Grammalecte  Check-in [1173853ba9]

Overview
Comment:[core][js] gc engine: update \w replacements, + remove useless code
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | rg
Files: files | file ages | folders
SHA3-256: 1173853ba9bc0ffc77a6593f1a694fe67b4ddf9bb9efb8415914fc9e68532ca8
User & Date: olr on 2018-09-17 09:34:34
Other Links: branch diff | manifest | tags
Context
2018-09-17
09:58
[core][js] better debugging info check-in: 3b6904a340 user: olr tags: core, rg
09:34
[core][js] gc engine: update \w replacements, + remove useless code check-in: 1173853ba9 user: olr tags: core, rg
09:32
[build] conversion to JS update check-in: ca8457058e user: olr tags: build, rg
Changes

Modified gc_core/js/lang_core/gc_engine.js from [1fed82ec9f] to [03bccc3c17].

966
967
968
969
970
971
972
973

974
975
976
977
978
979
980
981
982
983

984
985
986
987
988
989
990
991
992
993

994
995
996
997
998
999
1000
1001

1002
1003
1004
1005
1006
1007
1008
966
967
968
969
970
971
972

973
974
975
976
977
978
979
980
981
982

983
984
985
986
987
988
989
990
991
992

993
994
995
996
997
998
999
1000

1001
1002
1003
1004
1005
1006
1007
1008







-
+









-
+









-
+







-
+








//////// 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;
    }
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1019
1020
1021
1022
1023
1024
1025


















1026
1027
1028
1029
1030
1031
1032







-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-







    }
    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");