Grammalecte  Check-in [f1c63ee223]

    def countWordsOccurrences (self, sText, bByLemma=False, bOnlyUnknownWords=False, dWord={}):
        """count word occurrences.
           <dWord> can be used to cumulate count from several texts."""
        if not self.oTokenizer:
            self._loadTokenizer()
        for dToken in self.oTokenizer.genTokens(sText):
            if dToken['sType'] == "WORD":
            if dToken['sType'].startswith("WORD"):
                if bOnlyUnknownWords:
                    if not self.isValidToken(dToken['sValue']):
                        dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
                else:
                    if not bByLemma:
                        dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
                    else: