Files
StarPunk/tests/test_microformats_v280.py
T
PhilandClaude Opus 5.5 978c13358b feat: article titles and summaries stored apart from the text (v2.16.0, ADR-076)
Articles as the IndieWeb defines them: a name separate from the content.

- Migration 023 adds notes.title and notes.summary. A one-time Python data
  step (migrations.DATA_MIGRATIONS) moves each note's '# Heading' first line
  into title, rewrites the file and hash, empties FTS for a rebuild, and puts
  files back if the migration fails. Trashed notes included.
- Micropub: name -> title, summary stored when sent with content, summary
  updatable, q=source returns both. MCP tools take a summary.
- Feeds: titles only for articles (RSS/JSON none, Atom empty); Atom and
  JSON Feed summaries; the title is no longer repeated in the content.
- Pages: p-name/p-summary on the article page. Homepage and tag pages show
  articles as title, summary and "Read more" without images (hidden u-photo
  keeps the post type for parsers).
- Crossposts: articles go out as title, summary, link and hashtags, no
  images; the Bluesky card is the article. Notes unchanged.
- Editor: Title and Summary fields; an article may have no body.
- Fix: a line starting with a hashtag ('#indieweb ...') was rendered as a
  heading and crossposted without its '#' (HashtagLineExtension).
- Fix: excerpts showed raw Markdown; they are plain text now.

Back up the database and the data folder before deploying: the migration
rewrites note files.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 17:05:38 -07:00

270 lines
11 KiB
Python

"""
Microformats2 fixes (v2.8.0)
Pages are rendered and parsed with mf2py; assertions are on the parsed data,
which is what IndieWeb readers and Webmention receivers see.
"""
import re
import sqlite3
from unittest.mock import patch
import mf2py
import pytest
from starpunk import mf2_utils
from starpunk.models import split_title
from starpunk.webmention_processor import extract_author, extract_source_details
from starpunk.webmention_worker import WebmentionWorker
BASE = 'http://localhost:5000'
def parse(client, path):
response = client.get(path)
assert response.status_code == 200
return mf2py.parse(doc=response.data.decode(), url=BASE + path)
def entry_of(parsed):
return next(i for i in parsed['items'] if 'h-entry' in i['type'])
def make_note(app, content, **kw):
from starpunk.notes import create_note
with app.test_request_context():
return create_note(content, published=True, **kw)
def add_mention(app, note, kind, n, photo=True, **cols):
db = sqlite3.connect(app.config['DATABASE_PATH'])
fields = {
'source_url': f'https://src.example/{kind}/{n}',
'target_url': f'{BASE}/note/{note.slug}',
'target_note_id': note.id,
'mention_type': kind,
'author_name': f'{kind.title()} Person {n}',
'author_url': f'https://{kind}{n}.example/',
'author_photo': f'https://{kind}{n}.example/me.jpg' if photo else None,
'content_snippet': f'<p>{kind} text <a href="https://x.example/">link</a></p>',
'validation_status': 'valid',
'moderation_status': 'approved',
**cols,
}
db.execute(f"INSERT INTO webmentions ({', '.join(fields)}) VALUES ({', '.join('?' * len(fields))})",
tuple(fields.values()))
db.commit()
db.close()
# A1/A2: received responses are properties of the entry
def test_responses_are_entry_properties(app, client):
note = make_note(app, "A note")
add_mention(app, note, 'reply', 1, source_post_url='https://src.example/reply/1#canonical',
source_published='2026-11-01T10:00:00Z')
for n in range(10):
add_mention(app, note, 'like', n, photo=n % 2 == 0)
add_mention(app, note, 'repost', 1)
add_mention(app, note, 'bookmark', 1)
add_mention(app, note, 'mention', 1)
props = entry_of(parse(client, f'/note/{note.slug}'))['properties']
assert 'children' not in entry_of(parse(client, f'/note/{note.slug}'))
(comment,) = props['comment']
assert comment['type'] == ['h-cite']
author = comment['properties']['author'][0]
assert author['type'] == ['h-card']
assert author['properties']['name'] == ['Reply Person 1']
assert author['properties']['url'] == ['https://reply1.example/']
assert author['properties']['photo'][0] in ('https://reply1.example/me.jpg',
{'value': 'https://reply1.example/me.jpg', 'alt': ''})
assert '<a href="https://x.example/"' in comment['properties']['content'][0]['html']
# the source's own URL and published time, not ours
assert comment['properties']['url'] == ['https://src.example/reply/1#canonical']
assert comment['properties']['published'] == ['2026-11-01T10:00:00Z']
# all ten likes, including the ones past the visible eight
assert len(props['like']) == 10
names = {like['properties']['author'][0]['properties']['name'][0] for like in props['like']}
assert names == {f'Like Person {n}' for n in range(10)}
assert props['like'][0]['properties']['url'] == ['https://src.example/like/0']
assert props['repost'][0]['properties']['author'][0]['properties']['name'] == ['Repost Person 1']
assert props['bookmark'][0]['type'] == ['h-cite']
assert props['mention'][0]['properties']['author'][0]['properties']['url'] == ['https://mention1.example/']
# A3: dt-* are RFC 3339 UTC
UTC = re.compile(r'^\d{4}-\d\d-\d\dT\d\d:\d\d:\d\dZ$')
def test_dates_are_utc(app, client):
from starpunk.notes import update_note
note = make_note(app, "Dated")
with app.test_request_context():
update_note(id=note.id, content="Dated, edited")
add_mention(app, note, 'reply', 1)
props = entry_of(parse(client, f'/note/{note.slug}'))['properties']
assert UTC.match(props['published'][0]), props['published']
assert UTC.match(props['updated'][0]), props['updated']
assert UTC.match(props['comment'][0]['properties']['published'][0])
home = parse(client, '/')['items'][0]['children'][0]['properties']
assert UTC.match(home['published'][0])
def test_micropub_source_published_is_utc():
from datetime import datetime, timezone, timedelta
from starpunk.utils import iso_utc
assert iso_utc(datetime(2026, 11, 1, 16, 25, 12, 921768)) == '2026-11-01T16:25:12Z'
assert iso_utc(datetime(2026, 11, 1, 9, 0, tzinfo=timezone(timedelta(hours=-7)))) == '2026-11-01T16:00:00Z'
assert iso_utc('2026-11-01T16:25:15+0000') == '2026-11-01T16:25:15Z'
# A4: only a real Markdown heading is a title
@pytest.mark.parametrize("content,title", [
("# Title\n\nBody", "Title"),
("## Sub title ##\n\nBody", "Sub title"),
("#indieweb is great", None),
("#\n\nbody text", None),
("####### seven", None),
("Plain note", None),
])
def test_split_title(content, title):
assert split_title(content)[0] == title
@pytest.mark.parametrize("content,kind", [
("#indieweb is great, posting from my phone", "note"),
("#\n\nbody text", "note"),
# A heading in the text is no longer a title (v2.16.0, ADR-076)
("# A Title\n\nThe body", "note"),
])
def test_post_type_of_hash_notes(app, client, content, kind):
note = make_note(app, content)
for path in (f'/note/{note.slug}', '/'):
parsed = parse(client, path)
entry = entry_of(parsed) if path != '/' else parsed['items'][0]['children'][0]
props = entry['properties']
if kind == 'note':
assert 'name' not in props
assert props['content'][0]['value'].strip()
else:
assert props['name'] == ['A Title']
# A5: the note's own syndicated copy is not a response
def test_own_syndicated_copy_rejected(app):
note = make_note(app, "Crossposted")
db = sqlite3.connect(app.config['DATABASE_PATH'])
db.execute("INSERT INTO syndications (note_id, target, remote_url) VALUES (?, 'gotosocial', ?)",
(note.id, 'https://social.example/@me/statuses/1'))
db.execute("INSERT INTO webmentions (source_url, target_url, target_note_id) VALUES (?, ?, ?)",
('https://brid.gy/post/mastodon/@someone/1', f'{BASE}/note/{note.slug}', note.id))
db.commit()
result = {'valid': True, 'mention_type': 'mention', 'author_name': 'Me', 'author_url': 'https://me.example/',
'author_photo': None, 'content_snippet': 'x',
'source_post_url': 'https://social.example/@me/statuses/1', 'source_uid': None,
'source_published': None}
worker = WebmentionWorker(app, db_path=app.config['DATABASE_PATH'], site_url=BASE)
with patch("starpunk.webmention_worker.process_webmention", return_value=result):
worker._validate_webmention(1, 'https://brid.gy/post/mastodon/@someone/1', 'x', note.id)
status, error = db.execute("SELECT validation_status, validation_error FROM webmentions").fetchone()
assert status == 'invalid' and 'own syndicated copy' in error
# B1/B3: discovery links
def test_head_links_without_webmention(app, client):
app.config['WEBMENTION_ENABLED'] = False
rels = parse(client, '/')['rels']
assert 'webmention' not in rels
for rel in ('micropub', 'indieauth-metadata', 'authorization_endpoint', 'token_endpoint'):
assert rels.get(rel), rel
def test_home_has_representative_hcard(app, client):
# Fresh install: discovery fails, the fallback profile is used
parsed = parse(client, '/')
card = mf2_utils.representative_hcard(parsed, BASE + '/')
assert card and card['properties']['url'] == [app.config['ADMIN_ME']]
@pytest.mark.parametrize("path", ['/likes', '/tag/python'])
def test_list_feeds_have_url_and_author(app, client, path):
make_note(app, "Tagged", tags=["python"])
feed = parse(client, path)['items'][0]
assert feed['type'] == ['h-feed']
assert feed['properties']['url'] == [BASE + path]
assert feed['properties']['author'][0]['type'] == ['h-card']
# B2: representative h-card
def _cards(html, url='https://me.example/'):
return mf2py.parse(doc=html, url=url)
def test_representative_hcard_rules():
other = '<div class="h-card"><a class="p-name u-url" href="https://bob.example/">Bob</a></div>'
# someone else's h-card only: none
assert mf2_utils.representative_hcard(_cards(other), 'https://me.example/') is None
# uid + url
me = '<div class="h-card"><a class="p-name u-url u-uid" href="/">Me</a></div>'
assert mf2_utils.first(mf2_utils.representative_hcard(_cards(other + me), 'https://me.example/'), 'name') == 'Me'
# rel=me
relme = ('<a rel="me" href="https://social.example/@me">x</a>'
'<div class="h-card"><a class="p-name u-url" href="https://social.example/@me">Me</a></div>')
assert mf2_utils.first(mf2_utils.representative_hcard(_cards(other + relme), 'https://me.example/'), 'name') == 'Me'
# only one h-card, url = page
single = '<div class="h-card"><a class="p-name u-url" href="/">Me</a></div>'
assert mf2_utils.first(mf2_utils.representative_hcard(_cards(single), 'https://me.example/'), 'name') == 'Me'
# B4: the responding entry and its author
FEED_PAGE = '''
<div class="h-feed">
<div class="p-author h-card"><a class="p-name u-url" href="https://feed.example/">Feed Owner</a></div>
<div class="h-entry"><a class="u-url" href="https://feed.example/1">one</a>
<div class="e-content">unrelated</div></div>
<div class="h-entry"><a class="u-url" href="https://feed.example/2">two</a>
<time class="dt-published" datetime="2026-11-01T09:00:00-07:00">x</time>
<a class="u-in-reply-to" href="https://me.example/note/a">re</a>
<div class="e-content">my reply</div></div>
</div>'''
def test_responding_entry_and_feed_author():
parsed = mf2py.parse(doc=FEED_PAGE, url='https://feed.example/')
entry = mf2_utils.responding_entry(parsed, 'https://me.example/note/a#frag')
assert mf2_utils.first(entry, 'url') == 'https://feed.example/2'
assert mf2_utils.response_type(entry, 'https://me.example/note/a') == 'reply'
author = extract_author(parsed, 'https://feed.example/', entry)
assert author['author_name'] == 'Feed Owner'
assert author['author_url'] == 'https://feed.example/'
details = extract_source_details(entry)
assert details['source_post_url'] == 'https://feed.example/2'
assert details['source_published'] == '2026-11-01T16:00:00Z'
def test_author_as_url_or_name():
url_author = '<div class="h-entry"><a class="u-author" href="https://al.example/">al</a></div>'
parsed = mf2py.parse(doc=url_author, url='https://s.example/')
assert extract_author(parsed, 'https://s.example/')['author_url'] == 'https://al.example/'
name_author = '<div class="h-entry"><span class="p-author">Al Smith</span></div>'
parsed = mf2py.parse(doc=name_author, url='https://s.example/')
author = extract_author(parsed, 'https://s.example/')
assert author['author_name'] == 'Al Smith' and author['author_url'] == 'https://s.example/'