", toFieldOwner, toFieldType
# print " fieldValue:",ToStructName, fieldType, fieldValue
cdlog(logLvl, "FIELD {}: '{}'".format(fieldName, str(fieldValue)))
fields=[]
fromIsStruct = progSpec.isStruct(fieldType)
toIsBaseType = progSpec.isBaseType(toFieldType)
ToIsEmbedded = (not toIsBaseType) and (toFieldType[0]=='[' or toFieldType[0]=='{')
[fromIsALT, fields] = progSpec.isAltStruct(classes, fieldType)
fromIsOPT =False
fromIsList=False
toIsList =False
optionalWhiteSpace =False
if progSpec.isAContainer(typeSpec):
datastructID = progSpec.getDatastructID(typeSpec)
if datastructID=='opt': fromIsOPT=True;
else: fromIsList=True
if progSpec.isAContainer(toTypeSpec):
if datastructID != 'opt': toIsList=True
if debugTmp:
print(' fromIsOPT:', fromIsOPT)
print(' fromIsList:', fromIsList)
print(' toIsList:', toIsList)
print(' fromIsStruct:', fromIsStruct)
print(' toIsBaseType:', toIsBaseType)
print(' fieldType:', fieldType)
print(' ToIsEmbedded:', ToIsEmbedded)
print(' ToStructName:', ToStructName)
print(' memVersionName:', memVersionName, "\n")
################### W r i t e L V A L R e f e r e n c e
finalCodeStr=''
CodeLVAR_Alloc=''
CODE_LVAR_v2=''
if VarName=='' or VarName=='memStruct': # Default to the target argument name
#if VarName=='': print " VARNAME was ''; FIELDNAME:", fieldName
VarName='memStruct'
if(fieldName==None): # Field hasn't a name so in memory it's a cofactual or this is a parser marker.
globalFieldCount+=1
# We need two versions in case this is set in a function instead of assignment
CODE_LVAR_v2 = 'S'+str(globalFieldCount)
CodeLVAR_Alloc=' me string: '+CODE_LVAR_v2
CODE_LVAR = CodeLVAR_Alloc
if debugTmp: print(' CODE_LVARS:', CODE_LVAR)
else:
CODE_LVAR = VarName+'.'+fieldName
if fieldName=='inf': CODE_LVAR = VarName
CODE_LVAR_v2 = CODE_LVAR
else:
CODE_LVAR = VarName
CODE_LVAR_v2 = CODE_LVAR
################### W r i t e R V A L C o d e
CODE_RVAL=''
objName=''
humanIDType= VarTag+' ('+str(fieldName)+' / '+str(fieldValue) + ' / '+str(fieldType)[:40] +')'
humanIDType=humanIDType.replace('"', "'")
#print humanIDType
if advancePtr:
S+=indent+VarTag+' <- getNextStateRec('+VarTag+', EP)\n'
# UNCOMMENT FOR DEGUG: S+=' docPos('+str(level)+', '+VarTag+', "Get Next in SEQ for: '+humanIDType+'")\n'
if fieldOwner=='const'and (toField == None):
#print'CONSTFIELDVALUE("'+fieldValue+'")\n'
finalCodeStr += indent + 'tmpStr'+' <- makeStr('+VarTag+"<LVL_SUFFIX>"+'.child, EP)\n'
else:
if not toIsBaseType:
if debugTmp: print(' toFieldType:', toFieldType)
if not ToIsEmbedded:
objName=progSpec.fieldTypeKeyword(toFieldType)
if progSpec.typeIsInteger(objName):
strFieldType = progSpec.fieldTypeKeyword(fieldType)
if(strFieldType == "HexNum"):
CODE_RVAL='makeHexInt('+VarTag+'.child.next'+', EP)'
elif(strFieldType == "BinNum"):
CODE_RVAL='makeBinInt('+VarTag+'.child.next'+', EP)'
else:
CODE_RVAL='makeStr('+VarTag+'.child.next'+', EP)'
toIsBaseType=True; # it is really a base type.
elif (objName=='quotedStr1' or objName=='quotedStr2' or objName=='CID' or objName=='UniID'
or objName=='printables' or objName=='toEOL' or objName=='alphaNumSeq'):
CODE_RVAL='makeStr('+VarTag+'.child.next'+', EP)'
toIsBaseType=True; # it is really a base type.
elif (objName=='ws' or objName=='wsc'):
CODE_RVAL='makeStr('+VarTag+'.child.next'+', EP)'
optionalWhiteSpace = True
toIsBaseType=True; # it is really a base type.
else:
#print "toObjName:", objName, memVersionName, fieldName
[toMemObj, toMemVersionName]=fetchMemVersion(classes, objName)
if toMemVersionName==None:
# make alternate finalCodeStr. Also, write the extractor that extracts toStruct fields to memVersion of this
finalCodeStr=(indent + CodeLVAR_Alloc + '\n' +indent+' '+getFunctionName(fTypeKW, memVersionName)+'(getChildStateRec('+VarTag+"<LVL_SUFFIX>"+', EP), memStruct, EP)\n')
objSpec = progSpec.findSpecOf(classes[0], objName, 'string')
ToFields=objSpec['fields']
FromStructName=objName
Write_Extracter(classes, ToStructName, FromStructName, logLvl+1)
else:
fromFieldTypeCID = fieldType[0].replace('::', '_')
toFieldTypeCID = toMemVersionName.replace('::', '_')
#print "FUNC:", getFunctionName(fromFieldTypeCID, toFieldTypeCID)
if fromFieldTypeCID != toFieldTypeCID:
Write_Extracter(classes, toFieldTypeCID, fromFieldTypeCID, logLvl+1)
finalCodeStr=indent + CodeLVAR_Alloc + '\n' +indent+' '+getFunctionName(fromFieldTypeCID, toFieldTypeCID)+'(getChildStateRec('+VarTag+"<LVL_SUFFIX>"+', EP), '+CODE_LVAR_v2+', EP)\n'
else: pass
else:
CODE_RVAL = CodeRValExpr(toFieldType, VarTag, "")
#print "CODE_RVAL:", CODE_RVAL
################### H a n d l e o p t i o n a l a n d r e p e t i t i o n a n d a s s i g n m e n t c a s e s
gatherFieldCode=''
if fromIsList and toIsList:
CODE_RVAL='tmpVar'
globalFieldCount +=1
childRecName='SRec' + str(globalFieldCount)
gatherFieldCode+='\n'+indent+'\nour stateRec: '+childRecName+' <- '+VarTag+'.child'
gatherFieldCode+='\n'+indent+'while('+childRecName+' != NULL and getNextStateRec('+childRecName+', EP) !=NULL){\n'
if fromIsALT:
gatherFieldCode+=Write_ALT_Extracter(classes, fTypeKW, fields, childRecName, '', 'tmpVar', indent+' ', level)
gatherFieldCode+='\n'+indent+CODE_LVAR+'.append('+CODE_RVAL+')'
elif fromIsStruct and not toIsBaseType:
gatherFieldCode+='\n'+indent+toFieldOwner+' '+progSpec.baseStructName(toFTypeKW)+': tmpVar'
if toFieldOwner!='me':
gatherFieldCode+='\n'+indent+'Allocate('+CODE_RVAL+')'
gatherFieldCode+='\n'+indent+CODE_LVAR+'.append('+CODE_RVAL+')'
#print "##### FUNCT:", getFunctionName(fTypeKW, toFTypeKW)
gatherFieldCode+='\n'+indent+getFunctionName(fTypeKW, toFTypeKW)+'(getChildStateRec('+childRecName+', EP) , tmpVar, EP)\n'
PP_FuncName = getPostParseFunctionName(classes, toFTypeKW)
if PP_FuncName!=None:
gatherFieldCode+='\n'+indent+'if(!'+CODE_RVAL+'.postParseProcessed){'+PP_FuncName+'_'+toFTypeKW+'('+CODE_RVAL+', SRec0)}'
else:
CODE_RVAL = CodeRValExpr(toFieldType, childRecName, ".next")
gatherFieldCode+='\n'+indent+CODE_LVAR+'.append('+CODE_RVAL+')'
gatherFieldCode+=indent+' '+childRecName+' <- getNextStateRec('+childRecName+', EP)\n'
# UNCOMMENT FOR DEGUG: S+= ' docPos('+str(level)+', '+VarTag+', "Get Next in LIST for: '+humanIDType+'")\n'
gatherFieldCode+='\n'+indent+'}\n'
if(fromIsOPT):
print("Handle when the optional item is a list.");
exit(2)
else:
if toIsList: print("Error: parsing a non-list to a list is not supported.\n"); exit(1);
levelSuffix=''
assignerCode=''
oldIndent=indent
if (fromIsOPT):
setTrueCode=''
assignerCode+='\n'+indent+'if('+VarTag+'.child' +' == NULL or '+VarTag+'.child.next' +' == NULL){'
if toFieldOwner=='me':
if debugTmp: print(' toFieldOwner:', toFieldOwner)
## if fieldName==None and a model of fromFieldType has no cooresponding model But we are in EXTRACT_ mode:
## Make a special form of Extract_fromFieldType_to_ToFieldType()
## Call that function instead of the one in Code_LVAR
# First, create a new flag field
if fieldName==None:
fieldName="TEMP"+str(globalTempVarIdx)
globalTempVarIdx += globalTempVarIdx
newFieldsName=fieldName #'has_'+fieldName
fieldDef=progSpec.packField(ToStructName, False, 'me', 'flag', None, None, newFieldsName, None, None, None, False, False)
progSpec.addField(classes[0], memVersionName, 'struct', fieldDef)
# Second, generate the code to set the flag
assignerCode+='\n'+indent+' '+VarName+'.'+newFieldsName+' <- false'
setTrueCode += VarName+'.'+newFieldsName+' <- true'
elif LHS_IsPointer: # If owner is my, our or their
assignerCode+='\n'+indent+' '+CODE_LVAR+' <- NULL'
else:
print("ERROR: OPTional fields must not be '"+toFieldOwner+"'.\n")
exit(1)
assignerCode+='\n'+indent+'} else {\n'
levelSuffix='.child'
indent+=' '
assignerCode+=indent+setTrueCode+'\n'
if fromIsALT or fromIsEmbeddedAlt:
if(fromIsEmbeddedAlt):
# print "ALT-#2"
assignerCode+=Write_ALT_Extracter(classes, ToStructName, field['innerDefs'], VarTagBase, levelSuffix, VarName, indent+' ', level+1, logLvl+1)
else:
# print "ALT-#3"
fTypeKW = progSpec.fieldTypeKeyword(fieldType)
assignerCode+=Write_ALT_Extracter(classes, fTypeKW, fields, VarTagBase, levelSuffix, VarName+'X', indent+' ', level, logLvl+1)
assignerCode+=indent+CODE_LVAR+' <- '+(VarName+'X')+"\n"
elif fromIsEmbeddedSeq:
globalFieldCount +=1
childRecNameBase='childSRec' + str(globalFieldCount)
childRecName=childRecNameBase+str(level)
assignerCode+='\n'+indent+'our stateRec: '+childRecName+' <- '+VarTag+levelSuffix+'.child\n'
advance=False
for innerField in field['innerDefs']:
assignerCode+=Write_fieldExtracter(classes, ToStructName, innerField, memObjFields, childRecNameBase, '', advance, coFactualCode, ' ', level, logLvl+1)
advance = True
elif fromIsStruct and not toIsBaseType:
assignerCode+=finalCodeStr.replace("<LVL_SUFFIX>", levelSuffix);
if debugTmp: print(' assignerCode:', assignerCode)
elif optionalWhiteSpace:
assignerCode += '\n'+indent+'if('+VarTag+'.child' +' != NULL){'+CODE_LVAR+' <- '+CODE_RVAL+'}\n'
else:
# if toFieldOwner == 'const': print "Error: Attempt to extract a parse to const field.\n"; exit(1);
if CODE_RVAL!="":
if LHS_IsPointer:
assignerCode+=' '+CODE_LVAR+' <deep- '+CODE_RVAL+"\n"
else: assignerCode+=' '+CODE_LVAR+' <- '+CODE_RVAL+"\n"
elif finalCodeStr!="": assignerCode+=finalCodeStr.replace("<LVL_SUFFIX>", levelSuffix);
if (fromIsOPT):
indent=oldIndent
assignerCode += indent+'}\n'
#print '######################\n'+assignerCode, memVersionName, '\n'
# exit(2)
gatherFieldCode = assignerCode
#print ("##########################\n",S,"\n#####################################\n")
if LHS_IsPointer: # LVAL is a pointer and should be allocated or cleared.
S+= indent + 'AllocateOrClear(' +CODE_LVAR +')\n'
S+=coFactualCode
S+=gatherFieldCode
#print "ASSIGN_CODE", S
# if debugTmp: exit(2)
return S
extracterFunctionAccumulator = ""
parserFunctionAccumulator = ""
alreadyWrittenFunctions={}
def Write_structExtracter(classes, ToStructName, FromStructName, fields, nameForFunc, logLvl):
global extracterFunctionAccumulator
global parserFunctionAccumulator
memObjFields=[]
progSpec.populateCallableStructFields(memObjFields, classes, ToStructName)
if memObjFields==None: cdErr("struct {} is not defined".format(ToStructName.replace('str','mem')))
S=' me string: tmpStr;\n'
advance=False
for field in fields: # Extract all the fields in the string version.
S+=Write_fieldExtracter(classes, ToStructName, field, memObjFields, 'SRec', '', advance, '', ' ', 0, logLvl+1)
advance=True
if ToStructName==FromStructName:
if progSpec.doesClassContainFunc(classes, ToStructName, 'postParseProcessing'):
postParseFuncName = "postParseProcessing_"+ToStructName
S += " "+postParseFuncName+"(memStruct, SRec0)\n"
newStructtxt='\n struct '+ToStructName+'{flag: postParseProcessed}\n'
codeDogParser.AddToObjectFromText(classes[0], classes[1], newStructtxt, 'Adding '+ToStructName+'{flag: postParseProcessed}')
pppFunc="\n void: "+postParseFuncName+"(their "+ToStructName+": item, our stateRec: SRec) <- {item.postParseProcessing(); item.postParseProcessed<-true}\n"
extracterFunctionAccumulator += pppFunc
elif progSpec.doesClassContainFunc(classes, ToStructName, 'postParseProcessingEtc'):
postParseFuncName = "postParseProcessingEtc_"+ToStructName
S += " EP."+postParseFuncName+"(memStruct, SRec0)\n memStruct.postParseProcessed<-true\n"
newStructtxt='\n struct '+ToStructName+'{flag: postParseProcessed}\n'
codeDogParser.AddToObjectFromText(classes[0], classes[1], newStructtxt, 'Adding '+ToStructName+'{flag: postParseProcessed}')
pppFunc="\n void: "+postParseFuncName+"(their "+ToStructName+": item, our stateRec: SRec) <- {print(\"Override this function!\")}\n"
parserFunctionAccumulator += pppFunc
return S
def Write_Extracter(classes, ToStructName, FromStructName, logLvl):
global extracterFunctionAccumulator
global alreadyWrittenFunctions
nameForFunc=getFunctionName(FromStructName, ToStructName)
cdlog(logLvl, "WRITING function {}() to extract struct {} from parse tree: stage 1...".format(nameForFunc, ToStructName))
if nameForFunc in alreadyWrittenFunctions: return
alreadyWrittenFunctions[nameForFunc]=True
S=''
ObjectDef = progSpec.findSpecOf(classes[0], FromStructName, 'string')
fields=ObjectDef["fields"]
configType=ObjectDef['configType']
SeqOrAlt=''
if configType=='SEQ': SeqOrAlt='parseSEQ'
elif configType=='ALT': SeqOrAlt='parseALT'
cdlog(logLvl, "WRITING function {}() to extract struct {} from parse tree: stage 2...".format(nameForFunc, ToStructName))
if configType=='SEQ':
S+=Write_structExtracter(classes, ToStructName, FromStructName, fields, nameForFunc, logLvl)
elif configType=='ALT':
S+=Write_ALT_Extracter(classes, ToStructName, fields, 'SRec', '', 'tmpStr', ' ', -1, logLvl)
seqExtracter = "\n void: "+nameForFunc+"(our stateRec: SRec0, their "+ToStructName+": memStruct, their EParser: EP) <- {\n" + S + " }\n"
extracterFunctionAccumulator += seqExtracter
#print "########################## extracterFunctionAccumulator\n",extracterFunctionAccumulator,"\n#####################################\n"
def writeParserWrapperFunction(classes, className):
S='''
struct EParser{
me uint64: sourceID
our <CLASSNAME>: Parse_<CLASSNAME>(me string: textIn) <- {
our <CLASSNAME>: result
initParseFromString("<CLASSNAME>", textIn)
doParse()
if (doesParseHaveError()) {
print("Parse Error:" + errorMesg + "\\n")
} else {
our stateRec: topItem <- topDownResolve(lastTopLevelItem, "")
Allocate(result)
syntax.Extract_<CLASSNAME>_to_<CLASSNAME>(topItem, result, self)
}
return(result)
}
}
struct <CLASSNAME>ExtracterThread: inherits=Threads{
their Threaded_<CLASSNAME>ParseAndExtractor: ctrls
our stateRec: parseTree
our <CLASSNAME>: topItem
void: init(their Threaded_<CLASSNAME>ParseAndExtractor: Ctrls, our stateRec: ParseTree, our <CLASSNAME>: TopItem) <- {
topItem <- TopItem
parseTree <- ParseTree
ctrls <- Ctrls
ctrls.extractCompleted <- false
}
void: run() <- {
me string: streamID <- ctrls.streamName()
log("OPENING EXTRACT_THREAD:" + streamID)
ctrls.parser.syntax.Extract_<CLASSNAME>_to_<CLASSNAME>(parseTree, topItem, ctrls.parser)
log("Extracted_<CLASSNAME>:"+toString(topItem).subStr(0,120))
log("CLOSING EXTRACT_THREAD:" + streamID)
protect(ctrls.chkExtractDone){
ctrls.extractCompleted <- true
ctrls.extractDoneLock.notifyOne();
}
}
}
struct <CLASSNAME>ParserThread: inherits=Threads{
their Threaded_<CLASSNAME>ParseAndExtractor: ctrls
void: init(their Threaded_<CLASSNAME>ParseAndExtractor: Ctrls) <- {
ctrls <- Ctrls
ctrls.parseCompleted <- false
}
void: run() <- {
me string: streamID <- ctrls.streamName()
log("OPENING PARSE_THREAD:" + streamID)
ctrls.parser.doParse()
log("parser.lastTopLevelItem:"+ctrls.parser.lastTopLevelItem.mySymbol())
our <CLASSNAME>: crnt_<CLASSNAME>
if(ctrls.parser.doesParseHaveError()){
ctrls.handleSyntaxError(ctrls.parser.errorMesg)
crnt_<CLASSNAME> <- NULL
}
log("CLOSING PARSE_THREAD:" + streamID)
protect(ctrls.chkParseDone){
ctrls.parseCompleted <- true;
ctrls.parseDoneLock.notifyOne();
}
}
}
struct Threaded_<CLASSNAME>ParseAndExtractor{
me string: name
their EParser: parser
our stateRec: leftParseNode
me bool: parseCompleted
me bool: extractCompleted
me Mutex: chkParseDone
me Mutex: chkExtractDone
me SyncLock: parseDoneLock
me SyncLock: extractDoneLock
me <CLASSNAME>ParserThread: parserThread
me <CLASSNAME>ExtracterThread: extracterThread
void: handleSyntaxError(me string: mesg) <- { // Override as needed.
log("Syntax Error:"+mesg)
}
me string: streamName() <- {return("")} // Override as needed.
void: waitForParseCompletion()<-{
me MutexMngr: MtxMgr{chkParseDone}
while(!parseCompleted){
parseDoneLock.wait(MtxMgr)
}
}
void: waitForExtractCompletion()<-{
me MutexMngr: MtxMgr{chkExtractDone}
while(!extractCompleted){
extractDoneLock.wait(MtxMgr)
}
}
void: waitForThreadsToExit() <- {
parserThread.waitForExit()
extracterThread.waitForExit()
}
void: start(their EParser: iParser, their strBuf: streamToParse, our <CLASSNAME>: topItem, me string:Name) <- {
name <- Name
parser<-iParser
me int: startProduction <- parser.syntax.<CLASSNAME>_str
parser.errorMesg <- ""
parser.setStreamingMode(true)
leftParseNode <- parser.initParseFromStream(streamToParse)
extracterThread.init(self, leftParseNode, topItem)
extracterThread.start(name+"_X")
parserThread.init(self)
parserThread.start(name+"_P")
}
}
'''.replace('<CLASSNAME>', className)
codeDogParser.AddToObjectFromText(classes[0], classes[1], S, 'Parse_'+className+'() and threaded parse support structs')
def CreateStructsForStringModels(classes, newClasses, tags):
# Define fieldResult struct
#~ structsName = 'fetchResult'
#~ StructFieldStr = "mode [fetchOK, fetchNotReady, fetchSyntaxError, FetchIO_Error] : FetchResult"
#~ progSpec.addClass(classes[0], classes[1], structsName, 'struct', 'SEQ',["//^", "Added parser class: "+structsName])
#~ codeDogParser.AddToObjectFromText(classes[0], classes[1], progSpec.wrapFieldListInObjectDef(structsName, StructFieldStr))
global startSymbol
if len(newClasses)==0: return
populateBaseRules()
global extracterFunctionAccumulator
extracterFunctionAccumulator=""
global nextParseNameID
nextParseNameID=0
numStringStructs=0
for className in newClasses:
if className[0] == '!': continue
ObjectDef = classes[0][className]
if(ObjectDef['stateType'] == 'string'):
className=className[1:]
cdlog(1, " Writing parse system for "+className)
numStringStructs+=1
fields = ObjectDef["fields"]
configType= ObjectDef['configType']
classTags = ObjectDef['tags']
if 'StartSymbol' in classTags:
startSymbol=className+"_str"
writeParserWrapperFunction(classes, className)
SeqOrAlt=''
if configType=='SEQ': SeqOrAlt='parseSEQ' # seq has {}
elif configType=='ALT': SeqOrAlt='parseALT' # alt has []
normedObjectName = className.replace('::', '_')
if normedObjectName==className: normedObjectName+='_str'
# Write the rules for all the fields, and a parent rule which is either SEQ or ALT, and REP/OPT as needed.
cdlog(2, "CODING Parser Rules for {}".format(normedObjectName))
ruleID = writeNonTermParseRule(classes, tags, normedObjectName, fields, SeqOrAlt, '', 3)
if SeqOrAlt=='parseSEQ':
[memObj, memVersionName]=fetchMemVersion(classes, className)
if memObj!=None:
Write_Extracter(classes, className, className, 2)
else: cdlog(2, "NOTE: Skipping {} because it has no struct version defined.".format(className))
if numStringStructs==0: return
ExtracterCode = extracterFunctionAccumulator
############ Add struct parser
parserCode=genParserCode()
codeDogParser.AddToObjectFromText(classes[0], classes[1], parserCode, 'Parser for '+className)
structsName='EGrammar'
progSpec.addClass(classes[0], classes[1], structsName, 'struct', 'SEQ',["//^", "Added parser class: "+structsName])
codeDogParser.AddToObjectFromText(classes[0], classes[1], progSpec.wrapFieldListInObjectDef(structsName, ExtracterCode), 'class '+structsName)