Update modules/syntax_analysis.py

modules/syntax_analysis.py

@@ -5,12 +5,7 @@ import networkx as nx
 import matplotlib.pyplot as plt
 from collections import Counter
 
-@st.cache_resource
-def load_spacy_model():
-    return spacy.load("es_core_news_lg")
-
-# Load spaCy model
-nlp = spacy.load("es_core_news_lg")
+# Remove the global nlp model loading
 
 # Define colors for grammatical categories
 POS_COLORS = {
@@ -33,28 +28,66 @@ POS_COLORS = {
 }
 
 POS_TRANSLATIONS = {
-    'ADJ': 'Adjetivo',
-    'ADP': 'Advposición',
-    'ADV': 'Adverbio',
-    'AUX': 'Auxiliar',
-    'CCONJ': 'Conjunción Coordinante',
-    'DET': 'Determinante',
-    'INTJ': 'Interjección',
-    'NOUN': 'Sustantivo',
-    'NUM': 'Número',
-    'PART': 'Partícula',
-    'PRON': 'Pronombre',
-    'PROPN': 'Nombre Propio',
-    'SCONJ': 'Conjunción Subordinante',
-    'SYM': 'Símbolo',
-    'VERB': 'Verbo',
-    'X': 'Otro',
+    'es': {
+        'ADJ': 'Adjetivo',
+        'ADP': 'Adposición',
+        'ADV': 'Adverbio',
+        'AUX': 'Auxiliar',
+        'CCONJ': 'Conjunción Coordinante',
+        'DET': 'Determinante',
+        'INTJ': 'Interjección',
+        'NOUN': 'Sustantivo',
+        'NUM': 'Número',
+        'PART': 'Partícula',
+        'PRON': 'Pronombre',
+        'PROPN': 'Nombre Propio',
+        'SCONJ': 'Conjunción Subordinante',
+        'SYM': 'Símbolo',
+        'VERB': 'Verbo',
+        'X': 'Otro',
+    },
+    'en': {
+        'ADJ': 'Adjective',
+        'ADP': 'Adposition',
+        'ADV': 'Adverb',
+        'AUX': 'Auxiliary',
+        'CCONJ': 'Coordinating Conjunction',
+        'DET': 'Determiner',
+        'INTJ': 'Interjection',
+        'NOUN': 'Noun',
+        'NUM': 'Number',
+        'PART': 'Particle',
+        'PRON': 'Pronoun',
+        'PROPN': 'Proper Noun',
+        'SCONJ': 'Subordinating Conjunction',
+        'SYM': 'Symbol',
+        'VERB': 'Verb',
+        'X': 'Other',
+    },
+    'fr': {
+        'ADJ': 'Adjectif',
+        'ADP': 'Adposition',
+        'ADV': 'Adverbe',
+        'AUX': 'Auxiliaire',
+        'CCONJ': 'Conjonction de Coordination',
+        'DET': 'Déterminant',
+        'INTJ': 'Interjection',
+        'NOUN': 'Nom',
+        'NUM': 'Nombre',
+        'PART': 'Particule',
+        'PRON': 'Pronom',
+        'PROPN': 'Nom Propre',
+        'SCONJ': 'Conjonction de Subordination',
+        'SYM': 'Symbole',
+        'VERB': 'Verbe',
+        'X': 'Autre',
+    }
 }
 
 def count_pos(doc):
     return Counter(token.pos_ for token in doc if token.pos_ != 'PUNCT')
 
-def create_syntax_graph(doc):
+def create_syntax_graph(doc, lang):
     G = nx.DiGraph()
     pos_counts = count_pos(doc)
     word_nodes = {}
@@ -69,7 +102,7 @@ def create_syntax_graph(doc):
                 color = POS_COLORS.get(token.pos_, '#FFFFFF')
                 word_colors[lower_text] = color
                 G.add_node(node_id,
-                           label=f"{token.text}\n[{POS_TRANSLATIONS.get(token.pos_, token.pos_)}]",
+                           label=f"{token.text}\n[{POS_TRANSLATIONS[lang].get(token.pos_, token.pos_)}]",
                            pos=token.pos_,
                            size=pos_counts[token.pos_] * 500,
                            color=color)
@@ -81,8 +114,8 @@ def create_syntax_graph(doc):
 
     return G, word_colors
 
-def visualize_syntax_graph(doc):
-    G, word_colors = create_syntax_graph(doc)
+def visualize_syntax_graph(doc, lang):
+    G, word_colors = create_syntax_graph(doc, lang)
 
     plt.figure(figsize=(20, 15))
     pos = nx.spring_layout(G, k=2, iterations=100)
@@ -97,24 +130,23 @@ def visualize_syntax_graph(doc):
     edge_labels = nx.get_edge_attributes(G, 'label')
     nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8)
 
-    plt.title("Análisis Sintáctico")
+    plt.title("Syntactic Analysis" if lang == 'en' else "Analyse Syntaxique" if lang == 'fr' else "Análisis Sintáctico")
     plt.axis('off')
 
-    legend_elements = [plt.Rectangle((0,0),1,1, facecolor=color, edgecolor='none', label=f"{POS_TRANSLATIONS[pos]} ({count_pos(doc)[pos]})")
+    legend_elements = [plt.Rectangle((0,0),1,1, facecolor=color, edgecolor='none', label=f"{POS_TRANSLATIONS[lang][pos]} ({count_pos(doc)[pos]})")
                        for pos, color in POS_COLORS.items() if pos in set(nx.get_node_attributes(G, 'pos').values())]
     plt.legend(handles=legend_elements, loc='center left', bbox_to_anchor=(1, 0.5))
 
     return plt
 
-def visualize_syntax(text):
+def visualize_syntax(text, nlp, lang):
     max_tokens = 5000
     doc = nlp(text)
     if len(doc) > max_tokens:
         doc = nlp(text[:max_tokens])
         print(f"Warning: The input text is too long. Only the first {max_tokens} tokens will be visualized.")
-    return visualize_syntax_graph(doc)
+    return visualize_syntax_graph(doc, lang)
 
-# Repeated words colors
 def get_repeated_words_colors(doc):
     word_counts = Counter(token.text.lower() for token in doc if token.pos_ != 'PUNCT')
     repeated_words = {word: count for word, count in word_counts.items() if count > 1}