Nested-archive extraction (#718) + post-first ingest (#67) + post-body canary (#862) #109

Merged
bvandeusen merged 6 commits from dev into main 2026-06-15 21:37:39 -04:00
Showing only changes of commit 8b99dc9b81 - Show all commits
+5 -2
View File
@@ -174,8 +174,11 @@ def test_sidecar_written_and_findable(tmp_path):
data = json.loads(sidecar.read_text())
assert data["category"] == "patreon"
assert data["id"] == "1001"
assert data["title"] == "My Post Title"
assert data["url"] == "https://www.patreon.com/posts/1001"
# Post-first (#856): the per-media sidecar carries image identity ONLY — no
# post body/title/url. The post-record (`_post.json`) owns those now.
assert "title" not in data
assert "url" not in data
assert "content" not in data
# #830 Phase 2: the per-media sidecar records THIS file's CDN URL so the
# importer can persist its filehash for inline-image localization.
assert data["source_url"] == "https://cdn.patreon.com/media1.png"