zcbot/skills/ppt/scripts/svg_preview.py

303 lines
13 KiB
Python

"""svg_preview.py: 把 SVG 页渲成 PNG 的可选预览工具(chromium 优先,cairosvg 兜底)。
SVG-first 管线里 SVG 就是视觉真相(导出的 pptx 与之 1:1),想直观看一眼版面时
渲 SVG 最忠实 —— 比渲最终 pptx 更早、更准地暴露观感问题。
注意:本脚本是**可选工具**,不再是交付管线的强制环节。页面正确性(越界 /
压字 / 错位 / 网格漂移)由 svg_quality_checker.py 的几何检测保证,并在导出
边界自动复跑 —— 交付不依赖渲图,渲图只服务"人想看效果"
用法:
python svg_preview.py <project_dir> # 渲 <project_dir> 全部页
python svg_preview.py <project_dir> --pages 1,3,5 # 只渲第 1/3/5 页(按文件排序)
python svg_preview.py <project_dir> -o <out_dir> # 指定 PNG 输出目录(默认 .build/preview)
python svg_preview.py <svg_dir_or_file> # 直接渲某个目录/单文件
约定:优先渲 <project_dir>/.build/svg_final(图标/配图已内嵌);没有则渲
svg_output(图标占位符会由 cairosvg 路径就地展开)。
渲染器:找得到 Chrome/Edge/Chromium 就用无头浏览器(保真度最高);找不到、
或浏览器对某页渲染失败,自动回退 cairosvg(装了的话)。产物默认 2x 超采样。
"""
from __future__ import annotations
import argparse
import re
import subprocess
import sys
try: # zcbot: Windows GBK 控制台兼容,避免 emoji/© 等触发 UnicodeEncodeError
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
sys.stderr.reconfigure(encoding="utf-8", errors="replace")
except Exception:
pass
import tempfile
import os
import shutil
from pathlib import Path
_CHROME_CANDIDATES = [
r"C:\Program Files\Google\Chrome\Application\chrome.exe",
r"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe",
r"C:\Program Files\Microsoft\Edge\Application\msedge.exe",
r"C:\Program Files (x86)\Microsoft\Edge\Application\msedge.exe",
]
# Linux / zcbot sandbox: the image ships chromium at /usr/bin/chromium (installed
# for mermaid-cli). The original ppt-master discovery only knew Windows
# chrome/edge, so SVG preview always failed inside the container. Mirror the
# discovery zcbot already uses in rendering/pdf.py so it resolves the bundled
# chromium instead.
_LINUX_CANDIDATES = [
"/usr/bin/chromium", "/usr/bin/chromium-browser",
"/usr/bin/google-chrome", "/usr/bin/google-chrome-stable",
]
_WHICH_NAMES = (
"chrome", "chrome.exe", "msedge", "msedge.exe",
"chromium", "chromium-browser", "google-chrome", "google-chrome-stable",
)
def find_browser() -> str | None:
"""Return a chromium/chrome/edge executable path, or None if none found.
Returns None (not raise) so the caller can fall back to the cairosvg
renderer when no browser exists (e.g. a sandbox image built without the
chromium layer).
"""
# Explicit override first (matches rendering/pdf.py's CHROMIUM/CHROME env).
env = os.environ.get("CHROMIUM") or os.environ.get("CHROME")
if env and (shutil.which(env) or Path(env).exists()):
return shutil.which(env) or env
for c in _CHROME_CANDIDATES + _LINUX_CANDIDATES:
if Path(c).exists():
return c
for name in _WHICH_NAMES:
p = shutil.which(name)
if p:
return p
return None
def find_cairosvg():
"""Return the cairosvg module, or None if not importable."""
try:
import cairosvg
return cairosvg
except Exception:
return None
_VIEWBOX_RE = re.compile(r'viewBox\s*=\s*["\']\s*([\d.]+)\s+([\d.]+)\s+([\d.]+)\s+([\d.]+)\s*["\']')
_WH_RE = re.compile(r'\b(width|height)\s*=\s*["\']\s*([\d.]+)')
def _dims(svg_text: str) -> tuple[float, float]:
m = _VIEWBOX_RE.search(svg_text)
if m:
return float(m.group(3)), float(m.group(4))
w = h = None
for name, val in _WH_RE.findall(svg_text):
if name == "width":
w = float(val)
elif name == "height":
h = float(val)
return (w or 1280.0), (h or 720.0)
def _wrap_html(svg_path: Path, w: float, h: float) -> str:
# 内联引用本地 svg,固定画布尺寸、去边距,Chrome 截图即得整页
uri = svg_path.resolve().as_uri()
return (
"<!doctype html><html><head><meta charset='utf-8'><style>"
"html,body{margin:0;padding:0;background:#fff}"
f"img{{display:block;width:{w}px;height:{h}px}}"
"</style></head><body>"
f"<img src='{uri}'>"
"</body></html>"
)
def render(browser: str, svg_path: Path, out_png: Path, scale: float = 2.0) -> bool:
"""Render one SVG to PNG via headless chromium. Returns True on success.
On failure prints a concise warning with the chromium stderr tail (the
original code silenced stderr, so a broken render looked identical to a
missing browser — impossible to diagnose). The caller keeps going so one
bad page doesn't abort the whole batch.
"""
svg_text = svg_path.read_text(encoding="utf-8", errors="ignore")
w, h = _dims(svg_text)
html = _wrap_html(svg_path, w, h)
# chromium resolves --screenshot against its own cwd, not ours; a relative
# path silently fails to write ("系统找不到指定的路径"). Always pass absolute.
out_png = out_png.resolve()
out_png.parent.mkdir(parents=True, exist_ok=True)
# TemporaryDirectory holds both the wrapper HTML and a throwaway
# --user-data-dir; auto-cleaned on exit.
with tempfile.TemporaryDirectory(prefix="svgprev-") as tmp:
html_path = Path(tmp) / "page.html"
html_path.write_text(html, encoding="utf-8")
proc = subprocess.run(
[
browser, "--headless", "--disable-gpu", "--no-sandbox",
# Required in the cap-dropped sandbox: chromium's own setuid
# sandbox can't start (--no-sandbox), and the container's 64MB
# /dev/shm is too small (--disable-dev-shm-usage), else chromium
# crashes mid-render. Same flags rendering/pdf.py uses.
"--disable-dev-shm-usage", "--user-data-dir=%s" % (Path(tmp) / "cr"),
"--hide-scrollbars", "--force-device-scale-factor=%s" % scale,
"--window-size=%d,%d" % (round(w), round(h)),
"--default-background-color=FFFFFFFF",
"--screenshot=%s" % str(out_png),
html_path.as_uri(),
],
stdout=subprocess.DEVNULL, stderr=subprocess.PIPE, timeout=120, check=False,
)
if out_png.exists() and out_png.stat().st_size > 0:
return True
tail = (proc.stderr or b"").decode("utf-8", "replace").strip()[-400:]
print(f" [warn] chromium 渲染失败 {svg_path.name}(rc={proc.returncode})"
+ (f": {tail}" if tail else ""))
return False
def _collect(target: Path) -> tuple[list[Path], Path]:
"""返回 (svg 文件列表, 默认输出目录)。"""
from project_utils import svg_final_dir, preview_dir
if target.is_file() and target.suffix.lower() == ".svg":
return [target], preview_dir(target.parent)
# 目录:优先 .build/svg_final(finalize 后图标/配图已内嵌,渲出来最忠实);
# 没有就退而渲 svg_output(cairosvg 兜底会就地展开图标,chromium 直接渲则
# 图标仍是占位符不显示)。
sf = svg_final_dir(target)
if sf.is_dir() and any(sf.glob("*.svg")):
svg_dir = sf
elif (target / "svg_output").is_dir():
svg_dir = target / "svg_output"
else:
svg_dir = target
return sorted(svg_dir.glob("*.svg")), preview_dir(target)
def _select(files: list[Path], pages: str | None) -> list[Path]:
if not pages:
return files
idxs = []
for tok in pages.split(","):
tok = tok.strip()
if tok.isdigit():
idxs.append(int(tok) - 1)
return [files[i] for i in idxs if 0 <= i < len(files)]
def _expand_icons_for_cairo(svg_text: str) -> str:
"""Expand `<use data-icon>` placeholders to real `<g><path>` in-memory.
cairosvg does not understand the `data-icon` placeholder and errors on the
href-less `<use>` (observed: CAIRO_STATUS_INVALID_MATRIX on every icon-bearing
page). Reuse finalize's exact regex embedder so the fallback rasterizes the
same icons the native exporter draws. No-op when the SVG carries no
placeholders (e.g. already-finalized svg_final/).
"""
if 'data-icon' not in svg_text:
return svg_text
try:
from svg_finalize.embed_icons import process_svg_file, DEFAULT_ICONS_DIR
except Exception:
return svg_text # can't expand — let cairosvg try as-is
try:
import contextlib
import io as _io
with tempfile.TemporaryDirectory(prefix="svgprev-ico-") as tmp:
f = Path(tmp) / "x.svg"
f.write_text(svg_text, encoding="utf-8")
# Silence the embedder's per-file "[OK] x.svg (N icons)" chatter —
# the temp name is meaningless in preview output.
with contextlib.redirect_stdout(_io.StringIO()):
process_svg_file(f, DEFAULT_ICONS_DIR, dry_run=False, verbose=False,
fallback_dir=DEFAULT_ICONS_DIR)
return f.read_text(encoding="utf-8")
except Exception:
return svg_text
def render_cairosvg(cairosvg, svg_path: Path, out_png: Path, scale: float = 2.0) -> bool:
"""Rasterize one SVG via cairosvg (browser-free fallback). Returns True on success.
Icons are pre-expanded so cairosvg doesn't choke on `<use data-icon>`.
Fidelity is slightly below chromium (no JS, limited filter support), but it
lets preview run in a sandbox image built without chromium — or one whose
chromium crashes at runtime.
"""
svg_text = _expand_icons_for_cairo(
svg_path.read_text(encoding="utf-8", errors="ignore"))
out_png = out_png.resolve()
out_png.parent.mkdir(parents=True, exist_ok=True)
try:
cairosvg.svg2png(bytestring=svg_text.encode("utf-8"),
write_to=str(out_png), scale=scale)
except Exception as e:
print(f" [warn] cairosvg 渲染失败 {svg_path.name}: {e}")
return False
return out_png.exists() and out_png.stat().st_size > 0
def main() -> None:
ap = argparse.ArgumentParser(description="把 SVG 页渲成 PNG(可选预览工具)")
ap.add_argument("target", type=Path, help="project_dir / svg 目录 / 单个 .svg 文件")
ap.add_argument("--pages", default=None, help="只渲指定页,如 1,3,5(按文件排序)")
ap.add_argument("-o", "--out", type=Path, default=None, help="PNG 输出目录")
ap.add_argument("--scale", type=float, default=2.0, help="超采样倍数,默认 2")
args = ap.parse_args()
files, default_out = _collect(args.target)
if not files:
raise SystemExit(f"[fatal] 没找到 SVG:{args.target}")
all_count = len(files)
files = _select(files, args.pages)
if not files:
raise SystemExit(f"[fatal] --pages {args.pages} 没选中任何页(共 {all_count} 页)")
out_dir = args.out or default_out
# Renderer: prefer a real browser (chromium — highest fidelity, matches the
# native pptx); cairosvg covers both "no browser at all" and "browser found
# but crashes at render time" (seen with the sandbox chromium) — a found
# browser that can't render must not be a dead end.
browser = find_browser()
cairo = find_cairosvg()
if browser:
print(f"[svg_preview] browser={browser}"
+ ("" if cairo else " (无 cairosvg 兜底)"))
elif cairo:
print("[svg_preview] 未找到 chromium → 用 cairosvg 渲染(图标已预展开;"
"保真度略低于 chromium。装 chromium 或设 CHROMIUM 可用浏览器渲染)")
else:
raise SystemExit(
"[fatal] 未找到 Chrome / Edge / Chromium,也无 cairosvg。这是环境/镜像"
"问题:沙箱镜像应自带 /usr/bin/chromium(需 rebuild sandbox 镜像),"
"本机可设 CHROMIUM 环境变量指向浏览器。渲图只是可选预览,不阻塞"
"质检与导出 —— 请把本报错如实告知用户,不要在会话内安装渲染依赖。")
ok = 0
fell_back = 0
for svg in files:
png = out_dir / (svg.stem + ".png")
done = render(browser, svg, png, scale=args.scale) if browser else False
if not done and cairo:
if browser:
fell_back += 1
done = render_cairosvg(cairo, svg, png, scale=args.scale)
if done:
ok += 1
print(f" [ok] {svg.name} -> {png}")
else:
print(f" [FAIL] {svg.name} 未生成 PNG")
if fell_back:
print(f"[svg_preview] {fell_back} 页浏览器渲染失败,已回退 cairosvg")
print(f"[svg_preview] {ok}/{len(files)} 页渲好,输出目录:{out_dir}")
if ok < len(files):
raise SystemExit(1)
if __name__ == "__main__":
main()