Grammalecte  Check-in [8012c45f37]

                s += "\t" + str(dToken["aTags"])
            s += "\n"
        #for nPos, dToken in self.dTokenPos.items():
        #    s += "{}\t{}\n".format(nPos, dToken)
        return s

    def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False):
        "analyses sText and returns an iterable of errors"
        #sText = unicodedata.normalize("NFC", sText)
        dOpt = dOptions or _dOptions
        bShowRuleId = option('idrule')

        # parse paragraph
        try:
            self.parseText(self.sText, self.sText0, True, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext)
        except:
            raise
        # parse sentences

        sText = self._getCleanText()












        for iStart, iEnd in text.getSentenceBoundaries(sText):
            if 4 < (iEnd - iStart) < 2000:
                try:
                    self.sSentence = sText[iStart:iEnd]
                    self.sSentence0 = self.sText0[iStart:iEnd]
                    self.nOffsetWithinParagraph = iStart
                    self.lToken = list(_oTokenizer.genTokens(self.sSentence, True))
                    self.dTokenPos = { dToken["nStart"]: dToken  for dToken in self.lToken  if dToken["sType"] != "INFO" }
                    self.parseText(self.sSentence, self.sSentence0, False, iStart, sCountry, dOpt, bShowRuleId, bDebug, bContext)
                except:
                    raise
        return self.dError.values() # this is a view (iterable)

    def parseAndGetSentences (self, sCountry="${country_default}", bDebug=False):
        "analyses sText and returns a list of sentences with their tokens"
        #sText = unicodedata.normalize("NFC", sText)
        # parse paragraph
        try:
            self.parseText(self.sText, self.sText0, True, 0, sCountry, dOptions, bShowRuleId, bDebug, bContext)
        except:
            raise
        # parse sentences
        sText = self._getCleanText()
        lSentence = []
        i = 0
        for iStart, iEnd in text.getSentenceBoundaries(sText):
            try:
                self.sSentence = sText[iStart:iEnd]
                self.sSentence0 = self.sText0[iStart:iEnd]
                self.nOffsetWithinParagraph = iStart
                self.lToken = list(_oTokenizer.genTokens(self.sSentence, True))
                self.dTokenPos = { dToken["nStart"]: dToken  for dToken in self.lToken  if dToken["sType"] != "INFO" }
                i += 1
                lSentence.append({
                    "i": i,
                    "iStart": iStart,
                    "iEnd": iEnd,
                    "sSentence": self.sSentence,
                    "sSentence0": self.sSentence0,
                    "lToken": list(lToken) # this is a copy
                })
                self.parseText(self.sSentence, self.sSentence0, False, iStart, sCountry, dOptions, False, False, False)
            except:
                raise
        return lSentence

    def _getCleanText (self):
        sText = self.sText
        if " " in sText:
            sText = sText.replace(" ", ' ') # nbsp
        if " " in sText:
            sText = sText.replace(" ", ' ') # nnbsp
        if "'" in sText:
            sText = sText.replace("'", "’")
        if "‑" in sText:
            sText = sText.replace("‑", "-") # nobreakdash
        if "@@" in sText:
            sText = re.sub("@@+", "", sText)
        return sText

    def parseText (self, sText, sText0, bParagraph, nOffset, sCountry, dOptions, bShowRuleId, bDebug, bContext):
        "parse the text with rules"
        bChange = False
        for sOption, lRuleGroup in _getRules(bParagraph):
            if sOption == "@@@@":
                # graph rules

_HELP = """
    /help                       /h      show this text
    ?word1 [word2] ...                  words analysis
    !word                               suggestion
    >word                               draw path of word in the word graph
    =filter                             show all entries whose morphology fits to filter
    /lopt                       /lo     list options


    /lrules [pattern]           /lr     list rules
    /o+ option1 [option2] ...           activate grammar checking options
    /o- option1 [option2] ...           deactivate grammar checking options
    /r+ rule1 [rule2] ...               reactivate grammar checking rule
    /r- rule1 [rule2] ...               deactivate grammar checking rule
    /textformatter              /tf     switch on/off the text formatter
    /debug                      /d      switch on/off the debug mode
    /quit                       /q      exit
"""


def _getText (sInputText):
    sText = input(sInputText)
    if sText == "*":

                    sFlexPattern = sSearch[0:nCut]
                    sTagsPattern = sSearch[nCut+1:]
                else:
                    sFlexPattern = sSearch
                    sTagsPattern = ""
                for aRes in oSpellChecker.select(sFlexPattern, sTagsPattern):
                    echo("\t".join(aRes))
            elif sText.startswith("/o+ "):
                oGrammarChecker.gce.setOptions({ opt:True  for opt in sText[3:].strip().split()  if opt in oGrammarChecker.gce.getOptions() })
                echo("done")
            elif sText.startswith("/o- "):
                oGrammarChecker.gce.setOptions({ opt:False  for opt in sText[3:].strip().split()  if opt in oGrammarChecker.gce.getOptions() })
                echo("done")
            elif sText.startswith("/r- "):
                for sRule in sText[3:].strip().split():
                    oGrammarChecker.gce.ignoreRule(sRule)
                echo("done")
            elif sText.startswith("/r+ "):
                for sRule in sText[3:].strip().split():
                    oGrammarChecker.gce.reactivateRule(sRule)
                echo("done")
            elif sText in ("/debug", "/d"):
                xArgs.debug = not xArgs.debug
                echo("debug mode on"  if xArgs.debug  else "debug mode off")
            elif sText in ("/textformatter", "/tf"):