feat: 多轨道混音 + 字幕渲染引擎 + 视频拼接(后端) (#312)
CI/CD Pipeline / Build Staging API Image (push) Failing after 8s
CI/CD Pipeline / Build Staging Worker Image (push) Failing after 11s
CI/CD Pipeline / Build Staging Web Image (push) Failing after 1m50s
CI/CD Pipeline / Staging API Integration Tests (push) Failing after 1536h5m9s
CI/CD Pipeline / Staging E2E Tests (push) Failing after 1536h5m10s
CI/CD Pipeline / Deploy Staging (Watchtower auto-deploy) (push) Failing after 1536h5m11s
CI/CD Pipeline / Deploy Production (push) Failing after 1536h7m1s
CI/CD Pipeline / Build Production Web Image (push) Failing after 1536h7m2s
CI/CD Pipeline / Build Production API Image (push) Failing after 1536h7m3s
CI/CD Pipeline / Validate Code Quality And Tests (push) Has been skipped
CI/CD Pipeline / Unit Tests (push) Has been skipped
CI/CD Pipeline / Integration Tests (push) Has been skipped
CI/CD Pipeline / Frontend Lint (push) Has been skipped
CI/CD Pipeline / Production Browser E2E (push) Failing after 1536h38m37s
CI/CD Pipeline / Build Production Worker Image (push) Failing after 1536h38m41s

This commit was merged in pull request #312.
This commit is contained in:
2026-07-14 15:20:47 +08:00
parent b05966ff48
commit f268e208de
6 changed files with 2676 additions and 2 deletions
+633
View File
@@ -0,0 +1,633 @@
"""字幕渲染引擎 — 统一管理字幕样式配置与视频烧录.
与现有模块的关系:
- render_subtitles.py:生成静态整段标题/字幕的 ASS 文件
- subtitle_generator.py:从 ASR 时间轴生成 ASS 文件
- 本模块:统一的字幕样式配置 + 烧录滤镜生成 + 多源字幕合并
支持的字幕来源:
1. 静态标题/字幕(title_config / subtitle_config)
2. ASR 自动字幕(asr_subtitle_timeline)
3. 手动字幕(manual_subtitles 时间轴)
支持的样式配置:
- 字体、字号、颜色
- 描边(颜色、宽度)
- 阴影(偏移、模糊、颜色)
- 背景框(颜色、透明度、圆角、边距)
- 位置(9宫格 + 自定义坐标)
- 对齐方式
- 动画(淡入淡出、滑入滑出、打字机)
- 多行/换行规则
"""
from __future__ import annotations
import logging
from dataclasses import dataclass, field
from pathlib import Path
from typing import Any
from video_processing.render_subtitles import generate_ass_subtitles
from video_processing.subtitle_generator import generate_ass_from_timeline
logger = logging.getLogger(__name__)
# ── 常量 ──────────────────────────────────────────────────────────────────────
# 9宫格位置映射(ASS alignment 编号)
POSITION_ALIGNMENT = {
"top_left": 7,
"top_center": 8,
"top_right": 9,
"middle_left": 4,
"center": 5,
"middle_right": 6,
"bottom_left": 1,
"bottom_center": 2,
"bottom_right": 3,
}
# 位置简称兼容
POSITION_ALIASES = {
"top": "top_center",
"bottom": "bottom_center",
"middle": "center",
"left": "middle_left",
"right": "middle_right",
}
DEFAULT_FONT = "思源黑体"
DEFAULT_FONT_SIZE = 24
DEFAULT_COLOR = "#FFFFFF"
DEFAULT_STROKE_COLOR = "#000000"
DEFAULT_STROKE_WIDTH = 1.5
DEFAULT_POSITION = "bottom_center"
DEFAULT_MAX_CHARS_PER_LINE = 20
# ── 字幕样式配置 ────────────────────────────────────────────────────────────
@dataclass
class SubtitleStyle:
"""字幕样式配置."""
font_name: str = DEFAULT_FONT
font_size: int = DEFAULT_FONT_SIZE
font_color: str = DEFAULT_COLOR
bold: bool = False
italic: bool = False
# 描边
stroke_enabled: bool = True
stroke_color: str = DEFAULT_STROKE_COLOR
stroke_width: float = DEFAULT_STROKE_WIDTH
# 阴影
shadow_enabled: bool = False
shadow_color: str = "#000000"
shadow_offset_x: int = 2
shadow_offset_y: int = 2
shadow_blur: float = 0.0
# 背景框
background_enabled: bool = False
background_color: str = "#000000"
background_opacity: float = 0.5 # 0.0 ~ 1.0
background_padding: int = 8
background_radius: int = 4
# 位置
position: str = DEFAULT_POSITION # 9宫格位置名
margin_v: int = 60 # 垂直边距
margin_l: int = 40 # 左边距
margin_r: int = 40 # 右边距
# 多行
max_chars_per_line: int = DEFAULT_MAX_CHARS_PER_LINE
line_spacing: int = 0 # 行间距
# 动画
fade_in: float = 0.0 # 淡入时长(秒)
fade_out: float = 0.0 # 淡出时长(秒)
animation_type: str = "none" # none/fade/slide/typewriter
@classmethod
def from_dict(cls, config: dict[str, Any] | None) -> "SubtitleStyle":
"""从字典创建样式配置,带安全类型转换."""
if not config or not isinstance(config, dict):
return cls()
def safe_str(key: str, default: str) -> str:
val = config.get(key, default)
return str(val) if val is not None else default
def safe_int(key: str, default: int) -> int:
try:
return int(config.get(key, default))
except (TypeError, ValueError):
return default
def safe_float(key: str, default: float) -> float:
try:
return float(config.get(key, default))
except (TypeError, ValueError):
return default
def safe_bool(key: str, default: bool) -> bool:
return bool(config.get(key, default))
position = safe_str("position", DEFAULT_POSITION)
position = POSITION_ALIASES.get(position, position)
if position not in POSITION_ALIGNMENT:
position = DEFAULT_POSITION
return cls(
font_name=safe_str("font", DEFAULT_FONT),
font_size=safe_int("size", DEFAULT_FONT_SIZE),
font_color=safe_str("color", DEFAULT_COLOR),
bold=safe_bool("bold", False),
italic=safe_bool("italic", False),
stroke_enabled=safe_bool("stroke_enabled", True),
stroke_color=safe_str("stroke_color", DEFAULT_STROKE_COLOR),
stroke_width=safe_float("stroke_width", DEFAULT_STROKE_WIDTH),
shadow_enabled=safe_bool("shadow_enabled", False),
shadow_color=safe_str("shadow_color", "#000000"),
shadow_offset_x=safe_int("shadow_offset_x", 2),
shadow_offset_y=safe_int("shadow_offset_y", 2),
shadow_blur=safe_float("shadow_blur", 0.0),
background_enabled=safe_bool("background_enabled", False),
background_color=safe_str("background_color", "#000000"),
background_opacity=max(0.0, min(1.0, safe_float("background_opacity", 0.5))),
background_padding=safe_int("background_padding", 8),
background_radius=safe_int("background_radius", 4),
position=position,
margin_v=safe_int("margin_v", 60),
margin_l=safe_int("margin_l", 40),
margin_r=safe_int("margin_r", 40),
max_chars_per_line=safe_int("max_chars_per_line", DEFAULT_MAX_CHARS_PER_LINE),
line_spacing=safe_int("line_spacing", 0),
fade_in=max(0.0, safe_float("fade_in", 0.0)),
fade_out=max(0.0, safe_float("fade_out", 0.0)),
animation_type=safe_str("animation_type", "none"),
)
@property
def alignment(self) -> int:
"""获取 ASS alignment 编号."""
return POSITION_ALIGNMENT.get(self.position, 2)
@property
def ass_font_color(self) -> str:
"""ASS 格式颜色 &HAABBGGRR."""
return _hex_to_ass_color(self.font_color)
@property
def ass_stroke_color(self) -> str:
return _hex_to_ass_color(self.stroke_color)
@property
def ass_shadow_color(self) -> str:
return _hex_to_ass_color(self.shadow_color)
@property
def ass_background_color(self) -> str:
"""背景框颜色(ASS BackColour),带透明度."""
alpha_hex = _opacity_to_ass_alpha(self.background_opacity)
color_bgr = _hex_to_ass_bgr(self.background_color)
return f"&H{alpha_hex}{color_bgr}"
# ── 工具函数 ──────────────────────────────────────────────────────────────────
def _hex_to_ass_color(hex_color: str) -> str:
"""HEX → ASS 颜色 &HAABBGGRR(默认不透明)."""
hex_color = hex_color.lstrip("#")
if len(hex_color) != 6:
return "&H00FFFFFF"
r, g, b = hex_color[0:2], hex_color[2:4], hex_color[4:6]
return f"&H00{b.upper()}{g.upper()}{r.upper()}"
def _hex_to_ass_bgr(hex_color: str) -> str:
"""HEX → ASS BGR 部分(不含 alpha)."""
hex_color = hex_color.lstrip("#")
if len(hex_color) != 6:
return "FFFFFF"
r, g, b = hex_color[0:2], hex_color[2:4], hex_color[4:6]
return f"{b.upper()}{g.upper()}{r.upper()}"
def _opacity_to_ass_alpha(opacity: float) -> str:
"""不透明度 → ASS alpha(00=不透明,FF=完全透明)."""
alpha = 255 - int(opacity * 255)
return f"{alpha:02X}"
def _escape_ass_text(text: str) -> str:
"""转义 ASS 文本特殊字符."""
text = text.replace("\r\n", "\\N").replace("\n", "\\N").replace("\r", "\\N")
text = text.replace("{", "(").replace("}", ")")
return text
def _format_ass_time(seconds: float) -> str:
"""秒 → ASS 时间格式 H:MM:SS.cc."""
hours = int(seconds // 3600)
minutes = int((seconds % 3600) // 60)
secs = seconds % 60
return f"{hours}:{minutes:02d}:{secs:05.2f}"
def _wrap_text(text: str, max_chars: int) -> list[str]:
"""按字数换行,优先标点断开."""
if len(text) <= max_chars:
return [text]
lines: list[str] = []
remaining = text
while len(remaining) > max_chars:
break_point = max_chars
punctuations = ",。!?、;:,.;:!?"
for i in range(max_chars, max_chars // 2, -1):
if i < len(remaining) and remaining[i] in punctuations:
break_point = i + 1
break
lines.append(remaining[:break_point])
remaining = remaining[break_point:]
if remaining:
lines.append(remaining)
return lines
# ── 字幕片段 ──────────────────────────────────────────────────────────────────
@dataclass
class SubtitleSegment:
"""单个字幕片段."""
start: float # 开始时间(秒)
end: float # 结束时间(秒)
text: str # 字幕文本
style_name: str = "Default" # 使用的样式名
# ── 字幕渲染引擎 ──────────────────────────────────────────────────────────────
class SubtitleRenderEngine:
"""字幕渲染引擎 — 统一管理多源字幕的 ASS 文件生成.
支持合并多个字幕来源到同一个 ASS 文件:
- 标题(顶部,单独样式)
- 字幕(底部,单独样式)
- ASR 时间轴字幕
- 手动字幕
输出一个统一的 ASS 文件,供 FFmpeg subtitles filter 烧录。
"""
def __init__(
self,
video_width: int = 1080,
video_height: int = 1920,
video_duration: float = 0.0,
):
self.video_width = video_width
self.video_height = video_height
self.video_duration = video_duration
self._styles: dict[str, SubtitleStyle] = {}
self._segments: list[SubtitleSegment] = []
self._style_counter = 0
# ── 样式管理 ──────────────────────────────────────────────────────
def add_style(self, name: str, style: SubtitleStyle) -> str:
"""注册一个样式,返回样式名."""
self._styles[name] = style
return name
def get_or_create_style(self, base_name: str, style: SubtitleStyle) -> str:
"""获取或创建样式(避免重复)."""
if base_name in self._styles:
return base_name
self._styles[base_name] = style
return base_name
# ── 字幕源添加 ────────────────────────────────────────────────────
def add_title(self, text: str, style: SubtitleStyle | None = None) -> None:
"""添加整段标题(显示整个视频时长)."""
if not text or not text.strip():
return
style = style or SubtitleStyle(
position="top_center",
font_size=48,
bold=True,
stroke_enabled=True,
stroke_width=2.0,
)
style_name = self.get_or_create_style("TitleStyle", style)
self._segments.append(
SubtitleSegment(
start=0.0,
end=self.video_duration if self.video_duration > 0 else 9999.0,
text=text.strip(),
style_name=style_name,
)
)
def add_subtitle_text(self, text: str, style: SubtitleStyle | None = None) -> None:
"""添加整段字幕(显示整个视频时长)."""
if not text or not text.strip():
return
style = style or SubtitleStyle()
style_name = self.get_or_create_style("SubtitleStyle", style)
self._segments.append(
SubtitleSegment(
start=0.0,
end=self.video_duration if self.video_duration > 0 else 9999.0,
text=text.strip(),
style_name=style_name,
)
)
def add_timeline_segments(
self,
segments: list[dict] | list[SubtitleSegment],
style: SubtitleStyle | None = None,
) -> None:
"""添加时间轴字幕片段(ASR 或手动字幕).
segments 可以是:
- SubtitleSegment 列表
- dict 列表,每个 dict 含 start/end/text 字段
"""
if not segments:
return
style = style or SubtitleStyle()
style_name = self.get_or_create_style("Default", style)
for seg in segments:
if isinstance(seg, SubtitleSegment):
seg.style_name = style_name
self._segments.append(seg)
elif isinstance(seg, dict):
try:
start = float(seg.get("start", 0))
end = float(seg.get("end", 0))
text = str(seg.get("text", ""))
if end > start and text.strip():
self._segments.append(
SubtitleSegment(
start=start,
end=end,
text=text.strip(),
style_name=style_name,
)
)
except (TypeError, ValueError):
continue
def add_asr_timeline(self, timeline: Any, style: SubtitleStyle | None = None) -> None:
"""从 SubtitleTimeline 对象添加 ASR 字幕."""
if not timeline or not hasattr(timeline, "segments") or not timeline.segments:
return
style = style or SubtitleStyle()
style_name = self.get_or_create_style("ASRStyle", style)
for seg in timeline.segments:
if hasattr(seg, "start") and hasattr(seg, "end") and hasattr(seg, "text"):
if seg.end > seg.start and seg.text.strip():
self._segments.append(
SubtitleSegment(
start=seg.start,
end=seg.end,
text=seg.text.strip(),
style_name=style_name,
)
)
# ── ASS 文件生成 ──────────────────────────────────────────────────
def generate_ass(self, output_path: Path) -> Path:
"""生成 ASS 字幕文件.
Returns:
生成的文件路径;如果没有字幕内容,返回空文件。
"""
if not self._segments:
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_text("", encoding="utf-8")
return output_path
# 确保至少有 Default 样式
if "Default" not in self._styles:
self._styles["Default"] = SubtitleStyle()
# 生成样式行
style_lines = []
for name, style in self._styles.items():
style_lines.append(self._build_ass_style_line(name, style))
# 生成事件行(按时间排序)
self._segments.sort(key=lambda s: s.start)
event_lines = []
for seg in self._segments:
event_lines.append(self._build_ass_event_line(seg))
# 组装文件
ass_content = f"""[Script Info]
ScriptType: v4.00+
PlayResX: {self.video_width}
PlayResY: {self.video_height}
ScaledBorderAndShadow: yes
WrapStyle: 2
Encoding: UTF-8
[V4+ Styles]
Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
{chr(10).join(style_lines)}
[Events]
Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
{chr(10).join(event_lines)}
"""
output_path.parent.mkdir(parents=True, exist_ok=True)
output_path.write_text(ass_content, encoding="utf-8")
return output_path
def _build_ass_style_line(self, name: str, style: SubtitleStyle) -> str:
"""构建一条 ASS Style 行."""
bold_val = -1 if style.bold else 0
italic_val = -1 if style.italic else 0
# BorderStyle: 1=outline+shadow, 3=opaque box(背景框)
if style.background_enabled:
border_style = 3
back_color = style.ass_background_color
else:
border_style = 1
back_color = style.ass_shadow_color if style.shadow_enabled else style.ass_font_color
outline_val = style.stroke_width if style.stroke_enabled else 0.0
shadow_val = style.shadow_offset_y if style.shadow_enabled else 0
return (
f"Style: {name},{style.font_name},{style.font_size},{style.ass_font_color},"
f"&H000000FF,{style.ass_stroke_color},{back_color},"
f"{bold_val},{italic_val},0,0,100,100,0,0,"
f"{border_style},{outline_val},{shadow_val},{style.alignment},"
f"{style.margin_l},{style.margin_r},{style.margin_v},1"
)
def _build_ass_event_line(self, seg: SubtitleSegment) -> str:
"""构建一条 ASS Dialogue 事件行."""
style = self._styles.get(seg.style_name, SubtitleStyle())
max_chars = style.max_chars_per_line
# 自动换行
lines = _wrap_text(seg.text, max_chars)
display_text = "\\N".join(lines)
# 动画效果(淡入淡出)
effect_tags = ""
if style.fade_in > 0 or style.fade_out > 0:
fade_in_ms = int(style.fade_in * 1000)
fade_out_ms = int(style.fade_out * 1000)
effect_tags = f"{{\\fad({fade_in_ms},{fade_out_ms})}}"
safe_text = _escape_ass_text(display_text)
start_time = _format_ass_time(max(0, seg.start))
end_time = _format_ass_time(max(seg.start + 0.1, seg.end))
return f"Dialogue: 0,{start_time},{end_time},{seg.style_name},,0,0,0,," f"{effect_tags}{safe_text}"
@property
def has_subtitles(self) -> bool:
"""是否有字幕内容."""
return len(self._segments) > 0
# ── 便捷函数:从 plan.config 快速生成 ASS ────────────────────────────────────
def build_subtitles_from_plan(
output_path: Path,
plan_config: dict,
*,
video_width: int,
video_height: int,
video_duration: float,
asr_timeline: Any = None,
) -> Path | None:
"""从 plan.config 构建字幕 ASS 文件.
支持的配置项:
- title_config: 标题配置(含 text/style)
- subtitle_config: 字幕配置(含 text/style)
- asr_subtitles: ASR 字幕开关 + 样式
- manual_subtitles: 手动字幕片段列表
Returns:
生成的 ASS 文件路径;如果没有任何字幕,返回 None
"""
engine = SubtitleRenderEngine(
video_width=video_width,
video_height=video_height,
video_duration=video_duration,
)
has_any = False
# 1. 标题
title_cfg = plan_config.get("title_config") or {}
if isinstance(title_cfg, dict):
title_text = str(title_cfg.get("text", ""))
title_enabled = title_cfg.get("enabled", True)
if title_enabled and title_text.strip():
style_dict = title_cfg.get("style") or {}
style = SubtitleStyle.from_dict(style_dict)
# 标题默认样式:顶部、大字号、粗体
if style.position == DEFAULT_POSITION and style.font_size == DEFAULT_FONT_SIZE:
style.position = "top_center"
style.font_size = 48
style.bold = True
engine.add_title(title_text, style)
has_any = True
# 2. 静态字幕
sub_cfg = plan_config.get("subtitle_config") or {}
if isinstance(sub_cfg, dict):
sub_text = str(sub_cfg.get("text", ""))
sub_enabled = sub_cfg.get("enabled", True)
if sub_enabled and sub_text.strip():
style_dict = sub_cfg.get("style") or {}
style = SubtitleStyle.from_dict(style_dict)
engine.add_subtitle_text(sub_text, style)
has_any = True
# 3. ASR 自动字幕
asr_cfg = plan_config.get("asr_subtitles") or {}
if isinstance(asr_cfg, dict) and asr_cfg.get("enabled", False):
if asr_timeline is not None:
style_dict = asr_cfg.get("style") or {}
style = SubtitleStyle.from_dict(style_dict)
engine.add_asr_timeline(asr_timeline, style)
has_any = has_any or engine.has_subtitles
# 4. 手动字幕
manual_segs = plan_config.get("manual_subtitles") or []
if isinstance(manual_segs, list) and manual_segs:
style_dict = (plan_config.get("manual_subtitle_style") or {}) or {}
style = SubtitleStyle.from_dict(style_dict)
engine.add_timeline_segments(manual_segs, style)
has_any = has_any or engine.has_subtitles
if not has_any:
return None
return engine.generate_ass(output_path)
# ── FFmpeg 烧录滤镜生成 ───────────────────────────────────────────────────────
def build_subtitle_filter(
ass_path: Path | str,
*,
video_input_label: str = "0:v",
output_label: str = "subtitled",
) -> str:
"""生成 FFmpeg subtitles 滤镜字符串.
Args:
ass_path: ASS 字幕文件路径
video_input_label: 视频输入标签(如 "0:v" 或 "[v_out]")
output_label: 输出标签
Returns:
filter_complex 片段,如 "[0:v]subtitles=xxx.ass[subtitled]"
"""
# FFmpeg subtitles filter 的路径需要转义:
# - Windows 路径的 \ → /
# - 冒号 : → \:
# - 单引号 ' → '\''
safe_path = str(ass_path).replace("\\", "/").replace(":", "\\:").replace("'", "'\\''")
return f"{video_input_label}subtitles='{safe_path}'[{output_label}]"