Spaces:
Running
Running
#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__) | |
########################################################################### | |
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 | |
############################################################################ | |
def display_morphosyntax_interface(lang_code, nlp_models, morpho_t): | |
try: | |
# CSS mejorado para estabilidad, layout y prevenci贸n de saltos | |
st.markdown(""" | |
<style> | |
.stTextArea textarea { | |
font-size: 1rem; | |
line-height: 1.5; | |
padding: 0.5rem; | |
border-radius: 0.375rem; | |
border: 1px solid #e2e8f0; | |
background-color: white; | |
min-height: 100px !important; | |
height: 100px !important; | |
} | |
.arc-diagram-container { | |
width: 100%; | |
overflow-x: auto; | |
background-color: white; | |
padding: 0.5rem; | |
border-radius: 0.375rem; | |
box-shadow: 0 2px 4px rgba(0,0,0,0.1); | |
margin: 0.5rem 0; | |
} | |
.stTab { | |
position: sticky; | |
top: 0; | |
z-index: 999; | |
} | |
[data-testid="stVerticalBlock"] { | |
gap: 0 !important; | |
} | |
</style> | |
""", unsafe_allow_html=True) | |
# Inicializaci贸n del estado | |
if 'current_tab' not in st.session_state: | |
st.session_state.current_tab = "morphosyntax" | |
if 'morphosyntax_state' not in st.session_state: | |
st.session_state.morphosyntax_state = {} | |
default_state = { | |
'original_text': '', | |
'original_analysis': None, | |
'current_text': '', | |
'current_analysis': None, | |
'analysis_count': 0, | |
'show_original': False, | |
'show_iteration': False | |
} | |
for key, default_value in default_state.items(): | |
if key not in st.session_state.morphosyntax_state: | |
st.session_state.morphosyntax_state[key] = default_value | |
def update_analysis(): | |
st.session_state.current_tab = "morphosyntax" # Mantener tab activo | |
# Secci贸n del texto original - Layout simplificado | |
st.text_area( | |
"", # Label vac铆o | |
value=st.session_state.morphosyntax_state['original_text'], | |
key="original_text_input", | |
placeholder="Ingresar solo una oraci贸n hasta el punto y aparte.", | |
height=100, | |
on_change=update_analysis | |
) | |
col1, col2, col3 = st.columns([2,1,2]) | |
with col1: | |
analyze_original = st.button( | |
"Analizar Texto Original", | |
type="primary", | |
use_container_width=True, | |
disabled=not bool(st.session_state.get("original_text_input", "").strip()) | |
) | |
# Procesar y mostrar texto original | |
if analyze_original and st.session_state.get("original_text_input", "").strip(): | |
try: | |
with st.spinner(""): # Spinner sin texto | |
doc = nlp_models[lang_code](st.session_state.original_text_input) | |
analysis = perform_advanced_morphosyntactic_analysis( | |
st.session_state.original_text_input, | |
nlp_models[lang_code] | |
) | |
st.session_state.morphosyntax_state.update({ | |
'original_text': st.session_state.original_text_input, | |
'original_analysis': {'doc': doc, 'analysis': analysis}, | |
'current_text': st.session_state.original_text_input, | |
'show_original': True, | |
'analysis_count': st.session_state.morphosyntax_state['analysis_count'] + 1 | |
}) | |
if store_student_morphosyntax_result( | |
username=st.session_state.username, | |
text=st.session_state.original_text_input, | |
arc_diagrams=analysis['arc_diagrams'] | |
): | |
st.session_state.current_tab = "morphosyntax" | |
except Exception as e: | |
logger.error(f"Error en an谩lisis original: {str(e)}") | |
st.error("Error al procesar el texto") | |
# Mostrar diagrama original si existe | |
if st.session_state.morphosyntax_state.get('show_original'): | |
display_morphosyntax_results( | |
st.session_state.morphosyntax_state['original_analysis'], | |
lang_code, | |
morpho_t | |
) | |
st.markdown("---") | |
# Secci贸n de iteraci贸n - Layout simplificado | |
iteration_text = st.text_area( | |
"", # Label vac铆o | |
value=st.session_state.morphosyntax_state['current_text'], | |
key=f"iteration_input_{st.session_state.morphosyntax_state['analysis_count']}", | |
placeholder="Modifique el texto para mejorar la estructura", | |
height=100, | |
on_change=update_analysis | |
) | |
col1, col2, col3 = st.columns([2,1,2]) | |
with col1: | |
analyze_iteration = st.button( | |
"Analizar Cambios", | |
type="primary", | |
use_container_width=True, | |
disabled=not bool(iteration_text.strip()) | |
) | |
# Procesar y mostrar iteraci贸n | |
if analyze_iteration and iteration_text.strip(): | |
try: | |
with st.spinner(""): # Spinner sin texto | |
doc = nlp_models[lang_code](iteration_text) | |
analysis = perform_advanced_morphosyntactic_analysis( | |
iteration_text, | |
nlp_models[lang_code] | |
) | |
st.session_state.morphosyntax_state.update({ | |
'current_text': iteration_text, | |
'current_analysis': {'doc': doc, 'analysis': analysis}, | |
'show_iteration': True, | |
'analysis_count': st.session_state.morphosyntax_state['analysis_count'] + 1 | |
}) | |
if store_student_morphosyntax_result( | |
username=st.session_state.username, | |
text=iteration_text, | |
arc_diagrams=analysis['arc_diagrams'] | |
): | |
# Actualizar solo el diagrama de iteraci贸n | |
display_morphosyntax_results( | |
st.session_state.morphosyntax_state['current_analysis'], | |
lang_code, | |
morpho_t | |
) | |
except Exception as e: | |
logger.error(f"Error en iteraci贸n: {str(e)}") | |
st.error("Error al procesar los cambios") | |
except Exception as e: | |
logger.error(f"Error general: {str(e)}") | |
st.error("Se produjo un error. Por favor, intente de nuevo.") | |
#########################################################################3 | |
def display_morphosyntax_results(result, lang_code, morpho_t): | |
""" | |
Muestra solo el an谩lisis sint谩ctico con diagramas de arco. | |
""" | |
if result is None: | |
st.warning(morpho_t.get('no_results', 'No results available')) | |
return | |
doc = result['doc'] | |
# An谩lisis sint谩ctico (diagramas de arco) | |
# st.markdown(f"### {morpho_t.get('arc_diagram', 'Syntactic analysis: Arc diagram')}") | |
with st.container(): | |
sentences = list(doc.sents) | |
for i, sent in enumerate(sentences): | |
with st.container(): | |
st.subheader(f"{morpho_t.get('sentence', 'Sentence')} {i+1}") | |
try: | |
html = displacy.render(sent, style="dep", options={ | |
"distance": 100, | |
"arrow_spacing": 20, | |
"word_spacing": 30 | |
}) | |
# Ajustar dimensiones del SVG | |
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) | |
# Envolver en un div con clase para estilos | |
html = f'<div class="arc-diagram-container">{html}</div>' | |
st.write(html, unsafe_allow_html=True) | |
except Exception as e: | |
logger.error(f"Error rendering sentence {i}: {str(e)}") | |
st.error(f"Error displaying diagram for sentence {i+1}") |