Update modules/text_analysis/morpho_analysis.py

modules/text_analysis/morpho_analysis.py

@@ -114,14 +114,61 @@ def highlight_repeated_words(doc, word_colors):
     return ' '.join(highlighted_text)
     
 #################################################################################################
-def generate_arc_diagram(doc, lang_code):
-    sentences = list(doc.sents)
+def generate_arc_diagram(doc):
     arc_diagrams = []
-    for sent in sentences:
-        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)
+    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