Update app.py

app.py

@@ -2,9 +2,8 @@ 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"]
 unicodeAtoZ = ["ब्", "ध", "ऋ", "म्", "भ्", "ँ", "न्", "ज्", "क्ष्", "व्", "प्", "ी", "ः", "ल्", "इ", "ए", "त्त", "च्", "क्", "त्", "ग्", "ख्", "ध्", "ह्", "थ्", "श्"]
 unicode0to9 = ["ण्", "ज्ञ", "द्द", "घ", "द्ध", "छ", "ट", "ठ", "ड", "ढ"]
@@ -47,25 +46,40 @@ symbolsDict = {
     "÷": "/"
 }
 
-# Add normalization to handle conjunct consonants
 def normalizePreeti(preetitxt):
-    # 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
-    
-    # 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
+    normalized = ''
+    previoussymbol = ''
+    preetitxt = preetitxt.replace('qm', 's|')
+    preetitxt = preetitxt.replace('f]', 'ो')
+    preetitxt = preetitxt.replace('km', 'फ')
+    preetitxt = preetitxt.replace('0f', 'ण')
+    preetitxt = preetitxt.replace('If', 'क्ष')
+    preetitxt = preetitxt.replace('if', 'ष')
+    preetitxt = preetitxt.replace('cf', 'आ')
+    index = -1
+    while index + 1 < len(preetitxt):
+        index += 1
+        character = preetitxt[index]
+        try:
+            if preetitxt[index + 2] == '{':
+                if preetitxt[index + 1] == 'f' or preetitxt[index + 1] == 'ो':
+                    normalized += '{' + character + preetitxt[index + 1]
+                    index += 2
+                    continue
+            if preetitxt[index + 1] == '{':
+                if character != 'f':
+                    normalized += '{' + character
+                    index += 1
+                    continue
+        except IndexError:
+            pass
+        if character == 'l':
+            previoussymbol = 'l'
+            continue
+        else:
+            normalized += character + previoussymbol
+            previoussymbol = ''
+    return normalized
 
 def convert(preeti):
     converted = ''
@@ -87,13 +101,10 @@ def convert(preeti):
 
 def extract_text_from_pdf(pdf_file):
     text = ''
-    try:
-        with open(pdf_file, 'rb') as file:
-            reader = PyPDF2.PdfReader(file)
-            for page in reader.pages:
-                text += page.extract_text()
-    except Exception as e:
-        text = f"Error extracting text: {e}"
+    with open(pdf_file, 'rb') as file:
+        reader = PyPDF2.PdfReader(file)
+        for page in reader.pages:
+            text += page.extract_text()
     return text
 
 def process_file(inputfile):
@@ -101,12 +112,12 @@ def process_file(inputfile):
     if ext == '.pdf':
         preeti = extract_text_from_pdf(inputfile)
     else:
-        with open(inputfile, "r", encoding="utf-8") as fp:
+        with open(inputfile, "r") as fp:
             preeti = fp.read()
     return convert(preeti)
 
 def main():
-    st.title("Preeti to Unicode Converter")
+    st.title("PDF/TXT to Unicode Converter")
 
     uploaded_file = st.file_uploader("Choose a PDF or TXT file", type=["pdf", "txt"])
 
@@ -138,4 +149,4 @@ def main():
         )
 
 if __name__ == "__main__":
-    main()
+    main()