bindery/tests/test_optional_cwa.py

"""Downloads and builds work with uploads or library matching disabled."""

import json
import os
import subprocess
import sys
from unittest.mock import Mock

import pytest
from test_api import H
from test_api import client as client
from test_deliver import STORY_URL, add_story, rebuild, site, update
from test_deliver import jobs as jobs

from bindery import config, orchestrator
from bindery.cwa import Book
from bindery.ingest import IngestError
from bindery.jobs import DownloadMode, Job
from bindery.store import Store


@pytest.fixture(autouse=True)
def isolated(client, jobs, monkeypatch, tmp_path):
    monkeypatch.setattr(config, "INGEST_DIR", tmp_path / "ingest")
    config.INGEST_DIR.mkdir()
    monkeypatch.setattr(config, "TMP_DIR", tmp_path / "tmp")
    config.TMP_DIR.mkdir()
    monkeypatch.setattr(config, "CWA_URL", "")
    monkeypatch.setattr(config, "CALIBRE_DB_PATH", None)
    monkeypatch.setattr(orchestrator, "cwa", Mock(side_effect=AssertionError("Unexpected CWA request")))
    monkeypatch.setattr(orchestrator, "_find_book", Mock(side_effect=AssertionError("Unexpected book search")))


@pytest.fixture
def library(isolated, monkeypatch):
    monkeypatch.setattr(config, "CWA_URL", "https://cwa.invalid")
    client = Mock()
    client.get_book.return_value = Book(7, "uuid-7", "Test Story").to_dict()
    monkeypatch.setattr(orchestrator, "cwa", Mock(return_value=client))
    monkeypatch.setattr(orchestrator, "_find_book", Mock(return_value=None))


@pytest.mark.parametrize("enabled", [None, False, True])
def test_app_starts_without_any_cwa_configuration(tmp_path, enabled):
    env = {
        **os.environ,
        "CONFIG_DIR": str(tmp_path / "standalone"),
        "TMP_DIR": str(tmp_path / "builds"),
        "AUTH_METHOD": "none",
        "BINDERY_START_THREADS": "false",
        "URL_BASE": "",
        "CWA_ENABLED": str(enabled),
    }
    # CWA is off unless CWA_ENABLED turns it on.
    for name in (
        "INGEST_DIR",
        "CWA_URL",
        "CWA_DB_PATH",
        "CALIBRE_DB_PATH",
        *(["CWA_ENABLED"] if enabled is None else []),
    ):
        env.pop(name, None)
    result = subprocess.run(
        [
            sys.executable,
            "-c",
            "from bindery.web import app; "
            "client = app.test_client(); "
            "assert client.get('/api/health').status_code == 200; "
            f"assert client.get('/api/config').json['cwa_enabled'] is {bool(enabled)}; "
            "settings = client.get('/api/settings').json; "
            "assert settings['pause_uploads'] is True; "
            "assert settings['ingest_available'] is False; "
            "assert settings['link_books'] is False; "
            "assert settings['linking_available'] is False",
        ],
        env=env,
        capture_output=True,
        text=True,
        timeout=30,
    )
    assert result.returncode == 0, result.stderr
    assert "ERROR" not in result.stderr
    # Bindery names what is missing only for a user who turned CWA on.
    for text in ("WARNING", "INGEST_DIR is not set", "CWA_URL and CALIBRE_DB_PATH are not set", "remove CWA_ENABLED"):
        assert (text in result.stderr) is bool(enabled)
    if not enabled:
        assert "CWA" not in result.stderr and "INGEST" not in result.stderr


@pytest.fixture
def cwa_off(monkeypatch):
    monkeypatch.setattr(config, "CWA_ENABLED", False)


def test_without_cwa_and_an_ingest_folder_a_job_only_builds_a_changed_book(monkeypatch, cwa_off):
    monkeypatch.setattr(config, "INGEST_DIR", None)
    site(monkeypatch, [(1, "One", "First chapter")])
    job = Job(mode=DownloadMode.NEW, url=STORY_URL)
    assert orchestrator._run_site_job(job).endswith("Built the book")
    story_id = job.story_id
    story = orchestrator.store.get_story(story_id)
    assert (story["status"], story["message"], story["ingested_at"]) == ("ok", "Built the book", None)
    assert orchestrator.store.get_setting(story_id, "upload_held") is None
    assert len(list(config.TMP_DIR.glob(f"story-{story_id}-*.epub"))) == 1
    assert update(story_id).startswith("No changes")
    assert orchestrator._run_rebuild(Job(mode=DownloadMode.REBUILD, story_id=story_id)) == "No changes"
    assert rebuild(story_id) == "Built the book"
    site(monkeypatch, [(1, "One", "First chapter"), (2, "Two", "Second chapter")])
    assert update(story_id).endswith("Built the book")
    orchestrator.cwa.assert_not_called()


@pytest.mark.parametrize("saved_id", [None, 7])
def test_without_cwa_the_ingest_folder_gets_each_changed_book_as_a_plain_epub(cwa_off, saved_id):
    # A pause, a hold and a saved book ID are from a time with CWA. They do not apply.
    orchestrator.save_settings(pause_uploads=True, hold_new_links=True)
    story_id = add_story(calibre_id=saved_id, calibre_uuid="saved-uuid" if saved_id else None)
    orchestrator._link_changed(story_id)
    orchestrator.store.set_setting(story_id, "upload_held", True)
    assert rebuild(story_id) == "Sent to ingest folder"
    assert [p.suffix for p in config.INGEST_DIR.iterdir()] == [".epub"]
    assert orchestrator.store.get_story(story_id)["ingested_at"] is None
    assert orchestrator.store.get_setting(story_id, "upload_held") is None
    assert orchestrator._run_rebuild(Job(mode=DownloadMode.REBUILD, story_id=story_id)) == "No changes"
    assert len(list(config.INGEST_DIR.iterdir())) == 1
    orchestrator.cwa.assert_not_called()


def test_without_cwa_a_missing_ingest_folder_is_still_an_error(monkeypatch, tmp_path, cwa_off):
    monkeypatch.setattr(config, "INGEST_DIR", tmp_path / "missing")
    story_id = add_story()
    with pytest.raises(IngestError, match="does not exist"):
        rebuild(story_id)
    # The book counts as sent only when it is in the folder.
    assert orchestrator.store.get_setting(story_id, "sent_key") is None


def test_cwa_off_shows_in_the_config_and_refuses_cwa_logins(client, monkeypatch, cwa_off):
    assert client.get("/api/config").json["cwa_enabled"] is False
    monkeypatch.setattr(config, "AUTH_METHOD", "cwa")
    monkeypatch.setattr(config, "CWA_DB_PATH", "/cwa/app.db")
    response = client.get("/api/stories")
    assert response.status_code == 503
    assert response.json["error"].startswith("AUTH_METHOD=cwa needs CWA_ENABLED=true.")


def test_without_cwa_the_download_template_uses_the_story_id(client, cwa_off):
    assert client.get("/api/config").json["download_fields"]["id"] == "The Bindery story ID"
    story_id = add_story(calibre_id=77)
    client.put("/api/settings", json={"download_template": "{title} {id}"}, headers=H)
    response = client.get(f"/api/stories/{story_id}/epub")
    response.close()
    assert f'filename="My Title {story_id}.epub"' in response.headers["Content-Disposition"]


def test_link_setting_defaults_on_and_persists(client, monkeypatch, tmp_path, library):
    assert client.get("/api/settings").json["link_books"] is True
    response = client.put("/api/settings", json={"link_books": False}, headers=H)
    assert response.status_code == 200
    assert response.json["link_books"] is False
    monkeypatch.setattr(orchestrator, "store", Store(tmp_path / "bindery.db"))
    assert client.get("/api/settings").json["link_books"] is False
    response = client.put("/api/settings", json={"hold_new_links": True}, headers=H)
    assert response.json["link_books"] is False
    assert client.put("/api/settings", json={"link_books": True}, headers=H).json["link_books"] is True


@pytest.mark.parametrize("url", ["", "https://cwa.invalid"])
@pytest.mark.parametrize("database", [False, True])
def test_linking_requires_either_library_source(client, monkeypatch, tmp_path, url, database):
    monkeypatch.setattr(config, "CWA_URL", url)
    monkeypatch.setattr(config, "CALIBRE_DB_PATH", tmp_path / "metadata.db" if database else None)
    available = bool(url or database)
    settings = client.get("/api/settings").json
    assert settings["linking_available"] is available
    assert settings["link_books"] is available
    settings = client.put("/api/settings", json={"link_books": True}, headers=H).json
    assert settings["linking_available"] is available
    assert settings["link_books"] is available


@pytest.mark.parametrize("saved", [None, False, True])
def test_missing_sources_force_linking_off_without_changing_preferences(client, monkeypatch, tmp_path, jobs, saved):
    monkeypatch.setattr(config, "CWA_DB_PATH", tmp_path / "app.db")
    orchestrator.store.set_setting(None, "link_books", saved)
    orchestrator.store.set_setting(None, "hold_new_links", True)
    story_id = add_story()
    orchestrator.store.set_setting(story_id, "upload_held", True)
    for requested in (True, False):
        response = client.put("/api/settings", json={"link_books": requested}, headers=H)
        assert response.status_code == 200
        assert response.json["link_books"] is False
        assert response.json["linking_available"] is False
        assert response.json["hold_new_links"] is True
        assert orchestrator.store.get_setting(None, "link_books") is saved
        assert jobs.get_next() is None
    monkeypatch.setattr(config, "CALIBRE_DB_PATH", tmp_path / "metadata.db")
    assert client.get("/api/settings").json["linking_available"] is True
    assert client.get("/api/settings").json["link_books"] is (saved is not False)


@pytest.mark.parametrize("value", ["false", 0, [], {}])
def test_link_setting_requires_a_boolean(client, value):
    response = client.put("/api/settings", json={"link_books": value}, headers=H)
    assert response.status_code == 400
    assert client.get("/api/settings").json["link_books"] is False


@pytest.mark.parametrize("paused", [False, True])
def test_missing_ingest_forces_pause_without_changing_saved_preference(client, monkeypatch, tmp_path, paused):
    orchestrator.save_settings(pause_uploads=paused)
    monkeypatch.setattr(config, "INGEST_DIR", None)
    settings = client.get("/api/settings").json
    assert settings["pause_uploads"] is True
    assert settings["ingest_available"] is False
    for requested in (False, True):
        response = client.put("/api/settings", json={"pause_uploads": requested}, headers=H)
        assert response.status_code == 200
        assert response.json["pause_uploads"] is True
    monkeypatch.setattr(config, "INGEST_DIR", tmp_path / "enabled")
    assert client.get("/api/settings").json["pause_uploads"] is paused


@pytest.mark.parametrize("existing", [False, True])
@pytest.mark.parametrize("link_books", [False, True])
def test_build_without_ingest_succeeds_and_keeps_the_book_local(monkeypatch, tmp_path, existing, link_books, library):
    orchestrator.save_settings(link_books=link_books)
    monkeypatch.setattr(config, "INGEST_DIR", None)
    story_id = add_story(ingested_at="2026-01-01" if existing else None)
    assert rebuild(story_id) == "Not sent. INGEST_DIR is not set."
    story = orchestrator.store.get_story(story_id)
    assert story["status"] == "ok"
    assert story["ingested_at"] == ("2026-01-01" if existing else None)
    assert list(config.TMP_DIR.glob(f"story-{story_id}-*.epub"))
    assert not list((tmp_path / "ingest").iterdir())
    details = orchestrator.story_details(story_id)
    assert details["pause_uploads"] is True
    assert details["story"]["upload_held"] is True
    assert details["library_error"] is None


@pytest.mark.parametrize("configured", [False, True])
@pytest.mark.parametrize("saved_id", [None, 7])
@pytest.mark.parametrize("paused", [False, True])
def test_linking_off_exports_books_and_respects_pause(monkeypatch, tmp_path, configured, saved_id, paused):
    if configured:
        monkeypatch.setattr(config, "CWA_URL", "https://cwa.invalid")
        monkeypatch.setattr(config, "CALIBRE_DB_PATH", tmp_path / "unreadable.db")
    orchestrator.save_settings(link_books=False, pause_uploads=paused)
    story_id = add_story(calibre_id=saved_id, calibre_uuid="saved-uuid", ingested_at="2026-01-01")
    message = rebuild(story_id)
    assert orchestrator.store.get_story(story_id)["status"] == "ok"
    assert orchestrator.story_details(story_id)["library_error"] is None
    orchestrator.cwa.assert_not_called()
    orchestrator._find_book.assert_not_called()
    if not paused:
        if saved_id is not None:
            assert message == "Updated library book 7"
            manifest = next(config.INGEST_DIR.glob("*.cwa.json"))
            assert json.loads(manifest.read_text()) == {"action": "add_format", "book_id": 7}
        else:
            assert message == "Sent to ingest folder"
            assert not list(config.INGEST_DIR.glob("*.cwa.json"))
        assert len(list(config.INGEST_DIR.glob("*.epub"))) == 1
        assert orchestrator.store.get_setting(story_id, "upload_held") is None
    else:
        assert message.startswith("Not sent.")
        assert not list(config.INGEST_DIR.iterdir())
        assert orchestrator.store.get_setting(story_id, "upload_held") is True


def test_disabling_linking_releases_approval_holds_for_saved_ids(jobs, library):
    orchestrator.save_settings(hold_new_links=True)
    story_id = add_story(calibre_id=7, calibre_uuid="uuid-7", ingested_at="2026-01-01")
    orchestrator._link_changed(story_id)
    assert "Approve link" in rebuild(story_id)
    orchestrator.save_settings(link_books=False)
    assert orchestrator.get_settings()["hold_new_links"] is True
    assert orchestrator.story_details(story_id)["story"]["needs_approval"] is False
    job = jobs.get_next()
    assert job.story_id == story_id
    assert orchestrator._run_rebuild(job) == "Updated library book 7"


@pytest.mark.parametrize("link_books", [True, False])
def test_story_response_reports_linking_and_approval_settings(client, link_books, library):
    orchestrator.save_settings(link_books=link_books, hold_new_links=True)
    story_id = add_story()
    orchestrator._link_changed(story_id)
    response = client.get(f"/api/stories/{story_id}")
    assert response.status_code == 200
    assert response.json["link_books"] is link_books
    assert response.json["story"]["needs_approval"] is link_books


def test_enabling_linking_restores_the_saved_approval_preference(library):
    orchestrator.save_settings(link_books=False, hold_new_links=True)
    story_id = add_story(calibre_id=7, calibre_uuid="uuid-7", ingested_at="2026-01-01")
    orchestrator._link_changed(story_id)
    assert orchestrator.story_details(story_id)["story"]["needs_approval"] is False
    orchestrator.save_settings(link_books=True)
    assert orchestrator.get_settings()["hold_new_links"] is True
    assert orchestrator.story_details(story_id)["story"]["needs_approval"] is True
    assert "Approve link" in rebuild(story_id)
    assert not list(config.INGEST_DIR.iterdir())


def test_linking_off_exports_every_rebuild_without_an_id_or_approval():
    orchestrator.save_settings(link_books=False, hold_new_links=True)
    story_id = add_story()
    orchestrator._link_changed(story_id)
    for _ in range(2):
        assert rebuild(story_id) == "Sent to ingest folder"
    assert orchestrator.store.get_story(story_id)["ingested_at"] is not None
    assert len(list(config.INGEST_DIR.glob("*.epub"))) == 2
    assert not list(config.INGEST_DIR.glob("*.cwa.json"))
    assert orchestrator.store.get_setting(story_id, "upload_held") is None


def test_disabling_linking_releases_an_unlinked_book_without_approval(jobs, library):
    orchestrator.save_settings(hold_new_links=True)
    story_id = add_story()
    orchestrator._link_changed(story_id)
    assert "Approve as new book" in rebuild(story_id)
    orchestrator.save_settings(link_books=False)
    assert orchestrator.list_stories()[0]["approval_held"] is False
    assert orchestrator._run_rebuild(jobs.get_next()) == "Sent to ingest folder"
    assert orchestrator.store.get_setting(story_id, "upload_held") is None


@pytest.mark.parametrize("standalone", [False, True])
def test_new_story_download_skips_library_matching(monkeypatch, standalone):
    if standalone:
        monkeypatch.setattr(config, "INGEST_DIR", None)
    else:
        monkeypatch.setattr(config, "CWA_URL", "https://cwa.invalid")
        orchestrator.save_settings(link_books=False)
    site(monkeypatch, [(1, "One", "First chapter")])
    job = Job(mode=DownloadMode.NEW, url=STORY_URL)
    message = orchestrator._run_site_job(job)
    assert ("Not sent." if standalone else "Sent to ingest folder") in message
    assert len(orchestrator.store.list_chapters(job.story_id)) == 1
    assert orchestrator.store.get_story(job.story_id)["status"] == "ok"
    assert list(config.TMP_DIR.glob(f"story-{job.story_id}-*.epub"))
    orchestrator.cwa.assert_not_called()
    orchestrator._find_book.assert_not_called()


def test_site_updates_export_without_a_library_or_saved_id(monkeypatch):
    assert orchestrator.get_settings()["link_books"] is False
    site(monkeypatch, [(1, "One", "First chapter")])
    job = Job(mode=DownloadMode.NEW, url=STORY_URL)
    assert "Sent to ingest folder" in orchestrator._run_site_job(job)
    site(monkeypatch, [(1, "One", "First chapter"), (2, "Two", "Second chapter")])
    assert "Sent to ingest folder" in orchestrator._run_site_job(Job(mode=DownloadMode.NEW, story_id=job.story_id))
    assert len(orchestrator.store.list_chapters(job.story_id)) == 2
    assert len(list(config.INGEST_DIR.glob("*.epub"))) == 2
    assert not list(config.INGEST_DIR.glob("*.cwa.json"))
    orchestrator.cwa.assert_not_called()
    orchestrator._find_book.assert_not_called()


def test_saved_id_without_uuid_works_without_library_configuration():
    story_id = add_story(calibre_id=7, ingested_at="2026-01-01")
    assert rebuild(story_id) == "Updated library book 7"
    orchestrator.cwa.assert_not_called()
    orchestrator._find_book.assert_not_called()


def test_paused_unlinked_update_does_not_raise_not_found(monkeypatch):
    monkeypatch.setattr(config, "CWA_URL", "https://cwa.invalid")
    orchestrator._find_book.return_value = None
    orchestrator._find_book.side_effect = None
    orchestrator.save_settings(pause_uploads=True)
    story_id = add_story(ingested_at="2026-01-01")
    assert rebuild(story_id) == "Not sent. Turn off pause to send."
    assert orchestrator.store.get_story(story_id)["status"] == "ok"
    assert not list(config.INGEST_DIR.iterdir())


def test_enabling_linking_rebuilds_held_books_and_matches_again(monkeypatch, jobs, tmp_path):
    monkeypatch.setattr(config, "CWA_URL", "https://cwa.invalid")
    orchestrator.save_settings(link_books=False, pause_uploads=True)
    story_id = add_story()
    assert "Turn off pause" in rebuild(story_id)
    downloaded = tmp_path / "library.epub"
    downloaded.touch()
    orchestrator._find_book.side_effect = None
    orchestrator._find_book.return_value = (Book(7, "uuid-7", "Test Story"), downloaded)
    orchestrator.save_settings(link_books=True, pause_uploads=False)
    job = jobs.get_next()
    assert job.mode == DownloadMode.REBUILD
    assert job.story_id == story_id
    assert orchestrator._run_rebuild(job) == "Updated library book 7"
    assert orchestrator.store.get_story(story_id)["calibre_id"] == 7
    assert orchestrator.store.get_setting(story_id, "upload_held") is None


@pytest.mark.parametrize("link_books", [False, True])
@pytest.mark.parametrize("hold_new_links", [False, True])
@pytest.mark.parametrize("paused", [False, True])
@pytest.mark.parametrize("saved_id", [None, 7])
def test_upload_settings_matrix(client, link_books, hold_new_links, paused, saved_id, library):
    orchestrator.save_settings(link_books=link_books, hold_new_links=hold_new_links, pause_uploads=paused)
    story_id = add_story(
        calibre_id=saved_id,
        calibre_uuid="uuid-7" if saved_id else None,
        ingested_at="2026-01-01" if saved_id else None,
    )
    orchestrator._link_changed(story_id)
    assert client.get("/api/stories").json[0]["approval_held"] is False
    message = rebuild(story_id)
    pending = paused or (link_books and hold_new_links)
    assert message.startswith("Not sent.") is pending
    listed = client.get("/api/stories").json[0]
    assert listed["upload_held"] is pending
    assert listed["approval_held"] is (link_books and hold_new_links and not paused)
    assert bool(orchestrator.store.get_setting(story_id, "upload_held")) is pending
    assert bool(list(config.INGEST_DIR.iterdir())) is (not pending)


@pytest.mark.parametrize("missing_ingest", [False, True])
def test_approval_while_paused_preserves_pending_upload_until_resume(
    client, monkeypatch, jobs, missing_ingest, library
):
    ingest = config.INGEST_DIR
    orchestrator.save_settings(hold_new_links=True, pause_uploads=True)
    if missing_ingest:
        monkeypatch.setattr(config, "INGEST_DIR", None)
    story_id = add_story()
    orchestrator._link_changed(story_id)
    rebuild(story_id)
    response = client.post(f"/api/stories/{story_id}/approve", json={"uuid": None}, headers=H)
    assert response.status_code == 200
    assert response.json["job"] is None
    assert response.json["story"]["needs_approval"] is False
    assert response.json["story"]["upload_held"] is True
    assert jobs.get_next() is None
    assert client.get("/api/stories").json[0]["approval_held"] is False
    assert orchestrator.store.get_setting(story_id, "upload_held") is True
    monkeypatch.setattr(config, "INGEST_DIR", ingest)
    orchestrator.save_settings(pause_uploads=False)
    job = jobs.get_next()
    assert job.story_id == story_id
    assert orchestrator._run_rebuild(job) == "Sent to CWA"
    assert orchestrator.store.get_setting(story_id, "upload_held") is None
    assert client.get("/api/stories").json[0]["approval_held"] is False


def test_resuming_uploads_does_not_bypass_approval(client, jobs, library):
    orchestrator.save_settings(hold_new_links=True, pause_uploads=True)
    story_id = add_story(calibre_id=7, calibre_uuid="uuid-7", ingested_at="2026-01-01")
    orchestrator._link_changed(story_id)
    rebuild(story_id)
    assert client.get("/api/stories").json[0]["approval_held"] is False
    orchestrator.save_settings(pause_uploads=False)
    assert client.get("/api/stories").json[0]["approval_held"] is True
    assert "Approve link" in orchestrator._run_rebuild(jobs.get_next())
    assert orchestrator.store.get_setting(story_id, "upload_held") is True
    assert not list(config.INGEST_DIR.iterdir())


def test_missing_library_connection_is_not_an_approval_hold(client, monkeypatch):
    orchestrator.save_settings(hold_new_links=True)
    story_id = add_story(ingested_at="2026-01-01")
    orchestrator._link_changed(story_id)
    assert rebuild(story_id) == "Sent to ingest folder"
    assert client.get("/api/stories").json[0]["approval_held"] is False
    details = client.get(f"/api/stories/{story_id}").json
    assert details["story"]["upload_held"] is False
    assert details["story"]["needs_approval"] is False
    assert details["link_books"] is False
    assert details["ingest_available"] is True
    monkeypatch.setattr(config, "INGEST_DIR", None)
    assert client.get(f"/api/stories/{story_id}").json["ingest_available"] is False
    monkeypatch.setattr(config, "CWA_URL", "https://cwa.invalid")
    assert client.get(f"/api/stories/{story_id}").json["link_books"] is True


@pytest.mark.parametrize("missing_ingest", [False, True])
def test_releasing_other_holds_does_not_queue_uploads_while_paused(monkeypatch, jobs, missing_ingest, library):
    orchestrator.save_settings(link_books=False, hold_new_links=True, pause_uploads=True)
    story_id = add_story()
    rebuild(story_id)
    if missing_ingest:
        monkeypatch.setattr(config, "INGEST_DIR", None)
    orchestrator.save_settings(link_books=True, hold_new_links=False)
    assert jobs.get_next() is None
    assert orchestrator.get_settings()["pause_uploads"] is True