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
This commit is contained in:
@@ -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)}")
|
||||
Reference in New Issue
Block a user