From 4ce891a8ce5336da39180964792110e131756cdd Mon Sep 17 00:00:00 2001
From: Jose Colon Rodriguez
Date: Wed, 27 Mar 2024 21:52:02 -0400
Subject: ScriptsData and made all Datas const

---
 src/ScriptsData.zig | 226 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 226 insertions(+)
 create mode 100644 src/ScriptsData.zig

(limited to 'src/ScriptsData.zig')

diff --git a/src/ScriptsData.zig b/src/ScriptsData.zig
new file mode 100644
index 0000000..ac1c46a
--- /dev/null
+++ b/src/ScriptsData.zig
@@ -0,0 +1,226 @@
+const std = @import("std");
+const builtin = @import("builtin");
+const compress = std.compress;
+const mem = std.mem;
+const testing = std.testing;
+
+/// Script
+pub const Script = enum {
+    none,
+    Adlam,
+    Ahom,
+    Anatolian_Hieroglyphs,
+    Arabic,
+    Armenian,
+    Avestan,
+    Balinese,
+    Bamum,
+    Bassa_Vah,
+    Batak,
+    Bengali,
+    Bhaiksuki,
+    Bopomofo,
+    Brahmi,
+    Braille,
+    Buginese,
+    Buhid,
+    Canadian_Aboriginal,
+    Carian,
+    Caucasian_Albanian,
+    Chakma,
+    Cham,
+    Cherokee,
+    Chorasmian,
+    Common,
+    Coptic,
+    Cuneiform,
+    Cypriot,
+    Cypro_Minoan,
+    Cyrillic,
+    Deseret,
+    Devanagari,
+    Dives_Akuru,
+    Dogra,
+    Duployan,
+    Egyptian_Hieroglyphs,
+    Elbasan,
+    Elymaic,
+    Ethiopic,
+    Georgian,
+    Glagolitic,
+    Gothic,
+    Grantha,
+    Greek,
+    Gujarati,
+    Gunjala_Gondi,
+    Gurmukhi,
+    Han,
+    Hangul,
+    Hanifi_Rohingya,
+    Hanunoo,
+    Hatran,
+    Hebrew,
+    Hiragana,
+    Imperial_Aramaic,
+    Inherited,
+    Inscriptional_Pahlavi,
+    Inscriptional_Parthian,
+    Javanese,
+    Kaithi,
+    Kannada,
+    Katakana,
+    Kawi,
+    Kayah_Li,
+    Kharoshthi,
+    Khitan_Small_Script,
+    Khmer,
+    Khojki,
+    Khudawadi,
+    Lao,
+    Latin,
+    Lepcha,
+    Limbu,
+    Linear_A,
+    Linear_B,
+    Lisu,
+    Lycian,
+    Lydian,
+    Mahajani,
+    Makasar,
+    Malayalam,
+    Mandaic,
+    Manichaean,
+    Marchen,
+    Masaram_Gondi,
+    Medefaidrin,
+    Meetei_Mayek,
+    Mende_Kikakui,
+    Meroitic_Cursive,
+    Meroitic_Hieroglyphs,
+    Miao,
+    Modi,
+    Mongolian,
+    Mro,
+    Multani,
+    Myanmar,
+    Nabataean,
+    Nag_Mundari,
+    Nandinagari,
+    New_Tai_Lue,
+    Newa,
+    Nko,
+    Nushu,
+    Nyiakeng_Puachue_Hmong,
+    Ogham,
+    Ol_Chiki,
+    Old_Hungarian,
+    Old_Italic,
+    Old_North_Arabian,
+    Old_Permic,
+    Old_Persian,
+    Old_Sogdian,
+    Old_South_Arabian,
+    Old_Turkic,
+    Old_Uyghur,
+    Oriya,
+    Osage,
+    Osmanya,
+    Pahawh_Hmong,
+    Palmyrene,
+    Pau_Cin_Hau,
+    Phags_Pa,
+    Phoenician,
+    Psalter_Pahlavi,
+    Rejang,
+    Runic,
+    Samaritan,
+    Saurashtra,
+    Sharada,
+    Shavian,
+    Siddham,
+    SignWriting,
+    Sinhala,
+    Sogdian,
+    Sora_Sompeng,
+    Soyombo,
+    Sundanese,
+    Syloti_Nagri,
+    Syriac,
+    Tagalog,
+    Tagbanwa,
+    Tai_Le,
+    Tai_Tham,
+    Tai_Viet,
+    Takri,
+    Tamil,
+    Tangsa,
+    Tangut,
+    Telugu,
+    Thaana,
+    Thai,
+    Tibetan,
+    Tifinagh,
+    Tirhuta,
+    Toto,
+    Ugaritic,
+    Vai,
+    Vithkuqi,
+    Wancho,
+    Warang_Citi,
+    Yezidi,
+    Yi,
+    Zanabazar_Square,
+};
+
+allocator: mem.Allocator,
+s1: []u16 = undefined,
+s2: []u8 = undefined,
+s3: []u8 = undefined,
+
+const Self = @This();
+
+pub fn init(allocator: mem.Allocator) !Self {
+    const decompressor = compress.deflate.decompressor;
+    const in_bytes = @embedFile("scripts");
+    var in_fbs = std.io.fixedBufferStream(in_bytes);
+    var in_decomp = try decompressor(allocator, in_fbs.reader(), null);
+    defer in_decomp.deinit();
+    var reader = in_decomp.reader();
+
+    const endian = builtin.cpu.arch.endian();
+
+    var self = Self{ .allocator = allocator };
+
+    const s1_len: u16 = try reader.readInt(u16, endian);
+    self.s1 = try allocator.alloc(u16, s1_len);
+    for (0..s1_len) |i| self.s1[i] = try reader.readInt(u16, endian);
+
+    const s2_len: u16 = try reader.readInt(u16, endian);
+    self.s2 = try allocator.alloc(u8, s2_len);
+    _ = try reader.readAll(self.s2);
+
+    const s3_len: u16 = try reader.readInt(u8, endian);
+    self.s3 = try allocator.alloc(u8, s3_len);
+    _ = try reader.readAll(self.s3);
+
+    return self;
+}
+
+pub fn deinit(self: *const Self) void {
+    self.allocator.free(self.s1);
+    self.allocator.free(self.s2);
+    self.allocator.free(self.s3);
+}
+
+/// Lookup the Script type for `cp`.
+pub fn script(self: Self, cp: u21) ?Script {
+    const byte = self.s3[self.s2[self.s1[cp >> 8] + (cp & 0xff)]];
+    if (byte == 0) return null;
+    return @enumFromInt(byte);
+}
+
+test "script" {
+    const self = try init(std.testing.allocator);
+    defer self.deinit();
+    try testing.expectEqual(Script.Latin, self.script('A').?);
+}
-- 
cgit v1.2.3