Update modules/text_analysis/semantic_analysis.py

modules/text_analysis/semantic_analysis.py

@@ -87,60 +87,41 @@ def perform_semantic_analysis(text, nlp, lang_code):
     Returns:
         dict: Resultados del análisis
     """
-    
-    logger.info(f"Starting semantic analysis for language: {lang_code}")
     try:
-        tokens = process_text(text, lang_code, nlp)
+        logger.info(f"Starting semantic analysis for language: {lang_code}")
+        
+        # Procesar texto y remover stopwords
         doc = nlp(text)
-        key_concepts = identify_key_concepts(doc)
+        tokens = process_text(text, lang_code, nlp)
+        
+        # Identificar conceptos clave
+        key_concepts = identify_key_concepts(doc, stopwords=get_custom_stopwords(lang_code))
+        
+        # Crear y visualizar grafo de conceptos
         concept_graph = create_concept_graph(doc, key_concepts)
         concept_graph_fig = visualize_concept_graph(concept_graph, lang_code)
 
-        # Convertir figuras a bytes
+        # Convertir figura a bytes
         concept_graph_bytes = fig_to_bytes(concept_graph_fig)
 
-
         logger.info("Semantic analysis completed successfully")
         return {
+            'success': True,
             'key_concepts': key_concepts,
             'concept_graph': concept_graph_bytes,
         }
     except Exception as e:
         logger.error(f"Error in perform_semantic_analysis: {str(e)}")
-        raise
-
-
-def fig_to_bytes(fig):
-    buf = io.BytesIO()
-    fig.savefig(buf, format='png')
-    buf.seek(0)
-    return buf.getvalue()
-
-
-def fig_to_html(fig):
-    buf = io.BytesIO()
-    fig.savefig(buf, format='png')
-    buf.seek(0)
-    img_str = base64.b64encode(buf.getvalue()).decode()
-    return f'<img src="data:image/png;base64,{img_str}" />'
-
-
+        return {
+            'success': False,
+            'error': str(e)
+        }
 
-def identify_key_concepts(doc, min_freq=2, min_length=3):
+def identify_key_concepts(doc, stopwords, min_freq=2, min_length=3):
     """
     Identifica conceptos clave en el texto.
-    Args:
-        doc: Documento procesado por spaCy
-        min_freq: Frecuencia mínima para considerar un concepto
-        min_length: Longitud mínima de palabra para considerar
-    Returns:
-        list: Lista de tuplas (concepto, frecuencia)
     """
     try:
-        # Obtener stopwords para el idioma
-        stopwords = get_stopwords(doc.lang_)
-        
-        # Contar frecuencias de palabras
         word_freq = Counter()
         
         for token in doc:
@@ -152,19 +133,30 @@ def identify_key_concepts(doc, min_freq=2, min_length=3):
                 
                 word_freq[token.lemma_.lower()] += 1
         
-        # Filtrar por frecuencia mínima
         concepts = [(word, freq) for word, freq in word_freq.items() 
                    if freq >= min_freq]
-        
-        # Ordenar por frecuencia
         concepts.sort(key=lambda x: x[1], reverse=True)
         
-        return concepts[:10]  # Retornar los 10 conceptos más frecuentes
+        logger.info(f"Identified {len(concepts)} key concepts")
+        return concepts[:10]
         
     except Exception as e:
         logger.error(f"Error en identify_key_concepts: {str(e)}")
-        return []  # Retornar lista vacía en caso de error
+        return []
 
+def fig_to_bytes(fig):
+    buf = io.BytesIO()
+    fig.savefig(buf, format='png')
+    buf.seek(0)
+    return buf.getvalue()
+
+
+def fig_to_html(fig):
+    buf = io.BytesIO()
+    fig.savefig(buf, format='png')
+    buf.seek(0)
+    img_str = base64.b64encode(buf.getvalue()).decode()
+    return f'<img src="data:image/png;base64,{img_str}" />'
 
 def create_concept_graph(doc, key_concepts):
     """