chore: sprint cleanup — language unification, parser unification, fossils removal
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 - Removed obsolete *_edge_cases test files superseded by structured tests.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.
This commit is contained in:
@@ -0,0 +1,217 @@
|
||||
"""Tests for ``alfred.application.filesystem.enrich_from_probe``.
|
||||
|
||||
The function mutates a ``ParsedRelease`` in place using ffprobe ``MediaInfo``.
|
||||
Token-level values from the release name always win — only ``None`` fields
|
||||
are filled.
|
||||
|
||||
Coverage:
|
||||
|
||||
- ``TestQuality`` — resolution fill-in (and no-overwrite).
|
||||
- ``TestVideoCodec`` — codec map (hevc→x265, …) + uppercase fallback.
|
||||
- ``TestAudio`` — default track preferred over first; codec & channel maps
|
||||
with unknown-value fallbacks.
|
||||
- ``TestLanguages`` — append-only merge; ``und`` skipped; case-insensitive
|
||||
duplicate suppression.
|
||||
|
||||
Uses real ``ParsedRelease`` / ``MediaInfo`` instances — no mocking needed.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from alfred.application.filesystem.enrich_from_probe import enrich_from_probe
|
||||
from alfred.domain.release.value_objects import ParsedRelease
|
||||
from alfred.domain.shared.media import AudioTrack, MediaInfo, VideoTrack
|
||||
|
||||
|
||||
def _info_with_video(*, width=None, height=None, codec=None, **rest) -> MediaInfo:
|
||||
"""Helper: build a MediaInfo with a single video track (the common case)."""
|
||||
return MediaInfo(
|
||||
video_tracks=[VideoTrack(index=0, codec=codec, width=width, height=height)],
|
||||
**rest,
|
||||
)
|
||||
|
||||
|
||||
def _bare(**overrides) -> ParsedRelease:
|
||||
"""Build a minimal ParsedRelease with all enrichable fields = None."""
|
||||
defaults = dict(
|
||||
raw="X",
|
||||
normalised="X",
|
||||
title="X",
|
||||
year=None,
|
||||
season=None,
|
||||
episode=None,
|
||||
episode_end=None,
|
||||
quality=None,
|
||||
source=None,
|
||||
codec=None,
|
||||
group="UNKNOWN",
|
||||
tech_string="",
|
||||
)
|
||||
defaults.update(overrides)
|
||||
return ParsedRelease(**defaults)
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Quality / resolution #
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class TestQuality:
|
||||
def test_fills_when_none(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, _info_with_video(width=1920, height=1080))
|
||||
assert p.quality == "1080p"
|
||||
|
||||
def test_does_not_overwrite_existing(self):
|
||||
p = _bare(quality="2160p")
|
||||
enrich_from_probe(p, _info_with_video(width=1920, height=1080))
|
||||
assert p.quality == "2160p"
|
||||
|
||||
def test_no_dims_leaves_none(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, MediaInfo())
|
||||
assert p.quality is None
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Video codec #
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class TestVideoCodec:
|
||||
def test_hevc_to_x265(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, _info_with_video(codec="hevc"))
|
||||
assert p.codec == "x265"
|
||||
|
||||
def test_h264_to_x264(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, _info_with_video(codec="h264"))
|
||||
assert p.codec == "x264"
|
||||
|
||||
def test_unknown_codec_uppercased(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, _info_with_video(codec="weird"))
|
||||
assert p.codec == "WEIRD"
|
||||
|
||||
def test_does_not_overwrite_existing(self):
|
||||
p = _bare(codec="HEVC")
|
||||
enrich_from_probe(p, _info_with_video(codec="h264"))
|
||||
assert p.codec == "HEVC"
|
||||
|
||||
def test_no_codec_leaves_none(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, MediaInfo())
|
||||
assert p.codec is None
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Audio #
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class TestAudio:
|
||||
def test_uses_default_track(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[
|
||||
AudioTrack(0, "aac", 2, "stereo", "eng", is_default=False),
|
||||
AudioTrack(1, "eac3", 6, "5.1", "eng", is_default=True),
|
||||
]
|
||||
)
|
||||
p = _bare()
|
||||
enrich_from_probe(p, info)
|
||||
assert p.audio_codec == "EAC3"
|
||||
assert p.audio_channels == "5.1"
|
||||
|
||||
def test_falls_back_to_first_track_when_no_default(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[
|
||||
AudioTrack(0, "ac3", 6, "5.1", "eng"),
|
||||
AudioTrack(1, "aac", 2, "stereo", "fre"),
|
||||
]
|
||||
)
|
||||
p = _bare()
|
||||
enrich_from_probe(p, info)
|
||||
assert p.audio_codec == "AC3"
|
||||
assert p.audio_channels == "5.1"
|
||||
|
||||
def test_channel_count_unknown_falls_back(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[AudioTrack(0, "aac", 4, "quad", "eng")]
|
||||
)
|
||||
p = _bare()
|
||||
enrich_from_probe(p, info)
|
||||
assert p.audio_channels == "4ch"
|
||||
|
||||
def test_unknown_audio_codec_uppercased(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[AudioTrack(0, "newcodec", 2, "stereo", "eng")]
|
||||
)
|
||||
p = _bare()
|
||||
enrich_from_probe(p, info)
|
||||
assert p.audio_codec == "NEWCODEC"
|
||||
|
||||
def test_no_audio_tracks(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, MediaInfo())
|
||||
assert p.audio_codec is None
|
||||
assert p.audio_channels is None
|
||||
|
||||
def test_does_not_overwrite_existing_audio_fields(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[AudioTrack(0, "ac3", 6, "5.1", "eng")]
|
||||
)
|
||||
p = _bare(audio_codec="DTS-HD.MA", audio_channels="7.1")
|
||||
enrich_from_probe(p, info)
|
||||
assert p.audio_codec == "DTS-HD.MA"
|
||||
assert p.audio_channels == "7.1"
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Languages #
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
|
||||
class TestLanguages:
|
||||
def test_appends_new(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[
|
||||
AudioTrack(0, "aac", 2, "stereo", "eng"),
|
||||
AudioTrack(1, "aac", 2, "stereo", "fre"),
|
||||
]
|
||||
)
|
||||
p = _bare()
|
||||
enrich_from_probe(p, info)
|
||||
assert p.languages == ["eng", "fre"]
|
||||
|
||||
def test_skips_und(self):
|
||||
info = MediaInfo(
|
||||
audio_tracks=[
|
||||
AudioTrack(0, "aac", 2, "stereo", "und"),
|
||||
AudioTrack(1, "aac", 2, "stereo", "eng"),
|
||||
]
|
||||
)
|
||||
p = _bare()
|
||||
enrich_from_probe(p, info)
|
||||
assert p.languages == ["eng"]
|
||||
|
||||
def test_dedup_against_existing_case_insensitive(self):
|
||||
# existing token-level languages are typically upper-case ("FRENCH", "ENG")
|
||||
# The current logic compares track.lang.upper() against existing —
|
||||
# so a track with "eng" is suppressed if "ENG" is already in languages.
|
||||
info = MediaInfo(
|
||||
audio_tracks=[
|
||||
AudioTrack(0, "aac", 2, "stereo", "eng"),
|
||||
AudioTrack(1, "aac", 2, "stereo", "fre"),
|
||||
]
|
||||
)
|
||||
p = _bare()
|
||||
p.languages = ["ENG"]
|
||||
enrich_from_probe(p, info)
|
||||
# "eng" → upper "ENG" already present → skipped. "fre" → "FRE" new → kept.
|
||||
assert p.languages == ["ENG", "fre"]
|
||||
|
||||
def test_no_audio_tracks_leaves_languages_empty(self):
|
||||
p = _bare()
|
||||
enrich_from_probe(p, MediaInfo())
|
||||
assert p.languages == []
|
||||
Reference in New Issue
Block a user