text_extraction.py

import PyPDF2
import re

def extract_text_from_pdf(pdf_file_path):
    """Extracts text from a PDF file with improved error handling."""
    try:
        with open(pdf_file_path, 'rb') as pdf_file:
            pdf_reader = PyPDF2.PdfReader(pdf_file)
            text = ' '.join(page.extract_text() or '' for page in pdf_reader.pages)
            return text.strip()
    except Exception as e:
        return f"Error reading PDF: {str(e)}"

def extract_text_from_txt(txt_file_path):
    """Extracts text from a TXT file with encoding fallbacks."""
    encodings = ['utf-8', 'latin-1', 'ascii']
    for encoding in encodings:
        try:
            with open(txt_file_path, 'r', encoding=encoding) as txt_file:
                return txt_file.read().strip()
        except UnicodeDecodeError:
            continue
        except Exception as e:
            return f"Error reading TXT: {str(e)}"
    return "Error: Unable to decode file with supported encodings"