Add application file

app.py

@@ -1,292 +1,7 @@
-import gradio as gr
-import pandas as pd
-import cv2
-import numpy as np
-import requests
-import torch
-import base64
-import os
-import logging
-from io import BytesIO
-from PIL import Image
 from fastapi import FastAPI
-from fastapi.middleware.cors import CORSMiddleware
-from extract_text import extract_text_from_image
-from models import TextSimilarityRequest
-from text_similarity import analyze_similarity
-from starlette.responses import JSONResponse
 
-
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 app = FastAPI()
-# app.add_middleware(
-#     CORSMiddleware,
-#     allow_origins=["*"],
-#     allow_credentials=True,
-#     allow_methods=["*"],
-#     allow_headers=["*"],
-# )
-
-@app.post("/text_similarity", summary="Perform images text similarity", response_model=float, tags=["Text Similarities"])
-async def text_similarity(request: TextSimilarityRequest):
-    image_info = request.imageInfo
-    key_texts = request.keyTexts
-    similarity_threshold = request.similarityThreshold 
-    origin_id = image_info.originId
-
-    logging.info(f"Checking text similarity for main source with resource id {origin_id}")
-
-    image = load_image_url(image_info.source)
-
-    # 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)
-
-    results = analyze_similarity(
-            extracted_texts,
-            key_texts,
-            similarity_threshold=similarity_threshold/100,  # Convert percentage to decimal
-            fragment_threshold=100/100  # Convert percentage to decimal
-        )
-    
-    log_similarity_report(results, origin_id)
-    
-    total_texts = len(key_texts)
-    passed_texts = results["statistics"]["total_processed"]
-
-    percentage_passed = (passed_texts / total_texts) * 100
-
-    logging.info(f"Text similarity for main source with resource id {origin_id} is {percentage_passed}%")
-
-    return percentage_passed
-
-def log_similarity_report(results, originId):    
-    # General statistics
-    logging.info(f"[{originId}] Total texts analyzed: {results['statistics']['total_analyzed']}")
-    logging.info(f"[{originId}] Texts with detected similarity: {results['statistics']['total_processed']}")
-    
-    # Similar texts
-    if results["similar_texts"]:
-        logging.info(f"[{originId}] Direct Similar Texts Found: {len(results['similar_texts'])}")
-        for item in results["similar_texts"]:
-            logging.info(f"[{originId}] Similar Text: '{item['text']}' -> Key Text: '{item['key_text']}' with Similarity: {item['similarity']:.2%}")
-    
-    # Detected fragments
-    if results["fragments_detected"]:
-        logging.info(f"[{originId}] Fragments Detected: {len(results['fragments_detected'])}")
-        for item in results["fragments_detected"]:
-            logging.info(f"[{originId}] Fragment: '{item['text']}' -> Key Text: '{item['key_text']}' with Similarity: {item['similarity']:.2%}")
-    
-    # Combined texts
-    if results["combined"]:
-        logging.info(f"[{originId}] Texts to be Combined: {len(results['combined'])}")
-        for item in results["combined"]:
-            logging.info(f"[{originId}] Combined Text: '{item['combined_text']}' -> Key Text: '{item['key_text']}' with Similarity: {item['similarity']:.2%}")
-    
-    # If no significant similarity found
-    if not (results["similar_texts"] or results["fragments_detected"] or results["combined"]):
-        logging.info(f"[{originId}] No significant similarity found.")
-    
-    # Statistics
-    logging.info(f"[{originId}] Direct similarity: {results['statistics']['direct_similarity']}")
-    logging.info(f"[{originId}] Fragments: {results['statistics']['fragments']}")
-    logging.info(f"[{originId}] Combined: {results['statistics']['combined']}")
-
-def load_image_url(source):
-    Image.MAX_IMAGE_PIXELS = None
-
-    if source.startswith('http'):
-        response = requests.get(source)
-        img = np.asarray(bytearray(response.content), dtype=np.uint8)
-        img = cv2.imdecode(img, cv2.IMREAD_GRAYSCALE)
-    else:
-        img = base64.b64decode(source)
-        img = Image.open(BytesIO(img))
-        img = np.array(img)
-        img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
-
-    return img
-
-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
-    
-#app = gr.mount_gradio_app(app, demo, path="/")
-
-@app.get("/api")
-def read_root():
-    return JSONResponse(content={"message": "Hello from FastAPI inside Gradio!"})
-
-# if __name__ == "__main__":
-#     import uvicorn
-#     uvicorn.run(app)
-
-# 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)
+@app.get("/")
+def root():
+    return "oi"