Spaces:
Running
Running
| import gradio as gr | |
| import tempfile | |
| import os | |
| import subprocess | |
| def process_files(pdf_file, word_file): | |
| # 1. Save the uploaded files to temp | |
| temp_dir = tempfile.mkdtemp() | |
| pdf_path = os.path.join(temp_dir, "input.pdf") | |
| word_path = os.path.join(temp_dir, "input.docx") | |
| with open(pdf_path, "wb") as f: | |
| f.write(pdf_file.read()) | |
| with open(word_path, "wb") as f: | |
| f.write(word_file.read()) | |
| # 2. Step 1: Extract PDF data to txt | |
| pdf_txt_path = os.path.join(temp_dir, "pdf_data.txt") | |
| subprocess.run(["python", "extract_pdf_data.py", pdf_path, pdf_txt_path], check=True) | |
| # 3. Step 2: Extract red text from Word to JSON | |
| word_json_path = os.path.join(temp_dir, "word_data.json") | |
| subprocess.run(["python", "extract_red_text.py", word_path, word_json_path], check=True) | |
| # 4. Step 3: Update docx JSON with PDF txt, output updated JSON | |
| updated_json_path = os.path.join(temp_dir, "updated_word_data.json") | |
| subprocess.run([ | |
| "python", "update_docx_with_pdf.py", word_json_path, pdf_txt_path, updated_json_path | |
| ], check=True) | |
| # 5. Step 4: Compare word file with updated JSON and update docx | |
| final_docx_path = os.path.join(temp_dir, "updated.docx") | |
| subprocess.run([ | |
| "python", "updated_word.py", word_path, updated_json_path, final_docx_path | |
| ], check=True) | |
| # 6. Return final docx file | |
| return final_docx_path | |
| gr.Interface( | |
| fn=process_files, | |
| inputs=[ | |
| gr.File(label="Upload PDF File"), | |
| gr.File(label="Upload Word File") | |
| ], | |
| outputs=gr.File(label="Download Updated Word File"), | |
| title="Red Text Replacer", | |
| description="Upload a PDF and Word document. Red-colored text in the Word doc will be replaced by matching content from the PDF." | |
| ).launch() |