feat(i18n): offer every ISO 639-1 language

The table was thirty languages typed by hand. It is now generated:
utils/generate_languages.py takes the 184 alpha-2 codes from pycountry,
the display names from CLDR through babel, and the writing direction from
CLDR character order. 159 languages carry their endonym; the remaining 25
have no CLDR entry and carry their English ISO name.

That corrects the right-to-left set, which had four entries and needs ten
— dv, ks, ps, sd, ug and yi were simply missed.

Only 29 languages ship an interface catalogue, so the other 155 render in
English until one is filled. make i18n-ui fills app/i18n/ui/ for them, and
make i18n now covers the interface strings as well; neither asks for a
string a shipped catalogue already answers, so hand-written entries stay.

184 entries do not fit on a screen, so the language menu scrolls inside
itself. overscroll-behavior keeps the page behind it from moving once the
list reaches its end.

babel and pycountry are dev dependencies: the generator needs them, the
application does not.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

utils/generate_languages.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Regenerate app/utils/languages.py from ISO 639-1 and CLDR.
+
+Every ISO 639-1 alpha-2 code becomes an entry. The display name is the CLDR
+endonym where CLDR knows the language, and the English ISO name for the
+remainder. Writing direction comes from CLDR's character order.
+
+Needs the dev extra: pip install -e ".[dev]"
+"""
+
+import subprocess
+import sys
+from pathlib import Path
+
+import pycountry
+from babel import Locale
+from babel.localedata import locale_identifiers
+
+TARGET = Path(__file__).resolve().parents[1] / "app" / "utils" / "languages.py"
+
+HEADER = '''"""ISO 639-1 languages, their display names and writing direction.
+
+Generated by utils/generate_languages.py — edit that script, not this file.
+
+Display names are CLDR endonyms where CLDR covers the language and the English
+ISO 639-1 name for the {fallback} codes it does not.
+"""
+
+LANGUAGES = {{
+'''
+
+FOOTER = """}}
+
+RTL_LANGUAGES = frozenset({rtl})
+"""
+
+
+def collect():
+    """Return (code -> display name) and the set of right-to-left codes."""
+    cldr = {code for code in locale_identifiers() if len(code) == 2 and code.isalpha()}
+    names, rtl, fallbacks = {}, set(), 0
+
+    for language in sorted(
+        pycountry.languages, key=lambda item: getattr(item, "alpha_2", "")
+    ):
+        code = getattr(language, "alpha_2", None)
+        if not code:
+            continue
+        if code in cldr:
+            locale = Locale.parse(code)
+            names[code] = locale.get_display_name(code)
+            if locale.character_order == "right-to-left":
+                rtl.add(code)
+        else:
+            names[code] = language.name
+            fallbacks += 1
+
+    return names, rtl, fallbacks
+
+
+def render(names, rtl, fallbacks):
+    """Return the module source, English first and the rest by code."""
+    ordered = ["en"] + [code for code in sorted(names) if code != "en"]
+    body = "".join(f'    "{code}": "{names[code]}",\n' for code in ordered)
+    listed = ", ".join(f'"{code}"' for code in sorted(rtl))
+    return (
+        HEADER.format(fallback=fallbacks) + body + FOOTER.format(rtl="{" + listed + "}")
+    )
+
+
+def main():
+    names, rtl, fallbacks = collect()
+    TARGET.write_text(render(names, rtl, fallbacks), encoding="utf-8")
+    subprocess.run([sys.executable, "-m", "ruff", "format", str(TARGET)], check=False)
+    print(
+        f"{len(names)} languages, {len(rtl)} right-to-left, "
+        f"{fallbacks} without a CLDR endonym"
+    )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

utils/i18n_sync.py

@@ -144,9 +144,17 @@ def translate(session, url, api_key, text, target):
     return translated
 
 
-def sync(url, api_key, sources, targets):
-    """Fill and write the content catalogue of every language in ``targets``."""
-    i18n.CONTENT_DIR.mkdir(parents=True, exist_ok=True)
+def sync(url, api_key, sources, targets, directory):
+    """Fill and write the catalogue of every language in ``targets``.
+
+    Args:
+        url: base URL of the LibreTranslate instance.
+        api_key: API key, or an empty string.
+        sources: English strings to translate.
+        targets: language codes to fill.
+        directory: catalogue directory to write into.
+    """
+    directory.mkdir(parents=True, exist_ok=True)
     session = requests.Session()
 
     available = supported_languages(url, session)
@@ -155,12 +163,21 @@ def sync(url, api_key, sources, targets):
             print(f"- {target}: not offered by {url}, skipped")
             continue
 
-        path = i18n.CONTENT_DIR / f"{target}.yaml"
+        path = directory / f"{target}.yaml"
         catalog = load_existing(path)
         if catalog is None:
             continue
 
-        missing = sorted(source for source in sources if source not in catalog)
+        shipped = (
+            {}
+            if directory == i18n.UI_DIR
+            else i18n.read_catalog(i18n.UI_DIR / f"{target}.yaml")
+        )
+        missing = sorted(
+            source
+            for source in sources
+            if source not in catalog and source not in shipped
+        )
         if not missing:
             print(f"- {target}: complete")
             continue
@@ -201,6 +218,15 @@ def main(argv=None):
         default=DEFAULT_CONFIG_PATH,
         help=f"Configuration to read the prose from (default: {DEFAULT_CONFIG_PATH}).",
     )
+    parser.add_argument(
+        "--catalog",
+        choices=("content", "ui"),
+        default="content",
+        help=(
+            "content: your configuration's prose, generated per deployment. "
+            "ui: the interface strings that ship with the project."
+        ),
+    )
     parser.add_argument(
         "--languages",
         nargs="+",
@@ -209,12 +235,18 @@ def main(argv=None):
     )
     args = parser.parse_args(argv)
 
-    config = yaml.safe_load(args.config.read_text(encoding="utf-8"))
-    sources = collect_sources(config)
-    print(f"{len(sources)} translatable string(s) in {args.config}")
+    if args.catalog == "ui":
+        directory = i18n.UI_DIR
+        sources = set(i18n.UI_STRINGS)
+        print(f"{len(sources)} interface string(s)")
+    else:
+        directory = i18n.CONTENT_DIR
+        config = yaml.safe_load(args.config.read_text(encoding="utf-8"))
+        sources = collect_sources(config) | set(i18n.UI_STRINGS)
+        print(f"{len(sources)} string(s) in {args.config} and the interface")
 
     try:
-        sync(args.url.rstrip("/"), args.api_key, sources, args.languages)
+        sync(args.url.rstrip("/"), args.api_key, sources, args.languages, directory)
     except BackendError as error:
         print(f"ERROR: {error}", file=sys.stderr)
         return 1