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。
This commit is contained in:
2026-03-08 17:41:03 +08:00
parent 750ef50a8d
commit 15b63800a8
50 changed files with 66 additions and 60 deletions

View File

@@ -0,0 +1,57 @@
"""PDF 文件阅读器支持多种解析方法OCR 优先)。"""
import os
from typing import List, Optional, Tuple
from scripts.readers.base import BaseReader
from scripts.utils import is_valid_pdf
from . import docling_ocr
from . import unstructured_ocr
from . import docling
from . import unstructured
from . import markitdown
from . import pypdf
PARSERS = [
("docling OCR", docling_ocr.parse),
("unstructured OCR", unstructured_ocr.parse),
("docling", docling.parse),
("unstructured", unstructured.parse),
("MarkItDown", markitdown.parse),
("pypdf", pypdf.parse),
]
class PdfReader(BaseReader):
"""PDF 文件阅读器"""
@property
def supported_extensions(self) -> List[str]:
return [".pdf"]
def supports(self, file_path: str) -> bool:
return file_path.endswith('.pdf')
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
failures = []
# 检查文件是否存在
if not os.path.exists(file_path):
return None, ["文件不存在"]
# 验证文件格式
if not is_valid_pdf(file_path):
return None, ["不是有效的 PDF 文件"]
content = None
for parser_name, parser_func in PARSERS:
content, error = parser_func(file_path)
if content is not None:
return content, failures
else:
failures.append(f"- {parser_name}: {error}")
return None, failures