utils/file_readers.py

# utils/file_readers.py

import docx
import PyPDF2

def read_txt(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        return f.read()

def read_docx(file_path):
    doc = docx.Document(file_path)
    full_text = []
    for para in doc.paragraphs:
        full_text.append(para.text)
    return '\n'.join(full_text)

def read_pdf(file_path):
    text = ''
    with open(file_path, 'rb') as f:
        reader = PyPDF2.PdfReader(f)
        for page in reader.pages:
            page_text = page.extract_text()
            if page_text:
                text += page_text
    return text

def read_file(file_path):
    if file_path.endswith('.txt'):
        return read_txt(file_path)
    elif file_path.endswith('.docx'):
        return read_docx(file_path)
    elif file_path.endswith('.pdf'):
        return read_pdf(file_path)
    else:
        return ""