Grammalecte  Check-in [c5c926760b]

Overview
Comment:[graphspell] end of lemma is now a slash instead of a space
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | graphspell | rg
Files: files | file ages | folders
SHA3-256: c5c926760b88e94d5a1ea9b32aad40e78b329aa9b44308191a90a557bdde39fb
User & Date: olr on 2018-06-06 09:54:07
Other Links: branch diff | manifest | tags
Context
2018-06-06
10:35
[fr] end of lemma is now a slash instead of a space check-in: 3bd7a19c94 user: olr tags: fr, rg
09:54
[graphspell] end of lemma is now a slash instead of a space check-in: c5c926760b user: olr tags: graphspell, rg
09:30
[core] darg: merge morph and morphex functions check-in: 4134a01a49 user: olr tags: core, rg
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Modified graphspell-js/ibdawg.js from [241ce099fe] to [068f06a16d].

︙︙
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524

                    let sStem = ">" + this.funcStemming(sWord, this.lArcVal[nArc]);
                    // Now , we go to the next node and retrieve all following arcs values, all of them are tags
                    let iAddr2 = this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress));
                    let nRawArc2 = 0;
                    while (!(nRawArc2 & this._lastArcMask)) {
                        let iEndArcAddr2 = iAddr2 + this.nBytesArc;
                        nRawArc2 = this._convBytesToInteger(this.byDic.slice(iAddr2, iEndArcAddr2));
                        l.push(sStem + " " + this.lArcVal[nRawArc2 & this._arcMask]);
                        iAddr2 = iEndArcAddr2+this.nBytesNodeAddress;
                    }
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
            return l;
        }








|








510
511
512
513
514
515
516
517
518
519
520
521
522
523
524

                    let sStem = ">" + this.funcStemming(sWord, this.lArcVal[nArc]);
                    // Now , we go to the next node and retrieve all following arcs values, all of them are tags
                    let iAddr2 = this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress));
                    let nRawArc2 = 0;
                    while (!(nRawArc2 & this._lastArcMask)) {
                        let iEndArcAddr2 = iAddr2 + this.nBytesArc;
                        nRawArc2 = this._convBytesToInteger(this.byDic.slice(iAddr2, iEndArcAddr2));
                        l.push(sStem + "/" + this.lArcVal[nRawArc2 & this._arcMask]);
                        iAddr2 = iEndArcAddr2+this.nBytesNodeAddress;
                    }
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
            return l;
        }
︙︙

Modified graphspell-js/spellchecker.js from [a6bdb52bd3] to [5b9ccbbb56].

︙︙
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264

            lMorph.push(...this.oCommunityDic.getMorph(sWord));
        }
        if (this.bPersonalDic) {
            lMorph.push(...this.oPersonalDic.getMorph(sWord));
        }
        if (this.bStorage) {
            this._dMorphologies.set(sWord, lMorph);
            this._dLemmas.set(sWord, Array.from(new Set(this.getMorph(sWord).map((sMorph) => { return sMorph.slice(1, sMorph.indexOf(" ")); }))));
            //console.log(sWord, this._dLemmas.get(sWord));
        }
        return lMorph;
    }

    getLemma (sWord) {
        // retrieves lemmas
        if (this.bStorage) {
            if (!this._dLemmas.has(sWord)) {
                this.getMorph(sWord);
            }
            return this._dLemmas.get(sWord);
        }
        return Array.from(new Set(this.getMorph(sWord).map((sMorph) => { return sMorph.slice(1, sMorph.indexOf(" ")); })));
    }

    * suggest (sWord, nSuggLimit=10) {
        // generator: returns 1, 2 or 3 lists of suggestions
        yield this.oMainDic.suggest(sWord, nSuggLimit);
        if (this.bExtendedDic) {
            yield this.oExtendedDic.suggest(sWord, nSuggLimit);








|













|








236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264

            lMorph.push(...this.oCommunityDic.getMorph(sWord));
        }
        if (this.bPersonalDic) {
            lMorph.push(...this.oPersonalDic.getMorph(sWord));
        }
        if (this.bStorage) {
            this._dMorphologies.set(sWord, lMorph);
            this._dLemmas.set(sWord, Array.from(new Set(this.getMorph(sWord).map((sMorph) => { return sMorph.slice(1, sMorph.indexOf("/")); }))));
            //console.log(sWord, this._dLemmas.get(sWord));
        }
        return lMorph;
    }

    getLemma (sWord) {
        // retrieves lemmas
        if (this.bStorage) {
            if (!this._dLemmas.has(sWord)) {
                this.getMorph(sWord);
            }
            return this._dLemmas.get(sWord);
        }
        return Array.from(new Set(this.getMorph(sWord).map((sMorph) => { return sMorph.slice(1, sMorph.indexOf("/")); })));
    }

    * suggest (sWord, nSuggLimit=10) {
        // generator: returns 1, 2 or 3 lists of suggestions
        yield this.oMainDic.suggest(sWord, nSuggLimit);
        if (this.bExtendedDic) {
            yield this.oExtendedDic.suggest(sWord, nSuggLimit);
︙︙

Modified graphspell/ibdawg.py from [a255097656] to [71ae57c736].

︙︙
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499

                    sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
                    # Now , we go to the next node and retrieve all following arcs values, all of them are tags
                    iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
                    nRawArc2 = 0
                    while not (nRawArc2 & self._lastArcMask):
                        iEndArcAddr2 = iAddr2 + self.nBytesArc
                        nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
                        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>"








|








485
486
487
488
489
490
491
492
493
494
495
496
497
498
499

                    sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
                    # Now , we go to the next node and retrieve all following arcs values, all of them are tags
                    iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
                    nRawArc2 = 0
                    while not (nRawArc2 & self._lastArcMask):
                        iEndArcAddr2 = iAddr2 + self.nBytesArc
                        nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
                        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>"
︙︙
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604

                        while not (nRawArc & self._lastArcMask):
                            nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
                            iAddr2 += self.nBytesArc + self.nBytesNodeAddress
                    nRawArc2 = 0
                    while not (nRawArc2 & self._lastArcMask):
                        iEndArcAddr2 = iAddr2 + self.nBytesArc
                        nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
                        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>"








|








590
591
592
593
594
595
596
597
598
599
600
601
602
603
604

                        while not (nRawArc & self._lastArcMask):
                            nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
                            iAddr2 += self.nBytesArc + self.nBytesNodeAddress
                    nRawArc2 = 0
                    while not (nRawArc2 & self._lastArcMask):
                        iEndArcAddr2 = iAddr2 + self.nBytesArc
                        nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
                        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>"
︙︙
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716

                        iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
                    else:
                        iAddr2 = iAddrNode + int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
                    nRawArc2 = 0
                    while not (nRawArc2 & self._lastArcMask):
                        iEndArcAddr2 = iAddr2 + self.nBytesArc
                        nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
                        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>"








|








702
703
704
705
706
707
708
709
710
711
712
713
714
715
716

                        iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
                    else:
                        iAddr2 = iAddrNode + int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
                    nRawArc2 = 0
                    while not (nRawArc2 & self._lastArcMask):
                        iEndArcAddr2 = iAddr2 + self.nBytesArc
                        nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
                        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>"
︙︙

Modified graphspell/spellchecker.py from [70326fed78] to [e03172e122].

︙︙
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232

            lMorph.extend(self.oExtendedDic.getMorph(sWord))
        if self.bCommunityDic:
            lMorph.extend(self.oCommunityDic.getMorph(sWord))
        if self.bPersonalDic:
            lMorph.extend(self.oPersonalDic.getMorph(sWord))
        if self.bStorage:
            self._dMorphologies[sWord] = lMorph
            self._dLemmas[sWord] = set([ s[1:s.find(" ")]  for s in lMorph ])
        return lMorph

    def getLemma (self, sWord):
        "retrieves lemmas"
        if self.bStorage:
            if sWord not in self._dLemmas:
                self.getMorph(sWord)
            return self._dLemmas[sWord]
        return set([ 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:








|








|








209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232

            lMorph.extend(self.oExtendedDic.getMorph(sWord))
        if self.bCommunityDic:
            lMorph.extend(self.oCommunityDic.getMorph(sWord))
        if self.bPersonalDic:
            lMorph.extend(self.oPersonalDic.getMorph(sWord))
        if self.bStorage:
            self._dMorphologies[sWord] = lMorph
            self._dLemmas[sWord] = set([ s[1:s.find("/")]  for s in lMorph ])
        return lMorph

    def getLemma (self, sWord):
        "retrieves lemmas"
        if self.bStorage:
            if sWord not in self._dLemmas:
                self.getMorph(sWord)
            return self._dLemmas[sWord]
        return set([ 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:
︙︙

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.006s