refactor(subscriptions): remove the dead backfill dry-run preview (#1281)
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 17s
CI / backend-lint-and-test (push) Successful in 27s
CI / integration (push) Successful in 3m36s

PreviewDialog.vue was orphaned — nothing mounted it — so the dry-run preview
was unreachable. Rather than wire it up, remove the whole chain: its unique
value (a capped 3-page count of what a backfill would grab) is low, and its
adjacent needs are already covered — auth validation by verify_source_credential,
and actually fetching recent posts by "Check now". Operator decision 2026-07-06.

Removed:
- frontend: PreviewDialog.vue + sources store previewSource()
- backend: POST /api/sources/<id>/preview route, download_backends.preview_source,
  IngestCore.preview() + its now-unused NativeIngestError import
- tests: the 3 ingester preview tests

Nothing else referenced the chain (verified). Shared campaign-resolution and
ledger helpers stay — they're used by run()/verify_source_credential.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
This commit is contained in:
2026-07-06 14:15:19 -04:00
parent 2638cf1a35
commit 8f6547f8d7
6 changed files with 0 additions and 329 deletions
-46
View File
@@ -230,52 +230,6 @@ async def set_backfill(source_id: int):
return jsonify(record.to_dict())
@sources_bp.route("/<int:source_id>/preview", methods=["POST"])
async def preview_source_endpoint(source_id: int):
"""Plan #708 B4: dry-run — count what a backfill WOULD download for a native
platform (Patreon today), without downloading. Walks the first few feed pages
and counts media not already in the seen/dead ledgers. Returns
{total_new, posts_scanned, pages_scanned, has_more, sample[]} or 409 + reason
(unresolvable campaign id / auth / drift). 400 for gallery-dl platforms (no
cheap dry-run — their verify is a slow --simulate)."""
from pathlib import Path
from ..services.credential_service import CredentialService
from ..services.download_backends import preview_source, uses_native_ingester
from ..tasks._sync_engine import sync_session_factory
from .credentials import _get_crypto
async with get_session() as session:
rec = await SourceService(session).get(source_id)
if rec is None:
return _bad("not_found", status=404)
if not uses_native_ingester(rec.platform):
return _bad(
"unsupported",
detail="Preview is only available for native-ingester platforms.",
status=400,
)
cred = CredentialService(session, _get_crypto())
cookies_path = await cred.get_cookies_path(rec.platform)
auth_token = await cred.get_token(rec.platform)
# The walk + ledger reads are sync (run off the request loop); the process
# sync engine is the same one the download task uses.
result = await preview_source(
platform=rec.platform,
url=rec.url,
source_id=source_id,
config_overrides=rec.config_overrides or {},
cookies_path=str(cookies_path) if cookies_path else None,
images_root=Path("/images"),
sync_session_factory=sync_session_factory(),
auth_token=auth_token,
)
if "error" in result:
return _bad("preview_failed", detail=result["error"], status=409)
return jsonify(result)
@sources_bp.route("/<int:source_id>/check", methods=["POST"])
async def check_source(source_id: int):
"""FC-3c: enqueue a download for this source.
-44
View File
@@ -24,7 +24,6 @@ import asyncio
from pathlib import Path
from .gallery_dl import DownloadResult, ErrorType
from .native_ingest_common import NativeIngestError
from .patreon_ingester import PatreonIngester
from .patreon_resolver import extract_vanity, resolve_campaign_id_for_source
from .pixiv_client import user_id_from_url
@@ -204,49 +203,6 @@ async def _run_native_ingester(
return dl_result, resolved_campaign_id
async def preview_source(
*,
platform: str,
url: str,
source_id: int,
config_overrides: dict | None,
cookies_path: str | None,
images_root: Path,
sync_session_factory,
auth_token: str | None = None,
page_limit: int = 3,
) -> dict:
"""Dry-run preview for a native platform (plan #708 B4): resolve the campaign
id, then walk a few pages counting media not already seen/dead — no download.
Returns the preview dict (total_new / posts_scanned / pages_scanned /
has_more / sample), or `{"error": msg}` on a resolve / auth / drift failure.
Native-only — the caller gates on `uses_native_ingester`.
"""
import asyncio
campaign_id, _ = await _resolve_native_campaign_id(
platform, url, cookies_path, config_overrides or {}
)
if not campaign_id:
return {"error": _campaign_resolution_error(platform, url)}
ingester = _native_ingester_cls(platform)(
images_root=images_root,
cookies_path=cookies_path,
session_factory=sync_session_factory,
auth_token=auth_token,
)
loop = asyncio.get_running_loop()
try:
result = await loop.run_in_executor(
None,
lambda: ingester.preview(source_id, campaign_id, page_limit=page_limit),
)
except NativeIngestError as exc:
return {"error": f"Couldn't preview: {exc}"}
return result
async def verify_source_credential(
*,
platform: str,
-67
View File
@@ -577,73 +577,6 @@ class Ingester:
error_type=None, error_message=None,
)
# -- preview (dry-run) -------------------------------------------------
def preview(
self,
source_id: int,
campaign_id: str,
*,
page_limit: int = 3,
sample_size: int = 10,
) -> dict:
"""Dry-run (plan #708 B4): walk up to `page_limit` pages and count media
NOT already in the seen/dead ledgers, WITHOUT downloading anything.
Read-only — only the seen/dead SELECTs touch the DB (short sessions). Lets
an operator gauge "is this source worth a backfill?" cheaply. Returns:
{total_new, posts_scanned, pages_scanned, has_more,
sample: [{title, date, new}, ...]} # sample = posts with new media
A client-level failure (auth/drift) propagates to the caller.
"""
total_new = 0
posts_scanned = 0
pages_scanned = 0
has_more = False
sample: list[dict] = []
unset = object()
last_page: object = unset
# #874: same gated-post gate as run() — the preview must not count
# blurred locked-preview media as "new", or it would overstate a gated
# source's backlog (preview/apply parity, rule 93).
post_is_gated = getattr(self.client, "post_is_gated", None)
for post, included, page_cursor in self.client.iter_posts(
campaign_id, cursor=None
):
if page_cursor != last_page:
last_page = page_cursor
pages_scanned += 1
if pages_scanned > page_limit:
has_more = True
pages_scanned = page_limit
break
posts_scanned += 1
if post_is_gated and post_is_gated(post):
continue
media = self.client.extract_media(post, included)
if not media:
continue
keys = [self._ledger_key(m) for m in media]
skip = self._seen_keys(source_id, keys) | self._dead_keys(source_id, keys)
new_count = sum(1 for m in media if self._ledger_key(m) not in skip)
total_new += new_count
if new_count > 0 and len(sample) < sample_size:
meta = self.client.post_meta(post)
sample.append(
{
"title": meta.get("title") or "(untitled)",
"date": meta.get("date"),
"new": new_count,
}
)
return {
"total_new": total_new,
"posts_scanned": posts_scanned,
"pages_scanned": pages_scanned,
"has_more": has_more,
"sample": sample,
}
# -- failure mapping (adapter overrides) -------------------------------
def _failure_result(self, exc: Exception, _result) -> DownloadResult: