Merge pull request #629 from christianlouis/copilot/update-translation-file-indexing

feat(i18n): index all 49 translation files and add flags/locale formats

app/utils/i18n.py

@@ -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": "🏴󠁧󠁢󠁷󠁬󠁳󠁿"},  # Wales subdivision flag (U+1F3F4 + tag chars)
+    {"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日",
+        "date_short": "%Y/%m/%d",
+        "datetime": "%Y年%m月%d日 %H:%M",
+        "thousands_sep": ",",
+        "decimal_sep": ".",
+    },
+    "ko": {
+        "date": "%Y년 %m월 %d일",
+        "date_short": "%Y.%m.%d",
+        "datetime": "%Y년 %m월 %d일 %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": ",",
+    },
 }
 
 

docs/InternationalizationGuide.md

@@ -1,27 +1,67 @@
 # Internationalization (i18n) & Localization (l10n) Guide
 
-DocuElevate supports **10 languages** for its web UI, with automatic browser
+DocuElevate supports **49 languages** for its web UI, with automatic browser
 language detection, user-preference persistence, and an AI-powered fallback
 translator for strings that haven't been manually translated yet.
 
 ## Supported Languages
 
-| Code | Language    | Native Name | Priority |
+| Code  | Language         | Native Name        | Flag | Priority |
-|------|------------|-------------|----------|
+|-------|------------------|--------------------|------|----------|
-| `en` | English    | English     | Tier 1   |
+| `en`  | English          | English            | 🇬🇧   | Tier 1   |
-| `de` | German     | Deutsch     | Tier 1   |
+| `de`  | German           | Deutsch            | 🇩🇪   | Tier 1   |
-| `fr` | French     | Français    | Tier 1   |
+| `fr`  | French           | Français           | 🇫🇷   | Tier 1   |
-| `es` | Spanish    | Español     | Tier 1   |
+| `es`  | Spanish          | Español            | 🇪🇸   | Tier 1   |
-| `it` | Italian    | Italiano    | Tier 1   |
+| `it`  | Italian          | Italiano           | 🇮🇹   | Tier 1   |
-| `pt` | Portuguese | Português   | Tier 1   |
+| `pt`  | Portuguese       | Português          | 🇵🇹   | Tier 1   |
-| `nl` | Dutch      | Nederlands  | Tier 2   |
+| `nl`  | Dutch            | Nederlands         | 🇳🇱   | Tier 2   |
-| `pl` | Polish     | Polski      | Tier 2   |
+| `nb`  | Norwegian Bokmål | Norsk bokmål       | 🇳🇴   | Tier 2   |
-| `zh` | Chinese    | 中文         | Tier 2   |
+| `no`  | Norwegian        | Norsk              | 🇳🇴   | Tier 2   |
-| `ru` | Russian    | Русский     | Tier 2   |
+| `da`  | Danish           | Dansk              | 🇩🇰   | Tier 2   |
+| `sv`  | Swedish          | Svenska            | 🇸🇪   | Tier 2   |
+| `fi`  | Finnish          | Suomi              | 🇫🇮   | Tier 2   |
+| `is`  | Icelandic        | Íslenska           | 🇮🇸   | Tier 2   |
+| `ga`  | Irish            | Gaeilge            | 🇮🇪   | Tier 2   |
+| `lb`  | Luxembourgish    | Lëtzebuergesch     | 🇱🇺   | Tier 2   |
+| `ca`  | Catalan          | Català             | 🏴    | Tier 2   |
+| `cy`  | Welsh            | Cymraeg            | 🏴󠁧󠁢󠁷󠁬󠁳󠁿   | Tier 2   |
+| `fy`  | Frisian          | Frysk              | 🇳🇱   | Tier 2   |
+| `gl`  | Galician         | Galego             | 🇪🇸   | Tier 2   |
+| `li`  | Limburgish       | Limburgs           | 🇳🇱   | Tier 2   |
+| `vls` | West Flemish     | West-Vlams         | 🇧🇪   | Tier 2   |
+| `nds` | Low German       | Plattdüütsch       | 🇩🇪   | Tier 2   |
+| `pl`  | Polish           | Polski             | 🇵🇱   | Tier 3   |
+| `cs`  | Czech            | Čeština            | 🇨🇿   | Tier 3   |
+| `sk`  | Slovak           | Slovenčina         | 🇸🇰   | Tier 3   |
+| `hu`  | Hungarian        | Magyar             | 🇭🇺   | Tier 3   |
+| `sl`  | Slovenian        | Slovenščina        | 🇸🇮   | Tier 3   |
+| `hr`  | Croatian         | Hrvatski           | 🇭🇷   | Tier 3   |
+| `ro`  | Romanian         | Română             | 🇷🇴   | Tier 3   |
+| `bg`  | Bulgarian        | Български          | 🇧🇬   | Tier 3   |
+| `el`  | Greek            | Ελληνικά           | 🇬🇷   | Tier 3   |
+| `et`  | Estonian         | Eesti              | 🇪🇪   | Tier 3   |
+| `lv`  | Latvian          | Latviešu           | 🇱🇻   | Tier 3   |
+| `lt`  | Lithuanian       | Lietuvių           | 🇱🇹   | Tier 3   |
+| `sr`  | Serbian          | Српски             | 🇷🇸   | Tier 3   |
+| `tr`  | Turkish          | Türkçe             | 🇹🇷   | Tier 4   |
+| `uk`  | Ukrainian        | Українська         | 🇺🇦   | Tier 4   |
+| `ru`  | Russian          | Русский            | 🇷🇺   | Tier 4   |
+| `he`  | Hebrew           | עברית              | 🇮🇱   | Tier 4   |
+| `ar`  | Arabic           | العربية            | 🇸🇦   | Tier 4   |
+| `fa`  | Persian          | فارسی              | 🇮🇷   | Tier 4   |
+| `af`  | Afrikaans        | Afrikaans          | 🇿🇦   | Tier 4   |
+| `zh`  | Chinese          | 中文               | 🇨🇳   | Tier 5   |
+| `ja`  | Japanese         | 日本語             | 🇯🇵   | Tier 5   |
+| `ko`  | Korean           | 한국어             | 🇰🇷   | Tier 5   |
+| `vi`  | Vietnamese       | Tiếng Việt         | 🇻🇳   | Tier 5   |
+| `pa`  | Punjabi          | ਪੰਜਾਬੀ             | 🇮🇳   | Tier 5   |
+| `kn`  | Kannada          | ಕನ್ನಡ              | 🇮🇳   | Tier 5   |
+| `eo`  | Esperanto        | Esperanto          | 🌍    | Tier 6   |
 
-> **Tier 1** languages (European priority) have complete, manually-reviewed
+> **Tier 1** languages (major European) have complete, manually-reviewed
-> translations. **Tier 2** languages have complete translations but may
+> translations. **Tier 2–3** languages have complete translations but may
-> receive less frequent updates.
+> receive less frequent updates. **Tier 4–5** cover Non-EU European, Middle
+> Eastern, and Asian languages. **Tier 6** covers constructed languages.
 
 ## How Language Is Detected
 
@@ -71,15 +111,54 @@ Translations are stored as flat JSON files in `frontend/translations/`:
 ```
 frontend/translations/
 ├── en.json    # English (base / reference)
+├── af.json    # Afrikaans
+├── ar.json    # Arabic
+├── bg.json    # Bulgarian
+├── ca.json    # Catalan
+├── cs.json    # Czech
+├── cy.json    # Welsh
+├── da.json    # Danish
 ├── de.json    # German
-├── fr.json    # French
+├── el.json    # Greek
+├── eo.json    # Esperanto
 ├── es.json    # Spanish
+├── et.json    # Estonian
+├── fa.json    # Persian
+├── fi.json    # Finnish
+├── fr.json    # French
+├── fy.json    # Frisian
+├── ga.json    # Irish
+├── gl.json    # Galician
+├── he.json    # Hebrew
+├── hr.json    # Croatian
+├── hu.json    # Hungarian
+├── is.json    # Icelandic
 ├── it.json    # Italian
-├── pt.json    # Portuguese
+├── ja.json    # Japanese
+├── kn.json    # Kannada
+├── ko.json    # Korean
+├── lb.json    # Luxembourgish
+├── li.json    # Limburgish
+├── lt.json    # Lithuanian
+├── lv.json    # Latvian
+├── nb.json    # Norwegian Bokmål
+├── nds.json   # Low German (Plattdeutsch)
 ├── nl.json    # Dutch
+├── no.json    # Norwegian
+├── pa.json    # Punjabi
 ├── pl.json    # Polish
-├── zh.json    # Chinese
+├── pt.json    # Portuguese
-└── ru.json    # Russian
+├── ro.json    # Romanian
+├── ru.json    # Russian
+├── sk.json    # Slovak
+├── sl.json    # Slovenian
+├── sr.json    # Serbian
+├── sv.json    # Swedish
+├── tr.json    # Turkish
+├── uk.json    # Ukrainian
+├── vi.json    # Vietnamese
+├── vls.json   # West Flemish
+└── zh.json    # Chinese
 ```
 
 Each file is a flat key-value dictionary with dot-notation namespacing:

tests/test_i18n.py

@@ -161,7 +161,7 @@ class TestParseAcceptLanguage:
 
     @pytest.mark.unit
     def test_unsupported_language_fallback(self) -> None:
-        result = _parse_accept_language("ja, ko")
+        result = _parse_accept_language("xx, yy")
         assert result is None
 
     @pytest.mark.unit
@@ -326,7 +326,7 @@ class TestSupportedLanguages:
 
     @pytest.mark.unit
     def test_ten_languages_supported(self) -> None:
-        assert len(SUPPORTED_LANGUAGES) == 31
+        assert len(SUPPORTED_LANGUAGES) == 49
 
     @pytest.mark.unit
     def test_supported_codes_set(self) -> None:
@@ -338,10 +338,8 @@ class TestSupportedLanguages:
             "it",
             "pt",
             "nl",
-            "pl",
-            "zh",
-            "ru",
             "nb",
+            "no",
             "da",
             "sv",
             "fi",
@@ -349,6 +347,13 @@ class TestSupportedLanguages:
             "ga",
             "lb",
             "ca",
+            "cy",
+            "fy",
+            "gl",
+            "li",
+            "vls",
+            "nds",
+            "pl",
             "cs",
             "sk",
             "hu",
@@ -360,8 +365,21 @@ class TestSupportedLanguages:
             "et",
             "lv",
             "lt",
+            "sr",
             "tr",
             "uk",
+            "ru",
+            "he",
+            "ar",
+            "fa",
+            "af",
+            "zh",
+            "ja",
+            "ko",
+            "vi",
+            "pa",
+            "kn",
+            "eo",
         }
         assert SUPPORTED_LANGUAGE_CODES == expected
 
@@ -385,7 +403,7 @@ class TestI18nAPI:
         assert response.status_code == 200
         data = response.json()
         assert "languages" in data
-        assert len(data["languages"]) == 31
+        assert len(data["languages"]) == 49
         assert data["default"] == "en"
         # Verify each language has required fields
         for lang in data["languages"]: