| 1 | // \u00a1-\u00b1\u00b4-\u00b8\u00ba\u00bb\u00bf
|
| 2 | // is latin supplement punctuation except fractions and superscript
|
| 3 | // numbers
|
| 4 | // \u2010-\u2027\u2030-\u205e
|
| 5 | // is punctuation from the general punctuation block:
|
| 6 | // weird quotes, commas, bullets, dashes, etc.
|
| 7 | // \u30fb\u3001\u3002\u3008-\u3011\u3014-\u301f
|
| 8 | // is CJK punctuation
|
| 9 | // \uff1a-\uff1f\uff01-\uff0f\uff3b-\uff40\uff5b-\uff65
|
| 10 | // is some full-width/half-width punctuation
|
| 11 | // \u2E2E\u061f\u066a-\u066c\u061b\u060c\u060d\uFD3e\uFD3F
|
| 12 | // is some Arabic punctuation marks
|
| 13 | // \u1801\u0964\u104a\u104b
|
| 14 | // is misc. other language punctuation marks
|
| 15 | declare namespace TokenizeUtil {
|
| 16 | function getPunctuation(): string;
|
| 17 | }
|
| 18 |
|
| 19 | // eslint-disable-next-line @definitelytyped/export-just-namespace
|
| 20 | export = TokenizeUtil;
|