Update app.py

app.py

@@ -2,180 +2,151 @@ import streamlit as st
 import PyPDF2
 import io
 import os
-import re
 
-# Existing mapping dictionaries remain the same
+
 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"]
 symbolsDict = {
-    "~": "ञ्", "`": "ञ", "!": "१", "@": "२", "#": "३", "$": "४", "%": "५",
-    "^": "६", "&": "७", "*": "८", "(": "९", ")": "०", "-": "(", "_": ")",
-    "+": "ं", "[": "ृ", "{": "र्", "]": "े", "}": "ै", "\\": "्", "|": "्र",
-    ";": "स", ":": "स्", "'": "ु", "\"": "ू", ",": ",", "<": "?", ".": "।",
-    ">": "श्र", "/": "र", "?": "रु", "=": ".", "ˆ": "फ्", "Î": "ङ्ख",
-    "å": "द्व", "÷": "/"
-}
-
-# Common Preeti patterns that need to be preserved as units
-preeti_compounds = {
-    'qm': 's|',
-    'f]': 'ो',
-    'km': 'फ',
-    '0f': 'ण',
-    'If': 'क्ष',
-    'if': 'ष',
-    'cf': 'आ',
-    '6«': 'ट्र',
-    'g]': 'ने',
-    '8f': 'डा',
-    '«': '्र',
-    'j|m': 'क्र',
-    ';+': 'सं'
+    "~": "ञ्",
+    "`": "ञ",
+    "!": "१",
+    "@": "२",
+    "#": "३",
+    "$": "४",
+    "%": "५",
+    "^": "६",
+    "&": "७",
+    "*": "८",
+    "(": "९",
+    ")": "०",
+    "-": "(",
+    "_": ")",
+    "+": "ं",
+    "[": "ृ",
+    "{": "र्",
+    "]": "े",
+    "}": "ै",
+    "\\": "्",
+    "|": "्र",
+    ";": "स",
+    ":": "स्",
+    "'": "ु",
+    "\"": "ू",
+    ",": ",",
+    "<": "?",
+    ".": "।",
+    ">": "श्र",
+    "/": "र",
+    "?": "रु",
+    "=": ".",
+    "ˆ": "फ्",
+    "Î": "ङ्ख",
+    "å": "द्व",
+    "÷": "/"
 }
 
-def is_nepali_unicode(char):
-    """Check if character is already in Nepali Unicode range"""
-    return '\u0900' <= char <= '\u097F'
-
-def get_preeti_segment(text, start_idx):
-    """
-    Extract a complete Preeti segment starting from given index.
-    Returns the segment and the ending index.
-    """
-    if start_idx >= len(text):
-        return "", start_idx
-    
-    current_idx = start_idx
-    segment = ""
-    
-    while current_idx < len(text):
-        # Check for compound characters first
-        matched = False
-        for compound in sorted(preeti_compounds.keys(), key=len, reverse=True):
-            if text[current_idx:].startswith(compound):
-                segment += compound
-                current_idx += len(compound)
-                matched = True
-                break
-        
-        if not matched:
-            char = text[current_idx]
-            if char.isspace() or is_nepali_unicode(char):
-                break
-            segment += char
-            current_idx += 1
-            
-    return segment, current_idx
-
-def normalize_preeti(preetitxt):
-    """Normalize Preeti text with improved compound handling"""
-    # First handle the compound characters
-    for old, new in preeti_compounds.items():
-        preetitxt = preetitxt.replace(old, new)
-    
-    # Handle remaining special cases
+def normalizePreeti(preetitxt):
     normalized = ''
-    idx = 0
-    while idx < len(preetitxt):
-        if idx + 1 < len(preetitxt) and preetitxt[idx] == 'l':
-            normalized += preetitxt[idx + 1] + 'ि'
-            idx += 2
+    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 += preetitxt[idx]
-            idx += 1
-            
+            normalized += character + previoussymbol
+            previoussymbol = ''
     return normalized
 
-def convert_segment(segment):
-    """Convert a single Preeti segment to Unicode"""
-    if not segment.strip():
-        return segment
-    
-    # If already in Nepali Unicode, return as is
-    if all(is_nepali_unicode(char) for char in segment if char.strip()):
-        return segment
-    
+def convert(preeti):
     converted = ''
-    normalized = normalize_preeti(segment)
-    
-    for char in normalized:
-        if is_nepali_unicode(char):
-            converted += char
-        elif char.isascii():
-            try:
-                if 'a' <= char <= 'z':
-                    converted += unicodeatoz[ord(char) - ord('a')]
-                elif 'A' <= char <= 'Z':
-                    converted += unicodeAtoZ[ord(char) - ord('A')]
-                elif '0' <= char <= '9':
-                    converted += unicode0to9[ord(char) - ord('0')]
-                else:
-                    converted += symbolsDict.get(char, char)
-            except (IndexError, KeyError):
-                converted += char
-        else:
-            converted += char
-            
+    normalizedpreeti = normalizePreeti(preeti)
+    for index, character in enumerate(normalizedpreeti):
+        try:
+            if ord(character) >= 97 and ord(character) <= 122:
+                converted += unicodeatoz[ord(character) - 97]
+            elif ord(character) >= 65 and ord(character) <= 90:
+                converted += unicodeAtoZ[ord(character) - 65]
+            elif ord(character) >= 48 and ord(character) <= 57:
+                converted += unicode0to9[ord(character) - 48]
+            else:
+                converted += symbolsDict[character]
+        except KeyError:
+            converted += character
+
     return converted
 
-def smart_convert_mixed(text):
-    """
-    Convert text while handling mixed Preeti, Unicode and English.
-    Processes text character by character to maintain proper segmentation.
-    """
-    result = ""
-    idx = 0
-    
-    while idx < len(text):
-        char = text[idx]
-        
-        # Skip spaces and preserve them
-        if char.isspace():
-            result += char
-            idx += 1
-            continue
-            
-        # If character is already in Nepali Unicode, preserve it
-        if is_nepali_unicode(char):
-            result += char
-            idx += 1
-            continue
-            
-        # If it's a potential Preeti character, get the complete segment
-        if char.isascii():
-            preeti_segment, new_idx = get_preeti_segment(text, idx)
-            if preeti_segment:
-                result += convert_segment(preeti_segment)
-                idx = new_idx
-                continue
-                
-        # Default case: preserve the character
-        result += char
-        idx += 1
-        
-    return result
+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()
+    return text
+
+def process_file(inputfile):
+    ext = os.path.splitext(inputfile)[1].lower()
+    if ext == '.pdf':
+        preeti = extract_text_from_pdf(inputfile)
+    else:
+        with open(inputfile, "r") as fp:
+            preeti = fp.read()
+    return convert(preeti)
 
 def main():
-    st.title("Advanced Mixed Text Converter")
-    st.write("Converts Preeti text while preserving existing Nepali Unicode and English")
-
-    # Input area
-    input_text = st.text_area("Enter text to convert", height=200)
-    
-    if st.button("Convert"):
-        if input_text:
-            converted_text = smart_convert_mixed(input_text)
-            
-            st.subheader("Converted Text")
-            st.text_area("", value=converted_text, height=200)
-            
-            st.download_button(
-                label="Download Converted Text",
-                data=converted_text.encode("utf-8"),
-                file_name="converted_text.txt",
-                mime="text/plain"
-            )
+    st.title("PDF/TXT to Unicode Converter")
+
+    uploaded_file = st.file_uploader("Choose a PDF or TXT file", type=["pdf", "txt"])
+
+    if uploaded_file is not None:
+        file_extension = os.path.splitext(uploaded_file.name)[1].lower()
+
+        if file_extension == ".pdf":
+            pdf_reader = PyPDF2.PdfReader(io.BytesIO(uploaded_file.read()))
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+        else:  # .txt file
+            text = uploaded_file.getvalue().decode("utf-8")
+
+        converted_text = convert(text)
+
+        st.subheader("Original Text")
+        st.text_area("", value=text, height=200)
+
+        st.subheader("Converted Text")
+        st.text_area("", value=converted_text, height=200)
+
+        # Create a download button for the converted text
+        st.download_button(
+            label="Download Converted Text",
+            data=converted_text.encode("utf-8"),
+            file_name="converted_text.txt",
+            mime="text/plain"
+        )
 
 if __name__ == "__main__":
     main()