feat: 新增数据导出功能和 CLI export 命令（JSON/CSV）

src/cli/main.py

@@ -222,5 +222,30 @@ def stats(
             typer.echo(f"  - {s}")
 
 
+@app.command(help="导出 collection 数据为 JSON 或 CSV.")
+def export(
+    output: Annotated[str, typer.Option("--output", "-o", help="输出文件路径")],
+    fmt: Annotated[
+        str, typer.Option("--format", "-f", help="导出格式: json | csv")
+    ] = "json",
+    config: ConfigOpt = DEFAULT_CONFIG_PATH,
+    collection: CollectionOpt = None,
+):
+    """导出 collection 数据."""
+    _init_config(config)
+    state = get_state()
+    searcher = state.get_searcher(_resolve_collection(collection))
+
+    if fmt == "json":
+        searcher.export_json(file_path=output)
+    elif fmt == "csv":
+        searcher.export_csv(file_path=output)
+    else:
+        typer.echo(f"错误: 不支持的格式 '{fmt}'，可选: json, csv", err=True)
+        raise typer.Exit(code=1)
+
+    typer.echo(f"[OK] 已导出到: {output}")
+
+
 if __name__ == "__main__":
     app()

tests/test_export.py

@@ -0,0 +1,106 @@
+"""导出功能测试."""
+import csv
+import io
+import json
+
+import pytest
+
+from src.core.search import Searcher
+
+
+class FakeExportCollection:
+    def count(self):
+        return 2
+
+    def get(self, include=None):
+        return {
+            "ids": ["doc_0", "doc_1"],
+            "documents": ["内容A。\n\n段落B。", "内容C。"],
+            "metadatas": [
+                {"source_file": "a.md", "section_title": "标题A", "heading_level": 1, "chunk_index": 0},
+                {"source_file": "b.md", "section_title": "", "heading_level": 0, "chunk_index": 0},
+            ],
+        }
+
+
+class FakeExportDB:
+    def get_or_create_collection(self, name):
+        return FakeExportCollection()
+
+    def list_collections(self):
+        return []
+
+
+class FakeExportEmbedder:
+    @property
+    def dimension(self):
+        return 4
+
+    def embed(self, texts):
+        return [[0.1, 0.2, 0.3, 0.4] for _ in texts]
+
+
+@pytest.fixture
+def searcher():
+    db = FakeExportDB()
+    embedder = FakeExportEmbedder()
+    return Searcher(db, embedder, "test_export")
+
+
+def test_export_json_returns_valid_json(searcher):
+    """export_json 返回合法的 JSON 字符串."""
+    output = searcher.export_json()
+    data = json.loads(output)
+    assert isinstance(data, list)
+    assert len(data) == 2
+
+
+def test_export_json_contains_all_fields(searcher):
+    """导出包含所有必要字段."""
+    output = searcher.export_json()
+    data = json.loads(output)
+    first = data[0]
+    assert "id" in first
+    assert "content" in first
+    assert "source_file" in first
+    assert "section_title" in first
+
+
+def test_export_csv_returns_valid_csv(searcher):
+    """export_csv 返回合法的 CSV 字符串."""
+    output = searcher.export_csv()
+    reader = csv.DictReader(io.StringIO(output))
+    rows = list(reader)
+    assert len(rows) == 2
+
+
+def test_export_csv_has_header(searcher):
+    """CSV 包含表头."""
+    output = searcher.export_csv()
+    reader = csv.DictReader(io.StringIO(output))
+    assert reader.fieldnames is not None
+    assert "content" in reader.fieldnames
+    assert "source_file" in reader.fieldnames
+
+
+def test_export_empty_collection():
+    """空 collection 导出空列表."""
+
+    class EmptyCollection:
+        def count(self):
+            return 0
+        def get(self, include=None):
+            return {"ids": [], "documents": [], "metadatas": []}
+
+    class EmptyDB:
+        def get_or_create_collection(self, name):
+            return EmptyCollection()
+        def list_collections(self):
+            return []
+
+    s = Searcher(EmptyDB(), FakeExportEmbedder(), "empty")
+    json_out = s.export_json()
+    assert json.loads(json_out) == []
+    csv_out = s.export_csv()
+    lines = csv_out.strip().split("\n")
+    assert len(lines) == 1  # 仅表头