Merge dev → main: #830 rich post capture + external-host downloads (+ #768/#789/#739) #102

Merged
bvandeusen merged 15 commits from dev into main 2026-06-14 19:16:09 -04:00
2 changed files with 55 additions and 22 deletions
Showing only changes of commit 5e1655384f - Show all commits
+23 -17
View File
@@ -227,25 +227,31 @@ class Ingester:
# resume_cursor None, so everything counts.
if not (resume_cursor and page_cursor == resume_cursor):
chunk_new_posts += 1
# Capture the post body + external links ONCE per post (gated by
# the synthetic post key in the seen-ledger), for EVERY post —
# whether or not it has downloadable media. This is what makes a
# backfill/recovery re-walk RECAPTURE bodies + links for posts
# whose media is already on disk: re-downloading existing media
# never fills links the system never had, so the body recapture
# has to ride the walk itself. Detail-fetch (for an empty feed
# body) happens at most once per post — the gate then spares it on
# later walks. bypass_seen (recovery) re-captures unconditionally.
if post_record_key and write_post_record:
rk = post_record_key(post)
if rk is not None:
pkey, ppid = rk
already = (
set() if bypass_seen
else self._seen_keys(source_id, [pkey])
)
if pkey not in already:
rec_path = write_post_record(post, artist_slug)
if rec_path is not None:
post_records.append(str(rec_path))
self._mark_seen(source_id, [(pkey, ppid)])
media = self.client.extract_media(post, included)
if not media:
# No downloadable media — still capture the post itself
# (title/body/external links) so text-only posts aren't lost.
# Gate via the seen-ledger (synthetic post key) so a text post
# is detail-fetched + recorded ONCE, not re-walked every tick.
if post_record_key and write_post_record:
rk = post_record_key(post)
if rk is not None:
pkey, ppid = rk
already = (
set() if bypass_seen
else self._seen_keys(source_id, [pkey])
)
if pkey not in already:
rec_path = write_post_record(post, artist_slug)
if rec_path is not None:
post_records.append(str(rec_path))
self._mark_seen(source_id, [(pkey, ppid)])
continue
keys = [ledger_key(m) for m in media]
+32 -5
View File
@@ -173,7 +173,10 @@ async def test_tick_downloads_unseen_and_marks_seen(source_id, sync_engine, tmp_
# plan #704: structured run_stats carry the real counts.
assert result.run_stats["downloaded_count"] == 2
assert result.posts_processed == 1
assert _count_ledger(sync_engine, source_id) == 2
# 2 media keys + 1 synthetic post key (body/links recaptured per post).
assert _count_ledger(sync_engine, source_id) == 3
# The post body + links are captured for media posts too (rides the walk).
assert len(result.post_record_paths) == 1
@pytest.mark.asyncio
@@ -196,8 +199,9 @@ async def test_quarantined_media_surfaced_in_result(source_id, sync_engine, tmp_
assert result.run_stats["quarantined_count"] == 1
assert result.run_stats["downloaded_count"] == 1
assert len(result.written_paths) == 1 # quarantined NOT written
# Quarantined media is NOT marked seen (a fixed file may be re-fetched).
assert _count_ledger(sync_engine, source_id) == 1
# Quarantined media is NOT marked seen (a fixed file may be re-fetched);
# m1 + the synthetic post key (body/links captured per post) = 2.
assert _count_ledger(sync_engine, source_id) == 2
@pytest.mark.asyncio
@@ -550,8 +554,31 @@ async def test_recovery_tier2_disk_still_skips(source_id, sync_engine, tmp_path)
)
assert result.files_downloaded == 0
assert downloader.download_calls == 0
# Disk-skip still reconciles the ledger so a later tick skips at tier-1.
assert _count_ledger(sync_engine, source_id) == 1
# Disk-skip reconciles the media key + the synthetic post key (recovery
# recaptures the body/links per post) = 2.
assert _count_ledger(sync_engine, source_id) == 2
@pytest.mark.asyncio
async def test_backfill_recaptures_body_for_already_downloaded_post(
source_id, sync_engine, tmp_path,
):
"""Phase 5 guarantee: a post whose media is ALREADY on disk still gets its
body + external links recaptured on a re-walk. Re-downloading existing media
can never fill links the system never had — so the recapture rides the walk
itself, and a normal backfill is the backfill."""
m1 = _media("p1", 1)
client = _FakeClient([(None, [("p1", [m1])])])
downloader = _FakeDownloader(tmp_path, on_disk={_ledger_key(m1)})
ing = _ingester(sync_engine, tmp_path, client, downloader)
result = ing.run(
source_id=source_id, campaign_id="c1", artist_slug="ingest",
url="https://patreon.com/ingest", mode="backfill",
)
assert result.files_downloaded == 0 # media already on disk
assert len(result.post_record_paths) == 1 # body/links recaptured anyway
assert downloader.post_records == 1
# --- dead-letter ledger (plan #705 #7) ------------------------------------