Grammalecte  Check-in [18db5d65f0]

            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    getSpellChecker: function () {
        return _oSpellChecker;
    },

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {

    exports._rewrite = gc_engine._rewrite;
    exports.ignoreRule = gc_engine.ignoreRule;
    exports.resetIgnoreRules = gc_engine.resetIgnoreRules;
    exports.reactivateRule = gc_engine.reactivateRule;
    exports.listRules = gc_engine.listRules;
    exports._getRules = gc_engine._getRules;
    exports.load = gc_engine.load;
    exports.getSpellChecker = gc_engine.getSpellChecker;
    exports.setOption = gc_engine.setOption;
    exports.setOptions = gc_engine.setOptions;
    exports.getOptions = gc_engine.getOptions;
    exports.getDefaultOptions = gc_engine.getDefaultOptions;
    exports.resetOptions = gc_engine.resetOptions;
}

from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo
from . import gc_options


__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
            "load", "parse", "getSpellChecker", \
            "setOption", "setOptions", "getOptions", "getDefaultOptions", "getOptionsLabels", "resetOptions", "displayOptions", \
            "ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules" ]

__version__ = "${version}"


lang = "${lang}"

def resetOptions ():
    global _dOptions
    _dOptions = dict(gc_options.getOptions(_sAppContext))


def getSpellChecker ():
    return _oSpellChecker


def _getRules (bParagraph):
    try:
        if not bParagraph:
            return _rules.lSentenceRules

    ['<', "inférieur à"],
    ['>', "supérieur à"],
]);


class Lexicographe {

    constructor (oSpellChecker, oTokenizer, oLocGraph) {
        this.oSpellChecker = oSpellChecker;
        this.oTokenizer = oTokenizer;
        this.oLocGraph = JSON.parse(oLocGraph);

        this._zPartDemForm = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(là|ci)$", "i");
        this._aPartDemExceptList = new Set(["celui", "celle", "ceux", "celles", "de", "jusque", "par", "marie-couche-toi"]);
        this._zInterroVerb = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(t-(?:il|elle|on)|je|tu|ils?|elles?|on|[nv]ous)$", "i");
        this._zImperatifVerb = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts][’'](?:y|en)|les?|la|[mt]oi|leur|lui)$", "i");

                            sValue: oToken.sValue,
                            aLabel: ["forme verbale interrogative"],
                            aSubElem: [
                                { sType: oToken.sType, sValue: m[1],       aLabel: this._getMorph(m[1]) },
                                { sType: oToken.sType, sValue: "-" + m[2], aLabel: [this._formatSuffix(m[2].toLowerCase())] }
                            ]
                        };
                    } else if (this.oSpellChecker.isValidToken(oToken.sValue)) {
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: this._getMorph(oToken.sValue)
                        };
                    } else {
                        return {

            helpers.logerror(e);
        }
        return null;
    }

    _getMorph (sWord) {
        let aElem = [];
        for (let s of this.oSpellChecker.getMorph(sWord)) {
            if (s.includes(":")) aElem.push(this._formatTags(s));
        }
        if (aElem.length == 0) {
            aElem.push("mot inconnu du dictionnaire");
        }
        return aElem;
    }

    "t'en": " (te) pronom personnel objet + (en) pronom adverbial",
    "s'en": " (se) pronom personnel objet + (en) pronom adverbial",
}


class Lexicographe:

    def __init__ (self, oSpellChecker):
        self.oSpellChecker = oSpellChecker
        self._zElidedPrefix = re.compile("(?i)^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)")
        self._zCompoundWord = re.compile("(?i)(\\w+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$")
        self._zTag = re.compile("[:;/][\\w*][^:;/]*")

    def analyzeWord (self, sWord):
        try:
            if not sWord:

                sWord = m.group(2)
                aMorph.append( "{}’ : {}".format(m.group(1), _dPFX.get(m.group(1).lower(), "[?]")) )
            # mots composés
            m2 = self._zCompoundWord.match(sWord)
            if m2:
                sWord = m2.group(1)
            # Morphologies
            lMorph = self.oSpellChecker.getMorph(sWord)
            if len(lMorph) > 1:
                # sublist
                aMorph.append( (sWord, [ self.formatTags(s)  for s in lMorph  if ":" in s ]) )
            elif len(lMorph) == 1:
                aMorph.append( "{} : {}".format(sWord, self.formatTags(lMorph[0])) )
            else:
                aMorph.append( "{} :  inconnu du dictionnaire".format(sWord) )

    }
}



let bInitDone = false;

let oSpellChecker = null;
let oTokenizer = null;
let oLxg = null;
let oTest = null;
let oLocution = null;


/*

        if (!bInitDone) {
            //console.log("[Worker] Loading… Extension path: " + sExtensionPath);
            conj.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/conj_data.json"));
            phonet.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/phonet_data.json"));
            mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json"));
            //console.log("[Worker] Modules have been initialized…");
            gc_engine.load(sContext, sExtensionPath+"grammalecte/graphspell/_dictionaries");
            oSpellChecker = gc_engine.getSpellChecker();
            oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json");
            oTokenizer = new Tokenizer("fr");

            oLocution =  helpers.loadFile(sExtensionPath + "/grammalecte/fr/locutions_data.json");

            oLxg = new Lexicographe(oSpellChecker, oTokenizer, oLocution);
            if (dOptions !== null) {
                gc_engine.setOptions(dOptions);
            }
            //tests();
            bInitDone = true;
        } else {
            console.log("[Worker] Already initialized…")

}

function parseAndSpellcheck (sText, sCountry, bDebug, bContext, dInfo={}) {
    let i = 0;
    sText = sText.replace(/­/g, "").normalize("NFC");
    for (let sParagraph of text.getParagraph(sText)) {
        let aGrammErr = gc_engine.parse(sParagraph, sCountry, bDebug, bContext);
        let aSpellErr = oTokenizer.getSpellingErrors(sParagraph, oSpellChecker);
        postMessage(createResponse("parseAndSpellcheck", {sParagraph: sParagraph, iParaNum: i, aGrammErr: aGrammErr, aSpellErr: aSpellErr}, dInfo, false));
        i += 1;
    }
    postMessage(createResponse("parseAndSpellcheck", null, dInfo, true));
}

function parseAndSpellcheck1 (sParagraph, sCountry, bDebug, bContext, dInfo={}) {
    sParagraph = sParagraph.replace(/­/g, "").normalize("NFC");
    let aGrammErr = gc_engine.parse(sParagraph, sCountry, bDebug, bContext);
    let aSpellErr = oTokenizer.getSpellingErrors(sParagraph, oSpellChecker);
    postMessage(createResponse("parseAndSpellcheck1", {sParagraph: sParagraph, aGrammErr: aGrammErr, aSpellErr: aSpellErr}, dInfo, true));
}

function getOptions (dInfo={}) {
    postMessage(createResponse("getOptions", gc_engine.getOptions(), dInfo, true));
}

    postMessage(createResponse("fullTests", sMsg, dInfo, true));
}


// Spellchecker

function getSpellSuggestions (sWord, dInfo) {
    if (!oSpellChecker) {
        postMessage(createResponse("getSpellSuggestions", "# Error. Dictionary not loaded.", dInfo, true));
        return;
    }
    let i = 1;
    for (let aSugg of oSpellChecker.suggest(sWord)) {
        postMessage(createResponse("getSpellSuggestions", {sWord: sWord, aSugg: aSugg, iSugg: i}, dInfo, true));
        i += 1;
    }
}


// Lexicographer

function getListOfTokens (sText, dInfo={}) {
    try {

    if sys.platform == "win32":
        # Apparently, the console transforms «’» in «'».
        # So we reverse it to avoid many useless warnings.
        sText = sText.replace("'", "’")
    return sText


def _getErrors (sText, oTokenizer, oSpellChecker, bContext=False, bSpellSugg=False, bDebug=False):
    "returns a tuple: (grammar errors, spelling errors)"
    aGrammErrs = gce.parse(sText, "FR", bDebug=bDebug, bContext=bContext)
    aSpellErrs = []
    for dToken in oTokenizer.genTokens(sText):
        if dToken['sType'] == "WORD" and not oSpellChecker.isValidToken(dToken['sValue']):
            if bSpellSugg:
                dToken['aSuggestions'] = oSpellChecker.suggest(dToken['sValue'])
            aSpellErrs.append(dToken)
    return aGrammErrs, aSpellErrs


def generateText (sText, oTokenizer, oSpellChecker, bDebug=False, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100):
    aGrammErrs, aSpellErrs = _getErrors(sText, oTokenizer, oSpellChecker, False, bSpellSugg, bDebug)
    if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
        return ""
    return txt.generateParagraph(sText, aGrammErrs, aSpellErrs, nWidth)


def generateJSON (iIndex, sText, oTokenizer, oSpellChecker, bContext=False, bDebug=False, bEmptyIfNoErrors=False, bSpellSugg=False, lLineSet=None, bReturnText=False):
    aGrammErrs, aSpellErrs = _getErrors(sText, oTokenizer, oSpellChecker, bContext, bSpellSugg, bDebug)
    aGrammErrs = list(aGrammErrs)
    if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
        return ""
    if lLineSet:
        aGrammErrs, aSpellErrs = txt.convertToXY(aGrammErrs, aSpellErrs, lLineSet)
        return json.dumps({ "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
    if bReturnText:

    xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules")
    xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true")
    xArgs = xParser.parse_args()

    gce.load()
    if not xArgs.json:
        echo("Grammalecte v{}".format(gce.version))
    oSpellChecker = gce.getSpellChecker()
    oTokenizer = tkz.Tokenizer("fr")
    oLexGraphe = lxg.Lexicographe(oSpellChecker)
    if xArgs.textformatter or xArgs.textformatteronly:
        oTF = tf.TextFormatter()

    if xArgs.list_options or xArgs.list_rules:
        if xArgs.list_options:
            gce.displayOptions("fr")
        if xArgs.list_rules:
            gce.displayRules(None  if xArgs.list_rules == "*"  else xArgs.list_rules)
        exit()

    if xArgs.suggest:
        lSugg = oSpellChecker.suggest(xArgs.suggest)
        if xArgs.json:
            sText = json.dumps({ "aSuggestions": lSugg }, ensure_ascii=False)
        else:
            sText = "Suggestions : " + " | ".join(lSugg)
        echo(sText)
        exit()

            for i, sText in enumerate(readfile(sFile), 1):
                if xArgs.textformatter or xArgs.textformatteronly:
                    sText = oTF.formatText(sText)
                if xArgs.textformatteronly:
                    output(sText, hDst)
                else:
                    if xArgs.json:
                        sText = generateJSON(i, sText, oTokenizer, oSpellChecker, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter)
                    else:
                        sText = generateText(sText, oTokenizer, oSpellChecker, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
                    if sText:
                        if xArgs.json and bComma:
                            output(",\n", hDst)
                        output(sText, hDst)
                        bComma = True
                if hDst:
                    echo("§ %d\r" % i, end="", flush=True)
        else:
            # concaténation des lignes non séparées par une ligne vide
            for i, lLine in enumerate(readfileAndConcatLines(sFile), 1):
                sText, lLineSet = txt.createParagraphWithLines(lLine)
                if xArgs.json:
                    sText = generateJSON(i, sText, oTokenizer, oSpellChecker, bContext=xArgs.context, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, lLineSet=lLineSet)
                else:
                    sText = generateText(sText, oTokenizer, oSpellChecker, bDebug=False, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
                if sText:
                    if xArgs.json and bComma:
                        output(",\n", hDst)
                    output(sText, hDst)
                    bComma = True
                if hDst:
                    echo("§ %d\r" % i, end="", flush=True)
        if xArgs.json:
            output("\n]}\n", hDst)
    else:
        # pseudo-console
        sInputText = "\n~==========~ Enter your text [/h /q] ~==========~\n"
        sText = _getText(sInputText)
        while True:
            if sText.startswith("?"):
                for sWord in sText[1:].strip().split():
                    if sWord:
                        echo("* " + sWord)
                        for sMorph in oSpellChecker.getMorph(sWord):
                            echo("  {:<32} {}".format(sMorph, oLexGraphe.formatTags(sMorph)))
            elif sText.startswith("!"):
                for sWord in sText[1:].strip().split():
                    if sWord:
                        echo(" | ".join(oSpellChecker.suggest(sWord)))
                        #echo(" | ".join(oSpellChecker.suggest2(sWord)))
            elif sText.startswith(">"):
                oSpellChecker.drawPath(sText[1:].strip())
            elif sText.startswith("="):
                for sRes in oSpellChecker.select(sText[1:].strip()):
                    echo(sRes)
            elif sText.startswith("/+ "):
                gce.setOptions({ opt:True  for opt in sText[3:].strip().split()  if opt in gce.getOptions() })
                echo("done")
            elif sText.startswith("/- "):
                gce.setOptions({ opt:False  for opt in sText[3:].strip().split()  if opt in gce.getOptions() })
                echo("done")

            elif sText.startswith("/rl"):
                # reload (todo)
                pass
            else:
                for sParagraph in txt.getParagraph(sText):
                    if xArgs.textformatter:
                        sText = oTF.formatText(sText)
                    sRes = generateText(sText, oTokenizer, oSpellChecker, bDebug=xArgs.debug, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width)
                    if sRes:
                        echo("\n" + sRes)
                    else:
                        echo("\nNo error found.")
            sText = _getText(sInputText)


if __name__ == '__main__':
    main()

def genUserId ():
    i = 0
    while True:
        yield str(i)
        i += 1


def parseParagraph (iParagraph, sText, oTokenizer, oSpellChecker, dOptions, bDebug=False, bEmptyIfNoErrors=False):
    aGrammErrs = gce.parse(sText, "FR", bDebug, dOptions)
    aGrammErrs = list(aGrammErrs)
    aSpellErrs = []
    for dToken in oTokenizer.genTokens(sText):
        if dToken['sType'] == "WORD" and not oSpellChecker.isValidToken(dToken['sValue']):
            aSpellErrs.append(dToken)
    if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
        return ""
    return "  " + json.dumps({ "iParagraph": iParagraph, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
    

if __name__ == '__main__':

    gce.load("Server")
    echo("Grammalecte v{}".format(gce.version))
    dServerOptions = getServerOptions()
    dGCOptions = getConfigOptions("fr")
    if dGCOptions:
        gce.setOptions(dGCOptions)
    dServerGCOptions = gce.getOptions()
    echo("Grammar options:\n" + " | ".join([ k + ": " + str(v)  for k, v in sorted(dServerGCOptions.items()) ]))
    oSpellChecker = gce.getSpellChecker()
    oTokenizer = tkz.Tokenizer("fr")
    oTF = tf.TextFormatter()
    dUser = {}
    userGenerator = genUserId()

    app = Bottle()

                dOptions.update(json.loads(request.forms.options))
            except:
                sError = "request options not used"
        sJSON = '{ "program": "grammalecte-fr", "version": "'+gce.version+'", "lang": "'+gce.lang+'", "error": "'+sError+'", "data" : [\n'
        for i, sText in enumerate(txt.getParagraph(request.forms.text), 1):
            if bTF:
                sText = oTF.formatText(sText)
            sText = parseParagraph(i, sText, oTokenizer, oSpellChecker, dOptions, bEmptyIfNoErrors=True)
            if sText:
                if bComma:
                    sJSON += ",\n"
                sJSON += sText
                bComma = True
        sJSON += "\n]}\n"
        return sJSON

                }
            }
            i += nCut;
            sText = sText.slice(nCut);
        }
    }

    getSpellingErrors (sText, oSpellChecker) {
        let aSpellErr = [];
        for (let oToken of this.genTokens(sText)) {
            if (oToken.sType === 'WORD' && !oSpellChecker.isValidToken(oToken.sValue)) {
                aSpellErr.push(oToken);
            }
        }
        return aSpellErr;
    }
}


if (typeof(exports) !== 'undefined') {
    exports.Tokenizer = Tokenizer;
}