| ︙ | | | ︙ | |
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
|
self.oMainDic = self._loadDictionary(sfMainDic, True)
self.oCommunityDic = self._loadDictionary(sfCommunityDic)
self.oPersonalDic = self._loadDictionary(sfPersonalDic)
self.bCommunityDic = bool(self.oCommunityDic)
self.bPersonalDic = bool(self.oPersonalDic)
self.oTokenizer = None
# Default suggestions
self.dDefaultSugg = None
self.loadSuggestions(sLangCode)
# storage
self.bStorage = False
self._dMorphologies = {} # key: flexion, value: list of morphologies
self._dLemmas = {} # key: flexion, value: list of lemmas
def _loadDictionary (self, source, bNecessary=False):
"returns an IBDAWG object"
|
|
|
|
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
|
self.oMainDic = self._loadDictionary(sfMainDic, True)
self.oCommunityDic = self._loadDictionary(sfCommunityDic)
self.oPersonalDic = self._loadDictionary(sfPersonalDic)
self.bCommunityDic = bool(self.oCommunityDic)
self.bPersonalDic = bool(self.oPersonalDic)
self.oTokenizer = None
# Default suggestions
self.lexicographer = None
self.loadLexicographer(sLangCode)
# storage
self.bStorage = False
self._dMorphologies = {} # key: flexion, value: list of morphologies
self._dLemmas = {} # key: flexion, value: list of lemmas
def _loadDictionary (self, source, bNecessary=False):
"returns an IBDAWG object"
|
| ︙ | | | ︙ | |
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
|
def deactivatePersonalDictionary (self):
"deactivate personal dictionary"
self.bPersonalDic = False
# Default suggestions
def loadSuggestions (self, sLangCode):
"load default suggestion module for <sLangCode>"
try:
suggest = importlib.import_module("."+sLangCode, "grammalecte.graphspell")
except ImportError:
print("No suggestion module for language <"+sLangCode+">")
return
self.dDefaultSugg = suggest.dSugg
|
|
|
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
|
def deactivatePersonalDictionary (self):
"deactivate personal dictionary"
self.bPersonalDic = False
# Default suggestions
def loadLexicographer (self, sLangCode):
"load default suggestion module for <sLangCode>"
try:
self.lexicographer = importlib.import_module(".lexgraph_"+sLangCode, "grammalecte.graphspell")
except ImportError:
print("No suggestion module for language <"+sLangCode+">")
return
def analyze (self, sWord):
"returns a list of words and their morphologies"
if not self.lexicographer:
return []
lWordAndMorph = []
for sElem in self.lexicographer.split(sWord):
if sElem:
lMorph = self.getMorph(sElem)
sLex = self.lexicographer.analyze(sElem)
if sLex:
aRes = [ (" | ".join(lMorph), sLex) ]
else:
aRes = [ (sMorph, self.lexicographer.formatTags(sMorph)) for sMorph in lMorph ]
if aRes:
lWordAndMorph.append((sElem, aRes))
return lWordAndMorph
# Storage
def activateStorage (self):
"store all lemmas and morphologies retrieved from the word graph"
self.bStorage = True
|
| ︙ | | | ︙ | |
157
158
159
160
161
162
163
164
165
166
167
168
169
170
|
else:
if not bByLemma:
dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
else:
for sLemma in self.getLemma(dToken['sValue']):
dWord[sLemma] = dWord.get(sLemma, 0) + 1
return dWord
# IBDAWG functions
def isValidToken (self, sToken):
"checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)"
if self.oMainDic.isValidToken(sToken):
return True
|
>
|
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
|
else:
if not bByLemma:
dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
else:
for sLemma in self.getLemma(dToken['sValue']):
dWord[sLemma] = dWord.get(sLemma, 0) + 1
return dWord
# IBDAWG functions
def isValidToken (self, sToken):
"checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)"
if self.oMainDic.isValidToken(sToken):
return True
|
| ︙ | | | ︙ | |
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
|
if sWord not in self._dLemmas:
self.getMorph(sWord)
return self._dLemmas[sWord]
return { s[1:s.find("/")] for s in self.getMorph(sWord) }
def suggest (self, sWord, nSuggLimit=10):
"generator: returns 1, 2 or 3 lists of suggestions"
if self.dDefaultSugg:
if sWord in self.dDefaultSugg:
yield self.dDefaultSugg[sWord].split("|")
elif sWord.istitle() and sWord.lower() in self.dDefaultSugg:
lRes = self.dDefaultSugg[sWord.lower()].split("|")
yield list(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes))
else:
yield self.oMainDic.suggest(sWord, nSuggLimit, True)
else:
yield self.oMainDic.suggest(sWord, nSuggLimit, True)
if self.bCommunityDic:
yield self.oCommunityDic.suggest(sWord, (nSuggLimit//2)+1)
|
|
|
|
|
|
|
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
|
if sWord not in self._dLemmas:
self.getMorph(sWord)
return self._dLemmas[sWord]
return { s[1:s.find("/")] for s in self.getMorph(sWord) }
def suggest (self, sWord, nSuggLimit=10):
"generator: returns 1, 2 or 3 lists of suggestions"
if self.lexicographer.dSugg:
if sWord in self.lexicographer.dSugg:
yield self.lexicographer.dSugg[sWord].split("|")
elif sWord.istitle() and sWord.lower() in self.lexicographer.dSugg:
lRes = self.lexicographer.dSugg[sWord.lower()].split("|")
yield list(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes))
else:
yield self.oMainDic.suggest(sWord, nSuggLimit, True)
else:
yield self.oMainDic.suggest(sWord, nSuggLimit, True)
if self.bCommunityDic:
yield self.oCommunityDic.suggest(sWord, (nSuggLimit//2)+1)
|
| ︙ | | | ︙ | |