from __future__ import annotations import argparse import re from collections import defaultdict from dataclasses import dataclass from datetime import datetime from pathlib import Path SCRIPT_DIR = Path(__file__).resolve().parent DOC_ROOT = SCRIPT_DIR.parent if SCRIPT_DIR.name == "_tools" else SCRIPT_DIR REPO_ROOT = DOC_ROOT.parents[1] INCLUDE_ROOT = REPO_ROOT / "engine" / "include" PUBLIC_INCLUDE_ROOT = INCLUDE_ROOT / "XCEngine" PARALLEL_ROOT = DOC_ROOT / "XCEngine" META_ROOT = DOC_ROOT / "_meta" DEFAULT_REPORT = META_ROOT / "rebuild-status.md" HEADER_RE = re.compile(r"^\*\*头文件\*\*:\s*`([^`]+\.h)`", re.MULTILINE) NAMESPACE_RE = re.compile(r"^\*\*命名空间\*\*:\s*`[^`]+`", re.MULTILINE) TYPE_RE = re.compile(r"^\*\*类型\*\*:\s*`[^`]+`", re.MULTILINE) DESCRIPTION_RE = re.compile(r"^\*\*描述\*\*:\s*.+$", re.MULTILINE) MD_LINK_RE = re.compile(r"\[([^\]]+)\]\(([^)]+)\)") LEGACY_SECTION_RE = re.compile(r"^## (Syntax|Remarks|See Also|Examples)$", re.MULTILINE) FENCED_CODE_BLOCK_RE = re.compile(r"```.*?```", re.DOTALL) @dataclass class ModuleCoverage: module: str public_headers: int documented_headers: int @property def missing_headers(self) -> int: return self.public_headers - self.documented_headers def normalize_rel_path(path: str) -> str: return path.replace("\\", "/") def iter_markdown_files() -> list[Path]: return sorted( path for path in DOC_ROOT.rglob("*.md") if path.name != DEFAULT_REPORT.name ) def iter_canonical_markdown_files() -> list[Path]: return sorted( path for path in PARALLEL_ROOT.rglob("*.md") ) def iter_public_headers() -> list[str]: return sorted( normalize_rel_path(path.relative_to(INCLUDE_ROOT).as_posix()) for path in PUBLIC_INCLUDE_ROOT.rglob("*.h") ) def iter_public_include_dirs() -> list[str]: dirs = ["XCEngine"] dirs.extend( f"XCEngine/{path.relative_to(PUBLIC_INCLUDE_ROOT).as_posix()}" for path in sorted(PUBLIC_INCLUDE_ROOT.rglob("*")) if path.is_dir() ) return dirs def dir_index_name(relative: str) -> str: return f"{Path(relative).name}.md" def dir_index_doc_path(relative: str) -> Path: return DOC_ROOT / relative / dir_index_name(relative) def resolve_md_target(source: Path, target: str) -> Path: clean = target.split("#", 1)[0].replace("\\", "/") return (source.parent / clean).resolve() def strip_fenced_code_blocks(content: str) -> str: return FENCED_CODE_BLOCK_RE.sub("", content) def is_dir_index_page(page: Path) -> bool: if not page.is_relative_to(PARALLEL_ROOT): return False if page.stem != page.parent.name: return False relative_dir = page.parent.relative_to(PARALLEL_ROOT) source_dir = PUBLIC_INCLUDE_ROOT / relative_dir return source_dir.exists() and source_dir.is_dir() def is_flat_header_page(page: Path, rel_page: str) -> bool: if not rel_page.startswith("XCEngine/"): return False if is_dir_index_page(page): return False return (INCLUDE_ROOT / Path(rel_page).with_suffix(".h")).exists() def collect_doc_state(report_path: Path) -> dict[str, object]: markdown_files = iter_markdown_files() canonical_markdown_files = iter_canonical_markdown_files() public_headers = iter_public_headers() public_include_dirs = iter_public_include_dirs() declared_header_refs: set[str] = set() valid_header_refs: set[str] = set() canonical_valid_header_refs: set[str] = set() invalid_header_refs: list[tuple[str, str]] = [] broken_md_links: list[tuple[str, str]] = [] non_md_relative_links: list[tuple[str, str]] = [] old_template_pages: list[str] = [] flat_header_pages: list[str] = [] metadata_counts = { "namespace": 0, "type": 0, "description": 0, "header": 0, } for page in markdown_files: rel_page = normalize_rel_path(page.relative_to(DOC_ROOT).as_posix()) content = page.read_text(encoding="utf-8") is_canonical_page = rel_page.startswith("XCEngine/") if is_canonical_page and NAMESPACE_RE.search(content): metadata_counts["namespace"] += 1 if is_canonical_page and TYPE_RE.search(content): metadata_counts["type"] += 1 if is_canonical_page and DESCRIPTION_RE.search(content): metadata_counts["description"] += 1 if is_canonical_page and HEADER_RE.search(content): metadata_counts["header"] += 1 if is_canonical_page and LEGACY_SECTION_RE.search(content): old_template_pages.append(rel_page) if is_flat_header_page(page, rel_page): flat_header_pages.append(rel_page) for match in HEADER_RE.finditer(content): header = normalize_rel_path(match.group(1)) declared_header_refs.add(header) if (INCLUDE_ROOT / header).exists(): valid_header_refs.add(header) if is_canonical_page: canonical_valid_header_refs.add(header) elif is_canonical_page: invalid_header_refs.append((rel_page, header)) if is_canonical_page or rel_page.startswith(("_meta/", "_tools/")): link_scan_content = strip_fenced_code_blocks(content) for _, target in MD_LINK_RE.findall(link_scan_content): if target.startswith(("http://", "https://", "mailto:", "#")): continue normalized = target.replace("\\", "/") if normalized.endswith(".md") or ".md#" in normalized: resolved = resolve_md_target(page, normalized) if not resolved.exists() and resolved != report_path.resolve(): broken_md_links.append((rel_page, target)) continue non_md_relative_links.append((rel_page, target)) public_by_module: dict[str, list[str]] = defaultdict(list) documented_by_module: dict[str, set[str]] = defaultdict(set) for header in public_headers: module = header.split("/", 2)[1] public_by_module[module].append(header) for header in canonical_valid_header_refs: if not header.startswith("XCEngine/"): continue module = header.split("/", 2)[1] documented_by_module[module].add(header) module_coverages = [ ModuleCoverage( module=module, public_headers=len(headers), documented_headers=len(documented_by_module.get(module, set())), ) for module, headers in sorted(public_by_module.items()) ] missing_headers = [ header for header in public_headers if header not in canonical_valid_header_refs ] missing_parallel_indexes = [ relative for relative in public_include_dirs if not dir_index_doc_path(relative).exists() ] support_top_dirs = sorted( path.name for path in DOC_ROOT.iterdir() if path.is_dir() and path.name in {"_meta", "_tools"} ) return { "generated_at": datetime.now(), "markdown_files": markdown_files, "canonical_markdown_files": canonical_markdown_files, "public_headers": public_headers, "public_include_dirs": public_include_dirs, "declared_header_refs": sorted(declared_header_refs), "valid_header_refs": sorted(valid_header_refs), "canonical_valid_header_refs": sorted(canonical_valid_header_refs), "invalid_header_refs": invalid_header_refs, "broken_md_links": broken_md_links, "non_md_relative_links": non_md_relative_links, "old_template_pages": sorted(old_template_pages), "flat_header_pages": sorted(flat_header_pages), "missing_headers": missing_headers, "module_coverages": module_coverages, "metadata_counts": metadata_counts, "support_top_dirs": support_top_dirs, "missing_parallel_indexes": missing_parallel_indexes, } def format_pairs_table(headers: tuple[str, str], rows: list[tuple[str, str]]) -> list[str]: output = [ f"| {headers[0]} | {headers[1]} |", "|------|------|", ] for left, right in rows: output.append(f"| `{left}` | `{right}` |") return output def build_report(state: dict[str, object]) -> str: generated_at: datetime = state["generated_at"] # type: ignore[assignment] markdown_files: list[Path] = state["markdown_files"] # type: ignore[assignment] canonical_markdown_files: list[Path] = state["canonical_markdown_files"] # type: ignore[assignment] public_headers: list[str] = state["public_headers"] # type: ignore[assignment] public_include_dirs: list[str] = state["public_include_dirs"] # type: ignore[assignment] valid_header_refs: list[str] = state["valid_header_refs"] # type: ignore[assignment] canonical_valid_header_refs: list[str] = state["canonical_valid_header_refs"] # type: ignore[assignment] invalid_header_refs: list[tuple[str, str]] = state["invalid_header_refs"] # type: ignore[assignment] broken_md_links: list[tuple[str, str]] = state["broken_md_links"] # type: ignore[assignment] non_md_relative_links: list[tuple[str, str]] = state["non_md_relative_links"] # type: ignore[assignment] old_template_pages: list[str] = state["old_template_pages"] # type: ignore[assignment] flat_header_pages: list[str] = state["flat_header_pages"] # type: ignore[assignment] missing_headers: list[str] = state["missing_headers"] # type: ignore[assignment] module_coverages: list[ModuleCoverage] = state["module_coverages"] # type: ignore[assignment] metadata_counts: dict[str, int] = state["metadata_counts"] # type: ignore[assignment] support_top_dirs: list[str] = state["support_top_dirs"] # type: ignore[assignment] missing_parallel_indexes: list[str] = state["missing_parallel_indexes"] # type: ignore[assignment] lines: list[str] = [] lines.append("# API 文档重构状态") lines.append("") lines.append(f"**生成时间**: `{generated_at.strftime('%Y-%m-%d %H:%M:%S')}`") lines.append("") lines.append("**来源**: `docs/api/_tools/audit_api_docs.py`") lines.append("") lines.append("## 摘要") lines.append("") lines.append(f"- Markdown 页面数（全部）: `{len(markdown_files)}`") lines.append(f"- Markdown 页面数（canonical）: `{len(canonical_markdown_files)}`") lines.append(f"- Public headers 数: `{len(public_headers)}`") lines.append(f"- 有效头文件引用数（全部）: `{len(valid_header_refs)}`") lines.append(f"- 有效头文件引用数（canonical）: `{len(canonical_valid_header_refs)}`") lines.append(f"- 无效头文件引用数: `{len(invalid_header_refs)}`") lines.append(f"- 失效 `.md` 链接数: `{len(broken_md_links)}`") lines.append(f"- 非 `.md` 相对链接数: `{len(non_md_relative_links)}`") lines.append(f"- 旧模板页面数: `{len(old_template_pages)}`") lines.append(f"- 扁平 header 页面数: `{len(flat_header_pages)}`") lines.append("") lines.append("## 平行目录") lines.append("") lines.append(f"- Canonical 根目录: `{PARALLEL_ROOT.relative_to(DOC_ROOT).as_posix()}`") lines.append(f"- 源码目录节点数: `{len(public_include_dirs)}`") lines.append( f"- 已生成目录总览页节点数: `{len(public_include_dirs) - len(missing_parallel_indexes)}`" ) lines.append(f"- 缺失目录总览页节点数: `{len(missing_parallel_indexes)}`") if support_top_dirs: lines.append(f"- 支撑目录: `{', '.join(support_top_dirs)}`") lines.append("") lines.append("## 模块覆盖") lines.append("") lines.append("| 模块 | Public headers | 已覆盖 | 未覆盖 |") lines.append("|------|----------------|--------|--------|") for coverage in module_coverages: lines.append( f"| `{coverage.module}` | `{coverage.public_headers}` | " f"`{coverage.documented_headers}` | `{coverage.missing_headers}` |" ) lines.append("") lines.append("## 元信息覆盖") lines.append("") lines.append("| 字段 | 页面数 |") lines.append("|------|--------|") lines.append(f"| `命名空间` | `{metadata_counts['namespace']}` |") lines.append(f"| `类型` | `{metadata_counts['type']}` |") lines.append(f"| `描述` | `{metadata_counts['description']}` |") lines.append(f"| `头文件` | `{metadata_counts['header']}` |") lines.append("") if missing_parallel_indexes: lines.append("## 缺失的平行目录总览页") lines.append("") for relative in missing_parallel_indexes: lines.append(f"- `{relative}`") lines.append("") if invalid_header_refs: lines.append("## 无效头文件引用") lines.append("") lines.extend(format_pairs_table(("文档", "头文件"), invalid_header_refs[:50])) lines.append("") if broken_md_links: lines.append("## 失效 Markdown 链接") lines.append("") lines.extend(format_pairs_table(("文档", "目标"), broken_md_links[:50])) lines.append("") if non_md_relative_links: lines.append("## 非 `.md` 相对链接") lines.append("") lines.extend(format_pairs_table(("文档", "目标"), non_md_relative_links[:50])) lines.append("") if old_template_pages: lines.append("## 旧模板页面") lines.append("") for page in old_template_pages[:80]: lines.append(f"- `{page}`") if len(old_template_pages) > 80: lines.append(f"- 其余 `{len(old_template_pages) - 80}` 个页面请直接运行脚本查看。") lines.append("") if flat_header_pages: lines.append("## 扁平 header 页面") lines.append("") for page in flat_header_pages[:120]: lines.append(f"- `{page}`") if len(flat_header_pages) > 120: lines.append(f"- 其余 `{len(flat_header_pages) - 120}` 个页面请直接运行脚本查看。") lines.append("") if missing_headers: lines.append("## 未覆盖的 public headers") lines.append("") for header in missing_headers[:120]: lines.append(f"- `{header}`") if len(missing_headers) > 120: lines.append(f"- 其余 `{len(missing_headers) - 120}` 个 header 请直接运行脚本查看。") lines.append("") return "\n".join(lines).rstrip() + "\n" def main() -> int: parser = argparse.ArgumentParser(description="Audit XCEngine API documentation.") parser.add_argument( "--report", default=str(DEFAULT_REPORT), help="Markdown report output path.", ) args = parser.parse_args() report_path = Path(args.report) report_path.parent.mkdir(parents=True, exist_ok=True) state = collect_doc_state(report_path) report_path.write_text(build_report(state), encoding="utf-8") print(f"Markdown pages (all): {len(state['markdown_files'])}") print(f"Markdown pages (canonical): {len(state['canonical_markdown_files'])}") print(f"Public headers: {len(state['public_headers'])}") print(f"Valid header refs (all): {len(state['valid_header_refs'])}") print(f"Valid header refs (canonical): {len(state['canonical_valid_header_refs'])}") print(f"Invalid header refs: {len(state['invalid_header_refs'])}") print(f"Broken .md links: {len(state['broken_md_links'])}") print(f"Non-.md relative links: {len(state['non_md_relative_links'])}") print(f"Old template pages: {len(state['old_template_pages'])}") print(f"Flat header pages: {len(state['flat_header_pages'])}") print(f"Missing directory index pages: {len(state['missing_parallel_indexes'])}") print(f"Report written to: {report_path}") return 0 if __name__ == "__main__": raise SystemExit(main())