Keep section anchors in the original language on translated pages

docs/localization.md

@@ -88,6 +88,10 @@ Region tags normalize to their base subtag (`fi-FI` → `fi`).
 ### Rendering
 
 - The translated Markdown goes through the same `markdown.render` pipeline.
+- Section anchors (`#hash` ids on h1/h2 headings) stay in the original
+  language: render(anchors_from=...) pins the translated render's heading
+  ids to the original text's slugs, matched by heading position, so links
+  to sections don't break across languages.
 - Navigation/sidebar titles come from the translation's title map, with
   per-node fallback to the original title (a partially translated tree must
   still render).

pagerite/api.py

@@ -503,6 +503,14 @@ async def editor_ws(ws: WebSocket) -> None:
                         # The title is injected as h1 when the markdown has
                         # none; the editor's title field edits live-preview.
                         title=msg.get("title") or (node.title if node else ""),
+                        # Pin section anchors to the original language so the
+                        # preview of a translation matches the served page
+                        # (no-op when the previewed markdown is the original).
+                        anchors_from=(
+                            (node_markdown(data, node) or "", node.title)
+                            if node
+                            else None
+                        ),
                     )
                     await ws.send_json(
                         {

pagerite/markdown.py

@@ -402,7 +402,9 @@ def _heading_ids(state) -> None:
     its self-link is ``href=""`` (back to the top of the page). An
     author-set `{#id}` always wins; auto ids slugify the heading text
     (python-slugify, mirroring the editor's slugify.js) and dedupe with
-    -2/-3 suffixes per render. Headings that already contain a link are
+    -2/-3 suffixes per render — unless env["anchor_ids"] presets them, as
+    render(anchors_from=...) does for translated pages so section URLs
+    stay in the original language. Headings that already contain a link are
     ``data-line`` records the heading's markdown source line (0-based, after
     undoing the render(title=...) injection offset via ``env``) — the page
     editor uses it for section pens and piecewise-linear scroll sync.
@@ -443,13 +445,23 @@ def _heading_ids(state) -> None:
     if len(heads) < ANCHOR_MIN_HEADINGS:
         return
     seen: set[str] = set()
-    for i, token in heads:
+    preset = state.env.get("anchor_ids")
+    for k, (i, token) in enumerate(heads):
         inline = tokens[i + 1]
         hid = token.attrGet("id")
         if not isinstance(hid, str) or not hid:
+            if preset is not None and k < len(preset):
+                # Translated render: the original language's slug, matched
+                # by heading position (a translation never adds, removes or
+                # reorders headings; a patched one that does falls back to
+                # slugging its own text past the end of the list).
+                base = preset[k]
+            else:
                 # Slug the visible text, not the raw markdown (`## [a](url)`).
                 text = "".join(
-                c.content for c in inline.children if c.type in ("text", "code_inline")
+                    c.content
+                    for c in inline.children
+                    if c.type in ("text", "code_inline")
                 )
                 base = slugify(text) or "section"
             hid, n = base, 2
@@ -463,6 +475,36 @@ def _heading_ids(state) -> None:
         wrap(i, token, f"#{hid}")
 
 
+def anchor_ids(text: str, title: str | None = None) -> list[str]:
+    """The section anchor ids of text, in heading order.
+
+    render(anchors_from=...) feeds these to _heading_ids via
+    env["anchor_ids"], pinning a translated render's anchors to the
+    original language's slugs. The selection mirrors _heading_ids exactly
+    (the same md instance assigns the ids during this parse, author-set
+    {#id} included as-is); the in-body title h1 is excluded.
+    """
+    if title and not has_h1(text):
+        text = f"# {title}\n\n{text}"
+    tokens = md.parse(text, {"page_path": ""})
+    first_h1 = next(
+        (
+            i
+            for i, t in enumerate(tokens)
+            if t.type == "heading_open" and t.tag == "h1" and t.level == 0
+        ),
+        None,
+    )
+    return [
+        t.attrGet("id")
+        for i, t in enumerate(tokens)
+        if t.type == "heading_open"
+        and t.tag in ("h1", "h2")
+        and t.level == 0
+        and i != first_h1
+    ]
+
+
 def make_md(*, verbatim: bool = False) -> MarkdownIt:
     """A fully configured parser. The module-level ``md`` (below) is the
     render instance; ``verbatim=True`` builds the segmentation instance for
@@ -618,12 +660,16 @@ def render(
     created: datetime | None = None,
     modified: datetime | None = None,
     title: str | None = None,
+    anchors_from: tuple[str, str] | None = None,
 ) -> Rendered:
     """Render Markdown text to the article body's HTML and layout flags.
 
     ``title`` injects a ``# {title}`` line at the top when the markdown has
     no h1 of its own, so the implicit page title goes through the exact
     same pipeline as an explicit one (first-h1 anchor treatment included).
+    ``anchors_from`` is the (markdown, title) of the ORIGINAL language when
+    rendering a translation: section anchors are pinned to its slugs so
+    localized pages keep the original #hash URLs.
 
     The top-level blocks are grouped into column segments: boundary blocks
     (h1/h2 headings, .wide — see _is_boundary) are rendered bare, the runs
@@ -641,6 +687,8 @@ def render(
     right after the article's h1.
     """
     env = {"page_path": page_path, "line_offset": 0}
+    if anchors_from is not None:
+        env["anchor_ids"] = anchor_ids(*anchors_from)
     if title and not has_h1(text):
         text = f"# {title}\n\n{text}"
         # The injected title shifts source lines by two; _heading_ids

pagerite/views.py

@@ -783,7 +783,11 @@ def page_content(
     node = resolve(menu, path)[-1]
     content = node_markdown(data, node) or ""
     title = node.title
+    # The original text pins the section anchors: on a translated page the
+    # heading slugs (and thus #hash URLs) stay in the original language.
+    anchors_from = None
     if translation:
+        anchors_from = (content, title)
         if translation.markdown is not None:
             content = translation.markdown
         title = (
@@ -793,7 +797,9 @@ def page_content(
         )
     # The title is injected into the markdown (as # title when it has no
     # h1 of its own), so title and content render as one article.
-    rendered = render(content, path, node.created, node.modified, title=title)
+    rendered = render(
+        content, path, node.created, node.modified, title=title, anchors_from=anchors_from
+    )
     # Long articles get .multicol: the article column cap lifts (see the
     # #content grid in pagerite.css) and the .cols segments lay out in at
     # most two columns. The html is already segmented by render() — the