modules/morphosyntax/morphosyntax_interface.py

import streamlit as st
from streamlit_float import *
from streamlit_antd_components import *
from streamlit.components.v1 import html
import spacy
from spacy import displacy
import spacy_streamlit
import pandas as pd
import base64
import re

from .morphosyntax_process import (
    process_morphosyntactic_input,
    format_analysis_results,
    perform_advanced_morphosyntactic_analysis,
    get_repeated_words_colors,
    highlight_repeated_words,
    POS_COLORS,
    POS_TRANSLATIONS
)

from ..utils.widget_utils import generate_unique_key
from ..database.morphosintax_mongo_db import store_student_morphosyntax_result
from ..database.chat_mongo_db import store_chat_history, get_chat_history

import logging
logger = logging.getLogger(__name__)

def display_morphosyntax_interface(lang_code, nlp_models, morpho_t):
    try:
        # CSS para mejorar la estabilidad y prevenir saltos
        st.markdown("""
            <style>
            .stTextArea textarea {
                font-size: 1rem;
                line-height: 1.5;
                resize: vertical;
            }
            .block-container {
                padding-top: 1rem;
                padding-bottom: 1rem;
            }
            .stExpander {
                border: none;
                box-shadow: 0 1px 2px rgba(0,0,0,0.1);
                margin-bottom: 1rem;
            }
            .legend-container {
                position: sticky;
                top: 0;
                background: white;
                z-index: 100;
                padding: 0.5rem 0;
                border-bottom: 1px solid #eee;
            }
            </style>
        """, unsafe_allow_html=True)

        # 1. Inicializar el estado
        if 'morphosyntax_state' not in st.session_state:
            st.session_state.morphosyntax_state = {
                'input_text': "",
                'analysis_count': 0,
                'last_analysis': None,
                'current_tab': 0
            }

        # 2. Contenedor principal con diseño sticky
        with st.container():
            # Campo de entrada de texto
            input_key = f"morpho_input_{st.session_state.morphosyntax_state['analysis_count']}"
            sentence_input = st.text_area(
                morpho_t.get('morpho_input_label', 'Enter text to analyze'),
                height=150,
                placeholder=morpho_t.get('morpho_input_placeholder', 'Enter your text here...'),
                key=input_key,
                on_change=lambda: None  # Previene recargas innecesarias
            )

            # 3. Botón de análisis centrado
            col1, col2, col3 = st.columns([2,1,2])
            with col1:
                analyze_button = st.button(
                    morpho_t.get('morpho_analyze_button', 'Analyze Morphosyntax'),
                    key=f"morpho_button_{st.session_state.morphosyntax_state['analysis_count']}",
                    type="primary",
                    icon="🔍",
                    disabled=not bool(sentence_input.strip()),
                    use_container_width=True
                )

            # 4. Procesar análisis
            if analyze_button and sentence_input.strip():
                try:
                    with st.spinner(morpho_t.get('processing', 'Processing...')):
                        doc = nlp_models[lang_code](sentence_input)
                        advanced_analysis = perform_advanced_morphosyntactic_analysis(
                            sentence_input,
                            nlp_models[lang_code]
                        )

                        st.session_state.morphosyntax_result = {
                            'doc': doc,
                            'advanced_analysis': advanced_analysis
                        }
                        st.session_state.morphosyntax_state['analysis_count'] += 1

                        # Guardar resultado
                        if store_student_morphosyntax_result(
                            username=st.session_state.username,
                            text=sentence_input,
                            arc_diagrams=advanced_analysis['arc_diagrams']
                        ):
                            st.success(morpho_t.get('success_message', 'Analysis saved successfully'))
                            st.session_state.morphosyntax_state['current_tab'] = 0
                            display_morphosyntax_results(
                                st.session_state.morphosyntax_result,
                                lang_code,
                                morpho_t
                            )
                        else:
                            st.error(morpho_t.get('error_message', 'Error saving analysis'))

                except Exception as e:
                    logger.error(f"Error en análisis morfosintáctico: {str(e)}")
                    st.error(morpho_t.get('error_processing', f'Error processing text: {str(e)}'))

            # 5. Mostrar resultados previos
            elif 'morphosyntax_result' in st.session_state and st.session_state.morphosyntax_result:
                display_morphosyntax_results(
                    st.session_state.morphosyntax_result,
                    lang_code,
                    morpho_t
                )
            elif not sentence_input.strip():
                st.info(morpho_t.get('morpho_initial_message', 'Enter text to begin analysis'))

    except Exception as e:
        logger.error(f"Error general en display_morphosyntax_interface: {str(e)}")
        st.error("Se produjo un error. Por favor, intente de nuevo.")

def display_morphosyntax_results(result, lang_code, morpho_t):
    if result is None:
        st.warning(morpho_t.get('no_results', 'No results available'))
        return

    doc = result['doc']
    advanced_analysis = result['advanced_analysis']

    # Leyenda fija en la parte superior
    with st.container():
        st.markdown(f"##### {morpho_t.get('legend', 'Legend: Grammatical categories')}")
        legend_html = "<div class='legend-container'><div style='display: flex; flex-wrap: wrap;'>"
        for pos, color in POS_COLORS.items():
            if pos in POS_TRANSLATIONS[lang_code]:
                legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[lang_code][pos]}</span></div>"
        legend_html += "</div></div>"
        st.markdown(legend_html, unsafe_allow_html=True)

    # Palabras repetidas
    with st.expander(morpho_t.get('repeated_words', '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)

    # Análisis sintáctico (diagramas de arco)
    with st.expander(morpho_t.get('arc_diagram', 'Syntactic analysis: Arc diagram'), expanded=True):
        sentences = list(doc.sents)
        for i, sent in enumerate(sentences):
            st.subheader(f"{morpho_t.get('sentence', 'Sentence')} {i+1}")
            html = displacy.render(sent, style="dep", options={"distance": 100})
            html = html.replace('height="375"', 'height="200"')
            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)

    # Estructura de oraciones
    with st.expander(morpho_t.get('sentence_structure', 'Sentence structure'), expanded=True):
        for i, sent_analysis in enumerate(advanced_analysis['sentence_structure']):
            sentence_str = (
                f"**{morpho_t.get('sentence', 'Sentence')} {i+1}** "
                f"{morpho_t.get('root', 'Root')}: {sent_analysis['root']} ({sent_analysis['root_pos']}) -- "
                f"{morpho_t.get('subjects', 'Subjects')}: {', '.join(sent_analysis['subjects'])} -- "
                f"{morpho_t.get('objects', 'Objects')}: {', '.join(sent_analysis['objects'])} -- "
                f"{morpho_t.get('verbs', 'Verbs')}: {', '.join(sent_analysis['verbs'])}"
            )
            st.markdown(sentence_str)

    # Análisis de categorías gramaticales
    with st.expander(morpho_t.get('pos_analysis', 'Part of speech'), expanded=True):
        pos_df = pd.DataFrame(advanced_analysis['pos_analysis'])
        pos_df['pos'] = pos_df['pos'].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x))
        pos_df = pos_df.rename(columns={
            'pos': morpho_t.get('grammatical_category', 'Grammatical category'),
            'count': morpho_t.get('count', 'Count'),
            'percentage': morpho_t.get('percentage', 'Percentage'),
            'examples': morpho_t.get('examples', 'Examples')
        })
        st.dataframe(pos_df, use_container_width=True)

    # Análisis morfológico
    with st.expander(morpho_t.get('morphological_analysis', 'Morphological Analysis'), expanded=True):
        morph_df = pd.DataFrame(advanced_analysis['morphological_analysis'])
        column_mapping = {
            'text': morpho_t.get('word', 'Word'),
            'lemma': morpho_t.get('lemma', 'Lemma'),
            'pos': morpho_t.get('grammatical_category', 'Grammatical category'),
            'dep': morpho_t.get('dependency', 'Dependency'),
            'morph': morpho_t.get('morphology', 'Morphology')
        }
        morph_df = morph_df.rename(columns=column_mapping)
        
        # Traducir categorías gramaticales
        grammatical_category = morpho_t.get('grammatical_category', 'Grammatical category')
        morph_df[grammatical_category] = morph_df[grammatical_category].map(
            lambda x: POS_TRANSLATIONS[lang_code].get(x, x)
        )

        # Aplicar traducciones de dependencias y morfología
        dependency = morpho_t.get('dependency', 'Dependency')
        morphology = morpho_t.get('morphology', 'Morphology')
        
        def translate_morph(morph_string, lang_code):
            for key, value in morph_translations[lang_code].items():
                morph_string = morph_string.replace(key, value)
            return morph_string

        morph_df[dependency] = morph_df[dependency].map(
            lambda x: dep_translations[lang_code].get(x, x)
        )
        morph_df[morphology] = morph_df[morphology].apply(
            lambda x: translate_morph(x, lang_code)
        )
        
        st.dataframe(morph_df, use_container_width=True)