feat(backend): 更新核心模块和文件处理
- 更新配置模块 (config.py) - 更新数据库连接 (database.py) - 更新主应用入口 (main.py) - 更新数据模型 (models.py) - 更新基础 Schema (base.py) - 更新文件处理器 (docx, excel, pdf) - 更新 Dockerfile Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -1,8 +1,9 @@
|
||||
"""
|
||||
Excel/CSV Text Extractor
|
||||
"""
|
||||
import pandas as pd
|
||||
import asyncio
|
||||
from typing import Dict, List
|
||||
import pandas as pd
|
||||
|
||||
|
||||
class ExcelProcessor:
|
||||
@@ -13,6 +14,12 @@ class ExcelProcessor:
|
||||
df = pd.read_csv(file_path)
|
||||
return self._dataframe_to_text(df)
|
||||
|
||||
async def extract_csv_async(self, file_path: str) -> str:
|
||||
"""Extract CSV asynchronously"""
|
||||
return await asyncio.get_event_loop().run_in_executor(
|
||||
None, self.extract_csv, file_path
|
||||
)
|
||||
|
||||
def extract_excel(self, file_path: str, sheet_name: str = None) -> str:
|
||||
"""Extract text from Excel file"""
|
||||
if sheet_name:
|
||||
@@ -27,6 +34,12 @@ class ExcelProcessor:
|
||||
text_parts.append(self._dataframe_to_text(df))
|
||||
return "\n\n".join(text_parts)
|
||||
|
||||
async def extract_excel_async(self, file_path: str, sheet_name: str = None) -> str:
|
||||
"""Extract Excel asynchronously"""
|
||||
return await asyncio.get_event_loop().run_in_executor(
|
||||
None, self.extract_excel, file_path, sheet_name
|
||||
)
|
||||
|
||||
def _dataframe_to_text(self, df: pd.DataFrame) -> str:
|
||||
"""Convert DataFrame to readable text"""
|
||||
text_parts = []
|
||||
@@ -48,19 +61,25 @@ class ExcelProcessor:
|
||||
sheets = pd.read_excel(file_path, sheet_name=None)
|
||||
return {name: self._dataframe_to_text(df) for name, df in sheets.items()}
|
||||
|
||||
async def extract_all_sheets_async(self, file_path: str) -> Dict[str, str]:
|
||||
"""Extract all sheets asynchronously"""
|
||||
return await asyncio.get_event_loop().run_in_executor(
|
||||
None, self.extract_all_sheets, file_path
|
||||
)
|
||||
|
||||
def get_sheet_names(self, file_path: str) -> List[str]:
|
||||
"""Get all sheet names from Excel file"""
|
||||
xl = pd.ExcelFile(file_path)
|
||||
return xl.sheet_names
|
||||
|
||||
|
||||
def process_csv(file_path: str) -> str:
|
||||
async def process_csv(file_path: str) -> str:
|
||||
"""Process CSV file and return text"""
|
||||
processor = ExcelProcessor()
|
||||
return processor.extract_csv(file_path)
|
||||
return await processor.extract_csv_async(file_path)
|
||||
|
||||
|
||||
def process_excel(file_path: str) -> str:
|
||||
async def process_excel(file_path: str) -> str:
|
||||
"""Process Excel file and return text"""
|
||||
processor = ExcelProcessor()
|
||||
return processor.extract_excel(file_path)
|
||||
return await processor.extract_excel_async(file_path)
|
||||
|
||||
Reference in New Issue
Block a user