Update app.py

app.py

@@ -1,96 +1,118 @@
-
 # app.py
 import os
 os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
 os.environ['KMP_DUPLICATE_LIB_OK']='TRUE'
 
 import streamlit as st
+import spacy
+from spacy import displacy
+import re
 
 # Configure the page to use the full width
 st.set_page_config(
     page_title="AIdeaText",
     layout="wide",
-    page_icon="random"        
-    )
-
-import spacy
-from spacy import displacy
-import re
-import pydantic
-import numpy as np 
-import thinc
-
-#st.write(f"spaCy version: {spacy.__version__}")
-#st.write(f"Pydantic version: {pydantic.__version__}")
-#st.write(f"NumPy version: {np.__version__}")
-#st.write(f"Thinc version: {thinc.__version__}")
+    page_icon="random"
+)
 
 from modules.syntax_analysis import highlight_repeated_words, get_repeated_words_colors, POS_COLORS, POS_TRANSLATIONS, visualize_syntax
 
 @st.cache_resource
-def load_spacy_model():
-    return spacy.load("es_core_news_lg")
-
-#@st.cache_resource
-#def load_spacy_model():
-#    try:
-#        nlp = spacy.load("es_core_news_lg")
-#    except IOError:
-#        st.info("Downloading spaCy model...")
-#        spacy.cli.download("es_core_news_lg")
-#        nlp = spacy.load("es_core_news_lg")
-#    return nlp
-
-# Load spaCy model
-nlp = spacy.load("es_core_news_lg")
-
-st.markdown("### AIdeaText")
-st.markdown("##### Análisis morfológico y sintáctico")
-
-# First horizontal band: Text Input
-sentence_input = st.text_area("Ingresa un texto para analizar (max 5,000 words):", height=150)
-
-if st.button("Analizar texto"):
+def load_spacy_models():
+    return {
+        'es': spacy.load("es_core_news_lg"),
+        'en': spacy.load("en_core_web_lg"),
+        'fr': spacy.load("fr_core_news_lg")
+    }
+
+# Load spaCy models
+nlp_models = load_spacy_models()
+
+# Language selection
+languages = {
+    'Español': 'es',
+    'English': 'en',
+    'Français': 'fr'
+}
+selected_lang = st.sidebar.selectbox("Select Language / Seleccione el idioma / Choisissez la langue", list(languages.keys()))
+lang_code = languages[selected_lang]
+
+# Translations
+translations = {
+    'es': {
+        'title': "AIdeaText - Análisis morfológico y sintáctico",
+        'input_label': "Ingrese un texto para analizar (máx. 5,000 palabras):",
+        'input_placeholder': "Escriba o pegue su texto aquí...",
+        'analyze_button': "Analizar texto",
+        'repeated_words': "Palabras repetidas",
+        'legend': "Leyenda: Categorías gramaticales",
+        'arc_diagram': "Análisis sintáctico: Diagrama de arco",
+        'network_diagram': "Análisis sintáctico: Diagrama de red",
+        'sentence': "Oración"
+    },
+    'en': {
+        'title': "AIdeaText - Morphological and Syntactic Analysis",
+        'input_label': "Enter a text to analyze (max 5,000 words):",
+        'input_placeholder': "Type or paste your text here...",
+        'analyze_button': "Analyze text",
+        'repeated_words': "Repeated words",
+        'legend': "Legend: Grammatical categories",
+        'arc_diagram': "Syntactic analysis: Arc diagram",
+        'network_diagram': "Syntactic analysis: Network diagram",
+        'sentence': "Sentence"
+    },
+    'fr': {
+        'title': "AIdeaText - Analyse morphologique et syntaxique",
+        'input_label': "Entrez un texte à analyser (max 5 000 mots) :",
+        'input_placeholder': "Tapez ou collez votre texte ici...",
+        'analyze_button': "Analyser le texte",
+        'repeated_words': "Mots répétés",
+        'legend': "Légende : Catégories grammaticales",
+        'arc_diagram': "Analyse syntaxique : Diagramme en arc",
+        'network_diagram': "Analyse syntaxique : Diagramme de réseau",
+        'sentence': "Phrase"
+    }
+}
+
+# Use translations
+t = translations[lang_code]
+
+st.markdown(f"### {t['title']}")
+
+# Text Input with instructions
+sentence_input = st.text_area(t['input_label'], height=150, placeholder=t['input_placeholder'])
+
+if st.button(t['analyze_button']):
     if sentence_input:
-        doc = nlp(sentence_input)
+        doc = nlp_models[lang_code](sentence_input)
 
-        # Second horizontal band: Highlighted Repeated Words
-        with st.expander("Palabras repetidas", expanded=True):
-            #st.markdown("#### Palabras repetidas")
-            #st.write("En esta sección, se indican las palabras repetidas por categoría gramatical.")
+        # Highlighted Repeated Words
+        with st.expander(t['repeated_words'], expanded=True):
             word_colors = get_repeated_words_colors(doc)
             highlighted_text = highlight_repeated_words(doc, word_colors)
             st.markdown(highlighted_text, unsafe_allow_html=True)
 
-            # Legend for grammatical categories
-            st.markdown("##### Legenda: Categorías gramaticales")
-            legend_html = "<div style='display: flex; flex-wrap: wrap;'>"
-            for pos, color in POS_COLORS.items():
-                if pos in POS_TRANSLATIONS:
-                    legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[pos]}</span></div>"
-            legend_html += "</div>"
-            st.markdown(legend_html, unsafe_allow_html=True)
-
-        # Third horizontal band: Arc Diagram
-        with st.expander("Análisis sintáctico: Diagrama de arco", expanded=True):
-            #st.write("This section displays the syntactic structure of each sentence using arc diagrams.")
-
+        # Legend for grammatical categories
+        st.markdown(f"##### {t['legend']}")
+        legend_html = "<div style='display: flex; flex-wrap: wrap;'>"
+        for pos, color in POS_COLORS.items():
+            if pos in POS_TRANSLATIONS:
+                legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[pos]}</span></div>"
+        legend_html += "</div>"
+        st.markdown(legend_html, unsafe_allow_html=True)
+
+        # Arc Diagram
+        with st.expander(t['arc_diagram'], expanded=True):
             sentences = list(doc.sents)
             for i, sent in enumerate(sentences):
-                st.subheader(f"Sentence {i+1}")
+                st.subheader(f"{t['sentence']} {i+1}")
                 html = displacy.render(sent, style="dep", options={"distance": 100})
-                # Reduce the height of the SVG
                 html = html.replace('height="375"', 'height="200"')
-                # Reduce the top margin of the SVG
                 html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html)
-                html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"',
-                          lambda m: f'<g transform="translate({m.group(1)},50)"', html)
+                html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"', lambda m: f'<g transform="translate({m.group(1)},50)"', html)
                 st.write(html, unsafe_allow_html=True)
 
-        # Fourth horizontal band: Network graph
-        with st.expander("Análisis sintáctico: Diagrama de red", expanded=True):
-            #st.markdown("#### Análisis sintáctico: Diagrama de red")
-            #st.write("Esta sección muestra la estructura sintáctica del texto completo usando un diagrama de red.")
-
-            fig = visualize_syntax(sentence_input)
+        # Network graph
+        with st.expander(t['network_diagram'], expanded=True):
+            fig = visualize_syntax(sentence_input, nlp_models[lang_code])
             st.pyplot(fig)