modules/text_analysis/morpho_analysis.py

import spacy
from spacy import displacy
from streamlit.components.v1 import html
import base64

from collections import Counter
import re
from ..utils.widget_utils import generate_unique_key

import logging
logger = logging.getLogger(__name__)


# Define colors for grammatical categories
POS_COLORS = {
    'ADJ': '#FFA07A',    # Light Salmon
    'ADP': '#98FB98',    # Pale Green
    'ADV': '#87CEFA',    # Light Sky Blue
    'AUX': '#DDA0DD',    # Plum
    'CCONJ': '#F0E68C',  # Khaki
    'DET': '#FFB6C1',    # Light Pink
    'INTJ': '#FF6347',   # Tomato
    'NOUN': '#90EE90',   # Light Green
    'NUM': '#FAFAD2',    # Light Goldenrod Yellow
    'PART': '#D3D3D3',   # Light Gray
    'PRON': '#FFA500',   # Orange
    'PROPN': '#20B2AA',  # Light Sea Green
    'SCONJ': '#DEB887',  # Burlywood
    'SYM': '#7B68EE',    # Medium Slate Blue
    'VERB': '#FF69B4',   # Hot Pink
    'X': '#A9A9A9',      # Dark Gray
}

POS_TRANSLATIONS = {
    'es': {
        'ADJ': 'Adjetivo',
        'ADP': 'Preposición',
        'ADV': 'Adverbio',
        'AUX': 'Auxiliar',
        'CCONJ': 'Conjunción Coordinante',
        'DET': 'Determinante',
        'INTJ': 'Interjección',
        'NOUN': 'Sustantivo',
        'NUM': 'Número',
        'PART': 'Partícula',
        'PRON': 'Pronombre',
        'PROPN': 'Nombre Propio',
        'SCONJ': 'Conjunción Subordinante',
        'SYM': 'Símbolo',
        'VERB': 'Verbo',
        'X': 'Otro',
    },
    'en': {
        'ADJ': 'Adjective',
        'ADP': 'Preposition',
        'ADV': 'Adverb',
        'AUX': 'Auxiliary',
        'CCONJ': 'Coordinating Conjunction',
        'DET': 'Determiner',
        'INTJ': 'Interjection',
        'NOUN': 'Noun',
        'NUM': 'Number',
        'PART': 'Particle',
        'PRON': 'Pronoun',
        'PROPN': 'Proper Noun',
        'SCONJ': 'Subordinating Conjunction',
        'SYM': 'Symbol',
        'VERB': 'Verb',
        'X': 'Other',
    },
    'fr': {
        'ADJ': 'Adjectif',
        'ADP': 'Préposition',
        'ADV': 'Adverbe',
        'AUX': 'Auxiliaire',
        'CCONJ': 'Conjonction de Coordination',
        'DET': 'Déterminant',
        'INTJ': 'Interjection',
        'NOUN': 'Nom',
        'NUM': 'Nombre',
        'PART': 'Particule',
        'PRON': 'Pronom',
        'PROPN': 'Nom Propre',
        'SCONJ': 'Conjonction de Subordination',
        'SYM': 'Symbole',
        'VERB': 'Verbe',
        'X': 'Autre',
    }
}

def generate_arc_diagram(doc):
    arc_diagrams = []
    for sent in doc.sents:
        words = [token.text for token in sent]
        # Calculamos el ancho del SVG basado en la longitud de la oración
        svg_width = max(600, len(words) * 120)
        # Altura fija para cada oración
        svg_height = 350 # Controla la altura del SVG

        # Renderizamos el diagrama de dependencias
        html = displacy.render(sent, style="dep", options={
            "add_lemma":False, # Introduced in version 2.2.4, this argument prints the lemma’s in a separate row below the token texts.
            "arrow_spacing": 12, #This argument is used for adjusting the spacing between arrows in px to avoid overlaps.
            "arrow_width": 2, #This argument is used for adjusting the width of arrow head in px.
            "arrow_stroke": 2, #This argument is used for adjusting the width of arrow path in px.
            "collapse_punct": True, #It attaches punctuation to the tokens.
            "collapse_phrases": False, # This argument merges the noun phrases into one token.
            "compact":False, # If you will take this argument as true, you will get the “Compact mode” with square arrows that takes up less space.
            "color": "#ffffff",
            "bg": "#0d6efd",
            "compact": False, #Put the value of this argument True, if you want to use fine-grained part-of-speech tags (Token.tag_), instead of coarse-grained tags (Token.pos_).
            "distance": 100,  # Aumentamos la distancia entre palabras
            "fine_grained": False, #Put the value of this argument True, if you want to use fine-grained part-of-speech tags (Token.tag_), instead of coarse-grained tags (Token.pos_).
            "offset_x": 55, #	This argument is used for spacing on left side of the SVG in px.
            "word_spacing": 25, #This argument is used for adjusting the vertical spacing between words and arcs in px.
        })

        # Ajustamos el tamaño del SVG y el viewBox
        html = re.sub(r'width="(\d+)"', f'width="{svg_width}"', html)
        html = re.sub(r'height="(\d+)"', f'height="{svg_height}"', html)
        html = re.sub(r'<svg', f'<svg viewBox="0 0 {svg_width} {svg_height}"', html)

        #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)

        # Movemos todo el contenido hacia abajo
        #html = html.replace('<g', f'<g transform="translate(50, {svg_height - 200})"')

         # Movemos todo el contenido hacia arriba para eliminar el espacio vacío en la parte superior
        html = re.sub(r'<g transform="translate\((\d+),(\d+)\)"',
                      lambda m: f'<g transform="translate({m.group(1)},10)"', html)


        # Ajustamos la posición de las etiquetas de las palabras
        html = html.replace('dy="1em"', 'dy="-1em"')

        # Ajustamos la posición de las etiquetas POS
        html = html.replace('dy="0.25em"', 'dy="-3em"')

        # Aumentamos el tamaño de la fuente para las etiquetas POS
        html = html.replace('.displacy-tag {', '.displacy-tag { font-size: 14px;')

        # Rotamos las etiquetas de las palabras para mejorar la legibilidad
        #html = html.replace('class="displacy-label"', 'class="displacy-label" transform="rotate(30)"')

        arc_diagrams.append(html)
    return arc_diagrams
##################################################################################################################################


def perform_advanced_morphosyntactic_analysis(text, nlp):
    doc = nlp(text)
    arc_diagrams = generate_arc_diagram(doc)
    return {
        'arc_diagrams': arc_diagrams,
    }

__all__ = ['perform_advanced_morphosyntactic_analysis']