ytstream/tests/conftest.py

"""Test fixtures.

Every path the application uses is redirected into a tmpdir. No test touches the
network, a real yt-dlp, a real Jellyfin, or the real media tree — the YouTube API
client is always a stub (see `FakeApi`), because the point of a test suite here is
to pin down behaviour that only shows up on the failure paths: a 403, an empty
response, a video that ages out and must not come back.
"""

from __future__ import annotations

import os
import tempfile
from pathlib import Path

# config resolves its paths at import time, so the environment has to be set
# before anything from the package is imported.
_SANDBOX = Path(tempfile.mkdtemp(prefix="yts-tests-"))
os.environ.setdefault("YTS_STATE_DIR", str(_SANDBOX / "state"))
os.environ.setdefault("YTS_MEDIA_ROOT", str(_SANDBOX / "media"))
os.environ.setdefault("YTS_DB_PATH", str(_SANDBOX / "state" / "ytstream.db"))
os.environ.setdefault("YTS_LOCK_PATH", str(_SANDBOX / "state" / "run.lock"))
os.environ.setdefault("YTS_VENV_BIN", str(_SANDBOX / "venv" / "bin"))

import pytest  # noqa: E402

from ytstream import api, config, db, util, videos  # noqa: E402
from ytstream.settings import Settings  # noqa: E402

FIXTURES = Path(__file__).parent / "fixtures"

# A real-looking channel id: UC + 22 chars.
CHANNEL_ID = "UCW7jUEpYT_t0Gsf632d6_wQ"


@pytest.fixture()
def media_root(tmp_path, monkeypatch):
    """Point the media root at a per-test tmpdir."""
    root = tmp_path / "media"
    root.mkdir(parents=True)
    monkeypatch.setattr(config, "MEDIA_ROOT", root)
    return root


@pytest.fixture()
def conn(tmp_path):
    connection = db.connect(tmp_path / "ytstream.db")
    yield connection
    connection.close()


@pytest.fixture()
def settings(conn):
    settings = Settings(conn)
    # Tests that reach the API go through FakeApi, but the code refuses to call
    # out at all without a key, so give it one that is never used for real.
    settings.set("youtube_api_key", "test-key")
    return settings


@pytest.fixture()
def channel(conn):
    """One subscribed channel, returned as a row."""
    return add_channel(conn, CHANNEL_ID, "clabretro", "clabretro")


@pytest.fixture()
def no_network(monkeypatch):
    """Fail loudly if anything tries to open a socket.

    Belt and braces: a test that accidentally hits the network would pass locally
    and fail in a different week for reasons nobody could reproduce.
    """
    import urllib.request

    def forbidden(*args, **kwargs):
        raise AssertionError("test attempted a network call")

    monkeypatch.setattr(urllib.request, "urlopen", forbidden)


# --------------------------------------------------------------------- helpers


def add_channel(conn, channel_id: str, title: str, dir_name: str, **kwargs):
    fields = {"source": "youtube", "backfilled": 1, "uploads_playlist": "UULF"}
    fields.update(kwargs)
    columns = ", ".join(fields)
    marks = ", ".join("?" * len(fields))
    with conn:
        conn.execute(
            f"INSERT INTO channel (channel_id, handle, title, description, dir_name, "
            f"added_at, {columns}) VALUES (?, ?, ?, ?, ?, ?, {marks})",
            (channel_id, f"@{dir_name}", title, "A channel", dir_name,
             util.utcnow_iso(), *fields.values()),
        )
    return conn.execute(
        "SELECT * FROM channel WHERE channel_id = ?", (channel_id,)
    ).fetchone()


def add_video(conn, channel_pk, video_id, **kwargs):
    """Insert a video row with sensible defaults."""
    defaults = {
        "title": f"Video {video_id}",
        "upload_date": "2026-08-01",
        "state": videos.LISTED,
        "discovery_source": videos.SOURCE_UULF,
        "duration": 900,
    }
    defaults.update(kwargs)
    videos.insert(conn, channel_pk=channel_pk, video_id=video_id, **defaults)
    return videos.get(conn, video_id)


def feed_bytes(name: str) -> bytes:
    return (FIXTURES / name).read_bytes()


def make_feed(entries: list[dict], *, playlist_published: str = "2019-01-01T00:00:00+00:00") -> bytes:
    """Build an Atom feed shaped like YouTube's.

    Includes the feed-level <published> that is NOT an entry, because scraping
    timestamps instead of walking atom:entry picks it up and yields nonsense
    upload rates — a mistake made once while measuring.
    """
    items = "".join(
        f"""
  <entry>
    <id>yt:video:{e['video_id']}</id>
    <yt:videoId>{e['video_id']}</yt:videoId>
    <title>{e.get('title', 'Untitled')}</title>
    <published>{e['published']}</published>
  </entry>"""
        for e in entries
    )
    return f"""<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns:yt="http://www.youtube.com/xml/schemas/2015"
      xmlns:media="http://search.yahoo.com/mrss/"
      xmlns="http://www.w3.org/2005/Atom">
  <title>Videos</title>
  <published>{playlist_published}</published>{items}
</feed>""".encode()


class FakeApi:
    """Stand-in for `api.Api` with scriptable responses.

    Counts calls so tests can assert the batching actually batches — the whole
    quota argument in the plan rests on 50 ids per call, and a regression to one
    call per video would be silent and expensive.
    """

    def __init__(self, *, subs=None, uploads=None, durations=None, channel=None,
                 raises=None):
        self._subs = subs
        self._uploads = uploads or []
        self._durations = durations or {}
        self._channel = channel
        self._raises = raises
        self.calls = 0
        self.duration_calls = 0
        self.subscription_calls = 0

    def subscriptions(self, channel_id):
        self.subscription_calls += 1
        self.calls += 1
        if isinstance(self._raises, Exception):
            raise self._raises
        return list(self._subs or [])

    def uploads(self, channel_id, *, kind="UULF", since=None, limit=None,
                page_token=None):
        self.calls += 1
        produced = 0
        for entry, token in self._uploads:
            if since is not None and entry["published"] < since:
                return
            yield entry, token
            produced += 1
            if limit is not None and produced >= limit:
                return

    def details(self, video_ids):
        self.duration_calls += 1
        self.calls += 1
        return {vid: self._durations[vid] for vid in video_ids
                if vid in self._durations}

    # `durations` was the old name; kept so a stale caller fails loudly in tests
    # rather than silently skipping enrichment.
    durations = details

    def channel(self, channel_id):
        self.calls += 1
        return self._channel

    def resolve_handle(self, handle):
        self.calls += 1
        return self._channel


def patch_api(monkeypatch, module, fake: FakeApi):
    """Make `module.api.Api(...)` return `fake` regardless of arguments."""
    monkeypatch.setattr(module.api, "Api", lambda *a, **kw: fake)
    return fake