update: 2026-03-28 20:59

InfoGenie-frontend/scripts/tidy_profile_templates.py

@@ -0,0 +1,234 @@
+# -*- coding: utf-8 -*-
+"""筛选个人主页模板：删除非静态项，并按网页 title 重命名顶层文件夹。"""
+from __future__ import annotations
+
+import re
+import shutil
+import sys
+import uuid
+from pathlib import Path
+
+BASE = Path(
+    r"d:\SmyProjects\Frontend-Backend\InfoGenie\infogenie-frontend\public\toolbox\个人主页模板"
+)
+
+# 无 HTML 无法作为静态页；PHP 文件较多视为需服务端，非纯静态
+PHP_THRESHOLD = 5
+
+
+def count_html(root: Path) -> int:
+    n = 0
+    for p in root.rglob("*"):
+        if p.is_file() and p.suffix.lower() in (".html", ".htm"):
+            n += 1
+    return n
+
+
+def count_php(root: Path) -> int:
+    return sum(1 for p in root.rglob("*.php") if p.is_file())
+
+
+def extract_title_from_text(text: str) -> str | None:
+    for pattern in (
+        r"<title[^>]*>([^<]*)</title>",
+        r"<h1[^>]*>([^<]*)</h1>",
+    ):
+        m = re.search(pattern, text, re.I | re.DOTALL)
+        if m:
+            raw = m.group(1)
+            raw = re.sub(r"<[^>]+>", "", raw)
+            title = re.sub(r"\s+", " ", raw).strip()
+            title = re.sub(r'[<>:"/\\|?*]', "", title)
+            title = title.strip(" -_|")
+            if title and len(title) < 100:
+                return title
+    return None
+
+
+def read_html(path: Path) -> str:
+    for enc in ("utf-8", "utf-8-sig", "gbk", "gb2312"):
+        try:
+            return path.read_text(encoding=enc)
+        except (UnicodeDecodeError, OSError):
+            continue
+    return path.read_text(encoding="utf-8", errors="ignore")
+
+
+def find_entry_html(folder: Path) -> Path | None:
+    for name in ("index.html", "index.htm"):
+        for p in folder.rglob(name):
+            if p.is_file():
+                return p
+    for p in folder.rglob("*"):
+        if p.is_file() and p.suffix.lower() in (".html", ".htm"):
+            return p
+    return None
+
+
+def sanitize_folder_name(name: str) -> str:
+    for c in '<>:"/\\|?*':
+        name = name.replace(c, "")
+    name = name.strip(" .")
+    if len(name) > 120:
+        name = name[:120].rstrip()
+    return name or "未命名模板"
+
+
+def ps_single_quote(s: str) -> str:
+    return "'" + s.replace("'", "''") + "'"
+
+
+def write_rename_ps1(renames: list[tuple[str, str]], out_path: Path) -> None:
+    """两阶段重命名，避免 A→B 与 B→A 等占用冲突。"""
+    pairs = [(o, n) for o, n in renames if o != n]
+    tag = uuid.uuid4().hex[:8]
+    lines = [
+        "# 由 tidy_profile_templates.py 生成：关闭占用该目录的 IDE/资源管理器窗口后执行。",
+        "$ErrorActionPreference = 'Stop'",
+        f"$base = {ps_single_quote(str(BASE))}",
+        "",
+        "# 阶段 1：改为临时名",
+    ]
+    mids: list[tuple[str, str, str]] = []
+    for i, (old, new) in enumerate(pairs):
+        mid = f"__tmp_rename_{tag}_{i}__"
+        mids.append((old, mid, new))
+        lines.append(
+            f"Rename-Item -LiteralPath (Join-Path $base {ps_single_quote(old)}) "
+            f"-NewName {ps_single_quote(mid)}"
+        )
+    lines.extend(["", "# 阶段 2：改为最终名"])
+    for _old, mid, new in mids:
+        lines.append(
+            f"Rename-Item -LiteralPath (Join-Path $base {ps_single_quote(mid)}) "
+            f"-NewName {ps_single_quote(new)}"
+        )
+    out_path.write_text("\n".join(lines) + "\n", encoding="utf-8-sig")
+
+
+def compute_renames(remaining: list[Path]) -> list[tuple[str, str]]:
+    used: set[str] = {c.name for c in remaining}
+    renames: list[tuple[str, str]] = []
+    for folder in remaining:
+        entry = find_entry_html(folder)
+        if not entry:
+            continue
+        try:
+            text = read_html(entry)
+        except OSError:
+            continue
+        title = extract_title_from_text(text)
+        if not title:
+            continue
+        new_name = sanitize_folder_name(title)
+        if new_name == folder.name:
+            continue
+        final = new_name
+        if final in used and final != folder.name:
+            i = 2
+            while f"{new_name}-{i}" in used:
+                i += 1
+            final = f"{new_name}-{i}"
+        used.discard(folder.name)
+        used.add(final)
+        renames.append((folder.name, final))
+    return renames
+
+
+def main() -> None:
+    dry = "--apply" not in sys.argv
+    write_script = "--write-rename-script" in sys.argv
+    rename_only = "--rename-only" in sys.argv
+    script_path = Path(__file__).resolve().parent / "profile_template_renames.ps1"
+
+    if not BASE.is_dir():
+        print(f"Missing base: {BASE}")
+        sys.exit(1)
+
+    if rename_only:
+        remaining = sorted([c for c in BASE.iterdir() if c.is_dir()], key=lambda x: x.name)
+        renames = compute_renames(remaining)
+        write_rename_ps1(renames, script_path)
+        print(f"已写入重命名脚本: {script_path}")
+        print("请在关闭占用该文件夹的程序后，在 PowerShell 中执行:")
+        print(f"  powershell -ExecutionPolicy Bypass -File \"{script_path}\"")
+        return
+
+    children = [c for c in BASE.iterdir() if c.is_dir()]
+    to_delete: list[tuple[Path, str, int, int]] = []
+    for child in children:
+        h, p = count_html(child), count_php(child)
+        if h == 0:
+            to_delete.append((child, "no_html", h, p))
+        elif p >= PHP_THRESHOLD:
+            to_delete.append((child, "php_heavy", h, p))
+
+    print("=== 将删除（非静态或无可展示 HTML）===")
+    for path, reason, h, p in sorted(to_delete, key=lambda x: x[0].name):
+        print(f"  [{reason}] html={h} php={p}  {path.name}")
+
+    if dry:
+        print("\n[DRY RUN] 加参数 --apply 执行删除与重命名\n")
+
+    delete_set = {p for p, _, _, _ in to_delete}
+
+    if not dry:
+        for path, _, _, _ in to_delete:
+            shutil.rmtree(path, ignore_errors=False)
+            print(f"已删除: {path.name}")
+
+    # 重命名：dry-run 时排除即将删除的目录
+    remaining = sorted(
+        [c for c in BASE.iterdir() if c.is_dir() and (dry and c not in delete_set or not dry)],
+        key=lambda x: x.name,
+    )
+    renames = compute_renames(remaining)
+
+    print("=== 计划重命名（按页面 title）===")
+    for old, new in renames:
+        if old != new:
+            print(f"  {old}\n    -> {new}")
+
+    if dry:
+        if write_script:
+            write_rename_ps1(renames, script_path)
+            print(f"\n已写入重命名脚本: {script_path}")
+        return
+
+    write_rename_ps1(renames, script_path)
+    print(f"\n已写入重命名脚本（若本机重命名失败可手动执行）: {script_path}")
+
+    pairs = [(o, n) for o, n in renames if o != n]
+    tag = uuid.uuid4().hex[:8]
+    mids: list[tuple[str, str, str]] = []
+    for i, (old_name, new_name) in enumerate(pairs):
+        mid = f"__tmp_rename_{tag}_{i}__"
+        mids.append((old_name, mid, new_name))
+
+    for old_name, mid, new_name in mids:
+        src = BASE / old_name
+        dst = BASE / mid
+        if not src.is_dir():
+            continue
+        try:
+            src.rename(dst)
+        except OSError as e:
+            print(f"阶段1 重命名失败（可稍后运行脚本）: {old_name} -> {mid}  {e}")
+
+    for old_name, mid, new_name in mids:
+        src = BASE / mid
+        dst = BASE / new_name
+        if not src.is_dir():
+            continue
+        if dst.exists():
+            print(f"跳过（目标已存在）: {mid} -> {new_name}")
+            continue
+        try:
+            src.rename(dst)
+            print(f"重命名: {old_name} -> {new_name}")
+        except OSError as e:
+            print(f"阶段2 重命名失败（可稍后运行脚本）: {mid} -> {new_name}  {e}")
+
+
+if __name__ == "__main__":
+    main()