180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
|
asString () {
let s = "===== TEXT =====\n"
s += "sentence: " + this.sSentence0 + "\n";
s += "now: " + this.sSentence + "\n";
for (let dToken of this.lToken) {
s += '#${dToken["i"]}\t${dToken["nStart"]}:{$dToken["nEnd"]}\t${dToken["sValue"]}\t${dToken["sType"]}';
if (dToken.has("lMorph")) {
s += "\t" + dToken["lMorph"].toString();
}
if (dToken.has("tags")) {
s += "\t" + dToken["tags"].toString();
}
s += "\n";
}
return s;
}
|
|
|
|
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
|
asString () {
let s = "===== TEXT =====\n"
s += "sentence: " + this.sSentence0 + "\n";
s += "now: " + this.sSentence + "\n";
for (let dToken of this.lToken) {
s += '#${dToken["i"]}\t${dToken["nStart"]}:{$dToken["nEnd"]}\t${dToken["sValue"]}\t${dToken["sType"]}';
if (dToken.hasOwnProperty("lMorph")) {
s += "\t" + dToken["lMorph"].toString();
}
if (dToken.hasOwnProperty("tags")) {
s += "\t" + dToken["tags"].toString();
}
s += "\n";
}
return s;
}
|
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
|
bChange = false;
}
for (let [sGraphName, sLineId] of lRuleGroup) {
if (!dOptions.has(sGraphName) || dOptions.get(sGraphName)) {
if (bDebug) {
console.log("\n>>>> GRAPH: " + sGraphName + " " + sLineId);
}
sText = this.parseGraph(gc_rules_graph.dAllGraph.get(sGraphName), sCountry, dOptions, bDebug, bContext);
}
}
}
else if (!sOption || option(sOption)) {
for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
if (!_aIgnoredRules.has(sRuleId)) {
while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
|
|
|
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
|
bChange = false;
}
for (let [sGraphName, sLineId] of lRuleGroup) {
if (!dOptions.has(sGraphName) || dOptions.get(sGraphName)) {
if (bDebug) {
console.log("\n>>>> GRAPH: " + sGraphName + " " + sLineId);
}
sText = this.parseGraph(gc_rules_graph.dAllGraph[sGraphName] , sCountry, dOptions, bDebug, bContext);
}
}
}
else if (!sOption || option(sOption)) {
for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
if (!_aIgnoredRules.has(sRuleId)) {
while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
|
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
|
if (bDebug) {
console.log("~ " + sText + " -- " + m[eAct[0]] + " # " + sLineId);
}
break;
case "=":
// disambiguation
//console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
oEvalFunc[sWhat](sText, m, dDA);
if (bDebug) {
console.log("= " + m[0] + " # " + sLineId + "\nDA: " + dDA.gl_toString());
}
break;
case ">":
// we do nothing, this test is just a condition to apply all following actions
break;
|
|
|
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
|
if (bDebug) {
console.log("~ " + sText + " -- " + m[eAct[0]] + " # " + sLineId);
}
break;
case "=":
// disambiguation
//console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
oEvalFunc[sWhat](sText, m, this.dTokenPos);
if (bDebug) {
console.log("= " + m[0] + " # " + sLineId + "\nDA: " + dDA.gl_toString());
}
break;
case ">":
// we do nothing, this test is just a condition to apply all following actions
break;
|
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
|
// grammar error
let [iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL] = eAct;
let nTokenErrorStart = (iTokenStart > 0) ? nTokenOffset + iTokenStart : nLastToken + iTokenStart;
if (this.lToken[nTokenErrorStart].hasOwnProperty("bImmune")) {
let nTokenErrorEnd = (iTokenEnd > 0) ? nTokenOffset + iTokenEnd : nLastToken + iTokenEnd;
let nErrorStart = this.nOffsetWithinParagraph + ((cStartLimit == "<") ? this.lToken[nTokenErrorStart]["nStart"] : this.lToken[nTokenErrorStart]["nEnd"]);
let nErrorEnd = this.nOffsetWithinParagraph + ((cEndLimit == ">") ? this.lToken[nTokenErrorEnd]["nEnd"] : this.lToken[nTokenErrorEnd]["nStart"]);
if (this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart, -1)) {
this.dError[nErrorStart] = this._createErrorFromTokens(sWhat, nTokenOffset, nLastToken, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, bCaseSvty, sMessage, sURL, bShowRuleId, sOption, bContext);
this.dErrorPriority[nErrorStart] = nPriority;
if (bDebug) {
console.log(" NEW_ERROR: {} {}: {}".format(sRuleId, sLineId, this.dError[nErrorStart]));
}
}
}
|
|
|
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
|
// grammar error
let [iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL] = eAct;
let nTokenErrorStart = (iTokenStart > 0) ? nTokenOffset + iTokenStart : nLastToken + iTokenStart;
if (this.lToken[nTokenErrorStart].hasOwnProperty("bImmune")) {
let nTokenErrorEnd = (iTokenEnd > 0) ? nTokenOffset + iTokenEnd : nLastToken + iTokenEnd;
let nErrorStart = this.nOffsetWithinParagraph + ((cStartLimit == "<") ? this.lToken[nTokenErrorStart]["nStart"] : this.lToken[nTokenErrorStart]["nEnd"]);
let nErrorEnd = this.nOffsetWithinParagraph + ((cEndLimit == ">") ? this.lToken[nTokenErrorEnd]["nEnd"] : this.lToken[nTokenErrorEnd]["nStart"]);
if (!this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart, -1)) {
this.dError[nErrorStart] = this._createErrorFromTokens(sWhat, nTokenOffset, nLastToken, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, bCaseSvty, sMessage, sURL, bShowRuleId, sOption, bContext);
this.dErrorPriority[nErrorStart] = nPriority;
if (bDebug) {
console.log(" NEW_ERROR: {} {}: {}".format(sRuleId, sLineId, this.dError[nErrorStart]));
}
}
}
|
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
|
}
function morph (dTokenPos, aWord, sPattern, sNegPattern, bNoWord=false) {
// analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
if (!aWord) {
return bNoWord;
}
let lMorph = (dTokenPos.has(aWord[0]) && dTokenPos.get(aWord[0])).has("lMorph") ? dTokenPos.get(aWord[0])["lMorph"] : _oSpellChecker.getMorph(aWord[1]);
if (lMorph.length === 0) {
return false;
}
if (sNegPattern) {
// check negative condition
if (sNegPattern === "*") {
// all morph must match sPattern
|
|
|
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
|
}
function morph (dTokenPos, aWord, sPattern, sNegPattern, bNoWord=false) {
// analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
if (!aWord) {
return bNoWord;
}
let lMorph = (dTokenPos.has(aWord[0]) && dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : _oSpellChecker.getMorph(aWord[1]);
if (lMorph.length === 0) {
return false;
}
if (sNegPattern) {
// check negative condition
if (sNegPattern === "*") {
// all morph must match sPattern
|