feat: DocumentIngestor 支持增量入库（FileTracker）

src/core/ingest.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from src.core.config import ChunkConfig
 from src.core.db import VectorDB
 from src.core.embedder import Embedder, batch_embed
+from src.core.file_tracker import FileTracker
 from src.core.splitters.markdown import MarkdownSplitter  # 兼容旧 import 路径
 from src.core.splitters.base import Splitter  # 兼容旧 import 路径
 from src.core.splitters.registry import SUPPORTED_SUFFIXES, get_splitter
@@ -23,28 +24,41 @@ class DocumentIngestor:
         collection_name: str,
         splitter: Splitter | None = None,
         chunk_config: ChunkConfig | None = None,
+        file_tracker: FileTracker | None = None,
     ):
         self.db = db
         self.embedder = embedder
         self.collection_name = collection_name
         self.splitter = splitter or MarkdownSplitter()
         self.chunk_config = chunk_config or ChunkConfig()
+        self.file_tracker = file_tracker  # None = 不使用增量功能
 
     @property
     def collection(self):
         return self.db.get_or_create_collection(self.collection_name)
 
-    def ingest_file(self, file_path: str) -> int:
+    def ingest_file(self, file_path: str, incremental: bool = False, force: bool = False) -> int:
         """入库单个文件, 返回 chunk 数量.
 
         根据文件扩展名自动选择 Splitter（.md→MarkdownSplitter, .txt→TextSplitter, .pdf→PDFSplitter 等）。
         使用文件路径的 SHA256 前 12 位 + 文件名作为唯一标识。
+
+        Args:
+            file_path: 文件路径
+            incremental: 启用增量模式（需 file_tracker 已注入）
+            force: 强制重新入库（忽略增量检查）
         """
         import hashlib
         path = Path(file_path).resolve()
         path_hash = hashlib.sha256(str(path).encode()).hexdigest()[:12]
         file_name = f"{path_hash}_{path.name}"
 
+        # 增量模式：检查是否需要重新入库
+        if incremental and not force and self.file_tracker is not None:
+            if not self.file_tracker.is_stale(str(path)):
+                logger.debug("跳过未变更文件: %s", path.name)
+                return 0
+
         splitter = self.splitter or get_splitter(
             file_path,
             max_size=self.chunk_config.max_size,
@@ -55,10 +69,16 @@ class DocumentIngestor:
         suffix = path.suffix.lower()
         if suffix in (".pdf", ".epub"):
             chunks = splitter.split(str(path), source_file=file_name)
-            return self._add_chunks(chunks, file_name)
+            result = self._add_chunks(chunks, file_name)
+        else:
+            content = path.read_text(encoding="utf-8")
+            result = self._ingest_with_splitter(content, file_name, splitter)
 
-        content = path.read_text(encoding="utf-8")
+        # 入库成功后更新 tracker
-        return self._ingest_with_splitter(content, file_name, splitter)
+        if self.file_tracker is not None:
+            self.file_tracker.mark_ingested(str(path))
+
+        return result
 
     def _ingest_with_splitter(self, content: str, file_name: str, splitter) -> int:
         """分块 + 嵌入 + 入库（文本文件通用路径）."""

tests/test_ingest.py

@@ -221,3 +221,77 @@ class TestIngestDirectory:
 
         results = ingestor.ingest_directory(str(tmp_path))
         assert results == {}
+
+
+class TestIncrementalIngest:
+    """增量入库测试."""
+
+    def test_ingest_file_incremental_skips_unchanged(self, tmp_path):
+        """增量模式: 未修改的文件跳过入库."""
+        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
+        from src.core.file_tracker import FileTracker
+
+        file = tmp_path / "stable.md"
+        file.write_text("# 稳定文档\n\n内容不变。", encoding="utf-8")
+        tracker_path = str(tmp_path / "tracker.json")
+        db = VectorDB(persist_dir=str(tmp_path / "db"))
+        embedder = create_embedder(EmbedConfig(mode="local"))
+        ingestor = DocumentIngestor(
+            db, embedder, "test_incr",
+            chunk_config=ChunkConfig(max_size=1000, overlap=100),
+            file_tracker=FileTracker(tracker_path),
+        )
+        count1 = ingestor.ingest_file(str(file), incremental=True)
+        assert count1 > 0
+        count2 = ingestor.ingest_file(str(file), incremental=True)
+        assert count2 == 0  # 跳过
+
+    def test_ingest_file_incremental_reingests_modified(self, tmp_path):
+        """增量模式: 修改后的文件重新入库."""
+        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
+        from src.core.file_tracker import FileTracker
+
+        file = tmp_path / "changing.md"
+        file.write_text("# v1\n\n初始版本的内容段落。", encoding="utf-8")
+        tracker_path = str(tmp_path / "tracker2.json")
+        db = VectorDB(persist_dir=str(tmp_path / "db2"))
+        embedder = create_embedder(EmbedConfig(mode="local"))
+        ingestor = DocumentIngestor(
+            db, embedder, "test_incr2",
+            chunk_config=ChunkConfig(max_size=1000, overlap=100),
+            file_tracker=FileTracker(tracker_path),
+        )
+        count1 = ingestor.ingest_file(str(file), incremental=True)
+        assert count1 > 0
+        file.write_text("# v2\n\n新增段落，内容完全不同了。", encoding="utf-8")
+        count2 = ingestor.ingest_file(str(file), incremental=True)
+        assert count2 > 0
+
+    def test_ingest_file_force_mode_always_reingests(self, tmp_path):
+        """force=True 时始终重新入库（忽略 tracker）."""
+        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
+        from src.core.file_tracker import FileTracker
+
+        file = tmp_path / "force.md"
+        file.write_text("# force test\n\n这是强制入库测试的内容。", encoding="utf-8")
+        tracker_path = str(tmp_path / "tracker3.json")
+        db = VectorDB(persist_dir=str(tmp_path / "db3"))
+        embedder = create_embedder(EmbedConfig(mode="local"))
+        ingestor = DocumentIngestor(
+            db, embedder, "test_force",
+            chunk_config=ChunkConfig(max_size=1000, overlap=100),
+            file_tracker=FileTracker(tracker_path),
+        )
+        count1 = ingestor.ingest_file(str(file), incremental=True)
+        count2 = ingestor.ingest_file(str(file), incremental=True, force=True)
+        assert count1 > 0
+        assert count2 > 0  # force 模式重新入库