Keep container fence lines out of prose chunks

A closing ::: glued to a paragraph (no blank line before it) rode inside
the prose chunk and crossed to the translator as part of the text run;
when the model dropped it, validation passed and the splice lost the
fence — the rest of the page rendered inside the container (seen in the
Spanish translation). Container fence lines (::: openers and closers
alike) are now always their own prose-free chunk, never reaching the
translator. Affected pages re-chunk on next save and re-translate under
the new hashes, repairing themselves.

docs/analytics.md

@@ -73,10 +73,11 @@ 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
+stored, so WebSocket message handling is never delayed.  Only the downloaded
+`.mmdb.gz` is kept on disk (in the working directory, ignored by git); it is
+decompressed into RAM when opened.  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.
@@ -144,7 +146,11 @@ served Markdown at render time.
 
 `chunk_markdown(markdown)` splits the source into block-level chunks —
 blank-line-separated blocks: headings, paragraphs, code fences (kept whole),
-list blocks, tables, HTML blocks. A chunk's identity is its **source text**,
+list blocks, tables, HTML blocks. Container fence lines (`::: name` openers
+and `:::` closers) are always their own chunk, blank lines or not — folded
+into a prose chunk the closer would cross to the translator as part of the
+text, where the model can drop it (the rest of the page then renders inside
+the container). A chunk's identity is its **source text**,
 gettext-msgid style:
 
 ```python

frontend/src/LangSelector.vue

@@ -9,23 +9,28 @@
 // store and re-renders it).
 import { computed } from 'vue'
 import LangSelect from './LangSelect.vue'
-import { flagFor, langName } from './langs'
+import { flagFor, langName, langSort } from './langs'
 import { useStore } from './store'
 
 const store = useStore()
 
 // The "(primary)" marker is admin-panel information; the public selector
-// lists plain languages.
-const options = computed(() =>
-  store.langAlternates.map((a) => ({
-    tag: a.tag,
-    code: a.tag,
-    name: langName(a.tag),
-    flag: flagFor(a.tag),
-    primary: false,
-  })),
-)
+// lists plain languages. Order: the primary language first, then the rest
+// in the lang tab's geographic grouping (./langs langSort) — the head's
+// hreflang order is just alphabetical.
 const primaryTag = computed(() => store.langAlternates.find((a) => a.primary)?.tag ?? '')
+const options = computed(() => {
+  const rest = langSort(
+    store.langAlternates.map((a) => a.tag).filter((t) => t !== primaryTag.value),
+  )
+  return [primaryTag.value, ...rest].filter(Boolean).map((tag) => ({
+    tag,
+    code: tag,
+    name: langName(tag),
+    flag: flagFor(tag),
+    primary: false,
+  }))
+})
 // The explicit pick, else the served language (header-autodetected pages
 // may have neither), else the primary.
 const model = computed(() => store.lang || store.servedLang || primaryTag.value)

frontend/src/PageEditor.vue

@@ -33,7 +33,7 @@ import { keymap } from '@codemirror/view'
 import { indentWithTab } from '@codemirror/commands'
 import { markdown } from '@codemirror/lang-markdown'
 import { cmHighlight, cmTheme } from './cmtheme'
-import { flagFor, langName } from './langs'
+import { flagFor, langName, langSort } from './langs'
 import { editorLang, pagePrimary } from './editorLang'
 import LangSelect from './LangSelect.vue'
 import ConnNote from './ConnNote.vue'
@@ -121,11 +121,13 @@ function normPath(p) {
 // localization settings tab).
 
 // The picker's options: the primary language first, then the union of the
-// page's translations and the site-wide configured targets, sorted.
+// page's translations and the site-wide configured targets in the lang
+// tab's geographic grouping (./langs langSort).
 const langOptions = computed(() => {
-  const others = [...new Set([...siteLangs.value, ...pageLangs.value])]
-    .filter((l) => l && l !== primaryLang.value)
-    .sort()
+  const others = langSort(
+    [...new Set([...siteLangs.value, ...pageLangs.value])]
+      .filter((l) => l && l !== primaryLang.value),
+  )
   return [primaryLang.value, ...others].map((code) => ({
     tag: code === primaryLang.value ? '' : code,
     code,

frontend/src/StructureEditor.vue

@@ -19,7 +19,7 @@ import { computed, inject, onActivated, onMounted, onUnmounted, provide, ref, wa
 import StructureTree from './StructureTree.vue'
 import LangSelect from './LangSelect.vue'
 import { slugify } from './slugify'
-import { flagFor, langName } from './langs'
+import { flagFor, langName, langSort } from './langs'
 import { editorLang, pagePrimary } from './editorLang'
 import { dropPageCache, loadPlain } from './swapdoc'
 
@@ -40,9 +40,10 @@ const primaryLang = ref('en')
 const siteLangs = ref([])
 
 // The strip's options: the primary language first, then the configured
-// translation targets (the lang tab manages that set).
+// translation targets (the lang tab manages that set) in the lang tab's
+// geographic grouping (./langs langSort).
 const langOptions = computed(() =>
-  [primaryLang.value, ...siteLangs.value.filter((l) => l !== primaryLang.value)]
+  [primaryLang.value, ...langSort(siteLangs.value.filter((l) => l !== primaryLang.value))]
     .map((code) => ({
       tag: code === primaryLang.value ? '' : code,
       code,
@@ -63,7 +64,7 @@ watch(lang, () => refreshPages())
 // dropdown lists "inherit" first (naming what it resolves to), then every
 // site language. Setting it on a section covers its whole subtree.
 const rowLangChoices = computed(() =>
-  [primaryLang.value, ...siteLangs.value.filter((l) => l !== primaryLang.value)]
+  [primaryLang.value, ...langSort(siteLangs.value.filter((l) => l !== primaryLang.value))]
     .map((code) => ({ tag: code, code, name: langName(code), flag: flagFor(code), primary: false })),
 )
 function rowLangOptions(el) {

frontend/src/langs.js

@@ -30,6 +30,20 @@ export const LANG_GROUPS = [
 
 const displayNames = new Intl.DisplayNames(['en'], { type: 'language' })
 
+// Consistent menu ordering for language selectors: the geographic/cultural
+// grouping above (similar languages sit together, and it does not vary with
+// the display language the way alphabetical-by-name would). Tags outside
+// the groups trail, ordered by tag. The primary language is not special
+// here — callers put it first themselves.
+const groupOrder = new Map(LANG_GROUPS.flat().map((c, i) => [c, i]))
+export function langSort(codes) {
+  return [...codes].sort(
+    (a, b) =>
+      (groupOrder.get(a) ?? groupOrder.size) - (groupOrder.get(b) ?? groupOrder.size)
+      || a.localeCompare(b),
+  )
+}
+
 // English display name for a language tag ("fi" -> "Finnish").
 export function langName(tag) {
   try {

pagerite/chunks.py

@@ -17,6 +17,13 @@ from pagerite.segments import has_prose
 #: backticks or tildes (CommonMark).
 _FENCE_OPEN = re.compile(r"^ {0,3}(`{3,}|~{3,})")
 
+#: A container fence line (mdit-py-plugins container): the "::: aside"
+#: opener and the ":::" closer alike. Always its own block, even with no
+#: blank line around it: folded into a prose paragraph it would cross to
+#: the translator as part of the text run, where the model can drop it —
+#: the rest of the page then renders inside the container.
+_CONTAINER = re.compile(r"^ {0,3}:{3,}(?:[ \t]|$)")
+
 #: HTML block openers that may span blank lines (CommonMark types 1-5:
 #: script/pre/style/textarea, comments, processing instructions,
 #: declarations, CDATA) with their closing condition. Other HTML blocks
@@ -54,9 +61,11 @@ def chunk_markdown(markdown: str) -> list[str]:
     Blocks are separated by blank lines; fenced code blocks and the
     multi-line HTML blocks (comments, script/pre/style, CDATA...) are
     kept atomic, even across blank lines, and end at their closing
-    condition. Chunks carry no surrounding blank lines and no trailing
-    newline; rejoining with ``join_chunks`` reproduces the source modulo
-    blank-line normalization.
+    condition. Container fence lines (:::, open and close alike) are
+    always their own block, blank lines or not (see _CONTAINER). Chunks
+    carry no surrounding blank lines and no trailing newline; rejoining
+    with ``join_chunks`` reproduces the source modulo blank-line
+    normalization.
     """
     chunks: list[str] = []
     buf: list[str] = []
@@ -91,6 +100,13 @@ def chunk_markdown(markdown: str) -> list[str]:
             fence = m.group(1)
             buf.append(line)
             continue
+        if _CONTAINER.match(line):
+            # Container fence lines (open and close alike) are their own
+            # block — never part of a prose chunk (see _CONTAINER).
+            flush()
+            buf.append(line)
+            flush()
+            continue
         if not buf:
             for open_re, close_re in _HTML_ATOMIC:
                 if open_re.match(line):

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

@@ -3,18 +3,19 @@
 The visitor-activity WebSocket (``/_ws``, public) and the admin analytics
 stream (``/_api/ws/analytics``) plus the ``/_a`` viewer page. Client IPs are
 enriched in background tasks with reverse DNS (cached PTR lookups) and the
-DB-IP city MMDB (``GeoIP``, decompressed and opened once at startup);
+DB-IP city MMDB (``GeoIP``, decompressed into RAM and opened once at
+startup);
 external referrers get their favicon fetched and stored content-hashed.
 Snapshot broadcasts to connected admin sockets are debounced.
 """
 
 import asyncio
 import gzip
+import io
 import ipaddress
 import logging
 import os
 import re
-import shutil
 import socket
 from datetime import date
 from functools import lru_cache
@@ -44,8 +45,9 @@ _analytics_ws_clients: set[WebSocket] = set()
 _analytics_broadcast_task: asyncio.Task | None = None
 
 
-# Repository root from this file's location (pagerite/tracking.py -> ..).
-_REPO_ROOT = Path(__file__).resolve().parent.parent
+# DB-IP databases persist in the working directory (one download serves all
+# 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 +62,7 @@ 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 +70,7 @@ 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 +95,7 @@ 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)
@@ -102,15 +104,19 @@ def _download_dbip() -> None:
 
 
 def _geoip_db_path() -> Path | None:
-    """Find a DB-IP MMDB in the repo root, preferring an already-decompressed
-    ``.mmdb`` over the matching ``.mmdb.gz``.  Returns None if none is present.
+    """Find a DB-IP MMDB in the working directory: the ``.mmdb.gz`` download
+    is canonical (decompressed into RAM at open); a plain ``.mmdb`` left over
+    from older versions is still usable, and removed once the matching ``.gz``
+    is present so it does not linger on disk.  Returns None if none is present.
     """
-    mmdb = sorted(_REPO_ROOT.glob("dbip-*.mmdb"))
+    gz = sorted(_DBIP_DIR.glob("dbip-*.mmdb.gz"))
+    if gz:
+        for stale in _DBIP_DIR.glob("dbip-*.mmdb"):
+            stale.unlink()
+        return gz[0]
+    mmdb = sorted(_DBIP_DIR.glob("dbip-*.mmdb"))
     if mmdb:
         return mmdb[0]
-    gz = sorted(_REPO_ROOT.glob("dbip-*.mmdb.gz"))
-    if gz:
-        return gz[0]
     return None
 
 
@@ -123,27 +129,22 @@ class GeoIP:
     def __init__(self) -> None:
         self._reader: object | None = None
 
-    def _decompress(self, source: Path, target: Path) -> None:
-        if target.exists():
-            return
-        tmp = target.with_suffix(target.suffix + ".tmp")
-        with gzip.open(source, "rb") as src, open(tmp, "wb") as dst:
-            shutil.copyfileobj(src, dst)
-        os.replace(tmp, target)
-
     def _load(self) -> None:
         if self._reader is not None:
             return
         source = _geoip_db_path()
         if source is None:
             return
-        if source.suffix == ".gz":
-            target = source.with_suffix("")
-            self._decompress(source, target)
-            source = target
         try:
             import maxminddb
 
+            if source.suffix == ".gz":
+                # Only the .gz is kept on disk; the database is decompressed
+                # into RAM (MODE_FD makes the pure-Python Reader .read() the
+                # buffer — never mmap — and bypasses the C extension).
+                buf = io.BytesIO(gzip.decompress(source.read_bytes()))
+                self._reader = maxminddb.open_database(buf, maxminddb.MODE_FD)
+            else:
                 self._reader = maxminddb.open_database(str(source))
         except Exception:
             pass

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:
-                keys = set(node.chunks)
+            if node_lang != lang:
+                keys = set(node.chunks or ())
                 if node.title:
                     keys.add(chunk_key(node.title))
                 if keys & stored:

pagerite/views.py

@@ -263,20 +263,31 @@ def _transition_css_url(transition: str) -> str | None:
 
 
 def _editor_css_url(vite_url: str | None) -> str | None:
-    """URL for the editor-specific stylesheet (Vue component styles).
+    """URLs (comma-joined) for the editor-specific stylesheets (Vue
+    component styles).
 
     This is linked by the public-page edit pen so the editor styles are
-    loaded before the editor JS dynamic-import resolves.
+    loaded before the editor JS dynamic-import resolves. Component styles
+    can land on shared chunks rather than the entry's own stylesheet —
+    LangSelect's ride on the shared store chunk, as it is also used by the
+    on-demand public language selector — so collect the stylesheets of the
+    entry and its imported chunks (the same traversal _langselect_assets
+    does).
     """
     if vite_url:
         return None
     manifest = _manifest()
-    entry = manifest["src/main.js"]
     base = manifest.get(_BASE_CSS_KEY, {}).get("file")
-    for css in entry.get("css", []):
-        if css != base:
-            return f"/{css}"
-    return None
+    stylesheets, seen = [], set()
+    queue = ["src/main.js"]
+    for key in queue:  # grows with imported chunks
+        if key in seen:
+            continue
+        seen.add(key)
+        entry = manifest[key]
+        stylesheets += [f"/{css}" for css in entry.get("css", []) if css != base]
+        queue += entry.get("imports", [])
+    return ",".join(stylesheets) or None
 
 
 def _inline_asset(url: str) -> str:
@@ -1021,6 +1032,42 @@ 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:
+        # Only languages the page actually has AND that are still enabled
+        # site-wide (a disabled target stops being advertised).
+        enabled = {original, *data.translate_langs}
+        alternates = [("x-default", url)] + [
+            (tag, url if tag == original else f"{url}?lang={tag}")
+            for tag in sorted({original, *node.langs} & enabled)
+        ]
+    return canonical, alternates
+
+
 def render_page(
     menu: dict[str, Node],
     data: Data,
@@ -1050,24 +1097,7 @@ 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
-    # 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})
-            ]
+    canonical, alternates = _language_urls(data, path, node, lang, original, base_url)
     return str(
         _layout(
             *_page_assets(),
@@ -1100,6 +1130,7 @@ 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 +1146,16 @@ 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 +1172,7 @@ 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),