file_processing.py

ALLOWED_EXTENSIONS = {'pdf', 'doc', 'docx', 'xls', 'xlsx', 'txt'}

def allowed_file(filename):
    return '.' in filename and \
        filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS

from werkzeug.utils import secure_filename
from docx import Document
import PyPDF2
import pandas as pd

def extract_text_from_txt(file_stream):
    return file_stream.read().decode('utf-8', errors='ignore')

def extract_text_from_docx(file_stream):
    doc = Document(file_stream)
    return '\n'.join([p.text for p in doc.paragraphs])

def extract_text_from_pdf(file_stream):
    reader = PyPDF2.PdfReader(file_stream)
    text = ''
    for page in reader.pages:
        text += page.extract_text() or ''
    return text

def extract_text_from_excel(file_stream):
    # Retorna el contenido como CSV para mejor comprensión
    try:
        df = pd.read_excel(file_stream, header=None)
        return df.to_csv(index=False, header=False)
    except Exception:
        return ''

def extract_text(file, filename):
    ext = filename.rsplit('.', 1)[1].lower()
    if ext == 'txt':
        return extract_text_from_txt(file.stream)
    elif ext in ['doc', 'docx']:
        return extract_text_from_docx(file.stream)
    elif ext == 'pdf':
        return extract_text_from_pdf(file.stream)
    elif ext in ['xls', 'xlsx']:
        return extract_text_from_excel(file.stream)
    else:
        return ''