test: 补充测试覆盖率 — DB/CLI/Search/Ingest + 修复 chromadb 异常兼容

tests/test_cli.py

@@ -61,3 +61,21 @@ class TestCLIJSONOutput:
         if result.stdout.strip():
             data = json.loads(result.stdout)
             assert isinstance(data, dict)
+
+
+def test_ingest_help():
+    """ingest --help 正常输出."""
+    result = runner.invoke(app, ["ingest", "--help"])
+    assert result.exit_code == 0
+
+
+def test_search_help():
+    """search --help 正常输出."""
+    result = runner.invoke(app, ["search", "--help"])
+    assert result.exit_code == 0
+
+
+def test_export_help():
+    """export --help 正常输出."""
+    result = runner.invoke(app, ["export", "--help"])
+    assert result.exit_code == 0

tests/test_db.py

@@ -45,3 +45,33 @@ class TestVectorDB:
         # 再次获取会创建新的
         col = db.get_or_create_collection("tmp_col")
         assert col.count() == 0
+
+
+def test_write_guard_context_manager(tmp_path):
+    """write_guard 上下文管理器正常获取和释放锁."""
+    from src.core.db import VectorDB
+    vdb = VectorDB(persist_dir=str(tmp_path))
+    with vdb.write_guard():
+        pass
+
+
+def test_close(tmp_path):
+    """close 正常执行不抛异常."""
+    from src.core.db import VectorDB
+    vdb = VectorDB(persist_dir=str(tmp_path))
+    vdb.close()
+
+
+def test_delete_collection_nonexistent(tmp_path):
+    """删除不存在的 collection 不抛异常."""
+    from src.core.db import VectorDB
+    vdb = VectorDB(persist_dir=str(tmp_path))
+    vdb.delete_collection("nonexistent-collection-12345")
+
+
+def test_delete_by_source_no_match(tmp_path):
+    """删除不存在的 source 返回 False."""
+    from src.core.db import VectorDB
+    vdb = VectorDB(persist_dir=str(tmp_path))
+    result = vdb.delete_by_source("test_col", "no-such-file.md")
+    assert result is False

tests/test_ingest.py

@@ -286,3 +286,38 @@ class TestIncrementalIngest:
         count2 = ingestor.ingest_file(str(file), incremental=True, force=True)
         assert count1 > 0
         assert count2 > 0  # force 模式重新入库
+
+
+def test_ingest_content_default_splitter(tmp_path):
+    """未指定 splitter 时用 MarkdownSplitter."""
+    from src.core.config import EmbedConfig
+    from src.core.db import VectorDB
+    from src.core.embedder import create_embedder
+    from src.core.ingest import DocumentIngestor
+
+    db = VectorDB(persist_dir=str(tmp_path / "db"))
+    embedder = create_embedder(EmbedConfig(mode="local"))
+    ingestor = DocumentIngestor(db, 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(tmp_path):
+    """ingest_directory 递归处理子目录."""
+    from src.core.config import EmbedConfig, ChunkConfig
+    from src.core.db import VectorDB
+    from src.core.embedder import create_embedder
+    from src.core.ingest import DocumentIngestor
+
+    (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")
+    db = VectorDB(persist_dir=str(tmp_path / "db_r"))
+    embedder = create_embedder(EmbedConfig(mode="local"))
+    ingestor = DocumentIngestor(
+        db, 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())

tests/test_search.py

@@ -122,3 +122,25 @@ class TestSearcher:
         searcher = Searcher(db, embedder, "empty_coll")
         sources = searcher.list_sources()
         assert sources == []
+
+
+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() == []