From a9ae9c9a440084565fd5d9d72979f6a81002ebdf Mon Sep 17 00:00:00 2001 From: Lucas Media Date: Sun, 1 Nov 2026 10:49:22 +0100 Subject: [PATCH] chore(aidiobook_library): pyright formatter and value definition fixes --- .../metadata_audiobooks_library.py | 156 +++++++++++------- 1 file changed, 100 insertions(+), 56 deletions(-) diff --git a/audiobook_metadata/metadata_audiobooks_library.py b/audiobook_metadata/metadata_audiobooks_library.py index 14042f6..50e3452 100755 --- a/audiobook_metadata/metadata_audiobooks_library.py +++ b/audiobook_metadata/metadata_audiobooks_library.py @@ -4,29 +4,39 @@ import argparse import json import logging import re +import sqlite3 import subprocess import sys import tempfile -import sqlite3 from collections import defaultdict from concurrent.futures import ThreadPoolExecutor, as_completed -from serverlibrary import CustomLogger, setup_logging, score_match_jaccard, words, AUDIO_SUFFIXES, red_tag, blue_tag, \ - green_tag, AUDIO_RE_SUFFIXES from pathlib import Path -from mutagen.oggopus import OggOpus -from mutagen.mp4 import MP4Tags -from mutagen.mp4 import MP4 + from mutagen import File from mutagen.id3 import ( - ID3, COMM, - TIT2, + ID3, TALB, + TCOM, + TCON, + TIT1, + TIT2, TPE1, TPE2, - TCON, - TCOM, - TIT1, +) +from mutagen.mp4 import MP4, MP4Tags +from mutagen.oggopus import OggOpus + +from serverlibrary import ( + AUDIO_RE_SUFFIXES, + AUDIO_SUFFIXES, + CustomLogger, + blue_tag, + green_tag, + red_tag, + score_match_jaccard, + setup_logging, + words, ) ID3_FRAME_CLASSES = { @@ -81,9 +91,11 @@ series_patterns = [ rf"^(.+?){SEP}(?:Book|Band|Volume)\s+(\d+)(?:{SEP}(.+))$", ] + def ffmpeg_escape(path: Path) -> str: return str(path.resolve()).replace("'", r"'\''") + def clean_genre(genre): if not genre: return "" @@ -131,6 +143,7 @@ def clean_genre(genre): logger.debug(f"Update genre from {genre_old} to {genre}") return genre + def ffmetadata_escape(value: str) -> str: return ( value.replace("\\", "\\\\") @@ -140,6 +153,7 @@ def ffmetadata_escape(value: str) -> str: .replace("\n", "\\\n") ) + def get_chapters(media: Path) -> list[dict]: result = subprocess.run( [ @@ -159,7 +173,8 @@ def get_chapters(media: Path) -> list[dict]: data = json.loads(result.stdout) return data.get("chapters", []) -def _to_str(value): + +def _to_str(value) -> str: if value is None: return "" @@ -183,7 +198,6 @@ def get_metadata_all(file: Path) -> dict[str, str]: # MP4/M4A/M4B if isinstance(audio.tags, MP4Tags): - type = "mp4" for field, tag in MP4_MAP.items(): value = audio.tags.get(tag) if value: @@ -191,7 +205,6 @@ def get_metadata_all(file: Path) -> dict[str, str]: # ID3 (MP3 or mislabeled .m4b) elif isinstance(audio.tags, ID3): - type = "id3" for field, frame_id in ID3_MAP.items(): frame = audio.tags.get(frame_id) if frame: @@ -207,7 +220,6 @@ def get_metadata_all(file: Path) -> dict[str, str]: # FLAC / Opus / Vorbis else: - type="other" for field in metadata_fields: value = audio.tags.get(field) if value: @@ -218,6 +230,7 @@ def get_metadata_all(file: Path) -> dict[str, str]: return metadata + def write_metadata(file, fields, values, dry_run=False): changes = { field.lower().replace(" ", ""): str(value) @@ -296,8 +309,9 @@ def write_metadata(file, fields, values, dry_run=False): else: logger.warning(f"Unsupported file type: {file}") - except Exception as e: - logger.exception(f"Error writing metadata for {file}: {e}") + except Exception: + logger.exception(f"Error writing metadata for {file}") + def get_duration_ms(media: Path) -> int: duration = subprocess.check_output( @@ -316,6 +330,7 @@ def get_duration_ms(media: Path) -> int: return int(float(duration) * 1000) + def normalize_name(name: str, series: str) -> str: # Remove anything in (), [], {} name_out = "" @@ -350,6 +365,7 @@ def normalize_name(name: str, series: str) -> str: return name_out1 return name_out + def cleanup(text: str) -> str: # Collapse repeated punctuation groups like ", ,", ". .", "! !", "? ?" while True: @@ -363,12 +379,16 @@ def cleanup(text: str) -> str: return text.strip() + def get_empty_keys(data: dict) -> str: empty_keys = [str(key) for key, value in data.items() if not value] return f"Empty: {', '.join(empty_keys)}" if empty_keys else "" -def get_codec_bitrate(file: Path) -> tuple[str, str]: + +def get_codec_bitrate(file: Path | None) -> tuple[str, str]: + if not file: + raise ValueError info = json.loads( subprocess.check_output( [ @@ -393,32 +413,37 @@ def get_codec_bitrate(file: Path) -> tuple[str, str]: bitrate_k = f"{bitrate // 1000}k" return stream["codec_name"].lower(), bitrate_k # codec, bits/s + class Audiobook: def __init__(self, book_path: Path, library_root_path: Path) -> None: - self.title: str | list = "" - self.metadata_original = None - self.series_num = None - self.pdf_file = None - self.description = None - self.epub_file = None - self.files_extra = [] self.action_required = False - self.series_and_num = "" - self.series = "" - self.singleFile = False - self.fileConunt = 0 - self.size = 0 - self.firstFile = None self.changed = None + # Metadata self.metadata = {} + self.metadata_original = {} self.artist = "" self.genre = "" self.composer = "" self.name = "" self.comment = "" + self.description = "" + self.series_and_num = "" + self.series = "" + self.series_num = "" + self.title: str = "" + self.title_list: list = [] + # File Paths self.files: list[Path] = [] + self.files_extra = [] self.bookPath = book_path self.library_root_path = library_root_path + self.firstFile: Path | None = None + self.pdf_file = None + self.epub_file = None + # Files + self.singleFile = False + self.fileConunt = 0 + self.size = 0 def init_book(self) -> None: self.files = sorted( @@ -478,8 +503,10 @@ class Audiobook: self.series, self.series_num = self.metadata["grouping"].rsplit("#", 1) self.series = self.series.strip() self.series_and_num = self.metadata["grouping"] - artist = self.metadata.get("artist", "").strip() - self.artist = artist or self.metadata.get("albumartist") + if self.metadata.get("artist"): + self.artist = self.metadata["artist"].strip() + elif self.metadata.get("albumartist"): + self.artist = self.metadata.get("albumartist") self.description = self.metadata["description"] def write_metadata_from_fields(self): @@ -490,8 +517,9 @@ class Audiobook: self.metadata["grouping"] = self.series_and_num self.metadata["comment"] = self.comment self.metadata["description"] = self.description - self.metadata["artist"] = self.artist - self.metadata["albumartist"] = self.artist + if self.artist: + self.metadata["artist"] = self.artist + self.metadata["albumartist"] = self.artist def extract_track_number(self, file: Path) -> int: stem = file.stem @@ -512,7 +540,7 @@ class Audiobook: # CD1-01, CD 1 - 01, CD1 - 01. r"CD\s*(\d+)\s*-\s*(\d{1,3})", # 018-01, 018 - 01, 138-01, 0001-0999 - r"^(\d+)\s*-\s*(\d+)(?:\D|$)" + r"^(\d+)\s*-\s*(\d+)(?:\D|$)", # Track 01 r"Track\s+(\d+)$", # 01 - Kapitel 01 @@ -569,6 +597,9 @@ class Audiobook: logger.debug(f"Artist not visible in folder structure: {rel_path}") def fix_artist_from_comment(self): + if not isinstance(self.comment, str): + logger.trace(f"No comment for {self.name}") + return m = re.search( r"(?:" r"author(?:s)?:?|" @@ -642,7 +673,7 @@ class Audiobook: logger.trace(f"No Narrator found in metadata for {self.name}") return if not self.composer or len(self.composer) < 5: - self.composer = self.metadata.get("narrator") + self.composer = self.metadata["narrator"] def fix_composer_from_comment(self): m = re.search( @@ -665,7 +696,7 @@ class Audiobook: self.comment = cleanup(self.comment) if not self.composer or len(self.composer) < 5: logger.info(f"[Updated] composer found in comment for {self.name}") - self.composer = m.group(1).strip() + self.composer = str(m.group(1).strip()) def fix_composer_from_path(self): rel_path = self.bookPath.relative_to(self.library_root_path) @@ -684,15 +715,13 @@ class Audiobook: if not self.composer or len(self.composer) < 5: self.changed = True logger.info(f"[Updated] composer found in Path for {self.bookPath}") - self.composer = m.group(1).strip() + self.composer = str(m.group(1).strip()) def fix_name(self): if not self.name: self.name = normalize_name(self.bookPath.name, self.series) self.changed = True - logger.info( - f"[Updated] name {self.name} found in path for {self.bookPath}" - ) # + logger.info(f"[Updated] name {self.name} found in path for {self.bookPath}") return name = normalize_name(self.name, self.series) if name != self.name: @@ -749,7 +778,10 @@ class Audiobook: if self.singleFile: new_name = desired_path / f"{desired_name_stem}{file.suffix.lower()}" else: - new_name = desired_path / f"{number:0{padding}d} - {desired_name_stem}{file.suffix}" + new_name = ( + desired_path + / f"{number:0{padding}d} - {desired_name_stem}{file.suffix}" + ) if file == new_name: continue @@ -803,7 +835,9 @@ class Audiobook: if self.composer: composer = f" (by {self.composer})" name = self.name + composer - artist = re.split(r"[,;]", self.artist)[0].strip().replace("/", "_") + artist = "" + if self.artist: + artist = re.split(r"[,;]", self.artist)[0].strip().replace("/", "_") desired_path = self.library_root_path / artist / name if self.series_and_num: series = self.series_and_num @@ -819,7 +853,7 @@ class Audiobook: / f"{number}{name}".replace("/", "_") ) desired_name_stem = ( - self.artist + " - " + self.name + composer + self.bookPath.suffix + f"{self.artist} - {self.name}{composer}{self.bookPath.suffix}" ) desired_name_stem = desired_name_stem.replace("/", "_") return desired_path, desired_name_stem @@ -827,7 +861,7 @@ class Audiobook: def create_m4b_from_book(self, creat_m4b_no_delete: bool = False) -> None: output_file_final = self.bookPath / f"{self.bookPath.name}.m4b" if self.action_required: - logger.warning(f"Action required, resolve before creating m4b file") + logger.warning("Action required, resolve before creating m4b file") return if output_file_final.exists(): logger.info(f"{red_tag('SKIP')} {output_file_final}") @@ -995,15 +1029,16 @@ class Audiobook: def write_metadata(self, keys=None, dry_run=False): if self.action_required: - logger.warning(f"Action required, resolve before writing metadata file") + logger.warning("Action required, resolve before writing metadata file") return self.write_metadata_from_fields() if keys is None: keys = [] for key, value in self.metadata.items(): - if self.metadata_original.get(key) != value: - if not isinstance(value, list): - keys.append(key) + if self.metadata_original.get(key) != value and not isinstance( + value, list + ): + keys.append(key) self.metadata_original = self.metadata.copy() values = [self.metadata[key] for key in keys] if (not keys or not values) and self.metadata_original.get( @@ -1014,8 +1049,8 @@ class Audiobook: if keys: for file in self.files: write_metadata(file, keys, values, dry_run) - if isinstance(self.title, list): - for title, file in zip(self.title, self.files): + if len(self.title_list) == len(self.files): + for title, file in zip(self.title_list, self.files): write_metadata(file, ["title"], [title], dry_run) self.changed = False @@ -1025,12 +1060,9 @@ class Audiobook: if self.singleFile: self.title = self.name else: - self.title = [] padding = len(str(len(self.files))) for idx, file in enumerate(self.files): - self.title.append(f"{self.name} - {idx + 1:0{padding}d}") - - + self.title_list.append(f"{self.name} - {idx + 1:0{padding}d}") class AudiobookLibrary: @@ -1077,21 +1109,31 @@ class AudiobookLibrary: return True def cursor(self): + if not self.db: + raise ValueError return self.db.cursor() def commit(self): + if not self.db: + raise ValueError self.db.commit() def close(self): + if not self.db: + raise ValueError self.db.close() def init(self): + if not self.db: + raise ValueError if not self.connect(): return False return self.load_database_data() def load_database_data(self) -> bool: + if not self.db: + raise ValueError self.tables = self.db.execute( "SELECT name FROM sqlite_master WHERE type='table'" ).fetchall() @@ -1136,6 +1178,8 @@ class AudiobookLibrary: values = [book[c] for c in columns] values.append(book["id"]) + if not self.db: + raise ValueError self.db.execute(sql, values) # commit once after all updates