Files
xiaoxia-saas/apps/worker/video_processing/ffmpeg_utils.py
T
用户CI Test 9c99c9ea96
CI/CD Pipeline / Validate Code Quality And Tests (push) Failing after 8s
CI/CD Pipeline / Validate Code Quality And Tests (pull_request) Failing after 8s
CI/CD Pipeline / Frontend Lint (push) Successful in 2m4s
CI/CD Pipeline / Build & Push Staging (Watchtower auto-deploy) (push) Has been skipped
CI/CD Pipeline / Build Production Runtime Images (push) Has been skipped
CI/CD Pipeline / Staging E2E Tests (push) Has been skipped
CI/CD Pipeline / Staging API Integration Tests (push) Has been skipped
CI/CD Pipeline / Deploy Production (push) Has been skipped
CI/CD Pipeline / Production Browser E2E (push) Has been skipped
CI/CD Pipeline / Frontend Lint (pull_request) Successful in 1m58s
CI/CD Pipeline / Build & Push Staging (Watchtower auto-deploy) (pull_request) Has been skipped
CI/CD Pipeline / Build Production Runtime Images (pull_request) Has been skipped
CI/CD Pipeline / Staging E2E Tests (pull_request) Has been skipped
CI/CD Pipeline / Staging API Integration Tests (pull_request) Has been skipped
CI/CD Pipeline / Deploy Production (pull_request) Has been skipped
CI/CD Pipeline / Production Browser E2E (pull_request) Has been skipped
feat: 统一渲染引擎 + 打通一键生成全链路
核心变更:
1. 提取共享工具模块(ffmpeg_utils / oss_helpers / dedup_helpers)
2. 实现 UnifiedRenderService — 按 clip_type/config.role 分组为图层再合成
3. 重构 render_edit_plan() 使用 UnifiedRenderService(替换 concat demuxer)
4. 重构 generate_video() 使用 UnifiedRenderService(替换 EditingModeProcessor)
5. 集成 VideoDeduplicator 查重
6. 补 23 个单元测试 + 14 个四模式集成测试 + 6 个全链路测试

图层分组算法:
  main → main (z=0)
  main+config.role=b_roll → broll (z=0)
  overlay → overlay (z=1)
  background → background (z=-1)
  corner_voice → corner_voice (z=1)
  b_roll → broll (z=0)
  intro/outro → main (z=0)

合成流程:每个 clip 预处理 → 同层 xfade 串联 → overlay 合成 → 音频混入
2026-07-09 22:34:48 +08:00

290 lines
8.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""FFmpeg 工具函数 — 从 editing_modes.py / video_compose_service.py 提取的共享原语.
提供 FFmpeg / FFprobe 调用、视频信息探测、视频标准化、xfade 转场滤镜构建
等底层能力,供 EditingModeProcessor、VideoComposeService、UnifiedRenderService
共同复用。
"""
from __future__ import annotations
import logging
import shutil
import subprocess # nosec B404
from pathlib import Path
from typing import Any
logger = logging.getLogger(__name__)
# ── 常量 ──────────────────────────────────────────────────────────────────────
FFMPEG_BIN: str = shutil.which("ffmpeg") or "ffmpeg"
FFPROBE_BIN: str = shutil.which("ffprobe") or "ffprobe"
DEFAULT_OUTPUT_WIDTH = 1280
DEFAULT_OUTPUT_HEIGHT = 720
DEFAULT_FPS = 25
# xfade 转场映射:transition_effect 名称 → FFmpeg xfade transition 名称
# 键同时支持 TransitionEffect 枚举值和字符串名称(向后兼容)
XFADE_TRANSITION_MAP: dict[str, str] = {
"fade": "fade",
"slideleft": "slideleft",
"slide_left": "slideleft",
"slideright": "slideright",
"slide_right": "slideright",
"dissolve": "dissolve",
"wipe": "wipeleft",
"wipeleft": "wipeleft",
}
DEFAULT_TRANSITION_DURATION = 0.5
# ── FFmpeg 执行 ───────────────────────────────────────────────────────────────
def run_ffmpeg(
command: list[str],
*,
capture_output: bool = True,
) -> tuple[str, str]:
"""执行 FFmpeg 命令。
Args:
command: 完整的 ffmpeg 命令列表(含 "ffmpeg" 本身)
capture_output: 是否捕获 stdout/stderr
Returns:
(stdout, stderr) 元组
Raises:
subprocess.CalledProcessError: 命令执行失败时抛出
"""
result = subprocess.run( # nosec B603
command,
check=True,
stdout=subprocess.PIPE if capture_output else None,
stderr=subprocess.PIPE if capture_output else None,
text=True,
)
return (result.stdout or "", result.stderr or "")
def probe_duration(local_path: str | Path) -> float:
"""用 ffprobe 获取视频时长(秒)。
失败时返回默认值 5.0 秒。
"""
try:
result = subprocess.run( # nosec B603
[
FFPROBE_BIN,
"-v",
"error",
"-show_entries",
"format=duration",
"-of",
"default=noprint_wrappers=1:nokey=1",
str(local_path),
],
check=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
)
return round(float(result.stdout.strip()), 3)
except Exception:
return 5.0
def probe_video_info(video_path: str) -> dict[str, Any]:
"""获取视频信息(宽、高、时长、fps)。
Returns:
{"width": int, "height": int, "duration": float, "fps": float}
失败时返回默认值。
"""
try:
result = subprocess.run( # nosec B603
[
FFPROBE_BIN,
"-v",
"error",
"-select_streams",
"v:0",
"-show_entries",
"stream=width,height,r_frame_rate,duration",
"-show_entries",
"format=duration",
"-of",
"json",
video_path,
],
check=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
)
import json
info = json.loads(result.stdout)
stream = info.get("streams", [{}])[0]
fmt = info.get("format", {})
width = int(stream.get("width", DEFAULT_OUTPUT_WIDTH))
height = int(stream.get("height", DEFAULT_OUTPUT_HEIGHT))
# 解析帧率
fps_str = stream.get("r_frame_rate", "25/1")
if "/" in fps_str:
num, den = fps_str.split("/")
fps = float(num) / float(den) if float(den) > 0 else DEFAULT_FPS
else:
fps = float(fps_str) if fps_str else DEFAULT_FPS
# 时长
duration = float(fmt.get("duration", 0)) or float(stream.get("duration", 0))
return {
"width": width,
"height": height,
"duration": duration,
"fps": round(fps, 2),
}
except Exception as e:
logger.warning("获取视频信息失败: %s, error: %s", video_path, e)
return {
"width": DEFAULT_OUTPUT_WIDTH,
"height": DEFAULT_OUTPUT_HEIGHT,
"duration": 0.0,
"fps": DEFAULT_FPS,
}
def normalize_video(
input_path: str,
output_path: str,
*,
width: int = DEFAULT_OUTPUT_WIDTH,
height: int = DEFAULT_OUTPUT_HEIGHT,
fps: int = DEFAULT_FPS,
) -> dict[str, Any]:
"""标准化视频(缩放 + 恒定帧率)。
使用 scale + pad 保持宽高比,黑边填充到目标分辨率。
Returns:
{"width": int, "height": int, "path": str}
"""
command = [
FFMPEG_BIN,
"-y",
"-i",
input_path,
"-vf",
f"scale={width}:{height}:force_original_aspect_ratio=decrease,"
f"pad={width}:{height}:(ow-iw)/2:(oh-ih)/2:black,"
f"fps={fps}",
"-c:v",
"libx264",
"-crf",
"23",
"-preset",
"medium",
"-c:a",
"aac",
"-b:a",
"128k",
"-movflags",
"+faststart",
output_path,
]
run_ffmpeg(command)
return {"width": width, "height": height, "path": output_path}
# ── xfade / concat 滤镜构建 ──────────────────────────────────────────────────
def chain_filters(filters: list[str], output_label: str, *, input_label: str = "0:v") -> str:
"""将滤镜列表串联为 FFmpeg 滤镜字符串。
例:chain_filters(["scale=1280:720", "fps=25"], "v0")
→ "[0:v]scale=1280:720,fps=25[v0]"
"""
filter_body = ",".join(filters)
return f"[{input_label}]{filter_body}[{output_label}]"
def resolve_xfade_transition(transition_name: str) -> str:
"""将转场效果名称映射为 FFmpeg xfade transition 名称。
支持 TransitionEffect 枚举值和字符串名称,未知值回退到 "fade"。
"""
# 兼容 TransitionEffect 枚举(有 .value 属性)
if hasattr(transition_name, "value"):
transition_name = transition_name.value
return XFADE_TRANSITION_MAP.get(transition_name, "fade")
def build_xfade_filter_chain(
clip_durations: list[float],
clip_video_labels: list[str],
transitions: list[str],
*,
transition_duration: float = DEFAULT_TRANSITION_DURATION,
output_label: str = "outv",
) -> tuple[str, float]:
"""构建 xfade 转场滤镜链。
Args:
clip_durations: 每个片段的时长
clip_video_labels: 每个片段的视频流标签(如 "v0", "v1"
transitions: 每个片段对应的转场效果(第一个片段的转场被忽略)
transition_duration: 转场时长(秒)
output_label: 最终输出标签
Returns:
(filter_string, estimated_total_duration)
"""
n = len(clip_durations)
parts: list[str] = []
total_duration = sum(clip_durations)
if n == 0:
return "", 0.0
if n == 1:
parts.append(f"[{clip_video_labels[0]}]copy[{output_label}]")
return ";".join(parts), total_duration
# xfade 链
cumulative = 0.0
prev_label = clip_video_labels[0]
for i in range(1, n):
cumulative += clip_durations[i - 1]
offset = max(0.0, cumulative - transition_duration * i)
transition = transitions[i] if i < len(transitions) else "cut"
xfade_transition = resolve_xfade_transition(transition)
if i == n - 1:
out_label = output_label
else:
out_label = f"xf{i}"
parts.append(
f"[{prev_label}][{clip_video_labels[i]}]"
f"xfade=transition={xfade_transition}"
f":duration={transition_duration}"
f":offset={offset:.3f}"
f"[{out_label}]"
)
prev_label = out_label
# 总时长减去转场重叠部分
total_duration -= transition_duration * (n - 1)
return ";".join(parts), max(0.0, total_duration)