sebrief/tests/test_store.py

"""SQLite store: paper lifecycle (upsert/freeze/rollover), digest idempotency, deliveries."""

from __future__ import annotations

from datetime import date

from _fakes import WEEK, make_paper, make_payload, make_summary

from sebrief.models import DigestResult
from sebrief.store import Store


def make_store(tmp_path) -> Store:
    return Store(tmp_path / "data" / "test.sqlite3")


def make_result(papers=None, degraded=False) -> DigestResult:
    payload = make_payload(papers=papers)
    return DigestResult(
        payload=payload, digest=None, markdown="# md", model_used="m", degraded=degraded
    )


# ----------------------------------------------------------------------------------- papers
def test_upsert_inserts_and_counts_new(tmp_path):
    with make_store(tmp_path) as store:
        p1, p2 = make_paper("10.1/a"), make_paper("10.1/b")
        assert store.upsert_papers([p1, p2]) == 2
        assert store.upsert_papers([p1]) == 0  # re-collection is not new
        assert store.paper_count() == 2


def test_upsert_refreshes_undigested_metadata(tmp_path):
    with make_store(tmp_path) as store:
        store.upsert_papers([make_paper("10.1/a", abstract="")])
        store.upsert_papers([make_paper("10.1/a", abstract="now with abstract")])
        [paper] = store.pending_papers(WEEK)
        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")])
        store.mark_digested(["10.1/a"], WEEK)
        store.upsert_papers([make_paper("10.1/a", title="rewritten")])
        # not pending for a later week, and metadata unchanged
        assert store.pending_papers("2026-W37") == []
        [paper] = store.pending_papers(WEEK)  # --force re-run of the same week still sees it
        assert paper.title == "original"


def test_pending_includes_undigested_leftovers_and_orders_by_date(tmp_path):
    with make_store(tmp_path) as store:
        old = make_paper("10.1/old", published_date=date(2026, 8, 20))  # last week's late arrival
        new = make_paper("10.1/new", published_date=date(2026, 9, 2))
        undated = make_paper("10.1/undated", published_date=None)
        store.upsert_papers([new, undated, old])
        dois = [p.doi for p in store.pending_papers(WEEK)]
        assert dois == ["10.1/old", "10.1/new", "10.1/undated"]  # dated first (ascending), undated last


def test_paper_roundtrip_preserves_fields(tmp_path):
    with make_store(tmp_path) as store:
        original = make_paper("10.1/a", authors=["김철수", "Bob"], topics=["Testing", "LLM"])
        store.upsert_papers([original])
        [loaded] = store.pending_papers(WEEK)
        assert loaded == original


# ---------------------------------------------------------------------------- paper summaries
def test_paper_summaries_roundtrip_and_survive_metadata_refresh(tmp_path):
    with make_store(tmp_path) as store:
        store.upsert_papers([make_paper("10.1/a")])
        summary = make_summary(tldr="한 줄.")
        store.save_paper_summaries({"10.1/a": summary})
        [paper] = store.pending_papers(WEEK)
        assert paper.summary == summary
        # a later re-collection refreshes metadata but must not clear the summary
        store.upsert_papers([make_paper("10.1/a", abstract="updated")])
        [paper] = store.pending_papers(WEEK)
        assert paper.abstract == "updated" and paper.summary == summary


def test_paper_summaries_allowed_on_frozen_papers(tmp_path):
    with make_store(tmp_path) as store:
        store.upsert_papers([make_paper("10.1/a")])
        store.mark_digested(["10.1/a"], WEEK)
        store.save_paper_summaries({"10.1/a": make_summary()})
        [paper] = store.pending_papers(WEEK)  # digest_week = WEEK: visible on --force re-run
        assert paper.summary is not None


def test_migration_adds_summary_column_to_old_db(tmp_path):
    import sqlite3

    db = tmp_path / "data" / "old.sqlite3"
    db.parent.mkdir(parents=True)
    conn = sqlite3.connect(db)
    conn.executescript(
        """
        CREATE TABLE papers (
            doi TEXT PRIMARY KEY, title TEXT NOT NULL, abstract TEXT NOT NULL DEFAULT '',
            authors TEXT NOT NULL DEFAULT '[]', venue TEXT NOT NULL DEFAULT '',
            published_date TEXT, oa_url TEXT, pdf_url TEXT, topics TEXT NOT NULL DEFAULT '[]',
            source TEXT NOT NULL DEFAULT '', collected_at TEXT, digest_week TEXT
        );
        INSERT INTO papers (doi, title) VALUES ('10.1/legacy', 'Legacy Paper');
        """
    )
    conn.commit()
    conn.close()

    with Store(db) as store:
        [paper] = store.pending_papers(WEEK)
        assert paper.doi == "10.1/legacy" and paper.summary is None
        store.save_paper_summaries({"10.1/legacy": make_summary()})
        [paper] = store.pending_papers(WEEK)
        assert paper.summary is not None


# ---------------------------------------------------------------------------------- digests
def test_digest_idempotency_and_upsert(tmp_path):
    with make_store(tmp_path) as store:
        assert store.has_digest(WEEK) is False
        store.save_digest(make_result())
        assert store.has_digest(WEEK) is True
        store.save_digest(make_result(degraded=True))  # --force resend overwrites
        row = store._conn.execute("SELECT degraded FROM digests WHERE week = ?", (WEEK,)).fetchone()
        assert row["degraded"] == 1


def test_deliveries(tmp_path):
    with make_store(tmp_path) as store:
        store.save_digest(make_result())
        store.mark_sent(WEEK, "file", "/tmp/2026-W36.md")
        store.mark_sent(WEEK, "file", "/tmp/2026-W36.md (resend)")
        rows = store.deliveries_for(WEEK)
        assert [r["channel"] for r in rows] == ["file", "file"]
        assert rows[1]["receipt"].endswith("(resend)")