Files
cbc2027/processors/text_processor.py

56 lines
1.7 KiB
Python

"""
Text file processor
"""
import logging
from pathlib import Path
from typing import Dict, Any
from core import FileProcessingError
from config import settings
from .base_processor import FileProcessor
class TextProcessor(FileProcessor):
"""Processor for text files"""
def __init__(self):
super().__init__("TextProcessor")
self.logger = logging.getLogger(__name__)
def can_process(self, file_path: str) -> bool:
"""Check if file is a text file"""
ext = self.get_file_extension(file_path)
return ext in settings.TXT_EXTENSIONS
def process(self, file_path: str) -> Dict[str, Any]:
"""Process text file (copy to downloads)"""
self.validate_file(file_path)
text_path = Path(file_path)
output_path = settings.LOCAL_DOWNLOADS_PATH / text_path.name
self.logger.info(f"Processing text file: {text_path}")
try:
# Copy file to downloads directory
output_path.parent.mkdir(parents=True, exist_ok=True)
with open(text_path, 'r', encoding='utf-8') as src:
with open(output_path, 'w', encoding='utf-8') as dst:
dst.write(src.read())
self.logger.info(f"Text file processing completed: {output_path}")
return {
"success": True,
"text_path": str(output_path),
"text": self._read_file(output_path)
}
except Exception as e:
self.logger.error(f"Text processing failed: {e}")
raise FileProcessingError(f"Text processing failed: {e}")
def _read_file(self, file_path: Path) -> str:
"""Read file content"""
with open(file_path, 'r', encoding='utf-8') as f:
return f.read()