Update modules/morphosyntax/morphosyntax_interface.py
Browse files
modules/morphosyntax/morphosyntax_interface.py
CHANGED
@@ -34,50 +34,57 @@ def display_morphosyntax_interface(lang_code, nlp_models, morpho_t):
|
|
34 |
.stTextArea textarea {
|
35 |
font-size: 1rem;
|
36 |
line-height: 1.5;
|
37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
.block-container {
|
40 |
padding-top: 1rem;
|
41 |
padding-bottom: 1rem;
|
42 |
}
|
43 |
-
.
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
position: sticky;
|
50 |
-
top: 0;
|
51 |
-
background: white;
|
52 |
-
z-index: 100;
|
53 |
-
padding: 0.5rem 0;
|
54 |
-
border-bottom: 1px solid #eee;
|
55 |
}
|
56 |
</style>
|
57 |
""", unsafe_allow_html=True)
|
58 |
|
59 |
-
#
|
60 |
if 'morphosyntax_state' not in st.session_state:
|
61 |
st.session_state.morphosyntax_state = {
|
62 |
'input_text': "",
|
63 |
'analysis_count': 0,
|
64 |
'last_analysis': None,
|
65 |
-
'current_tab': 0
|
66 |
}
|
67 |
|
68 |
-
#
|
69 |
with st.container():
|
70 |
-
# Campo de entrada de texto
|
71 |
input_key = f"morpho_input_{st.session_state.morphosyntax_state['analysis_count']}"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
sentence_input = st.text_area(
|
73 |
morpho_t.get('morpho_input_label', 'Enter text to analyze'),
|
74 |
height=150,
|
75 |
-
placeholder=morpho_t.get('morpho_input_placeholder', 'Enter your text here...'),
|
76 |
key=input_key,
|
77 |
-
|
|
|
78 |
)
|
79 |
|
80 |
-
#
|
81 |
col1, col2, col3 = st.columns([2,1,2])
|
82 |
with col1:
|
83 |
analyze_button = st.button(
|
@@ -85,34 +92,39 @@ def display_morphosyntax_interface(lang_code, nlp_models, morpho_t):
|
|
85 |
key=f"morpho_button_{st.session_state.morphosyntax_state['analysis_count']}",
|
86 |
type="primary",
|
87 |
icon="🔍",
|
88 |
-
disabled=not bool(
|
89 |
use_container_width=True
|
90 |
)
|
91 |
|
92 |
-
#
|
93 |
-
if analyze_button and
|
94 |
try:
|
95 |
with st.spinner(morpho_t.get('processing', 'Processing...')):
|
96 |
-
|
|
|
|
|
|
|
97 |
advanced_analysis = perform_advanced_morphosyntactic_analysis(
|
98 |
-
|
99 |
nlp_models[lang_code]
|
100 |
)
|
101 |
|
|
|
102 |
st.session_state.morphosyntax_result = {
|
103 |
'doc': doc,
|
104 |
'advanced_analysis': advanced_analysis
|
105 |
}
|
|
|
|
|
106 |
st.session_state.morphosyntax_state['analysis_count'] += 1
|
107 |
|
108 |
-
# Guardar
|
109 |
if store_student_morphosyntax_result(
|
110 |
username=st.session_state.username,
|
111 |
-
text=
|
112 |
arc_diagrams=advanced_analysis['arc_diagrams']
|
113 |
):
|
114 |
st.success(morpho_t.get('success_message', 'Analysis saved successfully'))
|
115 |
-
st.session_state.morphosyntax_state['current_tab'] = 0
|
116 |
display_morphosyntax_results(
|
117 |
st.session_state.morphosyntax_result,
|
118 |
lang_code,
|
@@ -125,112 +137,51 @@ def display_morphosyntax_interface(lang_code, nlp_models, morpho_t):
|
|
125 |
logger.error(f"Error en análisis morfosintáctico: {str(e)}")
|
126 |
st.error(morpho_t.get('error_processing', f'Error processing text: {str(e)}'))
|
127 |
|
128 |
-
#
|
129 |
elif 'morphosyntax_result' in st.session_state and st.session_state.morphosyntax_result:
|
130 |
display_morphosyntax_results(
|
131 |
st.session_state.morphosyntax_result,
|
132 |
lang_code,
|
133 |
morpho_t
|
134 |
)
|
135 |
-
elif not sentence_input.strip():
|
136 |
-
st.info(morpho_t.get('morpho_initial_message', 'Enter text to begin analysis'))
|
137 |
|
138 |
except Exception as e:
|
139 |
logger.error(f"Error general en display_morphosyntax_interface: {str(e)}")
|
140 |
st.error("Se produjo un error. Por favor, intente de nuevo.")
|
141 |
|
142 |
def display_morphosyntax_results(result, lang_code, morpho_t):
|
|
|
|
|
|
|
143 |
if result is None:
|
144 |
st.warning(morpho_t.get('no_results', 'No results available'))
|
145 |
return
|
146 |
|
147 |
doc = result['doc']
|
148 |
-
advanced_analysis = result['advanced_analysis']
|
149 |
-
|
150 |
-
# Leyenda fija en la parte superior
|
151 |
-
with st.container():
|
152 |
-
st.markdown(f"##### {morpho_t.get('legend', 'Legend: Grammatical categories')}")
|
153 |
-
legend_html = "<div class='legend-container'><div style='display: flex; flex-wrap: wrap;'>"
|
154 |
-
for pos, color in POS_COLORS.items():
|
155 |
-
if pos in POS_TRANSLATIONS[lang_code]:
|
156 |
-
legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[lang_code][pos]}</span></div>"
|
157 |
-
legend_html += "</div></div>"
|
158 |
-
st.markdown(legend_html, unsafe_allow_html=True)
|
159 |
-
|
160 |
-
# Palabras repetidas
|
161 |
-
with st.expander(morpho_t.get('repeated_words', 'Repeated words'), expanded=True):
|
162 |
-
word_colors = get_repeated_words_colors(doc)
|
163 |
-
highlighted_text = highlight_repeated_words(doc, word_colors)
|
164 |
-
st.markdown(highlighted_text, unsafe_allow_html=True)
|
165 |
|
166 |
# Análisis sintáctico (diagramas de arco)
|
167 |
-
|
|
|
|
|
168 |
sentences = list(doc.sents)
|
169 |
for i, sent in enumerate(sentences):
|
170 |
-
st.
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
# Análisis de categorías gramaticales
|
191 |
-
with st.expander(morpho_t.get('pos_analysis', 'Part of speech'), expanded=True):
|
192 |
-
pos_df = pd.DataFrame(advanced_analysis['pos_analysis'])
|
193 |
-
pos_df['pos'] = pos_df['pos'].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x))
|
194 |
-
pos_df = pos_df.rename(columns={
|
195 |
-
'pos': morpho_t.get('grammatical_category', 'Grammatical category'),
|
196 |
-
'count': morpho_t.get('count', 'Count'),
|
197 |
-
'percentage': morpho_t.get('percentage', 'Percentage'),
|
198 |
-
'examples': morpho_t.get('examples', 'Examples')
|
199 |
-
})
|
200 |
-
st.dataframe(pos_df, use_container_width=True)
|
201 |
-
|
202 |
-
# Análisis morfológico
|
203 |
-
with st.expander(morpho_t.get('morphological_analysis', 'Morphological Analysis'), expanded=True):
|
204 |
-
morph_df = pd.DataFrame(advanced_analysis['morphological_analysis'])
|
205 |
-
column_mapping = {
|
206 |
-
'text': morpho_t.get('word', 'Word'),
|
207 |
-
'lemma': morpho_t.get('lemma', 'Lemma'),
|
208 |
-
'pos': morpho_t.get('grammatical_category', 'Grammatical category'),
|
209 |
-
'dep': morpho_t.get('dependency', 'Dependency'),
|
210 |
-
'morph': morpho_t.get('morphology', 'Morphology')
|
211 |
-
}
|
212 |
-
morph_df = morph_df.rename(columns=column_mapping)
|
213 |
-
|
214 |
-
# Traducir categorías gramaticales
|
215 |
-
grammatical_category = morpho_t.get('grammatical_category', 'Grammatical category')
|
216 |
-
morph_df[grammatical_category] = morph_df[grammatical_category].map(
|
217 |
-
lambda x: POS_TRANSLATIONS[lang_code].get(x, x)
|
218 |
-
)
|
219 |
-
|
220 |
-
# Aplicar traducciones de dependencias y morfología
|
221 |
-
dependency = morpho_t.get('dependency', 'Dependency')
|
222 |
-
morphology = morpho_t.get('morphology', 'Morphology')
|
223 |
-
|
224 |
-
def translate_morph(morph_string, lang_code):
|
225 |
-
for key, value in morph_translations[lang_code].items():
|
226 |
-
morph_string = morph_string.replace(key, value)
|
227 |
-
return morph_string
|
228 |
-
|
229 |
-
morph_df[dependency] = morph_df[dependency].map(
|
230 |
-
lambda x: dep_translations[lang_code].get(x, x)
|
231 |
-
)
|
232 |
-
morph_df[morphology] = morph_df[morphology].apply(
|
233 |
-
lambda x: translate_morph(x, lang_code)
|
234 |
-
)
|
235 |
-
|
236 |
-
st.dataframe(morph_df, use_container_width=True)
|
|
|
34 |
.stTextArea textarea {
|
35 |
font-size: 1rem;
|
36 |
line-height: 1.5;
|
37 |
+
padding: 0.5rem;
|
38 |
+
border-radius: 0.375rem;
|
39 |
+
border: 1px solid #e2e8f0;
|
40 |
+
background-color: white;
|
41 |
+
}
|
42 |
+
.stTextArea textarea:focus {
|
43 |
+
border-color: #3182ce;
|
44 |
+
box-shadow: 0 0 0 3px rgba(66, 153, 225, 0.5);
|
45 |
}
|
46 |
.block-container {
|
47 |
padding-top: 1rem;
|
48 |
padding-bottom: 1rem;
|
49 |
}
|
50 |
+
.arc-diagram-container {
|
51 |
+
background-color: white;
|
52 |
+
padding: 1rem;
|
53 |
+
border-radius: 0.5rem;
|
54 |
+
box-shadow: 0 1px 3px rgba(0,0,0,0.1);
|
55 |
+
margin-top: 1rem;
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
}
|
57 |
</style>
|
58 |
""", unsafe_allow_html=True)
|
59 |
|
60 |
+
# Inicializar el estado
|
61 |
if 'morphosyntax_state' not in st.session_state:
|
62 |
st.session_state.morphosyntax_state = {
|
63 |
'input_text': "",
|
64 |
'analysis_count': 0,
|
65 |
'last_analysis': None,
|
|
|
66 |
}
|
67 |
|
68 |
+
# Contenedor principal con manejo de estado mejorado
|
69 |
with st.container():
|
70 |
+
# Campo de entrada de texto con manejo de estado explícito
|
71 |
input_key = f"morpho_input_{st.session_state.morphosyntax_state['analysis_count']}"
|
72 |
+
|
73 |
+
# Función para manejar cambios en el texto
|
74 |
+
def on_text_change():
|
75 |
+
text = st.session_state[input_key]
|
76 |
+
st.session_state.morphosyntax_state['input_text'] = text
|
77 |
+
|
78 |
+
# Campo de texto con callback
|
79 |
sentence_input = st.text_area(
|
80 |
morpho_t.get('morpho_input_label', 'Enter text to analyze'),
|
81 |
height=150,
|
|
|
82 |
key=input_key,
|
83 |
+
placeholder=morpho_t.get('morpho_input_placeholder', 'Enter your text here...'),
|
84 |
+
on_change=on_text_change
|
85 |
)
|
86 |
|
87 |
+
# Botón de análisis
|
88 |
col1, col2, col3 = st.columns([2,1,2])
|
89 |
with col1:
|
90 |
analyze_button = st.button(
|
|
|
92 |
key=f"morpho_button_{st.session_state.morphosyntax_state['analysis_count']}",
|
93 |
type="primary",
|
94 |
icon="🔍",
|
95 |
+
disabled=not bool(st.session_state.morphosyntax_state['input_text'].strip()),
|
96 |
use_container_width=True
|
97 |
)
|
98 |
|
99 |
+
# Procesar análisis
|
100 |
+
if analyze_button and st.session_state.morphosyntax_state['input_text'].strip():
|
101 |
try:
|
102 |
with st.spinner(morpho_t.get('processing', 'Processing...')):
|
103 |
+
# Procesar el texto
|
104 |
+
doc = nlp_models[lang_code](st.session_state.morphosyntax_state['input_text'])
|
105 |
+
|
106 |
+
# Realizar análisis
|
107 |
advanced_analysis = perform_advanced_morphosyntactic_analysis(
|
108 |
+
st.session_state.morphosyntax_state['input_text'],
|
109 |
nlp_models[lang_code]
|
110 |
)
|
111 |
|
112 |
+
# Guardar resultado en el estado
|
113 |
st.session_state.morphosyntax_result = {
|
114 |
'doc': doc,
|
115 |
'advanced_analysis': advanced_analysis
|
116 |
}
|
117 |
+
|
118 |
+
# Incrementar contador
|
119 |
st.session_state.morphosyntax_state['analysis_count'] += 1
|
120 |
|
121 |
+
# Guardar en base de datos
|
122 |
if store_student_morphosyntax_result(
|
123 |
username=st.session_state.username,
|
124 |
+
text=st.session_state.morphosyntax_state['input_text'],
|
125 |
arc_diagrams=advanced_analysis['arc_diagrams']
|
126 |
):
|
127 |
st.success(morpho_t.get('success_message', 'Analysis saved successfully'))
|
|
|
128 |
display_morphosyntax_results(
|
129 |
st.session_state.morphosyntax_result,
|
130 |
lang_code,
|
|
|
137 |
logger.error(f"Error en análisis morfosintáctico: {str(e)}")
|
138 |
st.error(morpho_t.get('error_processing', f'Error processing text: {str(e)}'))
|
139 |
|
140 |
+
# Mostrar resultados previos
|
141 |
elif 'morphosyntax_result' in st.session_state and st.session_state.morphosyntax_result:
|
142 |
display_morphosyntax_results(
|
143 |
st.session_state.morphosyntax_result,
|
144 |
lang_code,
|
145 |
morpho_t
|
146 |
)
|
|
|
|
|
147 |
|
148 |
except Exception as e:
|
149 |
logger.error(f"Error general en display_morphosyntax_interface: {str(e)}")
|
150 |
st.error("Se produjo un error. Por favor, intente de nuevo.")
|
151 |
|
152 |
def display_morphosyntax_results(result, lang_code, morpho_t):
|
153 |
+
"""
|
154 |
+
Muestra solo el análisis sintáctico con diagramas de arco.
|
155 |
+
"""
|
156 |
if result is None:
|
157 |
st.warning(morpho_t.get('no_results', 'No results available'))
|
158 |
return
|
159 |
|
160 |
doc = result['doc']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
161 |
|
162 |
# Análisis sintáctico (diagramas de arco)
|
163 |
+
st.markdown(f"### {morpho_t.get('arc_diagram', 'Syntactic analysis: Arc diagram')}")
|
164 |
+
|
165 |
+
with st.container():
|
166 |
sentences = list(doc.sents)
|
167 |
for i, sent in enumerate(sentences):
|
168 |
+
with st.container():
|
169 |
+
st.subheader(f"{morpho_t.get('sentence', 'Sentence')} {i+1}")
|
170 |
+
try:
|
171 |
+
html = displacy.render(sent, style="dep", options={
|
172 |
+
"distance": 100,
|
173 |
+
"arrow_spacing": 20,
|
174 |
+
"word_spacing": 30
|
175 |
+
})
|
176 |
+
# Ajustar dimensiones del SVG
|
177 |
+
html = html.replace('height="375"', 'height="200"')
|
178 |
+
html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html)
|
179 |
+
html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"',
|
180 |
+
lambda m: f'<g transform="translate({m.group(1)},50)"', html)
|
181 |
+
|
182 |
+
# Envolver en un div con clase para estilos
|
183 |
+
html = f'<div class="arc-diagram-container">{html}</div>'
|
184 |
+
st.write(html, unsafe_allow_html=True)
|
185 |
+
except Exception as e:
|
186 |
+
logger.error(f"Error rendering sentence {i}: {str(e)}")
|
187 |
+
st.error(f"Error displaying diagram for sentence {i+1}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|