Spaces:
Paused
Paused
| import os | |
| import pytesseract | |
| from pdf2image import convert_from_path | |
| from PIL import Image | |
| import pandas as pd | |
| from pypdf import PdfReader | |
| from pptx import Presentation | |
| import io | |
| class DocumentProcessor: | |
| def __init__(self): | |
| self.text_chunks = [] | |
| def process_file(self, file_path): | |
| ext = os.path.splitext(file_path)[1].lower() | |
| if ext == '.pdf': | |
| return self._process_pdf(file_path) | |
| elif ext in ('.png', '.jpg', '.jpeg'): | |
| return self._process_image(file_path) | |
| elif ext == '.pptx': | |
| return self._process_pptx(file_path) | |
| elif ext in ('.xlsx', '.xls'): | |
| return self._process_excel(file_path) | |
| else: | |
| raise ValueError(f"Unsupported file type: {ext}") | |
| def _process_pdf(self, file_path): | |
| try: | |
| # Try text extraction first | |
| reader = PdfReader(file_path) | |
| text = "\n".join([page.extract_text() for page in reader.pages]) | |
| if len(text.strip()) > 10: | |
| return self._chunk_text(text) | |
| except Exception: | |
| pass | |
| # Fallback to OCR | |
| images = convert_from_path(file_path) | |
| return self._process_images(images) | |
| def _process_image(self, file_path): | |
| return pytesseract.image_to_string(Image.open(file_path)) | |
| def _process_pptx(self, file_path): | |
| prs = Presentation(file_path) | |
| text = [] | |
| for slide in prs.slides: | |
| for shape in slide.shapes: | |
| if hasattr(shape, "text"): | |
| text.append(shape.text) | |
| return "\n".join(text) | |
| def _process_excel(self, file_path): | |
| df = pd.read_excel(file_path) | |
| return df.to_markdown() | |
| def _chunk_text(self, text, chunk_size=512): | |
| return [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)] |