benstull/rfc-app
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

§22 S2: corpus mirror reads each collection's <subfolder>/rfcs/

Browse Source 
refresh_meta_repo now iterates a project's collections and keys cached_rfcs by
collection_id; the default collection (subfolder '') keeps the shipped rfcs/
root path. N=1 default path unchanged (469 green).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ben Stull
2026-06-05 13:02:59 -07:00
parent 868391870c
commit 91b0fb358c
2 changed files with 103 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/cache.py
+26 -11
View File
@@ -54,15 +54,27 @@ async def refresh_meta_repo(config: Config, gitea: Gitea) -> None:
async def _refresh_project_corpus(org: str, project_id: str, repo: str, gitea: Gitea) -> None:
# §22 S1: the corpus grain is the collection. The mirror is project-grained
# (reads rfcs/ at the repo root = the project's default collection); resolve
# that collection once and key cached_rfcs by it.
# §22 S2: the corpus grain is the collection. Mirror every collection of the
# project from its `<subfolder>/rfcs/` directory, keying cached_rfcs by the
# collection id. The default collection (subfolder '') reads `rfcs/` — the
# shipped path, unchanged. include_unlisted: the mirror serves every
# collection's content regardless of enumeration visibility.
from . import collections as collections_mod
collection_id = collections_mod.default_collection_id(project_id)
for col in collections_mod.list_collections(project_id, include_unlisted=True):
await _refresh_collection_corpus(
org, project_id, repo, col["id"], col["subfolder"] or "", gitea
)
async def _refresh_collection_corpus(
org: str, project_id: str, repo: str, collection_id: str, subfolder: str, gitea: Gitea
) -> None:
rfcs_dir = f"{subfolder}/rfcs" if subfolder else "rfcs"
try:
files = await gitea.list_dir(org, repo, "rfcs", ref="main")
files = await gitea.list_dir(org, repo, rfcs_dir, ref="main")
except GiteaError as e:
log.warning("refresh_meta_repo: project %s: cannot list rfcs/: %s", project_id, e)
log.warning("refresh_meta_repo: %s/%s: cannot list %s: %s",
project_id, collection_id, rfcs_dir, e)
return
seen_slugs: set[str] = set()
@@ -76,17 +88,19 @@ async def _refresh_project_corpus(org: str, project_id: str, repo: str, gitea: G
try:
entry = entry_mod.parse(text)
except Exception as parse_err:
log.warning("refresh_meta_repo: %s: skipping %s: %s", project_id, f["path"], parse_err)
log.warning("refresh_meta_repo: %s/%s: skipping %s: %s",
project_id, collection_id, f["path"], parse_err)
continue
if not entry.slug:
log.warning("refresh_meta_repo: %s: skipping %s: missing slug", project_id, f["path"])
log.warning("refresh_meta_repo: %s/%s: skipping %s: missing slug",
project_id, collection_id, f["path"])
continue
seen_slugs.add(entry.slug)
_upsert_cached_rfc(entry, body_sha=sha, collection_id=collection_id)
# Entries removed from a project's rfcs/ — the spec keeps withdrawn entries
# Entries removed from a collection's rfcs/ — the spec keeps withdrawn entries
# as historical record (§3), so this fires only for out-of-band deletes;
# leave the row, scoped to this project, for reconciler attention.
# leave the row, scoped to this collection, for reconciler attention.
existing = {
row["slug"]
for row in db.conn().execute(
@@ -94,7 +108,8 @@ async def _refresh_project_corpus(org: str, project_id: str, repo: str, gitea: G
)
}
for missing in existing - seen_slugs:
log.info("refresh_meta_repo: %s/%s no longer in rfcs/ — leaving cache row", project_id, missing)
log.info("refresh_meta_repo: %s/%s/%s no longer present — leaving cache row",
project_id, collection_id, missing)
def _upsert_cached_rfc(entry: entry_mod.Entry, body_sha: str, collection_id: str = "default") -> None: