Fix: Improved OUI calculation and report in English, added article scoring, and optimized article selection

app.py

@@ -80,7 +80,9 @@ def calculate_token_overlap(text1, text2):
 def calculate_oui(similarity, token_overlap, alpha=0.7, beta=0.3):
     oui = alpha * (1 - similarity / 100) + beta * (1 - token_overlap / 100)
     result = round(oui * 100, 2)
-    return 0.0 if result == -0.0 else result
+    if result < 0:
+        result = 0  # Limita il valore a 0 se diventa negativo
+    return result
 
 # Funzione di scoring degli articoli
 def score_article(article, pdf_text):
@@ -118,7 +120,8 @@ def validate_document(pdf_path, comparison_sources, method="local", titles=None,
             'text': doc_text
         }
         score = score_article(article, pdf_text)
-        scored_articles.append((score, article))
+        if score <= 100:  # Esclude articoli con punteggi anomali
+            scored_articles.append((score, article))
 
     # Ordina gli articoli in base al punteggio
     scored_articles.sort(reverse=True, key=lambda x: x[0])
@@ -263,13 +266,13 @@ def download_report():
     pdf = FPDF()
     pdf.add_page()
     pdf.set_font("Arial", "B", 16)
-    pdf.cell(0, 10, "NORUS Tool - Report Analisi", ln=True, align="C")
+    pdf.cell(0, 10, "NORUS Tool - Report Analysis", ln=True, align="C")
     pdf.ln(10)
     pdf.set_font('Arial', '', 12)
-    pdf.multi_cell(0, 10, "Indice OUI = alpha(1 - sim/100) + beta(1 - overlap/100), con alpha = 0.7 e beta = 0.3.\nValori più bassi di OUI indicano maggiore similarità semantica e testuale.")
+    pdf.multi_cell(0, 10, "OUI Index = alpha(1 - similarity/100) + beta(1 - overlap/100), with alpha = 0.7 and beta = 0.3.\nLower OUI values indicate higher semantic and textual similarity.")
     pdf.ln(5)
     pdf.set_font("Arial", "B", 12)
-    pdf.cell(90, 10, "Titolo", 1)
+    pdf.cell(90, 10, "Title", 1)
     pdf.cell(30, 10, "Sim %", 1)
     pdf.cell(30, 10, "Overlap %", 1)
     pdf.cell(30, 10, "OUI", 1)
@@ -287,7 +290,7 @@ def download_report():
     if last_common_keywords:
         pdf.ln(6)
         pdf.set_font("Arial", "B", 12)
-        pdf.cell(0, 10, "Parole chiave comuni:", ln=True)
+        pdf.cell(0, 10, "Common Keywords:", ln=True)
         pdf.set_font("Arial", "", 11)
         for kw, count in last_common_keywords:
             pdf.cell(0, 10, f"- {kw} ({count})", ln=True)
@@ -302,4 +305,4 @@ def download_report():
     return send_file(output_path, as_attachment=True)
 
 if __name__ == "__main__":
-    app.run(debug=True, host="0.0.0.0", port=7860)
+    app.run(debug=True, host="0.0.0.0", port=7860)