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
|
for c in sFlex:
if c not in dChar:
dChar[c] = nChar
lChar.append(c)
nChar += 1
dCharOccur[c] = dCharOccur.get(c, 0) + 1
# affixes to find stem from flexion
aff = funcStemmingGen(sFlex, sStem)
if aff not in dAff:
dAff[aff] = nAff
lAff.append(aff)
nAff += 1
dAffOccur[aff] = dCharOccur.get(aff, 0) + 1
# tags
if sTag not in dTag:
dTag[sTag] = nTag
lTag.append(sTag)
nTag += 1
dTagOccur[sTag] = dTagOccur.get(sTag, 0) + 1
lEntry.append((sFlex, dAff[aff], dTag[sTag]))
if not lEntry:
raise ValueError("# Error. Empty lexicon")
# Preparing DAWG
print(" > Preparing list of words")
lVal = lChar + lAff + lTag
lWord = [ [dChar[c] for c in sFlex] + [iAff+nChar] + [iTag+nChar+nAff] for sFlex, iAff, iTag in lEntry ]
|
|
|
|
|
|
|
|
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
|
for c in sFlex:
if c not in dChar:
dChar[c] = nChar
lChar.append(c)
nChar += 1
dCharOccur[c] = dCharOccur.get(c, 0) + 1
# affixes to find stem from flexion
sAff = funcStemmingGen(sFlex, sStem)
if sAff not in dAff:
dAff[sAff] = nAff
lAff.append(sAff)
nAff += 1
dAffOccur[sAff] = dCharOccur.get(sAff, 0) + 1
# tags
if sTag not in dTag:
dTag[sTag] = nTag
lTag.append(sTag)
nTag += 1
dTagOccur[sTag] = dTagOccur.get(sTag, 0) + 1
lEntry.append((sFlex, dAff[sAff], dTag[sTag]))
if not lEntry:
raise ValueError("# Error. Empty lexicon")
# Preparing DAWG
print(" > Preparing list of words")
lVal = lChar + lAff + lTag
lWord = [ [dChar[c] for c in sFlex] + [iAff+nChar] + [iTag+nChar+nAff] for sFlex, iAff, iTag in lEntry ]
|