Files
stack/tests/bib/test_dedupe_legacy.py

126 lines
4.1 KiB
Python

"""Tests for dev/scripts/dedupe_bib_legacy.py — merging legacy duplicate
rows inside bib.sqlite: Class C (same-url rows predating URL-dedup in
Store.upsert, #624/91c3306) and Class B (listserv re-sends stored as
separate items under distinct email:<Message-ID> urls, refs #665).
"""
from __future__ import annotations
import importlib.util
import json
import sys
from pathlib import Path
import pytest
from bib.item import Source
from bib.store import Store
# Load the script as a module — it lives outside the src/ tree, mirroring
# the pattern in tests/dev/test_migrate_fr_txt.py (dev/ isn't an
# importable package).
_SCRIPT = (
Path(__file__).resolve().parents[2] / "dev" / "scripts" / "dedupe_bib_legacy.py"
)
_spec = importlib.util.spec_from_file_location("_dedupe_bib_legacy", _SCRIPT)
assert _spec and _spec.loader
_dedupe_bib_legacy = importlib.util.module_from_spec(_spec)
sys.modules["_dedupe_bib_legacy"] = _dedupe_bib_legacy
_spec.loader.exec_module(_dedupe_bib_legacy)
dedupe_bib = _dedupe_bib_legacy.dedupe_bib
@pytest.fixture
def store(tmp_path):
s = Store(str(tmp_path / "bib.sqlite"))
yield s
s.close()
def test_url_group_keeps_earliest_and_unions_tags(store):
a = store.create(
Source(title="ACO REACH", url="https://x.test/reach"),
tags=["module:aco", "keep-me"],
)
# Second row with the same url — simulate a pre-#624 duplicate insert
# that predates Store.upsert's URL-based dedup.
con = store._con()
con.execute(
"INSERT INTO items (key, item_type, title, url, extra_json)"
" VALUES ('ZZZZZZZ2','source','ACO REACH','https://x.test/reach','{}')"
)
con.commit()
store.add_tag("ZZZZZZZ2", "loser-tag")
out = dedupe_bib(store, dry_run=False)
assert out["url_groups"] == 1
assert out["removed"] == 1
kept = store.get(a)
assert "loser-tag" in kept.tags
assert "keep-me" in kept.tags
assert (a, "ZZZZZZZ2") in out["pairs"]
with pytest.raises(KeyError):
store.get("ZZZZZZZ2")
def test_email_group_aliases_mids(store):
s1 = Source(title="iQIES Hold Times", url="email:aaa@x")
s1.abstract = "Same body."
s2 = Source(title="iQIES Hold Times", url="email:bbb@x")
s2.abstract = "Same body."
k1 = store.create(s1, tags=["source:email"])
k2 = store.create(s2, tags=["source:email"])
out = dedupe_bib(store, dry_run=False)
assert out["email_groups"] == 1
assert out["removed"] == 1
assert out["aliased"] == 1
assert (k1, k2) in out["pairs"]
# Read extra_json via raw SQL, not Item.to_row() — Source.to_row()
# only serializes its own declared fields (doc_type) and would
# silently drop alias_mids on a round-trip through the pydantic
# model (see dedupe_bib_legacy.py's docstring / email_ingest.py:180).
con = store._con()
row = con.execute("SELECT extra_json FROM items WHERE key = ?", (k1,)).fetchone()
ej = json.loads(row["extra_json"])
assert "bbb@x" in ej["alias_mids"]
with pytest.raises(KeyError):
store.get(k2)
def test_email_group_idempotent_second_run_adds_nothing(store):
s1 = Source(title="iQIES Hold Times", url="email:aaa@x")
s1.abstract = "Same body."
s2 = Source(title="iQIES Hold Times", url="email:bbb@x")
s2.abstract = "Same body."
k1 = store.create(s1, tags=["source:email"])
store.create(s2, tags=["source:email"])
dedupe_bib(store, dry_run=False)
out2 = dedupe_bib(store, dry_run=False)
assert out2["removed"] == 0
assert out2["aliased"] == 0
con = store._con()
row = con.execute("SELECT extra_json FROM items WHERE key = ?", (k1,)).fetchone()
ej = json.loads(row["extra_json"])
assert ej["alias_mids"] == ["bbb@x"]
def test_dry_run_touches_nothing(store):
s1 = Source(title="T", url="email:a@x")
s1.abstract = "B"
s2 = Source(title="T", url="email:b@x")
s2.abstract = "B"
store.create(s1, tags=["source:email"])
store.create(s2, tags=["source:email"])
out = dedupe_bib(store, dry_run=True)
assert out["removed"] == 0
assert out["email_groups"] == 1
assert out["pairs"] == []
assert len(store.list_items(query="T")) == 2