Update app.py

app.py

@@ -7,54 +7,16 @@ unicodeatoz = ["ब", "द", "अ", "म", "भ", "ा", "न", "ज", "ष्",
 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",
-    "$": "४",
-    "%": "५",
-    "^": "६",
-    "&": "७",
-    "*": "८",
-    "(": "९",
-    ")": "०",
-    "-": "(",
-    "_": ")",
-    "+": "ं",
-    "[": "ृ",
-    "{": "र्",
-    "]": "े",
-    "}": "ै",
-    "\\": "्",
-    "|": "्र",
-    ";": "स",
-    ":": "स्",
-    "'": "ु",
-    "\"": "ू",
-    ",": ",",
-    "<": "?",
-    ".": "।",
-    ">": "श्र",
-    "/": "र",
-    "?": "रु",
-    "=": ".",
-    "ˆ": "फ्",
-    "Î": "ङ्ख",
-    "å": "द्व",
-    "÷": "/"
+    "~": "ञ्", "`": "ञ", "!": "१", "@": "२", "#": "३", "$": "४", "%": "५", "^": "६", "&": "७", "*": "८",
+    "(": "९", ")": "०", "-": "(", "_": ")", "+": "ं", "[": "ृ", "{": "र्", "]": "े", "}": "ै", "\\": "्",
+    "|": "्र", ";": "स", ":": "स्", "'": "ु", "\"": "ू", ",": ",", "<": "?", ".": "।", ">": "श्र", "/": "र",
+    "?": "रु", "=": ".", "ˆ": "फ्", "Î": "ङ्ख", "å": "द्व", "÷": "/"
 }
 
 def 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')
+    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
@@ -83,19 +45,18 @@ def normalizePreeti(preetitxt):
 def convert(preeti):
     converted = ''
     normalizedpreeti = normalizePreeti(preeti)
-    for index, character in enumerate(normalizedpreeti):
+    for character in normalizedpreeti:
         try:
-            if ord(character) >= 97 and ord(character) <= 122:
+            if 97 <= ord(character) <= 122:
                 converted += unicodeatoz[ord(character) - 97]
-            elif ord(character) >= 65 and ord(character) <= 90:
+            elif 65 <= ord(character) <= 90:
                 converted += unicodeAtoZ[ord(character) - 65]
-            elif ord(character) >= 48 and ord(character) <= 57:
+            elif 48 <= ord(character) <= 57:
                 converted += unicode0to9[ord(character) - 48]
             else:
                 converted += symbolsDict[character]
         except KeyError:
             converted += character
-
     return converted
 
 def extract_text_from_pdf(pdf_file):
@@ -105,16 +66,12 @@ def extract_text_from_pdf(pdf_file):
             extracted_text = page.extract_text()
             if extracted_text:
                 text += extracted_text
-
     return handle_vertical_text(text)
 
 def handle_vertical_text(text):
-    # If the text is vertical, it's likely arranged with one character per line.
-    # We'll attempt to reformat the text by concatenating characters that are stacked vertically.
     lines = text.split('\n')
     vertical_lines = []
     horizontal_line = ''
-
     for line in lines:
         if len(line) == 1:  # Possible vertical arrangement (single character per line)
             horizontal_line += line
@@ -123,23 +80,12 @@ def handle_vertical_text(text):
                 vertical_lines.append(horizontal_line)
                 horizontal_line = ''
             vertical_lines.append(line)  # Add the full line if it's not vertical.
-
     if horizontal_line:
         vertical_lines.append(horizontal_line)
-
     return ' '.join(vertical_lines)
 
-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("PDF/TXT to Unicode Converter(Nepali RAG)")
+    st.title("PDF/TXT to Unicode Converter (Nepali RAG)")
 
     uploaded_file = st.file_uploader("Choose a PDF or TXT file", type=["pdf", "txt"])
 
@@ -148,10 +94,8 @@ def main():
 
         if file_extension == ".pdf":
             text = extract_text_from_pdf(io.BytesIO(uploaded_file.read()))
-            
         else:  # .txt file
-            with open(inputfile, "r") as fp:
-                text = fp.read()
+            text = uploaded_file.getvalue().decode("utf-8")
 
         converted_text = convert(text)
 
@@ -173,4 +117,4 @@ def main():
     st.markdown("Made with ❤️ by Sumit Yadav(https://sumityadav.com.np)")
 
 if __name__ == "__main__":
-    main()
+    main()