chore: ruff lint 修复 + 第一优先级全部完成

src/cli/main.py

@@ -1,10 +1,10 @@
 """命令行工具入口 — 可作为 MCP tool 直接调用."""
-from pathlib import Path
-import sys
+import glob as _glob
 import io
 import json
 import os
-import glob as _glob
+import sys
+from pathlib import Path
 from typing import Annotated
 
 import typer
@@ -18,7 +18,7 @@ sys.path.insert(0, str(Path(__file__).parent.parent))
 
 from src.core.config import DEFAULT_CONFIG_PATH
 from src.core.security import is_safe_cli_path
-from src.server.deps import get_state, get_default_collection
+from src.server.deps import get_default_collection, get_state
 
 app = typer.Typer(
     name="md-vector-db",
@@ -63,8 +63,12 @@ def ingest(
         typer.Argument(help="Markdown 文件路径 (可多个, 或 - 从标准输入读取)"),
     ] = None,
     name: Annotated[str | None, typer.Option("--name", help="标准输入模式下的虚拟文件名")] = None,
-    incremental: Annotated[bool, typer.Option("--incremental", help="增量模式：跳过未变更文件")] = False,
-    force: Annotated[bool, typer.Option("--force", help="强制重新入库（忽略增量检查）")] = False,
+    incremental: Annotated[
+        bool, typer.Option("--incremental", help="增量模式：跳过未变更文件")
+    ] = False,
+    force: Annotated[
+        bool, typer.Option("--force", help="强制重新入库（忽略增量检查）")
+    ] = False,
     config: ConfigOpt = DEFAULT_CONFIG_PATH,
     collection: CollectionOpt = None,
 ):

src/core/config.py

@@ -5,9 +5,8 @@ import os
 from dataclasses import dataclass, field
 from pathlib import Path
 
-from dotenv import load_dotenv
-
 import yaml
+from dotenv import load_dotenv
 
 # 加载 .env 文件 (若存在)
 load_dotenv()

src/core/embedder.py

@@ -17,9 +17,9 @@
 
     vectors = batch_embed(embedder, long_text_list)
 """
+import logging
 import os
 import threading
-import logging
 from typing import Protocol
 
 from src.core.config import EmbedConfig

src/core/ingest.py

@@ -1,14 +1,13 @@
 """Markdown 文档解析与入库模块."""
 import logging
-import re
 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.markdown import MarkdownSplitter  # 兼容旧 import 路径
 from src.core.splitters.registry import SUPPORTED_SUFFIXES, get_splitter
 
 logger = logging.getLogger("md-vector-db")
@@ -40,7 +39,7 @@ class DocumentIngestor:
     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）。
+        根据扩展名自动选择 Splitter（.md/.txt/.pdf/.html/.epub 等）。
         使用文件路径的 SHA256 前 12 位 + 文件名作为唯一标识。
 
         Args:

src/core/search.py

@@ -161,7 +161,9 @@ class Searcher:
         all_data = self.collection.get(include=["documents", "metadatas"])
         output = io.StringIO()
         writer = csv.writer(output)
-        writer.writerow(["id", "content", "source_file", "section_title", "heading_level", "chunk_index"])
+        writer.writerow([
+            "id", "content", "source_file", "section_title", "heading_level", "chunk_index",
+        ])
         if all_data and all_data["ids"]:
             for i, doc_id in enumerate(all_data["ids"]):
                 meta = all_data["metadatas"][i] if all_data["metadatas"] else {}

src/core/splitters/__init__.py

@@ -1,12 +1,12 @@
 """文档分块器包 — 支持 Markdown / 纯文本 / PDF / HTML / EPUB."""
 
-from src.core.splitters.base import Splitter, BaseTextSplitter
-from src.core.splitters.markdown import MarkdownSplitter
-from src.core.splitters.text import TextSplitter
-from src.core.splitters.pdf import PDFSplitter
-from src.core.splitters.html import HTMLSplitter
+from src.core.splitters.base import BaseTextSplitter, Splitter
 from src.core.splitters.epub import EPUBSplitter
-from src.core.splitters.registry import get_splitter, register_splitter, SUPPORTED_SUFFIXES
+from src.core.splitters.html import HTMLSplitter
+from src.core.splitters.markdown import MarkdownSplitter
+from src.core.splitters.pdf import PDFSplitter
+from src.core.splitters.registry import SUPPORTED_SUFFIXES, get_splitter, register_splitter
+from src.core.splitters.text import TextSplitter
 
 __all__ = [
     "Splitter",

src/core/splitters/epub.py

@@ -1,5 +1,6 @@
 """EPUB 电子书分块器 — 使用 ebooklib 提取文字后委托 TextSplitter."""
 import logging
+
 from src.core.splitters.text import TextSplitter
 
 logger = logging.getLogger("md-vector-db")

src/core/splitters/html.py

@@ -1,5 +1,6 @@
 """HTML 文档分块器 — 使用 BeautifulSoup 去标签后委托 TextSplitter."""
 import logging
+
 from src.core.splitters.text import TextSplitter
 
 logger = logging.getLogger("md-vector-db")

src/core/splitters/markdown.py

@@ -1,5 +1,6 @@
 """Markdown 文档分块器."""
 import re
+
 from src.core.splitters.base import BaseTextSplitter
 
 

src/core/splitters/pdf.py

@@ -1,5 +1,6 @@
 """PDF 文档分块器 — 使用 pymupdf 提取文字后委托 TextSplitter."""
 import logging
+
 from src.core.splitters.text import TextSplitter
 
 logger = logging.getLogger("md-vector-db")

src/core/splitters/registry.py

@@ -1,5 +1,6 @@
 """Splitter 注册表 — 按文件扩展名自动选择分块器."""
 from pathlib import Path
+
 from src.core.splitters.base import Splitter
 
 # 扩展名 → Splitter 类名映射

src/server/app.py

@@ -1,20 +1,19 @@
 """FastAPI 服务层."""
+import logging
 import os
 import time
 import uuid
-import logging
+from contextlib import asynccontextmanager
 from pathlib import Path
 
-from contextlib import asynccontextmanager
-
-from fastapi import FastAPI, HTTPException, Depends, Request, Query
+from fastapi import Depends, FastAPI, HTTPException, Query, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import RedirectResponse
 from pydantic import BaseModel, Field, model_validator
 
 from src.core.security import is_path_within_workspace
-from src.server.auth import verify_api_key, rate_limiter
-from src.server.deps import get_state, AppState
+from src.server.auth import rate_limiter, verify_api_key
+from src.server.deps import AppState, get_state
 
 logger = logging.getLogger("md-vector-db")
 

src/server/auth.py

@@ -1,9 +1,9 @@
 """API 认证与安全中间件."""
 import hmac
-import os
-import time
-import threading
 import logging
+import os
+import threading
+import time
 from collections import defaultdict
 
 from fastapi import Header, HTTPException, Request

src/server/deps.py

@@ -1,7 +1,7 @@
 """FastAPI 依赖注入 — 集中管理应用状态, 替代模块级全局变量."""
+import logging
 import os
 import threading
-import logging
 
 from src.core.config import load_config
 from src.core.db import VectorDB

tests/test_auth.py

@@ -1,11 +1,11 @@
 """认证与速率限制测试."""
-import time
 import threading
+import time
 
 import pytest
 from fastapi import HTTPException
 
-from src.server.auth import verify_api_key, RateLimiter
+from src.server.auth import RateLimiter, verify_api_key
 
 
 class TestVerifyApiKey:

tests/test_cli.py

@@ -1,5 +1,6 @@
 """CLI 命令测试."""
 from typer.testing import CliRunner
+
 from src.cli.main import app
 
 runner = CliRunner()

tests/test_config.py

@@ -1,11 +1,8 @@
 """配置加载模块测试."""
-import os
 import tempfile
 from pathlib import Path
 
-import pytest
-
-from src.core.config import AppConfig, EmbedConfig, ChunkConfig, load_config
+from src.core.config import AppConfig, EmbedConfig, load_config
 
 
 class TestEmbedConfig:

tests/test_db.py

@@ -1,5 +1,4 @@
 """数据库层测试."""
-import gc
 import tempfile
 from pathlib import Path
 

tests/test_deps.py

@@ -1,10 +1,7 @@
 """AppState 和依赖注入测试."""
-import os
-import tempfile
 
 import pytest
 
-from src.core.config import load_config
 from src.server.deps import AppState
 
 

tests/test_embedder.py

@@ -3,8 +3,12 @@ import pytest
 
 from src.core.config import EmbedConfig
 from src.core.embedder import (
-    LocalEmbedder, OpenAIEmbedder, DashscopeEmbedder,
-    create_embedder, batch_embed, SUPPORTED_PROVIDERS,
+    SUPPORTED_PROVIDERS,
+    DashscopeEmbedder,
+    LocalEmbedder,
+    OpenAIEmbedder,
+    batch_embed,
+    create_embedder,
 )
 
 

tests/test_ingest.py

@@ -4,8 +4,8 @@ from pathlib import Path
 
 import pytest
 
-from src.core.splitters import MarkdownSplitter
 from src.core.ingest import DocumentIngestor
+from src.core.splitters import MarkdownSplitter
 
 
 class TestMarkdownSplitter:
@@ -122,7 +122,6 @@ class TestIngestorIntegration:
         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))
         embedder = create_embedder(EmbedConfig(mode="local"))
@@ -137,13 +136,12 @@ class TestIngestorIntegration:
         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))
         embedder = create_embedder(EmbedConfig(mode="local"))
         ingestor = DocumentIngestor(db, embedder, "test_dedup")
 
-        c1 = ingestor.ingest_content("# A", "dup.md")
+        ingestor.ingest_content("# A", "dup.md")
         c2 = ingestor.ingest_content("# B", "dup.md")
         assert ingestor.collection.count() == c2
 
@@ -156,7 +154,6 @@ class TestIngestFile:
         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")
@@ -174,7 +171,6 @@ class TestIngestFile:
         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")
@@ -195,7 +191,6 @@ class TestIngestDirectory:
         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")
@@ -213,7 +208,6 @@ class TestIngestDirectory:
         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"))
@@ -228,10 +222,9 @@ class TestIncrementalIngest:
 
     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.config import ChunkConfig, EmbedConfig
         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"
@@ -251,10 +244,9 @@ class TestIncrementalIngest:
 
     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.config import ChunkConfig, EmbedConfig
         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"
@@ -275,10 +267,9 @@ class TestIncrementalIngest:
 
     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.config import ChunkConfig, EmbedConfig
         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"

tests/test_reranker.py

@@ -1,5 +1,4 @@
 """重排序器测试."""
-import pytest
 
 from src.core.reranker import Reranker
 

tests/test_security.py

@@ -1,5 +1,4 @@
 """is_safe_path 路径遍历防护测试."""
-import pytest
 from src.core.security import is_safe_path
 
 

tests/test_splitters.py

@@ -1,6 +1,11 @@
 """Splitter 注册表和 TextSplitter 测试."""
-import pytest
-from src.core.splitters import TextSplitter, MarkdownSplitter, get_splitter, register_splitter, SUPPORTED_SUFFIXES
+from src.core.splitters import (
+    SUPPORTED_SUFFIXES,
+    MarkdownSplitter,
+    TextSplitter,
+    get_splitter,
+    register_splitter,
+)
 
 
 class TestTextSplitter:

tests/test_splitters_epub.py

@@ -28,9 +28,10 @@ class TestEPUBSplitter:
 
     def test_split_simple_epub(self, tmp_path):
         """用 ebooklib 创建一个简单 EPUB 并测试分块."""
-        from src.core.splitters.epub import EPUBSplitter
         from ebooklib import epub
 
+        from src.core.splitters.epub import EPUBSplitter
+
         epub_path = tmp_path / "test.epub"
 
         book = epub.EpubBook()

tests/test_splitters_markdown.py

@@ -1,5 +1,6 @@
 """MarkdownSplitter 边界测试."""
 import pytest
+
 from src.core.splitters import MarkdownSplitter
 
 

tests/test_splitters_pdf.py

@@ -1,6 +1,6 @@
 """PDFSplitter 测试."""
+
 import pytest
-from pathlib import Path
 
 pymupdf = pytest.importorskip("fitz", reason="pymupdf 未安装")
 
@@ -10,9 +10,10 @@ class TestPDFSplitter:
 
     def test_split_simple_pdf(self, tmp_path):
         """用 pymupdf 创建一个简单 PDF 并测试分块."""
-        from src.core.splitters.pdf import PDFSplitter
         import fitz
 
+        from src.core.splitters.pdf import PDFSplitter
+
         pdf_path = tmp_path / "test.pdf"
         doc = fitz.open()
         # 插入纯 ASCII 文本避免 CJK 字体编码问题
@@ -29,9 +30,10 @@ class TestPDFSplitter:
 
     def test_empty_pdf(self, tmp_path):
         """空 PDF（有页但无文字）返回空列表."""
-        from src.core.splitters.pdf import PDFSplitter
         import fitz
 
+        from src.core.splitters.pdf import PDFSplitter
+
         pdf_path = tmp_path / "empty.pdf"
         doc = fitz.open()
         doc.new_page()  # pymupdf 必须有至少一页才能保存