Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import pandas as pd | |
| import torch | |
| from extract_text import extract_text_from_image | |
| from text_similarity import analyze_similarity | |
| def process_image(image, key_texts, similarity_threshold, fragment_threshold): | |
| """Processes the image, extracts text, and analyzes similarities.""" | |
| try: | |
| if image is None: | |
| return "Please upload an image for analysis.", None, None, None, None, None | |
| if not key_texts.strip(): | |
| return "Please enter key texts for comparison.", None, None, None, None, None | |
| # Extract text from the image using the user's method | |
| gpu_available = torch.cuda.is_available() | |
| extracted_texts = extract_text_from_image(image, gpu_available) | |
| if isinstance(key_texts, str): | |
| key_texts = [text.strip() for text in key_texts.split('\n') if text.strip()] | |
| # Process the analysis | |
| results = analyze_similarity( | |
| extracted_texts, | |
| key_texts, | |
| similarity_threshold=similarity_threshold/100, # Convert percentage to decimal | |
| fragment_threshold=fragment_threshold/100 # Convert percentage to decimal | |
| ) | |
| # Gerar relatório HTML | |
| html_report = generate_html_report(results) | |
| # Gerar DataFrames | |
| dfs = generate_results_dataframe(results) | |
| # Extrair DataFrames individuais (ou criar vazios se não existirem) | |
| df_statistics = dfs.get("statistics", pd.DataFrame()) | |
| df_similar = dfs.get("similar", pd.DataFrame(columns=["Index", "Original Text", "Key Text", "Similarity"])) | |
| df_fragments = dfs.get("fragments", pd.DataFrame(columns=["Index", "Original Text", "Key Text", "Similarity"])) | |
| df_combined = dfs.get("combined", pd.DataFrame(columns=["Indices", "Text 1", "Text 2", "Combined Text", "Key Text", "Similarity"])) | |
| return html_report, df_statistics, df_similar, df_fragments, df_combined, extracted_texts, gpu_available | |
| except Exception as e: | |
| return f"Erro ao processar: {str(e)}", None, None, None, None, None | |
| def process_manual_input(texts, key_texts, similarity_threshold, fragment_threshold): | |
| """Processes the user's manual text input.""" | |
| # Validate input | |
| if not texts.strip() or not key_texts.strip(): | |
| return "Please enter texts for analysis and key texts for comparison.", None, None, None, None | |
| try: | |
| # Process the analysis | |
| results = analyze_similarity( | |
| texts, | |
| key_texts, | |
| similarity_threshold=similarity_threshold/100, # Convert percentage to decimal | |
| fragment_threshold=fragment_threshold/100 # Convert percentage to decimal | |
| ) | |
| # Generate HTML report | |
| html_report = generate_html_report(results) | |
| # Gerar DataFrames | |
| dfs = generate_results_dataframe(results) | |
| # Extract individual DataFrames (or create empty ones if they don't exist) | |
| df_statistics = dfs.get("statistics", pd.DataFrame()) | |
| df_similar = dfs.get("similar", pd.DataFrame(columns=["Index", "Original Text", "Key Text", "Similarity"])) | |
| df_fragments = dfs.get("fragments", pd.DataFrame(columns=["Index", "Original Text", "Key Text", "Similarity"])) | |
| df_combined = dfs.get("combined", pd.DataFrame(columns=["Indices", "Text 1", "Text 2", "Combined Text", "Key Text", "Similarity"])) | |
| return html_report, df_statistics, df_similar, df_fragments, df_combined | |
| except Exception as e: | |
| return f"Erro ao processar: {str(e)}", None, None, None, None | |
| def generate_html_report(results): | |
| """Generates an HTML report about the detected similarities.""" | |
| html = "<h2>Similarity Report</h2>" | |
| # General statistics | |
| html += "<div padding: 15px; border-radius: 5px; margin-bottom: 20px;'>" | |
| html += f"<p><b>Total texts analyzed:</b> {results['statistics']['total_analyzed']}</p>" | |
| html += f"<p><b>Texts with detected similarity:</b> {results['statistics']['total_processed']}</p>" | |
| html += "</div>" | |
| # Results table | |
| html += "<h3>Detected Similarities</h3>" | |
| # Similar texts | |
| if results["similar_texts"]: | |
| html += "<h4>Direct Similar Texts</h4>" | |
| html += "<table width='100%' style='border-collapse: collapse; margin-bottom: 20px;'>" | |
| html += "<tr><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Original Text</th><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Key Text</th><th style='text-align: center; padding: 8px; border: 1px solid #ddd;'>Similarity</th></tr>" | |
| for item in results["similar_texts"]: | |
| html += f"<tr><td style='padding: 8px; border: 1px solid #ddd;'>{item['text']}</td><td style='padding: 8px; border: 1px solid #ddd;'>{item['key_text']}</td><td style='text-align: center; padding: 8px; border: 1px solid #ddd;'>{item['similarity']:.2%}</td></tr>" | |
| html += "</table>" | |
| # Detected fragments | |
| if results["fragments_detected"]: | |
| html += "<h4>Text with Detected Fragments</h4>" | |
| html += "<table width='100%' style='border-collapse: collapse; margin-bottom: 20px;'>" | |
| html += "<tr><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Original Text</th><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Key Text</th><th style='text-align: center; padding: 8px; border: 1px solid #ddd;'>Similarity</th></tr>" | |
| for item in results["fragments_detected"]: | |
| html += f"<tr><td style='padding: 8px; border: 1px solid #ddd;'>{item['text']}</td><td style='padding: 8px; border: 1px solid #ddd;'>{item['key_text']}</td><td style='text-align: center; padding: 8px; border: 1px solid #ddd;'>{item['similarity']:.2%}</td></tr>" | |
| html += "</table>" | |
| # Combined texts | |
| if results["combined"]: | |
| html += "<h4>Text that need to be combined</h4>" | |
| html += "<table width='100%' style='border-collapse: collapse; margin-bottom: 20px;'>" | |
| html += "<tr><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Text 1</th><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Text 2</th><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Combination</th><th style='text-align: left; padding: 8px; border: 1px solid #ddd;'>Key Text</th><th style='text-align: center; padding: 8px; border: 1px solid #ddd;'>Similarity</th></tr>" | |
| for item in results["combined"]: | |
| html += f"<tr><td style='padding: 8px; border: 1px solid #ddd;'>{item['texts'][0]}</td><td style='padding: 8px; border: 1px solid #ddd;'>{item['texts'][1]}</td><td style='padding: 8px; border: 1px solid #ddd;'>{item['combined_text']}</td><td style='padding: 8px; border: 1px solid #ddd;'>{item['key_text']}</td><td style='text-align: center; padding: 8px; border: 1px solid #ddd;'>{item['similarity']:.2%}</td></tr>" | |
| html += "</table>" | |
| if not (results["similar_texts"] or results["fragments_detected"] or results["combined"]): | |
| html += "<p>No significant similarity found with the current parameters.</p>" | |
| return html | |
| def generate_results_dataframe(results): | |
| """Generates pandas DataFrames to visualize the results.""" | |
| dfs = {} | |
| # DataFrame for similar texts | |
| if results["similar_texts"]: | |
| data = [(item['index'], item['text'], item['key_text'], f"{item['similarity']:.2%}") | |
| for item in results["similar_texts"]] | |
| dfs["similar"] = pd.DataFrame(data, columns=["Index", "Original Text", "Key Text", "Similarity"]) | |
| # DataFrame for fragments | |
| if results["fragments_detected"]: | |
| data = [(item['index'], item['text'], item['key_text'], f"{item['similarity']:.2%}") | |
| for item in results["fragments_detected"]] | |
| dfs["fragments"] = pd.DataFrame(data, columns=["Index", "Original Text", "Key Text", "Similarity"]) | |
| # DataFrame for combined | |
| if results["combined"]: | |
| data = [(f"{item['indices'][0]},{item['indices'][1]}", | |
| item['texts'][0], | |
| item['texts'][1], | |
| item['combined_text'], | |
| item['key_text'], | |
| f"{item['similarity']:.2%}") | |
| for item in results["combined"]] | |
| dfs["combined"] = pd.DataFrame(data, columns=["Indices", "Text 1", "Text 2", | |
| "Combined Text", "Key Text", "Similarity"]) | |
| # Statistics DataFrame | |
| data = [ | |
| ("Total analyzed", results["statistics"]["total_analyzed"]), | |
| ("Total with similarity", results["statistics"]["total_processed"]), | |
| ("Direct similarity", results["statistics"]["direct_similarity"]), | |
| ("Fragments", results["statistics"]["fragments"]), | |
| ("Combined", results["statistics"]["combined"]) | |
| ] | |
| dfs["statistics"] = pd.DataFrame(data, columns=["Metric", "Value"]) | |
| return dfs | |
| def generate_gradio(): | |
| with gr.Blocks(title="Text Similarity Detector") as demo: | |
| gr.Markdown("# 🔍 Text Similarity Detector with Image Extraction") | |
| gr.Markdown(""" | |
| This tool analyzes the similarity between texts extracted from an image and reference key texts. | |
| It can identify: | |
| - Direct similar texts | |
| - Key text fragments within the texts | |
| - Text combinations that match key texts | |
| """) | |
| with gr.Tabs() as tabs: | |
| with gr.TabItem("Image Analysis"): | |
| with gr.Row(): | |
| with gr.Column(scale=1): # Column for inputs on the left | |
| input_image = gr.Image(label="Upload an image to extract text", type="pil", height=600) | |
| key_texts_image = gr.Textbox( | |
| label="Key Texts for Comparison", | |
| placeholder="Paste your key texts here (one per line)", | |
| lines=5 | |
| ) | |
| # with gr.Row(): | |
| # key_texts_image = gr.Textbox( | |
| # label="Key Texts for Comparison", | |
| # placeholder="Paste your key texts here (one per line)", | |
| # lines=5 | |
| # ) | |
| # min_similarity_per_key_image = gr.Textbox( | |
| # label="Minimum Similarity for Each Key Text (%)", | |
| # placeholder="Enter one value per line, matching the key texts", | |
| # lines=5 | |
| # ) | |
| with gr.Row(): | |
| similarity_threshold_image = gr.Slider( | |
| label="Similarity Threshold (%)", | |
| minimum=50, | |
| maximum=100, | |
| value=70, | |
| step=1 | |
| ) | |
| fragment_threshold_image = gr.Slider( | |
| label="Fragment Similarity Threshold (%)", | |
| minimum=50, | |
| maximum=100, | |
| value=70, | |
| step=1 | |
| ) | |
| analyze_image_btn = gr.Button("Analyze Image", variant="primary") | |
| with gr.Column(scale=1): # Column for outputs on the right | |
| gpu_available = gr.Checkbox(label="Used GPU") | |
| extracted_texts = gr.Textbox(label="Extracted Texts from the Image", lines=5) | |
| html_output = gr.HTML(label="Similarity Report") | |
| with gr.Tabs(): | |
| with gr.TabItem("Statistics"): | |
| statistics_output = gr.Dataframe(label="Statistics") | |
| with gr.TabItem("Direct Similarity"): | |
| similar_texts_output = gr.Dataframe(label="Direct Similar Texts") | |
| with gr.TabItem("Fragments"): | |
| fragments_output = gr.Dataframe(label="Texts with Fragments") | |
| with gr.TabItem("Combined"): | |
| combined_output = gr.Dataframe(label="Combined Texts") | |
| with gr.TabItem("Manual Analysis"): | |
| with gr.Row(): | |
| with gr.Column(scale=1): # Column for inputs on the left | |
| input_texts = gr.Textbox( | |
| label="List of Texts for Analysis", | |
| placeholder="Paste your list of texts here (one per line)", | |
| lines=10 | |
| ) | |
| key_texts_input = gr.Textbox( | |
| label="Key Texts for Comparison", | |
| placeholder="Paste your key texts here (one per line)", | |
| lines=5 | |
| ) | |
| # with gr.Row(): | |
| # key_texts_input = gr.Textbox( | |
| # label="Key Texts for Comparison", | |
| # placeholder="Paste your key texts here (one per line)", | |
| # lines=5 | |
| # ) | |
| # min_similarity_per_key_input = gr.Textbox( | |
| # label="Minimum Similarity for Each Key Text (%)", | |
| # placeholder="Enter one value per line, matching the key texts", | |
| # lines=5 | |
| # ) | |
| with gr.Row(): | |
| similarity_threshold = gr.Slider( | |
| label="Similarity Threshold (%)", | |
| minimum=50, | |
| maximum=100, | |
| value=70, | |
| step=1 | |
| ) | |
| fragment_threshold = gr.Slider( | |
| label="Fragment Similarity Threshold (%)", | |
| minimum=50, | |
| maximum=100, | |
| value=70, | |
| step=1 | |
| ) | |
| analyze_btn = gr.Button("Analyze Image", variant="primary") | |
| with gr.Column(scale=1): # Column for outputs on the right | |
| html_output_manual = gr.HTML(label="Manual Similarity Report") | |
| with gr.Tabs(): | |
| with gr.TabItem("Statistics"): | |
| statistics_output_manual = gr.Dataframe(label="Statistics") | |
| with gr.TabItem("Direct Similarity"): | |
| similar_texts_output_manual = gr.Dataframe(label="Direct Similar Texts") | |
| with gr.TabItem("Fragments"): | |
| fragments_output_manual = gr.Dataframe(label="Texts with Fragments") | |
| with gr.TabItem("Combined"): | |
| combined_output_manual = gr.Dataframe(label="Combined Texts") | |
| # Connect the image processing function to the button | |
| analyze_image_btn.click( | |
| process_image, | |
| inputs=[input_image, key_texts_image, similarity_threshold_image, fragment_threshold_image], | |
| outputs=[html_output, statistics_output, similar_texts_output, fragments_output, combined_output, extracted_texts, gpu_available] | |
| ) | |
| # Connect the manual text processing function to the button | |
| analyze_btn.click( | |
| process_manual_input, | |
| inputs=[input_texts, key_texts_input, similarity_threshold, fragment_threshold], | |
| outputs=[html_output_manual, statistics_output_manual, similar_texts_output_manual, fragments_output_manual, combined_output_manual] | |
| ) | |
| return demo | |
| #app = gr.mount_gradio_app(app, demo, path="/") | |
| if __name__ == "__main__": | |
| generate_gradio.launch() | |
| # PORT = int(os.getenv("PORT", 7860)) | |
| # if __name__ == "__main__": | |
| # import uvicorn | |
| # print(f"A arrancar na porta {PORT}...") | |
| # uvicorn.run(app) | |
| #demo.launch(server_name="0.0.0.0", server_port=7860) | |