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 - Removed obsolete *_edge_cases test files superseded by structured tests.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.
118 lines
3.5 KiB
Python
118 lines
3.5 KiB
Python
"""SubtitlePlacer — hard-links matched subtitle tracks next to the destination video."""
|
|
|
|
import logging
|
|
import os
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
from ..entities import SubtitleCandidate
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def _build_dest_name(track: SubtitleCandidate, video_stem: str) -> str:
|
|
"""
|
|
Build the destination filename for a subtitle track.
|
|
|
|
Format: {video_stem}.{lang}.{ext}
|
|
{video_stem}.{lang}.sdh.{ext}
|
|
{video_stem}.{lang}.forced.{ext}
|
|
"""
|
|
from ..value_objects import SubtitleType
|
|
|
|
if not track.language or not track.format:
|
|
raise ValueError("Cannot compute destination name: language or format missing")
|
|
|
|
ext = track.format.extensions[0].lstrip(".")
|
|
parts = [video_stem, track.language.code]
|
|
if track.subtitle_type == SubtitleType.SDH:
|
|
parts.append("sdh")
|
|
elif track.subtitle_type == SubtitleType.FORCED:
|
|
parts.append("forced")
|
|
return ".".join(parts) + "." + ext
|
|
|
|
|
|
@dataclass
|
|
class PlacedTrack:
|
|
source: Path
|
|
destination: Path
|
|
filename: str
|
|
|
|
|
|
@dataclass
|
|
class PlaceResult:
|
|
placed: list[PlacedTrack]
|
|
skipped: list[tuple[SubtitleCandidate, str]] # (track, reason)
|
|
|
|
@property
|
|
def placed_count(self) -> int:
|
|
return len(self.placed)
|
|
|
|
@property
|
|
def skipped_count(self) -> int:
|
|
return len(self.skipped)
|
|
|
|
|
|
class SubtitlePlacer:
|
|
"""
|
|
Hard-links matched SubtitleCandidate files next to a destination video.
|
|
|
|
Uses the same hard-link strategy as FileManager.copy_file:
|
|
instant, no data duplication, qBittorrent keeps seeding.
|
|
|
|
Embedded tracks are skipped — nothing to place on disk.
|
|
"""
|
|
|
|
def place(
|
|
self,
|
|
tracks: list[SubtitleCandidate],
|
|
destination_video: Path,
|
|
) -> PlaceResult:
|
|
placed: list[PlacedTrack] = []
|
|
skipped: list[tuple[SubtitleCandidate, str]] = []
|
|
|
|
dest_dir = destination_video.parent
|
|
|
|
for track in tracks:
|
|
if track.is_embedded:
|
|
logger.debug(f"SubtitlePlacer: skip embedded track ({track.language})")
|
|
skipped.append((track, "embedded — no file to place"))
|
|
continue
|
|
|
|
if not track.file_path or not track.file_path.exists():
|
|
skipped.append((track, "source file not found"))
|
|
continue
|
|
|
|
try:
|
|
dest_name = _build_dest_name(track, destination_video.stem)
|
|
except ValueError as e:
|
|
skipped.append((track, str(e)))
|
|
continue
|
|
|
|
dest_path = dest_dir / dest_name
|
|
|
|
if dest_path.exists():
|
|
logger.debug(f"SubtitlePlacer: skip {dest_name} — already exists")
|
|
skipped.append((track, "destination already exists"))
|
|
continue
|
|
|
|
try:
|
|
os.link(track.file_path, dest_path)
|
|
placed.append(
|
|
PlacedTrack(
|
|
source=track.file_path,
|
|
destination=dest_path,
|
|
filename=dest_name,
|
|
)
|
|
)
|
|
logger.info(f"SubtitlePlacer: placed {dest_name}")
|
|
except OSError as e:
|
|
logger.warning(f"SubtitlePlacer: failed to place {dest_name}: {e}")
|
|
skipped.append((track, str(e)))
|
|
|
|
logger.info(
|
|
f"SubtitlePlacer: {len(placed)} placed, {len(skipped)} skipped "
|
|
f"for {destination_video.name}"
|
|
)
|
|
return PlaceResult(placed=placed, skipped=skipped)
|