Files
abogen/abogen/infrastructure/subtitle_writer.py
T
Artem Akymenko 953bef1e71 refactor: group ConversionRequest fields into config objects
Domain config types (domain/config_types.py):
- PronunciationConfig: pronunciation/heteronym/normalization overrides
- SubtitleConfig: mode, format, max_words
- CoverConfig: path, mime

Domain functions now accept config objects:
- build_tts_context(subtitle=, pronunciation=) instead of 9 individual params
- make_subtitle_writer(subtitle=) instead of 3 params
- process_and_write_subtitles(subtitle=) instead of 2 params
- embed_m4b_metadata(cover=) instead of 2 params
- build_epub3_package(cover=) instead of 2 params

ConversionRequest: 18 flat fields + 8 config objects
Application/config.py re-exports domain types
All tests updated to new API
2026-07-28 13:41:45 +03:00

375 lines
11 KiB
Python

from __future__ import annotations
from abc import ABC, abstractmethod
from dataclasses import dataclass
from enum import Enum
from pathlib import Path
from typing import List, Optional, TextIO
from abogen.domain.enums import SubtitleFormat, SubtitleMode
from abogen.subtitle_utils import clean_subtitle_text
class SubtitleAlignment(Enum):
LEFT = "left"
CENTER = "center"
NARROW = "narrow"
CENTER_NARROW = "center_narrow"
@dataclass
class SubtitleConfig:
"""Configuration for subtitle writer."""
format: SubtitleFormat
mode: SubtitleMode
alignment: SubtitleAlignment = SubtitleAlignment.LEFT
max_words: int = 50
highlight_color: str = "&H00FFFF00" # ASS highlight color
class SubtitleWriter(ABC):
"""Abstract base class for subtitle writers."""
def __init__(self, path: Path, config: SubtitleConfig):
self.path = path
self.config = config
self._file: Optional[TextIO] = None
self._index = 0
self._opened = False
def open(self) -> None:
"""Open the subtitle file and write header."""
if self._opened:
return
self._file = open(self.path, "w", encoding="utf-8", errors="replace")
self._write_header()
self._opened = True
@abstractmethod
def _write_header(self) -> None:
pass
def write_entry(
self,
start: float,
end: float,
text: str,
voice: Optional[str] = None,
) -> None:
"""Write a subtitle entry."""
if not self._opened:
self.open()
text = clean_subtitle_text(text)
if not text:
return
self._index += 1
self._write_entry(self._index, start, end, text, voice)
@abstractmethod
def _write_entry(
self,
index: int,
start: float,
end: float,
text: str,
voice: Optional[str],
) -> None:
pass
def close(self) -> None:
"""Close the subtitle file."""
if self._file:
self._file.close()
self._file = None
self._opened = False
def __enter__(self) -> "SubtitleWriter":
self.open()
return self
def __exit__(self, exc_type, exc_val, exc_tb) -> None:
self.close()
class SrtWriter(SubtitleWriter):
"""SRT subtitle writer."""
def _write_header(self) -> None:
pass # SRT has no header
def _write_entry(
self,
index: int,
start: float,
end: float,
text: str,
voice: Optional[str],
) -> None:
start_str = self._format_time(start)
end_str = self._format_time(end)
if voice:
text = f"[{voice}] {text}"
self._file.write(f"{index}\n")
self._file.write(f"{start_str} --> {end_str}\n")
self._file.write(f"{text}\n\n")
@staticmethod
def _format_time(seconds: float) -> str:
hours = int(seconds // 3600)
minutes = int((seconds % 3600) // 60)
secs = int(seconds % 60)
millis = int((seconds - int(seconds)) * 1000)
return f"{hours:02d}:{minutes:02d}:{secs:02d},{millis:03d}"
class VttWriter(SubtitleWriter):
"""WebVTT subtitle writer."""
def _write_header(self) -> None:
self._file.write("WEBVTT\n\n")
def _write_entry(
self,
index: int,
start: float,
end: float,
text: str,
voice: Optional[str],
) -> None:
start_str = self._format_time(start)
end_str = self._format_time(end)
if voice:
text = f"[{voice}] {text}"
self._file.write(f"{index}\n")
self._file.write(f"{start_str} --> {end_str}\n")
self._file.write(f"{text}\n\n")
@staticmethod
def _format_time(seconds: float) -> str:
hours = int(seconds // 3600)
minutes = int((seconds % 3600) // 60)
secs = seconds % 60
return f"{hours:02d}:{minutes:02d}:{secs:06.3f}".replace(".", ".")
class AssWriter(SubtitleWriter):
"""ASS subtitle writer with karaoke highlighting support."""
def __init__(self, path: Path, config: SubtitleConfig):
super().__init__(path, config)
self._is_centered = config.alignment in (SubtitleAlignment.CENTER, SubtitleAlignment.CENTER_NARROW)
self._is_narrow = config.alignment in (SubtitleAlignment.NARROW, SubtitleAlignment.CENTER_NARROW)
def _write_header(self) -> None:
margin = "90" if self._is_narrow else "10"
alignment = "5" if self._is_centered else "2"
self._file.write("[Script Info]\n")
self._file.write("Title: Generated by Abogen\n")
self._file.write("ScriptType: v4.00+\n\n")
# Styles
self._file.write("[V4+ Styles]\n")
self._file.write(
"Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, "
"OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, "
"ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, "
"Alignment, MarginL, MarginR, MarginV, Encoding\n"
)
if self.config.mode == SubtitleMode.SENTENCE_HIGHLIGHT:
# Karaoke style with highlighting
self._file.write(
f"Style: Default,Arial,24,&H00FFFFFF,&H00808080,&H00000000,&H00404040,"
f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n"
)
self._file.write(
f"Style: Highlight,Arial,24,&H0000FFFF,&H00808080,&H00000000,&H00404040,"
f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n\n"
)
else:
self._file.write(
f"Style: Default,Arial,24,&H00FFFFFF,&H00808080,&H00000000,&H00404040,"
f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n\n"
)
self._file.write("[Events]\n")
self._file.write(
"Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\n"
)
def _write_entry(
self,
index: int,
start: float,
end: float,
text: str,
voice: Optional[str],
) -> None:
start_str = self._format_time(start)
end_str = self._format_time(end)
if voice:
text = f"[{voice}] {text}"
style = "Default"
if self.config.mode == SubtitleMode.SENTENCE_HIGHLIGHT:
# Add karaoke tags for highlighting
text = self._add_karaoke_tags(text)
style = "Highlight"
alignment_tag = r"{\an5}" if self._is_centered else ""
self._file.write(
f"Dialogue: 0,{start_str},{end_str},{style},,0,0,0,,{alignment_tag}{text}\n"
)
def _add_karaoke_tags(self, text: str) -> str:
"""Add karaoke highlighting tags to text."""
# Simple word-level karaoke timing
words = text.split()
if not words:
return text
# This is a simplified version - real karaoke needs per-word timing
# For now, just return the text with the highlight color
return r"{\k100}" + r"{\k100}".join(words) + r"{\k0}"
@staticmethod
def _format_time(seconds: float) -> str:
hours = int(seconds // 3600)
minutes = int((seconds % 3600) // 60)
secs = seconds % 60
return f"{hours}:{minutes:02d}:{secs:05.2f}"
def create_subtitle_writer(
path: Path,
format: str,
mode: str,
alignment: str = "left",
max_words: int = 50,
) -> SubtitleWriter:
"""Factory function to create subtitle writer."""
fmt = SubtitleFormat(format.lower())
mode = SubtitleMode(mode)
align = SubtitleAlignment(alignment.lower())
config = SubtitleConfig(
format=fmt,
mode=mode,
alignment=align,
max_words=max_words,
)
if fmt == SubtitleFormat.SRT:
return SrtWriter(path, config)
elif fmt == SubtitleFormat.VTT:
return VttWriter(path, config)
elif fmt == SubtitleFormat.ASS:
return AssWriter(path, config)
else:
raise ValueError(f"Unsupported subtitle format: {format}")
def resolve_subtitle_format(
subtitle: "SubtitleConfig | str | None",
subtitle_mode: str | None = None,
) -> tuple[str, str]:
"""Resolve a subtitle config to (file_extension, alignment).
Accepts a SubtitleConfig object or individual format/mode strings
for backward compatibility.
Returns:
Tuple of (file_extension, alignment) suitable for
:func:`create_subtitle_writer`.
"""
from abogen.domain.config_types import SubtitleConfig
if isinstance(subtitle, SubtitleConfig):
fmt = subtitle.format.value.lower()
mode_str = subtitle.mode.value
else:
fmt = (subtitle or "srt").lower()
mode_str = subtitle_mode or "Disabled"
if mode_str == "Sentence + Highlighting" and fmt == "srt":
fmt = "ass"
if "ass" in fmt:
extension = "ass"
if "centered_narrow" in fmt:
alignment = "center_narrow"
elif "centered" in fmt:
alignment = "center"
elif "narrow" in fmt:
alignment = "narrow"
else:
alignment = "left"
else:
extension = fmt if fmt in ("srt", "vtt") else "srt"
alignment = "left"
return extension, alignment
def make_subtitle_writer(
audio_path: Path,
subtitle: "SubtitleConfig | str | None",
subtitle_mode: str | None = None,
max_words: int | None = None,
) -> SubtitleWriter | None:
"""Convenience: resolve format and create a writer, or return None if disabled.
Accepts a SubtitleConfig object or individual format/mode strings
for backward compatibility.
Returns ``None`` when subtitle mode is ``"Disabled"`` or the
format is unsupported.
"""
from abogen.domain.config_types import SubtitleConfig
if isinstance(subtitle, SubtitleConfig):
mode_str = subtitle.mode.value
if mode_str == "Disabled":
return None
words = subtitle.max_words
else:
mode_str = subtitle_mode or subtitle or "Disabled"
if mode_str == "Disabled":
return None
words = max_words or 50
extension, alignment = resolve_subtitle_format(subtitle, subtitle_mode)
try:
return create_subtitle_writer(
audio_path.with_suffix(f".{extension}"),
extension,
mode_str,
alignment=alignment,
max_words=words,
)
except (ValueError, KeyError):
return None
__all__ = [
"SubtitleFormat",
"SubtitleMode",
"SubtitleAlignment",
"SubtitleConfig",
"SubtitleWriter",
"SrtWriter",
"VttWriter",
"AssWriter",
"create_subtitle_writer",
"resolve_subtitle_format",
"make_subtitle_writer",
]