Add 4 stage trie to lookup unicode codepoint width and grapheme join rules. Generated by GraphemeTableGen from Microsoft Terminal (MIT Licence): https://github.com/microsoft/terminal/blob/a7e47b711a2adc7b9e80eddea8168089f7d3b11e/src/tools/GraphemeTableGen/Program.cs With minor adjustment to use it in C codebase. - Replaced constexpr with static - Replaced auto with explicit types Generated from Unicode 16.0.0: ucd.nounihan.grouped.xml: sha256(b11c2d23673bae660fff8ddcd3c1de4d54bdf6c60188a07696b010282f515fcf)
Showing the changes to test/codepoint_width.c (1 of 6 files). Show all
Unified · Split
| @@ -0,0 +1,67 @@ | |||
| 1 | /* | ||
| 2 | * This file is part of mpv. | ||
| 3 | * | ||
| 4 | * mpv is free software; you can redistribute it and/or | ||
| 5 | * modify it under the terms of the GNU Lesser General Public | ||
| 6 | * License as published by the Free Software Foundation; either | ||
| 7 | * version 2.1 of the License, or (at your option) any later version. | ||
| 8 | * | ||
| 9 | * mpv is distributed in the hope that it will be useful, | ||
| 10 | * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| 11 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| 12 | * GNU Lesser General Public License for more details. | ||
| 13 | * | ||
| 14 | * You should have received a copy of the GNU Lesser General Public | ||
| 15 | * License along with mpv. If not, see <http://www.gnu.org/licenses/>. | ||
| 16 | */ | ||
| 17 | |||
| 18 | #include "test_utils.h" | ||
| 19 | |||
| 20 | #include "misc/codepoint_width.h" | ||
| 21 | |||
| 22 | #define W(s) term_disp_width((bstr)bstr0_lit(s)) | ||
| 23 | |||
| 24 | int main(void) { | ||
| 25 | assert_int_equal(W("A"), 1); // Single ASCII character | ||
| 26 | assert_int_equal(W("ABC"), 3); // Multiple ASCII characters | ||
| 27 | |||
| 28 | assert_int_equal(W("\u3042"), 2); // Full-width Japanese Hiragana 'あ' (U+3042) | ||
| 29 | assert_int_equal(W("\u4F60"), 2); // Full-width Chinese character '你' (U+4F60) | ||
| 30 | assert_int_equal(W("\u4F60\u597D"), 4); // Two full-width Chinese characters '你好' (U+4F60 U+597D) | ||
| 31 | |||
| 32 | assert_int_equal(W("a\u0301"), 1); // 'a' + combining acute accent '́' (U+0301) | ||
| 33 | assert_int_equal(W("e\u0301"), 1); // 'e' + combining acute accent '́' (U+0301) | ||
| 34 | assert_int_equal(W("a\u0308"), 1); // 'a' + combining diaeresis '̈' (U+0308) | ||
| 35 | |||
| 36 | // Family emoji: 👩❤️👩 (Woman + ZWJ + Heart + ZWJ + Woman; | ||
| 37 | // Code points: U+1F469 U+200D U+2764 U+FE0F U+200D U+1F469) | ||
| 38 | assert_int_equal(W("\U0001F469\u200D\u2764\uFE0F\u200D\U0001F469"), 2); | ||
| 39 | // Man emoji with skin tone modifier | ||
| 40 | assert_int_equal(W("\U0001F468\U0001F3FE"), 2); | ||
| 41 | // Person Shrugging + skin tone modifier + ZWJ + woman sign + variant selector | ||
| 42 | assert_int_equal(W("\U0001F937\U0001F3FE\u200D\U00002640\U0000FE0F"), 2); | ||
| 43 | // Regional indicator symbols forming the flag of Poland | ||
| 44 | assert_int_equal(W("\U0001F1F5\U0001F1F1"), 2); | ||
| 45 | |||
| 46 | assert_int_equal(W("\n"), 0); // Newline (should not take up any visual space) | ||
| 47 | assert_int_equal(W("\t"), 0); // Tab (no visual width itself) | ||
| 48 | assert_int_equal(W("\0"), 0); // Null character (non-visible) | ||
| 49 | |||
| 50 | assert_int_equal(W("A\u3042"), 3); // ASCII 'A' + full-width Japanese Hiragana 'あ' (U+3042) | ||
| 51 | assert_int_equal(W("a\u0301A"), 2); // Combining character 'á' (a + U+0301) and ASCII 'A' | ||
| 52 | |||
| 53 | // Grapheme cluster + ASCII 'A' + full-width Japanese Hiragana 'あ' (U+3042) | ||
| 54 | assert_int_equal(W("\U0001F469\u200D\u2764\uFE0F\u200D\U0001F469A\u3042"), 5); | ||
| 55 | |||
| 56 | assert_int_equal(W("A\nB"), 2); // ASCII characters with newline (newline should not affect width) | ||
| 57 | assert_int_equal(W("ABC\tDEF"), 6); // Tab inside a string (no visual width for '\t') | ||
| 58 | |||
| 59 | // ASCII characters with color | ||
| 60 | assert_int_equal(W("\033[31mABC\033[0m\033[32mDEF\033[0m"), 6); | ||
| 61 | |||
| 62 | // ASCII characters with color and a newline | ||
| 63 | assert_int_equal(W("\033[31mABC\033[0m\033[32mDEF\033[0m\n"), 6); | ||
| 64 | |||
| 65 | // ASCII characters with carriage return | ||
| 66 | assert_int_equal(W("ABC\rDEF"), 3); | ||
| 67 | } | ||