Grammalecte  Diff

        aEntry = set()
        lChar = ['']; dChar = {}; nChar = 1; dCharOccur = {}
        lAff  = [];   dAff  = {}; nAff  = 0; dAffOccur = {}
        lTag  = [];   dTag  = {}; nTag  = 0; dTagOccur = {}
        nErr = 0

        self.a2grams = set()

        try:
            zFilter = re.compile(sSelectFilterRegex)  if sSelectFilterRegex  else None
        except:
            print(" # Error. Wrong filter regex. Filter ignored.")
            traceback.print_exc()
            zFilter = None

        # read lexicon
        if type(src) is str:
            iterable = readFile(src)
        else:
            iterable = src
        for sFlex, sStem, sTag in iterable:
            if not zFilter or zFilter.search(sTag):
                self.a2grams.update(st.getNgrams(sFlex))
                addWordToCharDict(sFlex)
                # chars
                for c in sFlex:
                    if c not in dChar:
                        dChar[c] = nChar
                        lChar.append(c)
                        nChar += 1

        print(" * {:<12} {:>16,}".format("Entries:", self.nEntry))
        print(" * {:<12} {:>16,}".format("Characters:", self.nChar))
        print(" * {:<12} {:>16,}".format("Affixes:", self.nAff))
        print(" * {:<12} {:>16,}".format("Tags:", self.nTag))
        print(" * {:<12} {:>16,}".format("Arc values:", self.nArcVal))
        print(" * {:<12} {:>16,}".format("Nodes:", self.nNode))
        print(" * {:<12} {:>16,}".format("Arcs:", self.nArc))
        print(" * {:<12} {:>16,}".format("2grams:", len(self.a2grams)))
        print(" * {:<12} {:>16}".format("Stemming:", self.cStemming + "FX"))

    def getArcStats (self):
        "return a string with statistics about nodes and arcs"
        d = {}
        for oNode in self.lMinimizedNodes:
            n = len(oNode.arcs)

            "nCompressionMethod": nCompressionMethod,
            "nBytesArc": self.nBytesArc,
            "nBytesNodeAddress": self.nBytesNodeAddress,
            "nBytesOffset": self.nBytesOffset,
            # Mozilla’s JS parser don’t like file bigger than 4 Mb!
            # So, if necessary, we use an hexadecimal string, that we will convert later in Firefox’s extension.
            # https://github.com/mozilla/addons-linter/issues/1361
            "sByDic": byDic.hex()  if bBinaryDictAsHexString  else [ e  for e in byDic ],
            "l2grams": list(self.a2grams)
        }

    def writeAsJSObject (self, spfDst, nCompressionMethod, bInJSModule=False, bBinaryDictAsHexString=True):
        "write a file (JSON or JS module) with all the necessary data"
        if not spfDst.endswith(".json"):
            spfDst += "."+str(nCompressionMethod)+".json"
        with open(spfDst, "w", encoding="utf-8", newline="\n") as hDst:

        - Section Values:
                * a list of strings encoded in binary from utf-8, each value separated with a tabulation

        - Section Word Graph (nodes / arcs)
                * A list of nodes which are a list of arcs with an address of the next node.
                  See DawgNode.convToBytes() for details.

        - Section 2grams:
                * A list of 2grams (as strings: 2 chars) encoded in binary from utf-8, each value separated with a tabulation
        """
        self._calculateBinary(nCompressionMethod)
        if not sPathFile.endswith(".bdic"):
            sPathFile += "."+str(nCompressionMethod)+".bdic"
        with open(sPathFile, 'wb') as hDst:
            # header
            hDst.write("/grammalecte-fsa/{}/".format(nCompressionMethod).encode("utf-8"))
            hDst.write(b"\0\0\0\0")
            # infos
            sInfo = "{}//{}//{}//{}//{}//{}//{}//{}//{}//{}//{}//{}//".format(self.sLangCode, self.sLangName, self.sDicName, self._getDate(), \
                                                                              self.nChar, self.nBytesArc, self.nBytesNodeAddress, \
                                                                              self.nEntry, self.nNode, self.nArc, self.nAff, self.cStemming)
            hDst.write(sInfo.encode("utf-8"))
            hDst.write(b"\0\0\0\0")
            # lArcVal
            hDst.write("\t".join(self.lArcVal).encode("utf-8"))
            hDst.write(b"\0\0\0\0")
            # 2grams
            hDst.write("\t".join(self.a2grams).encode("utf-8"))
            hDst.write(b"\0\0\0\0")
            # DAWG: nodes / arcs
            if nCompressionMethod == 1:
                hDst.write(self.oRoot.convToBytes1(self.nBytesArc, self.nBytesNodeAddress))
                for oNode in self.lMinimizedNodes:
                    hDst.write(oNode.convToBytes1(self.nBytesArc, self.nBytesNodeAddress))
            elif nCompressionMethod == 2:
                hDst.write(self.oRoot.convToBytes2(self.nBytesArc, self.nBytesNodeAddress))