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
|
if sLemma in dNode["<lemmas>"]:
if bDebug:
echo(" MATCH: >" + sLemma)
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<lemmas>"][sLemma]] }
bTokenFound = True
# regex morph arcs
if "<re_morph>" in dNode:
for sRegex in dNode["<re_morph>"]:
if "¬" not in sRegex:
# no anti-pattern
lMorph = dToken.get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]))
lMorph = dToken.get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]))
lMorph = dToken.get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]))
|
>
<
<
<
|
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
|
if sLemma in dNode["<lemmas>"]:
if bDebug:
echo(" MATCH: >" + sLemma)
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<lemmas>"][sLemma]] }
bTokenFound = True
# regex morph arcs
if "<re_morph>" in dNode:
lMorph = dToken.get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]))
for sRegex in dNode["<re_morph>"]:
if "¬" not in sRegex:
# no anti-pattern
if any(re.search(sRegex, sMorph) for sMorph in lMorph):
if bDebug:
echo(" MATCH: @" + sRegex)
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] }
bTokenFound = True
else:
# there is an anti-pattern
sPattern, sNegPattern = sRegex.split("¬", 1)
if sNegPattern == "*":
# all morphologies must match with <sPattern>
if sPattern:
if lMorph and all(re.search(sPattern, sMorph) for sMorph in lMorph):
if bDebug:
echo(" MATCH: @" + sRegex)
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] }
bTokenFound = True
else:
if sNegPattern and any(re.search(sNegPattern, sMorph) for sMorph in lMorph):
continue
if not sPattern or any(re.search(sPattern, sMorph) for sMorph in lMorph):
if bDebug:
echo(" MATCH: @" + sRegex)
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] }
bTokenFound = True
|