{{ r.content?.substring(0, 300) }}{{ r.content?.length > 300 ? '...' : '' }}
{{ ingestResult }}
| 名称 | Chunks |
|---|---|
| {{ c.name }} | {{ c.count }} |
{{ JSON.stringify(health.checks, null, 2) }}
段落A。
段落B。
" result = s.split(html, source_file="test.html") assert len(result) >= 1 assert "段落A" in result[0]["content"] def test_html_splitter_strips_script_style(): """去除 script 和 style 标签.""" from src.core.splitters.html import HTMLSplitter s = HTMLSplitter(max_size=500, overlap=50) html = "可见内容。
" result = s.split(html, source_file="test.html") assert "alert" not in result[0]["content"] assert "可见内容" in result[0]["content"] def test_html_splitter_empty(): """空 HTML 返回空列表.""" from src.core.splitters.html import HTMLSplitter s = HTMLSplitter() result = s.split("", source_file="empty.html") assert result == [] ``` - [ ] **Step 3: 补充 EPUB splitter 测试** ```python # 在 tests/test_splitters_epub.py 追加： def test_epub_splitter_creation(): """EPUBSplitter 创建正常.""" from src.core.splitters.epub import EPUBSplitter s = EPUBSplitter(max_size=500, overlap=50) assert s is not None def test_epub_splitter_file_not_found(): """不存在的文件抛出 ValueError.""" from src.core.splitters.epub import EPUBSplitter s = EPUBSplitter() import pytest with pytest.raises(ValueError): s.split(source="/nonexistent/file.epub", source_file="test.epub") ``` - [ ] **Step 4: 补充 CLI 测试** ```python # 在 tests/test_cli.py 追加： def test_ingest_help(cli_app): """ingest --help 正常.""" result = cli_app(["ingest", "--help"]) assert result.exit_code == 0 def test_search_no_results(cli_app, tmp_path): """空 collection 搜索返回提示.""" result = cli_app(["search", "测试查询", "-c", str(tmp_path / "cfg.yaml")]) # 可能返回 0（只是无结果）或出错 assert result.exit_code in (0, 1) def test_stats_empty(cli_app, tmp_path): """空 collection 的 stats.""" result = cli_app(["stats", "-c", str(tmp_path / "cfg.yaml")]) assert result.exit_code == 0 def test_stats_json(cli_app, tmp_path): """stats --json 输出.""" result = cli_app(["stats", "--json", "-c", str(tmp_path / "cfg.yaml")]) assert result.exit_code == 0 ``` - [ ] **Step 5: 补充 DB 测试** ```python # 在 tests/test_db.py 追加： def test_write_guard_context_manager(db): """write_guard 上下文管理器.""" with db.write_guard(): pass # 应正常获取和释放锁 def test_close(db): """close 正常执行.""" db.close() # close 后不应对 client 做任何操作，测试仅验证不抛异常 def test_delete_collection_nonexistent(db): """删除不存在的 collection 不抛异常.""" db.delete_collection("nonexistent-collection-12345") # 应静默处理 def test_delete_by_source_no_match(db): """删除不存在的 source 返回 False.""" result = db.delete_by_source("test_col", "no-such-file.md") assert result is False ``` - [ ] **Step 6: 补充搜索测试** ```python # 在 tests/test_search.py 追加： def test_list_sources_empty(): """空 collection 的 list_sources 返回空列表.""" from src.core.search import Searcher class EmptyColl: def count(self): return 0 def get(self, **kwargs): return {"ids": [], "documents": [], "metadatas": []} class EmptyDB: def get_or_create_collection(self, name): return EmptyColl() def list_collections(self): return [] class FakeEmb: @property def dimension(self): return 4 def embed(self, texts): return [[0.0]*4] s = Searcher(EmptyDB(), FakeEmb(), "empty") assert s.list_sources() == [] ``` - [ ] **Step 7: 补充 ingest 测试** ```python # 在 tests/test_ingest.py 追加： def test_ingest_file_returns_zero_for_dir(db, local_embedder, tmp_path: Path): """目录路径应被 ingest_directory 而非 ingest_file 处理.""" ingestor = DocumentIngestor(db, local_embedder, "test_ingest_dir") d = tmp_path / "subdir" d.mkdir() # ingest_file 不应处理目录 result = ingestor.ingest_file(str(d)) assert result == 0 # 目录不是文件，跳过 def test_ingest_file_markdown(db, local_embedder, tmp_path: Path): """MD 文件入库返回正确的 chunk 数.""" file = tmp_path / "hello.md" file.write_text("# 标题\n\n内容段落。", encoding="utf-8") ingestor = DocumentIngestor( db, local_embedder, "test_md", chunk_config=ChunkConfig(max_size=1000, overlap=100), ) count = ingestor.ingest_file(str(file)) assert count >= 1 def test_ingest_content_default_splitter(db, local_embedder): """未指定 splitter 时用 MarkdownSplitter.""" ingestor = DocumentIngestor(db, local_embedder, "test_content") count = ingestor.ingest_content("# 测试\n\n一些内容。", "test.md") assert count >= 1 def test_ingest_directory_recursive(db, local_embedder, tmp_path: Path): """ingest_directory 递归处理子目录.""" (tmp_path / "sub").mkdir() (tmp_path / "a.md").write_text("# A\n\n内容A。", encoding="utf-8") (tmp_path / "sub" / "b.md").write_text("# B\n\n内容B。", encoding="utf-8") ingestor = DocumentIngestor( db, local_embedder, "test_recurse", chunk_config=ChunkConfig(max_size=1000, overlap=100), ) results = ingestor.ingest_directory(str(tmp_path)) assert len(results) >= 2 assert all(v > 0 for v in results.values()) ``` - [ ] **Step 8: 运行全部测试并验证覆盖率** ```bash uv run pytest tests/ --cov=src --cov-report=term-missing -v ``` 预期: ≥ 80% 覆盖率 - [ ] **Step 9: Commit** ```bash git add tests/ git commit -m "test: 补充测试覆盖率至 80%+（PDF/HTML/EPUB/CLI/DB/Search/Ingest）" ``` --- ### Task 6: CORS 和安全配置修复 **Files:** - Modify: `src/server/app.py` - [ ] **Step 1: 修复 CORS 配置** 将 `allow_credentials` 改为 `False`： ```python app.add_middleware( CORSMiddleware, allow_origins=os.environ.get("CORS_ORIGINS", "http://localhost:3000").split(","), allow_credentials=False, # 修复：原来是 True allow_methods=["GET", "POST", "DELETE", "OPTIONS"], allow_headers=["Content-Type", "Authorization", "X-API-Key"], ) ``` - [ ] **Step 2: 更新 .env.example 添加 CORS 说明** ``` # CORS 允许的源列表（逗号分隔） CORS_ORIGINS=http://localhost:3000,http://localhost:5173 ``` - [ ] **Step 3: 测试 CORS 中间件** ```bash uv run pytest tests/test_api.py -v -k "cors or health" ``` - [ ] **Step 4: Commit** ```bash git add src/server/app.py .env.example git commit -m "fix: 修复 CORS allow_credentials 配置，更新 .env.example" ``` --- ### Task 7: 更新 README 和文档 **Files:** - Modify: `README.md` - [ ] **Step 1: 更新 README 功能特性和新命令说明** 在 README 的功能特性列表追加： ```markdown - **Web 管理界面**: 内置 Vue 3 单页管理面板，可视化搜索、入库、查看集合 - **数据导出**: 支持 JSON/CSV 导出 collection 全量数据 - **多格式扩展**: 新增 .docx 支持（通过 markitdown 库） ``` 在 CLI 命令参考表中追加： ```markdown | `export -o <文件> -f