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/text_parser.py

@@ -1,6 +1,8 @@
 import logging
-from .base_parser import BaseParser
-from typing import Dict, Any, Tuple, Union
+
+from docreader.models.document import Document
+from docreader.parser.base_parser import BaseParser
+from docreader.utils import endecode
 
 logger = logging.getLogger(__name__)
 
@@ -11,7 +13,7 @@ class TextParser(BaseParser):
     This parser handles text extraction and chunking from plain text documents.
     """
 
-    def parse_into_text(self, content: bytes) -> Union[str, Tuple[str, Dict[str, Any]]]:
+    def parse_into_text(self, content: bytes) -> Document:
         """
         Parse text document content by decoding bytes to string.
 
@@ -25,20 +27,15 @@ class TextParser(BaseParser):
             Parsed text content as string
         """
         logger.info(f"Parsing text document, content size: {len(content)} bytes")
-        text = self.decode_bytes(content)
+        text = endecode.decode_bytes(content)
         logger.info(
             f"Successfully parsed text document, extracted {len(text)} characters"
         )
-        return text
+        return Document(content=text)
 
 
 if __name__ == "__main__":
-    logging.basicConfig(
-        level=logging.INFO,
-        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S",
-    )
-    logger.info("Running TextParser in standalone mode")
+    logger = logging.getLogger(__name__)
 
     # Sample text for testing
     text = """## 标题1