internal script iterator

zero dependencies 🎉

build.sh

@@ -97,4 +97,5 @@ em++ \
 	gen/lang-script-database.cc \
 	gen/grapheme-break-trie.cc \
 	gen/line-break-trie.cc \
-	gen/emoji-trie.cc
+	gen/emoji-trie.cc \
+	gen/script-trie.cc

gen.js

@@ -374,19 +374,54 @@ async function generateEmojiTrie() {
   writeTrie(path.join(__dirname, 'gen/emoji-trie.cc'), 'emoji_trie', trie);
 }
 
+async function generateScriptTrie() {
+  const res = await fetch('https://www.unicode.org/Public/15.0.0/ucd/Scripts.txt');
+  const re = /^([0-9A-F]+)(?:\.\.([0-9A-F]+))?\s*;\s*([A-Za-z_]+)/gm;
+  const trie = new UnicodeTrieBuilder();
+  /** @type {Map<string, number>} */
+  const names = new Map();
+  let js = '// generated from gen.js\nexport default [\n  undefined,\n';
+  let nextId = 1;
+
+  if (res.status !== 200) throw new Error(res.status);
+
+  const text = await res.text();
+
+  let match;
+
+  while ((match = re.exec(text))) {
+    const start = match[1];
+    const end = match[2] != null ? match[2] : start;
+    const name = match[3];
+    if (!names.has(name)) {
+      const id = nextId++;
+      js += `  '${name}',\n`
+      names.set(name, id);
+    }
+    const id = names.get(name);
+    trie.setRange(parseInt(start, 16), parseInt(end, 16), id);
+  }
+
+  writeTrie(path.join(__dirname, 'gen/script-trie.cc'), 'script_trie', trie);
+  js += '];';
+  fs.writeFileSync(path.join(__dirname, 'gen/script-names.ts'), js);
+}
+
 const fns = process.argv.slice(2).map(command => {
   if (command === 'line-break-trie') return generateLineBreakTrie;
   if (command === 'grapheme-break-trie') return generateGraphemeBreakTrie;
   if (command === 'lang-script-database') return generateLangScriptDatabase;
   if (command === 'entity-trie') return generateEntityTrie;
   if (command === 'emoji-trie') return generateEmojiTrie;
+  if (command === 'script-trie') return generateScriptTrie;
   console.error(`Usage: node gen.js (cmd )+
 Available commands:
   line-break-trie
   grapheme-break-trie
   lang-script-database
   entity-trie
-  emoji-trie`);
+  emoji-trie
+  script-trie`);
   process.exit(1);
 });
 

gen/script-names.ts

@@ -0,0 +1,167 @@
+// generated from gen.js
+export default [
+  undefined,
+  'Common',
+  'Latin',
+  'Greek',
+  'Cyrillic',
+  'Armenian',
+  'Hebrew',
+  'Arabic',
+  'Syriac',
+  'Thaana',
+  'Devanagari',
+  'Bengali',
+  'Gurmukhi',
+  'Gujarati',
+  'Oriya',
+  'Tamil',
+  'Telugu',
+  'Kannada',
+  'Malayalam',
+  'Sinhala',
+  'Thai',
+  'Lao',
+  'Tibetan',
+  'Myanmar',
+  'Georgian',
+  'Hangul',
+  'Ethiopic',
+  'Cherokee',
+  'Canadian_Aboriginal',
+  'Ogham',
+  'Runic',
+  'Khmer',
+  'Mongolian',
+  'Hiragana',
+  'Katakana',
+  'Bopomofo',
+  'Han',
+  'Yi',
+  'Old_Italic',
+  'Gothic',
+  'Deseret',
+  'Inherited',
+  'Tagalog',
+  'Hanunoo',
+  'Buhid',
+  'Tagbanwa',
+  'Limbu',
+  'Tai_Le',
+  'Linear_B',
+  'Ugaritic',
+  'Shavian',
+  'Osmanya',
+  'Cypriot',
+  'Braille',
+  'Buginese',
+  'Coptic',
+  'New_Tai_Lue',
+  'Glagolitic',
+  'Tifinagh',
+  'Syloti_Nagri',
+  'Old_Persian',
+  'Kharoshthi',
+  'Balinese',
+  'Cuneiform',
+  'Phoenician',
+  'Phags_Pa',
+  'Nko',
+  'Sundanese',
+  'Lepcha',
+  'Ol_Chiki',
+  'Vai',
+  'Saurashtra',
+  'Kayah_Li',
+  'Rejang',
+  'Lycian',
+  'Carian',
+  'Lydian',
+  'Cham',
+  'Tai_Tham',
+  'Tai_Viet',
+  'Avestan',
+  'Egyptian_Hieroglyphs',
+  'Samaritan',
+  'Lisu',
+  'Bamum',
+  'Javanese',
+  'Meetei_Mayek',
+  'Imperial_Aramaic',
+  'Old_South_Arabian',
+  'Inscriptional_Parthian',
+  'Inscriptional_Pahlavi',
+  'Old_Turkic',
+  'Kaithi',
+  'Batak',
+  'Brahmi',
+  'Mandaic',
+  'Chakma',
+  'Meroitic_Cursive',
+  'Meroitic_Hieroglyphs',
+  'Miao',
+  'Sharada',
+  'Sora_Sompeng',
+  'Takri',
+  'Caucasian_Albanian',
+  'Bassa_Vah',
+  'Duployan',
+  'Elbasan',
+  'Grantha',
+  'Pahawh_Hmong',
+  'Khojki',
+  'Linear_A',
+  'Mahajani',
+  'Manichaean',
+  'Mende_Kikakui',
+  'Modi',
+  'Mro',
+  'Old_North_Arabian',
+  'Nabataean',
+  'Palmyrene',
+  'Pau_Cin_Hau',
+  'Old_Permic',
+  'Psalter_Pahlavi',
+  'Siddham',
+  'Khudawadi',
+  'Tirhuta',
+  'Warang_Citi',
+  'Ahom',
+  'Anatolian_Hieroglyphs',
+  'Hatran',
+  'Multani',
+  'Old_Hungarian',
+  'SignWriting',
+  'Adlam',
+  'Bhaiksuki',
+  'Marchen',
+  'Newa',
+  'Osage',
+  'Tangut',
+  'Masaram_Gondi',
+  'Nushu',
+  'Soyombo',
+  'Zanabazar_Square',
+  'Dogra',
+  'Gunjala_Gondi',
+  'Makasar',
+  'Medefaidrin',
+  'Hanifi_Rohingya',
+  'Sogdian',
+  'Old_Sogdian',
+  'Elymaic',
+  'Nandinagari',
+  'Nyiakeng_Puachue_Hmong',
+  'Wancho',
+  'Chorasmian',
+  'Dives_Akuru',
+  'Khitan_Small_Script',
+  'Yezidi',
+  'Cypro_Minoan',
+  'Old_Uyghur',
+  'Tangsa',
+  'Toto',
+  'Vithkuqi',
+  'Kawi',
+  'Nag_Mundari',
+];

package.json

@@ -32,8 +32,5 @@
     "ua"
   ],
   "author": "Caleb Hearon <[email protected]>",
-  "license": "MIT",
-  "dependencies": {
-    "itemizer": "^1.0.6"
-  }
+  "license": "MIT"
 }