File size: 9,020 Bytes
55c034b 831e193 b6ee9f7 831e193 72b2a4f 1ee3f25 1966cb7 1910fa3 831e193 1910fa3 72b2a4f 87370f4 72b2a4f 87370f4 40c546c 72b2a4f 0172e7f 1910fa3 0172e7f 1910fa3 40c546c 0172e7f 87370f4 054d2c2 0172e7f e33c25b 0172e7f 1910fa3 87370f4 1910fa3 e33c25b 1910fa3 0172e7f e33c25b 0172e7f e33c25b 0172e7f 87370f4 40c546c 0172e7f 1910fa3 87370f4 0172e7f 409ec3b 0172e7f 409ec3b 0172e7f 409ec3b 0172e7f 409ec3b f0d8559 0172e7f 87370f4 831e193 1910fa3 ebc275b 0172e7f 5bd23d0 407e78c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 |
#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 para layout estable
st.markdown("""
<style>
.stTextArea textarea {
font-size: 1rem;
line-height: 1.5;
min-height: 100px !important;
height: 100px !important;
}
.arc-diagram-container {
width: 100%;
padding: 0.5rem;
margin: 0.5rem 0;
}
</style>
""", unsafe_allow_html=True)
# Estado consistente
if 'morpho_state' not in st.session_state:
st.session_state.morpho_state = {
'original_text': '',
'original_analysis': None,
'iteration_text': '',
'iteration_analysis': None,
'analysis_count': 0,
'show_original': False,
'show_iteration': False
}
# Contenedor para entrada original
with st.container():
text_key = f"original_text_{st.session_state.morpho_state['analysis_count']}"
text_input = st.text_area(
"",
value=st.session_state.morpho_state['original_text'],
key=text_key,
height=100
)
col1, col2, col3 = st.columns([2,1,2])
with col1:
analyze_button = st.button(
"Analizar Texto Original",
type="primary",
use_container_width=True
)
# Contenedor para visualizaciones
diagram_container = st.container()
iteration_container = st.container()
# Procesar texto original
if analyze_button and text_input.strip():
try:
doc = nlp_models[lang_code](text_input)
analysis = perform_advanced_morphosyntactic_analysis(
text_input,
nlp_models[lang_code]
)
st.session_state.morpho_state.update({
'original_text': text_input,
'original_analysis': {'doc': doc, 'analysis': analysis},
'iteration_text': text_input,
'show_original': True,
'analysis_count': st.session_state.morpho_state['analysis_count'] + 1
})
if store_student_morphosyntax_result(
username=st.session_state.username,
text=text_input,
arc_diagrams=analysis['arc_diagrams']
):
with diagram_container:
st.subheader("An谩lisis Original")
display_morphosyntax_results(
st.session_state.morpho_state['original_analysis'],
lang_code,
morpho_t
)
except Exception as e:
st.error("Error al procesar texto original")
logger.error(f"Error: {str(e)}")
# Mostrar secci贸n de iteraci贸n si hay an谩lisis original
if st.session_state.morpho_state.get('show_original', False):
with iteration_container:
st.markdown("---")
iteration_key = f"iteration_{st.session_state.morpho_state['analysis_count']}"
iteration_text = st.text_area(
"",
value=st.session_state.morpho_state['iteration_text'],
key=iteration_key,
height=100
)
col1, col2, col3 = st.columns([2,1,2])
with col1:
iterate_button = st.button(
"Analizar Cambios",
type="primary",
use_container_width=True
)
if iterate_button and iteration_text.strip():
try:
doc_iter = nlp_models[lang_code](iteration_text)
analysis_iter = perform_advanced_morphosyntactic_analysis(
iteration_text,
nlp_models[lang_code]
)
st.session_state.morpho_state.update({
'iteration_text': iteration_text,
'iteration_analysis': {'doc': doc_iter, 'analysis': analysis_iter},
'show_iteration': True
})
if store_student_morphosyntax_result(
username=st.session_state.username,
text=iteration_text,
arc_diagrams=analysis_iter['arc_diagrams']
):
with diagram_container:
st.empty() # Limpiar contenedor
# Mostrar original
st.subheader("An谩lisis Original")
display_morphosyntax_results(
st.session_state.morpho_state['original_analysis'],
lang_code,
morpho_t
)
st.markdown("---")
# Mostrar iteraci贸n
st.subheader("An谩lisis de Cambios")
display_morphosyntax_results(
{'doc': doc_iter, 'analysis': analysis_iter},
lang_code,
morpho_t
)
except Exception as e:
st.error("Error al procesar iteraci贸n")
logger.error(f"Error: {str(e)}")
except Exception as e:
st.error("Error general en la interfaz")
logger.error(f"Error: {str(e)}")
############################################################################
def display_morphosyntax_results(result, lang_code, morpho_t):
"""
Muestra solo el diagrama de arco.
Args:
result: Diccionario con el documento procesado y su an谩lisis
lang_code: C贸digo del idioma
morpho_t: Diccionario de traducciones
"""
if result is None:
return
try:
doc = result['doc']
sentences = list(doc.sents)
for i, sent in enumerate(sentences):
try:
st.subheader(f"{morpho_t.get('sentence', 'Sentence')} {i+1}")
html = displacy.render(sent, style="dep", options={
"distance": 100,
"arrow_spacing": 20,
"word_spacing": 30
})
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)
html = f'<div class="arc-diagram-container">{html}</div>'
st.write(html, unsafe_allow_html=True)
except Exception as e:
logger.error(f"Error en diagrama {i}: {str(e)}")
continue
except Exception as e:
logger.error(f"Error en display_morphosyntax_results: {str(e)}")
|