test: 补充 ingest_file 和 ingest_directory 的测试覆盖

Co-Authored-By: Claude <noreply@anthropic.com>

tests/test_ingest.py

@@ -146,3 +146,78 @@ class TestIngestorIntegration:
         c1 = ingestor.ingest_content("# A", "dup.md")
         c2 = ingestor.ingest_content("# B", "dup.md")
         assert ingestor.collection.count() == c2
+
+
+class TestIngestFile:
+    """ingest_file 方法测试."""
+
+    def test_ingest_file_markdown(self, tmp_path):
+        """通过文件路径入库 .md 文件."""
+        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
+
+        md_file = tmp_path / "hello.md"
+        md_file.write_text("# 测试\n这是测试内容。", encoding="utf-8")
+
+        db = VectorDB(persist_dir=str(tmp_path / "db"))
+        embedder = create_embedder(EmbedConfig(mode="local"))
+        ingestor = DocumentIngestor(db, embedder, "test_file")
+
+        count = ingestor.ingest_file(str(md_file))
+        assert count > 0
+        assert ingestor.collection.count() == count
+
+    def test_ingest_file_text(self, tmp_path):
+        """通过文件路径入库 .txt 文件."""
+        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
+
+        txt_file = tmp_path / "notes.txt"
+        txt_file.write_text("这是一段纯文本内容。\n\n第二段内容在这里。", encoding="utf-8")
+
+        db = VectorDB(persist_dir=str(tmp_path / "db"))
+        embedder = create_embedder(EmbedConfig(mode="local"))
+        ingestor = DocumentIngestor(db, embedder, "test_txt")
+
+        count = ingestor.ingest_file(str(txt_file))
+        assert count > 0
+
+
+class TestIngestDirectory:
+    """ingest_directory 方法测试."""
+
+    def test_ingest_directory_mixed_formats(self, tmp_path):
+        """入库包含多种格式的目录."""
+        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
+
+        (tmp_path / "a.md").write_text("# A\n内容 A", encoding="utf-8")
+        (tmp_path / "b.txt").write_text("内容 B", encoding="utf-8")
+        (tmp_path / "not_supported.xyz").write_text("不应被处理", encoding="utf-8")
+
+        db = VectorDB(persist_dir=str(tmp_path / "db"))
+        embedder = create_embedder(EmbedConfig(mode="local"))
+        ingestor = DocumentIngestor(db, embedder, "test_dir")
+
+        results = ingestor.ingest_directory(str(tmp_path))
+        assert len(results) >= 2  # a.md + b.txt, .xyz 被忽略
+
+    def test_ingest_directory_empty(self, tmp_path):
+        """空目录返回空结果."""
+        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_empty_dir")
+
+        results = ingestor.ingest_directory(str(tmp_path))
+        assert results == {}