app.py

import streamlit as st
import pandas as pd
import requests
from wordcloud import WordCloud
import plotly.express as px

# Define array of file paths for each book
book_files = {
    "Maliks_Muwataa": [
        "maliks_muwataa_ahadith.utf8.csv",
        "maliks_muwataa_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Musnad_Ahmad_Ibn-Hanbal": [
        "musnad_ahmad_ibn-hanbal_ahadith.utf8.csv",
        "musnad_ahmad_ibn-hanbal_ahadith_mushakkala.utf8.csv"
    ],
    "Sahih_Al-Bukhari": [
        "sahih_al-bukhari_ahadith.utf8.csv",
        "sahih_al-bukhari_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Sahih_Muslim": [
        "sahih_muslim_ahadith.utf8.csv",
        "sahih_muslim_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Sunan_Abu-Dawud": [
        "sunan_abu-dawud_ahadith.utf8.csv",
        "sunan_abu-dawud_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Sunan_Al-Darimi": [
        "sunan_al-darimi_ahadith.utf8.csv",
        "sunan_al-darimi_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Sunan_Al-Nasai": [
        "sunan_al-nasai_ahadith.utf8.csv",
        "sunan_al-nasai_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Sunan_Al-Tirmidhi": [
        "sunan_al-tirmidhi_ahadith.utf8.csv",
        "sunan_al-tirmidhi_ahadith_mushakkala_mufassala.utf8.csv"
    ],
    "Sunan_Ibn-Maja": [
        "sunan_ibn-maja_ahadith.utf8.csv",
        "sunan_ibn-maja_ahadith_mushakkala_mufassala.utf8.csv"
    ]
}

# Main Streamlit app
def main():
    st.title("Hadith Viewer")

    st.sidebar.title("Navigation")
    st.sidebar.subheader("Actions")
    if st.sidebar.button("Home"):
        display_home()

    st.sidebar.title("Books")
    selected_book = st.sidebar.selectbox("Select a Book", list(book_files.keys()))

    selected_files = book_files[selected_book]
    selected_file = st.sidebar.selectbox("Select a File", selected_files)

    # Load CSV file immediately when selected from the list
    file_url = f"https://raw.githubusercontent.com/halimbahae/Hadith/main/{selected_book}/{selected_file}"
    csv_df = pd.read_csv(file_url, header=None)  # Assuming no header in CSV files

    if csv_df is not None:
        # Display dataframe with search
        display_table(csv_df)

def display_home():
    st.title("Hadith Viewer")
    st.image("https://raw.githubusercontent.com/halimbahae/Hadith/main/Hadith_Books.jpg", caption="Hadith Books", use_column_width=True)
    st.write("Welcome to the Hadith Viewer! This is a viewer for the Hadith collections. You can select a book from the dropdown menu on the left to view its contents.")

def display_table(csv_df):
    font_size = st.slider("Adjust Font Size", min_value=10, max_value=30, value=20, key="font_size_slider")
    st.write("### Table View")
    search_query = st.sidebar.text_input("Search", "", key="search_input")
    filtered_df = csv_df[csv_df.apply(lambda row: row.astype(str).str.contains(search_query, case=False).any(), axis=1)]
    styled_df = (
        filtered_df.style
        .set_properties(**{'font-size': f'{font_size}px'})
        .set_table_styles([{'selector': 'th', 'props': [('font-size', f'{font_size}px')]},
                           {'selector': 'td', 'props': [('font-size', f'{font_size}px'), ('line-height', '1.5')]}])
    )
    st.dataframe(styled_df)

    if st.button("Word Count"):
        display_word_count(filtered_df)

def display_word_count(df):
    st.title("Word Count")
    st.write("Select the number of words to display and exclude words.")

    col1, col2 = st.columns(2)

    with col1:
        word_count = st.slider("Select Number of Words", min_value=10, max_value=50, value=10, key="word_count_slider")

    with col2:
        words_to_exclude = st.text_input("Words to Exclude (comma-separated)", "", key="exclude_words_input")
        words_to_exclude = [word.strip() for word in words_to_exclude.split(",")]

    word_counts = {}
    for row in df.itertuples(index=False):
        for word in str(row[1]).split():
            if word not in words_to_exclude:
                if word in word_counts:
                    word_counts[word] += 1
                else:
                    word_counts[word] = 1

    sorted_word_counts = sorted(word_counts.items(), key=lambda x: x[1], reverse=True)[:word_count]
    words, counts = zip(*sorted_word_counts)

    wordcloud_data = {'word': words, 'count': counts}
    wordcloud_df = pd.DataFrame(wordcloud_data)

    fig = px.bar(wordcloud_df, x='word', y='count', title="Word Cloud")
    st.plotly_chart(fig)

if __name__ == "__main__":
    main()