Overview
Comment: | [graphspell] suggestions: split word at apostrophes and check each part |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk | graphspell |
Files: | files | file ages | folders |
SHA3-256: |
622060334cf37de6c5957200183b914d |
User & Date: | olr on 2018-11-23 15:33:45 |
Other Links: | manifest | tags |
Context
2018-11-23
| ||
16:05 | [graphspell] char_player: another simplification method for sound “é” to avoid oversimplification check-in: 93a0b84b63 user: olr tags: trunk, graphspell | |
15:33 | [graphspell] suggestions: split word at apostrophes and check each part check-in: 622060334c user: olr tags: trunk, graphspell | |
15:32 | [fr] ajustements check-in: def3f4276e user: olr tags: trunk, fr | |
Changes
Modified graphspell-js/ibdawg.js from [edb211270b] to [87959bb3f3].
︙ | |||
328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 | 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 | + + + + + + + + + + + + | let sSfx = ""; [sPfx, sWord, sSfx] = char_player.cut(sWord); let nMaxSwitch = Math.max(Math.floor(sWord.length / 3), 1); let nMaxDel = Math.floor(sWord.length / 5); let nMaxHardRepl = Math.max(Math.floor((sWord.length - 5) / 4), 1); let nMaxJump = Math.max(Math.floor(sWord.length / 4), 1); let oSuggResult = new SuggResult(sWord); this._splitSuggest(oSuggResult, sWord); this._suggest(oSuggResult, sWord, nMaxSwitch, nMaxDel, nMaxHardRepl, nMaxJump); let aSugg = oSuggResult.getSuggestions(nSuggLimit); if (sSfx || sPfx) { // we add what we removed return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx; } ); } //console.timeEnd("Suggestions for " + sWord); return aSugg; } _splitSuggest (oSuggResult, sWord) { for (let cSplitter of "'’") { if (sWord.includes(cSplitter)) { let [sWord1, sWord2] = sWord.split(cSplitter, 2); if (this.isValid(sWord1) && this.isValid(sWord2)) { oSuggResult.addSugg(sWord1+" "+sWord2); } } } } _suggest (oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=false) { // returns a set of suggestions // recursive function if (sRemain == "") { if (this._convBytesToInteger(this.byDic.slice(iAddr, iAddr+this.nBytesArc)) & this._finalNodeMask) { oSuggResult.addSugg(sNewWord); |
︙ |
Modified graphspell/ibdawg.py from [59273fbe60] to [630526bab1].
︙ | |||
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 | 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | + + + + + + + + | sWord = cp.spellingNormalization(sWord) sPfx, sWord, sSfx = cp.cut(sWord) nMaxSwitch = max(len(sWord) // 3, 1) nMaxDel = len(sWord) // 5 nMaxHardRepl = max((len(sWord) - 5) // 4, 1) nMaxJump = max(len(sWord) // 4, 1) oSuggResult = SuggResult(sWord) self._splitSuggest(oSuggResult, sWord) self._suggest(oSuggResult, sWord, nMaxSwitch, nMaxDel, nMaxHardRepl, nMaxJump) aSugg = oSuggResult.getSuggestions(nSuggLimit) if sSfx or sPfx: # we add what we removed return list(map(lambda sSug: sPfx + sSug + sSfx, aSugg)) return aSugg def _splitSuggest (self, oSuggResult, sWord): for cSplitter in "'’": if cSplitter in sWord: sWord1, sWord2 = sWord.split(cSplitter, 1) if self.isValid(sWord1) and self.isValid(sWord2): oSuggResult.addSugg(sWord1+" "+sWord2) def _suggest (self, oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=False): # recursive function #logging.info((nDeep * " ") + sNewWord + ":" + sRemain) if not sRemain: if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask: oSuggResult.addSugg(sNewWord, nDeep) for sTail in self._getTails(iAddr): |
︙ |