feat(screencast): 统一字幕样式 / 修字幕重叠 / 修子进程乱码

- composer.py:抽出 _JIANGCHANG_SUBTITLE_STYLE 常量,FontSize 28→14 /
  Outline 2→2(保持),1080p 屏幕约占 1.3% 高度,演示视频留足画面呼吸感
- subtitle.py:generate_srt 加 post-process 排队,相邻字幕互相让位
  (MIN_DURATION=1.0s / GAP=0.1s),任意时刻屏幕上最多 1 条字幕,
  避免开头几秒密集触发的字幕叠成两行
- runner.py:subprocess.Popen 注入 PYTHONIOENCODING=utf-8 + PYTHONUTF8=1,
  让 Windows 子进程 Python 强制 UTF-8 输出,runner 端 UTF-8 解码即对齐,
  修中文乱码

所有 skill 录屏受益,向后兼容(非 Windows 系统 UTF-8 注入无副作用)。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-05-25 10:14:03 +08:00
parent c8d136fb79
commit ffb64b2cfc
3 changed files with 47 additions and 4 deletions

View File

@@ -7,6 +7,17 @@ import sys
from pathlib import Path
# 匠厂统一字幕样式 —— 所有 skill 录屏共用,做品牌一致性
# FontSize 141080p 屏幕约占 1.3% 高度,演示视频留足画面呼吸感
# Outline 214 号字配 Outline 3 会显胖2 已足够在浅色背景上保持可读
# 修改请评估对所有 skill 录屏的影响。
_JIANGCHANG_SUBTITLE_STYLE = (
"FontName=Arial,FontSize=14,"
"PrimaryColour=&H00FFFFFF,OutlineColour=&H00000000,"
"Outline=2,Shadow=1,Alignment=2"
)
def compose_video(
frames_dir: str,
fps: int,
@@ -32,9 +43,7 @@ def compose_video(
subtitle_filter = (
f"subtitles='{srt_path_str}'"
":force_style='FontName=Arial,FontSize=28,"
"PrimaryColour=&H00FFFFFF,OutlineColour=&H00000000,"
"Outline=2,Shadow=1,Alignment=2'"
f":force_style='{_JIANGCHANG_SUBTITLE_STYLE}'"
)
# 视频和音频都放进 filter_complex避免 -vf 与 -filter_complex 混用报错

View File

@@ -66,6 +66,13 @@ def run_screencast(
engine.set_start_time(time.time())
try:
# Windows 子进程 stdout 默认走系统 ANSI code page中文 Windows 是 cp936/GBK
# 这边用 encoding="utf-8" 解码会乱码。注入 PYTHONIOENCODING + PYTHONUTF8 让
# 子进程 Python 强制以 UTF-8 输出,两端编码对齐。非 Windows 默认就 UTF-8无副作用。
env = os.environ.copy()
env["PYTHONIOENCODING"] = "utf-8"
env["PYTHONUTF8"] = "1"
proc = subprocess.Popen(
[sys.executable, "-m", "pytest", *pytest_args],
stdout=subprocess.PIPE,
@@ -73,6 +80,7 @@ def run_screencast(
text=True,
encoding="utf-8",
errors="replace",
env=env,
)
assert proc.stdout is not None
for line in proc.stdout:

View File

@@ -40,6 +40,15 @@ class SubtitleEngine:
self._matched.add(keyword)
def generate_srt(self, output_path: str) -> None:
"""生成 SRT 文件,自动处理字幕重叠。
字幕重叠修复策略(避免屏幕上同时显示 2+ 条叠成两行):
- 字幕按 start 时间升序排序后;
- 相邻字幕保留 GAP=0.1s 间隔;
- 每条字幕保证至少 MIN_DURATION=1.0s 显示时间(短到这个值仍读不完是字幕脚本设计问题);
- 若当前条让位给下一条后剩余时间 < MIN_DURATION则把下一条 start 往后推。
这样任意时刻屏幕上最多 1 条字幕。
"""
def _fmt(s: float) -> str:
h = int(s // 3600)
m = int((s % 3600) // 60)
@@ -47,9 +56,26 @@ class SubtitleEngine:
ms = int((s % 1) * 1000)
return f"{h:02d}:{m:02d}:{sec:02d},{ms:03d}"
# 防重叠 post-process
MIN_DURATION = 1.0
GAP = 0.1
entries = sorted(self._entries, key=lambda e: e.start)
for i in range(len(entries) - 1):
cur, nxt = entries[i], entries[i + 1]
max_end = nxt.start - GAP
new_dur = max_end - cur.start
if new_dur < MIN_DURATION:
# 太挤cur 至少撑 MIN_DURATION 秒,把 nxt 推迟
cur.duration = MIN_DURATION
nxt.start = cur.start + MIN_DURATION + GAP
else:
# 正常让位cur 显示到 (nxt.start - GAP)
cur.duration = min(cur.duration, new_dur)
# 最后一条不需要让位,保持原 duration
Path(output_path).parent.mkdir(parents=True, exist_ok=True)
with open(output_path, "w", encoding="utf-8") as f:
for i, e in enumerate(self._entries, 1):
for i, e in enumerate(entries, 1):
f.write(f"{i}\n")
f.write(f"{_fmt(e.start)} --> {_fmt(e.start + e.duration)}\n")
f.write(f"{e.text}\n\n")