Grammalecte  Diff

Annotate Patch Unified Diff

Differences From Artifact [18fa7e7c19]:

To Artifact [1a4cdd2a3d]:

︙︙
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245

                            "_addrBitMask": self._addrBitMask,
                            "nBytesOffset": self.nBytesOffset
                        }, 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

    def isValid (self, sWord):
        "checks if sWord is valid (different casing tested if the first letter is a capital)"
        if not sWord:
            return None
        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()))
                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:]))
            else:
                return bool(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

    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, cPrevious='', 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 + " !!!")
                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:], cCurrent, nDeep+1, jAddr, sNewWord+cChar))
        if not bAvoidLoop: # avoid infinite loop
            #show(nDeep, ":no loop:")
            if cPrevious == cCurrent:
                # same char, we remove 1 char without adding 1 to <sNewWord>
                lSugg.extend(self._suggest(sWord[1:], cCurrent, nDeep+1, iAddr, sNewWord))
            for sRepl in cp.d1toX.get(cCurrent, ()):
                #show(nDeep, sRepl)
                lSugg.extend(self._suggest(sRepl + sWord[1:], cCurrent, nDeep+1, iAddr, sNewWord, True))




            if len(sWord) == 1:
                #show(nDeep, ":end of word:")
                # end of word
                for sRepl in cp.dFinal1.get(sWord, ()):
                    #show(nDeep, sRepl)
                    lSugg.extend(self._suggest(sRepl, cCurrent, nDeep+1, iAddr, sNewWord, True))
        return lSugg

    def _getSimilarArcs (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for c in cp.d1to1.get(cChar, [cChar]):
            if c in self.dChar:
                jAddr = self._lookupArcNode(self.dChar[c], iAddr)
                if jAddr:
                    yield (c, jAddr)

    def _suggestWithCrushedUselessChars (self, sWord, cPrevious='', nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
        if not sWord:
            if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
                show(nDeep, "!!! " + sNewWord + " !!!")
                return [sNewWord]
            return []
        lSugg = []
        cCurrent = sWord[0:1]
        for cChar, jAddr in self._getSimilarArcsAndCrushedChars(cCurrent, iAddr):
            show(nDeep, cChar)
            lSugg.extend(self._suggestWithCrushedUselessChars(sWord[1:], cCurrent, nDeep+1, jAddr, sNewWord+cChar))
        return lSugg

    def _getSimilarArcsAndCrushedChars (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for nVal, jAddr in self._getArcs(iAddr):
            if self.dVal.get(nVal, "") in cp.aUselessChar:
                yield (self.dVal[nVal], jAddr)








|









|




















|












|









|











|


|

|


|
>
>
>
>
|




|










|









|








130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249

                            "_addrBitMask": self._addrBitMask,
                            "nBytesOffset": self.nBytesOffset
                        }, 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

    def isValid (self, sWord):
        "checks if <sWord> is valid (different casing tested if the first letter is a capital)"
        if not sWord:
            return None
        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()))
                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:]))
            else:
                return bool(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

    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 + " !!!")
                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))
            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
                for sRepl in cp.dFinal1.get(sWord, ()):
                    #show(nDeep, sRepl)
                    lSugg.extend(self._suggest(sRepl, nDeep+1, iAddr, sNewWord, True))
        return lSugg

    def _getSimilarArcs (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for c in cp.d1to1.get(cChar, [cChar]):
            if c in self.dChar:
                jAddr = self._lookupArcNode(self.dChar[c], iAddr)
                if jAddr:
                    yield (c, jAddr)

    def _suggestWithCrushedUselessChars (self, sWord, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False):
        if not sWord:
            if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
                show(nDeep, "!!! " + sNewWord + " !!!")
                return [sNewWord]
            return []
        lSugg = []
        cCurrent = sWord[0:1]
        for cChar, jAddr in self._getSimilarArcsAndCrushedChars(cCurrent, iAddr):
            show(nDeep, cChar)
            lSugg.extend(self._suggestWithCrushedUselessChars(sWord[1:], nDeep+1, jAddr, sNewWord+cChar))
        return lSugg

    def _getSimilarArcsAndCrushedChars (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for nVal, jAddr in self._getArcs(iAddr):
            if self.dVal.get(nVal, "") in cp.aUselessChar:
                yield (self.dVal[nVal], jAddr)
︙︙
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304

                        l.append(sStem + " " + self.lArcVal[nRawArc2 & self._arcMask])
                        iAddr2 = iEndArcAddr2+self.nBytesNodeAddress
                iAddr = iEndArcAddr+self.nBytesNodeAddress
            return l
        return []

    def _stem1 (self, sWord):
        "returns stems list of sWord"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []








|








294
295
296
297
298
299
300
301
302
303
304
305
306
307
308

                        l.append(sStem + " " + self.lArcVal[nRawArc2 & self._arcMask])
                        iAddr2 = iEndArcAddr2+self.nBytesNodeAddress
                iAddr = iEndArcAddr+self.nBytesNodeAddress
            return l
        return []

    def _stem1 (self, sWord):
        "returns stems list of <sWord>"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []
︙︙
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327

                    # This value is not a char, this is a stemming code 
                    l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
                iAddr = iEndArcAddr+self.nBytesNodeAddress
            return l
        return []

    def _lookupArcNode1 (self, nVal, iAddr):
        "looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None"
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            if nVal == (nRawArc & self._arcMask):
                # the value we are looking for 
                # we return the address of the next node
                return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')








|








317
318
319
320
321
322
323
324
325
326
327
328
329
330
331

                    # This value is not a char, this is a stemming code 
                    l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
                iAddr = iEndArcAddr+self.nBytesNodeAddress
            return l
        return []

    def _lookupArcNode1 (self, nVal, iAddr):
        "looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            if nVal == (nRawArc & self._arcMask):
                # the value we are looking for 
                # we return the address of the next node
                return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
︙︙
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371

                iAddr = iEndArcAddr+self.nBytesNodeAddress
                if (nRawArc & self._lastArcMask) and iAddr < len(self.byDic):
                    hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
            hDst.close()

    # VERSION 2
    def _morph2 (self, sWord):
        "returns morphologies of sWord"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []








|








361
362
363
364
365
366
367
368
369
370
371
372
373
374
375

                iAddr = iEndArcAddr+self.nBytesNodeAddress
                if (nRawArc & self._lastArcMask) and iAddr < len(self.byDic):
                    hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
            hDst.close()

    # VERSION 2
    def _morph2 (self, sWord):
        "returns morphologies of <sWord>"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []
︙︙
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409

                        l.append(sStem + " " + self.lArcVal[nRawArc2 & self._arcMask])
                        iAddr2 = iEndArcAddr2+self.nBytesNodeAddress  if not (nRawArc2 & self._addrBitMask) else iEndArcAddr2
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr
            return l
        return []

    def _stem2 (self, sWord):
        "returns stems list of sWord"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []








|








399
400
401
402
403
404
405
406
407
408
409
410
411
412
413

                        l.append(sStem + " " + self.lArcVal[nRawArc2 & self._arcMask])
                        iAddr2 = iEndArcAddr2+self.nBytesNodeAddress  if not (nRawArc2 & self._addrBitMask) else iEndArcAddr2
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr
            return l
        return []

    def _stem2 (self, sWord):
        "returns stems list of <sWord>"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []
︙︙
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441

                            nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
                            iAddr2 += self.nBytesArc + self.nBytesNodeAddress
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr
            return l
        return []

    def _lookupArcNode2 (self, nVal, iAddr):
        "looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None"
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            if nVal == (nRawArc & self._arcMask):
                # the value we are looking for 
                if not (nRawArc & self._addrBitMask):
                    # we return the address of the next node








|








431
432
433
434
435
436
437
438
439
440
441
442
443
444
445

                            nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
                            iAddr2 += self.nBytesArc + self.nBytesNodeAddress
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr
            return l
        return []

    def _lookupArcNode2 (self, nVal, iAddr):
        "looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            if nVal == (nRawArc & self._arcMask):
                # the value we are looking for 
                if not (nRawArc & self._addrBitMask):
                    # we return the address of the next node
︙︙
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486

                    iAddr = iEndArcAddr
                if (nRawArc & self._lastArcMask):
                    hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
            hDst.close()

    # VERSION 3
    def _morph3 (self, sWord):
        "returns morphologies of sWord"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []








|








476
477
478
479
480
481
482
483
484
485
486
487
488
489
490

                    iAddr = iEndArcAddr
                if (nRawArc & self._lastArcMask):
                    hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
            hDst.close()

    # VERSION 3
    def _morph3 (self, sWord):
        "returns morphologies of <sWord>"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []
︙︙
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521

                        l.append(sStem + " " + self.lArcVal[nRawArc2 & self._arcMask])
                        iAddr2 = iEndArcAddr2+self.nBytesNodeAddress  if not (nRawArc2 & self._addrBitMask) else iEndArcAddr2+self.nBytesOffset
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr+self.nBytesOffset
            return l
        return []

    def _stem3 (self, sWord):
        "returns stems list of sWord"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []








|








511
512
513
514
515
516
517
518
519
520
521
522
523
524
525

                        l.append(sStem + " " + self.lArcVal[nRawArc2 & self._arcMask])
                        iAddr2 = iEndArcAddr2+self.nBytesNodeAddress  if not (nRawArc2 & self._addrBitMask) else iEndArcAddr2+self.nBytesOffset
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr+self.nBytesOffset
            return l
        return []

    def _stem3 (self, sWord):
        "returns stems list of <sWord>"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []
            iAddr = self._lookupArcNode(self.dChar[c], iAddr)
            if iAddr == None:
                return []
︙︙
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545

                    # This value is not a char, this is a stemming code 
                    l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr+self.nBytesOffset
            return l
        return []

    def _lookupArcNode3 (self, nVal, iAddr):
        "looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None"
        iAddrNode = iAddr
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            if nVal == (nRawArc & self._arcMask):
                # the value we are looking for 
                if not (nRawArc & self._addrBitMask):








|








535
536
537
538
539
540
541
542
543
544
545
546
547
548
549

                    # This value is not a char, this is a stemming code 
                    l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
                iAddr = iEndArcAddr+self.nBytesNodeAddress  if not (nRawArc & self._addrBitMask)  else iEndArcAddr+self.nBytesOffset
            return l
        return []

    def _lookupArcNode3 (self, nVal, iAddr):
        "looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
        iAddrNode = iAddr
        while True:
            iEndArcAddr = iAddr+self.nBytesArc
            nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
            if nVal == (nRawArc & self._arcMask):
                # the value we are looking for 
                if not (nRawArc & self._addrBitMask):
︙︙
Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.007s