app.py

import streamlit as st
import pandas as pd
import os
from huggingface_hub import hf_hub_download


# Page configuration
st.set_page_config(
    page_title="Title-2-BookName",
    page_icon="📚",
    layout="centered",
    initial_sidebar_state="collapsed"
)

# Custom CSS for better styling
st.markdown("""
    <style>
    .main {
        padding: 2rem;
    }
    .stApp {
        background-color: #f5f7fa;
    }
    .stTitle {
        font-size: 3rem !important;
        margin-bottom: 1.5rem !important;
    }
    .search-container {
        background-color: white;
        padding: 2rem;
        border-radius: 10px;
        box-shadow: 0 2px 10px rgba(0,0,0,0.1);
    }
    .results-container {
        margin-top: 2rem;
        background-color: white;
        padding: 2rem;
        border-radius: 10px;
        box-shadow: 0 2px 10px rgba(0,0,0,0.1);
    }
    .st-emotion-cache-1n76uvr {
        font-size: 1.2rem;
    }
    </style>
""", unsafe_allow_html=True)

# Load the CSV file with caching
@st.cache_data
def load_data():
    try:
        HUGGINGFACE_TOKEN = os.getenv("HF_TOKEN")
        if not HUGGINGFACE_TOKEN:
            st.sidebar.error("HF_TOKEN environment variable is not set")
            return pd.DataFrame()
            
        csv_file = hf_hub_download(
            repo_id="Skoob/test-private",
            filename="2025Feb_3_Data_2k_267k.csv",
            use_auth_token=HUGGINGFACE_TOKEN
        )
        df = pd.read_csv(csv_file)
        # Prepare dataframe
        df = df.copy()
        return df
    except Exception as e:
        st.sidebar.error(f"Error loading data: {str(e)}")
        return pd.DataFrame()

st.title(":blue[Title-2-BookName]")

# Load data
title_df = load_data()

# Main search functionality
def get_file_info(user_title):
    if title_df.empty:
        return None
    
    # Always case-insensitive search with exact match only
    search_title = user_title.lower()
    result = title_df.loc[title_df['Title'].str.lower() == search_title]
    
    if not result.empty:
        # Remove 'BookSummary-' and '.docx' from the file names
        result_copy = result.copy()
        result_copy['Clean_name'] = result_copy['File_name'].str.replace("BookSummary-", "").str.replace(".docx", "")
        # Select relevant columns and reset index
        return result_copy[['Title', 'Clean_name', 'File_name']].reset_index(drop=True)
    else:
        return None

# Main app container
col1 = st.container()  # Use a single container for both input and button

with col1:
    user_titles = st.text_area("Enter book titles (one per line):")  # Input multiple titles separated by a newline
    search_button = st.button("🔍 Search", use_container_width=True)

# Search results display
if user_titles and search_button:
    titles_list = user_titles.strip().split("\n")  # Split the input into a list of titles
    
    if titles_list:
        # Initialize an empty DataFrame to store the results
        all_results = pd.DataFrame(columns=['Title', 'Clean_name', 'File_name'])
        
        with st.spinner("Searching..."):
            for title in titles_list:
                result_df = get_file_info(title.strip())
                if result_df is not None and not result_df.empty:
                    all_results = pd.concat([all_results, result_df], ignore_index=True)

        if not all_results.empty:
            st.success(f"Found {len(all_results)} matching result(s)!")

            # Display results in a nice table with copy buttons
            st.dataframe(
                all_results,
                column_config={
                    "Title": st.column_config.TextColumn("Original Title"),
                    "Clean_name": st.column_config.TextColumn("Book Name"),
                    "File_name": st.column_config.TextColumn("File Name")
                },
                use_container_width=True,
                hide_index=False
            )
            
            # # Display all file names in a list format
            # st.subheader("All File Names:")
            # for idx, row in all_results.iterrows():
            #     st.code(row['File_name'], language=None)

            # # Add option to copy all file names as text
            # all_filenames = '\n'.join(all_results['File_name'].tolist())
            # st.download_button(
            #     label="📋 Copy all file names",
            #     data=all_filenames,
            #     file_name=f"filenames_{'_'.join(titles_list)}.txt",
            #     mime="text/plain"
            # )
        else:
            st.warning("No results found. Try different search options or check your spelling.")
    else:
        st.warning("Please enter at least one book title.")