"""svg_preview.py: 用无头 Chrome/Edge 把 SVG 页渲成 PNG,供交付前肉眼/vision 验收。 SVG-first 管线里 SVG 就是视觉真相(导出的 pptx 与之 1:1),所以验收直接渲 SVG 最忠实 —— 比渲最终 pptx 更早、更准地暴露"标题层级 / 卡片过挤过空 / 文字掉色 / 节奏单调"这类观感问题。 用法: python svg_preview.py # 渲 /svg_output 全部页 python svg_preview.py --pages 1,3,5 # 只渲第 1/3/5 页(按文件排序) python svg_preview.py -o # 指定 PNG 输出目录(默认 /preview) python svg_preview.py # 直接渲某个目录/单文件 约定:优先渲 /svg_output;没有则退而渲 本身。 依赖:本机装了 Chrome 或 Edge(无需 pip 包)。两者都没有则报错退出。 产物默认 2x 超采样,够清晰看版面。 渲 project 目录时同步维护 `.build/acceptance.json` 验收记录(每页:源 sha1 + 渲染时间 + verdict)。看完 PNG 后用 accept_pages.py 标 pass/fail;svg_to_pptx 的导出 gate 要求每页 verdict=pass 且源文件此后未改动 —— "从没渲过就交付"和 "改了页不复看"都会被导出边界挡下。 """ from __future__ import annotations import argparse import hashlib import json import re import subprocess import sys from datetime import datetime 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 _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 ( "" f"" "" ) 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] 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, Path | None, str]: """返回 (svg 文件列表, 默认输出目录, project_root 或 None, 渲染来源标签)。 project_root 非 None 时(target 是标准 project 目录),渲染结束后会把每页 写进 `.build/acceptance.json` 验收记录 —— 导出 gate 依赖它。 """ from project_utils import svg_final_dir, preview_dir if target.is_file() and target.suffix.lower() == ".svg": return [target], preview_dir(target.parent), None, "file" # 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(生成中验收 —— 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, source = sf, "svg_final" elif (target / "svg_output").is_dir(): svg_dir, source = target / "svg_output", "svg_output" else: svg_dir, source = target, "dir" files = sorted(svg_dir.glob("*.svg")) root = target if source in ("svg_final", "svg_output") else None return files, preview_dir(target), root, source def _sha1(path: Path) -> str: return hashlib.sha1(path.read_bytes()).hexdigest() def acceptance_path(project_root: Path) -> Path: return project_root / ".build" / "acceptance.json" def load_acceptance(project_root: Path) -> dict: p = acceptance_path(project_root) if p.exists(): try: data = json.loads(p.read_text(encoding="utf-8")) if isinstance(data, dict) and isinstance(data.get("pages"), dict): return data except (json.JSONDecodeError, OSError): pass # 损坏就重建 —— 记录本身可再生 return {"version": 1, "pages": {}} def save_acceptance(project_root: Path, data: dict) -> Path: p = acceptance_path(project_root) p.parent.mkdir(parents=True, exist_ok=True) p.write_text(json.dumps(data, ensure_ascii=False, indent=1), encoding="utf-8") return p def record_renders(project_root: Path, source: str, rendered: list[tuple[Path, Path]]) -> None: """把本轮渲好的页写进验收记录(merge,verdict 归 pending)。 每条记录锚定 svg_output 源文件的 sha1:accept_pages 标 pass、导出 gate 放行 都要求源文件此后未再改动 —— 改一页就必须重渲重看那一页,盲改混不过去。 源比渲染对象新(改了 svg_output 没重跑 finalize)的页跳过不记,并提示。 """ data = load_acceptance(project_root) pages = data["pages"] now = datetime.now().isoformat(timespec="seconds") stale: list[str] = [] def rel(p: Path) -> str: # 存相对项目根的路径,项目目录整个挪走记录仍有效;跨盘等场景退绝对路径 try: return str(p.resolve().relative_to(project_root.resolve())) except ValueError: return str(p.resolve()) for svg, png in rendered: src = project_root / "svg_output" / svg.name if not src.exists(): src = svg if source == "svg_final" and src.stat().st_mtime > svg.stat().st_mtime + 1: stale.append(svg.stem) continue sha = _sha1(src) old = pages.get(svg.stem) or {} keep_verdict = old.get("verdict") if old.get("source_sha1") == sha else None pages[svg.stem] = { "png": rel(png), "source": rel(src), "source_sha1": sha, "rendered_from": source, "rendered_at": now, "verdict": keep_verdict or "pending", **({"verdict_at": old["verdict_at"]} if keep_verdict and old.get("verdict_at") else {}), } p = save_acceptance(project_root, data) if stale: print(f" [warn] {len(stale)} 页的 svg_output 比 .build/svg_final 新," f"渲的是旧版、未记入验收:{', '.join(stale[:8])}" f"{' …' if len(stale) > 8 else ''} —— 先重跑 finalize_svg 再渲。") pending = sum(1 for v in pages.values() if v.get("verdict") != "pass") print(f"[svg_preview] 验收记录已更新:{p}(pending {pending} 页)") print(" 下一步:read/look_at_image 逐页过目,再用 accept_pages.py 标记 " "--pass <页名…> / --pass-all;导出 gate 只认 pass 且源未改动的页。") 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 `` placeholders to real `` in-memory. cairosvg does not understand the `data-icon` placeholder and errors on the href-less `` (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 ``. Fidelity is slightly below chromium (no JS, limited filter support), but it lets visual acceptance run in a sandbox image built without chromium. """ 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 供肉眼/vision 验收") 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, project_root, source = _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). Fall back to cairosvg when no browser exists (sandbox image # built without the chromium layer) so visual acceptance still runs. browser = find_browser() cairo = None if browser: print(f"[svg_preview] browser={browser}") else: try: import cairosvg cairo = cairosvg print("[svg_preview] 未找到 chromium → 回退 cairosvg(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)") except Exception: raise SystemExit( "[fatal] 未找到 Chrome / Edge / Chromium,也无 cairosvg 兜底。" "沙箱镜像应自带 /usr/bin/chromium(rebuild sandbox 镜像)," "或 `pip install cairosvg`,或设 CHROMIUM 环境变量。") done: list[tuple[Path, Path]] = [] for svg in files: png = out_dir / (svg.stem + ".png") if browser: render(browser, svg, png, scale=args.scale) else: render_cairosvg(cairo, svg, png, scale=args.scale) if png.exists(): done.append((svg, png)) print(f" [ok] {svg.name} -> {png}") else: print(f" [FAIL] {svg.name} 未生成 PNG") print(f"[svg_preview] {len(done)}/{len(files)} 页渲好,输出目录:{out_dir}") if project_root is not None and done: record_renders(project_root, source, done) if __name__ == "__main__": main()