mkdocs2confluence 0.20.2__tar.gz → 0.20.3__tar.gz

{mkdocs2confluence-0.20.2/src/mkdocs2confluence.egg-info → mkdocs2confluence-0.20.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mkdocs2confluence
-Version: 0.20.2
+Version: 0.20.3
 Summary: Publish MkDocs Material pages to Confluence Cloud — admonitions, Mermaid diagrams, tabs, page properties and more
 Author: Anders Hybertz
 License: GPL-3.0-or-later

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mkdocs2confluence"
-version = "0.20.2"
+version = "0.20.3"
 description = "Publish MkDocs Material pages to Confluence Cloud — admonitions, Mermaid diagrams, tabs, page properties and more"
 readme = "README.md"
 license = { text = "GPL-3.0-or-later" }

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3/src/mkdocs2confluence.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mkdocs2confluence
-Version: 0.20.2
+Version: 0.20.3
 Summary: Publish MkDocs Material pages to Confluence Cloud — admonitions, Mermaid diagrams, tabs, page properties and more
 Author: Anders Hybertz
 License: GPL-3.0-or-later

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3}/src/mkdocs_to_confluence/emitter/xhtml.py

@@ -258,13 +258,9 @@ def _emit_section(node: Section) -> str:
     # Confluence's auto heading-anchors use a different naming scheme than the
     # MkDocs slug our links carry, so without an explicit named anchor a
     # `#slug` link lands at the top of the page instead of the section.
-    name = html.escape(node.explicit_anchor or node.anchor)
+    name = node.explicit_anchor or node.anchor
     if name:
-        anchor = (
-            f'<ac:structured-macro ac:name="anchor">'
-            f'<ac:parameter ac:name=""><![CDATA[{name}]]></ac:parameter>'
-            f"</ac:structured-macro>"
-        )
+        anchor = _anchor_macro(name)
     heading = f"{anchor}<{tag}{style_attr}>{title_html}</{tag}>\n"
     body = emit(node.children)
     return heading + body
@@ -303,6 +299,20 @@ def _emit_front_matter(node: FrontMatter) -> str:
     return "".join(parts)
 
 
+def _anchor_macro(name: str) -> str:
+    """Confluence anchor macro for *name*.
+
+    The name sits in CDATA, which is not entity-decoded, so it must not be
+    HTML-escaped — only a literal ``]]>`` needs splitting.
+    """
+    safe = name.replace("]]>", "]]]]><![CDATA[>")
+    return (
+        f'<ac:structured-macro ac:name="anchor">'
+        f'<ac:parameter ac:name=""><![CDATA[{safe}]]></ac:parameter>'
+        f"</ac:structured-macro>"
+    )
+
+
 def _xml_safe(text: str) -> str:
     """HTML-escape *text* and encode non-ASCII as XML numeric character references.
 
@@ -694,12 +704,7 @@ def _emit_abbrev_glossary_block(node: AbbrevGlossaryBlock) -> str:
     """End-of-page abbreviations list with Confluence anchor targets."""
     parts: list[str] = ["<hr />\n<h6>Abbreviations</h6>\n<ol>\n"]
     for fn in node.footnoted:
-        anchor = html.escape(f"abbr-{fn.number}")
-        anchor_macro = (
-            f'<ac:structured-macro ac:name="anchor">'
-            f'<ac:parameter ac:name=""><![CDATA[{anchor}]]></ac:parameter>'
-            f"</ac:structured-macro>"
-        )
+        anchor_macro = _anchor_macro(f"abbr-{fn.number}")
         abbr = html.escape(fn.abbr)
         defn = _emit_inlines(fn.definition)
         parts.append(f"<li>{anchor_macro}<strong>{abbr}</strong> — {defn}</li>\n")
@@ -714,12 +719,7 @@ def _emit_footnote_block(node: FootnoteBlock) -> str:
     """Footnotes section: heading + ordered list with anchor targets."""
     items: list[str] = []
     for fn in node.items:
-        anchor = html.escape(f"fn-{fn.label}")
-        anchor_macro = (
-            f'<ac:structured-macro ac:name="anchor">'
-            f'<ac:parameter ac:name=""><![CDATA[{anchor}]]></ac:parameter>'
-            f"</ac:structured-macro>"
-        )
+        anchor_macro = _anchor_macro(f"fn-{fn.label}")
         content = _emit_inlines(fn.children)
         items.append(f"<li>{anchor_macro}{content}</li>\n")
     return "<h2>Footnotes</h2>\n<ol>\n" + "".join(items) + "</ol>\n"
@@ -780,12 +780,7 @@ def _emit_inline(node: IRNode) -> str:
     if isinstance(node, RawInlineHtml):
         return node.html_str
     if isinstance(node, AnchorNode):
-        name = html.escape(node.name)
-        return (
-            f'<ac:structured-macro ac:name="anchor">'
-            f"<ac:parameter ac:name=\"\"><![CDATA[{name}]]></ac:parameter>"
-            f"</ac:structured-macro>"
-        )
+        return _anchor_macro(node.name)
     # Fallback: emit unknown inline nodes as escaped repr
     return html.escape(repr(node))
 

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3}/src/mkdocs_to_confluence/publisher/client.py

@@ -67,6 +67,10 @@ class ConfluenceClient:
             raise RuntimeError("ConfluenceClient must be used as a context manager.")
         return self._client
 
+    def _get(self, url: str, **kwargs: Any) -> httpx.Response:
+        # Reads are rate-limited too; retry 429s like writes do.
+        return http_request_with_retry(lambda: self._http.get(url, **kwargs), f"GET {url}")
+
     def _base(self) -> str:
         # Strip trailing slash and any trailing /wiki so users can supply either
         # "https://org.atlassian.net" or "https://org.atlassian.net/wiki".
@@ -95,7 +99,7 @@ class ConfluenceClient:
         Raises :class:`ConfluenceError` when the space is not found.
         """
         url = self._v2("/spaces")
-        resp = self._http.get(url, params={"keys": space_key, "limit": 1})
+        resp = self._get(url, params={"keys": space_key, "limit": 1})
         self._raise_for_status(resp, f"get_space_id({space_key!r})")
         data = resp.json()
         results = data.get("results", [])
@@ -112,7 +116,7 @@ class ConfluenceClient:
         Raises :class:`ConfluenceError` when the page is not found.
         """
         url = self._v2(f"/pages/{page_id}")
-        resp = self._http.get(url)
+        resp = self._get(url)
         if resp.status_code == 404:
             raise ConfluenceError(
                 f"Parent page {page_id!r} not found (HTTP 404). "
@@ -147,7 +151,7 @@ class ConfluenceClient:
         else:
             url = self._v2(f"/pages/{parent_id}/direct-children")
 
-        resp = self._http.get(url, params={"limit": 250})
+        resp = self._get(url, params={"limit": 250})
         self._raise_for_status(resp, f"find_folder_under({title!r})")
         for item in resp.json().get("results", []):
             if item.get("type") == "folder" and item.get("title") == title:
@@ -168,7 +172,7 @@ class ConfluenceClient:
         if not space_key:
             return None
         cql = f'type=folder AND title="{title}" AND space="{space_key}"'
-        resp = self._http.get(
+        resp = self._get(
             self._v1("/content/search"),
             params={"cql": cql, "limit": 10},
         )
@@ -218,7 +222,7 @@ class ConfluenceClient:
         return pages from other spaces.
         """
         url = self._v2(f"/spaces/{space_id}/pages")
-        resp = self._http.get(
+        resp = self._get(
             url,
             params={"title": title, "status": "current", "limit": 10},
         )
@@ -303,7 +307,7 @@ class ConfluenceClient:
         """
         key = "content-appearance-published"
         prop_url = self._v1(f"/content/{page_id}/property/{key}")
-        get_resp = self._http.get(prop_url)
+        get_resp = self._get(prop_url)
 
         if get_resp.status_code == 200:
             current_version = get_resp.json().get("version", {}).get("number", 1)
@@ -330,7 +334,7 @@ class ConfluenceClient:
         can safely treat a missing hash as "unknown — must update".
         """
         url = self._v1(f"/content/{page_id}/property/mk2conf-content-hash")
-        resp = self._http.get(url)
+        resp = self._get(url)
         if resp.is_error:
             return None
         value = resp.json().get("value", "")
@@ -345,7 +349,7 @@ class ConfluenceClient:
         """
         key = "mk2conf-content-hash"
         prop_url = self._v1(f"/content/{page_id}/property/{key}")
-        get_resp = self._http.get(prop_url)
+        get_resp = self._get(prop_url)
         if get_resp.status_code == 200:
             current_version = get_resp.json().get("version", {}).get("number", 1)
             http_request_with_retry(
@@ -373,7 +377,7 @@ class ConfluenceClient:
         label_url = self._v1(f"/content/{page_id}/label")
 
         # Remove all existing labels
-        existing_resp = self._http.get(label_url)
+        existing_resp = self._get(label_url)
         if existing_resp.status_code == 200:
             for lbl in existing_resp.json().get("results", []):
                 name = lbl.get("name", "")
@@ -453,7 +457,7 @@ class ConfluenceClient:
         Returns the ``spaceContentStates`` list, which is the same for every
         page in the space.
         """
-        resp = self._http.get(self._v1(f"/content/{page_id}/state/available"))
+        resp = self._get(self._v1(f"/content/{page_id}/state/available"))
         if resp.is_success:
             data: dict[str, Any] = resp.json()
             return list(data.get("spaceContentStates") or [])
@@ -466,7 +470,7 @@ class ConfluenceClient:
         Uses the v2 ``GET /pages/{id}/attachments`` endpoint.
         """
         url = self._v2(f"/pages/{page_id}/attachments")
-        resp = self._http.get(url, params={"limit": 250})
+        resp = self._get(url, params={"limit": 250})
         self._raise_for_status(resp, f"list_attachments({page_id!r})")
         results: list[dict[str, Any]] = resp.json().get("results", [])
         return {r["title"]: r for r in results}
@@ -533,7 +537,7 @@ class ConfluenceClient:
         a publish.
         """
         url = self._v2(f"/pages/{page_id}/properties/mk2conf-managed")
-        get_resp = self._http.get(url)
+        get_resp = self._get(url)
         if get_resp.status_code == 200:
             return  # already stamped
         http_request_with_retry(
@@ -555,7 +559,7 @@ class ConfluenceClient:
         url = self._v2(f"/pages/{page_id}/descendants")
         params: dict[str, str | int] = {"depth": "all", "limit": 250}
         while True:
-            resp = self._http.get(url, params=params)
+            resp = self._get(url, params=params)
             self._raise_for_status(resp, f"get_descendant_ids({page_id!r})")
             data = resp.json()
             for item in data.get("results", []):
@@ -571,7 +575,7 @@ class ConfluenceClient:
 
     def is_managed(self, page_id: str) -> bool:
         """Return ``True`` if *page_id* has the ``mk2conf-managed`` property."""
-        resp = self._http.get(self._v2(f"/pages/{page_id}/properties/mk2conf-managed"))
+        resp = self._get(self._v2(f"/pages/{page_id}/properties/mk2conf-managed"))
         return resp.status_code == 200
 
     def delete_page(self, page_id: str) -> None:
@@ -590,7 +594,7 @@ class ConfluenceClient:
         url = self._v2(f"/pages/{page_id}/inline-comments")
         params: dict[str, Any] = {"resolution-status": "open", "body-format": "storage", "limit": 250}
         while True:
-            resp = self._http.get(url, params=params)
+            resp = self._get(url, params=params)
             self._raise_for_status(resp, f"get_page_inline_comments({page_id!r})")
             data = resp.json()
             results.extend(data.get("results", []))
@@ -607,7 +611,7 @@ class ConfluenceClient:
         url = self._v2(f"/pages/{page_id}/footer-comments")
         params: dict[str, Any] = {"resolution-status": "open", "body-format": "storage", "limit": 250}
         while True:
-            resp = self._http.get(url, params=params)
+            resp = self._get(url, params=params)
             self._raise_for_status(resp, f"get_page_footer_comments({page_id!r})")
             data = resp.json()
             results.extend(data.get("results", []))
@@ -635,7 +639,7 @@ class ConfluenceClient:
     def resolve_inline_comment(self, comment_id: str) -> None:
         """Resolve an inline comment by setting *resolved=true*."""
         url = self._v2(f"/inline-comments/{comment_id}")
-        get_resp = self._http.get(url, params={"body-format": "storage"})
+        get_resp = self._get(url, params={"body-format": "storage"})
         self._raise_for_status(get_resp, f"get_inline_comment({comment_id!r})")
         data = get_resp.json()
         version = data.get("version", {}).get("number", 1)
@@ -650,7 +654,7 @@ class ConfluenceClient:
     def resolve_footer_comment(self, comment_id: str) -> None:
         """Resolve a footer comment by setting *resolved=true*."""
         url = self._v2(f"/footer-comments/{comment_id}")
-        get_resp = self._http.get(url, params={"body-format": "storage"})
+        get_resp = self._get(url, params={"body-format": "storage"})
         self._raise_for_status(get_resp, f"get_footer_comment({comment_id!r})")
         data = get_resp.json()
         version = data.get("version", {}).get("number", 1)

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3}/src/mkdocs_to_confluence/publisher/http_retry.py

@@ -38,7 +38,7 @@ def http_request_with_retry(fn: Callable[[], httpx.Response], context: str) -> h
             )
         header = resp.headers.get("Retry-After", "")
         try:
-            wait = min(float(header), _RETRY_AFTER_CAP)
+            wait = min(max(float(header), 0.0), _RETRY_AFTER_CAP)
         except ValueError:
             wait = min(2.0 ** attempt + random.uniform(0.0, 1.0), _RETRY_AFTER_CAP)
         print(

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3}/tests/test_emitter.py

@@ -113,6 +113,20 @@ class TestSectionEmitter:
         assert "{ #test-me }" not in out
         assert "<h2>Test me</h2>" in out
 
+    def test_anchor_name_not_html_escaped_in_cdata(self) -> None:
+        # CDATA is not entity-decoded, so escaping the name there would make it
+        # differ from the (attribute-decoded) ac:anchor on links pointing at it.
+        from mkdocs_to_confluence.ir.nodes import AnchorNode
+
+        out = emit((Paragraph((AnchorNode(name="it's"),)),))
+        assert "<![CDATA[it's]]>" in out
+
+    def test_anchor_name_splits_cdata_terminator(self) -> None:
+        from mkdocs_to_confluence.ir.nodes import AnchorNode
+
+        out = emit((Paragraph((AnchorNode(name="a]]>b"),)),))
+        assert "<![CDATA[a]]]]><![CDATA[>b]]>" in out
+
 
 class TestParagraphEmitter:
     def test_simple_paragraph(self) -> None:

{mkdocs2confluence-0.20.2 → mkdocs2confluence-0.20.3}/tests/test_publish_client.py

@@ -1061,3 +1061,49 @@ def test_request_prints_warning_each_retry(monkeypatch: pytest.MonkeyPatch, caps
     assert out.count("rate-limited") == 2
     assert "attempt 1/3" in out
     assert "attempt 2/3" in out
+
+
+def test_request_clamps_negative_retry_after(monkeypatch: pytest.MonkeyPatch) -> None:
+    # time.sleep raises ValueError on negative values.
+    sleeps: list[float] = []
+    monkeypatch.setattr("time.sleep", lambda s: sleeps.append(s))
+    transport = _MockTransport(
+        _rate_limit_response(retry_after="-5"),
+        _json_response({}),
+    )
+    with httpx.Client(transport=transport) as http:
+        http_request_with_retry(
+            lambda: http.get("https://example.atlassian.net/wiki/api/v2/test"), "test_op"
+        )
+    assert sleeps == [0.0]
+
+
+def test_client_get_retries_on_429(monkeypatch: pytest.MonkeyPatch) -> None:
+    # Reads are rate-limited too; a 429 on a lookup must not abort the publish.
+    monkeypatch.setattr("time.sleep", lambda _: None)
+    transport = _MockTransport(
+        _rate_limit_response(),
+        _json_response({"results": [{"id": "7", "title": "Home"}]}),
+    )
+    with ConfluenceClient(_make_config()) as client:
+        client._client = httpx.Client(transport=transport)  # type: ignore[assignment]
+        page = client.find_page("42", "Home")
+    assert page == {"id": "7", "title": "Home"}
+    assert len(transport.requests) == 2
+
+
+def test_client_paginated_get_retries_on_429(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr("time.sleep", lambda _: None)
+    transport = _MockTransport(
+        _json_response({
+            "results": [{"id": "1", "type": "page"}],
+            "_links": {"next": "/wiki/api/v2/pages/9/descendants?cursor=abc"},
+        }),
+        _rate_limit_response(),
+        _json_response({"results": [{"id": "2", "type": "page"}], "_links": {}}),
+    )
+    with ConfluenceClient(_make_config()) as client:
+        client._client = httpx.Client(transport=transport)  # type: ignore[assignment]
+        ids = client.get_descendant_ids("9")
+    assert ids == ["1", "2"]
+    assert transport.requests[2].url.params["cursor"] == "abc"