325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
|
}
}
}
}
}
// BINARY CONVERSION
createBinary (nMethod) {
console.log("Write DAWG as an indexable binary dictionary [method: "+nMethod+"]");
if (nMethod == 1) {
this.nBytesArc = Math.floor( (this.nArcVal.toString(2).length + 2) / 8 ) + 1; // We add 2 bits. See DawgNode.convToBytes1()
this.nBytesOffset = 0;
this._calcNumBytesNodeAddress();
this._calcNodesAddress1();
} else {
console.log("Error: unknown compression method");
}
console.log("Arc values (chars, affixes and tags): " + this.nArcVal);
console.log("Arc size: "+this.nBytesArc+" bytes, Address size: "+this.nBytesNodeAddress+" bytes");
console.log("-> " + this.nBytesArc+this.nBytesNodeAddress + " * " + this.nArc + " = " + (this.nBytesArc+this.nBytesNodeAddress)*this.nArc + " bytes");
return this._createJSON(nMethod);
}
_calcNumBytesNodeAddress () {
// how many bytes needed to store all nodes/arcs in the binary dictionary
this.nBytesNodeAddress = 1;
while (((this.nBytesArc + this.nBytesNodeAddress) * this.nArc) > (2 ** (this.nBytesNodeAddress * 8))) {
this.nBytesNodeAddress += 1;
}
}
_calcNodesAddress1 () {
let nBytesNode = this.nBytesArc + this.nBytesNodeAddress;
let iAddr = this.oRoot.arcs.size * nBytesNode;
for (let oNode of this.dMinimizedNodes.values()) {
oNode.addr = iAddr;
iAddr += Math.max(oNode.arcs.size, 1) * nBytesNode;
}
}
_createJSON (nMethod) {
let sByDic = "";
if (nMethod == 1) {
sByDic = this.oRoot.convToBytes1(this.nBytesArc, this.nBytesNodeAddress);
for (let oNode of this.dMinimizedNodes.values()) {
sByDic += oNode.convToBytes1(this.nBytesArc, this.nBytesNodeAddress);
}
}
let oJSON = {
"sName": this.sName,
"nVersion": nMethod,
"sDate": this._getDate(),
"sHeader": this.sHeader + nMethod + "/",
"lArcVal": this.lArcVal,
"nArcVal": this.nArcVal,
"byDic": sByDic, // binary word graph
"sLang": this.sLang,
"nChar": this.nChar,
"nBytesArc": this.nBytesArc,
"nBytesNodeAddress": this.nBytesNodeAddress,
|
|
|
|
|
|
|
|
|
|
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
|
}
}
}
}
}
// BINARY CONVERSION
createBinary (nCompressionMethod) {
console.log("Write DAWG as an indexable binary dictionary [method: "+nCompressionMethod+"]");
if (nCompressionMethod == 1) {
this.nBytesArc = Math.floor( (this.nArcVal.toString(2).length + 2) / 8 ) + 1; // We add 2 bits. See DawgNode.convToBytes1()
this.nBytesOffset = 0;
this._calcNumBytesNodeAddress();
this._calcNodesAddress1();
} else {
console.log("Error: unknown compression method");
}
console.log("Arc values (chars, affixes and tags): " + this.nArcVal);
console.log("Arc size: "+this.nBytesArc+" bytes, Address size: "+this.nBytesNodeAddress+" bytes");
console.log("-> " + this.nBytesArc+this.nBytesNodeAddress + " * " + this.nArc + " = " + (this.nBytesArc+this.nBytesNodeAddress)*this.nArc + " bytes");
return this._createJSON(nCompressionMethod);
}
_calcNumBytesNodeAddress () {
// how many bytes needed to store all nodes/arcs in the binary dictionary
this.nBytesNodeAddress = 1;
while (((this.nBytesArc + this.nBytesNodeAddress) * this.nArc) > (2 ** (this.nBytesNodeAddress * 8))) {
this.nBytesNodeAddress += 1;
}
}
_calcNodesAddress1 () {
let nBytesNode = this.nBytesArc + this.nBytesNodeAddress;
let iAddr = this.oRoot.arcs.size * nBytesNode;
for (let oNode of this.dMinimizedNodes.values()) {
oNode.addr = iAddr;
iAddr += Math.max(oNode.arcs.size, 1) * nBytesNode;
}
}
_createJSON (nCompressionMethod) {
let sByDic = "";
if (nCompressionMethod == 1) {
sByDic = this.oRoot.convToBytes1(this.nBytesArc, this.nBytesNodeAddress);
for (let oNode of this.dMinimizedNodes.values()) {
sByDic += oNode.convToBytes1(this.nBytesArc, this.nBytesNodeAddress);
}
}
let oJSON = {
"sName": this.sName,
"nCompressionMethod": nCompressionMethod,
"sDate": this._getDate(),
"sHeader": this.sHeader + nCompressionMethod + "/",
"lArcVal": this.lArcVal,
"nArcVal": this.nArcVal,
"byDic": sByDic, // binary word graph
"sLang": this.sLang,
"nChar": this.nChar,
"nBytesArc": this.nBytesArc,
"nBytesNodeAddress": this.nBytesNodeAddress,
|