app.py

import streamlit as st
import io
import os
import pdfplumber

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", "÷": "/"
}

def normalizePreeti(preetitxt):
    normalized = ''
    previoussymbol = ''
    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
        except IndexError:
            pass
        if character == 'l':
            previoussymbol = 'l'
            continue
        else:
            normalized += character + previoussymbol
            previoussymbol = ''
    return normalized

def convert(preeti):
    converted = ''
    normalizedpreeti = normalizePreeti(preeti)
    for character in normalizedpreeti:
        try:
            if 97 <= ord(character) <= 122:
                converted += unicodeatoz[ord(character) - 97]
            elif 65 <= ord(character) <= 90:
                converted += unicodeAtoZ[ord(character) - 65]
            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):
    text = ''
    with pdfplumber.open(pdf_file) as pdf:
        for page in pdf.pages:
            extracted_text = page.extract_text()
            if extracted_text:
                text += extracted_text
    return handle_vertical_text(text)

def handle_vertical_text(text):
    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
        else:
            if horizontal_line:  # If we've built a horizontal line, add it.
                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 main():
    st.title("PDF/TXT to Unicode Converter (Nepali RAG)")

    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":
            text = extract_text_from_pdf(io.BytesIO(uploaded_file.read()))
        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"
        )

    # Write footer
    st.markdown("Made with ❤️ by Sumit Yadav(https://sumityadav.com.np)")

if __name__ == "__main__":
    main()