| ︙ | | |
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
|
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
|
-
+
|
if not tWord:
return bNoWord
lMorph = dTokenPos[tWord[0]]["lMorph"] if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]] else _oSpellChecker.getMorph(tWord[1])
if not lMorph:
return False
zPattern = re.compile(sPattern)
if bStrict:
return all(zPattern.search(s) for s in lMorph)
return bool(lMorph) and all(zPattern.search(s) for s in lMorph)
return any(zPattern.search(s) for s in lMorph)
def morphex (dTokenPos, tWord, sPattern, sNegPattern, bNoWord=False):
"analyse a tuple (position, word), returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)"
if not tWord:
return bNoWord
|
| ︙ | | |
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
|
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
|
-
+
|
def analyse (sWord, sPattern, bStrict=True):
"analyse a word, return True if sPattern in morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(sWord)
if not lMorph:
return False
zPattern = re.compile(sPattern)
if bStrict:
return all(zPattern.search(s) for s in lMorph)
return bool(lMorph) and all(zPattern.search(s) for s in lMorph)
return any(zPattern.search(s) for s in lMorph)
def analysex (sWord, sPattern, sNegPattern):
"analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(sWord)
if not lMorph:
|
| ︙ | | |
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
|
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
|
+
+
-
-
-
-
+
+
+
+
|
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
else:
# there is an anti-pattern
sPattern, sNegPattern = sRegex.split("¬", 1)
if sNegPattern == "*":
# all morphologies must match with <sPattern>
if sPattern:
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if sPattern and all(re.search(sPattern, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
if bDebug:
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
if lMorph and all(re.search(sPattern, sMorph) for sMorph in lMorph):
if bDebug:
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
else:
if sNegPattern and any(re.search(sNegPattern, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
continue
if not sPattern or any(re.search(sPattern, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
if bDebug:
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
|
| ︙ | | |
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
|
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
|
+
+
|
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph:
return False
# check negative condition
if sNegPattern:
if sNegPattern == "*":
# all morph must match sPattern
if not lMorph:
return False
zPattern = re.compile(sPattern)
return all(zPattern.search(sMorph) for sMorph in lMorph)
else:
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(sMorph) for sMorph in lMorph):
return False
# search sPattern
|
| ︙ | | |
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
|
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
|
+
+
+
|
else:
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
if not lMorph:
return False
# check negative condition
if sNegPattern:
if sNegPattern == "*":
# all morph must match sPattern
if not lMorph:
return False
zPattern = re.compile(sPattern)
return all(zPattern.search(sMorph) for sMorph in lMorph)
else:
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(sMorph) for sMorph in lMorph):
return False
# search sPattern
|
| ︙ | | |