150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
|
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
-
+
-
-
+
+
-
+
-
+
-
+
+
+
+
|
if "’" in sWord: # ugly hack
sWord = sWord.replace("’", "'")
if self.lookup(sWord):
return True
if sWord[0:1].isupper():
if len(sWord) > 1:
if sWord.istitle():
return bool(self.lookup(sWord.lower()))
return self.lookup(sWord.lower())
if sWord.isupper():
if self.bOptNumSigle:
return True
return bool(self.lookup(sWord.lower()) or self.lookup(sWord.capitalize()))
return bool(self.lookup(sWord[:1].lower() + sWord[1:]))
return self.lookup(sWord.lower()) or self.lookup(sWord.capitalize())
return self.lookup(sWord[:1].lower() + sWord[1:])
else:
return bool(self.lookup(sWord.lower()))
return self.lookup(sWord.lower())
return False
def lookup (self, sWord):
"returns True if <sWord> in dictionary (strict verification)"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return False
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr == None:
return False
return int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask
return bool(int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask)
def suggest (self, sWord):
"returns a set of similar words"
# first, we check for similar words
#return set(self._suggestWithCrushedUselessChars(cp.clearWord(sWord)))
lSugg = self._suggest(sWord)
if not lSugg:
lSugg.extend(self._suggest(sWord[1:]))
lSugg.extend(self._suggest(sWord[:-1]))
lSugg.extend(self._suggest(sWord[1:-1]))
if not lSugg:
lSugg.extend(self._suggestWithCrushedUselessChars(cp.clearWord(sWord)))
return set(lSugg)
def _suggest (self, sWord, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
# RECURSIVE FUNCTION
if not sWord:
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
show(nDeep, "!!! " + sNewWord + " !!!")
show(nDeep, "___" + sNewWord + "___")
return [sNewWord]
return []
#show(nDeep, "<" + sWord + "> ===> " + sNewWord)
lSugg = []
cCurrent = sWord[0:1]
for cChar, jAddr in self._getSimilarArcs(cCurrent, iAddr):
#show(nDeep, cChar)
lSugg.extend(self._suggest(sWord[1:], nDeep+1, jAddr, sNewWord+cChar))
if not bAvoidLoop: # avoid infinite loop
#show(nDeep, ":no loop:")
if cCurrent == sWord[1:2]:
# same char, we remove 1 char without adding 1 to <sNewWord>
lSugg.extend(self._suggest(sWord[1:], nDeep+1, iAddr, sNewWord))
for sRepl in cp.d1toX.get(cCurrent, ()):
#show(nDeep, sRepl)
lSugg.extend(self._suggest(sRepl + sWord[1:], nDeep+1, iAddr, sNewWord, True))
for sRepl in cp.d2toX.get(sWord[0:2], ()):
#show(nDeep, sRepl)
lSugg.extend(self._suggest(sRepl + sWord[2:], nDeep+1, iAddr, sNewWord, True))
if len(sWord) == 2:
for sRepl in cp.dFinal2.get(sWord, ()):
#show(nDeep, sRepl)
lSugg.extend(self._suggest(sRepl, nDeep+1, iAddr, sNewWord, True))
elif len(sWord) == 1:
#show(nDeep, ":end of word:")
# end of word
|