e07c9ec77b
Several weeks of work accumulated without being committed. Grouped here for clarity; see CHANGELOG.md [Unreleased] for the user-facing summary. Highlights ---------- P1 #2 — ISO 639-2/B canonical migration - New Language VO + LanguageRegistry (alfred/domain/shared/knowledge/). - iso_languages.yaml as single source of truth for language codes. - SubtitleKnowledgeBase now delegates lookup to LanguageRegistry; subtitles.yaml only declares subtitle-specific tokens (vostfr, vf, vff, …). - SubtitlePreferences default → ["fre", "eng"]; subtitle filenames written as {iso639_2b}.srt (legacy fr.srt still read via alias). - Scanner: dropped _LANG_KEYWORDS / _SDH_TOKENS / _FORCED_TOKENS / SUBTITLE_EXTENSIONS hardcoded dicts. - Fixed: 'hi' token no longer marks SDH (conflicted with Hindi alias). - Added settings.min_movie_size_bytes (was a module constant). P1 #3 — Release parser unification + data-driven tokenizer - parse_release() is now the single source of truth for release-name parsing. - alfred/knowledge/release/separators.yaml declares the token separators used by the tokenizer (., space, [, ], (, ), _). New conventions can be added without code changes. - Tokenizer now splits on any configured separator instead of name.split('.'). Releases like 'The Father (2020) [1080p] [WEBRip] [5.1] [YTS.MX]' parse via the direct path without sanitization fallback. - Site-tag extraction always runs first; well-formedness only rejects truly forbidden chars. - _parse_season_episode() extended with NxNN / NxNNxNN alt forms. - Removed dead helpers: _sanitize, _normalize. Domain cleanup - Deleted fossil services with zero production callers: alfred/domain/movies/services.py alfred/domain/tv_shows/services.py alfred/domain/subtitles/services.py (replaced by subtitles/services/ package) alfred/domain/subtitles/repositories.py - Split monolithic subtitle services into a package (identifier, matcher, placer, pattern_detector, utils) + dedicated knowledge/ package. - MediaInfo split into dedicated package (alfred/domain/shared/media/: audio, video, subtitle, info, matching). Persistence cleanup - Removed dead JSON repositories (movie/subtitle/tvshow_repository.py). Tests - Major expansion of the test suite organized to mirror the source tree. - Removed obsolete *_edge_cases test files superseded by structured tests. - Suite: 990 passed, 8 skipped. Misc - .gitignore: exclude env_backup/ and *.bak. - Adjustments across agent/llm, app.py, application/filesystem, and infrastructure/filesystem to align with the new domain layout.
222 lines
7.6 KiB
Python
222 lines
7.6 KiB
Python
"""Tests for ``alfred.domain.subtitles.services.placer.SubtitlePlacer``.
|
|
|
|
The placer hard-links subtitle files next to a destination video, naming
|
|
them ``{video_stem}.{lang}[.sdh|.forced].{ext}``.
|
|
|
|
Coverage:
|
|
|
|
- ``TestBuildDestName`` — name construction for standard / SDH / forced;
|
|
errors on missing language or format.
|
|
- ``TestPlace`` — happy path: link is created, ``PlacedTrack`` populated.
|
|
- ``TestSkipReasons`` — embedded, missing source, missing language/format,
|
|
destination already exists.
|
|
- ``TestOSError`` — ``os.link`` failures are captured as ``skipped``.
|
|
- ``TestPlaceResultCounts`` — ``placed_count`` / ``skipped_count`` properties.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from alfred.domain.subtitles.entities import SubtitleCandidate
|
|
from alfred.domain.subtitles.services.placer import (
|
|
PlacedTrack,
|
|
PlaceResult,
|
|
SubtitlePlacer,
|
|
_build_dest_name,
|
|
)
|
|
from alfred.domain.subtitles.value_objects import (
|
|
SubtitleFormat,
|
|
SubtitleLanguage,
|
|
SubtitleType,
|
|
)
|
|
|
|
SRT = SubtitleFormat(id="srt", extensions=[".srt"])
|
|
ASS = SubtitleFormat(id="ass", extensions=[".ass", ".ssa"])
|
|
FRA = SubtitleLanguage(code="fra", tokens=["fr"])
|
|
|
|
|
|
def _track(
|
|
file_path: Path | None,
|
|
*,
|
|
lang=FRA,
|
|
fmt=SRT,
|
|
stype=SubtitleType.STANDARD,
|
|
is_embedded: bool = False,
|
|
) -> SubtitleCandidate:
|
|
return SubtitleCandidate(
|
|
language=lang,
|
|
format=fmt,
|
|
subtitle_type=stype,
|
|
file_path=file_path,
|
|
is_embedded=is_embedded,
|
|
)
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# _build_dest_name #
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
class TestBuildDestName:
|
|
def test_standard(self):
|
|
t = _track(None, stype=SubtitleType.STANDARD)
|
|
assert _build_dest_name(t, "Movie.2010") == "Movie.2010.fra.srt"
|
|
|
|
def test_sdh(self):
|
|
t = _track(None, stype=SubtitleType.SDH)
|
|
assert _build_dest_name(t, "Movie.2010") == "Movie.2010.fra.sdh.srt"
|
|
|
|
def test_forced(self):
|
|
t = _track(None, stype=SubtitleType.FORCED)
|
|
assert _build_dest_name(t, "Movie.2010") == "Movie.2010.fra.forced.srt"
|
|
|
|
def test_uses_first_extension_of_multi_ext_format(self):
|
|
t = _track(None, fmt=ASS)
|
|
# ASS has [.ass, .ssa] — first wins.
|
|
assert _build_dest_name(t, "x").endswith(".ass")
|
|
|
|
def test_missing_lang_raises(self):
|
|
t = _track(None, lang=None)
|
|
with pytest.raises(ValueError, match="language or format"):
|
|
_build_dest_name(t, "x")
|
|
|
|
def test_missing_format_raises(self):
|
|
t = _track(None, fmt=None)
|
|
with pytest.raises(ValueError, match="language or format"):
|
|
_build_dest_name(t, "x")
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# Place — happy path #
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
@pytest.fixture
|
|
def placer():
|
|
return SubtitlePlacer()
|
|
|
|
|
|
class TestPlace:
|
|
def test_creates_hard_link_with_correct_name(self, placer, tmp_path):
|
|
src = tmp_path / "input.srt"
|
|
src.write_text("subs")
|
|
video = tmp_path / "lib" / "Movie.2010.mkv"
|
|
video.parent.mkdir()
|
|
video.write_bytes(b"")
|
|
|
|
track = _track(src)
|
|
result = placer.place([track], video)
|
|
|
|
assert result.placed_count == 1
|
|
assert result.skipped_count == 0
|
|
placed = result.placed[0]
|
|
assert placed.filename == "Movie.2010.fra.srt"
|
|
assert placed.destination.exists()
|
|
# Hard link → same inode as source.
|
|
assert placed.destination.stat().st_ino == src.stat().st_ino
|
|
|
|
def test_multiple_tracks_distinct_destinations(self, placer, tmp_path):
|
|
s1 = tmp_path / "a.srt"
|
|
s1.write_text("")
|
|
s2 = tmp_path / "b.srt"
|
|
s2.write_text("")
|
|
video = tmp_path / "lib" / "Movie.mkv"
|
|
video.parent.mkdir()
|
|
video.write_bytes(b"")
|
|
|
|
ENG = SubtitleLanguage(code="eng", tokens=["en"])
|
|
t1 = _track(s1, lang=FRA)
|
|
t2 = _track(s2, lang=ENG, stype=SubtitleType.SDH)
|
|
result = placer.place([t1, t2], video)
|
|
assert result.placed_count == 2
|
|
names = {p.filename for p in result.placed}
|
|
assert names == {"Movie.fra.srt", "Movie.eng.sdh.srt"}
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# Skip reasons #
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
class TestSkipReasons:
|
|
def test_embedded_skipped(self, placer, tmp_path):
|
|
video = tmp_path / "Movie.mkv"
|
|
video.write_bytes(b"")
|
|
track = _track(None, is_embedded=True)
|
|
result = placer.place([track], video)
|
|
assert result.placed == []
|
|
assert len(result.skipped) == 1
|
|
assert "embedded" in result.skipped[0][1]
|
|
|
|
def test_missing_source_file(self, placer, tmp_path):
|
|
video = tmp_path / "Movie.mkv"
|
|
video.write_bytes(b"")
|
|
track = _track(tmp_path / "ghost.srt")
|
|
result = placer.place([track], video)
|
|
assert result.placed == []
|
|
assert "not found" in result.skipped[0][1]
|
|
|
|
def test_missing_lang_or_format_skipped(self, placer, tmp_path):
|
|
video = tmp_path / "Movie.mkv"
|
|
video.write_bytes(b"")
|
|
src = tmp_path / "x.srt"
|
|
src.write_text("")
|
|
track = _track(src, lang=None)
|
|
result = placer.place([track], video)
|
|
assert result.placed == []
|
|
assert "language or format" in result.skipped[0][1]
|
|
|
|
def test_destination_already_exists(self, placer, tmp_path):
|
|
src = tmp_path / "x.srt"
|
|
src.write_text("a")
|
|
video = tmp_path / "lib" / "Movie.mkv"
|
|
video.parent.mkdir()
|
|
video.write_bytes(b"")
|
|
# Pre-create destination
|
|
(video.parent / "Movie.fra.srt").write_text("preexisting")
|
|
track = _track(src)
|
|
result = placer.place([track], video)
|
|
assert result.placed == []
|
|
assert "already exists" in result.skipped[0][1]
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# OSError handling #
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
class TestOSError:
|
|
def test_link_failure_captured_as_skipped(self, placer, tmp_path):
|
|
src = tmp_path / "x.srt"
|
|
src.write_text("")
|
|
video = tmp_path / "lib" / "Movie.mkv"
|
|
video.parent.mkdir()
|
|
video.write_bytes(b"")
|
|
track = _track(src)
|
|
with patch(
|
|
"alfred.domain.subtitles.services.placer.os.link",
|
|
side_effect=OSError("cross-device link"),
|
|
):
|
|
result = placer.place([track], video)
|
|
assert result.placed == []
|
|
assert "cross-device" in result.skipped[0][1]
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# PlaceResult counters #
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
class TestPlaceResultCounts:
|
|
def test_counts(self):
|
|
# Synthesize a PlaceResult directly for property check.
|
|
pt = PlacedTrack(source=Path("/a"), destination=Path("/b"), filename="b")
|
|
st = _track(None, is_embedded=True)
|
|
r = PlaceResult(placed=[pt], skipped=[(st, "x")])
|
|
assert r.placed_count == 1
|
|
assert r.skipped_count == 1
|