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
|
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
|
-
+
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
-
-
-
+
+
+
-
+
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
-
-
-
+
+
+
|
print("TOKENS:", dTokenPos)
if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]:
echo("DA: " + str(dTokenPos[tWord[0]]["lMorph"]))
echo("FSA: " + str(lMorph))
return True
def morph (dTokenPos, tWord, sPattern, bStrict=True, bNoWord=False):
def morph (dTokenPos, tWord, sPattern, sNegPattern="", bNoWord=False):
"analyse a tuple (position, word), return True if sPattern in morphologies (disambiguation on)"
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 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
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
# check negative condition
if sNegPattern:
if sNegPattern == "*":
# all morph must match sPattern
zPattern = re.compile(sPattern)
return all(zPattern.search(sMorph) for sMorph in lMorph)
else:
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(s) for s in lMorph):
return False
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(s) for s in lMorph):
return False
# search sPattern
zPattern = re.compile(sPattern)
return any(zPattern.search(s) for s in lMorph)
def analyse (sWord, sPattern, bStrict=True):
def analyse (sWord, sPattern, sNegPattern=""):
"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 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:
return False
# check negative condition
if sNegPattern:
if sNegPattern == "*":
zPattern = re.compile(sPattern)
return all(zPattern.search(sMorph) for sMorph in lMorph)
else:
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(s) for s in lMorph):
return False
zNegPattern = re.compile(sNegPattern)
if any(zNegPattern.search(s) for s in lMorph):
return False
# search sPattern
zPattern = re.compile(sPattern)
return any(zPattern.search(s) for s in lMorph)
## functions to get text outside pattern scope
|
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
|
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
|
-
-
|
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
|
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
|
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
|
-
-
-
-
|
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
zPattern = re.compile(sPattern)
return any(zPattern.search(sMorph) for sMorph in lMorph)
def g_merged_analyse (dToken1, dToken2, cMerger, sPattern, sNegPattern="", bSetMorph=True):
"merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(dToken1["sValue"] + cMerger + dToken2["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)
bResult = all(zPattern.search(sMorph) for sMorph in lMorph)
if bResult and bSetMorph:
dToken1["lMorph"] = lMorph
return bResult
else:
zNegPattern = re.compile(sNegPattern)
|