Update app.py

app.py

@@ -2,6 +2,7 @@ import streamlit as st
 import PyPDF2
 import io
 import os
+import re
 
 # Updated Unicode mappings
 unicodeatoz = ["ब", "द", "अ", "म", "भ", "ा", "न", "ज", "ष्", "व", "प", "ि", "फ", "ल", "य", "उ", "त्र", "च", "क", "त", "ग", "ख", "ध", "ह", "थ", "श"]
@@ -46,34 +47,25 @@ symbolsDict = {
     "÷": "/"
 }
 
+# Add normalization to handle conjunct consonants
 def normalizePreeti(preetitxt):
-    normalized = ''
-    previoussymbol = ''
-    # Additional normalization for complex combinations
-    preetitxt = preetitxt.replace('qm', 's|').replace('f]', 'ो').replace('km', 'फ').replace('0f', 'ण').replace('If', 'क्ष').replace('if', 'ष').replace('cf', 'आ')
+    # Replace complex combinations for conjunct consonants first
+    preetitxt = re.sub(r'qm', 'ष', preetitxt)
+    preetitxt = re.sub(r'f]', 'ो', preetitxt)
+    preetitxt = re.sub(r'km', 'फ', preetitxt)
+    preetitxt = re.sub(r'0f', 'ण', preetitxt)
+    preetitxt = re.sub(r'If', 'क्ष', preetitxt)
+    preetitxt = re.sub(r'if', 'ष', preetitxt)
+    preetitxt = re.sub(r'cf', 'आ', preetitxt)
+    preetitxt = re.sub(r'ग्घ', 'घ', preetitxt)  # Handle conjunct consonants
     
-    index = -1
-    while index + 1 < len(preetitxt):
-        index += 1
-        character = preetitxt[index]
-        try:
-            if preetitxt[index + 2] == '{' and (preetitxt[index + 1] == 'f' or preetitxt[index + 1] == 'ो'):
-                normalized += '{' + character + preetitxt[index + 1]
-                index += 2
-                continue
-            if preetitxt[index + 1] == '{' and character != 'f':
-                normalized += '{' + character
-                index += 1
-                continue
-        except IndexError:
-            pass
-        if character == 'l':
-            previoussymbol = 'l'
-            continue
-        else:
-            normalized += character + previoussymbol
-            previoussymbol = ''
-    return normalized
+    # Additional normalization logic for complex combinations
+    preetitxt = re.sub(r'([a-zA-Z])\{', r'\1्', preetitxt)  # Handle half letters like क्, न्, म्, etc.
+    
+    # Special handling for common Nepali conjuncts
+    preetitxt = preetitxt.replace('ज्ञ', 'ज्ञ')  # Handle frequently used conjuncts
+    
+    return preetitxt
 
 def convert(preeti):
     converted = ''