Grammalecte  Diff

        self.aSugg.clear()
        self.dSugg.clear()


class IBDAWG:
    """INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH"""

    def __init__ (self, sfDict):
        self.by = pkgutil.get_data(__package__, "_dictionaries/" + sfDict)
        if not self.by:
            raise OSError("# Error. File not found or not loadable: "+sfDict)
    def __init__ (self, source):
        if type(source) is str:
            self.by = pkgutil.get_data(__package__, "_dictionaries/" + source)
            if not self.by:
                raise OSError("# Error. File not found or not loadable: "+source)

        if sfDict.endswith(".bdic"):
            self._initBinary()
        elif sfDict.endswith(".json"):
            self._initJSON()
        else:
            raise OSError("# Error. Unknown file type: "+sfDict)
            if source.endswith(".bdic"):
                self._initBinary()
            elif source.endswith(".json"):
                self._initJSON(json.loads(self.by.decode("utf-8")))     #json.loads(self.by)    # In Python 3.6, can read directly binary strings
            else:
                raise OSError("# Error. Unknown file type: "+source)
        else:
            self._initJSON(source)

        self.sFileName = sfDict
        self.sFileName = source  if type(source) is str  else "[None]"

        self._arcMask = (2 ** ((self.nBytesArc * 8) - 3)) - 1
        self._finalNodeMask = 1 << ((self.nBytesArc * 8) - 1)
        self._lastArcMask = 1 << ((self.nBytesArc * 8) - 2)
        self._addrBitMask = 1 << ((self.nBytesArc * 8) - 3)  # version 2

        # function to decode the affix/suffix code

        # <dChar> to get the value of an arc, <dCharVal> to get the char of an arc with its value
        self.dChar = {}
        for i in range(1, self.nChar+1):
            self.dChar[self.lArcVal[i]] = i
        self.dCharVal = { v: k  for k, v in self.dChar.items() }
        self.nBytesOffset = 1 # version 3

    def _initJSON (self):
    def _initJSON (self, oJSON):
        "initialize with a JSON text file"
        self.__dict__.update(json.loads(self.by.decode("utf-8")))
        self.__dict__.update(oJSON)
        #self.__dict__.update(json.loads(self.by))                  # In Python 3.6, can read directly binary strings
        self.byDic = binascii.unhexlify(self.sByDic)
        self.dCharVal = { v: k  for k, v in self.dChar.items() }

    def getInfo (self):
        return  "  Language: {0.sLangName}   Lang code: {0.sLangCode}   Dictionary name: {0.sDicName}" \
                "  Compression method: {0.nCompressionMethod:>2}   Date: {0.sDate}   Stemming: {0.cStemming}FX\n" \
                "  Arcs values:  {0.nArcVal:>10,} = {0.nChar:>5,} characters,  {0.nAff:>6,} affixes,  {0.nTag:>6,} tags\n" \
                "  Dictionary: {0.nEntry:>12,} entries,    {0.nNode:>11,} nodes,   {0.nArc:>11,} arcs\n" \
                "  Address size: {0.nBytesNodeAddress:>1} bytes,  Arc size: {0.nBytesArc:>1} bytes\n".format(self)

            n += 1
        if not sWord:
            return
        if iPos >= 0:
            print("\n   "+ " " * iPos + "|")
            self.drawPath(sWord[1:], iNextNodeAddr)

    def getSimilarEntries (self, sWord, nSuggLimit=10):
        "return a list of tuples (similar word, stem, morphology)"
        if not sWord:
            return []
        lResult = []
        for sSimilar in self.suggest(sWord, nSuggLimit):
            for sMorph in self.getMorph(sSimilar):
                nCut = sMorph.find(" ")
                lResult.append( (sSimilar, sMorph[1:nCut], sMorph[nCut+1:]) )
        return lResult

    def select (self, sPattern=""):
        "generator: returns all entries which morphology fits <sPattern>"
        zPattern = None
        if sPattern:
            try:
                zPattern = re.compile(sPattern)
            except:
                print("# Error in regex pattern")
                traceback.print_exc()
        yield from self._select1(zPattern, 0, "")
    def select (self, sFlexPattern="", sTagsPattern=""):
        "generator: returns all entries which flexion fits <sFlexPattern> and morphology fits <sTagsPattern>"
        zFlexPattern = None
        zTagsPattern = None
        try:
            if sFlexPattern:
                zFlexPattern = re.compile(sFlexPattern)
            if sTagsPattern:
                zTagsPattern = re.compile(sTagsPattern)
        except:
            print("# Error in regex pattern")
            traceback.print_exc()
        yield from self._select1(zFlexPattern, zTagsPattern, 0, "")

    # def morph (self, sWord):
    #     is defined in __init__

    # VERSION 1
    def _select1 (self, zPattern, iAddr, sWord):
    def _select1 (self, zFlexPattern, zTagsPattern, iAddr, sWord):
        # recursive generator
        for nVal, jAddr in self._getArcs1(iAddr):
            if nVal <= self.nChar:
                # simple character
                yield from self._select1(zPattern, jAddr, sWord + self.lArcVal[nVal])
                yield from self._select1(zFlexPattern, zTagsPattern, jAddr, sWord + self.lArcVal[nVal])
            else:
                if not zFlexPattern or zFlexPattern.search(sWord):
                sEntry = sWord + "\t" + self.funcStemming(sWord, self.lArcVal[nVal])
                for nMorphVal, _ in self._getArcs1(jAddr):
                    if not zPattern or zPattern.search(self.lArcVal[nMorphVal]):
                        yield sEntry + "\t" + self.lArcVal[nMorphVal]
                    sStem = self.funcStemming(sWord, self.lArcVal[nVal])
                    for nMorphVal, _ in self._getArcs1(jAddr):
                        if not zTagsPattern or zTagsPattern.search(self.lArcVal[nMorphVal]):
                            yield [sWord, sStem, self.lArcVal[nMorphVal]]

    def _morph1 (self, sWord):
        "returns morphologies of <sWord>"
        iAddr = 0
        for c in sWord:
            if c not in self.dChar:
                return []