mirror of
https://github.com/keymanapp/keyman.git
synced 2026-09-19 22:27:39 +00:00
change(developer/compilers): regexp detects whether SEA character exists anywhere
This commit is contained in:
parent
075b61b4f5
commit
59870ef2f7
2 changed files with 12 additions and 10 deletions
|
|
@ -63,7 +63,7 @@ console.log(`/**
|
|||
* AUTOMATICALLY GENERATED FILE. DO NOT MODIFY
|
||||
* See: libexec/create-override-script-regexp.ts for details!
|
||||
*/
|
||||
export const SOUTHEAST_ASIAN_LETTER = /^[${characterClasses}]$/;
|
||||
export const HAS_SOUTHEAST_ASIAN_LETTER = /[${characterClasses}]/;
|
||||
`);
|
||||
|
||||
////////////////////////////////// Helpers ///////////////////////////////////
|
||||
|
|
|
|||
|
|
@ -6,13 +6,15 @@ export function decorateWithScriptOverrides(breaker: WordBreakingFunction, optio
|
|||
}
|
||||
|
||||
/**
|
||||
* Matches a string that contains only characters that are letters or according
|
||||
* to Unicode. (e.g., their General Category is Lu, Ll, Lt, Lm, Lo, Mn, Mc, or Me).
|
||||
* Matches if when a span contains a Southeast-Asian letter or mark anywhere.
|
||||
* This makes it a candidate for joining.
|
||||
*
|
||||
* Last updated for unidata 12.1.0.
|
||||
* See: libexec/create-override-script-regexp.ts for how this RegExp was
|
||||
* generated.
|
||||
*
|
||||
* Last updated for Unicode 13.0.0.
|
||||
*/
|
||||
const LETTER_OR_MARK = /^[\u0041-\u005A\u0061-\u007A\u00AA\u00B5\u00BA\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0300-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u0483-\u052F\u0531-\u0556\u0559\u0560-\u0588\u0591-\u05BD\u05BF\u05C1\u05C2\u05C4\u05C5\u05C7\u05D0-\u05EA\u05EF-\u05F2\u0610-\u061A\u0620-\u065F\u066E-\u06D3\u06D5-\u06DC\u06DF-\u06E8\u06EA-\u06EF\u06FA-\u06FC\u06FF\u0710-\u074A\u074D-\u07B1\u07CA-\u07F5\u07FA\u07FD\u0800-\u082D\u0840-\u085B\u0860-\u086A\u08A0-\u08B4\u08B6-\u08BD\u08D3-\u08E1\u08E3-\u0963\u0971-\u0983\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7\u09C8\u09CB-\u09CE\u09D7\u09DC\u09DD\u09DF-\u09E3\u09F0\u09F1\u09FC\u09FE\u0A01-\u0A03\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A3C\u0A3E-\u0A42\u0A47\u0A48\u0A4B-\u0A4D\u0A51\u0A59-\u0A5C\u0A5E\u0A70-\u0A75\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0-\u0AE3\u0AF9-\u0AFF\u0B01-\u0B03\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3C-\u0B44\u0B47\u0B48\u0B4B-\u0B4D\u0B56\u0B57\u0B5C\u0B5D\u0B5F-\u0B63\u0B71\u0B82\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD0\u0BD7\u0C00-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C39\u0C3D-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55\u0C56\u0C58-\u0C5A\u0C60-\u0C63\u0C80-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5\u0CD6\u0CDE\u0CE0-\u0CE3\u0CF1\u0CF2\u0D00-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D44\u0D46-\u0D48\u0D4A-\u0D4E\u0D54-\u0D57\u0D5F-\u0D63\u0D7A-\u0D7F\u0D82\u0D83\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0DCA\u0DCF-\u0DD4\u0DD6\u0DD8-\u0DDF\u0DF2\u0DF3\u0E01-\u0E3A\u0E40-\u0E4E\u0E81\u0E82\u0E84\u0E86-\u0E8A\u0E8C-\u0EA3\u0EA5\u0EA7-\u0EBD\u0EC0-\u0EC4\u0EC6\u0EC8-\u0ECD\u0EDC-\u0EDF\u0F00\u0F18\u0F19\u0F35\u0F37\u0F39\u0F3E-\u0F47\u0F49-\u0F6C\u0F71-\u0F84\u0F86-\u0F97\u0F99-\u0FBC\u0FC6\u1000-\u103F\u1050-\u108F\u109A-\u109D\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u135D-\u135F\u1380-\u138F\u13A0-\u13F5\u13F8-\u13FD\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16F1-\u16F8\u1700-\u170C\u170E-\u1714\u1720-\u1734\u1740-\u1753\u1760-\u176C\u176E-\u1770\u1772\u1773\u1780-\u17D3\u17D7\u17DC\u17DD\u180B-\u180D\u1820-\u1878\u1880-\u18AA\u18B0-\u18F5\u1900-\u191E\u1920-\u192B\u1930-\u193B\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A1B\u1A20-\u1A5E\u1A60-\u1A7C\u1A7F\u1AA7\u1AB0-\u1ABE\u1B00-\u1B4B\u1B6B-\u1B73\u1B80-\u1BAF\u1BBA-\u1BF3\u1C00-\u1C37\u1C4D-\u1C4F\u1C5A-\u1C7D\u1C80-\u1C88\u1C90-\u1CBA\u1CBD-\u1CBF\u1CD0-\u1CD2\u1CD4-\u1CFA\u1D00-\u1DF9\u1DFB-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u20D0-\u20F0\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D7F-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2DE0-\u2DFF\u2E2F\u3005\u3006\u302A-\u302F\u3031-\u3035\u303B\u303C\u3041-\u3096\u3099\u309A\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312F\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FEF\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA672\uA674-\uA67D\uA67F-\uA6E5\uA6F0\uA6F1\uA717-\uA71F\uA722-\uA788\uA78B-\uA7BF\uA7C2-\uA7C6\uA7F7-\uA827\uA840-\uA873\uA880-\uA8C5\uA8E0-\uA8F7\uA8FB\uA8FD-\uA8FF\uA90A-\uA92D\uA930-\uA953\uA960-\uA97C\uA980-\uA9C0\uA9CF\uA9E0-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA36\uAA40-\uAA4D\uAA60-\uAA76\uAA7A-\uAAC2\uAADB-\uAADD\uAAE0-\uAAEF\uAAF2-\uAAF6\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB67\uAB70-\uABEA\uABEC\uABED\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE00-\uFE0F\uFE20-\uFE2F\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7]+$/;
|
||||
|
||||
const HAS_SOUTHEAST_ASIAN_LETTER = /[\u0E01-\u0E3A\u0E40-\u0E4E\u0E81\u0E82\u0E84\u0E86-\u0E8A\u0E8C-\u0EA3\u0EA5\u0EA7-\u0EBD\u0EC0-\u0EC4\u0EC6\u0EC8-\u0ECD\u0EDC-\u0EDF\u1000-\u103F\u1050-\u108F\u109A-\u109D\u1780-\u17D3\u17D7\u17DC\u17DD\u30A1-\u30FA\u30FC-\u30FF]/
|
||||
|
||||
return function enhancedBreaker(phrase: string): Span[] {
|
||||
let originalSpans = breaker(phrase);
|
||||
|
|
@ -26,8 +28,8 @@ export function decorateWithScriptOverrides(breaker: WordBreakingFunction, optio
|
|||
let previousSpan = lastFrom(outputSpans);
|
||||
|
||||
if (spansAreBackToBack(previousSpan, currentSpan) &&
|
||||
spanContainsOnlyLetters(previousSpan) &&
|
||||
spanContainsOnlyLetters(currentSpan)
|
||||
hasSouthEastAsianLetter(previousSpan) &&
|
||||
hasSouthEastAsianLetter(currentSpan)
|
||||
) {
|
||||
// previous span SHOULD be joined with current!
|
||||
outputSpans[outputSpans.length - 1] = concatenateSpans(previousSpan, currentSpan);
|
||||
|
|
@ -39,8 +41,8 @@ export function decorateWithScriptOverrides(breaker: WordBreakingFunction, optio
|
|||
return outputSpans;
|
||||
}
|
||||
|
||||
function spanContainsOnlyLetters(span: Span) {
|
||||
return LETTER_OR_MARK.test(span.text);
|
||||
function hasSouthEastAsianLetter(span: Span) {
|
||||
return HAS_SOUTHEAST_ASIAN_LETTER.test(span.text);
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue