siftlode/backend/tests/test_download_output.py

"""Picking the file yt-dlp actually produced, for sources that aren't YouTube.

The regression these cover: `Path(info["filepath"] or "")` is `Path(".")`, which PASSES `.exists()`,
so a missing filepath (an arbitrary-URL extractor) skipped the staging fallback and crashed later
with "PosixPath('.') has an empty name" instead of downloading."""

import pytest

from app.downloads.edit import _concat_quote, run_ffprobe_json
from app.downloads.pipeline import _media_info, _produced_file
from pathlib import Path, PurePosixPath


def _staging(tmp_path: Path, *names: str) -> Path:
    for n in names:
        p = tmp_path / n
        p.write_bytes(b"x" * (10 * (names.index(n) + 1)))
    return tmp_path


class TestProducedFile:
    def test_uses_the_reported_filepath(self, tmp_path):
        staging = _staging(tmp_path, "v.mp4", "v.jpg")
        info = {"requested_downloads": [{"filepath": str(tmp_path / "v.mp4")}]}
        assert _produced_file(info, staging) == tmp_path / "v.mp4"

    @pytest.mark.parametrize(
        "info", [{}, {"requested_downloads": [{}]}, {"requested_downloads": [{"filepath": ""}]}]
    )
    def test_missing_filepath_falls_back_to_staging(self, tmp_path, info):
        staging = _staging(tmp_path, "thumb.jpg", "clip.mp4")
        assert _produced_file(info, staging) == tmp_path / "clip.mp4"

    def test_stale_filepath_falls_back_to_staging(self, tmp_path):
        staging = _staging(tmp_path, "clip.mp4")
        info = {"requested_downloads": [{"filepath": str(tmp_path / "gone.mp4")}]}
        assert _produced_file(info, staging) == tmp_path / "clip.mp4"

    def test_picks_the_largest_media_file_ignoring_thumbs_and_partials(self, tmp_path):
        staging = _staging(tmp_path, "small.mp4", "big.mp4", "cover.webp")
        (tmp_path / "huge.mp4.part").write_bytes(b"x" * 999)
        assert _produced_file({}, staging) == tmp_path / "big.mp4"

    @pytest.mark.parametrize(
        "leftover",
        ["vid.f137.mp4", "vid.mp4.part-Frag12", "vid.ytdl", "vid.temp.mp4", "vid.mp4.part"],
    )
    def test_ytdlp_working_files_never_win(self, tmp_path, leftover):
        # Each of these can legitimately be the BIGGEST file in staging (a video-only per-format
        # stream especially) — storing one would serve a silent or truncated "download".
        (tmp_path / leftover).write_bytes(b"x" * 5000)
        (tmp_path / "vid.mp4").write_bytes(b"x" * 10)
        assert _produced_file({}, tmp_path) == tmp_path / "vid.mp4"

    def test_only_leftovers_is_treated_as_no_output(self, tmp_path):
        (tmp_path / "vid.f251.webm").write_bytes(b"x" * 5000)
        with pytest.raises(RuntimeError):
            _produced_file({}, tmp_path)

    def test_no_output_at_all_raises(self, tmp_path):
        staging = _staging(tmp_path, "only.jpg")
        with pytest.raises(RuntimeError):
            _produced_file({}, staging)


class TestMediaInfo:
    def test_playlist_wrapper_unwraps_to_the_entry_that_downloaded(self):
        info = {
            "id": "page",
            "title": "Article",
            "entries": [{"id": "vid", "requested_downloads": [{"filepath": "/x.mp4"}]}],
        }
        assert _media_info(info)["id"] == "vid"

    def test_plain_result_is_untouched(self):
        info = {"id": "vid", "requested_downloads": [{"filepath": "/x.mp4"}]}
        assert _media_info(info) is info

    def test_picks_the_entry_that_actually_downloaded(self):
        # A page whose first entry was skipped: taking entries[0] would label the produced file
        # with the teaser's id/title.
        info = {
            "id": "page",
            "entries": [
                {"id": "teaser", "title": "Teaser"},
                {"id": "main", "title": "Main", "requested_downloads": [{"filepath": "/x.mp4"}]},
            ],
        }
        assert _media_info(info)["id"] == "main"

    def test_falls_back_to_the_first_entry_when_none_downloaded(self):
        info = {"id": "page", "entries": [{"id": "a"}, {"id": "b"}]}
        assert _media_info(info)["id"] == "a"

    def test_wrapper_that_downloaded_itself_wins_over_its_entries(self):
        info = {
            "id": "vid",
            "requested_downloads": [{"filepath": "/x.mp4"}],
            "entries": [{"id": "other"}],
        }
        assert _media_info(info)["id"] == "vid"

    def test_empty_entries_are_ignored(self):
        info = {"id": "vid", "entries": [None]}
        assert _media_info(info)["id"] == "vid"


class TestRunFfprobeJson:
    """The single ffprobe-JSON invocation point (`probe.probe_json`, which the stored facts and the
    phone-safe rule both read). A failed
    probe or unparseable output must degrade to None, not raise — the malformed-input safety the old
    parse_probe_streams string parser used to own now lives here."""

    def test_unparseable_output_returns_none(self, monkeypatch):
        import subprocess

        class _R:
            stdout = "not json"

        monkeypatch.setattr(subprocess, "run", lambda *a, **k: _R())
        assert run_ffprobe_json(Path("x")) is None

    def test_ffprobe_failure_returns_none(self, monkeypatch):
        import subprocess

        def _boom(*a, **k):
            raise subprocess.CalledProcessError(1, "ffprobe")

        monkeypatch.setattr(subprocess, "run", _boom)
        assert run_ffprobe_json(Path("x")) is None

    def test_parses_streams_from_valid_json(self, monkeypatch):
        import subprocess

        class _R:
            stdout = '{"streams":[{"codec_name":"h264","codec_type":"video"}]}'

        monkeypatch.setattr(subprocess, "run", lambda *a, **k: _R())
        data = run_ffprobe_json(Path("x"), entries="stream=codec_type,codec_name")
        assert data["streams"] == [{"codec_name": "h264", "codec_type": "video"}]


class TestConcatQuote:
    # PurePosixPath so the escaping is asserted identically on a Windows dev box and in the
    # Linux test container (a WindowsPath would eat the backslash as a separator).
    def test_apostrophe_is_closed_escaped_and_reopened(self):
        # A pre-0.51.0 file can still be named with an apostrophe; unescaped it breaks the list.
        assert _concat_quote(PurePosixPath("/m/Don't_Look.mp4")) == "/m/Don'\\''t_Look.mp4"

    def test_backslash_stays_literal(self):
        # Inside single quotes ffmpeg treats `\` literally — doubling it would point at a
        # different (non-existent) path.
        assert _concat_quote(PurePosixPath("/m/a\\b.mp4")) == "/m/a\\b.mp4"

    def test_ordinary_path_is_unchanged(self):
        assert _concat_quote(PurePosixPath("/m/clip.mp4")) == "/m/clip.mp4"