verify/parse language codes
nrfq
parent
8095c60067
commit
8a450948c6
29
index.js
29
index.js
|
|
@ -1,6 +1,7 @@
|
|||
const fs = require('fs');
|
||||
const path = require('path');
|
||||
const remark = require('remark');
|
||||
const languages = require('./languages')
|
||||
|
||||
/**
|
||||
* Parses markdown from a file and returns an AST.
|
||||
|
|
@ -17,8 +18,9 @@ const remark = require('remark');
|
|||
*/
|
||||
let getAST = function(filename, outputFile="tree.json"){
|
||||
//import test markdown file
|
||||
let mk;
|
||||
try{
|
||||
let mk = fs.readFileSync(path.join(__dirname, filename), "utf8");
|
||||
mk = fs.readFileSync(path.join(__dirname, filename), "utf8");
|
||||
}
|
||||
catch(e){
|
||||
throw new Error("Could not open input file. Make sure the file exists.");
|
||||
|
|
@ -48,10 +50,13 @@ let getAST = function(filename, outputFile="tree.json"){
|
|||
*
|
||||
* @return {Object} Returns a JSON object, exact format still in progress.
|
||||
*/
|
||||
let exportJSON = function(children, outputFile="root.json"){
|
||||
let exportJSON = function(children, langCode, mediaType, outputFile="root.json"){
|
||||
// This will be the JSON to export
|
||||
let rootJSON = {
|
||||
type: 'root',
|
||||
langCode: langCode,
|
||||
language: languages[langCode],
|
||||
mediaType: mediaType,
|
||||
children: children
|
||||
};
|
||||
fs.writeFile(outputFile, JSON.stringify(rootJSON, null, 3), function(err) {
|
||||
|
|
@ -77,8 +82,8 @@ let parseListItem = function(listItem){
|
|||
return "NEEDS TO BE IMPLEMENTED";
|
||||
}
|
||||
|
||||
let main = function(args){
|
||||
let tree = getAST(args[0]);
|
||||
let main = function(inputFile, langCode, mediaType, outputFile){
|
||||
let tree = getAST(inputFile);
|
||||
let children = []; // This will go into root object later
|
||||
let currentDepth = 3;
|
||||
|
||||
|
|
@ -128,15 +133,23 @@ let main = function(args){
|
|||
}
|
||||
}
|
||||
}
|
||||
let rootJSON = exportJSON(children, args[1]);
|
||||
let rootJSON = exportJSON(children, langCode, mediaType, outputFile);
|
||||
}
|
||||
|
||||
let usageMessage = "Usage:\n node index.js [input_file] [output_file]\n"
|
||||
let args = process.argv.slice(2);
|
||||
if(args.length < 1)
|
||||
throw new SyntaxError(`Please provide an input filename.\n${usageMessage}`);
|
||||
throw new Error(`Please provide an input filename.\n${usageMessage}`);
|
||||
if(args.length > 2)
|
||||
throw new SyntaxError(`Too many arguments.\n${usageMessage}`);
|
||||
throw new Error(`Too many arguments.\n${usageMessage}`);
|
||||
if(args.length == 1)
|
||||
args[1] = "root.json";
|
||||
main(args);
|
||||
let fileRegex= /\S+-\S+.md/;
|
||||
if(!fileRegex.test(args[0]))
|
||||
throw new Error(`Wrong filename format. Input must be in the format 'free-media-type-languageCode.md`);
|
||||
let splitPoint = args[0].lastIndexOf("-");
|
||||
let langCode = args[0].substring(splitPoint + 1, args[0].length-3);
|
||||
if(!languages.hasOwnProperty(langCode))
|
||||
throw new Error('The language code must be in the ISO 639-1 set.');
|
||||
let mediaType = args[0].substring(0, splitPoint);
|
||||
main(args[0], langCode, mediaType, args[1]);
|
||||
|
|
@ -0,0 +1,188 @@
|
|||
const languages = {
|
||||
'ab': 'Abkhazian',
|
||||
'aa': 'Afar',
|
||||
'af': 'Afrikaans',
|
||||
'ak': 'Akan',
|
||||
'sq': 'Albanian',
|
||||
'am': 'Amharic',
|
||||
'ar': 'Arabic',
|
||||
'an': 'Aragonese',
|
||||
'hy': 'Armenian',
|
||||
'as': 'Assamese',
|
||||
'av': 'Avaric',
|
||||
'ae': 'Avestan',
|
||||
'ay': 'Aymara',
|
||||
'az': 'Azerbaijani',
|
||||
'bm': 'Bambara',
|
||||
'ba': 'Bashkir',
|
||||
'eu': 'Basque',
|
||||
'be': 'Belarusian',
|
||||
'bn': 'Bengali',
|
||||
'bh': 'Bihari languages',
|
||||
'bi': 'Bislama',
|
||||
'bs': 'Bosnian',
|
||||
'br': 'Breton',
|
||||
'bg': 'Bulgarian',
|
||||
'my': 'Burmese',
|
||||
'ca': 'Catalan, Valencian',
|
||||
'km': 'Central Khmer',
|
||||
'ch': 'Chamorro',
|
||||
'ce': 'Chechen',
|
||||
'ny': 'Chichewa, Chewa, Nyanja',
|
||||
'zh': 'Chinese',
|
||||
'cu': 'Church Slavonic, Old Bulgarian, Old Church Slavonic',
|
||||
'cv': 'Chuvash',
|
||||
'kw': 'Cornish',
|
||||
'co': 'Corsican',
|
||||
'cr': 'Cree',
|
||||
'hr': 'Croatian',
|
||||
'cs': 'Czech',
|
||||
'da': 'Danish',
|
||||
'dv': 'Divehi, Dhivehi, Maldivian',
|
||||
'nl': 'Dutch, Flemish',
|
||||
'dz': 'Dzongkha',
|
||||
'en': 'English',
|
||||
'eo': 'Esperanto',
|
||||
'et': 'Estonian',
|
||||
'ee': 'Ewe',
|
||||
'fo': 'Faroese',
|
||||
'fj': 'Fijian',
|
||||
'fi': 'Finnish',
|
||||
'fr': 'French',
|
||||
'ff': 'Fulah',
|
||||
'gd': 'Gaelic, Scottish Gaelic',
|
||||
'gl': 'Galician',
|
||||
'lg': 'Ganda',
|
||||
'ka': 'Georgian',
|
||||
'de': 'German',
|
||||
'ki': 'Gikuyu, Kikuyu',
|
||||
'el': 'Greek (Modern)',
|
||||
'kl': 'Greenlandic, Kalaallisut',
|
||||
'gn': 'Guarani',
|
||||
'gu': 'Gujarati',
|
||||
'ht': 'Haitian, Haitian Creole',
|
||||
'ha': 'Hausa',
|
||||
'he': 'Hebrew',
|
||||
'hz': 'Herero',
|
||||
'hi': 'Hindi',
|
||||
'ho': 'Hiri Motu',
|
||||
'hu': 'Hungarian',
|
||||
'is': 'Icelandic',
|
||||
'io': 'Ido',
|
||||
'ig': 'Igbo',
|
||||
'id': 'Indonesian',
|
||||
'ia': 'Interlingua (International Auxiliary Language Association)',
|
||||
'ie': 'Interlingue',
|
||||
'iu': 'Inuktitut',
|
||||
'ik': 'Inupiaq',
|
||||
'ga': 'Irish',
|
||||
'it': 'Italian',
|
||||
'ja': 'Japanese',
|
||||
'jv': 'Javanese',
|
||||
'kn': 'Kannada',
|
||||
'kr': 'Kanuri',
|
||||
'ks': 'Kashmiri',
|
||||
'kk': 'Kazakh',
|
||||
'rw': 'Kinyarwanda',
|
||||
'kv': 'Komi',
|
||||
'kg': 'Kongo',
|
||||
'ko': 'Korean',
|
||||
'kj': 'Kwanyama, Kuanyama',
|
||||
'ku': 'Kurdish',
|
||||
'ky': 'Kyrgyz',
|
||||
'lo': 'Lao',
|
||||
'la': 'Latin',
|
||||
'lv': 'Latvian',
|
||||
'lb': 'Letzeburgesch, Luxembourgish',
|
||||
'li': 'Limburgish, Limburgan, Limburger',
|
||||
'ln': 'Lingala',
|
||||
'lt': 'Lithuanian',
|
||||
'lu': 'Luba-Katanga',
|
||||
'mk': 'Macedonian',
|
||||
'mg': 'Malagasy',
|
||||
'ms': 'Malay',
|
||||
'ml': 'Malayalam',
|
||||
'mt': 'Maltese',
|
||||
'gv': 'Manx',
|
||||
'mi': 'Maori',
|
||||
'mr': 'Marathi',
|
||||
'mh': 'Marshallese',
|
||||
'ro': 'Moldovan, Moldavian, Romanian',
|
||||
'mn': 'Mongolian',
|
||||
'na': 'Nauru',
|
||||
'nv': 'Navajo, Navaho',
|
||||
'nd': 'Northern Ndebele',
|
||||
'ng': 'Ndonga',
|
||||
'ne': 'Nepali',
|
||||
'se': 'Northern Sami',
|
||||
'no': 'Norwegian',
|
||||
'nb': 'Norwegian Bokmål',
|
||||
'nn': 'Norwegian Nynorsk',
|
||||
'ii': 'Nuosu, Sichuan Yi',
|
||||
'oc': 'Occitan (post 1500)',
|
||||
'oj': 'Ojibwa',
|
||||
'or': 'Oriya',
|
||||
'om': 'Oromo',
|
||||
'os': 'Ossetian, Ossetic',
|
||||
'pi': 'Pali',
|
||||
'pa': 'Panjabi, Punjabi',
|
||||
'ps': 'Pashto, Pushto',
|
||||
'fa': 'Persian',
|
||||
'pl': 'Polish',
|
||||
'pt': 'Portuguese',
|
||||
'qu': 'Quechua',
|
||||
'rm': 'Romansh',
|
||||
'rn': 'Rundi',
|
||||
'ru': 'Russian',
|
||||
'sm': 'Samoan',
|
||||
'sg': 'Sango',
|
||||
'sa': 'Sanskrit',
|
||||
'sc': 'Sardinian',
|
||||
'sr': 'Serbian',
|
||||
'sn': 'Shona',
|
||||
'sd': 'Sindhi',
|
||||
'si': 'Sinhala, Sinhalese',
|
||||
'sk': 'Slovak',
|
||||
'sl': 'Slovenian',
|
||||
'so': 'Somali',
|
||||
'st': 'Sotho, Southern',
|
||||
'nr': 'South Ndebele',
|
||||
'es': 'Spanish, Castilian',
|
||||
'su': 'Sundanese',
|
||||
'sw': 'Swahili',
|
||||
'ss': 'Swati',
|
||||
'sv': 'Swedish',
|
||||
'tl': 'Tagalog',
|
||||
'ty': 'Tahitian',
|
||||
'tg': 'Tajik',
|
||||
'ta': 'Tamil',
|
||||
'tt': 'Tatar',
|
||||
'te': 'Telugu',
|
||||
'th': 'Thai',
|
||||
'bo': 'Tibetan',
|
||||
'ti': 'Tigrinya',
|
||||
'to': 'Tonga (Tonga Islands)',
|
||||
'ts': 'Tsonga',
|
||||
'tn': 'Tswana',
|
||||
'tr': 'Turkish',
|
||||
'tk': 'Turkmen',
|
||||
'tw': 'Twi',
|
||||
'ug': 'Uighur, Uyghur',
|
||||
'uk': 'Ukrainian',
|
||||
'ur': 'Urdu',
|
||||
'uz': 'Uzbek',
|
||||
've': 'Venda',
|
||||
'vi': 'Vietnamese',
|
||||
'vo': 'Volap_k',
|
||||
'wa': 'Walloon',
|
||||
'cy': 'Welsh',
|
||||
'fy': 'Western Frisian',
|
||||
'wo': 'Wolof',
|
||||
'xh': 'Xhosa',
|
||||
'yi': 'Yiddish',
|
||||
'yo': 'Yoruba',
|
||||
'za': 'Zhuang, Chuang',
|
||||
'zu': 'Zulu',
|
||||
};
|
||||
|
||||
module.exports = languages;
|
||||
Loading…
Reference in New Issue