988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
|
//////// 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-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-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i");
let m = z.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
return [m.index, m[1]];
}
function nextword1 (s, iStart) {
// get next word (optimization)
let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_-]*)", "ig");
let m = _zNextWord.exec(s.slice(iStart));
if (!m) {
return null;
}
return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}
const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-stᴀ-ᶿ_-]*) +$", "i");
function prevword1 (s, iEnd) {
// get previous word (optimization)
let m = _zPrevWord.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
|
|
|
|
|
|
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
|
//////// 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-ʯff-stᴀ-ᶿ%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-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-ʯff-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i");
let m = z.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
return [m.index, m[1]];
}
function nextword1 (s, iStart) {
// get next word (optimization)
let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*)", "ig");
let m = _zNextWord.exec(s.slice(iStart));
if (!m) {
return null;
}
return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}
const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*) +$", "i");
function prevword1 (s, iEnd) {
// get previous word (optimization)
let m = _zPrevWord.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
|