Grammalecte  Diff

// Grammar checker engine

"use strict";

${string}
${regex}
${map}


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");

    var gc_options = require("resource://grammalecte/${lang}/gc_options.js");
    var gc_rules = require("resource://grammalecte/${lang}/gc_rules.js");
    var cregex = require("resource://grammalecte/${lang}/cregex.js");
    var text = require("resource://grammalecte/text.js");
}

            sText = sText.replace(/‑/g, "-"); // nobreakdash
        }

        // parse sentence
        for (let [iStart, iEnd] of this._getSentenceBoundaries(sText)) {
            if (4 < (iEnd - iStart) < 2000) {
                dDA.clear();
                //helpers.echo(sText.slice(iStart, iEnd));
                try {
                    [, errs] = this._proofread(sText.slice(iStart, iEnd), sAlt.slice(iStart, iEnd), iStart, false, dDA, dPriority, sCountry, bDebug, bContext);
                    dErrors.gl_update(errs);
                }
                catch (e) {
                    helpers.logerror(e);
                }
            }
        }
        return Array.from(dErrors.values());
    },

    _zEndOfSentence: new RegExp ('([.?!:;…][ .?!… »”")]*|.$)', "g"),
    _zBeginOfParagraph: new RegExp ("^[-  –—.,;?!…]*", "ig"),
    _zEndOfParagraph: new RegExp ("[-  .,;?!…–—]*$", "ig"),

    _getSentenceBoundaries: function* (sText) {
        let mBeginOfSentence = this._zBeginOfParagraph.exec(sText);
        let iStart = this._zBeginOfParagraph.lastIndex;
        let m;
        while ((m = this._zEndOfSentence.exec(sText)) !== null) {
            yield [iStart, this._zEndOfSentence.lastIndex];
            iStart = this._zEndOfSentence.lastIndex;
        }
    },

        for (let [sOption, lRuleGroup] of this._getRules(bParagraph)) {
            if (!sOption || option(sOption)) {
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!_aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(s, lGroups, lNegLookBefore)) !== null) {
                            bCondMemo = null;
                            /*if (bDebug) {
                                helpers.echo(">>>> Rule # " + sLineId + " - Text: " + s + " opt: "+ sOption);
                            }*/
                            for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
                            // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try {
                                    //helpers.echo(oEvalFunc[sFuncCond]);
                                    bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo));
                                    if (bCondMemo) {
                                        switch (cActionType) {
                                            case "-":
                                                // grammar error
                                                //helpers.echo("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
                                                nErrorStart = nOffset + m.start[eAct[0]];
                                                if (!dErrs.has(nErrorStart) || nPriority > dPriority.get(nErrorStart)) {
                                                    dErrs.set(nErrorStart, this._createError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bIdRule, sOption, bContext));
                                                    dPriority.set(nErrorStart, nPriority);
                                                }
                                                break;
                                            case "~":
                                                // text processor
                                                //helpers.echo("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source);
                                                s = this._rewrite(s, sWhat, eAct[0], m, bUppercase);
                                                bChange = true;
                                                if (bDebug) {
                                                    helpers.echo("~ " + s + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                                }
                                                break;
                                            case "=":
                                                // disambiguation
                                                //helpers.echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
                                                oEvalFunc[sWhat](s, m, dDA);
                                                if (bDebug) {
                                                    helpers.echo("= " + m[0] + "  # " + sLineId + "\nDA: " + dDA.gl_toString());
                                                }
                                                break;
                                            case ">":
                                                // we do nothing, this test is just a condition to apply all following actions
                                                break;
                                            default:
                                                helpers.echo("# error: unknown action at " + sLineId);
                                        }
                                    } else {
                                        if (cActionType == ">") {
                                            break;
                                        }
                                    }
                                }
                                catch (e) {
                                    helpers.echo(s);
                                    helpers.echo("# line id: " + sLineId + "\n# rule id: " + sRuleId);
                                    helpers.logerror(e);
                                }
                            }
                        }
                    }
                }
            }

            } else {
                oErr["aSuggestions"] = sRepl.gl_expand(m).split("|");
            }
        }
        // Message
        let sMessage = "";
        if (sMsg.slice(0,1) === "=") {
            sMessage = oEvalFunc[sMsg.slice(1)](s, m);
        } else {
            sMessage = sMsg.gl_expand(m);
        }
        if (bIdRule) {
            sMessage += " ##" + sLineId + " #" + sRuleId;
        }
        oErr["sMessage"] = sMessage;

            if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) {
                sNew = sNew.gl_toCapitalize();
            }
        } else {
            sNew = sRepl.gl_expand(m);
            sNew = sNew + " ".repeat(ln-sNew.length);
        }
        //helpers.echo("\n"+s+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup])
        return s.slice(0, m.start[iGroup]) + sNew + s.slice(m.end[iGroup]);
    },

    // Actions on rules

    ignoreRule: function (sRuleId) {
        _aIgnoredRules.add(sRuleId);

    getDefaultOptions: function () {
        return gc_options.getOptions(_sAppContext).gl_shallowCopy();
    },

    resetOptions: function () {
        _dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy();
    }
};


//////// Common functions

function option (sOpt) {
    // return true if option sOpt is active
    return _dOptions.get(sOpt);
}

function displayInfo (dDA, aWord) {
    // for debugging: info of word
    if (!aWord) {
        helpers.echo("> nothing to find");
        return true;
    }
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        helpers.echo("> not in FSA");
        return true;
    }
    if (dDA.has(aWord[0])) {
        helpers.echo("DA: " + dDA.get(aWord[0]));
    }
    helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
    return true;
}

function _storeMorphFromFSA (sWord) {
    // retrieves morphologies list from _oDict -> _dAnalyses
    //helpers.echo("register: "+sWord + " " + _oDict.getMorph(sWord).toString())
    _dAnalyses.set(sWord, _oDict.getMorph(sWord));
    return !!_dAnalyses.get(sWord);
}

function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
    // analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
    if (!aWord) {
        //helpers.echo("morph: noword, returns " + bNoWord);
        return bNoWord;
    }
    //helpers.echo("aWord: "+aWord.toString());
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        return false;
    }
    let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]);
    //helpers.echo("lMorph: "+lMorph.toString());
    if (lMorph.length === 0) {
        return false;
    }
    //helpers.echo("***");
    if (bStrict) {
        return lMorph.every(s  =>  (s.search(sPattern) !== -1));
    }
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

function morphex (dDA, aWord, sPattern, sNegPattern, bNoWord=false) {
    // analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
    if (!aWord) {
        //helpers.echo("morph: noword, returns " + bNoWord);
        return bNoWord;
    }
    //helpers.echo("aWord: "+aWord.toString());
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        return false;
    }
    let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]);
    //helpers.echo("lMorph: "+lMorph.toString());
    if (lMorph.length === 0) {
        return false;
    }
    //helpers.echo("***");
    // check negative condition
    if (lMorph.some(s  =>  (s.search(sNegPattern) !== -1))) {
        return false;
    }
    // search sPattern
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

    // returns a list of sWord's stems
    if (!sWord) {
        return [];
    }
    if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
        return [];
    }
    return _dAnalyses.get(sWord).map( s => s.slice(1, s.indexOf(" ")) );
}


//// functions to get text outside pattern scope

// warning: check compile_rules.py to understand how it works

    return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}

const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*) +$", "i");

function prevword1 (s, iEnd) {
    // get previous word (optimization)
    //helpers.echo("prev1, s:"+s);
    //helpers.echo("prev1, s.slice(0, iEnd):"+s.slice(0, iEnd));
    let m = _zPrevWord.exec(s.slice(0, iEnd));
    //helpers.echo("prev1, m:"+m);
    if (!m) {
        return null;
    }
    //helpers.echo("prev1: " + m.index + " " + m[1]);
    return [m.index, m[1]];
}

function look (s, zPattern, zNegPattern=null) {
    // seek zPattern in s (before/after/fulltext), if antipattern zNegPattern not in s
    try {
        if (zNegPattern && zNegPattern.test(s)) {

    }
    if (dDA.has(nPos)) {
        return true;
    }
    if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
        return true;
    }
    //helpers.echo("morph: "+_dAnalyses.get(sWord).toString());
    if (_dAnalyses.get(sWord).length === 1) {
        return true;
    }
    let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) === -1 );
    //helpers.echo("lSelect: "+lSelect.toString());
    if (lSelect.length > 0) {
        if (lSelect.length != _dAnalyses.get(sWord).length) {
            dDA.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dDA.set(nPos, lDefaul);
    }

    }
    if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
        return true;
    }
    if (_dAnalyses.get(sWord).length === 1) {
        return true;
    }
    let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) === -1 );
    //helpers.echo("lSelect: "+lSelect.toString());
    if (lSelect.length > 0) {
        if (lSelect.length != _dAnalyses.get(sWord).length) {
            dDA.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dDA.set(nPos, lDefault);
    }