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/endecode.py

@@ -0,0 +1,103 @@
+import base64
+import binascii
+import io
+import logging
+from typing import List, Union
+
+import numpy as np
+from PIL import Image
+
+logger = logging.getLogger(__name__)
+
+
+def decode_image(image: Union[str, bytes, Image.Image, np.ndarray]) -> str:
+    """Convert image to base64 encoded string
+
+    Args:
+        image: Image file path, bytes, PIL Image object, or numpy array
+
+    Returns:
+        Base64 encoded image string, or empty string if conversion fails
+    """
+    if isinstance(image, str):
+        # It's a file path
+        with open(image, "rb") as image_file:
+            return base64.b64encode(image_file.read()).decode()
+
+    elif isinstance(image, bytes):
+        # It's bytes data
+        return base64.b64encode(image).decode()
+
+    elif isinstance(image, Image.Image):
+        # It's a PIL Image
+        buffer = io.BytesIO()
+        image.save(buffer, format=image.format)
+        return base64.b64encode(buffer.getvalue()).decode()
+
+    elif isinstance(image, np.ndarray):
+        # It's a numpy array
+        pil_image = Image.fromarray(image)
+        buffer = io.BytesIO()
+        pil_image.save(buffer, format="PNG")
+        return base64.b64encode(buffer.getvalue()).decode()
+
+    raise ValueError(f"Unsupported image type: {type(image)}")
+
+
+def encode_image(image: str, errors="strict") -> bytes:
+    """
+    Decode image bytes using base64.
+
+    errors
+        The error handling scheme to use for the handling of decoding errors.
+        The default is 'strict' meaning that decoding errors raise a
+        UnicodeDecodeError. Other possible values are 'ignore' and '????'
+        as well as any other name registered with codecs.register_error that
+        can handle UnicodeDecodeErrors.
+    """
+    try:
+        image_bytes = base64.b64decode(image)
+    except binascii.Error as e:
+        if errors == "ignore":
+            return b""
+        else:
+            raise e
+    return image_bytes
+
+
+def encode_bytes(content: str) -> bytes:
+    return content.encode()
+
+
+def decode_bytes(
+    content: bytes,
+    encodings: List[str] = [
+        "utf-8",
+        "gb18030",
+        "gb2312",
+        "gbk",
+        "big5",
+        "ascii",
+        "latin-1",
+    ],
+) -> str:
+    # Try decoding with each encoding format
+    for encoding in encodings:
+        try:
+            text = content.decode(encoding)
+            logger.debug(f"Decode content with {encoding}: {len(text)} characters")
+            return text
+        except UnicodeDecodeError:
+            continue
+
+    text = content.decode(encoding="latin-1", errors="replace")
+    logger.warning(
+        "Unable to determine correct encoding, using latin-1 as fallback. "
+        "This may cause character issues."
+    )
+    return text
+
+
+if __name__ == "__main__":
+    img = "test![](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAMgA)test"
+    encode_image(img, errors="ignore")

docreader/utils/request.py

@@ -1,10 +1,10 @@
-from contextvars import ContextVar
-import logging
-import uuid
 import contextlib
+import logging
 import time
-from typing import Optional
+import uuid
+from contextvars import ContextVar
 from logging import LogRecord
+from typing import Optional
 
 # 配置日志
 logger = logging.getLogger(__name__)
@@ -26,21 +26,21 @@ def get_request_id() -> Optional[str]:
 
 class MillisecondFormatter(logging.Formatter):
     """自定义日志格式化器，只显示毫秒级时间戳(3位数字)而不是微秒(6位)"""
-    
+
     def formatTime(self, record, datefmt=None):
         """重写formatTime方法，将微秒格式化为毫秒"""
         # 先获取标准的格式化时间
         result = super().formatTime(record, datefmt)
-        
+
         # 如果使用了包含.%f的格式，则将微秒(6位)截断为毫秒(3位)
         if datefmt and ".%f" in datefmt:
             # 格式化的时间字符串应该在最后有6位微秒数
-            parts = result.split('.')
+            parts = result.split(".")
             if len(parts) > 1 and len(parts[1]) >= 6:
                 # 只保留前3位作为毫秒
                 millis = parts[1][:3]
                 result = f"{parts[0]}.{millis}"
-                
+
         return result
 
 

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))

docreader/utils/tempfile.py

@@ -0,0 +1,77 @@
+import logging
+import os
+import tempfile
+
+logger = logging.getLogger(__name__)
+
+
+class TempFileContext:
+    def __init__(self, file_content: bytes, suffix: str):
+        """
+        Initialize the context
+        :param file_content: Byte data to write to file
+        :param suffix: File suffix
+        """
+        self.file_content = file_content
+        self.suffix = suffix
+        self.file = None
+
+    def __enter__(self):
+        """
+        Create file when entering context
+        """
+        self.temp_file = tempfile.NamedTemporaryFile(suffix=self.suffix, delete=False)
+        self.temp_file.write(self.file_content)
+        self.temp_file.flush()
+        logger.info(
+            f"Saved {self.suffix} content to temporary file: {self.temp_file.name}"
+        )
+        return self.temp_file.name
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """
+        Delete file when exiting context
+        """
+        if self.temp_file:
+            self.temp_file.close()
+            if os.path.exists(self.temp_file.name):
+                os.remove(self.temp_file.name)
+            logger.info(f"File {self.temp_file.name} has been deleted.")
+        # Return False to propagate exception (if any exception occurred)
+        return False
+
+
+class TempDirContext:
+    def __init__(self):
+        """
+        Initialize the context
+        """
+        self.temp_dir = None
+
+    def __enter__(self):
+        """
+        Create directory when entering context
+        """
+        self.temp_dir = tempfile.TemporaryDirectory()
+        logger.info(f"Created temporary directory: {self.temp_dir.name}")
+        return self.temp_dir.name
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """
+        Delete directory when exiting context
+        """
+        if self.temp_dir and os.path.exists(self.temp_dir.name):
+            self.temp_dir.cleanup()
+            logger.info(f"Directory {self.temp_dir.name} has been deleted.")
+        # Return False to propagate exception (if any exception occurred)
+        return False
+
+
+if __name__ == "__main__":
+    example_bytes = b"Hello, this is a test file."
+    file_name = "test_file.txt"
+
+    # Using with statement
+    with TempFileContext(example_bytes, file_name) as temp_file:
+        # File operations can be performed within the context
+        print(f"Does file {file_name} exist: {os.path.exists(file_name)}")