app.py

# app.py
!pip install https://huggingface.co/spacy/es_core_news_lg/resolve/main/es_core_news_lg-any-py3-none-any.whl

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
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__}")

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")

# Configure the page to use the full width
st.set_page_config(layout="wide", page_title="AIdeaText")

st.markdown("### AIdeaText - Advanced Text Analysis Tool")

# 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"):
    if sentence_input:
        doc = nlp(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.")
            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.")

            sentences = list(doc.sents)
            for i, sent in enumerate(sentences):
                st.subheader(f"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)
                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)
            st.pyplot(fig)