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/utils/split.py

@@ -0,0 +1,34 @@
+import re
+from typing import Callable, List
+
+
+def split_text_keep_separator(text: str, separator: str) -> List[str]:
+    """Split text with separator and keep the separator at the end of each split."""
+    parts = text.split(separator)
+    result = [separator + s if i > 0 else s for i, s in enumerate(parts)]
+    return [s for s in result if s]
+
+
+def split_by_sep(sep: str, keep_sep: bool = True) -> Callable[[str], List[str]]:
+    """Split text by separator."""
+    if keep_sep:
+        return lambda text: split_text_keep_separator(text, sep)
+    else:
+        return lambda text: text.split(sep)
+
+
+def split_by_char() -> Callable[[str], List[str]]:
+    """Split text by character."""
+    return lambda text: list(text)
+
+
+def split_by_regex(regex: str) -> Callable[[str], List[str]]:
+    """Split text by regex."""
+    pattern = re.compile(f"({regex})")
+    return lambda text: list(filter(None, pattern.split(text)))
+
+
+def match_by_regex(regex: str) -> Callable[[str], bool]:
+    """Split text by regex."""
+    pattern = re.compile(regex)
+    return lambda text: bool(pattern.match(text))