add new feature

app.py

@@ -3,7 +3,7 @@ import PyPDF2
 import io
 import os
 
-
+# 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"]
@@ -49,28 +49,22 @@ symbolsDict = {
 def normalizePreeti(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')
+    # 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')
+    
     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
+            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':
@@ -101,10 +95,13 @@ def convert(preeti):
 
 def extract_text_from_pdf(pdf_file):
     text = ''
-    with open(pdf_file, 'rb') as file:
-        reader = PyPDF2.PdfReader(file)
-        for page in reader.pages:
-            text += page.extract_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}"
     return text
 
 def process_file(inputfile):
@@ -112,12 +109,12 @@ def process_file(inputfile):
     if ext == '.pdf':
         preeti = extract_text_from_pdf(inputfile)
     else:
-        with open(inputfile, "r") as fp:
+        with open(inputfile, "r", encoding="utf-8") as fp:
             preeti = fp.read()
     return convert(preeti)
 
 def main():
-    st.title("PDF/TXT to Unicode Converter")
+    st.title("Preeti to Unicode Converter")
 
     uploaded_file = st.file_uploader("Choose a PDF or TXT file", type=["pdf", "txt"])
 
@@ -149,4 +146,4 @@ def main():
         )
 
 if __name__ == "__main__":
-    main()
+    main()