244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
|
"nNode": self.nNode,
"nArc": self.nArc,
"nArcVal": self.nArcVal,
"lArcVal": self.lArcVal,
"nCompressionMethod": self.nCompressionMethod,
"nBytesArc": self.nBytesArc,
"nBytesNodeAddress": self.nBytesNodeAddress,
"nBytesOffset": self.nBytesOffset,
# JavaScript is a pile of shit, so Mozilla’s JS parser don’t like file bigger than 4 Mb!
# So, if necessary, we use an hexadecimal string, that we will convert later in Firefox’s extension.
# https://github.com/mozilla/addons-linter/issues/1361
"sByDic": self.byDic.hex() if bBinaryDictAsHexString else [ e for e in self.byDic ],
"l2grams": list(self.a2grams)
}, ensure_ascii=False))
if bInJSModule:
|
<
|
240
241
242
243
244
245
246
247
248
249
250
251
252
253
|
"nNode": self.nNode,
"nArc": self.nArc,
"nArcVal": self.nArcVal,
"lArcVal": self.lArcVal,
"nCompressionMethod": self.nCompressionMethod,
"nBytesArc": self.nBytesArc,
"nBytesNodeAddress": self.nBytesNodeAddress,
# JavaScript is a pile of shit, so Mozilla’s JS parser don’t like file bigger than 4 Mb!
# So, if necessary, we use an hexadecimal string, that we will convert later in Firefox’s extension.
# https://github.com/mozilla/addons-linter/issues/1361
"sByDic": self.byDic.hex() if bBinaryDictAsHexString else [ e for e in self.byDic ],
"l2grams": list(self.a2grams)
}, ensure_ascii=False))
if bInJSModule:
|
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
|
sWord1, sWord2 = sWord.split(cSplitter, 1)
if self.isValid(sWord1) and self.isValid(sWord2):
oSuggResult.addSugg(sWord1+" "+sWord2)
def _suggest (self, oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
# recursive function
#logging.info((nDeep * " ") + sNewWord + ":" + sRemain)
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
if not sRemain:
oSuggResult.addSugg(sNewWord, nDeep)
for sTail in self._getTails(iAddr):
oSuggResult.addSugg(sNewWord+sTail, nDeep)
return
if (len(sNewWord) + len(sRemain) == len(oSuggResult.sWord)) and oSuggResult.sWord.lower().startswith(sNewWord.lower()) and self.isValid(sRemain):
if self.sLangCode == "fr" and sNewWord.lower() in ("l", "d", "n", "m", "t", "s", "c", "j", "qu", "lorsqu", "puisqu", "quoiqu", "jusqu", "quelqu") and sRemain[0:1] in cp.aVowel:
|
|
|
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
|
sWord1, sWord2 = sWord.split(cSplitter, 1)
if self.isValid(sWord1) and self.isValid(sWord2):
oSuggResult.addSugg(sWord1+" "+sWord2)
def _suggest (self, oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
# recursive function
#logging.info((nDeep * " ") + sNewWord + ":" + sRemain)
if self.byDic[iAddr] & self._finalNodeMask:
if not sRemain:
oSuggResult.addSugg(sNewWord, nDeep)
for sTail in self._getTails(iAddr):
oSuggResult.addSugg(sNewWord+sTail, nDeep)
return
if (len(sNewWord) + len(sRemain) == len(oSuggResult.sWord)) and oSuggResult.sWord.lower().startswith(sNewWord.lower()) and self.isValid(sRemain):
if self.sLangCode == "fr" and sNewWord.lower() in ("l", "d", "n", "m", "t", "s", "c", "j", "qu", "lorsqu", "puisqu", "quoiqu", "jusqu", "quelqu") and sRemain[0:1] in cp.aVowel:
|
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
|
if sFlexPattern:
zFlexPattern = re.compile(sFlexPattern)
if sTagsPattern:
zTagsPattern = re.compile(sTagsPattern)
except re.error:
print("# Error in regex pattern")
traceback.print_exc()
yield from self._select1(zFlexPattern, zTagsPattern, 0, "")
# def morph (self, sWord):
# is defined in __init__
# VERSION 1
def _select1 (self, zFlexPattern, zTagsPattern, iAddr, sWord):
# recursive generator
for nVal, jAddr in self._getArcs1(iAddr):
if nVal <= self.nChar:
# simple character
yield from self._select1(zFlexPattern, zTagsPattern, jAddr, sWord + self.lArcVal[nVal])
else:
if not zFlexPattern or zFlexPattern.search(sWord):
sStem = self.funcStemming(sWord, self.lArcVal[nVal])
for nMorphVal, _ in self._getArcs1(jAddr):
if not zTagsPattern or zTagsPattern.search(self.lArcVal[nMorphVal]):
yield [sWord, sStem, self.lArcVal[nMorphVal]]
def _morph1 (self, sWord):
"returns morphologies of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + self.nBytesArc
nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2+self.nBytesNodeAddress
iAddr = iEndArcAddr+self.nBytesNodeAddress
return l
return []
def _stem1 (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
iAddr = iEndArcAddr+self.nBytesNodeAddress
return l
return []
def _lookupArcNode1 (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
# we return the address of the next node
return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr+self.nBytesNodeAddress
def _getArcs1 (self, iAddr):
"generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)"
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
yield nRawArc & self._arcMask, int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
if nRawArc & self._lastArcMask:
break
iAddr = iEndArcAddr+self.nBytesNodeAddress
def _writeNodes1 (self, spfDest):
"for debugging only"
print(" > Write binary nodes")
with open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
iAddr = 0
hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
while iAddr < len(self.byDic):
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
hDst.write(" {:<20} {:0>16} i{:>10} #{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", \
int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], \
byteorder='big')))
iAddr = iEndArcAddr+self.nBytesNodeAddress
if (nRawArc & self._lastArcMask) and iAddr < len(self.byDic):
hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
hDst.close()
# VERSION 2
def _morph2 (self, sWord):
"returns morphologies of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
if not nRawArc & self._addrBitMask:
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
else:
# we go to the end of the node
iAddr2 = iEndArcAddr
while not nRawArc & self._lastArcMask:
nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
iAddr2 += self.nBytesArc + self.nBytesNodeAddress
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + self.nBytesArc
nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2+self.nBytesNodeAddress if not nRawArc2 & self._addrBitMask else iEndArcAddr2
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr
return l
return []
def _stem2 (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
# Now , we go to the next node
if not nRawArc & self._addrBitMask:
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
else:
# we go to the end of the node
iAddr2 = iEndArcAddr
while not nRawArc & self._lastArcMask:
nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
iAddr2 += self.nBytesArc + self.nBytesNodeAddress
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr
return l
return []
def _lookupArcNode2 (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
if not nRawArc & self._addrBitMask:
# we return the address of the next node
return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
# we go to the end of the node
iAddr = iEndArcAddr
while not nRawArc & self._lastArcMask:
nRawArc = int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big')
iAddr += self.nBytesArc + self.nBytesNodeAddress if not nRawArc & self._addrBitMask else self.nBytesArc
return iAddr
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr
def _writeNodes2 (self, spfDest):
"for debugging only"
print(" > Write binary nodes")
with open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
iAddr = 0
hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
while iAddr < len(self.byDic):
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if not nRawArc & self._addrBitMask:
iNextNodeAddr = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
hDst.write(" {:<20} {:0>16} i{:>10} #{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", iNextNodeAddr))
iAddr = iEndArcAddr+self.nBytesNodeAddress
else:
hDst.write(" {:<20} {:0>16}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:]))
iAddr = iEndArcAddr
if nRawArc & self._lastArcMask:
hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
hDst.close()
# VERSION 3
def _morph3 (self, sWord):
"returns morphologies of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
iAddrNode = iAddr
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
if not nRawArc & self._addrBitMask:
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
else:
iAddr2 = iAddrNode + int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + self.nBytesArc
nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2+self.nBytesNodeAddress if not nRawArc2 & self._addrBitMask else iEndArcAddr2+self.nBytesOffset
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr+self.nBytesOffset
return l
return []
def _stem3 (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
#iAddrNode = iAddr
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr+self.nBytesOffset
return l
return []
def _lookupArcNode3 (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
iAddrNode = iAddr
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
if not nRawArc & self._addrBitMask:
return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
return iAddrNode + int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr+self.nBytesOffset
def _writeNodes3 (self, spfDest):
"for debugging only"
print(" > Write binary nodes")
with open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
iAddr = 0
hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
while iAddr < len(self.byDic):
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if not nRawArc & self._addrBitMask:
iNextNodeAddr = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
hDst.write(" {:<20} {:0>16} i{:>10} #{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", iNextNodeAddr))
iAddr = iEndArcAddr+self.nBytesNodeAddress
else:
iNextNodeAddr = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
hDst.write(" {:<20} {:0>16} i{:>10} +{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", iNextNodeAddr))
iAddr = iEndArcAddr+self.nBytesOffset
if nRawArc & self._lastArcMask:
hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
hDst.close()
|
|
<
<
<
<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
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
|
if sFlexPattern:
zFlexPattern = re.compile(sFlexPattern)
if sTagsPattern:
zTagsPattern = re.compile(sTagsPattern)
except re.error:
print("# Error in regex pattern")
traceback.print_exc()
yield from self._select(zFlexPattern, zTagsPattern, 0, "")
def _select (self, zFlexPattern, zTagsPattern, iAddr, sWord):
# recursive generator
for nVal, jAddr in self._getArcs(iAddr):
if nVal <= self.nChar:
# simple character
yield from self._select(zFlexPattern, zTagsPattern, jAddr, sWord + self.lArcVal[nVal])
else:
if not zFlexPattern or zFlexPattern.search(sWord):
sStem = self.funcStemming(sWord, self.lArcVal[nVal])
for nMorphVal, _ in self._getArcs(jAddr):
if not zTagsPattern or zTagsPattern.search(self.lArcVal[nMorphVal]):
yield [sWord, sStem, self.lArcVal[nMorphVal]]
def _morph (self, sWord):
"returns morphologies of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if self.byDic[iAddr] & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + 1
nRawArc = self.byDic[iAddr]
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
iAddr2 = self.byDic[iEndArcAddr]
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + 1
nRawArc2 = self.byDic[iAddr2]
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2 + 1
iAddr = iEndArcAddr + 1
return l
return []
def _stem (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if self.byDic[iAddr] & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + 1
nRawArc = self.byDic[iAddr]
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
iAddr = iEndArcAddr + 1
return l
return []
def _lookupArcNode (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
while True:
iEndArcAddr = iAddr + 1
nRawArc = self.byDic[iAddr]
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
# we return the address of the next node
return self.byDic[iEndArcAddr]
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr + 1
def _getArcs (self, iAddr):
"generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)"
while True:
iEndArcAddr = iAddr + 1
nRawArc = self.byDic[iAddr]
yield nRawArc & self._arcMask, self.byDic[iEndArcAddr]
if nRawArc & self._lastArcMask:
break
iAddr = iEndArcAddr + 1
def _writeNodes (self, spfDest):
"for debugging only"
print(" > Write binary nodes")
with open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
iAddr = 0
hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
while iAddr < len(self.byDic):
iEndArcAddr = iAddr + 1
nRawArc = self.byDic[iAddr]
nArc = nRawArc & self._arcMask
hDst.write(" {:<20} {:0>16} i{:>10} #{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", self.byDic[iEndArcAddr]))
iAddr = iEndArcAddr + 1
if (nRawArc & self._lastArcMask) and iAddr < len(self.byDic):
hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
hDst.close()
|