214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
"sByDic": self.byDic.hex() if bBinaryDictAsHexString else [ e for e in self.byDic ]
}, ensure_ascii=False))
if bInJSModule:
hDst.write(";\n\nexports.dictionary = dictionary;\n")
def isValidToken (self, sToken):
"checks if <sToken> is valid (if there is hyphens in <sToken>, <sToken> is split, each part is checked)"
if self.isValid(sToken):
return True
if "-" in sToken:
if sToken.count("-") > 4:
return True
return all(self.isValid(sWord) for sWord in sToken.split("-"))
return False
|
>
|
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
|
"sByDic": self.byDic.hex() if bBinaryDictAsHexString else [ e for e in self.byDic ]
}, ensure_ascii=False))
if bInJSModule:
hDst.write(";\n\nexports.dictionary = dictionary;\n")
def isValidToken (self, sToken):
"checks if <sToken> is valid (if there is hyphens in <sToken>, <sToken> is split, each part is checked)"
sToken = cp.spellingNormalization(sToken)
if self.isValid(sToken):
return True
if "-" in sToken:
if sToken.count("-") > 4:
return True
return all(self.isValid(sWord) for sWord in sToken.split("-"))
return False
|
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
|
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr == None:
return False
return bool(int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask)
def getMorph (self, sWord):
"retrieves morphologies list, different casing allowed"
l = self.morph(sWord)
if sWord[0:1].isupper():
l.extend(self.morph(sWord.lower()))
if sWord.isupper() and len(sWord) > 1:
l.extend(self.morph(sWord.capitalize()))
return l
#@timethis
def suggest (self, sWord, nSuggLimit=10):
"returns a set of suggestions for <sWord>"
sPfx, sWord, sSfx = cp.cut(sWord)
nMaxSwitch = max(len(sWord) // 3, 1)
nMaxDel = len(sWord) // 5
nMaxHardRepl = max((len(sWord) - 5) // 4, 1)
oSuggResult = SuggResult(sWord)
self._suggest(oSuggResult, sWord, nMaxSwitch=nMaxSwitch, nMaxDel=nMaxDel, nMaxHardRepl=nMaxHardRepl)
if sWord.istitle():
|
>
>
|
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
|
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr == None:
return False
return bool(int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask)
def getMorph (self, sWord):
"retrieves morphologies list, different casing allowed"
sWord = cp.spellingNormalization(sWord)
l = self.morph(sWord)
if sWord[0:1].isupper():
l.extend(self.morph(sWord.lower()))
if sWord.isupper() and len(sWord) > 1:
l.extend(self.morph(sWord.capitalize()))
return l
#@timethis
def suggest (self, sWord, nSuggLimit=10):
"returns a set of suggestions for <sWord>"
sWord = cp.spellingNormalization(sWord)
sPfx, sWord, sSfx = cp.cut(sWord)
nMaxSwitch = max(len(sWord) // 3, 1)
nMaxDel = len(sWord) // 5
nMaxHardRepl = max((len(sWord) - 5) // 4, 1)
oSuggResult = SuggResult(sWord)
self._suggest(oSuggResult, sWord, nMaxSwitch=nMaxSwitch, nMaxDel=nMaxDel, nMaxHardRepl=nMaxHardRepl)
if sWord.istitle():
|
326
327
328
329
330
331
332
333
334
335
336
337
338
339
|
self._suggest(oSuggResult, "", nMaxSwitch, nMaxDel, nMaxHardRepl, nDeep+1, iAddr, sNewWord, True) # remove last char and go on
for sRepl in cp.dFinal1.get(sRemain, ()):
self._suggest(oSuggResult, sRepl, nMaxSwitch, nMaxDel, nMaxHardRepl, nDeep+1, iAddr, sNewWord, True)
#@timethis
def suggest2 (self, sWord, nMaxSugg=10):
"returns a set of suggestions for <sWord>"
sPfx, sWord, sSfx = cp.cut(sWord)
oSuggResult = SuggResult(sWord)
self._suggest2(oSuggResult)
aSugg = oSuggResult.getSuggestions()
if sSfx or sPfx:
# we add what we removed
return list(map(lambda sSug: sPfx + sSug + sSfx, aSugg))
|
>
|
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
|
self._suggest(oSuggResult, "", nMaxSwitch, nMaxDel, nMaxHardRepl, nDeep+1, iAddr, sNewWord, True) # remove last char and go on
for sRepl in cp.dFinal1.get(sRemain, ()):
self._suggest(oSuggResult, sRepl, nMaxSwitch, nMaxDel, nMaxHardRepl, nDeep+1, iAddr, sNewWord, True)
#@timethis
def suggest2 (self, sWord, nMaxSugg=10):
"returns a set of suggestions for <sWord>"
sWord = cp.spellingNormalization(sWord)
sPfx, sWord, sSfx = cp.cut(sWord)
oSuggResult = SuggResult(sWord)
self._suggest2(oSuggResult)
aSugg = oSuggResult.getSuggestions()
if sSfx or sPfx:
# we add what we removed
return list(map(lambda sSug: sPfx + sSug + sSfx, aSugg))
|
382
383
384
385
386
387
388
389
390
391
392
393
394
395
|
aTails.add(sTail + self.dCharVal[nVal])
if n and not aTails:
aTails.update(self._getTails(jAddr, sTail+self.dCharVal[nVal], n-1))
return aTails
def drawPath (self, sWord, iAddr=0):
"show the path taken by <sWord> in the graph"
c1 = sWord[0:1] if sWord else " "
iPos = -1
n = 0
print(c1 + ": ", end="")
for c2, jAddr in self._getCharArcs(iAddr):
print(c2, end="")
if c2 == sWord[0:1]:
|
>
|
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
|
aTails.add(sTail + self.dCharVal[nVal])
if n and not aTails:
aTails.update(self._getTails(jAddr, sTail+self.dCharVal[nVal], n-1))
return aTails
def drawPath (self, sWord, iAddr=0):
"show the path taken by <sWord> in the graph"
sWord = cp.spellingNormalization(sWord)
c1 = sWord[0:1] if sWord else " "
iPos = -1
n = 0
print(c1 + ": ", end="")
for c2, jAddr in self._getCharArcs(iAddr):
print(c2, end="")
if c2 == sWord[0:1]:
|