Merge branch 'fix/v2.6.9-webmention-processing' for v2.6.9 release
Build Container / build (push) Successful in 12s

This commit is contained in:
Phil committed 2026-11-03 07:53:19 -07:00
commit 0cfc9965df
6 files changed
+184 -18

No files matched your search

+12
View File
@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
## [2.6.9] - 2026-11-03
### Fixed
- Received webmentions failed when the sender's profile photo had alt text (Bridgy, Mastodon and most IndieWeb sites do this). The photo is now stored as its URL
- Outgoing webmentions were never sent: endpoint discovery crashed on every target that had an endpoint, and the target was then marked as having none. Discovery now works, and network errors during discovery are retried instead of giving up
- Each server process ran its own webmention worker, so a webmention could be processed or sent more than once. Only one process handles the queues at a time now; if it stops, another takes over
### Security
- A webmention sender could set its author link to a `javascript:` URL, which was shown as a clickable link on the note page. Author links and photos are now only kept if they are http or https URLs
## [2.6.8] - 2026-11-03
### Fixed
@@ -0,0 +1,36 @@
# v2.6.9: Webmention processing fixes
Found after v2.6.8 let the worker run in production, and by a review of the
implementation against the W3C Webmention Recommendation.
## Fixes
1. **Author photo with alt text** (`webmention_processor.extract_author`).
mf2py returns `u-photo` with an `alt` attribute as
`{'value': url, 'alt': ...}`; the dict was bound to SQLite and the update
failed. `_first_str()` reduces mf2 values to their `value`.
2. **Endpoint discovery** (`WebmentionWorker._discover_endpoint`).
`response.url` is an `httpx.URL`; `urljoin(str, URL)` raised `TypeError`,
which was caught and returned as "no endpoint", so every target was marked
`no_endpoint`. Pass `str(response.url)`. Fetch errors now propagate so the
caller schedules a retry, instead of being treated as "no endpoint".
3. **Duplicate processing.** gunicorn runs 4 processes, each with a worker,
and queue items were claimed by SELECT then UPDATE. The worker now takes a
non-blocking `flock` on `<data>/webmention-worker.lock` before processing;
others wait and retry each poll, so one takes over if the holder dies.
Orphan cleanup runs when the lock is acquired.
4. **XSS (spec 4.1).** `author_url` and `author_photo` are kept only if they
are absolute http(s) URLs; otherwise the source URL / no photo is used.
## Tests
`tests/test_webmention_worker.py`: the send test uses a real `httpx.Response`
(the old `MagicMock` with a string URL hid fix 2), plus tests for the lock,
an alt-text photo and a `javascript:` author URL. All fail on v2.6.8.
## Remaining spec gaps
Tracked separately: rel-token and document-order endpoint discovery, exact
target match during verification, Accept header, re-sending on delete, 410
for deleted notes, SSRF re-validation on redirects, and the others listed in
the compliance review.
+2 -2
View File
@@ -459,5 +459,5 @@ def create_app(config=None):
# Package version (Semantic Versioning 2.0.0)
# See docs/standards/versioning-strategy.md for details
__version__ = "2.6.8"
__version_info__ = (2, 6, 8)
__version__ = "2.6.9"
__version_info__ = (2, 6, 9)
+32 -7
View File
@@ -182,6 +182,28 @@ def detect_mention_type(parsed_mf2: Dict, target_url: str) -> str:
return 'mention'
def _first_str(props: Dict, name: str) -> Optional[str]:
"""
First value of an mf2 property as a string
mf2py gives u-photo with alt text as {'value': url, 'alt': ...} and nested
microformats as dicts with a 'value'; reduce those to the plain value.
"""
values = props.get(name) or [None]
value = values[0]
if isinstance(value, dict):
value = value.get('value')
return value if isinstance(value, str) and value else None
def _is_http_url(value: Optional[str]) -> bool:
"""True if value is an absolute http or https URL"""
if not value:
return False
parsed = urlparse(value.strip())
return parsed.scheme.lower() in ('http', 'https') and bool(parsed.netloc)
def extract_author(parsed_mf2: Dict, source_url: str) -> Dict[str, Optional[str]]:
"""
Extract author information from h-card.
@@ -212,26 +234,29 @@ def extract_author(parsed_mf2: Dict, source_url: str) -> Dict[str, Optional[str]
if isinstance(author_data, dict):
# h-card object
props = author_data.get('properties', {})
author_name = props.get('name', [None])[0]
author_url = props.get('url', [None])[0]
author_photo = props.get('photo', [None])[0]
author_name = _first_str(props, 'name')
author_url = _first_str(props, 'url')
author_photo = _first_str(props, 'photo')
# If no author in h-entry, find representative h-card
if not author_name:
for item in parsed_mf2.get('items', []):
if 'h-card' in item.get('type', []):
props = item.get('properties', {})
author_name = props.get('name', [None])[0]
author_url = props.get('url', [None])[0]
author_photo = props.get('photo', [None])[0]
author_name = _first_str(props, 'name')
author_url = _first_str(props, 'url')
author_photo = _first_str(props, 'photo')
break
# Fallback to hostname if no author found
if not author_name:
author_name = urlparse(source_url).netloc
if not author_url:
# Only http(s) URLs are rendered as links (blocks javascript: and data:)
if not _is_http_url(author_url):
author_url = source_url
if not _is_http_url(author_photo):
author_photo = None
return {
'author_name': author_name,
+44 -7
View File
@@ -12,6 +12,7 @@ References:
- ADR-063: Webmention Implementation
"""
import fcntl
import logging
import threading
import time
@@ -76,6 +77,7 @@ class WebmentionWorker(threading.Thread):
self.auto_approve = auto_approve
self._stop_event = threading.Event()
self._last_processed = None
self._lock_file = None
# Phase 3: Discovery cache (worker instance variable)
# Per architect's answer to Q4
@@ -94,11 +96,14 @@ class WebmentionWorker(threading.Thread):
try:
logger.info("Webmention worker started")
# Cleanup orphaned items from previous crashes
self._cleanup_orphaned_items()
# Main processing loop
while not self._stop_event.is_set():
# Every gunicorn process starts a worker; only the one holding
# the lock processes queues, so nothing is sent twice
if not self._acquire_lock():
self._stop_event.wait(self.poll_interval)
continue
try:
processed = 0
@@ -124,8 +129,40 @@ class WebmentionWorker(threading.Thread):
except Exception as e:
logger.error(f"Webmention worker thread failed: {e}", exc_info=True)
finally:
self._release_lock()
logger.info("Webmention worker stopped")
def _acquire_lock(self) -> bool:
"""
Take the cross-process worker lock (non-blocking)
On first acquisition, also reset items left mid-send by a previous
holder. The OS releases the lock if this process dies.
Returns:
True if this worker holds the lock
"""
if self._lock_file:
return True
lock_file = open(Path(self.db_path).parent / "webmention-worker.lock", "w")
try:
fcntl.flock(lock_file, fcntl.LOCK_EX | fcntl.LOCK_NB)
except OSError:
lock_file.close()
return False
self._lock_file = lock_file
logger.info("Webmention worker holds the queue lock")
self._cleanup_orphaned_items()
return True
def _release_lock(self):
"""Release the cross-process worker lock if held"""
if self._lock_file:
self._lock_file.close()
self._lock_file = None
def _cleanup_orphaned_items(self):
"""
Clean up orphaned 'sending' status items on startup
@@ -510,7 +547,7 @@ class WebmentionWorker(threading.Thread):
# 1. Check Link header
link_header = response.headers.get('Link', '')
if link_header:
endpoint = self._parse_link_header(link_header, response.url)
endpoint = self._parse_link_header(link_header, str(response.url))
if endpoint:
self._cache_endpoint(target_url, endpoint, hours=1)
return endpoint
@@ -518,7 +555,7 @@ class WebmentionWorker(threading.Thread):
# 2. Parse HTML for <link> and <a> elements
content_type = response.headers.get('Content-Type', '')
if 'html' in content_type.lower():
endpoint = self._parse_html_for_endpoint(response.text, response.url)
endpoint = self._parse_html_for_endpoint(response.text, str(response.url))
if endpoint:
self._cache_endpoint(target_url, endpoint, hours=1)
return endpoint
@@ -529,9 +566,9 @@ class WebmentionWorker(threading.Thread):
return None
except Exception as e:
# Don't cache; the caller schedules a retry
logger.warning(f"Failed to discover endpoint for {target_url}: {e}")
# Don't cache on error - allow retry
return None
raise
def _parse_link_header(self, link_header: str, base_url: str) -> Optional[str]:
"""
+58 -2
View File
@@ -7,6 +7,8 @@ whenever any app context ended.
"""
import sqlite3
import httpx
import time
from unittest.mock import MagicMock, patch
@@ -33,8 +35,8 @@ def test_worker_sends_queued_webmention(app):
conn.commit()
conn.close()
page = MagicMock(status_code=200, url="https://example.org/post",
headers={"Link": '<https://example.org/wm>; rel="webmention"'})
page = httpx.Response(200, headers={"Link": '</wm>; rel="webmention"'},
request=httpx.Request("GET", "https://example.org/post"))
accepted = MagicMock(status_code=202, text="")
worker = WebmentionWorker(app, db_path=db_path, site_url=app.config["SITE_URL"],
@@ -52,6 +54,7 @@ def test_worker_sends_queued_webmention(app):
assert _wait_for(lambda: status()[0] != "pending"), status()
assert status() == ("sent", None)
post.assert_called_once()
assert post.call_args.args[0] == "https://example.org/wm"
finally:
worker.stop()
worker.join(timeout=2)
@@ -70,3 +73,56 @@ def test_worker_survives_app_context_teardown(app):
finally:
worker.stop()
worker.join(timeout=2)
def test_only_one_worker_processes_queues(app):
"""Each gunicorn process starts a worker; only one may hold the queue lock"""
kwargs = dict(db_path=app.config["DATABASE_PATH"], site_url=app.config["SITE_URL"])
first = WebmentionWorker(app, **kwargs)
second = WebmentionWorker(app, **kwargs)
try:
assert first._acquire_lock()
assert not second._acquire_lock()
first._release_lock()
assert second._acquire_lock()
finally:
first._release_lock()
second._release_lock()
def test_author_photo_with_alt_text_is_a_string():
"""mf2py returns u-photo with alt as a dict; the database needs a URL string"""
import mf2py
from starpunk.webmention_processor import extract_author
html = """
<div class="h-entry">
<span class="p-author h-card">
<a class="u-url p-name" href="https://a.example/">A Person</a>
<img class="u-photo" src="https://a.example/me.jpg" alt=""></span>
<a href="https://site.example/note/1">target</a>
</div>"""
author = extract_author(mf2py.parse(doc=html, url="https://src.example/"),
"https://src.example/")
assert author == {
"author_name": "A Person",
"author_url": "https://a.example/",
"author_photo": "https://a.example/me.jpg",
}
def test_author_urls_must_be_http():
"""A javascript: author URL would be rendered as a clickable link (XSS)"""
import mf2py
from starpunk.webmention_processor import extract_author
html = """
<div class="h-entry">
<span class="p-author h-card">
<a class="u-url p-name" href="javascript:alert(1)">Evil</a>
<img class="u-photo" src="data:image/svg+xml,x" alt=""></span>
</div>"""
author = extract_author(mf2py.parse(doc=html, url="https://src.example/"),
"https://src.example/")
assert author["author_url"] == "https://src.example/"
assert author["author_photo"] is None