@fisharmy100/auto-i18n-cli 1.0.0

package/dist/langs.js

@@ -0,0 +1,464 @@
+export const LANGUAGE_CODES = [
+    'ace_Arab',
+    'ace_Latn',
+    'acm_Arab',
+    'acq_Arab',
+    'aeb_Arab',
+    'afr_Latn',
+    'als_Latn',
+    'amh_Ethi',
+    'apc_Arab',
+    'arb_Arab',
+    'arb_Latn',
+    'arg_Latn',
+    'ars_Arab',
+    'ary_Arab',
+    'arz_Arab',
+    'asm_Beng',
+    'ast_Latn',
+    'awa_Deva',
+    'ayr_Latn',
+    'azb_Arab',
+    'azj_Latn',
+    'bak_Cyrl',
+    'bam_Latn',
+    'ban_Latn',
+    'bel_Cyrl',
+    'bem_Latn',
+    'ben_Beng',
+    'bho_Deva',
+    'bjn_Arab',
+    'bjn_Latn',
+    'bod_Tibt',
+    'bos_Latn',
+    'brx_Deva',
+    'bug_Latn',
+    'bul_Cyrl',
+    'cat_Latn',
+    'ceb_Latn',
+    'ces_Latn',
+    'chv_Cyrl',
+    'cjk_Latn',
+    'ckb_Arab',
+    'cmn_Hans',
+    'cmn_Hant',
+    'crh_Latn',
+    'cym_Latn',
+    'dan_Latn',
+    'dar_Cyrl',
+    'deu_Latn',
+    'dgo_Deva',
+    'dik_Latn',
+    'dyu_Latn',
+    'dzo_Tibt',
+    'ekk_Latn',
+    'ell_Grek',
+    'eng_Latn',
+    'epo_Latn',
+    'eus_Latn',
+    'ewe_Latn',
+    'fao_Latn',
+    'fij_Latn',
+    'fil_Latn',
+    'fin_Latn',
+    'fon_Latn',
+    'fra_Latn',
+    'fur_Latn',
+    'fuv_Latn',
+    'gaz_Latn',
+    'gla_Latn',
+    'gle_Latn',
+    'glg_Latn',
+    'gom_Deva',
+    'gug_Latn',
+    'guj_Gujr',
+    'hat_Latn',
+    'hau_Latn',
+    'heb_Hebr',
+    'hin_Deva',
+    'hne_Deva',
+    'hrv_Latn',
+    'hun_Latn',
+    'hye_Armn',
+    'ibo_Latn',
+    'ilo_Latn',
+    'ind_Latn',
+    'isl_Latn',
+    'ita_Latn',
+    'jav_Latn',
+    'jpn_Jpan',
+    'kaa_Latn',
+    'kab_Latn',
+    'kac_Latn',
+    'kam_Latn',
+    'kan_Knda',
+    'kas_Arab',
+    'kas_Deva',
+    'kat_Geor',
+    'kaz_Cyrl',
+    'kbp_Latn',
+    'kea_Latn',
+    'khk_Cyrl',
+    'khm_Khmr',
+    'kik_Latn',
+    'kin_Latn',
+    'kir_Cyrl',
+    'kmb_Latn',
+    'kmr_Latn',
+    'knc_Arab',
+    'knc_Latn',
+    'kor_Hang',
+    'ktu_Latn',
+    'lao_Laoo',
+    'lij_Latn',
+    'lim_Latn',
+    'lin_Latn',
+    'lit_Latn',
+    'lld_Latn',
+    'lmo_Latn',
+    'ltg_Latn',
+    'ltz_Latn',
+    'lua_Latn',
+    'lug_Latn',
+    'luo_Latn',
+    'lus_Latn',
+    'lvs_Latn',
+    'mag_Deva',
+    'mai_Deva',
+    'mal_Mlym',
+    'mar_Deva',
+    'mfe_Latn',
+    'mhr_Cyrl',
+    'min_Arab',
+    'min_Latn',
+    'mkd_Cyrl',
+    'mlt_Latn',
+    'mni_Beng',
+    'mni_Mtei',
+    'mos_Latn',
+    'mri_Latn',
+    'mya_Mymr',
+    'myv_Cyrl',
+    'nld_Latn',
+    'nno_Latn',
+    'nob_Latn',
+    'npi_Deva',
+    'nqo_Nkoo',
+    'nso_Latn',
+    'nus_Latn',
+    'nya_Latn',
+    'oci_Latn',
+    'ory_Orya',
+    'pag_Latn',
+    'pan_Guru',
+    'pap_Latn',
+    'pbt_Arab',
+    'pes_Arab',
+    'plt_Latn',
+    'pol_Latn',
+    'por_Latn',
+    'prs_Arab',
+    'quy_Latn',
+    'ron_Latn',
+    'run_Latn',
+    'rus_Cyrl',
+    'sag_Latn',
+    'san_Deva',
+    'sat_Olck',
+    'scn_Latn',
+    'shn_Mymr',
+    'sin_Sinh',
+    'slk_Latn',
+    'slv_Latn',
+    'smo_Latn',
+    'sna_Latn',
+    'snd_Arab',
+    'snd_Deva',
+    'som_Latn',
+    'sot_Latn',
+    'spa_Latn',
+    'srd_Latn',
+    'srp_Cyrl',
+    'ssw_Latn',
+    'sun_Latn',
+    'swe_Latn',
+    'swh_Latn',
+    'szl_Latn',
+    'tam_Taml',
+    'taq_Latn',
+    'taq_Tfng',
+    'tat_Cyrl',
+    'tel_Telu',
+    'tgk_Cyrl',
+    'tha_Thai',
+    'tir_Ethi',
+    'tpi_Latn',
+    'tsn_Latn',
+    'tso_Latn',
+    'tuk_Latn',
+    'tum_Latn',
+    'tur_Latn',
+    'twi_Latn',
+    'tyv_Cyrl',
+    'uig_Arab',
+    'ukr_Cyrl',
+    'umb_Latn',
+    'urd_Arab',
+    'uzn_Latn',
+    'uzs_Arab',
+    'vec_Latn',
+    'vie_Latn',
+    'vmw_Latn',
+    'war_Latn',
+    'wol_Latn',
+    'wuu_Hans',
+    'xho_Latn',
+    'ydd_Hebr',
+    'yor_Latn',
+    'yue_Hant',
+    'zgh_Tfng',
+    'zsm_Latn',
+    'zul_Latn',
+];
+export function stringToLanguageCode(str) {
+    if (LANGUAGE_CODES.includes(str)) {
+        return str;
+    }
+    else {
+        return null;
+    }
+}
+/**
+ * Maps NLLB language codes to Azure Translator language codes.
+ * Azure uses BCP-47 tags: https://learn.microsoft.com/en-us/azure/ai-services/translator/language-support
+ * null = no Azure equivalent or not supported.
+ */
+const NLLB_TO_AZURE = {
+    ace_Arab: null,
+    ace_Latn: null,
+    acm_Arab: null,
+    acq_Arab: null,
+    aeb_Arab: null,
+    afr_Latn: 'af',
+    als_Latn: 'sq',
+    amh_Ethi: 'am',
+    apc_Arab: null,
+    arb_Arab: 'ar',
+    arb_Latn: 'ar',
+    arg_Latn: null,
+    ars_Arab: 'ar',
+    ary_Arab: null,
+    arz_Arab: null,
+    asm_Beng: 'as',
+    ast_Latn: null,
+    awa_Deva: null,
+    ayr_Latn: null,
+    azb_Arab: null,
+    azj_Latn: 'az',
+    bak_Cyrl: 'ba',
+    bam_Latn: null,
+    ban_Latn: null,
+    bel_Cyrl: null,
+    bem_Latn: null,
+    ben_Beng: 'bn',
+    bho_Deva: 'bho',
+    bjn_Arab: null,
+    bjn_Latn: null,
+    bod_Tibt: 'bo',
+    bos_Latn: 'bs',
+    brx_Deva: null,
+    bug_Latn: null,
+    bul_Cyrl: 'bg',
+    cat_Latn: 'ca',
+    ceb_Latn: 'ceb',
+    ces_Latn: 'cs',
+    chv_Cyrl: null,
+    cjk_Latn: null,
+    ckb_Arab: 'ku',
+    cmn_Hans: 'zh-Hans',
+    cmn_Hant: 'zh-Hant',
+    crh_Latn: 'crh',
+    cym_Latn: 'cy',
+    dan_Latn: 'da',
+    dar_Cyrl: null,
+    deu_Latn: 'de',
+    dgo_Deva: null,
+    dik_Latn: null,
+    dyu_Latn: null,
+    dzo_Tibt: null,
+    ekk_Latn: 'et',
+    ell_Grek: 'el',
+    eng_Latn: 'en',
+    epo_Latn: null,
+    eus_Latn: 'eu',
+    ewe_Latn: null,
+    fao_Latn: 'fo',
+    fij_Latn: 'fj',
+    fil_Latn: 'fil',
+    fin_Latn: 'fi',
+    fon_Latn: null,
+    fra_Latn: 'fr',
+    fur_Latn: null,
+    fuv_Latn: null,
+    gaz_Latn: 'om',
+    gla_Latn: 'ga', // Scottish Gaelic → closest is Irish; Azure has 'ga' for Irish but not 'gd' in all regions
+    gle_Latn: 'ga',
+    glg_Latn: 'gl',
+    gom_Deva: null,
+    gug_Latn: null,
+    guj_Gujr: 'gu',
+    hat_Latn: 'ht',
+    hau_Latn: 'ha',
+    heb_Hebr: 'he',
+    hin_Deva: 'hi',
+    hne_Deva: null,
+    hrv_Latn: 'hr',
+    hun_Latn: 'hu',
+    hye_Armn: 'hy',
+    ibo_Latn: 'ig',
+    ilo_Latn: null,
+    ind_Latn: 'id',
+    isl_Latn: 'is',
+    ita_Latn: 'it',
+    jav_Latn: 'jv',
+    jpn_Jpan: 'ja',
+    kaa_Latn: null,
+    kab_Latn: null,
+    kac_Latn: null,
+    kam_Latn: null,
+    kan_Knda: 'kn',
+    kas_Arab: null,
+    kas_Deva: null,
+    kat_Geor: 'ka',
+    kaz_Cyrl: 'kk',
+    kbp_Latn: null,
+    kea_Latn: null,
+    khk_Cyrl: 'mn-Cyrl',
+    khm_Khmr: 'km',
+    kik_Latn: null,
+    kin_Latn: 'rw',
+    kir_Cyrl: 'ky',
+    kmb_Latn: null,
+    kmr_Latn: 'kmr',
+    knc_Arab: null,
+    knc_Latn: null,
+    kor_Hang: 'ko',
+    ktu_Latn: null,
+    lao_Laoo: 'lo',
+    lij_Latn: null,
+    lim_Latn: null,
+    lin_Latn: null,
+    lit_Latn: 'lt',
+    lld_Latn: null,
+    lmo_Latn: null,
+    ltg_Latn: null,
+    ltz_Latn: 'lb',
+    lua_Latn: null,
+    lug_Latn: null,
+    luo_Latn: null,
+    lus_Latn: null,
+    lvs_Latn: 'lv',
+    mag_Deva: null,
+    mai_Deva: 'mai',
+    mal_Mlym: 'ml',
+    mar_Deva: 'mr',
+    mfe_Latn: null,
+    mhr_Cyrl: null,
+    min_Arab: null,
+    min_Latn: null,
+    mkd_Cyrl: 'mk',
+    mlt_Latn: 'mt',
+    mni_Beng: 'mni',
+    mni_Mtei: null,
+    mos_Latn: null,
+    mri_Latn: 'mi',
+    mya_Mymr: 'my',
+    myv_Cyrl: null,
+    nld_Latn: 'nl',
+    nno_Latn: 'nb', // Azure merges Norwegian Nynorsk/Bokmål under 'nb'
+    nob_Latn: 'nb',
+    npi_Deva: 'ne',
+    nqo_Nkoo: null,
+    nso_Latn: null,
+    nus_Latn: null,
+    nya_Latn: 'ny',
+    oci_Latn: null,
+    ory_Orya: 'or',
+    pag_Latn: null,
+    pan_Guru: 'pa',
+    pap_Latn: null,
+    pbt_Arab: 'ps',
+    pes_Arab: 'fa',
+    plt_Latn: 'mg',
+    pol_Latn: 'pl',
+    por_Latn: 'pt',
+    prs_Arab: 'prs',
+    quy_Latn: null,
+    ron_Latn: 'ro',
+    run_Latn: null,
+    rus_Cyrl: 'ru',
+    sag_Latn: null,
+    san_Deva: null,
+    sat_Olck: null,
+    scn_Latn: null,
+    shn_Mymr: null,
+    sin_Sinh: 'si',
+    slk_Latn: 'sk',
+    slv_Latn: 'sl',
+    smo_Latn: 'sm',
+    sna_Latn: null,
+    snd_Arab: 'sd',
+    snd_Deva: 'sd',
+    som_Latn: 'so',
+    sot_Latn: 'st',
+    spa_Latn: 'es',
+    srd_Latn: null,
+    srp_Cyrl: 'sr-Cyrl',
+    ssw_Latn: null,
+    sun_Latn: 'su',
+    swe_Latn: 'sv',
+    swh_Latn: 'sw',
+    szl_Latn: null,
+    tam_Taml: 'ta',
+    taq_Latn: null,
+    taq_Tfng: null,
+    tat_Cyrl: 'tt',
+    tel_Telu: 'te',
+    tgk_Cyrl: 'tg',
+    tha_Thai: 'th',
+    tir_Ethi: 'ti',
+    tpi_Latn: 'to',
+    tsn_Latn: 'tn',
+    tso_Latn: null,
+    tuk_Latn: 'tk',
+    tum_Latn: null,
+    tur_Latn: 'tr',
+    twi_Latn: null,
+    tyv_Cyrl: null,
+    uig_Arab: 'ug',
+    ukr_Cyrl: 'uk',
+    umb_Latn: null,
+    urd_Arab: 'ur',
+    uzn_Latn: 'uz',
+    uzs_Arab: null,
+    vec_Latn: null,
+    vie_Latn: 'vi',
+    vmw_Latn: null,
+    war_Latn: null,
+    wol_Latn: null,
+    wuu_Hans: 'wuu',
+    xho_Latn: 'xh',
+    ydd_Hebr: 'yua', // Yiddish → Azure has 'yua' for Yucatec Maya; true Yiddish is not well-supported
+    yor_Latn: 'yo',
+    yue_Hant: 'yue',
+    zgh_Tfng: null,
+    zsm_Latn: 'ms',
+    zul_Latn: 'zu',
+};
+/**
+ * Converts an NLLB LanguageCode to an Azure Translator BCP-47 language tag.
+ * Returns null if there is no Azure equivalent for the given code.
+ */
+export function nllbToAzure(code) {
+    return NLLB_TO_AZURE[code] ?? null;
+}

package/dist/parser.d.ts

@@ -0,0 +1,29 @@
+import ts from "typescript";
+export type FoundTranslation = {
+    key: string;
+    message: string | string[];
+};
+export type ParsedResult = {
+    type: "ok";
+    value: Partial<Record<string, FoundTranslation>>;
+} | {
+    type: "error";
+    value: string[];
+};
+export declare function parseTSFiles(dir: string): Promise<ParsedResult>;
+export declare function formatError(fileName: string, fileContent: string, message: string, start: ts.LineAndCharacter, end: ts.LineAndCharacter): string;
+export declare function getTSFiles(dir: string): Promise<string[]>;
+export type FoundCallsResult = {
+    type: "ok";
+    translations: {
+        translation: FoundTranslation;
+        idStart: ts.LineAndCharacter;
+        idEnd: ts.LineAndCharacter;
+    }[];
+} | {
+    type: "error";
+    message: string;
+    start: ts.LineAndCharacter;
+    end: ts.LineAndCharacter;
+};
+export declare function findTCalls(node: ts.Node, file: ts.SourceFile): FoundCallsResult;

package/dist/parser.js

@@ -0,0 +1,215 @@
+import * as path from "path";
+import * as fs from "fs/promises";
+import ts from "typescript";
+export async function parseTSFiles(dir) {
+    const files = await getTSFiles(dir);
+    const obj = {};
+    const errors = [];
+    for (let file of files) {
+        const content = await fs.readFile(file, "utf-8");
+        const sourceFile = ts.createSourceFile(file, content, ts.ScriptTarget.Latest, true);
+        const results = findTCalls(sourceFile, sourceFile);
+        if (results.type === "ok") {
+            for (let result of results.translations) {
+                if (obj[result.translation.key] !== undefined) {
+                    errors.push(formatError(file, content, `translation with id '${result.translation.key}' already exists`, result.idStart, result.idEnd));
+                }
+                else {
+                    obj[result.translation.key] = result.translation;
+                }
+            }
+        }
+        else {
+            errors.push(formatError(file, content, results.message, results.start, results.end));
+        }
+    }
+    if (errors.length > 0) {
+        return {
+            type: "error",
+            value: errors,
+        };
+    }
+    else {
+        return {
+            type: "ok",
+            value: obj,
+        };
+    }
+}
+export function formatError(fileName, fileContent, message, start, end) {
+    const lines = fileContent.split(/\r?\n/);
+    const errorLine = lines[start.line];
+    const markerLine = " ".repeat(start.character) +
+        "^".repeat(Math.max(end.character - start.character, 1));
+    return `${fileName}:${start.line + 1}:${start.character + 1} - Error: ${message}\n` +
+        `${errorLine}\n` +
+        `${markerLine}`;
+}
+export async function getTSFiles(dir) {
+    const stat = await fs.stat(dir);
+    if (stat.isFile()) {
+        const ext = path.extname(dir);
+        if (ext === ".ts" || ext === ".tsx") {
+            return [path.resolve(dir)];
+        }
+        else {
+            return [];
+        }
+    }
+    const entries = await fs.readdir(dir, { withFileTypes: true });
+    const files = await Promise.all(entries.map(entry => {
+        const fullPath = path.join(dir, entry.name);
+        if (entry.isDirectory()) {
+            return getTSFiles(fullPath);
+        }
+        else if (entry.isFile() && (fullPath.endsWith(".ts") || fullPath.endsWith(".tsx"))) {
+            return [path.resolve(fullPath)];
+        }
+        else {
+            return [];
+        }
+    }));
+    return files.flat();
+}
+export function findTCalls(node, file) {
+    if (ts.isCallExpression(node)) {
+        const expression = node.expression;
+        if (ts.isIdentifier(expression) && expression.text === "__t") {
+            if (node.arguments.length != 2 && node.arguments.length !== 3) {
+                return {
+                    type: "error",
+                    message: `__t calls must have 2-3 arguments`,
+                    start: file.getLineAndCharacterOfPosition(expression.getStart()),
+                    end: file.getLineAndCharacterOfPosition(expression.getEnd())
+                };
+            }
+            const arg1 = node.arguments[0];
+            const arg2 = node.arguments[1];
+            if (!ts.isStringLiteral(arg1)) {
+                return {
+                    type: "error",
+                    message: `arg1 is not a string literal`,
+                    start: file.getLineAndCharacterOfPosition(arg1.getStart()),
+                    end: file.getLineAndCharacterOfPosition(arg1.getEnd())
+                };
+            }
+            if (!ts.isStringLiteral(arg2)) {
+                return {
+                    type: "error",
+                    message: `arg2 is not a string literal`,
+                    start: file.getLineAndCharacterOfPosition(arg2.getStart()),
+                    end: file.getLineAndCharacterOfPosition(arg2.getEnd())
+                };
+            }
+            return {
+                type: "ok",
+                translations: [{
+                        translation: {
+                            key: arg1.text,
+                            message: arg2.text,
+                        },
+                        idStart: file.getLineAndCharacterOfPosition(arg1.getStart()),
+                        idEnd: file.getLineAndCharacterOfPosition(arg1.getEnd())
+                    }],
+            };
+        }
+        else if (ts.isIdentifier(expression) && expression.text === "__tv") {
+            if (node.arguments.length != 3) {
+                return {
+                    type: "error",
+                    message: `__t calls must have 2-3 arguments`,
+                    start: file.getLineAndCharacterOfPosition(expression.getStart()),
+                    end: file.getLineAndCharacterOfPosition(expression.getEnd())
+                };
+            }
+            const arg1 = node.arguments[0];
+            const arg2 = node.arguments[1];
+            if (!ts.isStringLiteral(arg1)) {
+                return {
+                    type: "error",
+                    message: `arg1 is not a string literal`,
+                    start: file.getLineAndCharacterOfPosition(arg1.getStart()),
+                    end: file.getLineAndCharacterOfPosition(arg1.getEnd())
+                };
+            }
+            if (!ts.isArrayLiteralExpression(arg2)) {
+                return {
+                    type: "error",
+                    message: `arg2 is not a array literal`,
+                    start: file.getLineAndCharacterOfPosition(arg2.getStart()),
+                    end: file.getLineAndCharacterOfPosition(arg2.getEnd())
+                };
+            }
+            const variants = [];
+            for (let i = 0; i < arg2.elements.length; i++) {
+                let variant = arg2.elements[i];
+                if (i >= arg2.elements.length - 1) {
+                    if (!ts.isStringLiteral(variant)) {
+                        return {
+                            type: "error",
+                            message: `The last element of the arg2 array must be an array literal`,
+                            start: file.getLineAndCharacterOfPosition(arg1.getStart()),
+                            end: file.getLineAndCharacterOfPosition(arg1.getEnd())
+                        };
+                    }
+                    variants.push(variant.text);
+                }
+                else {
+                    if (!ts.isArrayLiteralExpression(variant)) {
+                        return {
+                            type: "error",
+                            message: `This expression must be a array tuple literal`,
+                            start: file.getLineAndCharacterOfPosition(variant.getStart()),
+                            end: file.getLineAndCharacterOfPosition(variant.getEnd())
+                        };
+                    }
+                    if (variant.elements.length !== 2) {
+                        return {
+                            type: "error",
+                            message: `This array tuple literal must be of length 2`,
+                            start: file.getLineAndCharacterOfPosition(variant.getStart()),
+                            end: file.getLineAndCharacterOfPosition(variant.getEnd())
+                        };
+                    }
+                    const message = variant.elements[0];
+                    if (!ts.isStringLiteral(message)) {
+                        return {
+                            type: "error",
+                            message: `This expression must be a string literal`,
+                            start: file.getLineAndCharacterOfPosition(message.getStart()),
+                            end: file.getLineAndCharacterOfPosition(message.getEnd())
+                        };
+                    }
+                    variants.push(message.text);
+                }
+            }
+            return {
+                type: "ok",
+                translations: [{
+                        translation: {
+                            key: arg1.text,
+                            message: variants,
+                        },
+                        idStart: file.getLineAndCharacterOfPosition(arg1.getStart()),
+                        idEnd: file.getLineAndCharacterOfPosition(arg1.getEnd())
+                    }],
+            };
+        }
+    }
+    const translations = [];
+    const results = node.getChildren().map(n => {
+        return findTCalls(n, file);
+    });
+    for (let result of results) {
+        if (result.type === "error") {
+            return result;
+        }
+        else {
+            translations.push(...result.translations);
+        }
+    }
+    return {
+        type: "ok",
+        translations,
+    };
+}