feat: 新增文档模型类，调整配置与解析逻辑，优化日志及导入

移除日志设置与冗余代码，优化导入、类型提示及OCR后端管理
统一调整各文件模块导入路径为绝对导入
调整导入路径，移除部分导入，优化日志及注释
升级文档解析器为 Docx2Parser，优化超时与图片处理逻辑

docreader/parser/__init__.py

@@ -13,22 +13,18 @@ The parsers extract content from documents and can split them into
 meaningful chunks for further processing and indexing.
 """
 
-from .base_parser import BaseParser, ParseResult
-from .docx_parser import DocxParser
 from .doc_parser import DocParser
-from .pdf_parser import PDFParser
-from .markdown_parser import MarkdownParser
-from .text_parser import TextParser
+from .docx2_parser import Docx2Parser
 from .image_parser import ImageParser
-from .web_parser import WebParser
+from .markdown_parser import MarkdownParser
 from .parser import Parser
-from .config import ChunkingConfig
-from .ocr_engine import OCREngine
+from .pdf_parser import PDFParser
+from .text_parser import TextParser
+from .web_parser import WebParser
 
 # Export public classes and modules
 __all__ = [
-    "BaseParser",  # Base parser class that all format parsers inherit from
-    "DocxParser",  # Parser for .docx files (modern Word documents)
+    "Docx2Parser",  # Parser for .docx files (modern Word documents)
     "DocParser",  # Parser for .doc files (legacy Word documents)
     "PDFParser",  # Parser for PDF documents
     "MarkdownParser",  # Parser for Markdown text files
@@ -36,7 +32,4 @@ __all__ = [
     "ImageParser",  # Parser for images with text content
     "WebParser",  # Parser for web pages
     "Parser",  # Main parser factory that selects the appropriate parser
-    "ChunkingConfig",  # Configuration for text chunking behavior
-    "ParseResult",  # Standard result format returned by all parsers
-    "OCREngine",  # OCR engine for extracting text from images
 ]