Hreflang alternates on category placeholder pages too

docs/analytics.md

@@ -73,10 +73,10 @@ Each `Client` record (shared by every event, keyed by hash):
 A reverse-DNS lookup is attempted for each new client and the result, when
 available, is stored as `host`; local/reserved/multicast addresses are
 skipped.  If a DB-IP MMDB file (`dbip-*.mmdb` or `dbip-*.mmdb.gz`) is present
-in the repository root, it is loaded at startup and used to look up
+in the working directory, it is loaded at startup and used to look up
 `country`/`city`.  These lookups run in background tasks after the event is
 stored, so WebSocket message handling is never delayed.  The decompressed
-`dbip-*.mmdb` file is kept in the repository root and ignored by git.  The
+`dbip-*.mmdb` file is kept in the working directory and ignored by git.  The
 CLI flag `--dbip` (`uv run pagerite --dbip`) downloads the latest
 `dbip-city-lite-YYYY-MM.mmdb.gz` from DB-IP at startup (in the app lifespan,
 before the MMDB is opened), skipping the download when the local database is

docs/localization.md

@@ -106,7 +106,9 @@ Region tags normalize to their base subtag (`fi-FI` → `fi`).
   language like content pages, but over the **subtree's** combined
   availability (`subtree_languages`) — they have no chunks of their own;
   the heading, navigation and card text localize from the title map and
-  the target articles' translations.
+  the target articles' translations. Their hreflang alternates are
+  computed exactly like a content page's (a translated title counts as
+  availability, so the language selector is offered there too).
 - Card descriptions and cover picks run on the target article's hybrid
   Markdown where that page is available in the served language, with
   per-card fallback to the original.

pagerite/state.py

@@ -132,6 +132,7 @@ def _render_html(
             data.theme,
             data.favicon,
             data.brand_html,
+            base_url,
             transition=data.transition,
             lang=lang,
             translation=translation,

pagerite/tracking.py

@@ -44,8 +44,9 @@ _analytics_ws_clients: set[WebSocket] = set()
 _analytics_broadcast_task: asyncio.Task | None = None
 
 
-# Repository root from this file's location (pagerite/tracking.py -> ..).
+# DB-IP databases persist in the working directory (one download serves all
-_REPO_ROOT = Path(__file__).resolve().parent.parent
+# sites run from it). Not the package directory: reinstalls/upgrades wipe it.
+_DBIP_DIR = Path.cwd()
 
 DBIP_URL = "https://download.db-ip.com/free/dbip-city-lite-{month}.mmdb.gz"
 
@@ -60,7 +61,7 @@ def _download_dbip() -> None:
 
     existing = sorted(
         p.stem.removeprefix("dbip-city-lite-").removesuffix(".mmdb")
-        for p in _REPO_ROOT.glob("dbip-city-lite-*.mmdb*")
+        for p in _DBIP_DIR.glob("dbip-city-lite-*.mmdb*")
     )
     if existing and existing[-1] >= months[0]:
         logger.info("DB-IP database is current (%s), skipping download", existing[-1])
@@ -68,7 +69,7 @@ def _download_dbip() -> None:
 
     for month in months:
         url = DBIP_URL.format(month=month)
-        target = _REPO_ROOT / f"dbip-city-lite-{month}.mmdb.gz"
+        target = _DBIP_DIR / f"dbip-city-lite-{month}.mmdb.gz"
         tmp = target.with_suffix(".mmdb.gz.tmp")
         logger.info("Downloading %s", url)
         try:
@@ -93,7 +94,7 @@ def _download_dbip() -> None:
             continue
         os.replace(tmp, target)
         # Drop older databases so the app never picks up a stale one.
-        for old in _REPO_ROOT.glob("dbip-city-lite-*.mmdb*"):
+        for old in _DBIP_DIR.glob("dbip-city-lite-*.mmdb*"):
             if old.name != target.name:
                 old.unlink()
         logger.info("DB-IP database updated to %s", target.name)
@@ -102,13 +103,13 @@ def _download_dbip() -> None:
 
 
 def _geoip_db_path() -> Path | None:
-    """Find a DB-IP MMDB in the repo root, preferring an already-decompressed
+    """Find a DB-IP MMDB in the working directory, preferring an already-decompressed
     ``.mmdb`` over the matching ``.mmdb.gz``.  Returns None if none is present.
     """
-    mmdb = sorted(_REPO_ROOT.glob("dbip-*.mmdb"))
+    mmdb = sorted(_DBIP_DIR.glob("dbip-*.mmdb"))
     if mmdb:
         return mmdb[0]
-    gz = sorted(_REPO_ROOT.glob("dbip-*.mmdb.gz"))
+    gz = sorted(_DBIP_DIR.glob("dbip-*.mmdb.gz"))
     if gz:
         return gz[0]
     return None

pagerite/translate.py

@@ -101,7 +101,8 @@ ClientMsg = Hello | Result
 def pending_items(data: Data, lang: str) -> list[TransItem]:
     """Fragments of the site still untranslated for ``lang``, deduped by key.
 
-    Every page node (published or not) contributes its title and each chunk
+    Every node (published or not, pages and pure category labels alike)
+    contributes its title; pages also contribute each chunk
     that needs translation (``needs_translation``), is not editor-flagged
     no-translate (``node.no_trans``) and has no ``trans`` entry for ``lang``
     yet. Content-addressed text (shared paragraphs, repeated titles) appears
@@ -133,8 +134,10 @@ def pending_items(data: Data, lang: str) -> list[TransItem]:
             path = f"{prefix}/{slug}" if prefix else slug
             # An article whose primary language IS the target needs no
             # translation into it — skip its title and chunks entirely.
+            # Category labels (chunks is None) contribute only their title:
+            # it is their nav-menu label.
             node_lang = node.language or inherited
-            if node.chunks is not None and node_lang != lang:
+            if node_lang != lang:
                 if node.title:
                     emit(
                         chunk_key(node.title),
@@ -143,7 +146,7 @@ def pending_items(data: Data, lang: str) -> list[TransItem]:
                         "title",
                         context=opening(node),
                     )
-                for h in node.chunks:
+                for h in node.chunks or ():
                     text = data.chunks.get(h)
                     if (
                         text is not None
@@ -178,8 +181,8 @@ def store_results(data: Data, lang: str, items: list[TransResult]) -> list[str]:
         for slug, node in sorted_nodes(nodes):
             path = f"{prefix}/{slug}" if prefix else slug
             node_lang = node.language or inherited
-            if node.chunks is not None and node_lang != lang:
+            if node_lang != lang:
-                keys = set(node.chunks)
+                keys = set(node.chunks or ())
                 if node.title:
                     keys.add(chunk_key(node.title))
                 if keys & stored:

pagerite/views.py

@@ -1021,6 +1021,39 @@ def _social_meta(
     }
 
 
+def _language_urls(
+    data: Data,
+    path: str,
+    node: Node,
+    lang: str,
+    original: str,
+    base_url: str,
+) -> tuple[str, list[tuple[str, str]]]:
+    """(canonical, hreflang alternates) for a page (docs/localization.md).
+
+    The canonical names the actually served language — the plain URL for
+    the original (for SEO the non-query URL means the article's language),
+    ?lang= for a translation — regardless of how the language was arrived
+    at (query or header). The alternates list the languages the page is
+    actually available in (``node.langs``; a category label's title counts
+    as its content): x-default first (the plain, autodetecting URL), then
+    every available language — the original again by its plain URL,
+    translations by ?lang=. The public language selector keys off these.
+    ("", []) without a base_url.
+    """
+    if not base_url:
+        return "", []
+    url = f"{base_url}/{path}"
+    canonical = url if lang == original else f"{url}?lang={lang}"
+    alternates = []
+    if data.translate_langs:
+        alternates = [("x-default", url)] + [
+            (tag, url if tag == original else f"{url}?lang={tag}")
+            for tag in sorted({original, *node.langs})
+        ]
+    return canonical, alternates
+
+
 def render_page(
     menu: dict[str, Node],
     data: Data,
@@ -1050,24 +1083,7 @@ def render_page(
     title = _title(path.rpartition("/")[2], node, translation, path)
     main = page_content(menu, data, path, translation, link_lang, lang)
     social = _social_meta(node, path, title, str(main), brand, base_url)
-    # Canonical/hreflang URLs (docs/localization.md): the canonical names
+    canonical, alternates = _language_urls(data, path, node, lang, original, base_url)
-    # the actually served language — the plain URL for the original (for
-    # SEO the non-query URL means the article's language), ?lang= for a
-    # translation — regardless of how the language was arrived at (query
-    # or header). The alternates list the languages the page is actually
-    # available in: x-default first (the plain, autodetecting URL), then
-    # every available language — the original again by its plain URL,
-    # translations by ?lang=. The public language selector keys off these.
-    canonical = ""
-    alternates = []
-    if base_url:
-        url = f"{base_url}/{path}"
-        canonical = url if lang == original else f"{url}?lang={lang}"
-        if data.translate_langs:
-            alternates = [("x-default", url)] + [
-                (tag, url if tag == original else f"{url}?lang={tag}")
-                for tag in sorted({original, *node.langs})
-            ]
     return str(
         _layout(
             *_page_assets(),
@@ -1100,6 +1116,7 @@ def render_category(
     theme: str = "",
     favicon: str = "",
     brand_html: str = "",
+    base_url: str = "",
     transition: str = "cube",
     lang: str = i18n.ORIGINAL_LANGUAGE,
     translation: Translation | None = None,
@@ -1115,12 +1132,16 @@ def render_category(
     With a translation (titles only — the category has no Markdown) the
     heading, navigation and card text localize per target article
     (docs/localization.md); ``link_lang`` replicates the ?lang= override
-    onto the navigation links as on content pages.
+    onto the navigation links as on content pages. The hreflang alternates
+    are computed as on content pages — a translated title makes the
+    language available here too.
     """
     node = resolve(menu, path)[-1]
+    original = i18n.primary_lang(menu, path)
     if translation is None:
-        lang = i18n.primary_lang(menu, path)
+        lang = original
     title = _title(path.rpartition("/")[2], node, translation, path)
+    _, alternates = _language_urls(data, path, node, lang, original, base_url)
     doc = E.article
     with doc:
         doc.h1(title)
@@ -1137,6 +1158,7 @@ def render_category(
             transition,
             favicon,
             lang=lang,
+            alternates=alternates,
         )(
             Title=f"{title} – {brand}" if brand else title,
             Brand=_brand_link(brand, brand_html, link_lang),