Grammalecte  Check-in [e7f46d5ce1]

Overview
Comment:[graphspell][js] dawg: bug fixing + code clarification
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | graphspell
Files: files | file ages | folders
SHA3-256: e7f46d5ce14d28183fc1b590a8781bbb3e3b964d95cd67c2f0c830805b896822
User & Date: olr on 2018-02-06 10:23:39
Other Links: manifest | tags
Context
2018-02-06
10:25
[fx] lexicon editor: focus on main input check-in: 5fd6e26506 user: olr tags: trunk, fx
10:23
[graphspell][js] dawg: bug fixing + code clarification check-in: e7f46d5ce1 user: olr tags: trunk, graphspell
10:22
[graphspell][py] dawg: code clarification check-in: b181054462 user: olr tags: trunk, graphspell
Changes

Modified graphspell-js/dawg.js from [fa338df471] to [2837f59006].

94
95
96
97
98
99
100
101
102
103



104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123

124
125
126
127
128
129
130
94
95
96
97
98
99
100



101
102
103
104
105
106





107
108
109
110
111
112
113

114
115
116

117
118
119
120
121
122
123
124







-
-
-
+
+
+



-
-
-
-
-







-



-
+







            lTemp.push(iTag+nChar+nAff)
            lWord.push(lTemp);
        }
        lEntry.length = 0; // clear the array
        
        // Dictionary of arc values occurrency, to sort arcs of each node
        let lKeyVal = [];
        for (let c of dChar.keys()) { lKeyVal.push([dChar[c], dCharOccur[c]]); }
        for (let sAff of dAff.keys()) { lKeyVal.push([dAff[sAff]+nChar, dAffOccur[sAff]]); }
        for (let sTag in dTag.keys()) { lKeyVal.push([dTag[sTag]+nChar+nAff, dTagOccur[sTag]]); }
        for (let c of dChar.keys()) { lKeyVal.push([dChar.get(c), dCharOccur.get(c)]); }
        for (let sAff of dAff.keys()) { lKeyVal.push([dAff.get(sAff)+nChar, dAffOccur.get(sAff)]); }
        for (let sTag of dTag.keys()) { lKeyVal.push([dTag.get(sTag)+nChar+nAff, dTagOccur.get(sTag)]); }
        let dValOccur = new Map(lKeyVal);
        lKeyVal.length = 0; // clear the array

        //with open(spfSrc[:-8]+".valuesfreq.txt", 'w', encoding='utf-8') as hFreqDst:  # DEBUG
        //    for iKey, nOcc in sorted(dValOccur.entries(), key=lambda t: t[1], reverse=True):
        //        hFreqDst.write("{}: {}\n".format(lVal[iKey], nOcc))
        //    hFreqDst.close()
        
        this.sLang = sLangName;
        this.nEntry = lWord.length;
        this.aPreviousEntry = [];
        oNodeCounter.reset();
        this.oRoot = new DawgNode();
        this.lUncheckedNodes = [];          // list of nodes that have not been checked for duplication.
        this.dMinimizedNodes = new Map();   // list of unique nodes that have been checked for duplication.
        this.lSortedNodes = [];             // version 2 and 3
        this.nNode = 0;
        this.nArc = 0;
        this.dChar = dChar;
        this.nChar = dChar.length;
        this.nChar = dChar.size;
        this.nAff = nAff;
        this.lArcVal = lVal;
        this.nArcVal = lVal.length;
        this.nTag = this.nArcVal - this.nChar - nAff;
        this.cStemming = cStemming;
        if (cStemming == "A") {
            this.funcStemming = str_transform.changeWordWithAffixCode;
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
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







+









-


+
+







        lWord.sort();
        if (xProgressBarNode) {
            xProgressBarNode.value = 0;
            xProgressBarNode.max = lWord.length;
        }
        let i = 0;
        for (let aEntry of lWord) {
            console.log(aEntry);
            this.insert(aEntry);
            if (xProgressBarNode) {
                xProgressBarNode.value = i;
                i += 1;
            }
        }
        this.finish();
        this.countNodes();
        this.countArcs();
        this.sortNodes();
        this.sortNodeArcs(dValOccur);
        this.displayInfo();
        this.writeInfo();
        //this.oRoot.display(0, this.lArcVal, true);
    }

    // BUILD DAWG
    insert (aEntry) {
        if (aEntry < this.aPreviousEntry) {
            throw "Error: Words must be inserted in alphabetical order.";
        }
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
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
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
250
251
252

253
254
255
256
257
258
259
260







-
+


















-
+







-
+




-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-













-
+










-
+







    finish () {
        // minimize unchecked nodes
        this._minimize(0);
    }

    _minimize (nDownTo) {
        // proceed from the leaf up to a certain point
        for (let i = this.lUncheckedNodes.length-1;  i < nDownTo-1;  i--) {
        for (let i = this.lUncheckedNodes.length-1;  i > nDownTo-1;  i--) {
            let [oNode, char, oChildNode] = this.lUncheckedNodes[i];
            if (this.dMinimizedNodes.has(oChildNode.__hash__())) {
                // replace the child with the previously encountered one
                oNode.arcs.set(char, this.dMinimizedNodes.get(oChildNode.__hash__()));
            } else {
                // add the state to the minimized nodes.
                this.dMinimizedNodes.set(oChildNode.__hash__(), oChildNode);
            }
            this.lUncheckedNodes.pop();
        }
    }

    countNodes () {
        this.nNode = this.dMinimizedNodes.size;
    }

    countArcs () {
        this.nArc = 0;
        for (let oNode of this.dMinimizedNodes) {
        for (let oNode of this.dMinimizedNodes.values()) {
            this.nArc += oNode.arcs.size;
        }
    }
    
    sortNodeArcs (dValOccur) {
        console.log(" > Sort node arcs");
        this.oRoot.sortArcs(dValOccur);
        for (let oNode of this.dMinimizedNodes) {
        for (let oNode of this.dMinimizedNodes.values()) {
            oNode.sortArcs(dValOccur);
        }
    }

    sortNodes () {
        console.log(" > Sort nodes");
        for (let oNode of this.oRoot.arcs.values()) {
            this._parseNodes(oNode);
        }
    }
    
    _parseNodes (oNode) {
        // Warning: recursive method
        if (oNode.pos > 0) {
            return;
        }
        //oNode.setPos();  // version 2
        this.lSortedNodes.push(oNode);
        for (let oNextNode of oNode.arcs.values()) {
             this._parseNodes(oNextNode);
        }
    }
        
    lookup (sWord) {
        let oNode = this.oRoot;
        for (let c of sWord) {
            if (!oNode.arcs.has(this.dChar.gl_get(c, ''))) {
                return false;
            }
            oNode = oNode.arcs.get(this.dChar.get(c));
        }
        return oNode.final;
    }

    morph (sWord) {
        let oNode = this.oRoot;
        for (let c in sWord) {
        for (let c of sWord) {
            if (!oNode.arcs.has(this.dChar.get(c, ''))) {
                return '';
            }
            oNode = oNode.arcs.get(this.dChar.get(c));
        }
        if (oNode.final) {
            let s = "* ";
            for (let arc of oNode.arcs.keys()) {
                if (arc >= this.nChar) {
                    s += " [" + this.funcStemming(sWord, this.lArcVal[arc]);
                    let oNode2 = oNode.arcs[arc]
                    let oNode2 = oNode.arcs.get(arc);
                    for (let arc2 of oNode2.arcs.keys()) {
                        s += " / " + this.lArcVal[arc2];
                    }
                    s += "]";
                }
            }
            return s;
311
312
313
314
315
316
317

318
319
320
321
322
323
324
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302







+








    writeInfo () {
        console.log(this.getArcStats());
        console.log("\n * Values:\n");
        let i = 0;
        for (let s of this.lArcVal) {
            console.log(i + ": " + s);
            i++;
        }
    }

    // BINARY CONVERSION
    createBinary (sPathFile, nMethod) {
        console.log("Write DAWG as an indexable binary dictionary [method: "+nMethod+"]");
        if (nMethod == 1) {
441
442
443
444
445
446
447
448
449
450
451
452
453

454

455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479

480
481
482
483
484
485
486
487
488













489
490
491
492
493
494
495
419
420
421
422
423
424
425


426
427
428
429
430

431





432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450

451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480







-
-




+
-
+
-
-
-
-
-



















-
+









+
+
+
+
+
+
+
+
+
+
+
+
+







class DawgNode {

    constructor () {
        this.i = oNodeCounter.getId();
        this.final = false;
        this.arcs = new Map();  // key: arc value; value: a node
        this.addr = 0;          // address in the binary dictionary
        this.pos = 0;           // position in the binary dictionary (version 2)
        this.size = 0;          // size of node in bytes (version 3)
    }

    __str__ () {
        // Caution! this function is used for hashing and comparison!
        let sFinalChar = (self.final) ? "1" : "0";
        let l = [];
        let l = [sFinalChar];
        if (this.final) {
            l.push("1");
        } else {
            l.push("0");
        }
        for (let [key, node] of this.arcs.entries()) {
            l.push(key.toString());
            l.push(node.i.toString());
        }
        return l.join("_");
    }

    __hash__ () {
        // Used as a key in a python dictionary.
        return this.__str__();
    }

    __eq__ (other) {
        // Used as a key in a python dictionary.
        // Nodes are equivalent if they have identical arcs, and each identical arc leads to identical states.
        return this.__str__() == other.__str__();
    }

    sortArcs (dValOccur) {
        let lTemp = this.arcs.entries();
        let lTemp = Array.from(this.arcs.entries());
        lTemp.sort(function (a, b) {
            if (dValOccur.get(a[0], 0) > dValOccur.get(b[0], 0))
                return -1;
            if (dValOccur.get(a[0], 0) < dValOccur.get(b[0], 0))
                return 1;
            return 0;
        });
        this.arcs = new Map(lTemp);
    }

    display (nTab, lArcVal, bRecur=false) {
        let sResult = "    ".repeat(nTab) + "Node: " + this.i + " " + this.final + "\n";
        for (let arc of this.arcs.keys()) {
            sResult += "    ".repeat(nTab) + lArcVal[arc] + "\n";
        }
        console.log(sResult);
        if (bRecur) {
            for (let oNode of this.arcs.values()) {
                oNode.display(nTab+1, lArcVal, bRecur);
            }
        }
    }

    // VERSION 1 =====================================================================================================
    convToBytes1 (nBytesArc, nBytesNodeAddress) {
        /*
            Node scheme:
            - Arc length is defined by nBytesArc
            - Address length is defined by nBytesNodeAddress
572
573
574
575
576
577
578
579

580
581
582
583
584
585
586
587
588
589
590
591
592
557
558
559
560
561
562
563

564
565
566
567
568
569
570
571
572
573
574
575
576
577







-
+













function getCharOrderAfterChar (cChar) {
    return _dCharOrder.gl_get(cChar, null);
}

function displayCharOrder () {
    for (let [key, value] of _dCharOrder.entries()) {
        let s = "[" + key + "]: ";
        let lTemp = value.entries();
        let lTemp = Array.from(value.entries());
        lTemp.sort(function (a, b) {
            if (a[1] > b[1])
                return -1;
            if (a[1] < b[1])
                return 1;
            return 0;
        });
        for (let [c, n] of lTemp) {
            s += c+":"+n+", ";
        }
        console.log(s);
    }
}