refactor: 将核心代码迁移到 scripts 目录

- 创建 scripts/ 目录作为核心代码根目录
- 移动 core/, readers/, utils/ 到 scripts/ 下
- 移动 config.py, lyxy_document_reader.py 到 scripts/
- 移动 encoding_detection.py 到 scripts/utils/
- 更新 pyproject.toml 中的入口点路径和 pytest 配置
- 更新所有内部导入语句为 scripts.* 模块
- 更新 README.md 目录结构说明
- 更新 openspec/config.yaml 添加目录结构说明
- 删除无用的 main.py

此变更使项目结构更清晰，便于区分核心代码与测试、文档等支撑文件。

README.md

@@ -108,21 +108,26 @@ else:
 
 ```
 lyxy-document/
-├── lyxy_document_reader.py    # 统一 CLI 入口
+├── scripts/                    # 核心代码目录
-├── core/                       # 核心模块
+│   ├── lyxy_document_reader.py # 统一 CLI 入口
-│   ├── exceptions.py           # 自定义异常体系
+│   ├── config.py               # 统一配置类
-│   ├── markdown.py             # Markdown 工具函数
+│   ├── core/                   # 核心模块
-│   └── parser.py               # 统一解析调度器
+│   │   ├── exceptions.py       # 自定义异常体系
-├── readers/                    # 格式阅读器
+│   │   ├── markdown.py         # Markdown 工具函数
-│   ├── base.py                 # Reader 基类
+│   │   └── parser.py           # 统一解析调度器
-│   ├── docx/                   # DOCX 阅读器
+│   ├── readers/                # 格式阅读器
-│   ├── xlsx/                   # XLSX 阅读器
+│   │   ├── base.py             # Reader 基类
-│   ├── pptx/                   # PPTX 阅读器
+│   │   ├── docx/               # DOCX 阅读器
-│   ├── pdf/                    # PDF 阅读器
+│   │   ├── xlsx/               # XLSX 阅读器
-│   └── html/                   # HTML/URL 阅读器
+│   │   ├── pptx/               # PPTX 阅读器
-├── utils/                      # 工具函数
+│   │   ├── pdf/                # PDF 阅读器
-│   └── file_detection.py       # 文件类型检测
+│   │   └── html/               # HTML/URL 阅读器
-└── tests/                      # 测试
+│   └── utils/                  # 工具函数
+│       ├── file_detection.py   # 文件类型检测
+│       └── encoding_detection.py # 编码检测
+├── tests/                      # 测试
+├── openspec/                   # 规范文档
+└── README.md                   # 项目文档
 ```
 
 ## 解析器优先级

main.py

@@ -1,6 +0,0 @@
-def main():
-    print("Hello from lyxy-document!")
-
-
-if __name__ == "__main__":
-    main()

openspec/config.yaml

@@ -5,7 +5,6 @@ context: |
   - 语言: 仅中文(交流/注释/文档/代码)
   - Python: 始终用uv运行(脚本/临时命令uv run python -c); 禁用主机python/禁主机安装包
   - 依赖: pyproject.toml声明,使用uv安装
-  - 临时文件: 统一放temp目录
   - 主机环境: 禁止污染配置,需操作须请求用户
   - 文档: README.md,每次迭代按需更新用户文档和开发文档; 禁emoji/特殊字符
   - 测试: 所有需求必须设计全面测试
@@ -13,3 +12,11 @@ context: |
   - 代码: 模块文件150-300行; 错误需自定义异常+清晰信息+位置上下文
   - 项目阶段: 未上线,无用户,破坏性变更无需迁移说明
   - Git提交: 仅中文; 格式为"类型: 简短描述",类型可选: feat(新功能)/fix(修复)/refactor(重构)/docs(文档)/style(格式)/test(测试)/chore(构建/工具); 多行描述空行后加详细说明
+
+  # 项目目录结构
+  - scripts/: 核心代码目录
+  - tests/: 测试目录
+  - openspec/: 规范文档目录
+  - temp/: 开发临时文件目录
+  - pyproject.toml: 项目配置
+  - README.md: 项目文档

pyproject.toml

@@ -69,7 +69,7 @@ dev = [
 ]
 
 [project.scripts]
-lyxy-document-reader = "lyxy_document_reader:main"
+lyxy-document-reader = "scripts.lyxy_document_reader:main"
 
 [build-system]
 requires = ["hatchling"]
@@ -91,4 +91,4 @@ disallow_untyped_defs = true
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-pythonpath = ["."]
+pythonpath = ["scripts", "."]

scripts/core/parser.py

@@ -4,12 +4,12 @@ import argparse
 import sys
 from typing import List, Optional, Tuple
 
-from core.exceptions import FileDetectionError, ReaderNotFoundError
+from scripts.core.exceptions import FileDetectionError, ReaderNotFoundError
-from core.markdown import (
+from scripts.core.markdown import (
     normalize_markdown_whitespace,
     remove_markdown_images,
 )
-from readers import BaseReader
+from scripts.readers import BaseReader
 
 
 def parse_input(

scripts/lyxy_document_reader.py

@@ -20,14 +20,14 @@ logging.basicConfig(level=logging.ERROR, format='%(levelname)s: %(message)s')
 logging.getLogger('docling').setLevel(logging.ERROR)
 logging.getLogger('unstructured').setLevel(logging.ERROR)
 
-from core import (
+from scripts.core import (
     FileDetectionError,
     ReaderNotFoundError,
     output_result,
     parse_input,
     process_content,
 )
-from readers import READERS
+from scripts.readers import READERS
 
 
 def main() -> None:

scripts/readers/docx/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from readers.base import BaseReader
+from scripts.readers.base import BaseReader
-from utils import is_valid_docx
+from scripts.utils import is_valid_docx
 
 from . import docling
 from . import unstructured

scripts/readers/docx/docling.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_docling
+from scripts.core import parse_with_docling
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_markitdown
+from scripts.core import parse_with_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/native_xml.py

@@ -4,7 +4,7 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import Any, Dict, List, Optional, Tuple
 
-from core import build_markdown_table, safe_open_zip
+from scripts.core import build_markdown_table, safe_open_zip
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/python_docx.py

@@ -2,7 +2,7 @@
 
 from typing import Any, List, Optional, Tuple
 
-from core import build_markdown_table
+from scripts.core import build_markdown_table
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import _unstructured_elements_to_markdown
+from scripts.core import _unstructured_elements_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/html/__init__.py

@@ -3,9 +3,9 @@
 import os
 from typing import List, Optional, Tuple
 
-from readers.base import BaseReader
+from scripts.readers.base import BaseReader
-from utils import is_url
+from scripts.utils import is_url
-import encoding_detection
+from scripts.utils import encoding_detection
 
 from . import cleaner
 from . import downloader

scripts/readers/pdf/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from readers.base import BaseReader
+from scripts.readers.base import BaseReader
-from utils import is_valid_pdf
+from scripts.utils import is_valid_pdf
 
 from . import docling_ocr
 from . import unstructured_ocr

scripts/readers/pdf/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_markitdown
+from scripts.core import parse_with_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pdf/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import _unstructured_elements_to_markdown
+from scripts.core import _unstructured_elements_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pdf/unstructured_ocr.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import _unstructured_elements_to_markdown
+from scripts.core import _unstructured_elements_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from readers.base import BaseReader
+from scripts.readers.base import BaseReader
-from utils import is_valid_pptx
+from scripts.utils import is_valid_pptx
 
 from . import docling
 from . import unstructured

scripts/readers/pptx/docling.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_docling
+from scripts.core import parse_with_docling
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_markitdown
+from scripts.core import parse_with_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/native_xml.py

@@ -5,7 +5,7 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import Any, List, Optional, Tuple
 
-from core import build_markdown_table, flush_list_stack
+from scripts.core import build_markdown_table, flush_list_stack
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/python_pptx.py

@@ -2,7 +2,7 @@
 
 from typing import Any, List, Optional, Tuple
 
-from core import build_markdown_table, flush_list_stack
+from scripts.core import build_markdown_table, flush_list_stack
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import _unstructured_elements_to_markdown
+from scripts.core import _unstructured_elements_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from readers.base import BaseReader
+from scripts.readers.base import BaseReader
-from utils import is_valid_xlsx
+from scripts.utils import is_valid_xlsx
 
 from . import docling
 from . import unstructured

scripts/readers/xlsx/docling.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_docling
+from scripts.core import parse_with_docling
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import parse_with_markitdown
+from scripts.core import parse_with_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/native_xml.py

@@ -4,7 +4,7 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import List, Optional, Tuple
 
-from core import build_markdown_table, safe_open_zip
+from scripts.core import build_markdown_table, safe_open_zip
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from core import _unstructured_elements_to_markdown
+from scripts.core import _unstructured_elements_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/utils/encoding_detection.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from config import Config
+from scripts.config import Config
 
 
 def detect_encoding(file_path: str) -> Tuple[Optional[str], Optional[str]]:

tests/test_core/test_markdown.py

@@ -1,6 +1,6 @@
 """测试 Markdown 工具函数。"""
 
-from core import (
+from scripts.core import (
     get_heading_level,
     extract_titles,
     normalize_markdown_whitespace,

tests/test_utils/test_file_detection.py

@@ -1,6 +1,6 @@
 """测试文件检测工具函数。"""
 
-from utils import is_url, is_html_file
+from scripts.utils import is_url, is_html_file
 
 
 class TestIsUrl: