diff --git a/.gitignore b/.gitignore index f6e7089..6574b17 100644 --- a/.gitignore +++ b/.gitignore @@ -33,3 +33,7 @@ public/legacy/ # Logs *.log + +# fetched dasher demo release artifact +public/demo/ +.cache/ diff --git a/package.json b/package.json index cd3b6e5..7cdaae2 100644 --- a/package.json +++ b/package.json @@ -4,7 +4,8 @@ "description": "Dasher - An information-efficient text-entry interface", "type": "module", "scripts": { - "prebuild": "node scripts/sync-related-research.mjs", + "prebuild": "node scripts/fetch-demo.mjs && node scripts/sync-related-research.mjs", + "demo:fetch": "node scripts/fetch-demo.mjs", "dev": "astro dev", "build": "astro check && astro build && pagefind --site dist", "research:sync": "node scripts/sync-related-research.mjs", diff --git a/scripts/fetch-demo.mjs b/scripts/fetch-demo.mjs new file mode 100644 index 0000000..9d4dcfe --- /dev/null +++ b/scripts/fetch-demo.mjs @@ -0,0 +1,58 @@ +// Fetches a pinned dasher-web WASM demo release artifact and unpacks it +// into public/demo/, so the site self-hosts a known-good demo instead of +// iframing the always-moving GitHub Pages deployment. +// +// Pin the version with DASHER_DEMO_VERSION (default below). The artifact +// is produced by dasher-web's wasm-release workflow on v* tags. + +import { createWriteStream, existsSync, mkdirSync, statSync } from 'node:fs'; +import { spawnSync } from 'node:child_process'; +import process from 'node:process'; +import { fileURLToPath } from 'node:url'; +import path from 'node:path'; + +const root = path.dirname(path.dirname(fileURLToPath(import.meta.url))); +const version = process.env.DASHER_DEMO_VERSION || 'v0.2.8'; +const outDir = path.join(root, 'public', 'demo'); +const marker = path.join(outDir, 'VERSION'); + +const assetName = `dasher-wasm-demo-${version}.zip`; +const url = `https://github.com/dasher-project/dasher-web/releases/download/${version}/${assetName}`; +const zipPath = path.join(root, '.cache', assetName); + +// Skip if the pinned version is already unpacked. +if (existsSync(marker) && existsSync(path.join(outDir, 'index.html'))) { + const installed = + statSync(marker).size > 0 ? (await import('node:fs')).readFileSync(marker, 'utf8').trim() : ''; + if (installed === version) { + console.log(`demo ${version} already installed at public/demo/`); + process.exit(0); + } +} + +mkdirSync(path.dirname(zipPath), { recursive: true }); +mkdirSync(outDir, { recursive: true }); + +console.log(`downloading ${url}`); +const response = await fetch(url); +if (!response.ok) { + console.error( + `failed: HTTP ${response.status} — is dasher-web release ${version} published with asset ${assetName}?` + ); + process.exit(1); +} +await (await import('node:stream')).promises.pipeline(response.body, createWriteStream(zipPath)); + +console.log('unpacking'); +const unzip = spawnSync('unzip', ['-oq', zipPath, '-d', root], { stdio: 'inherit' }); +if (unzip.status !== 0) { + console.error('unzip failed'); + process.exit(1); +} +const staged = path.join(root, 'dasher-wasm-demo'); +for (const entry of ['index.html', 'dasher-wasm-wrapper.js', 'wasm', 'BUILD']) { + spawnSync('mv', [path.join(staged, entry), path.join(outDir, entry)], { stdio: 'inherit' }); +} +spawnSync('rm', ['-rf', staged]); +(await import('node:fs')).writeFileSync(marker, version); +console.log(`demo ${version} installed at public/demo/`); diff --git a/src/data/alphabets.json b/src/data/alphabets.json new file mode 100644 index 0000000..460a89f --- /dev/null +++ b/src/data/alphabets.json @@ -0,0 +1,14341 @@ +{ + "generator": "generate-alphabet-index.py", + "generated_utc": "2026-08-28T18:20:19Z", + "count": 474, + "summaries": { + "by_script": { + "Latn": 317, + "Cyrl": 33, + "Deva": 18, + "Arab": 14, + "Hira": 9, + "Ethi": 8, + "Hani": 7, + "Beng": 4, + "unknown": 3, + "Kana": 3, + "Orya": 3, + "Mymr": 2, + "Cher": 2, + "Hans": 2, + "Thaa": 2, + "Tibt": 2, + "Geor": 2, + "Gujr": 2, + "Hebr": 2, + "Cans": 2, + "Knda": 2, + "Hang": 2, + "Laoo": 2, + "Mlym": 2, + "Guru": 2, + "Sinh": 2, + "Taml": 2, + "Telu": 2, + "Thai": 2, + "Armn": 1, + "Bamu": 1, + "Cakm": 1, + "Bopo": 1, + "Copt": 1, + "Adlm": 1, + "Grek": 1, + "Khmr": 1, + "Lepc": 1, + "Lisu": 1, + "Nkoo": 1, + "Ogam": 1, + "Osge": 1, + "Rohg": 1, + "Saur": 1, + "Yiii": 1, + "Syrc": 1, + "Vaii": 1, + "Runr": 1 + }, + "by_orientation": { + "ltr": 451, + "rtl": 22, + "ttb": 1 + }, + "with_lang_code": 456, + "without_lang_code": 18 + }, + "alphabets": [ + { + "id": "Abc (Musical language)", + "file": "autoConverted/alphabet.abc.musical.language.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_abc_XX.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 100, + "groups": [ + "Second octave notes", + "First octave notes", + "Numbers", + "Annotation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.abc.xml"] + }, + { + "id": "Abkhazian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.abkhazian.ab-Cyrl.xml", + "orientation": "ltr", + "lang": "ab", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 95, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Adangbe with lots of punctuation", + "file": "autoConverted/alphabet.adangbe.with.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "adq", + "script": "Latn", + "script_name": "Latin", + "training": "training_adangbe_GH.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 106, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.adangbe.xml"] + }, + { + "id": "Adyghe (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.adyghe.ady-Cyrl.xml", + "orientation": "ltr", + "lang": "ady", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Afaan Oromo - with numerals and punctuation", + "file": "autoConverted/alphabet.afaan.oromo.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "om", + "script": "Latn", + "script_name": "Latin", + "training": "training_AfaanOromo_ET.txt", + "palette": "Default", + "conversion": "none", + "chars": 97, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.AfaanOromo.xml"] + }, + { + "id": "Afar (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.afar.aa-Latn.xml", + "orientation": "ltr", + "lang": "aa", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Afrikaans (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.afrikaans.af-Latn.xml", + "orientation": "ltr", + "lang": "af", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_af_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Afrikaans with punctuation and numerals", + "file": "autoConverted/alphabet.afrikaans.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "af", + "script": "Latn", + "script_name": "Latin", + "training": "training_Afrikaans_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 123, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.afrikaans.xml"] + }, + { + "id": "Aghem (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.aghem.agq-Latn.xml", + "orientation": "ltr", + "lang": "agq", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 111, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Akan (Twi) with lots of punctuation", + "file": "autoConverted/alphabet.akan.twi.with.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "ak", + "script": "Latn", + "script_name": "Latin", + "training": "training_akan_GH.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 106, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.akan.xml"] + }, + { + "id": "Akan (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.akan.ak-Latn.xml", + "orientation": "ltr", + "lang": "ak", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Akoose (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.akoose.bss-Latn.xml", + "orientation": "ltr", + "lang": "bss", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 111, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Albanian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.albanian.sq-Latn.xml", + "orientation": "ltr", + "lang": "sq", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_sq_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Amharic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.amharic.am-Ethi.xml", + "orientation": "ltr", + "lang": "am", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 579, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 282 + }, + { + "id": "Amharic (አማርኛ) with punctuation and numerals", + "file": "autoConverted/alphabet.amharic.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "am", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "training_amharic_ET.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 361, + "groups": ["ethiopic letters", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.amharic.xml"] + }, + { + "id": "Ar brezhoneg / Breton with punctuation and numerals", + "file": "autoConverted/alphabet.ar.brezhoneg.breton.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "br", + "script": "Latn", + "script_name": "Latin", + "training": "training_breton_FR.txt", + "palette": "Default", + "conversion": "none", + "chars": 114, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.breton.xml"] + }, + { + "id": "Arabic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.arabic.ar-Arab.xml", + "orientation": "rtl", + "lang": "ar", + "script": "Arab", + "script_name": "Arabic", + "training": "training_wa_ar_Arab.txt", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 36 + }, + { + "id": "Aragonese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.aragonese.an-Latn.xml", + "orientation": "ltr", + "lang": "an", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Armenian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.armenian.hy-Armn.xml", + "orientation": "ltr", + "lang": "hy", + "script": "Armn", + "script_name": "Armenian", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Assamese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.assamese.as-Beng.xml", + "orientation": "ltr", + "lang": "as", + "script": "Beng", + "script_name": "Bengali", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 93, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 44 + }, + { + "id": "Assamese অসমীয়া with punctuation and numerals", + "file": "autoConverted/alphabet.assamese..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "as", + "script": "Beng", + "script_name": "Bengali", + "training": "training_Assamese_IN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 130, + "groups": [ + "bengali letters", + "bengali vowels", + "bengali consonants", + "Bengali combining vowels", + "Bengali numbers", + "Numbers", + "Punctuation", + "Bengali Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Assamese.xml"] + }, + { + "id": "Asturian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.asturian.ast-Latn.xml", + "orientation": "ltr", + "lang": "ast", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Asu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.asu.asa-Latn.xml", + "orientation": "ltr", + "lang": "asa", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Aymara (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.aymara.ay-Latn.xml", + "orientation": "ltr", + "lang": "ay", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Azerbaijani (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.azerbaijani.az-Cyrl.xml", + "orientation": "ltr", + "lang": "az", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.azerbaijani.az-Latn.xml"] + }, + { + "id": "Azərbaycanca / Azeri / Azerbaijani with punctuation and numerals", + "file": "autoConverted/alphabet.azrbaycanca.azeri.azerbaijani.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "az", + "script": "Latn", + "script_name": "Latin", + "training": "training_Azerbaijani_AZ.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Azerbaijani.xml"] + }, + { + "id": "Bafia (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bafia.ksf-Latn.xml", + "orientation": "ltr", + "lang": "ksf", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Bahasa Indonesia / Indonesian with numerals and punctuation", + "file": "autoConverted/alphabet.bahasa.indonesia.indonesian.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "id", + "script": "Latn", + "script_name": "Latin", + "training": "training_Indonesian_ID.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Indonesian.xml"] + }, + { + "id": "Bahasa Melayu / Malay alphabet with numerals and punctuation", + "file": "autoConverted/alphabet.bahasa.melayu.malay.alphabet.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "ms", + "script": "Latn", + "script_name": "Latin", + "training": "training_Malay_MY.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Malay.xml"] + }, + { + "id": "Balinese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.balinese.ban-Latn.xml", + "orientation": "ltr", + "lang": "ban", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 157, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 76 + }, + { + "id": "Baluchi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.baluchi.bal-Arab.xml", + "orientation": "rtl", + "lang": "bal", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 28, + "variants": ["autoConverted/alphabet.wa.baluchi.bal-Latn.xml"] + }, + { + "id": "Bambara (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bambara.bm-Latn.xml", + "orientation": "ltr", + "lang": "bm", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.bambara.bm-Nkoo.xml"] + }, + { + "id": "Bamun (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bamun.bax-Bamu.xml", + "orientation": "ltr", + "lang": "bax", + "script": "Bamu", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 165, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 80 + }, + { + "id": "Bangla (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bangla.bn-Beng.xml", + "orientation": "ltr", + "lang": "bn", + "script": "Beng", + "script_name": "Bengali", + "training": "training_wa_bn_Beng.txt", + "palette": "Default", + "conversion": "none", + "chars": 107, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 51 + }, + { + "id": "Basaa (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.basaa.bas-Latn.xml", + "orientation": "ltr", + "lang": "bas", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 125, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Bashkir (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bashkir.ba-Cyrl.xml", + "orientation": "ltr", + "lang": "ba", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 99, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Basque (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.basque.eu-Latn.xml", + "orientation": "ltr", + "lang": "eu", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_eu_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Batak (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.batak.bya-Latn.xml", + "orientation": "ltr", + "lang": "bya", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 109, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 52 + }, + { + "id": "Belarusian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.belarusian.be-Cyrl.xml", + "orientation": "ltr", + "lang": "be", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.belarusian.be-x-old.xml"] + }, + { + "id": "Belarusian with punctuation and numerals", + "file": "autoConverted/alphabet.belarusian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "be", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_Belarusian_BY.txt", + "palette": "Default", + "conversion": "none", + "chars": 281, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Belarusian.xml"] + }, + { + "id": "Bemba (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bemba.bem-Latn.xml", + "orientation": "ltr", + "lang": "bem", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 55, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Bena (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bena.bez-Latn.xml", + "orientation": "ltr", + "lang": "bez", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Betawi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.betawi.bew-Latn.xml", + "orientation": "ltr", + "lang": "bew", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Bhojpuri (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bhojpuri.bho-Deva.xml", + "orientation": "ltr", + "lang": "bho", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 32 + }, + { + "id": "Blin (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.blin.byn-Ethi.xml", + "orientation": "ltr", + "lang": "byn", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 591, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 288 + }, + { + "id": "Bodo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bodo.brx-Deva.xml", + "orientation": "ltr", + "lang": "brx", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 105, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 45 + }, + { + "id": "Bosanski / Bosnian with punctuation and numerals", + "file": "autoConverted/alphabet.bosanski.bosnian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "bs", + "script": "Latn", + "script_name": "Latin", + "training": "training_bosnian_BA.txt", + "palette": "Default", + "conversion": "none", + "chars": 106, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.bosnian.xml"] + }, + { + "id": "Bosnian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bosnian.bs-Latn.xml", + "orientation": "ltr", + "lang": "bs", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Breton (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.breton.br-Latn.xml", + "orientation": "ltr", + "lang": "br", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Buginese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.buginese.bug-Latn.xml", + "orientation": "ltr", + "lang": "bug", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 30 + }, + { + "id": "Buhid (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.buhid.bku-Latn.xml", + "orientation": "ltr", + "lang": "bku", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 45, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 20 + }, + { + "id": "Bulgarian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.bulgarian.bg-Cyrl.xml", + "orientation": "ltr", + "lang": "bg", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Bulgarian / Български with punctuation and numerals", + "file": "autoConverted/alphabet.bulgarian..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "bg", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_Bulgarian_BG.txt", + "palette": "Default", + "conversion": "none", + "chars": 108, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Bulgarian.xml"] + }, + { + "id": "Burmese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.burmese.my-Mymr.xml", + "orientation": "ltr", + "lang": "my", + "script": "Mymr", + "script_name": "Myanmar", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 42 + }, + { + "id": "Burmese / Myanmar with punctuation and numerals", + "file": "autoConverted/alphabet.burmese.myanmar.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "my", + "script": "Mymr", + "script_name": "Myanmar", + "training": "training_myanmar_MM.txt", + "palette": "Default", + "conversion": "none", + "chars": 103, + "groups": ["Myanmar letters", "Vowels Myanmar", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.myanmar.xml"] + }, + { + "id": "Caddo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.caddo.cad-Latn.xml", + "orientation": "ltr", + "lang": "cad", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 3 + }, + { + "id": "Cantonese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.cantonese.zh-yue-Hant.xml", + "orientation": "ltr", + "lang": "yue", + "script": "Hani", + "script_name": "Han", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 4425, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 2210 + }, + { + "id": "Cantonese 倉頡輸入法 (trad) by Cangjie", + "file": "autoConverted/alphabet.cantonese.trad.by.cangjie.xml", + "orientation": "ltr", + "lang": "yue", + "script": "Hani", + "script_name": "Han", + "training": "training_cantonese_CN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 17454, + "groups": ["Punctuation", "space"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.cangjie.xml"] + }, + { + "id": "Catalan (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.catalan.ca-Latn.xml", + "orientation": "ltr", + "lang": "ca", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_ca_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Català / Catalan (combining accents) with punctuation and numerals", + "file": "autoConverted/alphabet.catal.catalan.combining.accents.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ca", + "script": "Latn", + "script_name": "Latin", + "training": "training_catalanC_ES.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 108, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Català / Catalan with punctuation and numerals", + "file": "autoConverted/alphabet.catal.catalan.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ca", + "script": "Latn", + "script_name": "Latin", + "training": "training_catalan_ES.txt", + "palette": "Default", + "conversion": "none", + "chars": 124, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.catalan.xml"] + }, + { + "id": "Cebuano (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.cebuano.ceb-Latn.xml", + "orientation": "ltr", + "lang": "ceb", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 43, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Central Atlas Tamazight (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.central.atlas.tamazight.tzm-Latn.xml", + "orientation": "ltr", + "lang": "tzm", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Central Kurdish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.central.kurdish.ckb-Arab.xml", + "orientation": "rtl", + "lang": "ckb", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 33 + }, + { + "id": "Central Melanau (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.central.melanau.mel-Latn.xml", + "orientation": "ltr", + "lang": "mel", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Chakma (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.chakma.ccp-Cakm.xml", + "orientation": "ltr", + "lang": "ccp", + "script": "Cakm", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 36 + }, + { + "id": "Chechen (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.chechen.ce-Cyrl.xml", + "orientation": "ltr", + "lang": "ce", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Cherokee", + "file": "autoConverted/alphabet.cherokee.xml", + "orientation": "ltr", + "lang": "chr", + "script": "Cher", + "script_name": "Cherokee", + "training": "training_cherokee_US.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 87, + "groups": [ + "A", + "GA", + "HA", + "LA", + "MA", + "NA", + "QUA", + "SA", + "DA", + "DL", + "TS", + "WA", + "YA", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.cherokee.xml"] + }, + { + "id": "Cherokee (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.cherokee.chr-Cher.xml", + "orientation": "ltr", + "lang": "chr", + "script": "Cher", + "script_name": "Cherokee", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 185, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Chickasaw (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.chickasaw.cic-Latn.xml", + "orientation": "ltr", + "lang": "cic", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 51, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Chiga (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.chiga.cgg-Latn.xml", + "orientation": "ltr", + "lang": "cgg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Chinese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.chinese.zh-Hans.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Hans", + "script_name": "Han", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 4425, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 2210, + "variants": ["autoConverted/alphabet.wa.chinese.zh-Hant.xml"] + }, + { + "id": "Chinese Pin Yin with combining tones (no chinese characters)", + "file": "autoConverted/alphabet.chinese.pin.yin.with.combining.tones.no.chinese.characters.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Latn", + "script_name": "Latin", + "training": "training_pinyinC_CN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 76, + "groups": [ + "pin yin roman letters", + "combining diacritics", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Chinese Pin Yin with no tones (no chinese characters)", + "file": "autoConverted/alphabet.chinese.pin.yin.with.no.tones.no.chinese.characters.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Latn", + "script_name": "Latin", + "training": "training_pinyinNT_CN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 76, + "groups": [ + "pin yin roman letters", + "combining diacritics", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Chinese Pin Yin with tones (no chinese characters) (11 groups)", + "file": "autoConverted/alphabet.chinese.pin.yin.with.tones.no.chinese.characters.11.groups.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Latn", + "script_name": "Latin", + "training": "training_pinyin_CN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 96, + "groups": [ + "pin yin roman letters", + "a", + "b-d", + "e", + "f-h", + "i", + "j-n", + "o", + "p-t", + "u", + "ü", + "v-z", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Chinese Pin Yin with tones (no chinese characters) (5 groups)", + "file": "autoConverted/alphabet.chinese.pin.yin.with.tones.no.chinese.characters.5.groups.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Latn", + "script_name": "Latin", + "training": "training_pinyin_CN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 96, + "groups": [ + "pin yin roman letters", + "a", + "e", + "i", + "o", + "u", + "ü", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.pinyin2.xml"] + }, + { + "id": "Chinese Zhùyīn fúhào ㄅㄆㄇㄈ (Bopomofo) with punctuation and numerals", + "file": "autoConverted/alphabet.chinese.zhyn.fho..bopomofo.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Bopo", + "script_name": "Bopomofo", + "training": "training_bopomofo_CN.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "consonants (then vowels)", + "combining diacritics", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.bopomofo.xml"] + }, + { + "id": "Choctaw (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.choctaw.cho-Latn.xml", + "orientation": "ltr", + "lang": "cho", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 55, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Church Slavic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.church.slavic.cu-Cyrl.xml", + "orientation": "ltr", + "lang": "cu", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 119, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 2 + }, + { + "id": "Chuvash (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.chuvash.cv-Cyrl.xml", + "orientation": "ltr", + "lang": "cv", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Colognian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.colognian.ksh-Latn.xml", + "orientation": "ltr", + "lang": "ksh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Coptic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.coptic.cop-Copt.xml", + "orientation": "ltr", + "lang": "cop", + "script": "Copt", + "script_name": "Greek", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Cornish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.cornish.kw-Latn.xml", + "orientation": "ltr", + "lang": "kw", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Corsican (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.corsican.co-Latn.xml", + "orientation": "ltr", + "lang": "co", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Corsu / Corsican with punctuation and numerals", + "file": "autoConverted/alphabet.corsu.corsican.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "co", + "script": "Latn", + "script_name": "Latin", + "training": "training_corsican_FR.txt", + "palette": "Default", + "conversion": "none", + "chars": 106, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.corsican.xml"] + }, + { + "id": "Croatian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.croatian.hr-Latn.xml", + "orientation": "ltr", + "lang": "hr", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_hr_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Cymraeg / Welsh with punctuation and numerals", + "file": "autoConverted/alphabet.cymraeg.welsh.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "cy", + "script": "Latn", + "script_name": "Latin", + "training": "training_welsh_GB.txt", + "palette": "Default", + "conversion": "none", + "chars": 152, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.welsh.xml"] + }, + { + "id": "Czech (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.czech.cs-Latn.xml", + "orientation": "ltr", + "lang": "cs", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_cs_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Danish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.danish.da-Latn.xml", + "orientation": "ltr", + "lang": "da", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_da_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Dansk / Danish lower case", + "file": "autoConverted/alphabet.dansk.danish.lower.case.xml", + "orientation": "ltr", + "lang": "da", + "script": "Latn", + "script_name": "Latin", + "training": "training_danish_DK.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 39, + "groups": ["lower case letters", "Punctuation", "paragraphSpace"], + "source": "worldalphabets" + }, + { + "id": "Dansk / Danish with limited punctuation", + "file": "autoConverted/alphabet.dansk.danish.with.limited.punctuation.xml", + "orientation": "ltr", + "lang": "da", + "script": "Latn", + "script_name": "Latin", + "training": "training_danish_DK.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 77, + "groups": ["lower case letters", "upper case letters", "Punctuation", "paragraphSpace"], + "source": "worldalphabets" + }, + { + "id": "Dansk / Danish with punctuation and numerals", + "file": "autoConverted/alphabet.dansk.danish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "da", + "script": "Latn", + "script_name": "Latin", + "training": "training_danish_DK.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 125, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.danish.xml"] + }, + { + "id": "Deutsch / German with limited punctuation", + "file": "alphabet.deutsch.german.with.limited.punctuation.xml", + "orientation": "ltr", + "lang": "de", + "script": "Latn", + "script_name": "Latin", + "training": "training_german_DE.txt", + "palette": "Default", + "conversion": "none", + "chars": 66, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained" + }, + { + "id": "Deutsch / German with numerals and punctuation", + "file": "alphabet.deutsch.german.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "de", + "script": "Latn", + "script_name": "Latin", + "training": "training_german_DE.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 110, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained", + "variants": ["oldAlphabets/alphabet.german.xml"] + }, + { + "id": "Dhivehi (thaana) with punctuation and numerals", + "file": "autoConverted/alphabet.dhivehi.thaana.with.punctuation.and.numerals.xml", + "orientation": "rtl", + "lang": "dv", + "script": "Thaa", + "script_name": "Thaana", + "training": "training_thaana_MV.txt", + "palette": "Default", + "conversion": "none", + "chars": 94, + "groups": ["thaana letters", "thaana vowels", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.thaana.xml"] + }, + { + "id": "Divehi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.divehi.dv-Thaa.xml", + "orientation": "rtl", + "lang": "dv", + "script": "Thaa", + "script_name": "Thaana", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 24 + }, + { + "id": "Duala (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.duala.dua-Latn.xml", + "orientation": "ltr", + "lang": "dua", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Dutch (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.dutch.nl-Latn.xml", + "orientation": "ltr", + "lang": "nl", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_nl_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Dzongkha (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.dzongkha.dz-Tibt.xml", + "orientation": "ltr", + "lang": "dz", + "script": "Tibt", + "script_name": "Tibetan", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 30 + }, + { + "id": "Eesti / Estonian with punctuation and numerals", + "file": "autoConverted/alphabet.eesti.estonian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "et", + "script": "Latn", + "script_name": "Latin", + "training": "training_Estonian_EE.txt", + "palette": "Default", + "conversion": "none", + "chars": 112, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Estonian.xml"] + }, + { + "id": "Embu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.embu.ebu-Latn.xml", + "orientation": "ltr", + "lang": "ebu", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "English (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.english.en-Latn.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_en_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "English Latex", + "file": "alphabet.english.latex.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_latex_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained", + "variants": ["oldAlphabets/alphabet.latex.xml"] + }, + { + "id": "English with accents, numerals, punctuation", + "file": "alphabet.english.with.accents.numerals.punctuation.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_english_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 115, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained", + "variants": ["oldAlphabets/alphabet.englishC.xml"] + }, + { + "id": "English with limited punctuation", + "file": "alphabet.english.with.limited.punctuation.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_english_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 61, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained", + "variants": ["oldAlphabets/alphabet.english.xml"] + }, + { + "id": "English with numerals and limited punctuation", + "file": "alphabet.english.with.numerals.and.limited.punctuation.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_english_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 71, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained" + }, + { + "id": "English with numerals and lots of punctuation", + "file": "alphabet.english.with.numerals.and.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_english_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 103, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "maintained" + }, + { + "id": "English without punctuation", + "file": "alphabet.english.without.punctuation.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_english_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 53, + "groups": ["Lower case Latin letters", "Upper case Latin letters", "space"], + "source": "maintained" + }, + { + "id": "English, lower case", + "file": "alphabet.english.lower.case.xml", + "orientation": "ltr", + "lang": "en", + "script": null, + "script_name": null, + "training": "training_englishLC_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 32, + "groups": ["Lower case Latin letters", "Punctuation", "space"], + "source": "maintained" + }, + { + "id": "Erzya (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.erzya.myv-Cyrl.xml", + "orientation": "ltr", + "lang": "myv", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Español / Spanish (combining accents) with numerals and punctuation", + "file": "autoConverted/alphabet.espaol.spanish.combining.accents.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "es", + "script": "Latn", + "script_name": "Latin", + "training": "training_spanishC_ES.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 113, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Español / Spanish with punctuation and numerals", + "file": "autoConverted/alphabet.espaol.spanish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "es", + "script": "Latn", + "script_name": "Latin", + "training": "training_spanish_ES.txt", + "palette": "Default", + "conversion": "none", + "chars": 121, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.spanish.xml"] + }, + { + "id": "Esperanto (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.esperanto.eo-Latn.xml", + "orientation": "ltr", + "lang": "eo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Esperanto with punctuation and numerals", + "file": "autoConverted/alphabet.esperanto.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "eo", + "script": "Latn", + "script_name": "Latin", + "training": "training_Esperanto_XX.txt", + "palette": "Default", + "conversion": "none", + "chars": 108, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Esperanto.xml"] + }, + { + "id": "Estonian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.estonian.et-Latn.xml", + "orientation": "ltr", + "lang": "et", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Ethiopic with punctuation and numerals", + "file": "autoConverted/alphabet.ethiopic.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Ethi", + "script_name": "Ethiopic", + "training": "training_ethiopic_ET.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 361, + "groups": ["ethiopic letters", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ethiopic.xml"] + }, + { + "id": "Euskara / Basque with punctuation and numerals", + "file": "autoConverted/alphabet.euskara.basque.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "eu", + "script": "Latn", + "script_name": "Latin", + "training": "training_basque_ES.txt", + "palette": "Default", + "conversion": "none", + "chars": 98, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.basque.xml"] + }, + { + "id": "Ewe (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ewe.ee-Latn.xml", + "orientation": "ltr", + "lang": "ee", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 95, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Ewe with lots of punctuation", + "file": "autoConverted/alphabet.ewe.with.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "ee", + "script": "Latn", + "script_name": "Latin", + "training": "training_ewe_GH.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 114, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ewe.xml"] + }, + { + "id": "Ewondo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ewondo.ewo-Latn.xml", + "orientation": "ltr", + "lang": "ewo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 111, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Faroese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.faroese.fo-Latn.xml", + "orientation": "ltr", + "lang": "fo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Filipino (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.filipino.tl-Latn.xml", + "orientation": "ltr", + "lang": "tl", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 45, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 20 + }, + { + "id": "Finnish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.finnish.fi-Latn.xml", + "orientation": "ltr", + "lang": "fi", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_fi_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Français / French (combining accents) with numerals and punctuation", + "file": "autoConverted/alphabet.franais.french.combining.accents.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "fr", + "script": "Latn", + "script_name": "Latin", + "training": "training_frenchC_FR.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 111, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Français / French with numerals and punctuation", + "file": "autoConverted/alphabet.franais.french.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "fr", + "script": "Latn", + "script_name": "Latin", + "training": "training_french_FR.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 124, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1, + "variants": ["oldAlphabets/alphabet.french.xml"] + }, + { + "id": "Français / French with numerals and punctuation (vowels grouped)", + "file": "autoConverted/alphabet.franais.french.with.numerals.and.punctuation.vowels.grouped.xml", + "orientation": "ltr", + "lang": "fr", + "script": "Latn", + "script_name": "Latin", + "training": "training_french_FR.txt", + "palette": "Vowels", + "conversion": "none", + "chars": 114, + "groups": [ + "Lower case Latin letters", + "a", + "Combining accents", + "c", + "e", + "i", + "o", + "u", + "Upper case Latin letters", + "A", + "C", + "E", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 6 + }, + { + "id": "French (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.french.fr-Latn.xml", + "orientation": "ltr", + "lang": "fr", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_fr_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 99, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Friulian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.friulian.fur-Latn.xml", + "orientation": "ltr", + "lang": "fur", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Fula (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.fula.ff-Adlm.xml", + "orientation": "rtl", + "lang": "ff", + "script": "Adlm", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1, + "variants": ["autoConverted/alphabet.wa.fula.ff-Latn.xml"] + }, + { + "id": "Føroyskt / Faroese with punctuation and numerals", + "file": "autoConverted/alphabet.froyskt.faroese.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "fo", + "script": "Latn", + "script_name": "Latin", + "training": "training_faroese_FO.txt", + "palette": "Default", + "conversion": "none", + "chars": 118, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.faroese.xml"] + }, + { + "id": "Ga (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ga.gaa-Latn.xml", + "orientation": "ltr", + "lang": "gaa", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Ga with lots of punctuation", + "file": "autoConverted/alphabet.ga.with.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_ga_GH.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 106, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ga.xml"] + }, + { + "id": "Gaeilge na hÉireann / Irish Gaelic with punctuation and numerals", + "file": "autoConverted/alphabet.gaeilge.na.hireann.irish.gaelic.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ga", + "script": "Latn", + "script_name": "Latin", + "training": "training_IrishGaelic_IE.txt", + "palette": "Default", + "conversion": "none", + "chars": 106, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.IrishGaelic.xml"] + }, + { + "id": "Galego / Galician with punctuation and numerals", + "file": "autoConverted/alphabet.galego.galician.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "gl", + "script": "Latn", + "script_name": "Latin", + "training": "training_galician_ES.txt", + "palette": "Default", + "conversion": "none", + "chars": 108, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.galician.xml"] + }, + { + "id": "Galician (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.galician.gl-Latn.xml", + "orientation": "ltr", + "lang": "gl", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Ganda (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ganda.lg-Latn.xml", + "orientation": "ltr", + "lang": "lg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Geez (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.geez.gez-Ethi.xml", + "orientation": "ltr", + "lang": "gez", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 419, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 202 + }, + { + "id": "Georgian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.georgian.ka-Geor.xml", + "orientation": "ltr", + "lang": "ka", + "script": "Geor", + "script_name": "Georgian", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 33 + }, + { + "id": "Georgian / ქართული ენა with punctuation and numerals", + "file": "autoConverted/alphabet.georgian..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ka", + "script": "Geor", + "script_name": "Georgian", + "training": "training_georgian_GE.txt", + "palette": "Default", + "conversion": "none", + "chars": 124, + "groups": [ + "lower case georgian letters (Mkhedruli) ", + "upper case letters (Mkhedruli) ", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.georgian.xml"] + }, + { + "id": "German (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.german.de-Latn.xml", + "orientation": "ltr", + "lang": "de", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_de_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Greek (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.greek.el-Grek.xml", + "orientation": "ltr", + "lang": "el", + "script": "Grek", + "script_name": "Greek", + "training": "training_wa_el_Grek.txt", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Guarani (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.guarani.gn-Latn.xml", + "orientation": "ltr", + "lang": "gn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Gujarati (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.gujarati.gu-Gujr.xml", + "orientation": "ltr", + "lang": "gu", + "script": "Gujr", + "script_name": "Gujarati", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 105, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 50 + }, + { + "id": "Gujarati with punctuation and numerals", + "file": "autoConverted/alphabet.gujarati.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "gu", + "script": "Gujr", + "script_name": "Gujarati", + "training": "training_Gujarati_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 113, + "groups": [ + "Gujarati letters", + "vowel signs and other marks", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Gujarati.xml"] + }, + { + "id": "Gusii (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.gusii.guz-Latn.xml", + "orientation": "ltr", + "lang": "guz", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Gàidhlig / Scots Gaelic with punctuation and numerals", + "file": "autoConverted/alphabet.gidhlig.scots.gaelic.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "gd", + "script": "Latn", + "script_name": "Latin", + "training": "training_ScotsGaelic_GB.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ScotsGaelic.xml"] + }, + { + "id": "Haitian Creole (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.haitian.creole.ht-Latn.xml", + "orientation": "ltr", + "lang": "ht", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Hanunoo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.hanunoo.hnn-Latn.xml", + "orientation": "ltr", + "lang": "hnn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 51, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 23 + }, + { + "id": "Haryanvi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.haryanvi.bgc-Deva.xml", + "orientation": "ltr", + "lang": "bgc", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 103, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 44 + }, + { + "id": "Hausa (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.hausa.ha-Latn.xml", + "orientation": "ltr", + "lang": "ha", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Hausa (boko) with punctuation and numerals", + "file": "autoConverted/alphabet.hausa.boko.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ha", + "script": "Latn", + "script_name": "Latin", + "training": "training_hausa_NE.txt", + "palette": "Default", + "conversion": "none", + "chars": 104, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.hausa.xml"] + }, + { + "id": "Hawaiian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.hawaiian.haw-Latn.xml", + "orientation": "ltr", + "lang": "haw", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 51, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Hawaiian / ʻŌlelo Hawaiʻi with lots of punctuation", + "file": "autoConverted/alphabet.hawaiian.lelo.hawaii.with.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "haw", + "script": "Latn", + "script_name": "Latin", + "training": "training_Hawaiian_US.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 107, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Hawaiian.xml"] + }, + { + "id": "Hebrew (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.hebrew.he-Hebr.xml", + "orientation": "rtl", + "lang": "he", + "script": "Hebr", + "script_name": "Hebrew", + "training": "training_wa_he_Hebr.txt", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 27 + }, + { + "id": "Hindi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.hindi.hi-Deva.xml", + "orientation": "ltr", + "lang": "hi", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 115, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 50 + }, + { + "id": "Hindi / हिंदी", + "file": "autoConverted/alphabet.hindi...xml", + "orientation": "ltr", + "lang": null, + "script": "Deva", + "script_name": "Devanagari", + "training": "training_Hindi_IN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 129, + "groups": [ + "DEVANAGARI letters", + "combining signs and vowels", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Hindi.xml"] + }, + { + "id": "Hindi / हिंदी Grouped", + "file": "autoConverted/alphabet.hindi..grouped..xml", + "orientation": "ltr", + "lang": null, + "script": "Deva", + "script_name": "Devanagari", + "training": "training_Hindi_IN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 133, + "groups": [ + "DEVANAGARI letters", + "combining signs and vowels", + "regular vowels", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Hiragana ひらがな 60", + "file": "autoConverted/alphabet.hiragana.60.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana60_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 68, + "groups": [ + "Diacriticals", + "60 Letters (actually 55 plus two diacriticals)", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Hiragana ひらがな 60 + 0-9", + "file": "autoConverted/alphabet.hiragana.60.09.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana60_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 79, + "groups": [ + "Diacriticals", + "60 Letters (actually 55)", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Hiragana ひらがな 83", + "file": "autoConverted/alphabet.hiragana.83.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana83_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 91, + "groups": ["83 Letters (actually 81)", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.hiragana.xml"] + }, + { + "id": "Hiragana ひらがな 83 (diacritical groups)", + "file": "autoConverted/alphabet.hiragana.83.diacritical.groups.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana83_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 71, + "groups": ["aiueo", "m", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 2 + }, + { + "id": "Hiragana ひらがな 83 (diacritical groups, marks first)", + "file": "autoConverted/alphabet.hiragana.83.diacritical.groups.marks.first.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana83_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 71, + "groups": ["aiueo", "m", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 4 + }, + { + "id": "Hiragana ひらがな 83 + 0-9", + "file": "autoConverted/alphabet.hiragana.83.09.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana83_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 102, + "groups": ["83 Letters (actually 81)", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.hiragana2.xml"] + }, + { + "id": "Hiragana(Alternate Grouped) ひらがな 60 + 0-9", + "file": "autoConverted/alphabet.hiraganaalternate.grouped.60.09.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana60_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 79, + "groups": [ + "DIACR", + "A", + "A small", + "KA", + "SA", + "TA", + "NA", + "HA", + "MA", + "YA", + "YA small", + "RA", + "WA", + "N", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Hiragana(Grouped) ひらがな 60 + 0-9", + "file": "autoConverted/alphabet.hiraganagrouped.60.09.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_hiragana60_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 79, + "groups": [ + "DIACR", + "A", + "KA", + "SA", + "TA", + "NA", + "HA", + "MA", + "YA", + "RA", + "WA", + "N", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Hrvatski / Croatian with punctuation and numerals", + "file": "autoConverted/alphabet.hrvatski.croatian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "hr", + "script": "Latn", + "script_name": "Latin", + "training": "training_croatian_HR.txt", + "palette": "Default", + "conversion": "none", + "chars": 106, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.croatian.xml"] + }, + { + "id": "Hungarian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.hungarian.hu-Latn.xml", + "orientation": "ltr", + "lang": "hu", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Icelandic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.icelandic.is-Latn.xml", + "orientation": "ltr", + "lang": "is", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Icelandic / Íslensku with punctuation and numerals", + "file": "autoConverted/alphabet.icelandic.slensku.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "is", + "script": "Latn", + "script_name": "Latin", + "training": "training_Icelandic_IS.txt", + "palette": "Default", + "conversion": "none", + "chars": 122, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Icelandic.xml"] + }, + { + "id": "Ido (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ido.io-Latn.xml", + "orientation": "ltr", + "lang": "io", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Igbo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.igbo.ig-Latn.xml", + "orientation": "ltr", + "lang": "ig", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Igbo with punctuation and numerals", + "file": "autoConverted/alphabet.igbo.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ig", + "script": "Latn", + "script_name": "Latin", + "training": "training_Igbo_NG.txt", + "palette": "Default", + "conversion": "none", + "chars": 112, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Igbo.xml"] + }, + { + "id": "Inari Sami (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.inari.sami.smn-Latn.xml", + "orientation": "ltr", + "lang": "smn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Indonesian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.indonesian.id-Latn.xml", + "orientation": "ltr", + "lang": "id", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Interlingua (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.interlingua.ia-Latn.xml", + "orientation": "ltr", + "lang": "ia", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Interlingue (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.interlingue.ie-Latn.xml", + "orientation": "ltr", + "lang": "ie", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "International Phonetic Alphabet", + "file": "autoConverted/alphabet.international.phonetic.alphabet.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_ipa_GB.txt", + "palette": "Default", + "conversion": "none", + "chars": 133, + "groups": ["Lower case Latin letters", "Phonetic symbols", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ipa.xml"] + }, + { + "id": "Inuktitut (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.inuktitut.iu-Cans.xml", + "orientation": "ltr", + "lang": "iu", + "script": "Cans", + "script_name": "Canadian Aboriginal", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 223, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 109, + "variants": ["autoConverted/alphabet.wa.inuktitut.iu-Latn.xml"] + }, + { + "id": "Irish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.irish.ga-Latn.xml", + "orientation": "ltr", + "lang": "ga", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 51, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Italian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.italian.it-Latn.xml", + "orientation": "ltr", + "lang": "it", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_it_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Italiano / Italian (combining accents) with numerals and punctuation", + "file": "autoConverted/alphabet.italiano.italian.combining.accents.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "it", + "script": "Latn", + "script_name": "Latin", + "training": "training_italianC_IT.txt", + "palette": "Default", + "conversion": "none", + "chars": 108, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Italiano / Italian - limited punctuation", + "file": "autoConverted/alphabet.italiano.italian.limited.punctuation.xml", + "orientation": "ltr", + "lang": "it", + "script": "Latn", + "script_name": "Latin", + "training": "training_italian_IT.txt", + "palette": "Default", + "conversion": "none", + "chars": 84, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.italian.xml"] + }, + { + "id": "Italiano / Italian with lots of punctuation", + "file": "autoConverted/alphabet.italiano.italian.with.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "it", + "script": "Latn", + "script_name": "Latin", + "training": "training_italian_IT.txt", + "palette": "Default", + "conversion": "none", + "chars": 113, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Jane Austen English - UC, LC, limited punctuation", + "file": "autoConverted/alphabet.jane.austen.english.uc.lc.limited.punctuation.xml", + "orientation": "ltr", + "lang": "en", + "script": "Latn", + "script_name": "Latin", + "training": "training_emma_GB.txt", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Austen.xml"] + }, + { + "id": "Jane Austen English Lower Case", + "file": "autoConverted/alphabet.jane.austen.english.lower.case.xml", + "orientation": "ltr", + "lang": "en", + "script": null, + "script_name": null, + "training": "training_emmaLC_GB.txt", + "palette": "Default", + "conversion": "none", + "chars": 29, + "groups": ["Lower case Latin letters", "Punctuation", "paragraphSpace"], + "source": "worldalphabets" + }, + { + "id": "Japanese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.japanese.ja-Hira.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Hira", + "script_name": "Hiragana", + "training": "training_wa_ja_Hira.txt", + "palette": "Default", + "conversion": "none", + "chars": 97, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 46, + "variants": [ + "autoConverted/alphabet.wa.japanese.ja-Jpan.xml", + "autoConverted/alphabet.wa.japanese.ja-Kana.xml" + ] + }, + { + "id": "Japanese Canna", + "file": "autoConverted/alphabet.japanese.canna.xml", + "orientation": "ltr", + "lang": "ja", + "script": "Kana", + "script_name": "Katakana", + "training": "training_canna_JP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 310, + "groups": [ + "Hiragana", + "A Gyo", + "Small A Gyo", + "KA Gyo", + "GA Gyo", + "SA Gyo", + "TA Gyo", + "Small TA Gyo", + "DA Gyo", + "NA Gyo", + "HA Gyo", + "BA Gyo", + "PA Gyo", + "MA Gyo", + "YA Gyo", + "Small YA Gyo", + "RA Gyo", + "WA Gyo", + "Punctuation", + "katakana", + "Numerals", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.japanese.canna.xml"] + }, + { + "id": "Javanese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.javanese.jv-Latn.xml", + "orientation": "ltr", + "lang": "jv", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Jola-Fonyi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.jolafonyi.dyo-Latn.xml", + "orientation": "ltr", + "lang": "dyo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kabuverdianu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kabuverdianu.kea-Latn.xml", + "orientation": "ltr", + "lang": "kea", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kabyle (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kabyle.kab-Latn.xml", + "orientation": "ltr", + "lang": "kab", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kaingang (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kaingang.kgp-Latn.xml", + "orientation": "ltr", + "lang": "kgp", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kako (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kako.kkj-Latn.xml", + "orientation": "ltr", + "lang": "kkj", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 101, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kalaallisut (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kalaallisut.kl-Latn.xml", + "orientation": "ltr", + "lang": "kl", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kamba (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kamba.kam-Latn.xml", + "orientation": "ltr", + "lang": "kam", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kangri (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kangri.xnr-Deva.xml", + "orientation": "ltr", + "lang": "xnr", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 115, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 47 + }, + { + "id": "Kannada (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kannada.kn-Knda.xml", + "orientation": "ltr", + "lang": "kn", + "script": "Knda", + "script_name": "Kannada", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 109, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 52 + }, + { + "id": "Kannada with punctuation and numerals", + "file": "autoConverted/alphabet.kannada.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "kn", + "script": "Knda", + "script_name": "Kannada", + "training": "training_Kannada_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 113, + "groups": [ + "KANNADA letters", + "Kannada vowel signs and other marks", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Kannada.xml"] + }, + { + "id": "Kara (Korea) (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kara.korea.zra-Latn.xml", + "orientation": "ltr", + "lang": "zra", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 101, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 48 + }, + { + "id": "Kara-Kalpak (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.karakalpak.kaa-Cyrl.xml", + "orientation": "ltr", + "lang": "kaa", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 97, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.karakalpak.kaa-Latn.xml"] + }, + { + "id": "Kashmiri (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kashmiri.ks-Arab.xml", + "orientation": "rtl", + "lang": "ks", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 97, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 46, + "variants": ["autoConverted/alphabet.wa.kashmiri.ks-Deva.xml"] + }, + { + "id": "Kazakh (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kazakh.kk-Cyrl.xml", + "orientation": "ltr", + "lang": "kk", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kazakh / Қазақ with punctuation and numerals", + "file": "autoConverted/alphabet.kazakh..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "kk", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_kazakh_KZ.txt", + "palette": "Default", + "conversion": "none", + "chars": 278, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.kazakh.xml"] + }, + { + "id": "Kenyang (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kenyang.ken-Latn.xml", + "orientation": "ltr", + "lang": "ken", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 91, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Khmer (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.khmer.km-Khmr.xml", + "orientation": "ltr", + "lang": "km", + "script": "Khmr", + "script_name": "Khmer", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 99, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 47 + }, + { + "id": "Kikuyu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kikuyu.ki-Latn.xml", + "orientation": "ltr", + "lang": "ki", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 45, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kinyarwanda (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kinyarwanda.rw-Latn.xml", + "orientation": "ltr", + "lang": "rw", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kirghiz / Кыргыз with punctuation and numerals", + "file": "autoConverted/alphabet.kirghiz..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ky", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_kirghiz_KG.txt", + "palette": "Default", + "conversion": "none", + "chars": 278, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.kirghiz.xml"] + }, + { + "id": "Kirundi (Rundi) with numerals and punctuation", + "file": "autoConverted/alphabet.kirundi.rundi.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "rn", + "script": "Latn", + "script_name": "Latin", + "training": "training_kirundi_BI.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 100, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.kirundi.xml"] + }, + { + "id": "Konkani (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.konkani.kok-Deva.xml", + "orientation": "ltr", + "lang": "kok", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 115, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 50, + "variants": ["autoConverted/alphabet.wa.konkani.kok-Latn.xml"] + }, + { + "id": "Korean (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.korean.ko-Hang.xml", + "orientation": "ltr", + "lang": "ko", + "script": "Hang", + "script_name": "Hangul", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 24, + "variants": ["autoConverted/alphabet.wa.korean.ko-Kore.xml"] + }, + { + "id": "Korean 한국어 2350 syllables (Nested)", + "file": "autoConverted/alphabet.korean.2350.syllables.nested.xml", + "orientation": "ltr", + "lang": "ko", + "script": "Hang", + "script_name": "Hangul", + "training": "training_korean2350_KR.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 2003, + "groups": ["Korean syllables", "Korean trailing consonants", "paragraphSpace"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 26, + "variants": ["oldAlphabets/alphabet.koreanNested.xml"] + }, + { + "id": "Koyra Chiini (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.koyra.chiini.khq-Latn.xml", + "orientation": "ltr", + "lang": "khq", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Koyraboro Senni (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.koyraboro.senni.ses-Latn.xml", + "orientation": "ltr", + "lang": "ses", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kpelle (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kpelle.kpe-Latn.xml", + "orientation": "ltr", + "lang": "kpe", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kuku (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kuku.ukv-Latn.xml", + "orientation": "ltr", + "lang": "ukv", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kurdish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kurdish.ku-Latn.xml", + "orientation": "ltr", + "lang": "ku", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kurdî / Kurdish with punctuation and numerals", + "file": "autoConverted/alphabet.kurd.kurdish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ku", + "script": "Latn", + "script_name": "Latin", + "training": "training_kurdish_IQ.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.kurdish.xml"] + }, + { + "id": "Kuvi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kuvi.kxv-Orya.xml", + "orientation": "ltr", + "lang": "kxv", + "script": "Orya", + "script_name": "Oriya", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 29 + }, + { + "id": "Kwasio (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kwasio.nmg-Latn.xml", + "orientation": "ltr", + "lang": "nmg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 121, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kyrgyz (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kyrgyz.ky-Cyrl.xml", + "orientation": "ltr", + "lang": "ky", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Kʼicheʼ (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.kʼicheʼ.quc-Latn.xml", + "orientation": "ltr", + "lang": "quc", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Ladin (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ladin.lld-Latn.xml", + "orientation": "ltr", + "lang": "lld", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 97, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lakota (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lakota.lkt-Latn.xml", + "orientation": "ltr", + "lang": "lkt", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Langi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.langi.lag-Latn.xml", + "orientation": "ltr", + "lang": "lag", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lao", + "file": "autoConverted/alphabet.lao.xml", + "orientation": "ltr", + "lang": "lo", + "script": "Laoo", + "script_name": "Lao", + "training": "training_lao_LA.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 67, + "groups": [ + "lao tones (combining)", + "Lao letters", + "lao vowels (combining)", + "Punctuation?", + "Numbers", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.lao.xml"] + }, + { + "id": "Lao (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lao.lo-Laoo.xml", + "orientation": "ltr", + "lang": "lo", + "script": "Laoo", + "script_name": "Lao", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 85, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 40 + }, + { + "id": "Latgalian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.latgalian.ltg-Latn.xml", + "orientation": "ltr", + "lang": "ltg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 85, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Latin (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.latin.la-Latn.xml", + "orientation": "ltr", + "lang": "la", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Latin (classical) with numerals and punctuation", + "file": "autoConverted/alphabet.latin.classical.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "la", + "script": "Latn", + "script_name": "Latin", + "training": "training_latin_XX.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 101, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.latin.xml"] + }, + { + "id": "Latin ISO-8859 (combining accents) with numerals and punctuation", + "file": "autoConverted/alphabet.latin.iso8859.combining.accents.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "la", + "script": "Latn", + "script_name": "Latin", + "training": "training_frenchC_FR.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 144, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "LC non-ascii Characters", + "UC non-ascii Characters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.iso8859.xml"] + }, + { + "id": "Latvian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.latvian.lv-Latn.xml", + "orientation": "ltr", + "lang": "lv", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Latviešu / Latvian with punctuation and numerals", + "file": "autoConverted/alphabet.latvieu.latvian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "lv", + "script": "Latn", + "script_name": "Latin", + "training": "training_latvian_LV.txt", + "palette": "Default", + "conversion": "none", + "chars": 122, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.latvian.xml"] + }, + { + "id": "Lepcha (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lepcha.lep-Lepc.xml", + "orientation": "ltr", + "lang": "lep", + "script": "Lepc", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 123, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 59 + }, + { + "id": "Lietuvos / Lithuanian with punctuation and numerals", + "file": "autoConverted/alphabet.lietuvos.lithuanian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "lt", + "script": "Latn", + "script_name": "Latin", + "training": "training_lithuanian_LT.txt", + "palette": "Default", + "conversion": "none", + "chars": 114, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.lithuanian.xml"] + }, + { + "id": "Ligurian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ligurian.lij-Latn.xml", + "orientation": "ltr", + "lang": "lij", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 107, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Limbu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.limbu.lif-Deva.xml", + "orientation": "ltr", + "lang": "lif", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 117, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 44 + }, + { + "id": "Lingala (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lingala.ln-Latn.xml", + "orientation": "ltr", + "lang": "ln", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lisu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lisu.lis-Lisu.xml", + "orientation": "ltr", + "lang": "lis", + "script": "Lisu", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 85, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 40 + }, + { + "id": "Literary Chinese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.literary.chinese.lzh-Hans.xml", + "orientation": "ltr", + "lang": "lzh", + "script": "Hans", + "script_name": "Han", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 4425, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 2210 + }, + { + "id": "Lithuanian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lithuanian.lt-Latn.xml", + "orientation": "ltr", + "lang": "lt", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lojban (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lojban.jbo-Latn.xml", + "orientation": "ltr", + "lang": "jbo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lombard (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lombard.lmo-Latn.xml", + "orientation": "ltr", + "lang": "lmo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Low German (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.low.german.nds-Latn.xml", + "orientation": "ltr", + "lang": "nds", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lower Sorbian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lower.sorbian.dsb-Latn.xml", + "orientation": "ltr", + "lang": "dsb", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Luba-Katanga (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lubakatanga.lu-Latn.xml", + "orientation": "ltr", + "lang": "lu", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lule Sami (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.lule.sami.smj-Latn.xml", + "orientation": "ltr", + "lang": "smj", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Luo (Kenya and Tanzania) (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.luo.kenya.and.tanzania.luo-Latn.xml", + "orientation": "ltr", + "lang": "luo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Luxembourgish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.luxembourgish.lb-Latn.xml", + "orientation": "ltr", + "lang": "lb", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Luyia (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.luyia.luy-Latn.xml", + "orientation": "ltr", + "lang": "luy", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Lëtzebuergesch / Luxembourgish with punctuation and numerals", + "file": "autoConverted/alphabet.ltzebuergesch.luxembourgish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "lb", + "script": "Latn", + "script_name": "Latin", + "training": "training_luxembourgish_LU.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.luxembourgish.xml"] + }, + { + "id": "Macedonian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.macedonian.mk-Cyrl.xml", + "orientation": "ltr", + "lang": "mk", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Macedonian / Македонски with punctuation and numerals", + "file": "autoConverted/alphabet.macedonian..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "mk", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_macedonian_MK.txt", + "palette": "Default", + "conversion": "none", + "chars": 276, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.macedonian.xml"] + }, + { + "id": "Magyar / Hungarian / nagybetűssel, rövid", + "file": "autoConverted/alphabet.magyar.hungarian.nagybetssel.rvid.xml", + "orientation": "ltr", + "lang": "hu", + "script": "Latn", + "script_name": "Latin", + "training": "training_hungarian_HU.txt", + "palette": "Default", + "conversion": "none", + "chars": 114, + "groups": [ + "Lower case Hungarian letters, short", + "Upper case Hungarian letters, short", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.hungarian.xml"] + }, + { + "id": "Magyar, kisbetűs, rövid / Hungarian lowercase only", + "file": "autoConverted/alphabet.magyar.kisbets.rvid.hungarian.lowercase.only.xml", + "orientation": "ltr", + "lang": "hu", + "script": "Latn", + "script_name": "Latin", + "training": "training_hungarian_HU.txt", + "palette": "Default", + "conversion": "none", + "chars": 37, + "groups": ["Lower case Hungarian letters", "paragraphSpace"], + "source": "worldalphabets" + }, + { + "id": "Mainstream Kenyah (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mainstream.kenyah.xkl-Latn.xml", + "orientation": "ltr", + "lang": "xkl", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Maithili (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.maithili.mai-Deva.xml", + "orientation": "ltr", + "lang": "mai", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 32 + }, + { + "id": "Makhuwa (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.makhuwa.vmw-Latn.xml", + "orientation": "ltr", + "lang": "vmw", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Makhuwa-Meetto (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.makhuwameetto.mgh-Latn.xml", + "orientation": "ltr", + "lang": "mgh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Makonde (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.makonde.kde-Latn.xml", + "orientation": "ltr", + "lang": "kde", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Malagasy (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.malagasy.mg-Latn.xml", + "orientation": "ltr", + "lang": "mg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Malay (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.malay.ms-Latn.xml", + "orientation": "ltr", + "lang": "ms", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Malayalam (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.malayalam.ml-Mlym.xml", + "orientation": "ltr", + "lang": "ml", + "script": "Mlym", + "script_name": "Malayalam", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 103, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 49 + }, + { + "id": "Malayalam with punctuation and numerals", + "file": "autoConverted/alphabet.malayalam.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ms", + "script": "Mlym", + "script_name": "Malayalam", + "training": "training_Malayalam_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "MALAYALAM letters", + "Vowels and other signs", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Malayalam.xml"] + }, + { + "id": "Maltese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.maltese.mt-Latn.xml", + "orientation": "ltr", + "lang": "mt", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Malti / Maltese with punctuation and numerals", + "file": "autoConverted/alphabet.malti.maltese.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "mt", + "script": "Latn", + "script_name": "Latin", + "training": "training_maltese_MT.txt", + "palette": "Default", + "conversion": "none", + "chars": 104, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.maltese.xml"] + }, + { + "id": "Mandaic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mandaic.mid-Latn.xml", + "orientation": "ltr", + "lang": "mid", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 29 + }, + { + "id": "Mandarin (simp) by Pinyin, tone after first vowel", + "file": "autoConverted/alphabet.mandarin.simp.by.pinyin.tone.after.first.vowel.xml", + "orientation": "ltr", + "lang": "zh-Hans", + "script": "Hani", + "script_name": "Han", + "training": "training_spyNew.txt", + "palette": "European/Asian", + "conversion": "mandarin", + "chars": 7720, + "groups": [ + "ā", + "āi", + "ān", + "āng", + "āo", + "á", + "ái", + "án", + "áng", + "áo", + "ǎ", + "ǎi", + "ǎn", + "ǎo", + "à", + "ài", + "àn", + "àng", + "ào", + "å", + "b", + "bā", + "bāi", + "bān", + "bāng", + "bāo", + "bá", + "bái", + "báo", + "bǎ", + "bǎi", + "bǎn", + "bǎng", + "bǎo", + "bà", + "bài", + "bàn", + "bàng", + "bào", + "ba", + "bē", + "bēi", + "bēn", + "bēng", + "bé", + "bén", + "béng", + "bě", + "běi", + "běn", + "běng", + "bè", + "bèi", + "bèn", + "bèng", + "be", + "bei", + "bī", + "bīa", + "bīan", + "bīao", + "bīe", + "bīn", + "bīng", + "bí", + "bíe", + "bǐ", + "bǐa", + "bǐan", + "bǐao", + "bǐe", + "bǐn", + "bǐng", + "bì", + "bìa", + "bìan", + "bìao", + "bìe", + "bìn", + "bìng", + "bō", + "bó", + "bǒ", + "bò", + "bo", + "bū", + "bú", + "bǔ", + "bù", + "c", + "cā", + "cāi", + "cān", + "cāng", + "cāo", + "cá", + "cái", + "cán", + "cáng", + "cáo", + "cǎ", + "cǎi", + "cǎn", + "cǎo", + "cà", + "cài", + "càn", + "cào", + "cē", + "cēn", + "cēng", + "cé", + "cén", + "céng", + "cè", + "cèn", + "cèng", + "ch", + "chā", + "chāi", + "chān", + "chāng", + "chāo", + "chá", + "chái", + "chán", + "cháng", + "cháo", + "chǎ", + "chǎn", + "chǎng", + "chǎo", + "chà", + "chài", + "chàn", + "chàng", + "chào", + "chē", + "chēn", + "chēng", + "ché", + "chén", + "chéng", + "chě", + "chěn", + "chěng", + "chè", + "chèn", + "chèng", + "chī", + "chí", + "chǐ", + "chì", + "chō", + "chōn", + "chōng", + "chōu", + "chó", + "chón", + "chóng", + "chóu", + "chǒ", + "chǒn", + "chǒng", + "chǒu", + "chò", + "chòn", + "chòng", + "chū", + "chūa", + "chūai", + "chūan", + "chūang", + "chūi", + "chūn", + "chūo", + "chú", + "chúa", + "chúan", + "chúang", + "chúi", + "chún", + "chǔ", + "chǔa", + "chǔai", + "chǔan", + "chǔang", + "chǔn", + "chù", + "chùa", + "chùai", + "chùan", + "chùang", + "chùo", + "cī", + "cí", + "cǐ", + "cì", + "cō", + "cōn", + "cōng", + "có", + "cón", + "cóng", + "cò", + "còu", + "cū", + "cūa", + "cūan", + "cūi", + "cūn", + "cūo", + "cú", + "cúa", + "cúan", + "cún", + "cúo", + "cǔ", + "cǔi", + "cǔn", + "cǔo", + "cù", + "cùa", + "cùan", + "cùi", + "cùn", + "cùo", + "d", + "dā", + "dāi", + "dān", + "dāng", + "dāo", + "dá", + "dǎ", + "dǎi", + "dǎn", + "dǎng", + "dǎo", + "dà", + "dài", + "dàn", + "dàng", + "dào", + "da", + "dē", + "dēn", + "dēng", + "dé", + "dě", + "děi", + "děn", + "děng", + "dè", + "dèn", + "dèng", + "de", + "dī", + "dīa", + "dīan", + "dīao", + "dīe", + "dīn", + "dīng", + "dīu", + "dí", + "díe", + "dǐ", + "dǐa", + "dǐan", + "dǐao", + "dǐn", + "dǐng", + "dì", + "dìa", + "dìan", + "dìao", + "dìn", + "dìng", + "dō", + "dōn", + "dōng", + "dōu", + "dǒ", + "dǒn", + "dǒng", + "dǒu", + "dò", + "dòn", + "dòng", + "dòu", + "dū", + "dūa", + "dūan", + "dūi", + "dūn", + "dūo", + "dú", + "dúo", + "dǔ", + "dǔa", + "dǔan", + "dǔn", + "dǔo", + "dù", + "dùa", + "dùan", + "dùi", + "dùn", + "dùo", + "ē", + "ēn", + "é", + "éi", + "én", + "ér", + "ě", + "ěi", + "ěn", + "ěr", + "è", + "èi", + "èn", + "èr", + "f", + "fā", + "fān", + "fāng", + "fá", + "fán", + "fáng", + "fǎ", + "fǎn", + "fǎng", + "fà", + "fàn", + "fàng", + "fē", + "fēi", + "fēn", + "fēng", + "fé", + "féi", + "fén", + "féng", + "fě", + "fěi", + "fěn", + "fěng", + "fè", + "fèi", + "fèn", + "fèng", + "fó", + "fǒ", + "fǒu", + "fū", + "fú", + "fǔ", + "fù", + "g", + "gā", + "gāi", + "gān", + "gāng", + "gāo", + "gá", + "gǎ", + "gǎi", + "gǎn", + "gǎng", + "gǎo", + "gà", + "gài", + "gàn", + "gàng", + "gào", + "gē", + "gēn", + "gēng", + "gé", + "gén", + "gě", + "gěi", + "gěn", + "gěng", + "gè", + "gèn", + "gèng", + "gō", + "gōn", + "gōng", + "gōu", + "gǒ", + "gǒn", + "gǒng", + "gǒu", + "gò", + "gòn", + "gòng", + "gòu", + "gū", + "gūa", + "gūai", + "gūan", + "gūang", + "gūi", + "gūo", + "gú", + "gúo", + "gǔ", + "gǔa", + "gǔai", + "gǔan", + "gǔang", + "gǔi", + "gǔn", + "gǔo", + "gù", + "gùa", + "gùai", + "gùan", + "gùang", + "gùi", + "gùn", + "gùo", + "h", + "hā", + "hāi", + "hān", + "hāng", + "hāo", + "há", + "hái", + "hán", + "háng", + "háo", + "hǎ", + "hǎi", + "hǎn", + "hǎo", + "hà", + "hài", + "hàn", + "hàng", + "hào", + "hē", + "hēi", + "hēn", + "hēng", + "hé", + "hén", + "héng", + "hě", + "hěn", + "hè", + "hèn", + "hèng", + "hn", + "hng", + "hō", + "hōn", + "hōng", + "hó", + "hón", + "hóng", + "hóu", + "hǒ", + "hǒn", + "hǒng", + "hǒu", + "hò", + "hòn", + "hòng", + "hòu", + "hū", + "hūa", + "hūan", + "hūang", + "hūi", + "hūn", + "hūo", + "hú", + "húa", + "húai", + "húan", + "húang", + "húi", + "hún", + "húo", + "hǔ", + "hǔa", + "hǔan", + "hǔang", + "hǔi", + "hǔo", + "hù", + "hùa", + "hùai", + "hùan", + "hùang", + "hùi", + "hùn", + "hùo", + "hu", + "hua", + "huai", + "j", + "jī", + "jīa", + "jīan", + "jīang", + "jīao", + "jīe", + "jīn", + "jīng", + "jīo", + "jīon", + "jīong", + "jīu", + "jí", + "jía", + "jían", + "jíao", + "jíe", + "jǐ", + "jǐa", + "jǐan", + "jǐang", + "jǐao", + "jǐe", + "jǐn", + "jǐng", + "jǐo", + "jǐon", + "jǐong", + "jǐu", + "jì", + "jìa", + "jìan", + "jìang", + "jìao", + "jìe", + "jìn", + "jìng", + "jìu", + "ji", + "jie", + "jū", + "jūa", + "jūan", + "jūe", + "jūn", + "jú", + "júe", + "jǔ", + "jǔa", + "jǔan", + "jǔe", + "jù", + "jùa", + "jùan", + "jùe", + "jùn", + "k", + "kā", + "kāi", + "kān", + "kāng", + "kāo", + "ká", + "kán", + "káng", + "kǎ", + "kǎi", + "kǎn", + "kǎo", + "kà", + "kài", + "kàn", + "kàng", + "kào", + "kē", + "kēn", + "kēng", + "ké", + "kě", + "kěn", + "kè", + "kèn", + "kō", + "kōn", + "kōng", + "kōu", + "kǒ", + "kǒn", + "kǒng", + "kǒu", + "kò", + "kòn", + "kòng", + "kòu", + "kū", + "kūa", + "kūan", + "kūang", + "kūi", + "kūn", + "kú", + "kúa", + "kúan", + "kúang", + "kúi", + "kǔ", + "kǔa", + "kǔai", + "kǔan", + "kǔang", + "kǔi", + "kǔn", + "kù", + "kùa", + "kùai", + "kùan", + "kùang", + "kùi", + "kùn", + "kùo", + "l", + "lā", + "lān", + "lāng", + "lāo", + "lá", + "lái", + "lán", + "láng", + "láo", + "lǎ", + "lǎn", + "lǎng", + "lǎo", + "là", + "lài", + "làn", + "làng", + "lào", + "la", + "lē", + "lēi", + "lēn", + "lēng", + "lé", + "léi", + "lén", + "léng", + "lě", + "lěi", + "lěn", + "lěng", + "lè", + "lèi", + "lèn", + "lèng", + "le", + "lei", + "lī", + "līa", + "līao", + "līe", + "līn", + "līu", + "lí", + "lía", + "lían", + "líang", + "líao", + "lín", + "líng", + "líu", + "lǐ", + "lǐa", + "lǐan", + "lǐang", + "lǐao", + "lǐe", + "lǐn", + "lǐng", + "lǐu", + "lì", + "lìa", + "lìan", + "lìang", + "lìao", + "lìe", + "lìn", + "lìng", + "lìu", + "li", + "lie", + "lō", + "lōn", + "lōng", + "lōu", + "ló", + "lón", + "lóng", + "lóu", + "lǒ", + "lǒn", + "lǒng", + "lǒu", + "lò", + "lòn", + "lòng", + "lòu", + "lo", + "lou", + "lū", + "lūn", + "lūo", + "lú", + "lúa", + "lúan", + "lún", + "lúo", + "lǔ", + "lǔa", + "lǔan", + "lǔo", + "lù", + "lùa", + "lùan", + "lùn", + "lùo", + "lu", + "lǘ", + "lǚ", + "lǚe", + "lǜ", + "lǜe", + "ḿ", + "m", + "mā", + "mān", + "māo", + "má", + "mái", + "mán", + "máng", + "máo", + "mǎ", + "mǎi", + "mǎn", + "mǎng", + "mǎo", + "mà", + "mài", + "màn", + "mào", + "ma", + "mē", + "mēn", + "mēng", + "mé", + "méi", + "mén", + "méng", + "mě", + "měi", + "měn", + "měng", + "mè", + "mèi", + "mèn", + "mèng", + "me", + "men", + "mī", + "mīa", + "mīao", + "mīe", + "mí", + "mía", + "mían", + "míao", + "mín", + "míng", + "mǐ", + "mǐa", + "mǐan", + "mǐao", + "mǐn", + "mǐng", + "mì", + "mìa", + "mìan", + "mìao", + "mìe", + "mìn", + "mìng", + "mìu", + "mō", + "mōu", + "mó", + "móu", + "mǒ", + "mǒu", + "mò", + "mú", + "mǔ", + "mù", + "n", + "nā", + "nān", + "nāng", + "nāo", + "ná", + "nán", + "náng", + "náo", + "nǎ", + "nǎi", + "nǎn", + "nǎng", + "nǎo", + "nà", + "nài", + "nàn", + "nào", + "na", + "né", + "nén", + "néng", + "ně", + "něi", + "nè", + "nèi", + "nèn", + "ne", + "nī", + "nīa", + "nīan", + "nīe", + "nīu", + "ní", + "nía", + "nían", + "níang", + "nín", + "níng", + "níu", + "nǐ", + "nǐa", + "nǐan", + "nǐao", + "nǐn", + "nǐng", + "nǐu", + "nì", + "nìa", + "nìan", + "nìang", + "nìao", + "nìe", + "nìn", + "nìng", + "nìu", + "nó", + "nón", + "nóng", + "nò", + "nòn", + "nòng", + "nòu", + "nú", + "núo", + "nǔ", + "nǔa", + "nǔan", + "nù", + "nùo", + "nǚ", + "nǜ", + "nǜe", + "ō", + "ōu", + "ó", + "ǒ", + "ǒu", + "ò", + "òu", + "p", + "pā", + "pāi", + "pān", + "pāng", + "pāo", + "pá", + "pái", + "pán", + "páng", + "páo", + "pǎ", + "pǎi", + "pǎn", + "pǎng", + "pǎo", + "pà", + "pài", + "pàn", + "pàng", + "pào", + "pē", + "pēi", + "pēn", + "pēng", + "pé", + "péi", + "pén", + "péng", + "pě", + "pěn", + "pěng", + "pè", + "pèi", + "pèn", + "pèng", + "pī", + "pīa", + "pīan", + "pīao", + "pīe", + "pīn", + "pīng", + "pí", + "pía", + "pían", + "píao", + "pín", + "píng", + "pǐ", + "pǐa", + "pǐan", + "pǐao", + "pǐe", + "pǐn", + "pì", + "pìa", + "pìan", + "pìao", + "pìn", + "pō", + "pōu", + "pó", + "póu", + "pǒ", + "pǒu", + "pò", + "pū", + "pú", + "pǔ", + "pù", + "q", + "qī", + "qīa", + "qīan", + "qīang", + "qīao", + "qīe", + "qīn", + "qīng", + "qīu", + "qí", + "qía", + "qían", + "qíang", + "qíao", + "qíe", + "qín", + "qíng", + "qío", + "qíon", + "qíong", + "qíu", + "qǐ", + "qǐa", + "qǐan", + "qǐang", + "qǐao", + "qǐe", + "qǐn", + "qǐng", + "qǐu", + "qì", + "qìa", + "qìan", + "qìang", + "qìao", + "qìe", + "qìn", + "qìng", + "qi", + "qū", + "qūa", + "qūan", + "qūe", + "qūn", + "qú", + "qúa", + "qúan", + "qúe", + "qún", + "qǔ", + "qǔa", + "qǔan", + "qù", + "qùa", + "qùan", + "qùe", + "qu", + "r", + "rā", + "rān", + "rāng", + "rá", + "rán", + "ráng", + "ráo", + "rǎ", + "rǎn", + "rǎng", + "rǎo", + "rà", + "ràn", + "ràng", + "ra", + "rao", + "rē", + "rēn", + "rēng", + "ré", + "rén", + "réng", + "rě", + "rěn", + "rè", + "rèn", + "rì", + "ró", + "rón", + "róng", + "róu", + "rǒ", + "rǒn", + "rǒng", + "rò", + "ròu", + "rú", + "rúi", + "rǔ", + "rǔa", + "rǔan", + "rǔi", + "rù", + "rùi", + "rùn", + "rùo", + "s", + "sā", + "sāi", + "sān", + "sāng", + "sāo", + "sǎ", + "sǎn", + "sǎng", + "sǎo", + "sà", + "sài", + "sàn", + "sàng", + "sào", + "sē", + "sēn", + "sēng", + "sè", + "sh", + "shā", + "shāi", + "shān", + "shāng", + "shāo", + "shá", + "sháo", + "shǎ", + "shǎi", + "shǎn", + "shǎng", + "shǎo", + "shà", + "shài", + "shàn", + "shàng", + "shào", + "sha", + "shan", + "shang", + "shē", + "shēn", + "shēng", + "shé", + "shéi", + "shén", + "shéng", + "shě", + "shěn", + "shěng", + "shè", + "shèn", + "shèng", + "shī", + "shí", + "shǐ", + "shì", + "shi", + "shō", + "shōu", + "shó", + "shóu", + "shǒ", + "shǒu", + "shò", + "shòu", + "shū", + "shūa", + "shūai", + "shūan", + "shūang", + "shūo", + "shú", + "shúi", + "shǔ", + "shǔa", + "shǔai", + "shǔan", + "shǔang", + "shǔi", + "shǔn", + "shù", + "shùa", + "shùai", + "shùan", + "shùi", + "shùn", + "shùo", + "sī", + "sǐ", + "sì", + "sō", + "sōn", + "sōng", + "sōu", + "sǒ", + "sǒn", + "sǒng", + "sǒu", + "sò", + "sòn", + "sòng", + "sòu", + "sū", + "sūa", + "sūan", + "sūi", + "sūn", + "sūo", + "sú", + "súi", + "sǔ", + "sǔi", + "sǔn", + "sǔo", + "sù", + "sùa", + "sùan", + "sùi", + "t", + "tā", + "tāi", + "tān", + "tāng", + "tāo", + "tá", + "tái", + "tán", + "táng", + "táo", + "tǎ", + "tǎn", + "tǎng", + "tǎo", + "tà", + "tài", + "tàn", + "tàng", + "tào", + "té", + "tén", + "téng", + "tè", + "tī", + "tīa", + "tīan", + "tīao", + "tīe", + "tīn", + "tīng", + "tí", + "tía", + "tían", + "tíao", + "tín", + "tíng", + "tǐ", + "tǐa", + "tǐan", + "tǐao", + "tǐe", + "tǐn", + "tǐng", + "tì", + "tìa", + "tìan", + "tìao", + "tìe", + "tìn", + "tìng", + "tō", + "tōn", + "tōng", + "tōu", + "tó", + "tón", + "tóng", + "tóu", + "tǒ", + "tǒn", + "tǒng", + "tǒu", + "tò", + "tòn", + "tòng", + "tòu", + "tū", + "tūa", + "tūan", + "tūi", + "tūn", + "tūo", + "tú", + "túa", + "túan", + "túi", + "tún", + "túo", + "tǔ", + "tǔa", + "tǔan", + "tǔi", + "tǔn", + "tǔo", + "tù", + "tùa", + "tùan", + "tùi", + "tùn", + "tùo", + "w", + "wā", + "wāi", + "wān", + "wāng", + "wá", + "wán", + "wáng", + "wǎ", + "wǎi", + "wǎn", + "wǎng", + "wà", + "wài", + "wàn", + "wàng", + "wa", + "wē", + "wēi", + "wēn", + "wēng", + "wé", + "wéi", + "wén", + "wě", + "wěi", + "wěn", + "wěng", + "wè", + "wèi", + "wèn", + "wèng", + "wō", + "wǒ", + "wò", + "wū", + "wú", + "wǔ", + "wù", + "x", + "xī", + "xīa", + "xīan", + "xīang", + "xīao", + "xīe", + "xīn", + "xīng", + "xīo", + "xīon", + "xīong", + "xīu", + "xí", + "xía", + "xían", + "xíang", + "xíao", + "xíe", + "xín", + "xíng", + "xío", + "xíon", + "xíong", + "xǐ", + "xǐa", + "xǐan", + "xǐang", + "xǐao", + "xǐe", + "xǐn", + "xǐng", + "xǐu", + "xì", + "xìa", + "xìan", + "xìang", + "xìao", + "xìe", + "xìn", + "xìng", + "xìu", + "xū", + "xūa", + "xūan", + "xūe", + "xūn", + "xú", + "xúa", + "xúan", + "xúe", + "xún", + "xǔ", + "xǔa", + "xǔan", + "xǔe", + "xù", + "xùa", + "xùan", + "xùe", + "xùn", + "xu", + "y", + "yā", + "yān", + "yāng", + "yāo", + "yá", + "yán", + "yáng", + "yáo", + "yǎ", + "yǎn", + "yǎng", + "yǎo", + "yà", + "yàn", + "yàng", + "yào", + "ya", + "yē", + "yé", + "yě", + "yè", + "yī", + "yīn", + "yīng", + "yí", + "yín", + "yíng", + "yǐ", + "yǐn", + "yǐng", + "yì", + "yìn", + "yìng", + "yō", + "yōn", + "yōng", + "yōu", + "yó", + "yón", + "yóng", + "yóu", + "yǒ", + "yǒn", + "yǒng", + "yǒu", + "yò", + "yòn", + "yòng", + "yòu", + "yo", + "yū", + "yūa", + "yūan", + "yūe", + "yūn", + "yú", + "yúa", + "yúan", + "yún", + "yǔ", + "yǔa", + "yǔan", + "yǔe", + "yǔn", + "yù", + "yùa", + "yùan", + "yùe", + "yùn", + "z", + "zā", + "zāi", + "zān", + "zāng", + "zāo", + "zá", + "zán", + "záo", + "zǎ", + "zǎi", + "zǎn", + "zǎng", + "zǎo", + "zà", + "zài", + "zàn", + "zàng", + "zào", + "za", + "zan", + "zē", + "zēn", + "zēng", + "zé", + "zéi", + "zě", + "zěn", + "zè", + "zèn", + "zèng", + "zh", + "zhā", + "zhāi", + "zhān", + "zhāng", + "zhāo", + "zhá", + "zhái", + "zháo", + "zhǎ", + "zhǎi", + "zhǎn", + "zhǎng", + "zhǎo", + "zhà", + "zhài", + "zhàn", + "zhàng", + "zhào", + "zhē", + "zhēn", + "zhēng", + "zhé", + "zhě", + "zhěn", + "zhěng", + "zhè", + "zhèi", + "zhèn", + "zhèng", + "zhe", + "zhī", + "zhí", + "zhǐ", + "zhì", + "zhō", + "zhōn", + "zhōng", + "zhōu", + "zhó", + "zhóu", + "zhǒ", + "zhǒn", + "zhǒng", + "zhǒu", + "zhò", + "zhòn", + "zhòng", + "zhòu", + "zhū", + "zhūa", + "zhūai", + "zhūan", + "zhūang", + "zhūi", + "zhūn", + "zhūo", + "zhú", + "zhúo", + "zhǔ", + "zhǔa", + "zhǔai", + "zhǔan", + "zhǔang", + "zhǔn", + "zhù", + "zhùa", + "zhùai", + "zhùan", + "zhùang", + "zhùi", + "zī", + "zǐ", + "zì", + "zi", + "zō", + "zōn", + "zōng", + "zōu", + "zǒ", + "zǒn", + "zǒng", + "zǒu", + "zò", + "zòn", + "zòng", + "zòu", + "zū", + "zūa", + "zūan", + "zūn", + "zūo", + "zú", + "zúo", + "zǔ", + "zǔa", + "zǔan", + "zǔi", + "zǔn", + "zǔo", + "zù", + "zùa", + "zùan", + "zùi", + "zùo", + "Punctuation", + "Roman alphabet and numbers", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 785, + "variants": ["oldAlphabets/alphabet.spyTonesNew.xml"] + }, + { + "id": "Mandarin (simp) by Pinyin, tone last", + "file": "autoConverted/alphabet.mandarin.simp.by.pinyin.tone.last.xml", + "orientation": "ltr", + "lang": "zh-Hans", + "script": "Hani", + "script_name": "Han", + "training": "training_spyNew.txt", + "palette": "European/Asian", + "conversion": "mandarin", + "chars": 7720, + "groups": [ + "a", + "ā", + "á", + "ǎ", + "à", + "å", + "ai", + "āi", + "ái", + "ǎi", + "ài", + "an", + "ān", + "ǎn", + "àn", + "ang", + "āng", + "áng", + "àng", + "ao", + "āo", + "áo", + "ǎo", + "ào", + "b", + "ba", + "bā", + "bá", + "bǎ", + "bà", + "bai", + "bāi", + "bái", + "bǎi", + "bài", + "ban", + "bān", + "bǎn", + "bàn", + "bang", + "bāng", + "bǎng", + "bàng", + "bao", + "bāo", + "báo", + "bǎo", + "bào", + "be", + "bei", + "bēi", + "běi", + "bèi", + "ben", + "bēn", + "běn", + "bèn", + "beng", + "bēng", + "béng", + "běng", + "bèng", + "bi", + "bī", + "bí", + "bǐ", + "bì", + "bia", + "bian", + "bīan", + "bǐan", + "bìan", + "biao", + "bīao", + "bǐao", + "bìao", + "bie", + "bīe", + "bíe", + "bǐe", + "bìe", + "bin", + "bīn", + "bìn", + "bing", + "bīng", + "bǐng", + "bìng", + "bo", + "bō", + "bó", + "bǒ", + "bò", + "bu", + "bū", + "bú", + "bǔ", + "bù", + "c", + "ca", + "cā", + "cǎ", + "cai", + "cāi", + "cái", + "cǎi", + "cài", + "can", + "cān", + "cán", + "cǎn", + "càn", + "cang", + "cāng", + "cáng", + "cao", + "cāo", + "cáo", + "cǎo", + "cào", + "ce", + "cè", + "cen", + "cēn", + "cén", + "ceng", + "cēng", + "céng", + "cèng", + "ch", + "cha", + "chā", + "chá", + "chǎ", + "chà", + "chai", + "chāi", + "chái", + "chài", + "chan", + "chān", + "chán", + "chǎn", + "chàn", + "chang", + "chāng", + "cháng", + "chǎng", + "chàng", + "chao", + "chāo", + "cháo", + "chǎo", + "chào", + "che", + "chē", + "chě", + "chè", + "chen", + "chēn", + "chén", + "chěn", + "chèn", + "cheng", + "chēng", + "chéng", + "chěng", + "chèng", + "chi", + "chī", + "chí", + "chǐ", + "chì", + "cho", + "chon", + "chong", + "chōng", + "chóng", + "chǒng", + "chòng", + "chou", + "chōu", + "chóu", + "chǒu", + "chu", + "chū", + "chú", + "chǔ", + "chù", + "chua", + "chuai", + "chūai", + "chǔai", + "chùai", + "chuan", + "chūan", + "chúan", + "chǔan", + "chùan", + "chuang", + "chūang", + "chúang", + "chǔang", + "chùang", + "chui", + "chūi", + "chúi", + "chun", + "chūn", + "chún", + "chǔn", + "chuo", + "chūo", + "chùo", + "ci", + "cī", + "cí", + "cǐ", + "cì", + "co", + "con", + "cong", + "cōng", + "cóng", + "cou", + "còu", + "cu", + "cū", + "cú", + "cù", + "cua", + "cuan", + "cūan", + "cúan", + "cùan", + "cui", + "cūi", + "cǔi", + "cùi", + "cun", + "cūn", + "cún", + "cǔn", + "cùn", + "cuo", + "cūo", + "cúo", + "cǔo", + "cùo", + "d", + "da", + "dā", + "dá", + "dǎ", + "dà", + "dai", + "dāi", + "dǎi", + "dài", + "dan", + "dān", + "dǎn", + "dàn", + "dang", + "dāng", + "dǎng", + "dàng", + "dao", + "dāo", + "dǎo", + "dào", + "de", + "dé", + "dei", + "děi", + "den", + "deng", + "dēng", + "děng", + "dèng", + "di", + "dī", + "dí", + "dǐ", + "dì", + "dia", + "dǐa", + "dian", + "dīan", + "dǐan", + "dìan", + "diao", + "dīao", + "dǐao", + "dìao", + "die", + "dīe", + "díe", + "din", + "ding", + "dīng", + "dǐng", + "dìng", + "diu", + "dīu", + "do", + "don", + "dong", + "dōng", + "dǒng", + "dòng", + "dou", + "dōu", + "dǒu", + "dòu", + "du", + "dū", + "dú", + "dǔ", + "dù", + "dua", + "duan", + "dūan", + "dǔan", + "dùan", + "dui", + "dūi", + "dùi", + "dun", + "dūn", + "dǔn", + "dùn", + "duo", + "dūo", + "dúo", + "dǔo", + "dùo", + "e", + "ē", + "é", + "ě", + "è", + "ei", + "éi", + "ěi", + "èi", + "en", + "ēn", + "én", + "ěn", + "èn", + "er", + "ér", + "ěr", + "èr", + "f", + "fa", + "fā", + "fá", + "fǎ", + "fà", + "fan", + "fān", + "fán", + "fǎn", + "fàn", + "fang", + "fāng", + "fáng", + "fǎng", + "fàng", + "fe", + "fei", + "fēi", + "féi", + "fěi", + "fèi", + "fen", + "fēn", + "fén", + "fěn", + "fèn", + "feng", + "fēng", + "féng", + "fěng", + "fèng", + "fo", + "fó", + "fou", + "fǒu", + "fu", + "fū", + "fú", + "fǔ", + "fù", + "g", + "ga", + "gā", + "gá", + "gǎ", + "gà", + "gai", + "gāi", + "gǎi", + "gài", + "gan", + "gān", + "gǎn", + "gàn", + "gang", + "gāng", + "gǎng", + "gàng", + "gao", + "gāo", + "gǎo", + "gào", + "ge", + "gē", + "gé", + "gě", + "gè", + "gei", + "gěi", + "gen", + "gēn", + "gén", + "gěn", + "gèn", + "geng", + "gēng", + "gěng", + "gèng", + "go", + "gon", + "gong", + "gōng", + "gǒng", + "gòng", + "gou", + "gōu", + "gǒu", + "gòu", + "gu", + "gū", + "gǔ", + "gù", + "gua", + "gūa", + "gǔa", + "gùa", + "guai", + "gūai", + "gǔai", + "gùai", + "guan", + "gūan", + "gǔan", + "gùan", + "guang", + "gūang", + "gǔang", + "gùang", + "gui", + "gūi", + "gǔi", + "gùi", + "gun", + "gǔn", + "gùn", + "guo", + "gūo", + "gúo", + "gǔo", + "gùo", + "h", + "ha", + "hā", + "há", + "hǎ", + "hà", + "hai", + "hāi", + "hái", + "hǎi", + "hài", + "han", + "hān", + "hán", + "hǎn", + "hàn", + "hang", + "hāng", + "háng", + "hàng", + "hao", + "hāo", + "háo", + "hǎo", + "hào", + "he", + "hē", + "hé", + "hè", + "hei", + "hēi", + "hen", + "hén", + "hěn", + "hèn", + "heng", + "hēng", + "héng", + "hèng", + "hn", + "hng", + "ho", + "hon", + "hong", + "hōng", + "hóng", + "hǒng", + "hòng", + "hou", + "hóu", + "hǒu", + "hòu", + "hu", + "hū", + "hú", + "hǔ", + "hù", + "hua", + "hūa", + "húa", + "hùa", + "huai", + "húai", + "hùai", + "huan", + "hūan", + "húan", + "hǔan", + "hùan", + "huang", + "hūang", + "húang", + "hǔang", + "hùang", + "hui", + "hūi", + "húi", + "hǔi", + "hùi", + "hun", + "hūn", + "hún", + "hùn", + "huo", + "hūo", + "húo", + "hǔo", + "hùo", + "j", + "ji", + "jī", + "jí", + "jǐ", + "jì", + "jia", + "jīa", + "jía", + "jǐa", + "jìa", + "jian", + "jīan", + "jían", + "jǐan", + "jìan", + "jiang", + "jīang", + "jǐang", + "jìang", + "jiao", + "jīao", + "jíao", + "jǐao", + "jìao", + "jie", + "jīe", + "jíe", + "jǐe", + "jìe", + "jin", + "jīn", + "jǐn", + "jìn", + "jing", + "jīng", + "jǐng", + "jìng", + "jio", + "jion", + "jiong", + "jīong", + "jǐong", + "jiu", + "jīu", + "jǐu", + "jìu", + "ju", + "jū", + "jú", + "jǔ", + "jù", + "jua", + "juan", + "jūan", + "jǔan", + "jùan", + "jue", + "jūe", + "júe", + "jǔe", + "jùe", + "jun", + "jūn", + "jùn", + "k", + "ka", + "kā", + "kǎ", + "kai", + "kāi", + "kǎi", + "kài", + "kan", + "kān", + "kǎn", + "kàn", + "kang", + "kāng", + "káng", + "kàng", + "kao", + "kāo", + "kǎo", + "kào", + "ke", + "kē", + "ké", + "kě", + "kè", + "ken", + "kěn", + "kèn", + "keng", + "kēng", + "ko", + "kon", + "kong", + "kōng", + "kǒng", + "kòng", + "kou", + "kōu", + "kǒu", + "kòu", + "ku", + "kū", + "kǔ", + "kù", + "kua", + "kūa", + "kǔa", + "kùa", + "kuai", + "kǔai", + "kùai", + "kuan", + "kūan", + "kǔan", + "kuang", + "kūang", + "kúang", + "kǔang", + "kùang", + "kui", + "kūi", + "kúi", + "kǔi", + "kùi", + "kun", + "kūn", + "kǔn", + "kùn", + "kuo", + "kùo", + "l", + "la", + "lā", + "lá", + "lǎ", + "là", + "lai", + "lái", + "lài", + "lan", + "lán", + "lǎn", + "làn", + "lang", + "lāng", + "láng", + "lǎng", + "làng", + "lao", + "lāo", + "láo", + "lǎo", + "lào", + "le", + "lē", + "lè", + "lei", + "lēi", + "léi", + "lěi", + "lèi", + "len", + "leng", + "lēng", + "léng", + "lěng", + "lèng", + "li", + "lī", + "lí", + "lǐ", + "lì", + "lia", + "lǐa", + "lian", + "lían", + "lǐan", + "lìan", + "liang", + "líang", + "lǐang", + "lìang", + "liao", + "līao", + "líao", + "lǐao", + "lìao", + "lie", + "līe", + "lǐe", + "lìe", + "lin", + "līn", + "lín", + "lǐn", + "lìn", + "ling", + "líng", + "lǐng", + "lìng", + "liu", + "līu", + "líu", + "lǐu", + "lìu", + "lo", + "lon", + "long", + "lōng", + "lóng", + "lǒng", + "lòng", + "lou", + "lōu", + "lóu", + "lǒu", + "lòu", + "lu", + "lū", + "lú", + "lǔ", + "lù", + "lua", + "luan", + "lúan", + "lǔan", + "lùan", + "lue", + "lǚe", + "lǜe", + "lun", + "lūn", + "lún", + "lùn", + "luo", + "lūo", + "lúo", + "lǔo", + "lùo", + "luu", + "lǘ", + "lǚ", + "lǜ", + "m", + "ḿ", + "ma", + "mā", + "má", + "mǎ", + "mà", + "mai", + "mái", + "mǎi", + "mài", + "man", + "mān", + "mán", + "mǎn", + "màn", + "mang", + "máng", + "mǎng", + "mao", + "māo", + "máo", + "mǎo", + "mào", + "me", + "mei", + "méi", + "měi", + "mèi", + "men", + "mēn", + "mén", + "mèn", + "meng", + "mēng", + "méng", + "měng", + "mèng", + "mi", + "mī", + "mí", + "mǐ", + "mì", + "mia", + "mian", + "mían", + "mǐan", + "mìan", + "miao", + "mīao", + "míao", + "mǐao", + "mìao", + "mie", + "mīe", + "mìe", + "min", + "mín", + "mǐn", + "ming", + "míng", + "mǐng", + "mìng", + "miu", + "mìu", + "mo", + "mō", + "mó", + "mǒ", + "mò", + "mou", + "mōu", + "móu", + "mǒu", + "mu", + "mú", + "mǔ", + "mù", + "n", + "na", + "nā", + "ná", + "nǎ", + "nà", + "nai", + "nǎi", + "nài", + "nan", + "nān", + "nán", + "nǎn", + "nàn", + "nang", + "nāng", + "náng", + "nǎng", + "nao", + "nāo", + "náo", + "nǎo", + "nào", + "ne", + "né", + "nè", + "nei", + "něi", + "nèi", + "nen", + "nèn", + "neng", + "néng", + "ni", + "nī", + "ní", + "nǐ", + "nì", + "nia", + "nian", + "nīan", + "nían", + "nǐan", + "nìan", + "niang", + "níang", + "nìang", + "niao", + "nǐao", + "nìao", + "nie", + "nīe", + "nìe", + "nin", + "nín", + "ning", + "níng", + "nǐng", + "nìng", + "niu", + "nīu", + "níu", + "nǐu", + "nìu", + "no", + "non", + "nong", + "nóng", + "nòng", + "nou", + "nòu", + "nu", + "nú", + "nǔ", + "nù", + "nua", + "nuan", + "nǔan", + "nue", + "nǜe", + "nuo", + "núo", + "nùo", + "nuu", + "nǚ", + "nǜ", + "o", + "ō", + "ó", + "ò", + "ou", + "ōu", + "ǒu", + "òu", + "p", + "pa", + "pā", + "pá", + "pà", + "pai", + "pāi", + "pái", + "pǎi", + "pài", + "pan", + "pān", + "pán", + "pàn", + "pang", + "pāng", + "páng", + "pǎng", + "pàng", + "pao", + "pāo", + "páo", + "pǎo", + "pào", + "pe", + "pei", + "pēi", + "péi", + "pèi", + "pen", + "pēn", + "pén", + "pèn", + "peng", + "pēng", + "péng", + "pěng", + "pèng", + "pi", + "pī", + "pí", + "pǐ", + "pì", + "pia", + "pian", + "pīan", + "pían", + "pǐan", + "pìan", + "piao", + "pīao", + "píao", + "pǐao", + "pìao", + "pie", + "pīe", + "pǐe", + "pin", + "pīn", + "pín", + "pǐn", + "pìn", + "ping", + "pīng", + "píng", + "po", + "pō", + "pó", + "pǒ", + "pò", + "pou", + "pōu", + "póu", + "pǒu", + "pu", + "pū", + "pú", + "pǔ", + "pù", + "q", + "qi", + "qī", + "qí", + "qǐ", + "qì", + "qia", + "qīa", + "qǐa", + "qìa", + "qian", + "qīan", + "qían", + "qǐan", + "qìan", + "qiang", + "qīang", + "qíang", + "qǐang", + "qìang", + "qiao", + "qīao", + "qíao", + "qǐao", + "qìao", + "qie", + "qīe", + "qíe", + "qǐe", + "qìe", + "qin", + "qīn", + "qín", + "qǐn", + "qìn", + "qing", + "qīng", + "qíng", + "qǐng", + "qìng", + "qio", + "qion", + "qiong", + "qíong", + "qiu", + "qīu", + "qíu", + "qǐu", + "qu", + "qū", + "qú", + "qǔ", + "qù", + "qua", + "quan", + "qūan", + "qúan", + "qǔan", + "qùan", + "que", + "qūe", + "qúe", + "qùe", + "qun", + "qūn", + "qún", + "r", + "ra", + "ran", + "rán", + "rǎn", + "rang", + "rāng", + "ráng", + "rǎng", + "ràng", + "rao", + "ráo", + "rǎo", + "re", + "rě", + "rè", + "ren", + "rén", + "rěn", + "rèn", + "reng", + "rēng", + "réng", + "ri", + "rì", + "ro", + "ron", + "rong", + "róng", + "rǒng", + "rou", + "róu", + "ròu", + "ru", + "rú", + "rǔ", + "rù", + "rua", + "ruan", + "rǔan", + "rui", + "rúi", + "rǔi", + "rùi", + "run", + "rùn", + "ruo", + "rùo", + "s", + "sa", + "sā", + "sǎ", + "sà", + "sai", + "sāi", + "sài", + "san", + "sān", + "sǎn", + "sàn", + "sang", + "sāng", + "sǎng", + "sàng", + "sao", + "sāo", + "sǎo", + "sào", + "se", + "sè", + "sen", + "sēn", + "seng", + "sēng", + "sh", + "sha", + "shā", + "shá", + "shǎ", + "shà", + "shai", + "shāi", + "shǎi", + "shài", + "shan", + "shān", + "shǎn", + "shàn", + "shang", + "shāng", + "shǎng", + "shàng", + "shao", + "shāo", + "sháo", + "shǎo", + "shào", + "she", + "shē", + "shé", + "shě", + "shè", + "shei", + "shéi", + "shen", + "shēn", + "shén", + "shěn", + "shèn", + "sheng", + "shēng", + "shéng", + "shěng", + "shèng", + "shi", + "shī", + "shí", + "shǐ", + "shì", + "sho", + "shou", + "shōu", + "shóu", + "shǒu", + "shòu", + "shu", + "shū", + "shú", + "shǔ", + "shù", + "shua", + "shūa", + "shǔa", + "shùa", + "shuai", + "shūai", + "shǔai", + "shùai", + "shuan", + "shūan", + "shùan", + "shuang", + "shūang", + "shǔang", + "shui", + "shúi", + "shǔi", + "shùi", + "shun", + "shǔn", + "shùn", + "shuo", + "shūo", + "shùo", + "si", + "sī", + "sǐ", + "sì", + "so", + "son", + "song", + "sōng", + "sǒng", + "sòng", + "sou", + "sōu", + "sǒu", + "sòu", + "su", + "sū", + "sú", + "sù", + "sua", + "suan", + "sūan", + "sùan", + "sui", + "sūi", + "súi", + "sǔi", + "sùi", + "sun", + "sūn", + "sǔn", + "suo", + "sūo", + "sǔo", + "t", + "ta", + "tā", + "tǎ", + "tà", + "tai", + "tāi", + "tái", + "tài", + "tan", + "tān", + "tán", + "tǎn", + "tàn", + "tang", + "tāng", + "táng", + "tǎng", + "tàng", + "tao", + "tāo", + "táo", + "tǎo", + "tào", + "te", + "tè", + "ten", + "teng", + "téng", + "ti", + "tī", + "tí", + "tǐ", + "tì", + "tia", + "tian", + "tīan", + "tían", + "tǐan", + "tìan", + "tiao", + "tīao", + "tíao", + "tǐao", + "tìao", + "tie", + "tīe", + "tǐe", + "tìe", + "tin", + "ting", + "tīng", + "tíng", + "tǐng", + "tìng", + "to", + "ton", + "tong", + "tōng", + "tóng", + "tǒng", + "tòng", + "tou", + "tōu", + "tóu", + "tǒu", + "tòu", + "tu", + "tū", + "tú", + "tǔ", + "tù", + "tua", + "tuan", + "tūan", + "túan", + "tǔan", + "tùan", + "tui", + "tūi", + "túi", + "tǔi", + "tùi", + "tun", + "tūn", + "tún", + "tǔn", + "tùn", + "tuo", + "tūo", + "túo", + "tǔo", + "tùo", + "w", + "wa", + "wā", + "wá", + "wǎ", + "wà", + "wai", + "wāi", + "wǎi", + "wài", + "wan", + "wān", + "wán", + "wǎn", + "wàn", + "wang", + "wāng", + "wáng", + "wǎng", + "wàng", + "we", + "wei", + "wēi", + "wéi", + "wěi", + "wèi", + "wen", + "wēn", + "wén", + "wěn", + "wèn", + "weng", + "wēng", + "wěng", + "wèng", + "wo", + "wō", + "wǒ", + "wò", + "wu", + "wū", + "wú", + "wǔ", + "wù", + "x", + "xi", + "xī", + "xí", + "xǐ", + "xì", + "xia", + "xīa", + "xía", + "xìa", + "xian", + "xīan", + "xían", + "xǐan", + "xìan", + "xiang", + "xīang", + "xíang", + "xǐang", + "xìang", + "xiao", + "xīao", + "xíao", + "xǐao", + "xìao", + "xie", + "xīe", + "xíe", + "xǐe", + "xìe", + "xin", + "xīn", + "xín", + "xìn", + "xing", + "xīng", + "xíng", + "xǐng", + "xìng", + "xio", + "xion", + "xiong", + "xīong", + "xíong", + "xiu", + "xīu", + "xǐu", + "xìu", + "xu", + "xū", + "xú", + "xǔ", + "xù", + "xua", + "xuan", + "xūan", + "xúan", + "xǔan", + "xùan", + "xue", + "xūe", + "xúe", + "xǔe", + "xùe", + "xun", + "xūn", + "xún", + "xùn", + "y", + "ya", + "yā", + "yá", + "yǎ", + "yà", + "yan", + "yān", + "yán", + "yǎn", + "yàn", + "yang", + "yāng", + "yáng", + "yǎng", + "yàng", + "yao", + "yāo", + "yáo", + "yǎo", + "yào", + "ye", + "yē", + "yé", + "yě", + "yè", + "yi", + "yī", + "yí", + "yǐ", + "yì", + "yin", + "yīn", + "yín", + "yǐn", + "yìn", + "ying", + "yīng", + "yíng", + "yǐng", + "yìng", + "yo", + "yō", + "yon", + "yong", + "yōng", + "yóng", + "yǒng", + "yòng", + "you", + "yōu", + "yóu", + "yǒu", + "yòu", + "yu", + "yū", + "yú", + "yǔ", + "yù", + "yua", + "yuan", + "yūan", + "yúan", + "yǔan", + "yùan", + "yue", + "yūe", + "yǔe", + "yùe", + "yun", + "yūn", + "yún", + "yǔn", + "yùn", + "z", + "za", + "zā", + "zá", + "zǎ", + "zai", + "zāi", + "zǎi", + "zài", + "zan", + "zān", + "zán", + "zǎn", + "zàn", + "zang", + "zāng", + "zǎng", + "zàng", + "zao", + "zāo", + "záo", + "zǎo", + "zào", + "ze", + "zé", + "zè", + "zei", + "zéi", + "zen", + "zěn", + "zèn", + "zeng", + "zēng", + "zèng", + "zh", + "zha", + "zhā", + "zhá", + "zhǎ", + "zhà", + "zhai", + "zhāi", + "zhái", + "zhǎi", + "zhài", + "zhan", + "zhān", + "zhǎn", + "zhàn", + "zhang", + "zhāng", + "zhǎng", + "zhàng", + "zhao", + "zhāo", + "zháo", + "zhǎo", + "zhào", + "zhe", + "zhē", + "zhé", + "zhě", + "zhè", + "zhei", + "zhèi", + "zhen", + "zhēn", + "zhěn", + "zhèn", + "zheng", + "zhēng", + "zhěng", + "zhèng", + "zhi", + "zhī", + "zhí", + "zhǐ", + "zhì", + "zho", + "zhon", + "zhong", + "zhōng", + "zhǒng", + "zhòng", + "zhou", + "zhōu", + "zhóu", + "zhǒu", + "zhòu", + "zhu", + "zhū", + "zhú", + "zhǔ", + "zhù", + "zhua", + "zhūa", + "zhǔa", + "zhuai", + "zhūai", + "zhǔai", + "zhùai", + "zhuan", + "zhūan", + "zhǔan", + "zhùan", + "zhuang", + "zhūang", + "zhǔang", + "zhùang", + "zhui", + "zhūi", + "zhùi", + "zhun", + "zhūn", + "zhǔn", + "zhuo", + "zhūo", + "zhúo", + "zi", + "zī", + "zǐ", + "zì", + "zo", + "zon", + "zong", + "zōng", + "zǒng", + "zòng", + "zou", + "zōu", + "zǒu", + "zòu", + "zu", + "zū", + "zú", + "zǔ", + "zua", + "zuan", + "zūan", + "zǔan", + "zùan", + "zui", + "zǔi", + "zùi", + "zun", + "zūn", + "zǔn", + "zuo", + "zūo", + "zúo", + "zǔo", + "zùo", + "Punctuation", + "Roman alphabet and numbers", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 785, + "variants": ["oldAlphabets/alphabet.spyNew.xml"] + }, + { + "id": "Mandarin (simp) by Pinyin, tones as written", + "file": "autoConverted/alphabet.mandarin.simp.by.pinyin.tones.as.written.xml", + "orientation": "ltr", + "lang": "zh-Hans", + "script": "Hani", + "script_name": "Han", + "training": "training_spyNew.txt", + "palette": "European/Asian", + "conversion": "mandarin", + "chars": 7719, + "groups": [ + "a", + "ā", + "āi", + "ān", + "āng", + "āo", + "á", + "ái", + "a2n", + "áng", + "áo", + "ǎ", + "ǎi", + "ǎn", + "ǎo", + "à", + "ài", + "àn", + "àng", + "ào", + "å", + "b", + "ba", + "bā", + "bāi", + "bān", + "bāng", + "bāo", + "bá", + "bái", + "báo", + "bǎ", + "bǎi", + "bǎn", + "bǎng", + "bǎo", + "bà", + "bài", + "bàn", + "bàng", + "bào", + "be", + "be1", + "bēi", + "bēn", + "bēng", + "be2", + "be2n", + "béng", + "be3", + "běi", + "běn", + "běng", + "be4", + "bèi", + "bèn", + "bèng", + "be5", + "bei", + "bı", + "bī", + "bīn", + "bīng", + "bí", + "bǐ", + "bı3n", + "bǐng", + "bì", + "bìn", + "bìng", + "bi", + "bia", + "bia1", + "bīan", + "bīao", + "bia3", + "bǐan", + "bǐao", + "bia4", + "bìan", + "bìao", + "bie", + "bīe", + "bíe", + "bǐe", + "bìe", + "bo", + "bō", + "bó", + "bǒ", + "bò", + "bu", + "bū", + "bú", + "bǔ", + "bù", + "c", + "ca", + "cā", + "cāi", + "cān", + "cāng", + "cāo", + "ca2", + "cái", + "cán", + "cáng", + "cáo", + "cǎ", + "cǎi", + "cǎn", + "cǎo", + "ca4", + "cài", + "càn", + "cào", + "ce", + "ce1", + "cēn", + "cēng", + "ce2", + "cén", + "céng", + "cè", + "ce4n", + "cèng", + "ch", + "cha", + "chā", + "chāi", + "chān", + "chāng", + "chāo", + "chá", + "chái", + "chán", + "cháng", + "cháo", + "chǎ", + "chǎn", + "chǎng", + "chǎo", + "chà", + "chài", + "chàn", + "chàng", + "chào", + "che", + "chē", + "chēn", + "chēng", + "che2", + "chén", + "chéng", + "chě", + "chěn", + "chěng", + "chè", + "chèn", + "chèng", + "chı", + "chī", + "chí", + "chǐ", + "chì", + "cho", + "cho1", + "cho1n", + "chōng", + "chōu", + "cho2", + "cho2n", + "chóng", + "chóu", + "cho3", + "cho3n", + "chǒng", + "chǒu", + "cho4", + "cho4n", + "chòng", + "chu", + "chū", + "chūn", + "chú", + "chún", + "chǔ", + "chǔn", + "chù", + "chua", + "chua1", + "chūai", + "chūan", + "chūang", + "chua2", + "chúan", + "chúang", + "chua3", + "chǔai", + "chǔan", + "chǔang", + "chua4", + "chùai", + "chùan", + "chùang", + "chuı", + "chūi", + "chúi", + "chuo", + "chūo", + "chùo", + "cı", + "cī", + "cí", + "cǐ", + "cì", + "co", + "co1", + "co1n", + "cōng", + "co2", + "co2n", + "cóng", + "co4", + "còu", + "cu", + "cū", + "cūn", + "cú", + "cún", + "cu3", + "cǔn", + "cù", + "cùn", + "cua", + "cua1", + "cūan", + "cua2", + "cúan", + "cua4", + "cùan", + "cuı", + "cūi", + "cǔi", + "cùi", + "cuo", + "cūo", + "cúo", + "cǔo", + "cùo", + "d", + "da", + "dā", + "dāi", + "dān", + "dāng", + "dāo", + "dá", + "dǎ", + "dǎi", + "dǎn", + "dǎng", + "dǎo", + "dà", + "dài", + "dàn", + "dàng", + "dào", + "de", + "de1", + "de1n", + "dēng", + "dé", + "de3", + "děi", + "de3n", + "děng", + "de4", + "de4n", + "dèng", + "dı", + "dī", + "dı1n", + "dīng", + "dí", + "dǐ", + "dı3n", + "dǐng", + "dì", + "dı4n", + "dìng", + "di", + "dia", + "dia1", + "dīan", + "dīao", + "dǐa", + "dǐan", + "dǐao", + "dia4", + "dìan", + "dìao", + "die", + "dīe", + "díe", + "diu", + "dīu", + "do", + "do1", + "do1n", + "dōng", + "dōu", + "do3", + "do3n", + "dǒng", + "dǒu", + "do4", + "do4n", + "dòng", + "dòu", + "du", + "dū", + "dūn", + "dú", + "dǔ", + "dǔn", + "dù", + "dùn", + "dua", + "dua1", + "dūan", + "dua3", + "dǔan", + "dua4", + "dùan", + "duı", + "dūi", + "dùi", + "duo", + "dūo", + "dúo", + "dǔo", + "dùo", + "e", + "ē", + "ēn", + "é", + "éi", + "én", + "ér", + "ě", + "ěi", + "ěn", + "ěr", + "è", + "èi", + "èn", + "èr", + "f", + "fa", + "fā", + "fān", + "fāng", + "fá", + "fán", + "fáng", + "fǎ", + "fǎn", + "fǎng", + "fà", + "fàn", + "fàng", + "fe", + "fe1", + "fēi", + "fēn", + "fēng", + "fe2", + "féi", + "fén", + "féng", + "fe3", + "fěi", + "fěn", + "fěng", + "fe4", + "fèi", + "fèn", + "fèng", + "fo", + "fó", + "fo3", + "fǒu", + "fu", + "fū", + "fú", + "fǔ", + "fù", + "g", + "ga", + "gā", + "gāi", + "gān", + "gāng", + "gāo", + "gá", + "gǎ", + "gǎi", + "gǎn", + "gǎng", + "gǎo", + "gà", + "gài", + "gàn", + "gàng", + "gào", + "ge", + "gē", + "gēn", + "gēng", + "gé", + "gén", + "gě", + "gěi", + "gěn", + "gěng", + "gè", + "gèn", + "gèng", + "go", + "go1", + "go1n", + "gōng", + "gōu", + "go3", + "go3n", + "gǒng", + "gǒu", + "go4", + "go4n", + "gòng", + "gòu", + "gu", + "gū", + "gǔ", + "gǔn", + "gù", + "gùn", + "gua", + "gūa", + "gūai", + "gūan", + "gūang", + "gǔa", + "gǔai", + "gǔan", + "gǔang", + "gùa", + "gùai", + "gùan", + "gùang", + "guı", + "gūi", + "gǔi", + "gùi", + "guo", + "gūo", + "gúo", + "gǔo", + "gùo", + "h", + "ha", + "hā", + "hāi", + "hān", + "hāng", + "hāo", + "há", + "hái", + "hán", + "háng", + "háo", + "hǎ", + "hǎi", + "hǎn", + "hǎo", + "hà", + "hài", + "hàn", + "hàng", + "hào", + "he", + "hē", + "hēi", + "he1n", + "hēng", + "hé", + "hén", + "héng", + "he3", + "hěn", + "hè", + "hèn", + "hèng", + "hn", + "hng", + "ho", + "ho1", + "ho1n", + "hōng", + "ho2", + "ho2n", + "hóng", + "hóu", + "ho3", + "ho3n", + "hǒng", + "hǒu", + "ho4", + "ho4n", + "hòng", + "hòu", + "hu", + "hū", + "hūn", + "hú", + "hún", + "hǔ", + "hù", + "hùn", + "hua", + "hūa", + "hūan", + "hūang", + "húa", + "húai", + "húan", + "húang", + "hua3", + "hǔan", + "hǔang", + "hùa", + "hùai", + "hùan", + "hùang", + "hua5", + "huai", + "huı", + "hūi", + "húi", + "hǔi", + "hùi", + "huo", + "hūo", + "húo", + "hǔo", + "hùo", + "j", + "jı", + "jī", + "jīn", + "jīng", + "jí", + "jǐ", + "jǐn", + "jǐng", + "jì", + "jìn", + "jìng", + "ji", + "jia", + "jīa", + "jīan", + "jīang", + "jīao", + "jía", + "jían", + "jíao", + "jǐa", + "jǐan", + "jǐang", + "jǐao", + "jìa", + "jìan", + "jìang", + "jìao", + "jie", + "jīe", + "jíe", + "jǐe", + "jìe", + "jio", + "jio1", + "jio1n", + "jīong", + "jio3", + "jio3n", + "jǐong", + "jiu", + "jīu", + "jǐu", + "jìu", + "ju", + "jū", + "jūn", + "jú", + "jǔ", + "jù", + "jùn", + "jua", + "jua1", + "jūan", + "jua3", + "jǔan", + "jua4", + "jùan", + "jue", + "jūe", + "júe", + "jǔe", + "jùe", + "k", + "ka", + "kā", + "kāi", + "kān", + "kāng", + "kāo", + "ka2", + "ka2n", + "káng", + "kǎ", + "kǎi", + "kǎn", + "kǎo", + "ka4", + "kài", + "kàn", + "kàng", + "kào", + "ke", + "kē", + "ke1n", + "kēng", + "ké", + "kě", + "kěn", + "kè", + "kèn", + "ko", + "ko1", + "ko1n", + "kōng", + "kōu", + "ko3", + "ko3n", + "kǒng", + "kǒu", + "ko4", + "ko4n", + "kòng", + "kòu", + "ku", + "kū", + "kūn", + "kǔ", + "kǔn", + "kù", + "kùn", + "kua", + "kūa", + "kūan", + "kūang", + "kua2", + "kua2n", + "kúang", + "kǔa", + "kǔai", + "kǔan", + "kǔang", + "kùa", + "kùai", + "kua4n", + "kùang", + "kuı", + "kūi", + "kúi", + "kǔi", + "kùi", + "kuo", + "kùo", + "l", + "la", + "lā", + "la1n", + "lāng", + "lāo", + "lá", + "lái", + "lán", + "láng", + "láo", + "lǎ", + "lǎn", + "lǎng", + "lǎo", + "là", + "lài", + "làn", + "làng", + "lào", + "le", + "lē", + "lēi", + "le1n", + "lēng", + "le2", + "léi", + "le2n", + "léng", + "le3", + "lěi", + "le3n", + "lěng", + "lè", + "lèi", + "le4n", + "lèng", + "lei", + "lı", + "lī", + "līn", + "lí", + "lín", + "líng", + "lǐ", + "lǐn", + "lǐng", + "lì", + "lìn", + "lìng", + "li", + "lia", + "lia1", + "līao", + "lia2", + "lían", + "líang", + "líao", + "lǐa", + "lǐan", + "lǐang", + "lǐao", + "lia4", + "lìan", + "lìang", + "lìao", + "lie", + "līe", + "lǐe", + "lìe", + "liu", + "līu", + "líu", + "lǐu", + "lìu", + "lo", + "lo1", + "lo1n", + "lōng", + "lōu", + "lo2", + "lo2n", + "lóng", + "lóu", + "lo3", + "lo3n", + "lǒng", + "lǒu", + "lo4", + "lo4n", + "lòng", + "lòu", + "lou", + "lu", + "lū", + "lūn", + "lú", + "lún", + "lǔ", + "lù", + "lùn", + "lua", + "lua2", + "lúan", + "lua3", + "lǔan", + "lua4", + "lùan", + "luo", + "lūo", + "lúo", + "lǔo", + "lùo", + "lü", + "lǘ", + "lǚ", + "lǜ", + "lüe", + "lǚe", + "lǜe", + "m", + "m1", + "ma", + "mā", + "mān", + "māo", + "má", + "mái", + "mán", + "máng", + "máo", + "mǎ", + "mǎi", + "mǎn", + "mǎng", + "mǎo", + "mà", + "mài", + "màn", + "mào", + "me", + "me1", + "mēn", + "mēng", + "me2", + "méi", + "mén", + "méng", + "me3", + "měi", + "me3n", + "měng", + "me4", + "mèi", + "mèn", + "mèng", + "men", + "mı", + "mī", + "mí", + "mín", + "míng", + "mǐ", + "mǐn", + "mǐng", + "mì", + "mı4n", + "mìng", + "mi", + "mia", + "mia1", + "mīao", + "mia2", + "mían", + "míao", + "mia3", + "mǐan", + "mǐao", + "mia4", + "mìan", + "mìao", + "mie", + "mīe", + "mìe", + "miu", + "mìu", + "mo", + "mō", + "mōu", + "mó", + "móu", + "mǒ", + "mǒu", + "mò", + "mu", + "mú", + "mǔ", + "mù", + "n", + "na", + "nā", + "nān", + "nāng", + "nāo", + "ná", + "nán", + "náng", + "náo", + "nǎ", + "nǎi", + "nǎn", + "nǎng", + "nǎo", + "nà", + "nài", + "nàn", + "nào", + "ne", + "né", + "ne2n", + "néng", + "ne3", + "něi", + "nè", + "nèi", + "nèn", + "nı", + "nī", + "ní", + "nín", + "níng", + "nǐ", + "nı3n", + "nǐng", + "nì", + "nı4n", + "nìng", + "ni", + "nia", + "nia1", + "nīan", + "nia2", + "nían", + "níang", + "nia3", + "nǐan", + "nǐao", + "nia4", + "nìan", + "nìang", + "nìao", + "nie", + "nīe", + "nìe", + "niu", + "nīu", + "níu", + "nǐu", + "nìu", + "no", + "no2", + "no2n", + "nóng", + "no4", + "no4n", + "nòng", + "nòu", + "nu", + "nú", + "nǔ", + "nù", + "nua", + "nua3", + "nǔan", + "nuo", + "núo", + "nùo", + "nü", + "nǚ", + "nǜ", + "nüe", + "nǜe", + "o", + "ō", + "ōu", + "ó", + "o3", + "ǒu", + "ò", + "òu", + "p", + "pa", + "pā", + "pāi", + "pān", + "pāng", + "pāo", + "pá", + "pái", + "pán", + "páng", + "páo", + "pa3", + "pǎi", + "pa3n", + "pǎng", + "pǎo", + "pà", + "pài", + "pàn", + "pàng", + "pào", + "pe", + "pe1", + "pēi", + "pēn", + "pēng", + "pe2", + "péi", + "pén", + "péng", + "pe3", + "pe3n", + "pěng", + "pe4", + "pèi", + "pèn", + "pèng", + "pı", + "pī", + "pīn", + "pīng", + "pí", + "pín", + "píng", + "pǐ", + "pǐn", + "pì", + "pìn", + "pi", + "pia", + "pia1", + "pīan", + "pīao", + "pia2", + "pían", + "píao", + "pia3", + "pǐan", + "pǐao", + "pia4", + "pìan", + "pìao", + "pie", + "pīe", + "pǐe", + "po", + "pō", + "pōu", + "pó", + "póu", + "pǒ", + "pǒu", + "pò", + "pu", + "pū", + "pú", + "pǔ", + "pù", + "q", + "qı", + "qī", + "qīn", + "qīng", + "qí", + "qín", + "qíng", + "qǐ", + "qǐn", + "qǐng", + "qì", + "qìn", + "qìng", + "qi", + "qia", + "qīa", + "qīan", + "qīang", + "qīao", + "qia2", + "qían", + "qíang", + "qíao", + "qǐa", + "qǐan", + "qǐang", + "qǐao", + "qìa", + "qìan", + "qìang", + "qìao", + "qie", + "qīe", + "qíe", + "qǐe", + "qìe", + "qio", + "qio2", + "qio2n", + "qíong", + "qiu", + "qīu", + "qíu", + "qǐu", + "qu", + "qū", + "qūn", + "qú", + "qún", + "qǔ", + "qù", + "qua", + "qua1", + "qūan", + "qua2", + "qúan", + "qua3", + "qǔan", + "qua4", + "qùan", + "que", + "qūe", + "qúe", + "qùe", + "r", + "ra", + "ra1", + "ra1n", + "rāng", + "ra2", + "rán", + "ráng", + "ráo", + "ra3", + "rǎn", + "rǎng", + "rǎo", + "ra4", + "ra4n", + "ràng", + "ra5", + "rao", + "re", + "re1", + "re1n", + "rēng", + "re2", + "rén", + "réng", + "rě", + "rěn", + "rè", + "rèn", + "rı", + "rì", + "ro", + "ro2", + "ro2n", + "róng", + "róu", + "ro3", + "ro3n", + "rǒng", + "ro4", + "ròu", + "ru", + "rú", + "rǔ", + "rù", + "rùn", + "rua", + "rua3", + "rǔan", + "ruı", + "rúi", + "rǔi", + "rùi", + "ruo", + "rùo", + "s", + "sa", + "sā", + "sāi", + "sān", + "sāng", + "sāo", + "sǎ", + "sǎn", + "sǎng", + "sǎo", + "sà", + "sài", + "sàn", + "sàng", + "sào", + "se", + "se1", + "sēn", + "sēng", + "sè", + "sh", + "sha", + "shā", + "shāi", + "shān", + "shāng", + "shāo", + "shá", + "sháo", + "shǎ", + "shǎi", + "shǎn", + "shǎng", + "shǎo", + "shà", + "shài", + "shàn", + "shàng", + "shào", + "sha5", + "sha5n", + "shang", + "she", + "shē", + "shēn", + "shēng", + "shé", + "shéi", + "shén", + "shéng", + "shě", + "shěn", + "shěng", + "shè", + "shèn", + "shèng", + "shı", + "shī", + "shí", + "shǐ", + "shì", + "shi", + "sho", + "sho1", + "shōu", + "sho2", + "shóu", + "sho3", + "shǒu", + "sho4", + "shòu", + "shu", + "shū", + "shú", + "shǔ", + "shǔn", + "shù", + "shùn", + "shua", + "shūa", + "shūai", + "shūan", + "shūang", + "shǔa", + "shǔai", + "shua3n", + "shǔang", + "shùa", + "shùai", + "shùan", + "shuı", + "shúi", + "shǔi", + "shùi", + "shuo", + "shūo", + "shùo", + "sı", + "sī", + "sǐ", + "sì", + "so", + "so1", + "so1n", + "sōng", + "sōu", + "so3", + "so3n", + "sǒng", + "sǒu", + "so4", + "so4n", + "sòng", + "sòu", + "su", + "sū", + "sūn", + "sú", + "su3", + "sǔn", + "sù", + "sua", + "sua1", + "sūan", + "sua4", + "sùan", + "suı", + "sūi", + "súi", + "sǔi", + "sùi", + "suo", + "sūo", + "sǔo", + "t", + "ta", + "tā", + "tāi", + "tān", + "tāng", + "tāo", + "ta2", + "tái", + "tán", + "táng", + "táo", + "tǎ", + "tǎn", + "tǎng", + "tǎo", + "tà", + "tài", + "tàn", + "tàng", + "tào", + "te", + "te2", + "te2n", + "téng", + "tè", + "tı", + "tī", + "tı1n", + "tīng", + "tí", + "tı2n", + "tíng", + "tǐ", + "tı3n", + "tǐng", + "tì", + "tı4n", + "tìng", + "ti", + "tia", + "tia1", + "tīan", + "tīao", + "tia2", + "tían", + "tíao", + "tia3", + "tǐan", + "tǐao", + "tia4", + "tìan", + "tìao", + "tie", + "tīe", + "tǐe", + "tìe", + "to", + "to1", + "to1n", + "tōng", + "tōu", + "to2", + "to2n", + "tóng", + "tóu", + "to3", + "to3n", + "tǒng", + "tǒu", + "to4", + "to4n", + "tòng", + "tòu", + "tu", + "tū", + "tūn", + "tú", + "tún", + "tǔ", + "tǔn", + "tù", + "tùn", + "tua", + "tua1", + "tūan", + "tua2", + "túan", + "tua3", + "tǔan", + "tua4", + "tùan", + "tuı", + "tūi", + "túi", + "tǔi", + "tùi", + "tuo", + "tūo", + "túo", + "tǔo", + "tùo", + "w", + "wa", + "wā", + "wāi", + "wān", + "wāng", + "wá", + "wán", + "wáng", + "wǎ", + "wǎi", + "wǎn", + "wǎng", + "wà", + "wài", + "wàn", + "wàng", + "we", + "we1", + "wēi", + "wēn", + "wēng", + "we2", + "wéi", + "wén", + "we3", + "wěi", + "wěn", + "wěng", + "we4", + "wèi", + "wèn", + "wèng", + "wo", + "wō", + "wǒ", + "wò", + "wu", + "wū", + "wú", + "wǔ", + "wù", + "x", + "xı", + "xī", + "xīn", + "xīng", + "xí", + "xín", + "xíng", + "xǐ", + "xı3n", + "xǐng", + "xì", + "xìn", + "xìng", + "xi", + "xia", + "xīa", + "xīan", + "xīang", + "xīao", + "xía", + "xían", + "xíang", + "xíao", + "xia3", + "xǐan", + "xǐang", + "xǐao", + "xìa", + "xìan", + "xìang", + "xìao", + "xie", + "xīe", + "xíe", + "xǐe", + "xìe", + "xio", + "xio1", + "xio1n", + "xīong", + "xio2", + "xio2n", + "xíong", + "xiu", + "xīu", + "xǐu", + "xìu", + "xu", + "xū", + "xūn", + "xú", + "xún", + "xǔ", + "xù", + "xùn", + "xua", + "xua1", + "xūan", + "xua2", + "xúan", + "xua3", + "xǔan", + "xua4", + "xùan", + "xue", + "xūe", + "xúe", + "xǔe", + "xùe", + "y", + "ya", + "yā", + "yān", + "yāng", + "yāo", + "yá", + "yán", + "yáng", + "yáo", + "yǎ", + "yǎn", + "yǎng", + "yǎo", + "yà", + "yàn", + "yàng", + "yào", + "ye", + "yē", + "yé", + "yě", + "yè", + "yı", + "yī", + "yīn", + "yīng", + "yí", + "yín", + "yíng", + "yǐ", + "yǐn", + "yǐng", + "yì", + "yìn", + "yìng", + "yo", + "yō", + "yo1n", + "yōng", + "yōu", + "yo2", + "yo2n", + "yóng", + "yóu", + "yo3", + "yo3n", + "yǒng", + "yǒu", + "yo4", + "yo4n", + "yòng", + "yòu", + "yu", + "yū", + "yūn", + "yú", + "yún", + "yǔ", + "yǔn", + "yù", + "yùn", + "yua", + "yua1", + "yūan", + "yua2", + "yúan", + "yua3", + "yǔan", + "yua4", + "yùan", + "yue", + "yūe", + "yǔe", + "yùe", + "z", + "za", + "zā", + "zāi", + "zān", + "zāng", + "zāo", + "zá", + "zán", + "záo", + "zǎ", + "zǎi", + "zǎn", + "zǎng", + "zǎo", + "za4", + "zài", + "zàn", + "zàng", + "zào", + "za5", + "zan", + "ze", + "ze1", + "ze1n", + "zēng", + "zé", + "zéi", + "ze3", + "zěn", + "zè", + "zèn", + "zèng", + "zh", + "zha", + "zhā", + "zhāi", + "zhān", + "zhāng", + "zhāo", + "zhá", + "zhái", + "zháo", + "zhǎ", + "zhǎi", + "zhǎn", + "zhǎng", + "zhǎo", + "zhà", + "zhài", + "zhàn", + "zhàng", + "zhào", + "zhe", + "zhē", + "zhēn", + "zhēng", + "zhé", + "zhě", + "zhěn", + "zhěng", + "zhè", + "zhèi", + "zhèn", + "zhèng", + "zhı", + "zhī", + "zhí", + "zhǐ", + "zhì", + "zho", + "zho1", + "zho1n", + "zhōng", + "zhōu", + "zho2", + "zhóu", + "zho3", + "zho3n", + "zhǒng", + "zhǒu", + "zho4", + "zho4n", + "zhòng", + "zhòu", + "zhu", + "zhū", + "zhūn", + "zhú", + "zhǔ", + "zhǔn", + "zhù", + "zhua", + "zhūa", + "zhūai", + "zhūan", + "zhūang", + "zhǔa", + "zhǔai", + "zhǔan", + "zhǔang", + "zhua4", + "zhùai", + "zhùan", + "zhùang", + "zhuı", + "zhūi", + "zhùi", + "zhuo", + "zhūo", + "zhúo", + "zı", + "zī", + "zǐ", + "zì", + "zi", + "zo", + "zo1", + "zo1n", + "zōng", + "zōu", + "zo3", + "zo3n", + "zǒng", + "zǒu", + "zo4", + "zo4n", + "zòng", + "zòu", + "zu", + "zū", + "zūn", + "zú", + "zǔ", + "zǔn", + "zua", + "zua1", + "zūan", + "zua3", + "zǔan", + "zua4", + "zùan", + "zuı", + "zǔi", + "zùi", + "zuo", + "zūo", + "zúo", + "zǔo", + "zùo", + "Punctuation", + "Roman alphabet and numbers", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 785, + "variants": ["oldAlphabets/alphabet.spyTones2New.xml"] + }, + { + "id": "Mandarin (trad) via ㄅㄆㄇㄈ (Bopomofo)", + "file": "autoConverted/alphabet.mandarin.trad.via.bopomofo.xml", + "orientation": "ltr", + "lang": "zh-Hant", + "script": "Hani", + "script_name": "Han", + "training": "training_bopoTrad.txt", + "palette": "European/Asian", + "conversion": "routingContextSensitive", + "chars": 14176, + "groups": [ + "ˇ", + "ˊ", + "ˋ", + "˙", + "ㄚ", + "ㄚˋ", + "ㄚ˙", + "ㄛ", + "ㄛˊ", + "ㄜ", + "ㄜˇ", + "ㄜˊ", + "ㄜˋ", + "ㄝ", + "ㄝˋ", + "ㄞ", + "ㄞˇ", + "ㄞˊ", + "ㄞˋ", + "ㄟ", + "ㄠ", + "ㄠˇ", + "ㄠˊ", + "ㄠˋ", + "ㄡ", + "ㄡˇ", + "ㄡˊ", + "ㄡˋ", + "ㄢ", + "ㄢˇ", + "ㄢˊ", + "ㄢˋ", + "ㄣ", + "ㄣˋ", + "ㄤ", + "ㄤˇ", + "ㄤˊ", + "ㄤˋ", + "ㄥ", + "ㄦ", + "ㄦˇ", + "ㄦˊ", + "ㄦˋ", + "ㄧ", + "ㄧˇ", + "ㄧˊ", + "ㄧˋ", + "ㄧㄚ", + "ㄧㄚˇ", + "ㄧㄚˊ", + "ㄧㄚˋ", + "ㄧㄛ", + "ㄧㄝ", + "ㄧㄝˇ", + "ㄧㄝˊ", + "ㄧㄝˋ", + "ㄧㄞˊ", + "ㄧㄠ", + "ㄧㄠˇ", + "ㄧㄠˊ", + "ㄧㄠˋ", + "ㄧㄡ", + "ㄧㄡˇ", + "ㄧㄡˊ", + "ㄧㄡˋ", + "ㄧㄢ", + "ㄧㄢˇ", + "ㄧㄢˊ", + "ㄧㄢˋ", + "ㄧㄣ", + "ㄧㄣˇ", + "ㄧㄣˊ", + "ㄧㄣˋ", + "ㄧㄤ", + "ㄧㄤˇ", + "ㄧㄤˊ", + "ㄧㄤˋ", + "ㄧㄥ", + "ㄧㄥˇ", + "ㄧㄥˊ", + "ㄧㄥˋ", + "ㄨ", + "ㄨˇ", + "ㄨˊ", + "ㄨˋ", + "ㄨㄚ", + "ㄨㄚˇ", + "ㄨㄚˊ", + "ㄨㄚˋ", + "ㄨㄛ", + "ㄨㄛˇ", + "ㄨㄛˋ", + "ㄨㄞ", + "ㄨㄞˇ", + "ㄨㄞˋ", + "ㄨㄟ", + "ㄨㄟˇ", + "ㄨㄟˊ", + "ㄨㄟˋ", + "ㄨㄢ", + "ㄨㄢˇ", + "ㄨㄢˊ", + "ㄨㄢˋ", + "ㄨㄣ", + "ㄨㄣˇ", + "ㄨㄣˊ", + "ㄨㄣˋ", + "ㄨㄤ", + "ㄨㄤˇ", + "ㄨㄤˊ", + "ㄨㄤˋ", + "ㄨㄥ", + "ㄨㄥˇ", + "ㄨㄥˋ", + "ㄩ", + "ㄩˇ", + "ㄩˊ", + "ㄩˋ", + "ㄩㄝ", + "ㄩㄝˋ", + "ㄩㄢ", + "ㄩㄢˇ", + "ㄩㄢˊ", + "ㄩㄢˋ", + "ㄩㄣ", + "ㄩㄣˇ", + "ㄩㄣˊ", + "ㄩㄣˋ", + "ㄩㄥ", + "ㄩㄥˇ", + "ㄩㄥˊ", + "ㄩㄥˋ", + "ㄅ", + "ㄅㄚ", + "ㄅㄚˇ", + "ㄅㄚˊ", + "ㄅㄚˋ", + "ㄅㄚ˙", + "ㄅㄛ", + "ㄅㄛˇ", + "ㄅㄛˊ", + "ㄅㄛˋ", + "ㄅㄞ", + "ㄅㄞˇ", + "ㄅㄞˊ", + "ㄅㄞˋ", + "ㄅㄟ", + "ㄅㄟˇ", + "ㄅㄟˋ", + "ㄅㄠ", + "ㄅㄠˇ", + "ㄅㄠˊ", + "ㄅㄠˋ", + "ㄅㄢ", + "ㄅㄢˇ", + "ㄅㄢˋ", + "ㄅㄣ", + "ㄅㄣˇ", + "ㄅㄣˋ", + "ㄅㄤ", + "ㄅㄤˇ", + "ㄅㄤˋ", + "ㄅㄥ", + "ㄅㄥˇ", + "ㄅㄥˊ", + "ㄅㄥˋ", + "ㄅㄧ", + "ㄅㄧˇ", + "ㄅㄧˊ", + "ㄅㄧˋ", + "ㄅㄧㄝ", + "ㄅㄧㄝˇ", + "ㄅㄧㄝˊ", + "ㄅㄧㄝˋ", + "ㄅㄧㄠ", + "ㄅㄧㄠˇ", + "ㄅㄧㄠˋ", + "ㄅㄧㄢ", + "ㄅㄧㄢˇ", + "ㄅㄧㄢˋ", + "ㄅㄧㄣ", + "ㄅㄧㄣˋ", + "ㄅㄧㄥ", + "ㄅㄧㄥˇ", + "ㄅㄧㄥˋ", + "ㄅㄨ", + "ㄅㄨˇ", + "ㄅㄨˊ", + "ㄅㄨˋ", + "ㄆ", + "ㄆㄚ", + "ㄆㄚˊ", + "ㄆㄚˋ", + "ㄆㄛ", + "ㄆㄛˇ", + "ㄆㄛˊ", + "ㄆㄛˋ", + "ㄆㄞ", + "ㄆㄞˇ", + "ㄆㄞˊ", + "ㄆㄞˋ", + "ㄆㄟ", + "ㄆㄟˇ", + "ㄆㄟˊ", + "ㄆㄟˋ", + "ㄆㄠ", + "ㄆㄠˇ", + "ㄆㄠˊ", + "ㄆㄠˋ", + "ㄆㄡ", + "ㄆㄡˇ", + "ㄆㄡˊ", + "ㄆㄢ", + "ㄆㄢˇ", + "ㄆㄢˊ", + "ㄆㄢˋ", + "ㄆㄣ", + "ㄆㄣˇ", + "ㄆㄣˊ", + "ㄆㄤ", + "ㄆㄤˇ", + "ㄆㄤˊ", + "ㄆㄤˋ", + "ㄆㄥ", + "ㄆㄥˇ", + "ㄆㄥˊ", + "ㄆㄥˋ", + "ㄆㄧ", + "ㄆㄧˇ", + "ㄆㄧˊ", + "ㄆㄧˋ", + "ㄆㄧㄝ", + "ㄆㄧㄝˇ", + "ㄆㄧㄠ", + "ㄆㄧㄠˇ", + "ㄆㄧㄠˊ", + "ㄆㄧㄠˋ", + "ㄆㄧㄢ", + "ㄆㄧㄢˊ", + "ㄆㄧㄢˋ", + "ㄆㄧㄣ", + "ㄆㄧㄣˇ", + "ㄆㄧㄣˊ", + "ㄆㄧㄣˋ", + "ㄆㄧㄥ", + "ㄆㄧㄥˇ", + "ㄆㄧㄥˊ", + "ㄆㄨ", + "ㄆㄨˇ", + "ㄆㄨˊ", + "ㄆㄨˋ", + "ㄇ", + "ㄇㄚ", + "ㄇㄚˇ", + "ㄇㄚˊ", + "ㄇㄚˋ", + "ㄇㄚ˙", + "ㄇㄛ", + "ㄇㄛˇ", + "ㄇㄛˊ", + "ㄇㄛˋ", + "ㄇㄛ˙", + "ㄇㄜ˙", + "ㄇㄞˇ", + "ㄇㄞˊ", + "ㄇㄞˋ", + "ㄇㄟˇ", + "ㄇㄟˊ", + "ㄇㄟˋ", + "ㄇㄠ", + "ㄇㄠˇ", + "ㄇㄠˊ", + "ㄇㄠˋ", + "ㄇㄡˇ", + "ㄇㄡˊ", + "ㄇㄢˇ", + "ㄇㄢˊ", + "ㄇㄢˋ", + "ㄇㄣ", + "ㄇㄣˇ", + "ㄇㄣˊ", + "ㄇㄣˋ", + "ㄇㄣ˙", + "ㄇㄤˇ", + "ㄇㄤˊ", + "ㄇㄥˇ", + "ㄇㄥˊ", + "ㄇㄥˋ", + "ㄇㄧ", + "ㄇㄧˇ", + "ㄇㄧˊ", + "ㄇㄧˋ", + "ㄇㄧㄝ", + "ㄇㄧㄝˋ", + "ㄇㄧㄠ", + "ㄇㄧㄠˇ", + "ㄇㄧㄠˊ", + "ㄇㄧㄠˋ", + "ㄇㄧㄡ", + "ㄇㄧㄡˋ", + "ㄇㄧㄢˇ", + "ㄇㄧㄢˊ", + "ㄇㄧㄢˋ", + "ㄇㄧㄣˇ", + "ㄇㄧㄣˊ", + "ㄇㄧㄥˇ", + "ㄇㄧㄥˊ", + "ㄇㄧㄥˋ", + "ㄇㄨˇ", + "ㄇㄨˊ", + "ㄇㄨˋ", + "ㄈ", + "ㄈㄚ", + "ㄈㄚˇ", + "ㄈㄚˊ", + "ㄈㄚˋ", + "ㄈㄛˊ", + "ㄈㄟ", + "ㄈㄟˇ", + "ㄈㄟˊ", + "ㄈㄟˋ", + "ㄈㄡˇ", + "ㄈㄡˊ", + "ㄈㄢ", + "ㄈㄢˇ", + "ㄈㄢˊ", + "ㄈㄢˋ", + "ㄈㄣ", + "ㄈㄣˇ", + "ㄈㄣˊ", + "ㄈㄣˋ", + "ㄈㄤ", + "ㄈㄤˇ", + "ㄈㄤˊ", + "ㄈㄤˋ", + "ㄈㄥ", + "ㄈㄥˇ", + "ㄈㄥˊ", + "ㄈㄥˋ", + "ㄈㄧㄠˋ", + "ㄈㄨ", + "ㄈㄨˇ", + "ㄈㄨˊ", + "ㄈㄨˋ", + "ㄈㄨㄥˋ", + "ㄉ", + "ㄉㄚ", + "ㄉㄚˇ", + "ㄉㄚˊ", + "ㄉㄚˋ", + "ㄉㄜˊ", + "ㄉㄜ˙", + "ㄉㄞ", + "ㄉㄞˇ", + "ㄉㄞˋ", + "ㄉㄟˇ", + "ㄉㄠ", + "ㄉㄠˇ", + "ㄉㄠˋ", + "ㄉㄡ", + "ㄉㄡˇ", + "ㄉㄡˋ", + "ㄉㄢ", + "ㄉㄢˇ", + "ㄉㄢˋ", + "ㄉㄤ", + "ㄉㄤˇ", + "ㄉㄤˋ", + "ㄉㄥ", + "ㄉㄥˇ", + "ㄉㄥˋ", + "ㄉㄧ", + "ㄉㄧˇ", + "ㄉㄧˊ", + "ㄉㄧˋ", + "ㄉㄧㄚ", + "ㄉㄧㄝ", + "ㄉㄧㄝˊ", + "ㄉㄧㄠ", + "ㄉㄧㄠˇ", + "ㄉㄧㄠˋ", + "ㄉㄧㄡ", + "ㄉㄧㄢ", + "ㄉㄧㄢˇ", + "ㄉㄧㄢˋ", + "ㄉㄧㄥ", + "ㄉㄧㄥˇ", + "ㄉㄧㄥˋ", + "ㄉㄨ", + "ㄉㄨˇ", + "ㄉㄨˊ", + "ㄉㄨˋ", + "ㄉㄨㄛ", + "ㄉㄨㄛˇ", + "ㄉㄨㄛˊ", + "ㄉㄨㄛˋ", + "ㄉㄨㄟ", + "ㄉㄨㄟˋ", + "ㄉㄨㄢ", + "ㄉㄨㄢˇ", + "ㄉㄨㄢˋ", + "ㄉㄨㄣ", + "ㄉㄨㄣˇ", + "ㄉㄨㄣˋ", + "ㄉㄨㄥ", + "ㄉㄨㄥˇ", + "ㄉㄨㄥˋ", + "ㄊ", + "ㄊㄚ", + "ㄊㄚˇ", + "ㄊㄚˋ", + "ㄊㄜˋ", + "ㄊㄞ", + "ㄊㄞˊ", + "ㄊㄞˋ", + "ㄊㄠ", + "ㄊㄠˇ", + "ㄊㄠˊ", + "ㄊㄠˋ", + "ㄊㄡ", + "ㄊㄡˇ", + "ㄊㄡˊ", + "ㄊㄡˋ", + "ㄊㄡ˙", + "ㄊㄢ", + "ㄊㄢˇ", + "ㄊㄢˊ", + "ㄊㄢˋ", + "ㄊㄤ", + "ㄊㄤˇ", + "ㄊㄤˊ", + "ㄊㄤˋ", + "ㄊㄥˊ", + "ㄊㄧ", + "ㄊㄧˇ", + "ㄊㄧˊ", + "ㄊㄧˋ", + "ㄊㄧㄝ", + "ㄊㄧㄝˇ", + "ㄊㄧㄝˋ", + "ㄊㄧㄠ", + "ㄊㄧㄠˇ", + "ㄊㄧㄠˊ", + "ㄊㄧㄠˋ", + "ㄊㄧㄢ", + "ㄊㄧㄢˇ", + "ㄊㄧㄢˊ", + "ㄊㄧㄢˋ", + "ㄊㄧㄥ", + "ㄊㄧㄥˇ", + "ㄊㄧㄥˊ", + "ㄊㄧㄥˋ", + "ㄊㄨ", + "ㄊㄨˇ", + "ㄊㄨˊ", + "ㄊㄨˋ", + "ㄊㄨㄛ", + "ㄊㄨㄛˇ", + "ㄊㄨㄛˊ", + "ㄊㄨㄛˋ", + "ㄊㄨㄟ", + "ㄊㄨㄟˇ", + "ㄊㄨㄟˊ", + "ㄊㄨㄟˋ", + "ㄊㄨㄢ", + "ㄊㄨㄢˊ", + "ㄊㄨㄢˋ", + "ㄊㄨㄣ", + "ㄊㄨㄣˇ", + "ㄊㄨㄣˊ", + "ㄊㄨㄣˋ", + "ㄊㄨㄥ", + "ㄊㄨㄥˇ", + "ㄊㄨㄥˊ", + "ㄊㄨㄥˋ", + "ㄋ", + "ㄋㄚˇ", + "ㄋㄚˊ", + "ㄋㄚˋ", + "ㄋㄜ", + "ㄋㄞˇ", + "ㄋㄞˊ", + "ㄋㄞˋ", + "ㄋㄟˇ", + "ㄋㄟˋ", + "ㄋㄠ", + "ㄋㄠˇ", + "ㄋㄠˊ", + "ㄋㄠˋ", + "ㄋㄡˊ", + "ㄋㄡˋ", + "ㄋㄢ", + "ㄋㄢˇ", + "ㄋㄢˊ", + "ㄋㄢˋ", + "ㄋㄣˋ", + "ㄋㄤ", + "ㄋㄤˇ", + "ㄋㄤˊ", + "ㄋㄤˋ", + "ㄋㄤ˙", + "ㄋㄥˊ", + "ㄋㄥˋ", + "ㄋㄧˇ", + "ㄋㄧˊ", + "ㄋㄧˋ", + "ㄋㄧㄝ", + "ㄋㄧㄝˊ", + "ㄋㄧㄝˋ", + "ㄋㄧㄠˇ", + "ㄋㄧㄠˋ", + "ㄋㄧㄡ", + "ㄋㄧㄡˇ", + "ㄋㄧㄡˊ", + "ㄋㄧㄡˋ", + "ㄋㄧㄢˇ", + "ㄋㄧㄢˊ", + "ㄋㄧㄢˋ", + "ㄋㄧㄣˇ", + "ㄋㄧㄣˊ", + "ㄋㄧㄤˊ", + "ㄋㄧㄤˋ", + "ㄋㄧㄥˇ", + "ㄋㄧㄥˊ", + "ㄋㄧㄥˋ", + "ㄋㄨˇ", + "ㄋㄨˊ", + "ㄋㄨˋ", + "ㄋㄨㄛˇ", + "ㄋㄨㄛˊ", + "ㄋㄨㄛˋ", + "ㄋㄨㄢˇ", + "ㄋㄨㄥˊ", + "ㄋㄨㄥˋ", + "ㄋㄩˇ", + "ㄋㄩˋ", + "ㄋㄩㄝˋ", + "ㄌ", + "ㄌㄚ", + "ㄌㄚˇ", + "ㄌㄚˊ", + "ㄌㄚˋ", + "ㄌㄚ˙", + "ㄌㄜˋ", + "ㄌㄜ˙", + "ㄌㄞˊ", + "ㄌㄞˋ", + "ㄌㄟ", + "ㄌㄟˇ", + "ㄌㄟˊ", + "ㄌㄟˋ", + "ㄌㄠ", + "ㄌㄠˇ", + "ㄌㄠˊ", + "ㄌㄠˋ", + "ㄌㄡ", + "ㄌㄡˇ", + "ㄌㄡˊ", + "ㄌㄡˋ", + "ㄌㄢˇ", + "ㄌㄢˊ", + "ㄌㄢˋ", + "ㄌㄤ", + "ㄌㄤˇ", + "ㄌㄤˊ", + "ㄌㄤˋ", + "ㄌㄥˇ", + "ㄌㄥˊ", + "ㄌㄥˋ", + "ㄌㄧ", + "ㄌㄧˇ", + "ㄌㄧˊ", + "ㄌㄧˋ", + "ㄌㄧㄚˇ", + "ㄌㄧㄝ", + "ㄌㄧㄝˇ", + "ㄌㄧㄝˋ", + "ㄌㄧㄠ", + "ㄌㄧㄠˇ", + "ㄌㄧㄠˊ", + "ㄌㄧㄠˋ", + "ㄌㄧㄡ", + "ㄌㄧㄡˇ", + "ㄌㄧㄡˊ", + "ㄌㄧㄡˋ", + "ㄌㄧㄢˇ", + "ㄌㄧㄢˊ", + "ㄌㄧㄢˋ", + "ㄌㄧㄣˇ", + "ㄌㄧㄣˊ", + "ㄌㄧㄣˋ", + "ㄌㄧㄤˇ", + "ㄌㄧㄤˊ", + "ㄌㄧㄤˋ", + "ㄌㄧㄥ", + "ㄌㄧㄥˇ", + "ㄌㄧㄥˊ", + "ㄌㄧㄥˋ", + "ㄌㄨ", + "ㄌㄨˇ", + "ㄌㄨˊ", + "ㄌㄨˋ", + "ㄌㄨㄛ", + "ㄌㄨㄛˇ", + "ㄌㄨㄛˊ", + "ㄌㄨㄛˋ", + "ㄌㄨㄢˇ", + "ㄌㄨㄢˊ", + "ㄌㄨㄢˋ", + "ㄌㄨㄣ", + "ㄌㄨㄣˇ", + "ㄌㄨㄣˊ", + "ㄌㄨㄣˋ", + "ㄌㄨㄥˇ", + "ㄌㄨㄥˊ", + "ㄌㄨㄥˋ", + "ㄌㄩˇ", + "ㄌㄩˊ", + "ㄌㄩˋ", + "ㄌㄩㄝˋ", + "ㄌㄩㄢˇ", + "ㄌㄩㄢˊ", + "ㄍ", + "ㄍㄚ", + "ㄍㄚˊ", + "ㄍㄚˋ", + "ㄍㄚ˙", + "ㄍㄜ", + "ㄍㄜˇ", + "ㄍㄜˊ", + "ㄍㄜˋ", + "ㄍㄜ˙", + "ㄍㄞ", + "ㄍㄞˇ", + "ㄍㄞˋ", + "ㄍㄟˇ", + "ㄍㄠ", + "ㄍㄠˇ", + "ㄍㄠˋ", + "ㄍㄡ", + "ㄍㄡˇ", + "ㄍㄡˋ", + "ㄍㄢ", + "ㄍㄢˇ", + "ㄍㄢˋ", + "ㄍㄣ", + "ㄍㄣˇ", + "ㄍㄣˊ", + "ㄍㄣˋ", + "ㄍㄤ", + "ㄍㄤˇ", + "ㄍㄤˋ", + "ㄍㄥ", + "ㄍㄥˇ", + "ㄍㄥˋ", + "ㄍㄨ", + "ㄍㄨˇ", + "ㄍㄨˊ", + "ㄍㄨˋ", + "ㄍㄨㄚ", + "ㄍㄨㄚˇ", + "ㄍㄨㄚˋ", + "ㄍㄨㄛ", + "ㄍㄨㄛˇ", + "ㄍㄨㄛˊ", + "ㄍㄨㄛˋ", + "ㄍㄨㄞ", + "ㄍㄨㄞˇ", + "ㄍㄨㄞˋ", + "ㄍㄨㄟ", + "ㄍㄨㄟˇ", + "ㄍㄨㄟˋ", + "ㄍㄨㄢ", + "ㄍㄨㄢˇ", + "ㄍㄨㄢˋ", + "ㄍㄨㄣˇ", + "ㄍㄨㄣˋ", + "ㄍㄨㄤ", + "ㄍㄨㄤˇ", + "ㄍㄨㄤˋ", + "ㄍㄨㄥ", + "ㄍㄨㄥˇ", + "ㄍㄨㄥˋ", + "ㄎ", + "ㄎㄚ", + "ㄎㄚˇ", + "ㄎㄚˋ", + "ㄎㄜ", + "ㄎㄜˇ", + "ㄎㄜˊ", + "ㄎㄜˋ", + "ㄎㄞ", + "ㄎㄞˇ", + "ㄎㄞˋ", + "ㄎㄠ", + "ㄎㄠˇ", + "ㄎㄠˋ", + "ㄎㄡ", + "ㄎㄡˇ", + "ㄎㄡˋ", + "ㄎㄢ", + "ㄎㄢˇ", + "ㄎㄢˋ", + "ㄎㄣˇ", + "ㄎㄣˋ", + "ㄎㄤ", + "ㄎㄤˇ", + "ㄎㄤˊ", + "ㄎㄤˋ", + "ㄎㄥ", + "ㄎㄥˇ", + "ㄎㄨ", + "ㄎㄨˇ", + "ㄎㄨˋ", + "ㄎㄨㄚ", + "ㄎㄨㄚˇ", + "ㄎㄨㄚˋ", + "ㄎㄨㄛˇ", + "ㄎㄨㄛˋ", + "ㄎㄨㄞ", + "ㄎㄨㄞˇ", + "ㄎㄨㄞˋ", + "ㄎㄨㄟ", + "ㄎㄨㄟˇ", + "ㄎㄨㄟˊ", + "ㄎㄨㄟˋ", + "ㄎㄨㄢ", + "ㄎㄨㄢˇ", + "ㄎㄨㄣ", + "ㄎㄨㄣˇ", + "ㄎㄨㄣˋ", + "ㄎㄨㄤ", + "ㄎㄨㄤˇ", + "ㄎㄨㄤˊ", + "ㄎㄨㄤˋ", + "ㄎㄨㄥ", + "ㄎㄨㄥˇ", + "ㄎㄨㄥˋ", + "ㄏ", + "ㄏㄚ", + "ㄏㄚˇ", + "ㄏㄚˊ", + "ㄏㄜ", + "ㄏㄜˊ", + "ㄏㄜˋ", + "ㄏㄞ", + "ㄏㄞˇ", + "ㄏㄞˊ", + "ㄏㄞˋ", + "ㄏㄟ", + "ㄏㄟˇ", + "ㄏㄠ", + "ㄏㄠˇ", + "ㄏㄠˊ", + "ㄏㄠˋ", + "ㄏㄡ", + "ㄏㄡˇ", + "ㄏㄡˊ", + "ㄏㄡˋ", + "ㄏㄢ", + "ㄏㄢˇ", + "ㄏㄢˊ", + "ㄏㄢˋ", + "ㄏㄣˇ", + "ㄏㄣˊ", + "ㄏㄣˋ", + "ㄏㄤ", + "ㄏㄤˇ", + "ㄏㄤˊ", + "ㄏㄤˋ", + "ㄏㄥ", + "ㄏㄥˊ", + "ㄏㄥˋ", + "ㄏㄨ", + "ㄏㄨˇ", + "ㄏㄨˊ", + "ㄏㄨˋ", + "ㄏㄨㄚ", + "ㄏㄨㄚˊ", + "ㄏㄨㄚˋ", + "ㄏㄨㄛ", + "ㄏㄨㄛˇ", + "ㄏㄨㄛˊ", + "ㄏㄨㄛˋ", + "ㄏㄨㄛ˙", + "ㄏㄨㄞˊ", + "ㄏㄨㄞˋ", + "ㄏㄨㄟ", + "ㄏㄨㄟˇ", + "ㄏㄨㄟˊ", + "ㄏㄨㄟˋ", + "ㄏㄨㄢ", + "ㄏㄨㄢˇ", + "ㄏㄨㄢˊ", + "ㄏㄨㄢˋ", + "ㄏㄨㄣ", + "ㄏㄨㄣˇ", + "ㄏㄨㄣˊ", + "ㄏㄨㄣˋ", + "ㄏㄨㄤ", + "ㄏㄨㄤˇ", + "ㄏㄨㄤˊ", + "ㄏㄨㄤˋ", + "ㄏㄨㄥ", + "ㄏㄨㄥˇ", + "ㄏㄨㄥˊ", + "ㄏㄨㄥˋ", + "ㄐ", + "ㄐㄧ", + "ㄐㄧˇ", + "ㄐㄧˊ", + "ㄐㄧˋ", + "ㄐㄧㄚ", + "ㄐㄧㄚˇ", + "ㄐㄧㄚˊ", + "ㄐㄧㄚˋ", + "ㄐㄧㄝ", + "ㄐㄧㄝˇ", + "ㄐㄧㄝˊ", + "ㄐㄧㄝˋ", + "ㄐㄧㄠ", + "ㄐㄧㄠˇ", + "ㄐㄧㄠˊ", + "ㄐㄧㄠˋ", + "ㄐㄧㄡ", + "ㄐㄧㄡˇ", + "ㄐㄧㄡˋ", + "ㄐㄧㄢ", + "ㄐㄧㄢˇ", + "ㄐㄧㄢˋ", + "ㄐㄧㄣ", + "ㄐㄧㄣˇ", + "ㄐㄧㄣˋ", + "ㄐㄧㄤ", + "ㄐㄧㄤˇ", + "ㄐㄧㄤˋ", + "ㄐㄧㄥ", + "ㄐㄧㄥˇ", + "ㄐㄧㄥˋ", + "ㄐㄩ", + "ㄐㄩˇ", + "ㄐㄩˊ", + "ㄐㄩˋ", + "ㄐㄩㄝ", + "ㄐㄩㄝˇ", + "ㄐㄩㄝˊ", + "ㄐㄩㄝˋ", + "ㄐㄩㄢ", + "ㄐㄩㄢˇ", + "ㄐㄩㄢˋ", + "ㄐㄩㄣ", + "ㄐㄩㄣˇ", + "ㄐㄩㄣˋ", + "ㄐㄩㄥ", + "ㄐㄩㄥˇ", + "ㄑ", + "ㄑㄧ", + "ㄑㄧˇ", + "ㄑㄧˊ", + "ㄑㄧˋ", + "ㄑㄧㄚ", + "ㄑㄧㄚˇ", + "ㄑㄧㄚˋ", + "ㄑㄧㄝ", + "ㄑㄧㄝˇ", + "ㄑㄧㄝˊ", + "ㄑㄧㄝˋ", + "ㄑㄧㄠ", + "ㄑㄧㄠˇ", + "ㄑㄧㄠˊ", + "ㄑㄧㄠˋ", + "ㄑㄧㄡ", + "ㄑㄧㄡˇ", + "ㄑㄧㄡˊ", + "ㄑㄧㄢ", + "ㄑㄧㄢˇ", + "ㄑㄧㄢˊ", + "ㄑㄧㄢˋ", + "ㄑㄧㄣ", + "ㄑㄧㄣˇ", + "ㄑㄧㄣˊ", + "ㄑㄧㄣˋ", + "ㄑㄧㄤ", + "ㄑㄧㄤˇ", + "ㄑㄧㄤˊ", + "ㄑㄧㄤˋ", + "ㄑㄧㄥ", + "ㄑㄧㄥˇ", + "ㄑㄧㄥˊ", + "ㄑㄧㄥˋ", + "ㄑㄩ", + "ㄑㄩˇ", + "ㄑㄩˊ", + "ㄑㄩˋ", + "ㄑㄩㄝ", + "ㄑㄩㄝˊ", + "ㄑㄩㄝˋ", + "ㄑㄩㄢ", + "ㄑㄩㄢˇ", + "ㄑㄩㄢˊ", + "ㄑㄩㄢˋ", + "ㄑㄩㄣ", + "ㄑㄩㄣˊ", + "ㄑㄩㄥ", + "ㄑㄩㄥˊ", + "ㄒ", + "ㄒㄧ", + "ㄒㄧˇ", + "ㄒㄧˊ", + "ㄒㄧˋ", + "ㄒㄧㄚ", + "ㄒㄧㄚˊ", + "ㄒㄧㄚˋ", + "ㄒㄧㄝ", + "ㄒㄧㄝˇ", + "ㄒㄧㄝˊ", + "ㄒㄧㄝˋ", + "ㄒㄧㄠ", + "ㄒㄧㄠˇ", + "ㄒㄧㄠˊ", + "ㄒㄧㄠˋ", + "ㄒㄧㄡ", + "ㄒㄧㄡˇ", + "ㄒㄧㄡˋ", + "ㄒㄧㄢ", + "ㄒㄧㄢˇ", + "ㄒㄧㄢˊ", + "ㄒㄧㄢˋ", + "ㄒㄧㄣ", + "ㄒㄧㄣˇ", + "ㄒㄧㄣˊ", + "ㄒㄧㄣˋ", + "ㄒㄧㄤ", + "ㄒㄧㄤˇ", + "ㄒㄧㄤˊ", + "ㄒㄧㄤˋ", + "ㄒㄧㄥ", + "ㄒㄧㄥˇ", + "ㄒㄧㄥˊ", + "ㄒㄧㄥˋ", + "ㄒㄩ", + "ㄒㄩˇ", + "ㄒㄩˊ", + "ㄒㄩˋ", + "ㄒㄩㄝ", + "ㄒㄩㄝˇ", + "ㄒㄩㄝˊ", + "ㄒㄩㄝˋ", + "ㄒㄩㄢ", + "ㄒㄩㄢˇ", + "ㄒㄩㄢˊ", + "ㄒㄩㄢˋ", + "ㄒㄩㄣ", + "ㄒㄩㄣˊ", + "ㄒㄩㄣˋ", + "ㄒㄩㄥ", + "ㄒㄩㄥˊ", + "ㄒㄩㄥˋ", + "ㄓ", + "ㄓˇ", + "ㄓˊ", + "ㄓˋ", + "ㄓㄚ", + "ㄓㄚˇ", + "ㄓㄚˊ", + "ㄓㄚˋ", + "ㄓㄜ", + "ㄓㄜˇ", + "ㄓㄜˊ", + "ㄓㄜˋ", + "ㄓㄜ˙", + "ㄓㄞ", + "ㄓㄞˇ", + "ㄓㄞˊ", + "ㄓㄞˋ", + "ㄓㄠ", + "ㄓㄠˇ", + "ㄓㄠˊ", + "ㄓㄠˋ", + "ㄓㄡ", + "ㄓㄡˇ", + "ㄓㄡˊ", + "ㄓㄡˋ", + "ㄓㄢ", + "ㄓㄢˇ", + "ㄓㄢˋ", + "ㄓㄣ", + "ㄓㄣˇ", + "ㄓㄣˋ", + "ㄓㄤ", + "ㄓㄤˇ", + "ㄓㄤˋ", + "ㄓㄥ", + "ㄓㄥˇ", + "ㄓㄥˋ", + "ㄓㄨ", + "ㄓㄨˇ", + "ㄓㄨˊ", + "ㄓㄨˋ", + "ㄓㄨㄚ", + "ㄓㄨㄚˇ", + "ㄓㄨㄛ", + "ㄓㄨㄛˊ", + "ㄓㄨㄞ", + "ㄓㄨㄞˇ", + "ㄓㄨㄞˋ", + "ㄓㄨㄟ", + "ㄓㄨㄟˇ", + "ㄓㄨㄟˋ", + "ㄓㄨㄢ", + "ㄓㄨㄢˇ", + "ㄓㄨㄢˋ", + "ㄓㄨㄣ", + "ㄓㄨㄣˇ", + "ㄓㄨㄣˋ", + "ㄓㄨㄤ", + "ㄓㄨㄤˇ", + "ㄓㄨㄤˋ", + "ㄓㄨㄥ", + "ㄓㄨㄥˇ", + "ㄓㄨㄥˋ", + "ㄔ", + "ㄔˇ", + "ㄔˊ", + "ㄔˋ", + "ㄔㄚ", + "ㄔㄚˇ", + "ㄔㄚˊ", + "ㄔㄚˋ", + "ㄔㄜ", + "ㄔㄜˇ", + "ㄔㄜˋ", + "ㄔㄞ", + "ㄔㄞˊ", + "ㄔㄞˋ", + "ㄔㄠ", + "ㄔㄠˇ", + "ㄔㄠˊ", + "ㄔㄠˋ", + "ㄔㄡ", + "ㄔㄡˇ", + "ㄔㄡˊ", + "ㄔㄡˋ", + "ㄔㄢ", + "ㄔㄢˇ", + "ㄔㄢˊ", + "ㄔㄢˋ", + "ㄔㄣ", + "ㄔㄣˇ", + "ㄔㄣˊ", + "ㄔㄣˋ", + "ㄔㄤ", + "ㄔㄤˇ", + "ㄔㄤˊ", + "ㄔㄤˋ", + "ㄔㄥ", + "ㄔㄥˇ", + "ㄔㄥˊ", + "ㄔㄥˋ", + "ㄔㄨ", + "ㄔㄨˇ", + "ㄔㄨˊ", + "ㄔㄨˋ", + "ㄔㄨㄚ", + "ㄔㄨㄛ", + "ㄔㄨㄛˋ", + "ㄔㄨㄞˇ", + "ㄔㄨㄞˊ", + "ㄔㄨㄞˋ", + "ㄔㄨㄟ", + "ㄔㄨㄟˊ", + "ㄔㄨㄟˋ", + "ㄔㄨㄢ", + "ㄔㄨㄢˇ", + "ㄔㄨㄢˊ", + "ㄔㄨㄢˋ", + "ㄔㄨㄣ", + "ㄔㄨㄣˇ", + "ㄔㄨㄣˊ", + "ㄔㄨㄤ", + "ㄔㄨㄤˇ", + "ㄔㄨㄤˊ", + "ㄔㄨㄤˋ", + "ㄔㄨㄥ", + "ㄔㄨㄥˇ", + "ㄔㄨㄥˊ", + "ㄔㄨㄥˋ", + "ㄕ", + "ㄕˇ", + "ㄕˊ", + "ㄕˋ", + "ㄕ˙", + "ㄕㄚ", + "ㄕㄚˇ", + "ㄕㄚˊ", + "ㄕㄚˋ", + "ㄕㄜ", + "ㄕㄜˇ", + "ㄕㄜˊ", + "ㄕㄜˋ", + "ㄕㄞ", + "ㄕㄞˇ", + "ㄕㄞˋ", + "ㄕㄟˊ", + "ㄕㄠ", + "ㄕㄠˇ", + "ㄕㄠˊ", + "ㄕㄠˋ", + "ㄕㄡ", + "ㄕㄡˇ", + "ㄕㄡˊ", + "ㄕㄡˋ", + "ㄕㄢ", + "ㄕㄢˇ", + "ㄕㄢˋ", + "ㄕㄣ", + "ㄕㄣˇ", + "ㄕㄣˊ", + "ㄕㄣˋ", + "ㄕㄤ", + "ㄕㄤˇ", + "ㄕㄤˋ", + "ㄕㄤ˙", + "ㄕㄥ", + "ㄕㄥˇ", + "ㄕㄥˊ", + "ㄕㄥˋ", + "ㄕㄨ", + "ㄕㄨˇ", + "ㄕㄨˊ", + "ㄕㄨˋ", + "ㄕㄨㄚ", + "ㄕㄨㄚˇ", + "ㄕㄨㄛ", + "ㄕㄨㄛˋ", + "ㄕㄨㄞ", + "ㄕㄨㄞˇ", + "ㄕㄨㄞˋ", + "ㄕㄨㄟˇ", + "ㄕㄨㄟˊ", + "ㄕㄨㄟˋ", + "ㄕㄨㄢ", + "ㄕㄨㄢˋ", + "ㄕㄨㄣˇ", + "ㄕㄨㄣˋ", + "ㄕㄨㄤ", + "ㄕㄨㄤˇ", + "ㄕㄨㄤˋ", + "ㄖ", + "ㄖˋ", + "ㄖㄜˇ", + "ㄖㄜˋ", + "ㄖㄠˇ", + "ㄖㄠˊ", + "ㄖㄠˋ", + "ㄖㄡˇ", + "ㄖㄡˊ", + "ㄖㄡˋ", + "ㄖㄢˇ", + "ㄖㄢˊ", + "ㄖㄣˇ", + "ㄖㄣˊ", + "ㄖㄣˋ", + "ㄖㄤˇ", + "ㄖㄤˊ", + "ㄖㄤˋ", + "ㄖㄥ", + "ㄖㄥˇ", + "ㄖㄥˊ", + "ㄖㄨˇ", + "ㄖㄨˊ", + "ㄖㄨˋ", + "ㄖㄨㄛˋ", + "ㄖㄨㄟˇ", + "ㄖㄨㄟˊ", + "ㄖㄨㄟˋ", + "ㄖㄨㄢˇ", + "ㄖㄨㄢˊ", + "ㄖㄨㄣ", + "ㄖㄨㄣˋ", + "ㄖㄨㄥˇ", + "ㄖㄨㄥˊ", + "ㄗ", + "ㄗˇ", + "ㄗˋ", + "ㄗ˙", + "ㄗㄚ", + "ㄗㄚˊ", + "ㄗㄜˇ", + "ㄗㄜˊ", + "ㄗㄜˋ", + "ㄗㄞ", + "ㄗㄞˇ", + "ㄗㄞˋ", + "ㄗㄟˊ", + "ㄗㄠ", + "ㄗㄠˇ", + "ㄗㄠˊ", + "ㄗㄠˋ", + "ㄗㄡ", + "ㄗㄡˇ", + "ㄗㄡˋ", + "ㄗㄢ", + "ㄗㄢˇ", + "ㄗㄢˊ", + "ㄗㄢˋ", + "ㄗㄣˇ", + "ㄗㄣˋ", + "ㄗㄤ", + "ㄗㄤˇ", + "ㄗㄤˋ", + "ㄗㄥ", + "ㄗㄥˋ", + "ㄗㄨ", + "ㄗㄨˇ", + "ㄗㄨˊ", + "ㄗㄨㄛˇ", + "ㄗㄨㄛˊ", + "ㄗㄨㄛˋ", + "ㄗㄨㄟ", + "ㄗㄨㄟˇ", + "ㄗㄨㄟˋ", + "ㄗㄨㄢ", + "ㄗㄨㄢˇ", + "ㄗㄨㄢˋ", + "ㄗㄨㄣ", + "ㄗㄨㄣˇ", + "ㄗㄨㄣˋ", + "ㄗㄨㄥ", + "ㄗㄨㄥˇ", + "ㄗㄨㄥˋ", + "ㄘ", + "ㄘˇ", + "ㄘˊ", + "ㄘˋ", + "ㄘㄚ", + "ㄘㄚˇ", + "ㄘㄚˋ", + "ㄘㄜˋ", + "ㄘㄞ", + "ㄘㄞˇ", + "ㄘㄞˊ", + "ㄘㄞˋ", + "ㄘㄠ", + "ㄘㄠˇ", + "ㄘㄠˊ", + "ㄘㄠˋ", + "ㄘㄡˋ", + "ㄘㄢ", + "ㄘㄢˇ", + "ㄘㄢˊ", + "ㄘㄢˋ", + "ㄘㄣ", + "ㄘㄣˊ", + "ㄘㄤ", + "ㄘㄤˊ", + "ㄘㄥ", + "ㄘㄥˊ", + "ㄘㄥˋ", + "ㄘㄨ", + "ㄘㄨˊ", + "ㄘㄨˋ", + "ㄘㄨㄛ", + "ㄘㄨㄛˇ", + "ㄘㄨㄛˊ", + "ㄘㄨㄛˋ", + "ㄘㄨㄟ", + "ㄘㄨㄟˇ", + "ㄘㄨㄟˊ", + "ㄘㄨㄟˋ", + "ㄘㄨㄢ", + "ㄘㄨㄢˊ", + "ㄘㄨㄢˋ", + "ㄘㄨㄣ", + "ㄘㄨㄣˇ", + "ㄘㄨㄣˊ", + "ㄘㄨㄣˋ", + "ㄘㄨㄥ", + "ㄘㄨㄥˊ", + "ㄘㄨㄥˋ", + "ㄙ", + "ㄙˇ", + "ㄙˋ", + "ㄙ˙", + "ㄙㄚ", + "ㄙㄚˇ", + "ㄙㄚˋ", + "ㄙㄜˋ", + "ㄙㄞ", + "ㄙㄞˋ", + "ㄙㄠ", + "ㄙㄠˇ", + "ㄙㄠˋ", + "ㄙㄡ", + "ㄙㄡˇ", + "ㄙㄡˋ", + "ㄙㄢ", + "ㄙㄢˇ", + "ㄙㄢˋ", + "ㄙㄣ", + "ㄙㄤ", + "ㄙㄤˇ", + "ㄙㄤˋ", + "ㄙㄥ", + "ㄙㄨ", + "ㄙㄨˊ", + "ㄙㄨˋ", + "ㄙㄨㄛ", + "ㄙㄨㄛˇ", + "ㄙㄨㄛˋ", + "ㄙㄨㄟ", + "ㄙㄨㄟˇ", + "ㄙㄨㄟˊ", + "ㄙㄨㄟˋ", + "ㄙㄨㄢ", + "ㄙㄨㄢˇ", + "ㄙㄨㄢˋ", + "ㄙㄨㄣ", + "ㄙㄨㄣˇ", + "ㄙㄨㄣˋ", + "ㄙㄨㄥ", + "ㄙㄨㄥˇ", + "ㄙㄨㄥˋ", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 960, + "variants": ["oldAlphabets/alphabet.bopoTrad.xml"] + }, + { + "id": "Manipuri (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.manipuri.mni-Beng.xml", + "orientation": "ltr", + "lang": "mni", + "script": "Beng", + "script_name": "Bengali", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 103, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 44, + "variants": ["autoConverted/alphabet.wa.manipuri.mni-Mtei.xml"] + }, + { + "id": "Manx (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.manx.gv-Latn.xml", + "orientation": "ltr", + "lang": "gv", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Mapuche (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mapuche.arn-Latn.xml", + "orientation": "ltr", + "lang": "arn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Marathi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.marathi.mr-Deva.xml", + "orientation": "ltr", + "lang": "mr", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 103, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 49, + "variants": ["autoConverted/alphabet.wa.marathi.mr-Latn.xml"] + }, + { + "id": "Marathi - Devanagari with punctuation and numerals", + "file": "autoConverted/alphabet.marathi.devanagari.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "mr", + "script": "Deva", + "script_name": "Devanagari", + "training": "training_Marathi_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 128, + "groups": [ + "DEVANAGARI letters", + "signs and vowels", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Marathi.xml"] + }, + { + "id": "Masai (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.masai.mas-Latn.xml", + "orientation": "ltr", + "lang": "mas", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 107, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Mazanderani (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mazanderani.mzn-Arab.xml", + "orientation": "rtl", + "lang": "mzn", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 91, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 38 + }, + { + "id": "Meru (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.meru.mer-Latn.xml", + "orientation": "ltr", + "lang": "mer", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Metaʼ (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.metaʼ.mgo-Latn.xml", + "orientation": "ltr", + "lang": "mgo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Mi'kmaw (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mikmaw.mic-Latn.xml", + "orientation": "ltr", + "lang": "mic", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Michoacán Mazahua (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.michoacán.mazahua.mmc-Latn.xml", + "orientation": "ltr", + "lang": "mmc", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 107, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Min Nan Chinese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.min.nan.chinese.zh-min-nan-Hans.xml", + "orientation": "ltr", + "lang": "zh", + "script": "Hani", + "script_name": "Han", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 4425, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 2210 + }, + { + "id": "Mohawk (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mohawk.moh-Latn.xml", + "orientation": "ltr", + "lang": "moh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Moksha (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.moksha.mdf-Cyrl.xml", + "orientation": "ltr", + "lang": "mdf", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Moldavian with punctuation and numerals", + "file": "autoConverted/alphabet.moldavian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_Moldavian_MD.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Moldavian.xml"] + }, + { + "id": "Mongolian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mongolian.mn-Cyrl.xml", + "orientation": "ltr", + "lang": "mn", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_wa_mn_Cyrl.txt", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.mongolian.mn-Mong.xml"] + }, + { + "id": "Morisyen (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.morisyen.mfe-Latn.xml", + "orientation": "ltr", + "lang": "mfe", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Mundang (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mundang.mua-Latn.xml", + "orientation": "ltr", + "lang": "mua", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Muscogee (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.muscogee.mus-Latn.xml", + "orientation": "ltr", + "lang": "mus", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Mócheno (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.mócheno.mhn-Latn.xml", + "orientation": "ltr", + "lang": "mhn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Māori (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.māori.mi-Latn.xml", + "orientation": "ltr", + "lang": "mi", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Nama (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nama.naq-Latn.xml", + "orientation": "ltr", + "lang": "naq", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 4 + }, + { + "id": "Navajo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.navajo.nv-Latn.xml", + "orientation": "ltr", + "lang": "nv", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Ndebele alphabet with numerals and lots of punctuation", + "file": "autoConverted/alphabet.ndebele.alphabet.with.numerals.and.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_Ndebele_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Ndebele.xml"] + }, + { + "id": "Nederlands / Dutch with punctuation and numerals", + "file": "autoConverted/alphabet.nederlands.dutch.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "nl", + "script": "Latn", + "script_name": "Latin", + "training": "training_dutch_NL.txt", + "palette": "Default", + "conversion": "none", + "chars": 111, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.dutch.xml"] + }, + { + "id": "Nepali (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nepali.ne-Deva.xml", + "orientation": "ltr", + "lang": "ne", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 105, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 50 + }, + { + "id": "Nepali with punctuation and numerals", + "file": "autoConverted/alphabet.nepali.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ne", + "script": "Deva", + "script_name": "Devanagari", + "training": "training_nepali_NP.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 93, + "groups": ["lower case letters", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.nepali.xml"] + }, + { + "id": "Ngiemboon (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ngiemboon.nnh-Latn.xml", + "orientation": "ltr", + "lang": "nnh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 115, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Ngomba (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ngomba.jgo-Latn.xml", + "orientation": "ltr", + "lang": "jgo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 93, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Nheengatu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nheengatu.yrl-Latn.xml", + "orientation": "ltr", + "lang": "yrl", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Nigerian Pidgin (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nigerian.pidgin.pcm-Latn.xml", + "orientation": "ltr", + "lang": "pcm", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Norsk / Norwegian with punctuation and numerals", + "file": "autoConverted/alphabet.norsk.norwegian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "no", + "script": "Latn", + "script_name": "Latin", + "training": "training_norwegian_NO.txt", + "palette": "Default", + "conversion": "none", + "chars": 124, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.norwegian.xml"] + }, + { + "id": "North Ndebele (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.north.ndebele.nd-Latn.xml", + "orientation": "ltr", + "lang": "nd", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 55, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Northern Frisian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.northern.frisian.frr-Latn.xml", + "orientation": "ltr", + "lang": "frr", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Northern Luri (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.northern.luri.lrc-Arab.xml", + "orientation": "rtl", + "lang": "lrc", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 97, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 41 + }, + { + "id": "Northern Sami (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.northern.sami.se-Latn.xml", + "orientation": "ltr", + "lang": "se", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Northern Sotho (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.northern.sotho.nso-Latn.xml", + "orientation": "ltr", + "lang": "nso", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Norwegian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.norwegian.no-Latn.xml", + "orientation": "ltr", + "lang": "no", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_no_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Norwegian Bokmål (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.norwegian.bokmål.nb-Latn.xml", + "orientation": "ltr", + "lang": "nb", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Norwegian Nynorsk (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.norwegian.nynorsk.nn-Latn.xml", + "orientation": "ltr", + "lang": "nn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Nuer (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nuer.nus-Latn.xml", + "orientation": "ltr", + "lang": "nus", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Nyanja (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nyanja.ny-Latn.xml", + "orientation": "ltr", + "lang": "ny", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Nyankole (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nyankole.nyn-Latn.xml", + "orientation": "ltr", + "lang": "nyn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "N’Ko (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.nko.nqo-Nkoo.xml", + "orientation": "rtl", + "lang": "nqo", + "script": "Nkoo", + "script_name": "N'Ko", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 32 + }, + { + "id": "O'zbek / Uzbek with punctuation and numerals", + "file": "autoConverted/alphabet.ozbek.uzbek.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "uz", + "script": "Latn", + "script_name": "Latin", + "training": "training_uzbek_UZ.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 101, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.uzbek.xml"] + }, + { + "id": "Occitan (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.occitan.oc-Latn.xml", + "orientation": "ltr", + "lang": "oc", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Occitan with punctuation and numerals", + "file": "autoConverted/alphabet.occitan.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "oc", + "script": "Latn", + "script_name": "Latin", + "training": "training_occitan_FR.txt", + "palette": "Default", + "conversion": "none", + "chars": 121, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.occitan.xml"] + }, + { + "id": "Odia (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.odia.or-Orya.xml", + "orientation": "ltr", + "lang": "or", + "script": "Orya", + "script_name": "Oriya", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 99, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 47 + }, + { + "id": "Ogham", + "file": "autoConverted/alphabet.ogham.xml", + "orientation": "ltr", + "lang": null, + "script": "Ogam", + "script_name": "Ogham", + "training": "training_ogham_XX.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 31, + "groups": ["Ogham", "Ogham marks", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ogham.xml"] + }, + { + "id": "Oriya with punctuation and numerals", + "file": "autoConverted/alphabet.oriya.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Orya", + "script_name": "Oriya", + "training": "training_Oriya_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "ORIYA letters", + "vowels, other signs and marks", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Oriya.xml"] + }, + { + "id": "Oromo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.oromo.om-Latn.xml", + "orientation": "ltr", + "lang": "om", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Osage (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.osage.osa-Osge.xml", + "orientation": "ltr", + "lang": "osa", + "script": "Osge", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Ossetic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ossetic.os-Cyrl.xml", + "orientation": "ltr", + "lang": "os", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Papantla Totonac (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.papantla.totonac.top-Latn.xml", + "orientation": "ltr", + "lang": "top", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Papiamento (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.papiamento.pap-Latn.xml", + "orientation": "ltr", + "lang": "pap", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Pashto (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.pashto.ps-Arab.xml", + "orientation": "rtl", + "lang": "ps", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 105, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 50 + }, + { + "id": "Perl programming language", + "file": "autoConverted/alphabet.perl.programming.language.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_perl_GB.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.perl.xml"] + }, + { + "id": "Persian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.persian.fa-Arab.xml", + "orientation": "rtl", + "lang": "fa", + "script": "Arab", + "script_name": "Arabic", + "training": "training_wa_fa_Arab.txt", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 38 + }, + { + "id": "Pijin (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.pijin.pis-Latn.xml", + "orientation": "ltr", + "lang": "pis", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 58, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Polish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.polish.pl-Latn.xml", + "orientation": "ltr", + "lang": "pl", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_pl_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Polski / Polish", + "file": "autoConverted/alphabet.polski.polish.xml", + "orientation": "ltr", + "lang": "pl", + "script": "Latn", + "script_name": "Latin", + "training": "training_polish_PL.txt", + "palette": "Default", + "conversion": "none", + "chars": 118, + "groups": ["Małe litery", "Duże litery", "Liczby", "Interpunkcja", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.polish.xml"] + }, + { + "id": "Portuguese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.portuguese.pt-Latn.xml", + "orientation": "ltr", + "lang": "pt", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_pt_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Português / Portuguese (Brazilian)", + "file": "autoConverted/alphabet.portugus.portuguese.brazilian.xml", + "orientation": "ltr", + "lang": "pt", + "script": "Latn", + "script_name": "Latin", + "training": "training_portuguese_BR.txt", + "palette": "Default", + "conversion": "none", + "chars": 129, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.portuguese.xml"] + }, + { + "id": "Português / Portuguese (Brazilian) (combining accents) with numerals and punctuation", + "file": "autoConverted/alphabet.portugus.portuguese.brazilian.combining.accents.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "pt", + "script": "Latn", + "script_name": "Latin", + "training": "training_portugueseC_BR.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 108, + "groups": [ + "Combining accents", + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Prussian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.prussian.prg-Latn.xml", + "orientation": "ltr", + "lang": "prg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 93, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Punjabi (Gurmukhi) with punctuation and numerals", + "file": "autoConverted/alphabet.punjabi.gurmukhi.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "pa", + "script": "Guru", + "script_name": "Gurmukhi", + "training": "training_Punjabi_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 106, + "groups": ["GURMUKHI letters", "GURMUKHI vowels", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Punjabi.xml"] + }, + { + "id": "Punjabi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.punjabi.pa-Guru.xml", + "orientation": "ltr", + "lang": "pa", + "script": "Guru", + "script_name": "Gurmukhi", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 95, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 45 + }, + { + "id": "Pure Katakana, halfwidths, many smalls", + "file": "autoConverted/alphabet.pure.katakana.halfwidths.many.smalls.xml", + "orientation": "ltr", + "lang": "ak", + "script": "Kana", + "script_name": "Katakana", + "training": "training_Japanese_JP.txt", + "palette": "Default", + "conversion": "none", + "chars": 244, + "groups": [ + "katakana merged, no halfwidths", + "Smalls (extra!)", + "katakana merged, halfwidths only", + "Smalls", + "Hiragana, finalized", + "smalls", + "paragraphSpace" + ], + "source": "worldalphabets" + }, + { + "id": "Pure Katakana, no halfwidths", + "file": "autoConverted/alphabet.pure.katakana.no.halfwidths.xml", + "orientation": "ttb", + "lang": "ak", + "script": "Kana", + "script_name": "Katakana", + "training": "training_Japanese_JP.txt", + "palette": "Default", + "conversion": "none", + "chars": 164, + "groups": [ + "katakana, finalized", + "Smalls", + "Hiragana, finalized", + "smalls", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Katakana.xml"] + }, + { + "id": "Quechua (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.quechua.qu-Latn.xml", + "orientation": "ltr", + "lang": "qu", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 39, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Rajasthani (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.rajasthani.raj-Deva.xml", + "orientation": "ltr", + "lang": "raj", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 34 + }, + { + "id": "Rejang (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.rejang.rej-Latn.xml", + "orientation": "ltr", + "lang": "rej", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 37 + }, + { + "id": "Rohingya (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.rohingya.rhg-Rohg.xml", + "orientation": "rtl", + "lang": "rhg", + "script": "Rohg", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 85, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 35 + }, + { + "id": "Romanian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.romanian.mo-Latn.xml", + "orientation": "ltr", + "lang": "mo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.romanian.ro-Latn.xml"] + }, + { + "id": "Romansh (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.romansh.rm-Latn.xml", + "orientation": "ltr", + "lang": "rm", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Română / Romanian with punctuation and numerals", + "file": "autoConverted/alphabet.romn.romanian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ro", + "script": "Latn", + "script_name": "Latin", + "training": "training_Romanian_RO.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Romanian.xml"] + }, + { + "id": "Rumantsch / Romansch with punctuation and numerals", + "file": "autoConverted/alphabet.rumantsch.romansch.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_romansch_CH.txt", + "palette": "Default", + "conversion": "none", + "chars": 110, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.romansch.xml"] + }, + { + "id": "Rundi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.rundi.rn-Latn.xml", + "orientation": "ltr", + "lang": "rn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Russian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.russian.ru-Cyrl.xml", + "orientation": "ltr", + "lang": "ru", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_wa_ru_Cyrl.txt", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Russian (Русский) - Кириллица alphabet", + "file": "autoConverted/alphabet.russian..alphabet.xml", + "orientation": "ltr", + "lang": "ru", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_russian_RU.txt", + "palette": "Default", + "conversion": "none", + "chars": 114, + "groups": [ + "lower case cyrillic (Кириллица) letters", + "upper case cyrillic (Кириллица) letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.russian.xml"] + }, + { + "id": "Ruuli (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ruuli.ruc-Latn.xml", + "orientation": "ltr", + "lang": "ruc", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Rwa (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.rwa.rwk-Latn.xml", + "orientation": "ltr", + "lang": "rwk", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sabah Malay (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sabah.malay.msi-Latn.xml", + "orientation": "ltr", + "lang": "msi", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Saho (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.saho.ssy-Latn.xml", + "orientation": "ltr", + "lang": "ssy", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Samaritan Aramaic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.samaritan.aramaic.sam-Latn.xml", + "orientation": "ltr", + "lang": "sam", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 127, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 61 + }, + { + "id": "Samburu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.samburu.saq-Latn.xml", + "orientation": "ltr", + "lang": "saq", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sami / Lappish with punctuation and numerals", + "file": "autoConverted/alphabet.sami.lappish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_Sami_NO.txt", + "palette": "Default", + "conversion": "none", + "chars": 142, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Sami.xml"] + }, + { + "id": "Sango (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sango.sg-Latn.xml", + "orientation": "ltr", + "lang": "sg", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sangu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sangu.sbp-Latn.xml", + "orientation": "ltr", + "lang": "sbp", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sanskrit (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sanskrit.sa-Deva.xml", + "orientation": "ltr", + "lang": "sa", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 105, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 50 + }, + { + "id": "Sanskrit with punctuation and numerals", + "file": "autoConverted/alphabet.sanskrit.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "sa", + "script": "Deva", + "script_name": "Devanagari", + "training": "training_sanskrit_IN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 97, + "groups": ["lower case letters", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.sanskrit.xml"] + }, + { + "id": "Santali (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.santali.sat-Deva.xml", + "orientation": "ltr", + "lang": "sat", + "script": "Deva", + "script_name": "Devanagari", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 26, + "variants": ["autoConverted/alphabet.wa.santali.sat-Olck.xml"] + }, + { + "id": "Sardinian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sardinian.sc-Latn.xml", + "orientation": "ltr", + "lang": "sc", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Saurashtra (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.saurashtra.saz-Saur.xml", + "orientation": "ltr", + "lang": "saz", + "script": "Saur", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 107, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 51 + }, + { + "id": "Scottish Gaelic (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.scottish.gaelic.gd-Latn.xml", + "orientation": "ltr", + "lang": "gd", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 51, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sena (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sena.seh-Latn.xml", + "orientation": "ltr", + "lang": "seh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 93, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sepedi with punctuation and numerals", + "file": "autoConverted/alphabet.sepedi.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_Sepedi_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 102, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Sepedi.xml"] + }, + { + "id": "Serbian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.serbian.sh-Latn.xml", + "orientation": "ltr", + "lang": "sh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": [ + "autoConverted/alphabet.wa.serbian.sr-Cyrl.xml", + "autoConverted/alphabet.wa.serbian.sr-Latn.xml" + ] + }, + { + "id": "Serbian (Српски) with punctuation and numerals", + "file": "autoConverted/alphabet.serbian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "sr", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_serbian_YU.txt", + "palette": "Default", + "conversion": "none", + "chars": 276, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.serbian.xml"] + }, + { + "id": "Sesotho alphabet with numerals and lots of punctuation", + "file": "autoConverted/alphabet.sesotho.alphabet.with.numerals.and.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "st", + "script": "Latn", + "script_name": "Latin", + "training": "training_Sesotho_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Sesotho.xml"] + }, + { + "id": "Shambala (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.shambala.ksb-Latn.xml", + "orientation": "ltr", + "lang": "ksb", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Shona (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.shona.sn-Latn.xml", + "orientation": "ltr", + "lang": "sn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Shqip / Albanian with punctuation and numerals", + "file": "autoConverted/alphabet.shqip.albanian.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "sq", + "script": "Latn", + "script_name": "Latin", + "training": "training_albanian_SQ.txt", + "palette": "Default", + "conversion": "none", + "chars": 103, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.albanian.xml"] + }, + { + "id": "Sichuan Yi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sichuan.yi.ii-Yiii.xml", + "orientation": "ltr", + "lang": "ii", + "script": "Yiii", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 2335, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1165 + }, + { + "id": "Sicilian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sicilian.scn-Latn.xml", + "orientation": "ltr", + "lang": "scn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Silesian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.silesian.szl-Latn.xml", + "orientation": "ltr", + "lang": "szl", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sindhi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sindhi.sd-Arab.xml", + "orientation": "rtl", + "lang": "sd", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 109, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 52 + }, + { + "id": "Sinhala (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sinhala.si-Sinh.xml", + "orientation": "ltr", + "lang": "si", + "script": "Sinh", + "script_name": "Sinhala", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 115, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 55 + }, + { + "id": "Sinhala with punctuation and numerals", + "file": "autoConverted/alphabet.sinhala.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "si", + "script": "Sinh", + "script_name": "Sinhala", + "training": "training_Sinhala_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 121, + "groups": ["SINHALA letters", "signs and vowels", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Sinhala.xml"] + }, + { + "id": "Skolt Sami (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.skolt.sami.sms-Latn.xml", + "orientation": "ltr", + "lang": "sms", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Slovak (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.slovak.sk-Latn.xml", + "orientation": "ltr", + "lang": "sk", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_sk_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 91, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Slovenian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.slovenian.sl-Latn.xml", + "orientation": "ltr", + "lang": "sl", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_sl_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 55, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Slovenský / Slovak with punctuation and numerals", + "file": "autoConverted/alphabet.slovensk.slovak.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "sk", + "script": "Latn", + "script_name": "Latin", + "training": "training_Slovak_SK.txt", + "palette": "Default", + "conversion": "none", + "chars": 130, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Slovak.xml"] + }, + { + "id": "Slovenščina / Slovene with punctuation and numerals", + "file": "autoConverted/alphabet.slovenina.slovene.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_Slovenian_SI.txt", + "palette": "Default", + "conversion": "none", + "chars": 102, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Slovenian.xml"] + }, + { + "id": "Soga (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.soga.xog-Latn.xml", + "orientation": "ltr", + "lang": "xog", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Somali (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.somali.so-Latn.xml", + "orientation": "ltr", + "lang": "so", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 41, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Somali with punctuation and numerals", + "file": "autoConverted/alphabet.somali.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "so", + "script": "Latn", + "script_name": "Latin", + "training": "training_somali_SO.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 101, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.somali.xml"] + }, + { + "id": "South Ndebele (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.south.ndebele.nr-Latn.xml", + "orientation": "ltr", + "lang": "nr", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 55, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Southern Kurdish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.southern.kurdish.sdh-Arab.xml", + "orientation": "rtl", + "lang": "sdh", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 34 + }, + { + "id": "Southern Sami (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.southern.sami.sma-Latn.xml", + "orientation": "ltr", + "lang": "sma", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Southern Sotho (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.southern.sotho.st-Latn.xml", + "orientation": "ltr", + "lang": "st", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 49, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Southwestern Tlaxiaco Mixtec (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.southwestern.tlaxiaco.mixtec.meh-Latn.xml", + "orientation": "ltr", + "lang": "meh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 69, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Spanish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.spanish.es-Latn.xml", + "orientation": "ltr", + "lang": "es", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_es_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Sundanese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.sundanese.su-Latn.xml", + "orientation": "ltr", + "lang": "su", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Suomalainen / Finnish with limited punctuation", + "file": "autoConverted/alphabet.suomalainen.finnish.with.limited.punctuation.xml", + "orientation": "ltr", + "lang": "fi", + "script": "Latn", + "script_name": "Latin", + "training": "training_finnish_FI.txt", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["lower case letters", "upper case letters", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.finnish2.xml"] + }, + { + "id": "Suomalainen / Finnish with punctuation and numerals", + "file": "autoConverted/alphabet.suomalainen.finnish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "fi", + "script": "Latn", + "script_name": "Latin", + "training": "training_finnish_FI.txt", + "palette": "Default", + "conversion": "none", + "chars": 109, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.finnish.xml"] + }, + { + "id": "Svenska / Swedish with punctuation and numerals", + "file": "autoConverted/alphabet.svenska.swedish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "sv", + "script": "Latn", + "script_name": "Latin", + "training": "training_swedish_SE.txt", + "palette": "Default", + "conversion": "none", + "chars": 109, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.swedish.xml"] + }, + { + "id": "Swahili (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.swahili.sw-Latn.xml", + "orientation": "ltr", + "lang": "sw", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_sw_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 53, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Swahili / Kiswahili with numerals and punctuation", + "file": "autoConverted/alphabet.swahili.kiswahili.with.numerals.and.punctuation.xml", + "orientation": "ltr", + "lang": "sw", + "script": "Latn", + "script_name": "Latin", + "training": "training_swahili_KE.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.swahili.xml"] + }, + { + "id": "Swampy Cree (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.swampy.cree.csw-Cans.xml", + "orientation": "ltr", + "lang": "csw", + "script": "Cans", + "script_name": "Canadian Aboriginal", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 209, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 97 + }, + { + "id": "Swati (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.swati.ss-Latn.xml", + "orientation": "ltr", + "lang": "ss", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Swati alphabet with numerals and lots of punctuation", + "file": "autoConverted/alphabet.swati.alphabet.with.numerals.and.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "ss", + "script": "Latn", + "script_name": "Latin", + "training": "training_Swati_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Swati.xml"] + }, + { + "id": "Swedish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.swedish.sv-Latn.xml", + "orientation": "ltr", + "lang": "sv", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_sv_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Swiss German (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.swiss.german.gsw-Latn.xml", + "orientation": "ltr", + "lang": "gsw", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Syriac (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.syriac.syr-Syrc.xml", + "orientation": "rtl", + "lang": "syr", + "script": "Syrc", + "script_name": "Syriac", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 49, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 22 + }, + { + "id": "Tachelhit (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tachelhit.shi-Latn.xml", + "orientation": "ltr", + "lang": "shi", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 77, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Tagalog / Filipino with punctuation and numerals", + "file": "autoConverted/alphabet.tagalog.filipino.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "tl", + "script": "Latn", + "script_name": "Latin", + "training": "training_Filipino_PH.txt", + "palette": "Default", + "conversion": "none", + "chars": 98, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Filipino.xml"] + }, + { + "id": "Tagbanwa (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tagbanwa.tbw-Latn.xml", + "orientation": "ltr", + "lang": "tbw", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 41, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 18 + }, + { + "id": "Taita (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.taita.dav-Latn.xml", + "orientation": "ltr", + "lang": "dav", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tajik (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tajik.tg-Cyrl.xml", + "orientation": "ltr", + "lang": "tg", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tajik with punctuation and numerals", + "file": "autoConverted/alphabet.tajik.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "tg", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_Tajik_TJ.txt", + "palette": "Default", + "conversion": "none", + "chars": 277, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Tajik.xml"] + }, + { + "id": "Tamil (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tamil.ta-Taml.xml", + "orientation": "ltr", + "lang": "ta", + "script": "Taml", + "script_name": "Tamil", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 75, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 35 + }, + { + "id": "Tamil with punctuation and numerals", + "file": "autoConverted/alphabet.tamil.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ta", + "script": "Taml", + "script_name": "Tamil", + "training": "training_Tamil_IN.txt", + "palette": "Default", + "conversion": "none", + "chars": 92, + "groups": [ + "TAMIL letters", + "other signs, marks, and vowels", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Tamil.xml"] + }, + { + "id": "Tasawaq (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tasawaq.twq-Latn.xml", + "orientation": "ltr", + "lang": "twq", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tatar (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tatar.tt-Cyrl.xml", + "orientation": "ltr", + "lang": "tt", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Telugu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.telugu.te-Telu.xml", + "orientation": "ltr", + "lang": "te", + "script": "Telu", + "script_name": "Telugu", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 107, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 51 + }, + { + "id": "Telugu / తెలుగు with punctuation and numerals", + "file": "autoConverted/alphabet.telugu..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "te", + "script": "Telu", + "script_name": "Telugu", + "training": "training_Telugu_IN.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 111, + "groups": [ + "TELUGU letters", + "vowel signs etc", + "vowel-like letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Telugu.xml"] + }, + { + "id": "Teso (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.teso.teo-Latn.xml", + "orientation": "ltr", + "lang": "teo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Thai (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.thai.th-Thai.xml", + "orientation": "ltr", + "lang": "th", + "script": "Thai", + "script_name": "Thai", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 119, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 57 + }, + { + "id": "Thai / ภาษาไทย with punctuation and numerals", + "file": "autoConverted/alphabet.thai..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "th", + "script": "Thai", + "script_name": "Thai", + "training": "training_Thai_TH.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 122, + "groups": [ + "Thai letters", + "Character modifiers?", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Thai.xml", "oldAlphabets/alphabet.Thai2.xml"] + }, + { + "id": "Tibetan (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tibetan.bo-Tibt.xml", + "orientation": "ltr", + "lang": "bo", + "script": "Tibt", + "script_name": "Tibetan", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 36 + }, + { + "id": "Tigre (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tigre.tig-Ethi.xml", + "orientation": "ltr", + "lang": "tig", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 857, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 421 + }, + { + "id": "Tigrinya (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tigrinya.ti-Ethi.xml", + "orientation": "ltr", + "lang": "ti", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 605, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 300 + }, + { + "id": "Tigrinya (ትግርኛ) with punctuation and numerals", + "file": "autoConverted/alphabet.tigrinya.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "ti", + "script": "Ethi", + "script_name": "Ethiopic", + "training": "training_tigrinya_ET.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 361, + "groups": ["ethiopic letters", "Numbers", "Punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.tigrinya.xml"] + }, + { + "id": "Toba (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.toba.tob-Latn.xml", + "orientation": "ltr", + "lang": "tob", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tok Pisin (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tok.pisin.tpi-Latn.xml", + "orientation": "ltr", + "lang": "tpi", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Toki Pona (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.toki.pona.tok-Latn.xml", + "orientation": "ltr", + "lang": "tok", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 42, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tongan (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tongan.to-Latn.xml", + "orientation": "ltr", + "lang": "to", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Tooro (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tooro.ttj-Latn.xml", + "orientation": "ltr", + "lang": "ttj", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tsonga (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tsonga.ts-Latn.xml", + "orientation": "ltr", + "lang": "ts", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tsonga alphabet with numerals and lots of punctuation", + "file": "autoConverted/alphabet.tsonga.alphabet.with.numerals.and.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "ts", + "script": "Latn", + "script_name": "Latin", + "training": "training_Tsonga_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Tsonga.xml"] + }, + { + "id": "Tswana (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tswana.tn-Latn.xml", + "orientation": "ltr", + "lang": "tn", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 51, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tswana with punctuation and numerals", + "file": "autoConverted/alphabet.tswana.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "tn", + "script": "Latn", + "script_name": "Latin", + "training": "training_Tswana_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 102, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Tswana.xml"] + }, + { + "id": "Turkish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.turkish.tr-Latn.xml", + "orientation": "ltr", + "lang": "tr", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_tr_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Turkmen (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.turkmen.tk-Latn.xml", + "orientation": "ltr", + "lang": "tk", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 65, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Tuvinian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.tuvinian.tyv-Cyrl.xml", + "orientation": "ltr", + "lang": "tyv", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Türkmen / Turkmen with punctuation and numerals", + "file": "autoConverted/alphabet.trkmen.turkmen.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "tk", + "script": "Latn", + "script_name": "Latin", + "training": "training_turkmen_TM.txt", + "palette": "Default", + "conversion": "none", + "chars": 112, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.turkmen.xml"] + }, + { + "id": "Türkçe / Turkish with punctuation and numerals", + "file": "autoConverted/alphabet.trke.turkish.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "tr", + "script": "Latn", + "script_name": "Latin", + "training": "training_turkish_TR.txt", + "palette": "Default", + "conversion": "none", + "chars": 123, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Turkish.xml"] + }, + { + "id": "Ukrainian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.ukrainian.uk-Cyrl.xml", + "orientation": "ltr", + "lang": "uk", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_wa_uk_Cyrl.txt", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 1 + }, + { + "id": "Ukrainian / Українська with punctuation and numerals", + "file": "autoConverted/alphabet.ukrainian..with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "uk", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "training_ukrainian_UA.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 278, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.ukrainian.xml"] + }, + { + "id": "Upper Sorbian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.upper.sorbian.hsb-Latn.xml", + "orientation": "ltr", + "lang": "hsb", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Urdu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.urdu.ur-Arab.xml", + "orientation": "rtl", + "lang": "ur", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 81, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 38 + }, + { + "id": "Urdu with punctuation and numerals", + "file": "autoConverted/alphabet.urdu.with.punctuation.and.numerals.xml", + "orientation": "rtl", + "lang": "ur", + "script": "Arab", + "script_name": "Arabic", + "training": "training_Urdu_PK.txt", + "palette": "European/Asian", + "conversion": "none", + "chars": 106, + "groups": [ + "letters", + "Vowels etc", + "Hamza", + "Numbers", + "Arabic-Indic numbers", + "ASCII Punctuation", + "Punctuation", + "Joiners", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Urdu.xml"] + }, + { + "id": "Uyghur (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.uyghur.ug-Arab.xml", + "orientation": "rtl", + "lang": "ug", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 34 + }, + { + "id": "Uzbek (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.uzbek.uz-Cyrl.xml", + "orientation": "ltr", + "lang": "uz", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 71, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "variants": ["autoConverted/alphabet.wa.uzbek.uz-Latn.xml"] + }, + { + "id": "Vai (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.vai.vai-Vaii.xml", + "orientation": "ltr", + "lang": "vai", + "script": "Vaii", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 563, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 274 + }, + { + "id": "Venda (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.venda.ve-Latn.xml", + "orientation": "ltr", + "lang": "ve", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Venda with punctuation and numerals", + "file": "autoConverted/alphabet.venda.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": null, + "script": "Latn", + "script_name": "Latin", + "training": "training_Venda_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 106, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.venda.xml"] + }, + { + "id": "Venetian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.venetian.vec-Latn.xml", + "orientation": "ltr", + "lang": "vec", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Vietnamese (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.vietnamese.vi-Latn.xml", + "orientation": "ltr", + "lang": "vi", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 73, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Việt ngữ / Vietnamese with punctuation and numerals", + "file": "autoConverted/alphabet.vit.ng.vietnamese.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "vi", + "script": "Latn", + "script_name": "Latin", + "training": "training_Vietnamese_VN.txt", + "palette": "Default", + "conversion": "none", + "chars": 230, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Vietnamese.xml"] + }, + { + "id": "Volapük (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.volapük.vo-Latn.xml", + "orientation": "ltr", + "lang": "vo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 59, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Vunjo (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.vunjo.vun-Latn.xml", + "orientation": "ltr", + "lang": "vun", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Walloon (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.walloon.wa-Latn.xml", + "orientation": "ltr", + "lang": "wa", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 91, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Walser (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.walser.wae-Latn.xml", + "orientation": "ltr", + "lang": "wae", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 93, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Warlpiri (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.warlpiri.wbp-Latn.xml", + "orientation": "ltr", + "lang": "wbp", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 45, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Welsh (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.welsh.cy-Latn.xml", + "orientation": "ltr", + "lang": "cy", + "script": "Latn", + "script_name": "Latin", + "training": "training_wa_cy_Latn.txt", + "palette": "Default", + "conversion": "none", + "chars": 113, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Western Balochi (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.western.balochi.bgn-Arab.xml", + "orientation": "rtl", + "lang": "bgn", + "script": "Arab", + "script_name": "Arabic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 89, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 37 + }, + { + "id": "Western Frisian (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.western.frisian.fy-Latn.xml", + "orientation": "ltr", + "lang": "fy", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 87, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Wolof (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.wolof.wo-Latn.xml", + "orientation": "ltr", + "lang": "wo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 63, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Xhosa (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.xhosa.xh-Latn.xml", + "orientation": "ltr", + "lang": "xh", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Xhosa alphabet with numerals and lots of punctuation", + "file": "autoConverted/alphabet.xhosa.alphabet.with.numerals.and.lots.of.punctuation.xml", + "orientation": "ltr", + "lang": "xh", + "script": "Latn", + "script_name": "Latin", + "training": "training_Xhosa_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "Lower case Latin letters", + "Upper case Latin letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Xhosa.xml"] + }, + { + "id": "Yakut (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.yakut.sah-Cyrl.xml", + "orientation": "ltr", + "lang": "sah", + "script": "Cyrl", + "script_name": "Cyrillic", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 67, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Yangben (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.yangben.yav-Latn.xml", + "orientation": "ltr", + "lang": "yav", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 105, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Yiddish (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.yiddish.yi-Hebr.xml", + "orientation": "rtl", + "lang": "yi", + "script": "Hebr", + "script_name": "Hebrew", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 61, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets", + "flags": ["duplicate-symbols"], + "duplicate_symbols": 28 + }, + { + "id": "Yoruba (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.yoruba.yo-Latn.xml", + "orientation": "ltr", + "lang": "yo", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Yorùbá / Yoruba with punctuation and numerals", + "file": "autoConverted/alphabet.yorb.yoruba.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "yo", + "script": "Latn", + "script_name": "Latin", + "training": "training_Yoruba_NG.txt", + "palette": "Default", + "conversion": "none", + "chars": 122, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Yoruba.xml"] + }, + { + "id": "Zarma (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.zarma.dje-Latn.xml", + "orientation": "ltr", + "lang": "dje", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 79, + "groups": ["Lower case", "Upper case", "Digits", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Zhuang (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.zhuang.za-Latn.xml", + "orientation": "ltr", + "lang": "za", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Zulu (WorldAlphabets)", + "file": "autoConverted/alphabet.wa.zulu.zu-Latn.xml", + "orientation": "ltr", + "lang": "zu", + "script": "Latn", + "script_name": "Latin", + "training": "", + "palette": "Default", + "conversion": "none", + "chars": 57, + "groups": ["Lower case", "Upper case", "paragraphSpace", "Editing"], + "source": "worldalphabets" + }, + { + "id": "Zulu / isiZulu with punctuation and numerals", + "file": "autoConverted/alphabet.zulu.isizulu.with.punctuation.and.numerals.xml", + "orientation": "ltr", + "lang": "zu", + "script": "Latn", + "script_name": "Latin", + "training": "training_Zulu_ZA.txt", + "palette": "Default", + "conversion": "none", + "chars": 96, + "groups": [ + "lower case letters", + "upper case letters", + "Numbers", + "Punctuation", + "paragraphSpace" + ], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.Zulu.xml"] + }, + { + "id": "_ Klingon / tlhIngan Hol", + "file": "autoConverted/alphabet..klingon.tlhingan.hol.xml", + "orientation": "ltr", + "lang": null, + "script": null, + "script_name": null, + "training": "training_klingon_US.txt", + "palette": "Default", + "conversion": "none", + "chars": 41, + "groups": ["Klingon / pIqaD", "Numerals", "Punctuation, etc", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.klingon.xml"] + }, + { + "id": "_ Runic", + "file": "autoConverted/alphabet..runic.xml", + "orientation": "ltr", + "lang": null, + "script": "Runr", + "script_name": "Runic", + "training": "training_runic_XX.txt", + "palette": "Default", + "conversion": "none", + "chars": 83, + "groups": ["Runic characters", "Runic punctuation", "paragraphSpace"], + "source": "worldalphabets", + "variants": ["oldAlphabets/alphabet.runic.xml"] + } + ] +} diff --git a/src/data/related-research.json b/src/data/related-research.json index 190bbad..a4a4523 100644 --- a/src/data/related-research.json +++ b/src/data/related-research.json @@ -1,7 +1,7 @@ { "sourceBibtexUrl": "https://paperpile.com/eb/VDzRdyJpus", "sharedPageUrl": "https://paperpile.com/shared/sfRoEJyQ5QA2Oe4GSpZo2~A", - "generatedAt": "2026-08-15T21:04:04.826Z", + "generatedAt": "2026-08-28T19:15:39.952Z", "count": 24, "papers": [ { diff --git a/src/pages/alphabets.astro b/src/pages/alphabets.astro new file mode 100644 index 0000000..6e73736 --- /dev/null +++ b/src/pages/alphabets.astro @@ -0,0 +1,311 @@ +--- +import BaseLayout from '../layouts/BaseLayout.astro'; +import index from '../data/alphabets.json'; + +// Normalize the JSON's union shape into one plain structure (the ESLint +// astro plugin parses frontmatter as plain JS — no TS syntax allowed here). +const alphabets = index.alphabets.map((a) => ({ + id: a.id, + file: a.file, + orientation: a.orientation ?? 'ltr', + lang: a.lang ?? null, + script: a.script ?? null, + script_name: a.script_name ?? null, + chars: a.chars ?? 0, + source: a.source ?? 'legacy', + variants: a.variants ?? [], + flags: a.flags ?? [], +})); +const byScript = index.summaries.by_script; +const scriptCount = Object.keys(byScript).length; +const langCount = index.summaries.with_lang_code; +const rtlCount = index.summaries.by_orientation.rtl ?? 0; +const scripts = Object.entries(byScript); +--- + + +
+
+

Built in

+

Dasher alphabets

+

+ Every Dasher v6 app ships with all {index.count} alphabets — {langCount} languages across + {scriptCount} writing systems, including {rtlCount} right-to-left sets. Nothing to download, nothing + to install: switch alphabet from the app's settings. +

+

+ Catalogue generated from the + alphabet sources + on . +

+
+
+ +
+ + +
+ RTL right-to-left + · + M maintained + · + WA WorldAlphabets + · + L legacy + · + flagged entries have known data issues +
+ + + +

+ Missing a language, or want to write one yourself? See the + guide to creating custom alphabets — custom alphabet + files still work: drop them in Dasher's alphabet directory. +

+
+ + + + + diff --git a/src/pages/downloads.astro b/src/pages/downloads.astro index 52038b1..67beb7e 100644 --- a/src/pages/downloads.astro +++ b/src/pages/downloads.astro @@ -229,18 +229,19 @@ import BaseLayout from '../layouts/BaseLayout.astro';
-

Alphabet Files

+

Alphabets

- Dasher supports over 60 languages through alphabet XML files. These files define the - characters, ordering, and display properties for each language. + Every Dasher v6 app ships with all 474 alphabets built in — 456 languages across 48 + writing systems, including right-to-left sets. There is nothing to download: pick your + alphabet from the app's settings.

- -

All Alphabets

-

Complete package with all alphabet files

- ~410KB + +

Browse all alphabets

+

Filter by language, writing system and direction

+ 474 alphabets @@ -250,132 +251,52 @@ import BaseLayout from '../layouts/BaseLayout.astro';
-
-

Individual Alphabet Files

-

- Browse individual alphabet files by language. These files can be placed in Dasher's - alphabet directory to add language support. -

- -
-
-

European Languages

-
- English - French - German - Spanish - Italian - Portuguese - Dutch - Swedish - Danish - Norwegian - Finnish - Polish - Czech - Hungarian - Greek - Russian - Bulgarian -
-
- -
-

Middle-Eastern Languages

-
- Arabic - Hebrew - Persian (Farsi) -
-
- -
-

Indian Languages

-
- Hindi - Bengali - Tamil - Telugu - Kannada - Malayalam - Gujarati - Punjabi - Marathi - Oriya - Assamese - Urdu -
-
- -
-

Asian Languages

-
- Japanese (Hiragana) - Japanese (Katakana) - Korean - Thai - Mongolian - Chinese (Simplified) -
-
- -
-

African Languages

-
- Swahili - Afrikaans - Zulu - Xhosa -
-
- -
-

Other Languages

-
- Esperanto - Turkish - Icelandic -
-
-
-
+

+ Writing your own alphabet? Custom alphabet files still work — see the + guide to creating custom alphabets. The alphabet file archive remains available for Dasher 5 users. +

-

How to Install Alphabet Files

+

Custom Alphabet Files

+ +

+ Dasher v6 already includes every alphabet we publish, but you can still add your own — a + language we don't cover, a specialist symbol set, or an adapted layout. See the + creating custom alphabets guide, then place + your file in the alphabet directory for your platform: +

Windows

    -
  1. Download the alphabet file
    2. -
  2. Place it in: C:\Program Files\Dasher\alphabets\
    3. +
  3. Copy your alphabet.*.xml file
    4. +
  4. Place it in: %APPDATA%\dasher\alphabets\
  5. Restart Dasher
    6. -
  6. Select Options → Alphabet to choose your language
    7. +
  7. Select Settings → Alphabet to choose it
-

Linux

+

Linux (GTK)

    -
  1. Download the alphabet file
    2. -
  2. Place it in: /usr/share/dasher/alphabets/
    3. -
  3. Or use ~/.dasher/alphabets/ for user-specific files
    4. +
  4. Copy your alphabet.*.xml file
    5. +
  5. Place it in: ~/.local/share/dasher/alphabets/
  6. Restart Dasher
    7. -
  7. Select Options → Alphabet to choose your language
    8. +
  8. Select Settings → Alphabet to choose it
-

macOS

+

macOS / iOS / visionOS

    -
  1. Download the alphabet file
    2. -
  2. Right-click Dasher.app and select "Show Package Contents"
    3. -
  3. Navigate to Contents/Resources/alphabets/
    4. -
  4. Copy the file there
    5. +
  5. Copy your alphabet.*.xml file
    6. +
  6. Place it in Dasher's application-support alphabet directory
  7. Restart Dasher
    8. -
  8. Select Options → Alphabet to choose your language
    9. +
  9. Select Settings → Alphabet to choose it
diff --git a/src/pages/index.astro b/src/pages/index.astro index 639b2b7..15a96d2 100644 --- a/src/pages/index.astro +++ b/src/pages/index.astro @@ -58,10 +58,18 @@ import BaseLayout from '../layouts/BaseLayout.astro';

Try It Now

-

Try Dasher right here in your browser — no download required.

+

+ Try Dasher right here in your browser — no download required. Want the full tour with + settings, themes, game mode and 470+ alphabets? Try the + enhanced demo. +