feat(i18n): expand supported languages from 31 to 49 with flags and locale formats

Add 18 previously missing language entries to SUPPORTED_LANGUAGES in
app/utils/i18n.py so every translation JSON file in frontend/translations/
is properly indexed and served by the language selector:

New languages: af, ar, cy, eo, fa, fy, gl, he, ja, kn, ko, li, nds, no, pa, sr, vi, vls

Each new language entry includes:
- Correct ISO 639-1/639-3 code matching its JSON filename
- Native name and display name
- Appropriate country/language flag emoji
- Locale-specific date and number formatting rules in _LOCALE_FORMATS

Also: rename nb "Norwegian" → "Norwegian Bokmål" to distinguish it from no "Norwegian".

Update tests/test_i18n.py:
- Count assertions: 31 → 49
- Expected code set expanded to all 49 codes
- Fix test_unsupported_language_fallback (ja/ko now supported, use xx/yy)

Update docs/InternationalizationGuide.md:
- Language count: 10 → 49
- Full language table with flags, native names, tiers
- Complete file structure listing all 49 JSON files

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-03-13 14:03:31 +00:00
parent 34c5d9e55e
commit 87d85624be
3 changed files with 273 additions and 29 deletions
+150 -3
View File
@@ -2,7 +2,7 @@
Provides a JSON-based translation system for the DocuElevate UI with:
* **31 supported languages** covering all major European languages plus ZH
* **49 supported languages** covering European, Asian, Middle-Eastern, and other languages
* Browser ``Accept-Language`` detection with cookie & user-profile persistence
* AI-powered fallback translation via the configured LLM provider
* Locale-aware date, number, and file-size formatting helpers
@@ -42,7 +42,8 @@ SUPPORTED_LANGUAGES: list[dict[str, str]] = [
{"code": "pt", "name": "Portuguese", "native": "Português", "flag": "🇵🇹"},
# --- Tier 2: Western & Northern European ---
{"code": "nl", "name": "Dutch", "native": "Nederlands", "flag": "🇳🇱"},
{"code": "nb", "name": "Norwegian", "native": "Norsk", "flag": "🇳🇴"},
{"code": "nb", "name": "Norwegian Bokmål", "native": "Norsk bokmål", "flag": "🇳🇴"},
{"code": "no", "name": "Norwegian", "native": "Norsk", "flag": "🇳🇴"},
{"code": "da", "name": "Danish", "native": "Dansk", "flag": "🇩🇰"},
{"code": "sv", "name": "Swedish", "native": "Svenska", "flag": "🇸🇪"},
{"code": "fi", "name": "Finnish", "native": "Suomi", "flag": "🇫🇮"},
@@ -50,6 +51,12 @@ SUPPORTED_LANGUAGES: list[dict[str, str]] = [
{"code": "ga", "name": "Irish", "native": "Gaeilge", "flag": "🇮🇪"},
{"code": "lb", "name": "Luxembourgish", "native": "Lëtzebuergesch", "flag": "🇱🇺"},
{"code": "ca", "name": "Catalan", "native": "Català", "flag": "🏴"},
{"code": "cy", "name": "Welsh", "native": "Cymraeg", "flag": "🏴󠁧󠁢󠁷󠁬󠁳󠁿"},
{"code": "fy", "name": "Frisian", "native": "Frysk", "flag": "🇳🇱"},
{"code": "gl", "name": "Galician", "native": "Galego", "flag": "🇪🇸"},
{"code": "li", "name": "Limburgish", "native": "Limburgs", "flag": "🇳🇱"},
{"code": "vls", "name": "West Flemish", "native": "West-Vlams", "flag": "🇧🇪"},
{"code": "nds", "name": "Low German", "native": "Plattdüütsch", "flag": "🇩🇪"},
# --- Tier 3: Central & Eastern European ---
{"code": "pl", "name": "Polish", "native": "Polski", "flag": "🇵🇱"},
{"code": "cs", "name": "Czech", "native": "Čeština", "flag": "🇨🇿"},
@@ -63,11 +70,24 @@ SUPPORTED_LANGUAGES: list[dict[str, str]] = [
{"code": "et", "name": "Estonian", "native": "Eesti", "flag": "🇪🇪"},
{"code": "lv", "name": "Latvian", "native": "Latviešu", "flag": "🇱🇻"},
{"code": "lt", "name": "Lithuanian", "native": "Lietuvių", "flag": "🇱🇹"},
# --- Tier 4: Non-EU European & Other ---
{"code": "sr", "name": "Serbian", "native": "Српски", "flag": "🇷🇸"},
# --- Tier 4: Non-EU European, Middle Eastern & African ---
{"code": "tr", "name": "Turkish", "native": "Türkçe", "flag": "🇹🇷"},
{"code": "uk", "name": "Ukrainian", "native": "Українська", "flag": "🇺🇦"},
{"code": "ru", "name": "Russian", "native": "Русский", "flag": "🇷🇺"},
{"code": "he", "name": "Hebrew", "native": "עברית", "flag": "🇮🇱"},
{"code": "ar", "name": "Arabic", "native": "العربية", "flag": "🇸🇦"},
{"code": "fa", "name": "Persian", "native": "فارسی", "flag": "🇮🇷"},
{"code": "af", "name": "Afrikaans", "native": "Afrikaans", "flag": "🇿🇦"},
# --- Tier 5: Asian languages ---
{"code": "zh", "name": "Chinese", "native": "中文", "flag": "🇨🇳"},
{"code": "ja", "name": "Japanese", "native": "日本語", "flag": "🇯🇵"},
{"code": "ko", "name": "Korean", "native": "한국어", "flag": "🇰🇷"},
{"code": "vi", "name": "Vietnamese", "native": "Tiếng Việt", "flag": "🇻🇳"},
{"code": "pa", "name": "Punjabi", "native": "ਪੰਜਾਬੀ", "flag": "🇮🇳"},
{"code": "kn", "name": "Kannada", "native": "ಕನ್ನಡ", "flag": "🇮🇳"},
# --- Tier 6: Constructed & other languages ---
{"code": "eo", "name": "Esperanto", "native": "Esperanto", "flag": "🌍"},
]
SUPPORTED_LANGUAGE_CODES: set[str] = {lang["code"] for lang in SUPPORTED_LANGUAGES}
@@ -503,6 +523,133 @@ _LOCALE_FORMATS: dict[str, dict[str, Any]] = {
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
# --- New languages ---
"no": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"cy": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"fy": {
"date": "%d %B %Y",
"date_short": "%d-%m-%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"gl": {
"date": "%d de %B de %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d de %B de %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"li": {
"date": "%d %B %Y",
"date_short": "%d-%m-%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"vls": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"nds": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"sr": {
"date": "%d. %B %Y.",
"date_short": "%d.%m.%Y.",
"datetime": "%d. %B %Y. %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"he": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"ar": {
"date": "%d %B %Y",
"date_short": "%Y/%m/%d",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"fa": {
"date": "%d %B %Y",
"date_short": "%Y/%m/%d",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"af": {
"date": "%d %B %Y",
"date_short": "%Y/%m/%d",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"ja": {
"date": "%Y年%m月%d",
"date_short": "%Y/%m/%d",
"datetime": "%Y年%m月%d%H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"ko": {
"date": "%Y년 %m월 %d",
"date_short": "%Y.%m.%d",
"datetime": "%Y년 %m월 %d%H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"vi": {
"date": "ngày %d tháng %m năm %Y",
"date_short": "%d/%m/%Y",
"datetime": "ngày %d tháng %m năm %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"pa": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"kn": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"eo": {
"date": "%d-a de %B %Y",
"date_short": "%Y-%m-%d",
"datetime": "%d-a de %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
}