Grammalecte  Diff

Differences From Artifact [10dd14ace9]:

To Artifact [cdddd20c84]:


72
73
74
75
76
77
78
79

80
81
82
83
84
85
86

87
88
89
90
91
92
93
94
95
96
97
98
99
100

101
102
103
104
105
106
107
                break;
            default:
                throw ValueError("# Error: unknown code: " + this.nVersion);
        }
        //console.log(this.getInfo());
        this.bOptNumSigle = true;
        this.bOptNumAtLast = false;
    };


    getInfo () {
        return  `  Language: ${this.sLang}      Version: ${this.nVersion}      Stemming: ${this.cStemming}FX\n` +
                `  Arcs values:  ${this.nArcVal} = ${this.nChar} characters,  ${this.nAff} affixes,  ${this.nTag} tags\n` +
                `  Dictionary: ${this.nEntries} entries,    ${this.nNode} nodes,   ${this.nArc} arcs\n` +
                `  Address size: ${this.nBytesNodeAddress} bytes,  Arc size: ${this.nBytesArc} bytes\n`;
    };


    isValidToken (sToken) {
        // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)
        if (this.isValid(sToken)) {
            return true;
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
            return sToken.split("-").every(sWord  =>  this.isValid(sWord)); 
        }
        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







<
>






<
>













<
>







72
73
74
75
76
77
78

79
80
81
82
83
84
85

86
87
88
89
90
91
92
93
94
95
96
97
98
99

100
101
102
103
104
105
106
107
                break;
            default:
                throw ValueError("# Error: unknown code: " + this.nVersion);
        }
        //console.log(this.getInfo());
        this.bOptNumSigle = true;
        this.bOptNumAtLast = false;

    }

    getInfo () {
        return  `  Language: ${this.sLang}      Version: ${this.nVersion}      Stemming: ${this.cStemming}FX\n` +
                `  Arcs values:  ${this.nArcVal} = ${this.nChar} characters,  ${this.nAff} affixes,  ${this.nTag} tags\n` +
                `  Dictionary: ${this.nEntries} entries,    ${this.nNode} nodes,   ${this.nArc} arcs\n` +
                `  Address size: ${this.nBytesNodeAddress} bytes,  Arc size: ${this.nBytesArc} bytes\n`;

    }

    isValidToken (sToken) {
        // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)
        if (this.isValid(sToken)) {
            return true;
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
            return sToken.split("-").every(sWord  =>  this.isValid(sWord)); 
        }
        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
123
124
125
126
127
128
129
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
                }
                return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1));
            } else {
                return !!this.lookup(sWord.toLowerCase());
            }
        }
        return false;
    };


    _convBytesToInteger (aBytes) {
        // Byte order = Big Endian (bigger first)
        let nVal = 0;
        let nWeight = (aBytes.length - 1) * 8;
        for (let n of aBytes) {
            nVal += n << nWeight;
            nWeight = nWeight - 8;
        }
        return nVal;
    };


    lookup (sWord) {
        // returns true if sWord in dictionary (strict verification)
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
                return false;
            }
            iAddr = this._lookupArcNode(this.dChar.get(c), iAddr);
            if (iAddr === null) {
                return false;
            }
        }
        return Boolean(this._convBytesToInteger(this.byDic.slice(iAddr, iAddr+this.nBytesArc)) & this._finalNodeMask);
    };


    getMorph (sWord) {
        // retrieves morphologies list, different casing allowed
        let l = this.morph(sWord);
        if (sWord[0].gl_isUpperCase()) {
            l = l.concat(this.morph(sWord.toLowerCase()));
            if (sWord.gl_isUpperCase() && sWord.length > 1) {
                l = l.concat(this.morph(sWord.gl_toCapitalize()));
            }
        }
        return l;
    };


    // morph (sWord) {
    //     is defined in constructor
    // };
    
    // VERSION 1
    _morph1 (sWord) {
        // returns morphologies of sWord
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {







<
>










<
>














<
>











<
>



|







123
124
125
126
127
128
129

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
                }
                return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1));
            } else {
                return !!this.lookup(sWord.toLowerCase());
            }
        }
        return false;

    }

    _convBytesToInteger (aBytes) {
        // Byte order = Big Endian (bigger first)
        let nVal = 0;
        let nWeight = (aBytes.length - 1) * 8;
        for (let n of aBytes) {
            nVal += n << nWeight;
            nWeight = nWeight - 8;
        }
        return nVal;

    }

    lookup (sWord) {
        // returns true if sWord in dictionary (strict verification)
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
                return false;
            }
            iAddr = this._lookupArcNode(this.dChar.get(c), iAddr);
            if (iAddr === null) {
                return false;
            }
        }
        return Boolean(this._convBytesToInteger(this.byDic.slice(iAddr, iAddr+this.nBytesArc)) & this._finalNodeMask);

    }

    getMorph (sWord) {
        // retrieves morphologies list, different casing allowed
        let l = this.morph(sWord);
        if (sWord[0].gl_isUpperCase()) {
            l = l.concat(this.morph(sWord.toLowerCase()));
            if (sWord.gl_isUpperCase() && sWord.length > 1) {
                l = l.concat(this.morph(sWord.gl_toCapitalize()));
            }
        }
        return l;

    }

    // morph (sWord) {
    //     is defined in constructor
    // }
    
    // VERSION 1
    _morph1 (sWord) {
        // returns morphologies of sWord
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
205
206
207
208
209
210
211
212

213
214
215
216
217
218
219
                    }
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
            return l;
        }
        return [];
    };


    _stem1 (sWord) {
        // returns stems list of sWord
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
                return [];







<
>







205
206
207
208
209
210
211

212
213
214
215
216
217
218
219
                    }
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
            return l;
        }
        return [];

    }

    _stem1 (sWord) {
        // returns stems list of sWord
        let iAddr = 0;
        for (let c of sWord) {
            if (!this.dChar.has(c)) {
                return [];
235
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
265
266
267

268
269
270
271

272
273
274
275

276
277
278
279
280
281

282
283
284
285

286
287
288
289

290
291
292
293
294
295
                    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;
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
        }
    };


    // VERSION 2
    _morph2 (sWord) {
        // to do
    };


    _stem2 (sWord) {
        // to do
    };


    _lookupArcNode2 (nVal, iAddr) {
        // to do
    };



    // VERSION 3
    _morph3 (sWord) {
        // to do
    };


    _stem3 (sWord) {
        // to do
    };


    _lookupArcNode3 (nVal, iAddr) {
        // to do
    };

}


if (typeof(exports) !== 'undefined') {
    exports.IBDAWG = IBDAWG;
}







<
>



















<
>




<
>



<
>



<
>





<
>



<
>



<
>






235
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
265
266

267
268
269
270

271
272
273
274

275
276
277
278
279
280

281
282
283
284

285
286
287
288

289
290
291
292
293
294
295
                    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;
                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
        }

    }

    // VERSION 2
    _morph2 (sWord) {
        // to do

    }

    _stem2 (sWord) {
        // to do

    }

    _lookupArcNode2 (nVal, iAddr) {
        // to do

    }


    // VERSION 3
    _morph3 (sWord) {
        // to do

    }

    _stem3 (sWord) {
        // to do

    }

    _lookupArcNode3 (nVal, iAddr) {
        // to do

    }
}


if (typeof(exports) !== 'undefined') {
    exports.IBDAWG = IBDAWG;
}