ryan
b8d8bb8a57
`reindex` deleted every chunk before contacting Paperless, so an unreachable or empty Paperless left the store empty (which happened when Paperless was crash-looping during its v3 upgrade). It now fetches first, aborts without deleting if that fails or returns nothing, and indexes the fetched documents instead of fetching twice. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
67 lines
2.0 KiB
Python
67 lines
2.0 KiB
Python
import sys
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from scripts import manage_vectorstore as cli
|
|
|
|
|
|
@pytest.fixture
|
|
def calls(monkeypatch):
|
|
calls = []
|
|
monkeypatch.setattr(cli, "delete_all_documents", lambda: calls.append("delete_all"))
|
|
monkeypatch.setattr(
|
|
cli,
|
|
"delete_documents_by_metadata",
|
|
lambda k, v: calls.append(f"delete {k}={v}"),
|
|
)
|
|
monkeypatch.setattr(
|
|
cli,
|
|
"fetch_documents_from_paperless_ngx",
|
|
AsyncMock(side_effect=lambda: calls.append("fetch") or ["doc"]),
|
|
)
|
|
monkeypatch.setattr(
|
|
cli,
|
|
"index_documents",
|
|
AsyncMock(side_effect=lambda *docs: calls.append(f"paperless {list(docs)}")),
|
|
)
|
|
monkeypatch.setattr(
|
|
cli,
|
|
"index_obsidian_documents",
|
|
AsyncMock(side_effect=lambda: calls.append("obsidian")),
|
|
)
|
|
monkeypatch.setattr(cli, "stats", MagicMock())
|
|
return calls
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"command, expected",
|
|
[
|
|
# A full reindex must not drop Obsidian notes after wiping everything.
|
|
# Fetch before deleting, then index the fetched documents (no refetch).
|
|
("reindex", ["fetch", "delete_all", "paperless [['doc']]", "obsidian"]),
|
|
("reindex-obsidian", ["delete source=obsidian", "obsidian"]),
|
|
],
|
|
)
|
|
def test_reindex_commands(calls, monkeypatch, command, expected):
|
|
monkeypatch.setattr(sys, "argv", ["manage_vectorstore", command])
|
|
cli.main()
|
|
assert calls == expected
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"failure",
|
|
[
|
|
AsyncMock(side_effect=ConnectionError("Name or service not known")),
|
|
AsyncMock(return_value=[]),
|
|
],
|
|
)
|
|
def test_reindex_leaves_index_untouched_when_paperless_fails(
|
|
calls, monkeypatch, failure
|
|
):
|
|
monkeypatch.setattr(cli, "fetch_documents_from_paperless_ngx", failure)
|
|
monkeypatch.setattr(sys, "argv", ["manage_vectorstore", "reindex"])
|
|
with pytest.raises(SystemExit):
|
|
cli.main()
|
|
assert "delete_all" not in calls
|