Grammalecte  Check-in [8ea89d19b5]

Overview
Comment:[core] ibdawg: suggest2 > char priority
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | spellsugg
Files: files | file ages | folders
SHA3-256: 8ea89d19b58e96a0da175eaaca177071b4fe20063f9d816c032d2b0c6026b2e7
User & Date: olr on 2017-11-07 19:56:28
Other Links: branch diff | manifest | tags
Context
2017-11-07
22:04
[core][bug] ibdawg: suggest2 > fix char priority check-in: 41d308e073 user: olr tags: core, spellsugg
19:56
[core] ibdawg: suggest2 > char priority check-in: 8ea89d19b5 user: olr tags: core, spellsugg
19:28
[core] sort first range of suggestions + code clarification check-in: d22466bd67 user: olr tags: core, spellsugg
Changes

Modified gc_core/py/ibdawg.py from [69a64ae917] to [7b0e081c93].

327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
...
344
345
346
347
348
349
350







351
352
353
354
355
356
357
        if nDeep >= oSuggResult.nDistLimit:
            sCleanNewWord = cp.cleanWord(sNewWord)
            if st.distanceSift4(oSuggResult.sCleanWord[:len(sCleanNewWord)], sCleanNewWord) > oSuggResult.nDistLimit:
                return
        if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
            #logging.info((nDeep * "  ") + "__" + sNewWord + "__")
            oSuggResult.addSugg(sNewWord, nDeep)
        for cChar, jAddr in self._getCharArcs(iAddr):
            self._suggest2(oSuggResult, nDeep+1, jAddr, sNewWord+cChar)
        return

    def _getCharArcs (self, iAddr):
        "generator: yield all chars and addresses from node at address <iAddr>"
        for nVal, jAddr in self._getArcs(iAddr):
            if nVal < self.nChar:
................................................................................
    def _getSimilarCharArcs (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for c in cp.d1to1.get(cChar, [cChar]):
            if c in self.dChar:
                jAddr = self._lookupArcNode(self.dChar[c], iAddr)
                if jAddr:
                    yield (c, jAddr)








    def _getTails (self, iAddr, sTail="", n=2):
        "return a list of suffixes ending at a distance of <n> from <iAddr>"
        aTails = set()
        for nVal, jAddr in self._getArcs(iAddr):
            if nVal < self.nChar:
                if int.from_bytes(self.byDic[jAddr:jAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:







|







 







>
>
>
>
>
>
>







327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
...
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
        if nDeep >= oSuggResult.nDistLimit:
            sCleanNewWord = cp.cleanWord(sNewWord)
            if st.distanceSift4(oSuggResult.sCleanWord[:len(sCleanNewWord)], sCleanNewWord) > oSuggResult.nDistLimit:
                return
        if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
            #logging.info((nDeep * "  ") + "__" + sNewWord + "__")
            oSuggResult.addSugg(sNewWord, nDeep)
        for cChar, jAddr in self._getCharArcsWithPriority(iAddr, oSuggResult.sWord[nDeep:nDeep+1]):
            self._suggest2(oSuggResult, nDeep+1, jAddr, sNewWord+cChar)
        return

    def _getCharArcs (self, iAddr):
        "generator: yield all chars and addresses from node at address <iAddr>"
        for nVal, jAddr in self._getArcs(iAddr):
            if nVal < self.nChar:
................................................................................
    def _getSimilarCharArcs (self, cChar, iAddr):
        "generator: yield similar char of <cChar> and address of the following node"
        for c in cp.d1to1.get(cChar, [cChar]):
            if c in self.dChar:
                jAddr = self._lookupArcNode(self.dChar[c], iAddr)
                if jAddr:
                    yield (c, jAddr)

    def _getCharArcsWithPriority (self, iAddr, cChar):
        if not cChar:
            yield from self._getCharArcs(iAddr)
        lTuple = list(self._getCharArcs(iAddr))
        lTuple.sort(key=lambda t: 0  if t[0] in cp.d1to1.get(cChar, "")  else  1)
        yield from lTuple

    def _getTails (self, iAddr, sTail="", n=2):
        "return a list of suffixes ending at a distance of <n> from <iAddr>"
        aTails = set()
        for nVal, jAddr in self._getArcs(iAddr):
            if nVal < self.nChar:
                if int.from_bytes(self.byDic[jAddr:jAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask: