bee5f57893
Attaches an open-access PDF to Zotero items that lack a full text. Built on the selection, ledger and attach machinery from PR #826 (feat/zot-fetch-z1, left untouched on its branch); delivery is the stack's legal open-access cascade only — every Unpaywall location → Semantic Scholar openAccessPdf → PMC S3 → PMC OA service → Europe PMC (prisma.fetch.fetch_one with no proxied client, so its mirror tier never runs). No DOI? a Crossref title match first. Downloads must be real PDFs before they are attached; the run ledgers every attempt (attached / no_candidate / error; misses wait 30 days unless --retry). From the #828 review list: - Lazy selection: select_ids() is one cheap query (deleted and full-text items excluded in SQL for --all) and iter_refs() reads each item only when the run reaches it, so --limit bites before ~167k file-less items are materialised while the desktop is held down. - A locked database (--no-hold with the desktop writing) aborts the run with a usage error that names the Zotero desktop, instead of a raw sqlite3.OperationalError — or one error per item. - --dry-run reads only (checked against the running desktop), so it no longer stops/starts zotero; UNPAYWALL_EMAIL is documented in --help. Tests: 66 (scratch Zotero DB, no network), 100% of src/zot/fetch.
51 lines
1.1 KiB
Python
51 lines
1.1 KiB
Python
"""Scratch Zotero DB for the fetch tests (no live DB, no network)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sqlite3
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tests.zot.test_db import ZOTERO_SCHEMA, _seed_schema_maps
|
|
from zot.db import TYPE_MAP, Db
|
|
|
|
EXTRA_SCHEMA = """
|
|
CREATE TABLE IF NOT EXISTS deletedItems (
|
|
itemID INTEGER PRIMARY KEY,
|
|
dateDeleted TEXT DEFAULT CURRENT_TIMESTAMP NOT NULL
|
|
);
|
|
"""
|
|
|
|
|
|
@pytest.fixture()
|
|
def zdb(tmp_path: Path) -> Db:
|
|
path = str(tmp_path / "zotero.sqlite")
|
|
con = sqlite3.connect(path)
|
|
con.executescript(ZOTERO_SCHEMA)
|
|
con.executescript(EXTRA_SCHEMA)
|
|
_seed_schema_maps(con)
|
|
con.commit()
|
|
con.close()
|
|
d = Db(path)
|
|
yield d
|
|
d.close()
|
|
|
|
|
|
def mk_item(
|
|
db: Db,
|
|
*,
|
|
type_name: str = "journalArticle",
|
|
title: str = "",
|
|
doi: str = "",
|
|
isbn: str = "",
|
|
date: str = "",
|
|
extra: str = "",
|
|
) -> int:
|
|
item_id = db.create_item(TYPE_MAP[type_name])
|
|
db.set_fields(
|
|
item_id,
|
|
{"title": title, "DOI": doi, "ISBN": isbn, "date": date, "extra": extra},
|
|
)
|
|
return item_id
|