Grammalecte  Check-in [764811b5f1]

Overview
Comment:[graphspell] handling apostrophes
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | graphspell | rg
Files: files | file ages | folders
SHA3-256: 764811b5f19783c83bcb50bfd13541519375d39e87f5da56303360e3965260d3
User & Date: olr on 2018-08-26 14:44:48
Other Links: branch diff | manifest | tags
Context
2018-08-26
15:02
[fr] gendicfr: plus de copie des dictionnaires Hunspell dans les extensions Mozilla check-in: 8d3060486d user: olr tags: fr, rg
14:44
[graphspell] handling apostrophes check-in: 764811b5f1 user: olr tags: graphspell, rg
13:41
[fr] gendicfr: utilise le lemme alternatif s’il existe check-in: a9d1f17b1f user: olr tags: fr, rg
Changes

Modified graphspell-js/ibdawg.js from [068f06a16d] to [bd4ff8b3de].

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
250
...
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
...
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
...
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
...
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
        if (this.isValid(sToken)) {
            return true;
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
            return sToken.split("-").every(sWord  =>  this.isValid(sWord)); 
        }
        if (sToken.includes(".") || sToken.includes("·")) {
            return true;
        }
        return false;
    }

    isValid (sWord) {
        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (!sWord) {
            return null;
        }
        if (sWord.includes("")) { // ugly hack
            sWord = sWord.replace("’", "'");
        }
        if (this.lookup(sWord)) {
            return true;
        }
        if (sWord.charAt(0).gl_isUpperCase()) {
            if (sWord.length > 1) {
                if (sWord.gl_isTitle()) {
................................................................................
                        if (!zTagsPattern || zTagsPattern.test(this.lArcVal[nMorphVal])) {
                            yield [sWord, sStem, this.lArcVal[nMorphVal]];
                        }
                    }
                }
            }
        }
    }            

    _morph1 (sWord) {
        // returns morphologies of sWord
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
                return [];
................................................................................
            let l = [];
            let nRawArc = 0;
            while (!(nRawArc & this._lastArcMask)) {
                let iEndArcAddr = iAddr + this.nBytesArc;
                nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
                let nArc = nRawArc & this._arcMask;
                if (nArc > this.nChar) {
                    // This value is not a char, this is a stemming code 
                    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));
................................................................................
            let l = [];
            let nRawArc = 0;
            while (!(nRawArc & this._lastArcMask)) {
                let iEndArcAddr = iAddr + this.nBytesArc;
                nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
                let nArc = nRawArc & this._arcMask;
                if (nArc > this.nChar) {
                    // This value is not a char, this is a stemming code 
                    l.push(this.funcStemming(sWord, this.lArcVal[nArc]));
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
            return l;
        }
        return [];
................................................................................

    _lookupArcNode1 (nVal, iAddr) {
        // looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None
        while (true) {
            let iEndArcAddr = iAddr+this.nBytesArc;
            let nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
            if (nVal == (nRawArc & this._arcMask)) {
                // the value we are looking for 
                // we return the address of the next node
                return this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress));
            }
            else {
                // value not found
                if (nRawArc & this._lastArcMask) {
                    return null;







|












|
|







 







|







 







|







 







|







 







|







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
250
...
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
...
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
...
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
...
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
        if (this.isValid(sToken)) {
            return true;
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
            return sToken.split("-").every(sWord  =>  this.isValid(sWord));
        }
        if (sToken.includes(".") || sToken.includes("·")) {
            return true;
        }
        return false;
    }

    isValid (sWord) {
        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (!sWord) {
            return null;
        }
        if (sWord.includes("'")) { // ugly hack
            sWord = sWord.replace("'", "’");
        }
        if (this.lookup(sWord)) {
            return true;
        }
        if (sWord.charAt(0).gl_isUpperCase()) {
            if (sWord.length > 1) {
                if (sWord.gl_isTitle()) {
................................................................................
                        if (!zTagsPattern || zTagsPattern.test(this.lArcVal[nMorphVal])) {
                            yield [sWord, sStem, this.lArcVal[nMorphVal]];
                        }
                    }
                }
            }
        }
    }

    _morph1 (sWord) {
        // returns morphologies of sWord
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
                return [];
................................................................................
            let l = [];
            let nRawArc = 0;
            while (!(nRawArc & this._lastArcMask)) {
                let iEndArcAddr = iAddr + this.nBytesArc;
                nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
                let nArc = nRawArc & this._arcMask;
                if (nArc > this.nChar) {
                    // This value is not a char, this is a stemming code
                    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));
................................................................................
            let l = [];
            let nRawArc = 0;
            while (!(nRawArc & this._lastArcMask)) {
                let iEndArcAddr = iAddr + this.nBytesArc;
                nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
                let nArc = nRawArc & this._arcMask;
                if (nArc > this.nChar) {
                    // This value is not a char, this is a stemming code
                    l.push(this.funcStemming(sWord, this.lArcVal[nArc]));
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
            return l;
        }
        return [];
................................................................................

    _lookupArcNode1 (nVal, iAddr) {
        // looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None
        while (true) {
            let iEndArcAddr = iAddr+this.nBytesArc;
            let nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
            if (nVal == (nRawArc & this._arcMask)) {
                // the value we are looking for
                // we return the address of the next node
                return this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress));
            }
            else {
                // value not found
                if (nRawArc & this._lastArcMask) {
                    return null;

Modified graphspell/ibdawg.py from [0f1b5456be] to [15b71c861b].

245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
            return True
        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 self.lookup(sWord.lower())
                if sWord.isupper():







|
|







245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
            return True
        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 self.lookup(sWord.lower())
                if sWord.isupper():