Supplement slow-indexed IEEE journals from Crossref (TSE fresh papers)

OpenAlex indexes TSE ~2-3 months late (nothing after 2026-06-26 as of Sep 2),
so TSE never appeared in weekly digests. Sources can now be flagged
crossref_fresh: their recent papers are discovered via Crossref (created-date
window, paper-level CC licence = OA) and listed without abstracts; a digested
paper's missing abstract is filled once OpenAlex indexes the DOI, so a later
--force re-run can add its per-paper summary.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
jsahn
2026-09-02 21:00:32 +09:00
co-authored by Claude Fable 5
parent a6ccf04fb2
commit 3f1d16cae1
8 changed files with 307 additions and 4 deletions
+11
View File
@@ -38,6 +38,17 @@ def test_upsert_refreshes_undigested_metadata(tmp_path):
assert paper.abstract == "now with abstract"
def test_digested_paper_gains_missing_abstract_but_stays_frozen(tmp_path):
with make_store(tmp_path) as store:
store.upsert_papers([make_paper("10.1/a", title="fresh via crossref", abstract="")])
store.mark_digested(["10.1/a"], WEEK)
# OpenAlex later indexes the DOI with an abstract (and a normalised title)
store.upsert_papers([make_paper("10.1/a", title="OpenAlex Title", abstract="now indexed")])
[paper] = store.pending_papers(WEEK)
assert paper.abstract == "now indexed" # 초록만 보강
assert paper.title == "fresh via crossref" # 그 외 메타데이터는 동결 유지
def test_digested_papers_are_frozen_and_skipped(tmp_path):
with make_store(tmp_path) as store:
store.upsert_papers([make_paper("10.1/a", title="original")])