@whiteslove/parsing-lexicon 0.2.0

package/src/hiring-languages.js

@@ -0,0 +1,135 @@
+import { aliasesOf, aliasesToRegex, findCanonical, normalizeUnicode } from './normalization.js';
+import { lexiconEntity } from './lexicon-core.js';
+
+const group = (canonical, aliases, extra = {}) => lexiconEntity(canonical, aliases, extra);
+
+export const LANGUAGES = Object.freeze([
+  group('en', { ru: ['английский', 'английского', 'английским', 'англ', 'англ.'], en: ['english'], uk: ['англійська', 'англійський', 'англійської'], ro: ['engleză', 'engleza', 'limba engleză'], uzLatn: ['ingliz tili', 'inglizcha'], uzCyrl: ['инглиз тили', 'инглизча'], kk: ['ағылшын тілі', 'ағылшынша'] }, { name: 'English' }),
+  group('ru', { ru: ['русский', 'русского', 'русским', 'рус.'], en: ['russian'], uk: ['російська', 'російський'], ro: ['rusă', 'rusa', 'limba rusă'], uzLatn: ['rus tili', 'ruscha'], uzCyrl: ['рус тили', 'русча'], kk: ['орыс тілі', 'орысша'] }, { name: 'Russian' }),
+  group('uz', { ru: ['узбекский', 'узбекского'], en: ['uzbek'], uk: ['узбецька', 'узбецький'], ro: ['uzbecă', 'uzbeca'], uzLatn: ["o'zbek tili", 'o‘zbek tili', 'ozbek tili', "o'zbekcha", 'o‘zbekcha'], uzCyrl: ['ўзбек тили', 'ўзбекча'], kk: ['өзбек тілі', 'өзбекше'] }, { name: 'Uzbek' }),
+  group('kk', { ru: ['казахский', 'казахского'], en: ['kazakh'], uk: ['казахська', 'казахський'], ro: ['kazahă', 'kazaha'], uzLatn: ['qozoq tili', 'qozoqcha'], uzCyrl: ['қозоқ тили', 'қозоқча'], kk: ['қазақ тілі', 'қазақша'] }, { name: 'Kazakh' }),
+  group('uk', { ru: ['украинский', 'украинского'], en: ['ukrainian'], uk: ['українська', 'український', 'українською'], ro: ['ucraineană', 'ucraineana'], uzLatn: ['ukrain tili'], uzCyrl: ['украин тили'], kk: ['украин тілі'] }, { name: 'Ukrainian' }),
+  group('tr', { ru: ['турецкий', 'турецкого'], en: ['turkish'], uk: ['турецька', 'турецький'], ro: ['turcă', 'turca'], uzLatn: ['turk tili', 'turkcha'], uzCyrl: ['турк тили'], kk: ['түрік тілі', 'түрікше'] }, { name: 'Turkish' }),
+  group('de', { ru: ['немецкий', 'немецкого'], en: ['german', 'deutsch'], uk: ['німецька', 'німецький'], ro: ['germană', 'germana'], uzLatn: ['nemis tili'], uzCyrl: ['немис тили'], kk: ['неміс тілі'] }, { name: 'German' }),
+  group('fr', { ru: ['французский', 'французского'], en: ['french', 'français', 'francais'], uk: ['французька', 'французький'], ro: ['franceză', 'franceza'], uzLatn: ['fransuz tili'], uzCyrl: ['француз тили'], kk: ['француз тілі'] }, { name: 'French' }),
+  group('es', { ru: ['испанский', 'испанского'], en: ['spanish', 'español', 'espanol'], uk: ['іспанська', 'іспанський'], ro: ['spaniolă', 'spaniola'], uzLatn: ['ispan tili'], uzCyrl: ['испан тили'], kk: ['испан тілі'] }, { name: 'Spanish' }),
+  group('zh', { ru: ['китайский', 'китайского', 'мандарин'], en: ['chinese', 'mandarin'], uk: ['китайська', 'китайський'], ro: ['chineză', 'chineza', 'mandarină'], uzLatn: ['xitoy tili', 'xitoycha'], uzCyrl: ['хитой тили'], kk: ['қытай тілі', 'қытайша'] }, { name: 'Chinese' }),
+  group('ko', { ru: ['корейский', 'корейского'], en: ['korean'], uk: ['корейська', 'корейський'], ro: ['coreeană', 'coreeana'], uzLatn: ['koreys tili'], uzCyrl: ['корейс тили'], kk: ['корей тілі'] }, { name: 'Korean' }),
+  group('ja', { ru: ['японский', 'японского'], en: ['japanese'], uk: ['японська', 'японський'], ro: ['japoneză', 'japoneza'], uzLatn: ['yapon tili'], uzCyrl: ['япон тили'], kk: ['жапон тілі'] }, { name: 'Japanese' }),
+  group('ar', { ru: ['арабский', 'арабского'], en: ['arabic'], uk: ['арабська', 'арабський'], ro: ['arabă', 'araba'], uzLatn: ['arab tili'], uzCyrl: ['араб тили'], kk: ['араб тілі'] }, { name: 'Arabic' }),
+  group('tg', { ru: ['таджикский', 'таджикского'], en: ['tajik'], uk: ['таджицька'], ro: ['tadjică', 'tadjica'], uzLatn: ['tojik tili', 'tojikcha'], uzCyrl: ['тожик тили'], kk: ['тәжік тілі'] }, { name: 'Tajik' }),
+  group('ky', { ru: ['кыргызский', 'киргизский', 'кыргызского'], en: ['kyrgyz', 'kirghiz'], uk: ['киргизька'], ro: ['kârgâză', 'kargaza'], uzLatn: ['qirgiz tili', "qirg'iz tili"], uzCyrl: ['қирғиз тили'], kk: ['қырғыз тілі', 'қырғызша'] }, { name: 'Kyrgyz' }),
+  group('ro', { ru: ['румынский', 'румынского'], en: ['romanian'], uk: ['румунська'], ro: ['română', 'romana', 'limba română'], uzLatn: ['rumin tili'], uzCyrl: ['румин тили'], kk: ['румын тілі'] }, { name: 'Romanian' }),
+  group('pl', { ru: ['польский', 'польского'], en: ['polish'], uk: ['польська'], ro: ['poloneză', 'poloneza'], uzLatn: ['polyak tili'], uzCyrl: ['поляк тили'], kk: ['поляк тілі'] }, { name: 'Polish' }),
+]);
+
+export const LANGUAGE_LEVELS = Object.freeze([
+  group('basic', { ru: ['базовый', 'начальный', 'со словарём', 'со словарем'], en: ['basic', 'beginner'], uk: ['базовий', 'початковий'], ro: ['de bază', 'de baza', 'începător', 'incepator'], uzLatn: ['boshlangich', "boshlang'ich", 'asosiy'], uzCyrl: ['бошланғич', 'асосий'], kk: ['бастапқы', 'негізгі'] }),
+  group('elementary', { ru: ['элементарный'], en: ['elementary'], uk: ['елементарний'], ro: ['elementar'], uzLatn: ['elementar'], uzCyrl: ['элементар'], kk: ['элементарлық'] }),
+  group('preIntermediate', { ru: ['ниже среднего', 'pre-intermediate'], en: ['pre-intermediate', 'pre intermediate'], uk: ['нижче середнього'], ro: ['pre-intermediar'], uzLatn: ['pre-intermediate'], uzCyrl: ['pre-intermediate'], kk: ['pre-intermediate'] }),
+  group('intermediate', { ru: ['средний', 'разговорный', 'разговорный уровень'], en: ['intermediate', 'conversational', 'working knowledge'], uk: ['середній', 'розмовний'], ro: ['intermediar', 'conversațional', 'conversational'], uzLatn: ['orta', "o'rta", 'suhbat darajasi'], uzCyrl: ['ўрта', 'суҳбат даражаси'], kk: ['орта', 'сөйлесу деңгейі'] }),
+  group('upperIntermediate', { ru: ['выше среднего', 'upper-intermediate'], en: ['upper-intermediate', 'upper intermediate'], uk: ['вище середнього'], ro: ['upper-intermediate'], uzLatn: ['upper-intermediate'], uzCyrl: ['upper-intermediate'], kk: ['upper-intermediate'] }),
+  group('advanced', { ru: ['продвинутый', 'уверенный'], en: ['advanced', 'proficient'], uk: ['просунутий', 'впевнений'], ro: ['avansat', 'competent'], uzLatn: ['yuqori daraja', 'ishonchli'], uzCyrl: ['юқори даража'], kk: ['жоғары деңгей', 'сенімді'] }),
+  group('fluent', { ru: ['свободный', 'свободное владение', 'в совершенстве'], en: ['fluent', 'fluency', 'full professional proficiency'], uk: ['вільний', 'вільне володіння', 'досконало'], ro: ['fluent', 'fluență', 'fluenta'], uzLatn: ['erkin', 'erkin gaplashish'], uzCyrl: ['эркин', 'эркин гаплашиш'], kk: ['еркін', 'еркін сөйлейді'] }),
+  group('native', { ru: ['родной', 'носитель языка'], en: ['native', 'native speaker', 'mother tongue'], uk: ['рідна', 'носій мови'], ro: ['nativ', 'vorbitor nativ', 'limbă maternă'], uzLatn: ['ona tili', 'native speaker'], uzCyrl: ['она тили'], kk: ['ана тілі', 'тіл иесі'] }),
+]);
+
+export const LANGUAGE_CONTEXT_TERMS = Object.freeze({
+  required: group('required', {
+    ru: ['требуется знание языка', 'знание языка обязательно', 'обязательное знание', 'необходимо знание', 'необходим язык', 'требуется владение', 'свободное владение обязательно', 'со знанием английского', 'английский обязателен'],
+    en: ['language required', 'english required', 'must speak', 'must know', 'fluency required', 'proficiency required', 'required language'],
+    uk: ['знання мови обов’язкове', "знання мови обов'язкове", 'потрібне знання мови', 'необхідне знання'],
+    ro: ['limba este obligatorie', 'cunoașterea limbii este obligatorie', 'trebuie să vorbească'],
+    uzLatn: ['til bilish talab qilinadi', 'tilni bilish shart', 'ingliz tilini bilish kerak', 'tilni yaxshi bilishi kerak'],
+    uzCyrl: ['тил билиш талаб қилинади', 'тилни билиш шарт', 'инглиз тилини билиш керак'],
+    kk: ['тіл білу талап етіледі', 'тілді білу міндетті', 'ағылшын тілін білу қажет'],
+  }),
+  preferred: group('preferred', {
+    ru: ['желательно знание', 'знание будет плюсом', 'будет преимуществом', 'приветствуется знание'],
+    en: ['preferred', 'nice to have', 'language is a plus', 'would be an advantage'],
+    uk: ['бажане знання', 'знання буде плюсом', 'буде перевагою'],
+    ro: ['cunoașterea constituie un avantaj', 'de preferat să cunoască'],
+    uzLatn: ['til bilsa yaxshi', 'til bilishi afzal', 'til plus boladi'],
+    uzCyrl: ['тил билса яхши', 'тил билиши афзал'],
+    kk: ['тіл білу артықшылық болады', 'тіл білгені дұрыс'],
+  }),
+  notRequired: group('notRequired', {
+    ru: ['язык не требуется', 'знание языка не обязательно', 'без обязательного знания', 'язык не нужен'],
+    en: ['language not required', 'english not required', 'language optional', 'no language requirement'],
+    uk: ['мова не потрібна', 'знання мови не обов’язкове'],
+    ro: ['limba nu este necesară', 'limba nu este obligatorie'],
+    uzLatn: ['til shart emas', 'til bilish talab qilinmaydi'],
+    uzCyrl: ['тил шарт эмас', 'тил билиш талаб қилинмайди'],
+    kk: ['тіл міндетті емес', 'тіл білу талап етілмейді'],
+  }),
+  candidateHas: group('candidateHas', {
+    ru: ['владею языками', 'знаю английский', 'владею английским', 'свободно говорю', 'разговорный английский', 'английский на уровне'],
+    en: ['i speak', 'i know', 'fluent in', 'proficient in', 'native speaker', 'working proficiency'],
+    uk: ['володію мовами', 'знаю англійську', 'вільно говорю'],
+    ro: ['vorbesc', 'cunosc limba', 'fluent în', 'fluent in'],
+    uzLatn: ['tillarni bilaman', 'ingliz tilini bilaman', 'erkin gaplashaman'],
+    uzCyrl: ['тилларни биламан', 'инглиз тилини биламан', 'эркин гаплашаман'],
+    kk: ['тілдерді білемін', 'ағылшын тілін білемін', 'еркін сөйлеймін'],
+  }),
+});
+
+const CEFR_RE = /(?:^|[^A-Za-z0-9])(A1|A2|B1|B2|C1|C2)(?![A-Za-z0-9])/i;
+const NEGATION_RE = /(?:не\s+(?:требуется|обязател|нужен|нужна)|без\s+обязатель|not\s+required|not\s+mandatory|optional|nu\s+(?:este\s+)?(?:necesar|obligatoriu)|shart\s+emas|talab\s+qilinmaydi|міндетті\s+емес|талап\s+етілмейді)/iu;
+const REQUIRED_RE = /(?:обязател|требуется|необходим|required|must\s+(?:speak|know)|mandatory|потріб|необхід|obligatoriu|trebuie|shart|talab\s+qilinadi|міндетті|талап\s+етіледі|қажет)/iu;
+const PREFERRED_RE = /(?:желатель|плюс|приветств|preferred|nice\s+to\s+have|advantage|бажан|переваг|avantaj|afzal|bolsa\s+yaxshi|артықшылық)/iu;
+const CANDIDATE_RE = /(?:владею|знаю|говорю|мой\s+уровень|i\s+(?:speak|know)|fluent\s+in|proficient\s+in|володію|vorbesc|bilaman|gaplashaman|білемін|сөйлеймін)/iu;
+
+function relationFromWindow(window, mode) {
+  if (NEGATION_RE.test(window)) return 'notRequired';
+  if (PREFERRED_RE.test(window)) return 'preferred';
+  if (REQUIRED_RE.test(window)) return 'required';
+  if (CANDIDATE_RE.test(window)) return 'candidateHas';
+  return mode === 'candidate' ? 'candidateHas' : mode === 'vacancy' ? 'mentioned' : 'mentioned';
+}
+
+function levelFromWindow(window) {
+  const cefr = window.match(CEFR_RE)?.[1]?.toUpperCase() || null;
+  if (cefr) return { level: null, cefr };
+  const qualitative = findCanonical(window, LANGUAGE_LEVELS, { partial: true });
+  return { level: qualitative?.canonical || null, cefr: null };
+}
+
+export function languageByCode(code) {
+  return LANGUAGES.find((entry) => entry.canonical === String(code || '').toLowerCase()) || null;
+}
+
+export function parseLanguageMentions(value, { mode = null } = {}) {
+  const text = normalizeUnicode(value || '');
+  if (!text) return [];
+  const results = [];
+  for (const language of LANGUAGES) {
+    const re = aliasesToRegex([language.canonical, language.name, ...aliasesOf(language)], 'giu');
+    for (const match of text.matchAll(re)) {
+      const index = match.index ?? 0;
+      const raw = match[0].trim();
+      const start = Math.max(0, index - 90);
+      const end = Math.min(text.length, index + match[0].length + 90);
+      const window = text.slice(start, end);
+      const levels = levelFromWindow(window);
+      results.push(Object.freeze({
+        language: language.canonical,
+        name: language.name,
+        relation: relationFromWindow(window, mode),
+        level: levels.level,
+        cefr: levels.cefr,
+        matched: raw,
+        index,
+      }));
+    }
+  }
+  results.sort((a, b) => a.index - b.index);
+  const deduped = [];
+  const seen = new Set();
+  for (const result of results) {
+    const key = `${result.language}:${result.relation}:${result.cefr || result.level || ''}`;
+    if (seen.has(key)) continue;
+    seen.add(key);
+    deduped.push(result);
+  }
+  return deduped;
+}

package/src/hiring-location-fields.d.ts

@@ -0,0 +1,3 @@
+export function detectHiringLocationName(value: unknown, country: unknown): string | null;
+export function isHiringNonCityLocation(value: unknown): boolean;
+export function isHiringRemoteLocationScope(value: unknown): boolean;

package/src/hiring-location-fields.js

@@ -0,0 +1,53 @@
+import { detectCityFromText } from './geography-detection.js';
+
+const B = '(?<![\\p{L}\\p{N}])';
+const E = '(?![\\p{L}\\p{N}])';
+const re = (pattern) => new RegExp(`${B}(?:${pattern})(?:\\p{Script=Cyrillic}{1,3})?${E}`, 'iu');
+
+const NON_CITY_LOCATION_RE = /^(?:europe|europa|європа|европа|штати|states|worldwide|global|anywhere|emea|apac)$/iu;
+const REMOTE_LOCATION_SCOPE_RE = /^(?:worldwide|global|work\s+from\s+anywhere|anywhere(?:\s+in\b.*)?)$/iu;
+
+export function isHiringNonCityLocation(value) {
+  return NON_CITY_LOCATION_RE.test(String(value || '').trim());
+}
+
+export function isHiringRemoteLocationScope(value) {
+  return REMOTE_LOCATION_SCOPE_RE.test(String(value || '').trim());
+}
+
+// Public Uzbek CV boards sometimes expose only a region. Keep the historic
+// Personal-Site canonical names as a stable consumer contract while matching
+// multilingual source spellings centrally.
+const UZ_HIRING_REGIONS = Object.freeze([
+  ['Tashkent Region', re('ташкент(?:ская)?\\s+(?:обл(?:асть)?\\.?|region)|toshkent\\s+viloyati|tashkent\\s+region')],
+  ['Karakalpakstan', re("каракалпакстан|qoraqalpog(?:'|’)iston|karakalpakstan")],
+  ['Kashkadarya', re('кашкадар\\p{L}*|qashqadaryo|kashkadarya')],
+  ['Surkhandarya', re('сурхандар\\p{L}*|surxondaryo|surkhandarya')],
+  ['Jizzakh', re('джизак\\p{L}*|jizzax|jizzakh')],
+  ['Syrdarya', re('сырдар\\p{L}*|sirdaryo|syrdarya')],
+  ['Khorezm', re('хорезм\\p{L}*|xorazm|khorezm')],
+]);
+
+// Keep legacy consumer canonicals and inflected aliases where the broader
+// geography catalog intentionally uses a different modern spelling.
+const HIRING_CITY_OVERRIDES = Object.freeze({
+  UZ: Object.freeze([
+    ['Navoi', re('навои|navoi')],
+  ]),
+  UA: Object.freeze([
+    ['Odesa', re('одесс|одес|odesa|odessa')],
+  ]),
+});
+
+export function detectHiringLocationName(value, country) {
+  const text = String(value || '');
+  const code = String(country || '').toUpperCase();
+  if (!text || !code) return null;
+  if (code === 'UZ') {
+    const region = UZ_HIRING_REGIONS.find(([, matcher]) => matcher.test(text));
+    if (region) return region[0];
+  }
+  const override = HIRING_CITY_OVERRIDES[code]?.find(([, matcher]) => matcher.test(text));
+  if (override) return override[0];
+  return detectCityFromText(text, code)?.canonical || null;
+}

package/src/hiring-professions-ro.js

@@ -0,0 +1,191 @@
+export const ROMANIAN_GROUP_ALIASES = Object.freeze({
+  software_development: ['dezvoltare software', 'programare', 'dezvoltare aplicații', 'dezvoltare aplicatii'],
+  quality_assurance: ['asigurarea calității', 'asigurarea calitatii', 'testare software'],
+  infrastructure: ['infrastructură', 'infrastructura', 'administrare sisteme'],
+  data: ['date', 'analiză de date', 'analiza de date', 'analitică', 'analitica'],
+  information_security: ['securitatea informației', 'securitatea informatiei', 'securitate cibernetică', 'securitate cibernetica'],
+  design: ['design', 'proiectare'],
+  product: ['produs', 'management de produs'],
+  project_management: ['management de proiect', 'management proiecte'],
+  sales: ['vânzări', 'vanzari'],
+  marketing: ['marketing'],
+  finance: ['finanțe', 'finante', 'contabilitate'],
+  human_resources: ['resurse umane', 'recrutare'],
+  customer_support: ['suport clienți', 'suport clienti', 'relații clienți', 'relatii clienti'],
+  administration: ['administrație', 'administratie', 'birou'],
+  logistics: ['logistică', 'logistica', 'depozit'],
+  retail: ['retail', 'comerț cu amănuntul', 'comert cu amanuntul'],
+  hospitality: ['ospitalitate', 'horeca', 'restaurant', 'hotel'],
+  medicine: ['medicină', 'medicina', 'sănătate', 'sanatate'],
+  education: ['educație', 'educatie', 'învățământ', 'invatamant'],
+  construction: ['construcții', 'constructii'],
+  manufacturing: ['producție', 'productie', 'industrie'],
+  transport: ['transport', 'șoferi', 'soferi'],
+  security: ['securitate', 'pază', 'paza'],
+  legal: ['juridic', 'drept'],
+  media_content: ['media', 'conținut', 'continut'],
+  beauty_wellness: ['frumusețe', 'frumusete', 'wellness'],
+  agriculture: ['agricultură', 'agricultura'],
+});
+
+export const ROMANIAN_PROFESSION_ALIASES = Object.freeze({
+  software_developer: ['dezvoltator software', 'inginer software', 'programator'],
+  frontend_developer: ['dezvoltator frontend', 'programator frontend', 'inginer frontend'],
+  backend_developer: ['dezvoltator backend', 'programator backend', 'inginer backend'],
+  fullstack_developer: ['dezvoltator full stack', 'dezvoltator fullstack', 'programator full stack'],
+  mobile_developer: ['dezvoltator aplicații mobile', 'dezvoltator aplicatii mobile', 'programator mobile'],
+  ios_developer: ['dezvoltator ios', 'programator ios'],
+  android_developer: ['dezvoltator android', 'programator android'],
+  flutter_developer: ['dezvoltator flutter'],
+  react_native_developer: ['dezvoltator react native'],
+  game_developer: ['dezvoltator jocuri', 'programator jocuri'],
+  embedded_developer: ['dezvoltator embedded', 'inginer sisteme embedded'],
+  solutions_architect: ['arhitect soluții', 'arhitect solutii'],
+  software_architect: ['arhitect software'],
+  integration_engineer: ['inginer integrare', 'inginer de integrare'],
+  qa_engineer: ['inginer qa', 'inginer testare', 'tester software'],
+  manual_qa_engineer: ['tester manual', 'inginer testare manuală', 'inginer testare manuala'],
+  qa_automation_engineer: ['inginer automatizare teste', 'tester automatizare'],
+  qa_lead: ['lider qa', 'coordonator qa'],
+  devops_engineer: ['inginer devops'],
+  sre_engineer: ['inginer sre', 'inginer fiabilitate site'],
+  cloud_engineer: ['inginer cloud'],
+  system_administrator: ['administrator de sistem', 'administrator sisteme'],
+  network_engineer: ['inginer rețea', 'inginer retea', 'administrator rețea', 'administrator retea'],
+  database_administrator: ['administrator baze de date', 'administrator bază de date'],
+  data_analyst: ['analist de date', 'analist date'],
+  business_analyst: ['analist de business', 'analist business'],
+  system_analyst: ['analist de sistem', 'analist sistem'],
+  data_engineer: ['inginer de date', 'inginer date'],
+  data_scientist: ['cercetător de date', 'cercetator de date', 'specialist data science'],
+  ml_engineer: ['inginer machine learning', 'inginer învățare automată', 'inginer invatare automata'],
+  ai_engineer: ['inginer inteligență artificială', 'inginer inteligenta artificiala'],
+  bi_analyst: ['analist bi', 'analist business intelligence'],
+  security_engineer: ['inginer securitate', 'inginer securitate cibernetică', 'inginer securitate cibernetica'],
+  security_analyst: ['analist securitate', 'analist securitate cibernetică', 'analist soc'],
+  penetration_tester: ['tester de penetrare', 'specialist testare penetrare'],
+  product_designer: ['designer de produs', 'designer produs'],
+  ui_designer: ['designer ui', 'designer interfață', 'designer interfata'],
+  ux_designer: ['designer ux', 'designer experiență utilizator', 'designer experienta utilizator'],
+  ui_ux_designer: ['designer ui ux', 'designer ui/ux'],
+  graphic_designer: ['designer grafic'],
+  web_designer: ['designer web'],
+  interior_designer: ['designer de interior', 'designer interior'],
+  product_manager: ['manager de produs', 'manager produs'],
+  product_owner: ['proprietar de produs', 'product owner'],
+  product_analyst: ['analist de produs', 'analist produs'],
+  project_manager: ['manager de proiect', 'manager proiect'],
+  program_manager: ['manager de program', 'manager program'],
+  project_coordinator: ['coordonator de proiect', 'coordonator proiect'],
+  sales_manager: ['manager de vânzări', 'manager vanzari'],
+  sales_representative: ['reprezentant de vânzări', 'reprezentant vanzari', 'agent de vânzări', 'agent vanzari'],
+  account_manager: ['manager de cont', 'account manager', 'manager clienți', 'manager clienti'],
+  key_account_manager: ['manager clienți cheie', 'manager clienti cheie'],
+  business_development_manager: ['manager dezvoltare afaceri', 'manager de dezvoltare a afacerii'],
+  sales_director: ['director de vânzări', 'director vanzari'],
+  real_estate_agent: ['agent imobiliar', 'consultant imobiliar'],
+  insurance_agent: ['agent de asigurări', 'agent de asigurari'],
+  marketing_manager: ['manager marketing'],
+  digital_marketing_manager: ['manager marketing digital'],
+  social_media_manager: ['manager social media', 'administrator rețele sociale', 'administrator retele sociale'],
+  seo_specialist: ['specialist seo'],
+  content_marketing_manager: ['manager marketing de conținut', 'manager marketing continut'],
+  accountant: ['contabil'],
+  chief_accountant: ['contabil șef', 'contabil sef'],
+  financial_analyst: ['analist financiar'],
+  finance_manager: ['manager financiar'],
+  controller: ['controlor financiar', 'controller financiar'],
+  hr_manager: ['manager resurse umane', 'manager hr'],
+  recruiter: ['recrutor', 'specialist recrutare'],
+  talent_acquisition_specialist: ['specialist achiziție talente', 'specialist achizitie talente'],
+  hr_business_partner: ['partener de afaceri hr', 'hr business partner'],
+  customer_support_specialist: ['specialist suport clienți', 'specialist suport clienti'],
+  call_center_operator: ['operator call center', 'operator centru de apel'],
+  customer_success_manager: ['manager succes clienți', 'manager succes clienti'],
+  office_manager: ['manager de birou', 'office manager'],
+  administrative_assistant: ['asistent administrativ'],
+  executive_assistant: ['asistent executiv'],
+  secretary: ['secretar', 'secretară', 'secretara'],
+  logistics_manager: ['manager logistică', 'manager logistica'],
+  logistics_specialist: ['specialist logistică', 'specialist logistica'],
+  warehouse_worker: ['lucrător depozit', 'lucrator depozit', 'muncitor depozit'],
+  warehouse_manager: ['manager depozit', 'șef depozit', 'sef depozit'],
+  store_manager: ['manager magazin', 'șef magazin', 'sef magazin'],
+  cashier: ['casier', 'casieră', 'casiera'],
+  sales_assistant: ['consultant vânzări', 'consultant vanzari', 'asistent vânzări', 'asistent vanzari'],
+  merchandiser: ['merchandiser', 'mercantizor'],
+  waiter: ['ospătar', 'ospatar'],
+  bartender: ['barman'],
+  barista: ['barista'],
+  cook: ['bucătar', 'bucatar'],
+  chef: ['bucătar șef', 'bucatar sef', 'chef bucătar'],
+  receptionist: ['recepționer', 'receptioner', 'recepționeră', 'receptionera'],
+  hotel_manager: ['manager hotel'],
+  doctor: ['medic', 'doctor'],
+  nurse: ['asistent medical', 'asistentă medicală', 'asistenta medicala'],
+  pharmacist: ['farmacist', 'farmacistă', 'farmacista'],
+  dentist: ['medic dentist', 'stomatolog'],
+  psychologist: ['psiholog'],
+  teacher: ['profesor', 'profesoară', 'profesoara'],
+  tutor: ['meditator', 'tutore'],
+  kindergarten_teacher: ['educatoare', 'educator grădiniță', 'educator gradinita'],
+  civil_engineer: ['inginer constructor', 'inginer civil'],
+  architect: ['arhitect'],
+  construction_manager: ['manager construcții', 'manager constructii'],
+  site_manager: ['șef de șantier', 'sef de santier'],
+  electrician: ['electrician'],
+  plumber: ['instalator'],
+  welder: ['sudor'],
+  carpenter: ['tâmplar', 'tamplar'],
+  painter: ['zugrav', 'vopsitor'],
+  crane_operator: ['macaragiu', 'operator macara'],
+  production_worker: ['muncitor producție', 'muncitor productie', 'operator producție'],
+  machine_operator: ['operator utilaj', 'operator mașină', 'operator masina'],
+  cnc_operator: ['operator cnc'],
+  mechanical_engineer: ['inginer mecanic'],
+  electrical_engineer: ['inginer electrician', 'inginer electric'],
+  maintenance_technician: ['tehnician mentenanță', 'tehnician mentenanta'],
+  driver: ['șofer', 'sofer'],
+  truck_driver: ['șofer camion', 'sofer camion', 'șofer tir', 'sofer tir'],
+  taxi_driver: ['șofer taxi', 'sofer taxi', 'taximetrist'],
+  bus_driver: ['șofer autobuz', 'sofer autobuz'],
+  courier: ['curier'],
+  forklift_operator: ['stivuitorist', 'operator stivuitor'],
+  auto_mechanic: ['mecanic auto'],
+  security_guard: ['agent de securitate', 'paznic', 'agent pază', 'agent paza'],
+  lawyer: ['avocat', 'jurist'],
+  legal_counsel: ['consilier juridic'],
+  paralegal: ['asistent juridic'],
+  compliance_specialist: ['specialist conformitate', 'ofițer conformitate', 'ofiter conformitate'],
+  copywriter: ['copywriter', 'redactor publicitar'],
+  content_manager: ['manager de conținut', 'manager continut'],
+  editor: ['redactor', 'editor'],
+  journalist: ['jurnalist'],
+  translator: ['traducător', 'traducator', 'interpret'],
+  video_editor: ['editor video', 'montaj video'],
+  photographer: ['fotograf'],
+  hairdresser: ['coafor', 'coafeză', 'coafeza'],
+  barber: ['frizer', 'barber'],
+  manicurist: ['manichiuristă', 'manichiurista', 'tehnician unghii'],
+  cosmetologist: ['cosmetician', 'cosmeticiană'],
+  massage_therapist: ['maseur', 'maseuză', 'maseuza'],
+  fitness_trainer: ['antrenor fitness', 'antrenor personal'],
+  farmer: ['fermier'],
+  agronomist: ['agronom'],
+  tractor_driver: ['tractorist'],
+  farm_worker: ['muncitor agricol', 'lucrător agricol', 'lucrator agricol'],
+});
+
+export const ROMANIAN_SENIORITY_ALIASES = Object.freeze({
+  intern: ['stagiar', 'internship', 'practicant'],
+  junior: ['junior', 'începător', 'incepator'],
+  middle: ['nivel mediu', 'intermediar', 'mid-level'],
+  senior: ['senior', 'specialist senior', 'experimentat'],
+  staff: ['staff engineer', 'inginer staff'],
+  principal: ['principal', 'inginer principal'],
+  lead: ['lead', 'lider tehnic', 'lider de echipă', 'lider de echipa'],
+  head: ['șef departament', 'sef departament', 'conducător departament', 'conducator departament'],
+  director: ['director'],
+  vp: ['vicepreședinte', 'vicepresedinte'],
+  chief: ['director executiv', 'director tehnic', 'director financiar', 'director operațional', 'director operational'],
+});