Overview
| Comment: | [core][js][py] nextWord and previousWord: only necessary groups + bug fix for JS |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | core | webext2 |
| Files: | files | file ages | folders |
| SHA3-256: |
30b40b6153989bf9778012ef20e2a44e |
| User & Date: | olr on 2017-08-04 06:32:56 |
| Other Links: | branch diff | manifest | tags |
Context
|
2017-08-04
| ||
| 08:18 | [core][fx] gc engine in a dedicated worker check-in: 51a209f202 user: olr tags: fx, webext2 | |
| 06:32 | [core][js][py] nextWord and previousWord: only necessary groups + bug fix for JS check-in: 30b40b6153 user: olr tags: core, webext2 | |
| 05:44 | [core][js] use strict + remove useless vars + remove warnings check-in: 7aa5eaf131 user: olr tags: core, webext2 | |
Changes
Modified gc_core/js/lang_core/gc_engine.js from [bccda67b32] to [64ba38ab05].
| ︙ | ︙ | |||
473 474 475 476 477 478 479 |
//// 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
| | | | < < < > | > > | 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 |
//// 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 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() + "}$", "i");
let m = z.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
return [m.index, m[1]];
}
function nextword1 (s, iStart) {
// get next word (optimization)
let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*)", "ig");
let m = _zNextWord.exec(s.slice(iStart));
if (!m) {
return null;
}
return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}
const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*) +$", "i");
function prevword1 (s, iEnd) {
// get previous word (optimization)
//echo("prev1, s:"+s);
//echo("prev1, s.slice(0, iEnd):"+s.slice(0, iEnd));
let m = _zPrevWord.exec(s.slice(0, iEnd));
//echo("prev1, m:"+m);
|
| ︙ | ︙ |
Modified gc_core/py/lang_core/gc_engine.py from [4742310603] to [27a1e1120d].
| ︙ | ︙ | |||
470 471 472 473 474 475 476 |
## functions to get text outside pattern scope
# warning: check compile_rules.py to understand how it works
def nextword (s, iStart, n):
"get the nth word of the input string or empty string"
| | | | | 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 |
## functions to get text outside pattern scope
# warning: check compile_rules.py to understand how it works
def nextword (s, iStart, n):
"get the nth word of the input string or empty string"
m = re.match("(?: +[\\w%-]+){" + str(n-1) + "} +([\\w%-]+)", s[iStart:])
if not m:
return None
return (iStart+m.start(1), m.group(1))
def prevword (s, iEnd, n):
"get the (-)nth word of the input string or empty string"
m = re.search("([\\w%-]+) +(?:[\\w%-]+ +){" + str(n-1) + "}$", s[:iEnd])
if not m:
return None
return (m.start(1), m.group(1))
def nextword1 (s, iStart):
"get next word (optimization)"
|
| ︙ | ︙ |