Update modules/morpho_analysis.py

modules/morpho_analysis.py

@@ -1,6 +1,8 @@
 # /modules/morpho_analysis.py
 import spacy
 from collections import Counter
+from spacy import displacy
+import re
 
 # Define colors for grammatical categories
 POS_COLORS = {
@@ -79,6 +81,7 @@ POS_TRANSLATIONS = {
     }
 }
 
+#############################################################################################
 def get_repeated_words_colors(doc):
     word_counts = Counter(token.text.lower() for token in doc if token.pos_ != 'PUNCT')
     repeated_words = {word: count for word, count in word_counts.items() if count > 1}
@@ -89,7 +92,8 @@ def get_repeated_words_colors(doc):
             word_colors[token.text.lower()] = POS_COLORS.get(token.pos_, '#FFFFFF')
 
     return word_colors
-
+    
+######################################################################################################
 def highlight_repeated_words(doc, word_colors):
     highlighted_text = []
     for token in doc:
@@ -98,4 +102,16 @@ def highlight_repeated_words(doc, word_colors):
             highlighted_text.append(f'<span style="background-color: {color};">{token.text}</span>')
         else:
             highlighted_text.append(token.text)
-    return ' '.join(highlighted_text)
+    return ' '.join(highlighted_text)
+    
+#################################################################################################
+    def generate_arc_diagram(doc, lang_code):
+    sentences = list(doc.sents)
+    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)
+        arc_diagrams.append(html)
+    return arc_diagrams