Grammalecte  Check-in [1173853ba9]

//////// functions to get text outside pattern scope

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

function nextword (s, iStart, n) {
    // get the nth word of the input string or empty string
    let z = new RegExp("^(?: +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+)", "ig");
    let z = new RegExp("^(?: +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ%_-]+)", "ig");
    let m = z.exec(s.slice(iStart));
    if (!m) {
        return null;
    }
    return [iStart + z.lastIndex - m[1].length, m[1]];
}

function prevword (s, iEnd, n) {
    // get the (-)nth word of the input string or empty string
    let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+ +){" + (n-1).toString() + "}$", "i");
    let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i");
    let m = z.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }
    return [m.index, m[1]];
}

function nextword1 (s, iStart) {
    // get next word (optimization)
    let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*)", "ig");
    let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_-]*)", "ig");
    let m = _zNextWord.exec(s.slice(iStart));
    if (!m) {
        return null;
    }
    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_-]*) +$", "i");
const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_-]*) +$", "i");

function prevword1 (s, iEnd) {
    // get previous word (optimization)
    let m = _zPrevWord.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }

    }
    catch (e) {
        console.error(e);
    }
    return false;
}

function look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1="") {
    // returns True if s has pattern sPattern and m.group(1) has pattern sPatternGroup1
    let zPattern = createRegExp(sPattern);
    let m = zPattern.gl_exec2(s, null);
    if (!m) {
        return false;
    }
    try {
        let sWord = m[1];
        let nPos = m.start[1] + nOffset;
        return morph(dTokenPos, [nPos, sWord], sPatternGroup1, sNegPatternGroup1);
    }
    catch (e) {
        console.error(e);
        return false;
    }
}


//////// Analyse groups for regex rules

function displayInfo (dTokenPos, aWord) {
    // for debugging: info of word
    if (!aWord) {
        console.log("> nothing to find");