From c117966782fe826ae0146467dacb4ad20893046e Mon Sep 17 00:00:00 2001 From: Julian Hurst Date: Fri, 21 Mar 2025 19:24:09 +0100 Subject: Add a bunch of unicode blocks to width.ha --- tests/runewidth.ha | 16 ++++++++++++++++ tests/strwidth.ha | 2 ++ tui/width.ha | 37 +++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+) diff --git a/tests/runewidth.ha b/tests/runewidth.ha index 5e570a5..820dcf0 100644 --- a/tests/runewidth.ha +++ b/tests/runewidth.ha @@ -6,4 +6,20 @@ fn runewidth() void = { assert(tui::runewidth('ๅคง') == 2); assert(tui::runewidth('ใ') == 2); assert(tui::runewidth('๐Ÿ˜€') == 2); + assert(tui::runewidth('่ฟ‘') == 2); + assert(tui::runewidth('ใ') == 2); + assert(tui::runewidth('ใฎ') == 2); + assert(tui::runewidth('ใ•') == 2); + assert(tui::runewidth('ใ‚„') == 2); + assert(tui::runewidth('ใ') == 2); + assert(tui::runewidth('๐Ÿ˜ช') == 2); + assert(tui::runewidth('ใ€Œ') == 2); + assert(tui::runewidth('ใพ') == 2); + assert(tui::runewidth('่กŒ') == 2); + assert(tui::runewidth('ใ€') == 2); + assert(tui::runewidth('ใ‚ช') == 2); + assert(tui::runewidth('ใƒŽ') == 2); + assert(tui::runewidth('ใƒž') == 2); + assert(tui::runewidth('ใƒˆ') == 2); + assert(tui::runewidth('ใƒš') == 2); }; diff --git a/tests/strwidth.ha b/tests/strwidth.ha index e3863d6..2024ca9 100644 --- a/tests/strwidth.ha +++ b/tests/strwidth.ha @@ -3,4 +3,6 @@ use tui; @test fn strwidth() void = { assert(tui::strwidth("ๅคงใ๐Ÿ˜€f") == 7); + assert(tui::strwidth("่ฟ‘ใ้ ใใฎใ•ใ•ใ‚„ใ๐Ÿ˜ชใ€Œใพ่กŒใ€ใ‚ชใƒŽใƒžใƒˆใƒš") == 38); + assert(tui::strwidth("ํž๋Ÿฌ๋ฝ€๋ชจ์จฉ็™’ใ—ใฎใƒ’ใƒผใƒฉใƒผใกใ‚ƒใ‚“") == 30); }; diff --git a/tui/width.ha b/tui/width.ha index f6d6078..cb4464a 100644 --- a/tui/width.ha +++ b/tui/width.ha @@ -1,5 +1,6 @@ use strings; +//https://unicodeplus.com/ export fn runewidth(r: rune) uint = { let ru = r: u32; // emoticons: https://en.wikipedia.org/wiki/Emoticons_(Unicode_block) @@ -18,6 +19,42 @@ export fn runewidth(r: rune) uint = { if (ru >= '\U00004E00' && ru <= '\U00009FFF') { return 2; }; + // CJK Symbols and Punctuation: https://en.wikipedia.org/wiki/CJK_Symbols_and_Punctuation + if (ru >= '\U00003000' && ru <= '\U0000303F') { + return 2; + }; + // Hangul Syllables: https://en.wikipedia.org/wiki/Hangul_Syllables + if (ru >= '\U0000AC00' && ru <= '\U0000D7AF') { + return 2; + }; + // Miscellaneous Symbols: https://en.wikipedia.org/wiki/Miscellaneous_Symbols_and_Pictographs + if (ru >= '\U00002600' && ru <= '\U000026FF') { + return 2; + }; + // Miscellaneous Symbols and Pictographs: https://en.wikipedia.org/wiki/Miscellaneous_Symbols_and_Pictographs + if (ru >= '\U0001F300' && ru <= '\U0001F5FF') { + return 2; + }; + // Dingbats: https://en.wikipedia.org/wiki/Dingbats_(Unicode_block) + if (ru >= '\U00002700' && ru <= '\U000027BF') { + return 2; + }; + // Transport and Map symbols: https://en.wikipedia.org/wiki/Transport_and_Map_Symbols + if (ru >= '\U0001F680' && ru <= '\U0001F6FF') { + return 2; + }; + // Supplemental Symbols and Pictographs: https://en.wikipedia.org/wiki/Supplemental_Symbols_and_Pictographs + if (ru >= '\U0001F900' && ru <= '\U0001F9FF') { + return 2; + }; + // Miscellaneous Symbols and Arrows: https://en.wikipedia.org/wiki/Miscellaneous_Symbols_and_Arrows + if (ru >= '\U00002B00' && ru <= '\U00002BFF') { + return 2; + }; + // Symbols and Pictographs Extended-A: https://en.wikipedia.org/wiki/Symbols_and_Pictographs_Extended-A + if (ru >= '\U0001FA70' && ru <= '\U0001FAFF') { + return 2; + }; return 1; }; -- cgit v1.2.3