import os
import zipfile
import streamlit as st
import nltk
from nltk.corpus import stopwords
from sklearn.feature_extraction.text import CountVectorizer
import plotly.express as px

nltk.download('punkt')
nltk.download('stopwords')

def preprocess_text(text):
    # Tokenize the text and remove stopwords
    tokens = nltk.word_tokenize(text.lower())
    stop_words = set(stopwords.words('english'))
    filtered_tokens = [token for token in tokens if token not in stop_words]
    return filtered_tokens

def get_context_files(prompt, md_files):
    # Preprocess the prompt and context files
    processed_prompt = preprocess_text(prompt)
    processed_files = {}
    for file in md_files:
        with open(file, 'r') as f:
            content = f.read()
            processed_files[file] = preprocess_text(content)
    
    # Calculate word matches and LCS bonus
    file_matches = {}
    for file, tokens in processed_files.items():
        single_matches = set(tokens) & set(processed_prompt)
        double_matches = set(nltk.bigrams(tokens)) & set(nltk.bigrams(processed_prompt))
        triple_matches = set(nltk.trigrams(tokens)) & set(nltk.trigrams(processed_prompt))
        match_count = len(single_matches) + len(double_matches) * 4 + len(triple_matches) * 9
        file_matches[file] = {
            'single_matches': single_matches,
            'double_matches': double_matches,
            'triple_matches': triple_matches,
            'match_count': match_count
        }
    
    # Sort the files by the match count
    sorted_files = sorted(file_matches.items(), key=lambda x: x[1]['match_count'], reverse=True)
    
    # Create a markdown outline with match counts and word matches
    outline = "## Outline\n"
    for file, matches in sorted_files:
        outline += f"- {file}: {matches['match_count']} matches\n"
        if matches['single_matches']:
            outline += f"  - Single word matches: {', '.join(matches['single_matches'])}\n"
        if matches['double_matches']:
            outline += f"  - Double word matches: {', '.join(' '.join(pair) for pair in matches['double_matches'])}\n"
        if matches['triple_matches']:
            outline += f"  - Triple word matches: {', '.join(' '.join(trio) for trio in matches['triple_matches'])}\n"
    
    # Create a single prompt by concatenating the original prompt and the content of the top ten files
    context_prompt = prompt
    for file, _ in sorted_files[:10]:
        with open(file, 'r') as f:
            content = f.read()
            # Highlight the matching words in bold
            for word in file_matches[file]['single_matches']:
                content = content.replace(word, f"**{word}**")
            for pair in file_matches[file]['double_matches']:
                content = content.replace(' '.join(pair), f"**{' '.join(pair)}**")
            for trio in file_matches[file]['triple_matches']:
                content = content.replace(' '.join(trio), f"**{' '.join(trio)}**")
            context_prompt += '\n\n' + content
    
    # Create a plotly graph showing the match counts for the top ten files
    fig = px.bar(x=[file for file, _ in sorted_files[:10]], y=[matches['match_count'] for _, matches in sorted_files[:10]])
    fig.update_layout(xaxis_title='File', yaxis_title='Match Count')
    st.plotly_chart(fig)
    
    return outline, context_prompt

# Streamlit app
def main():
    st.title("Context-Aware Prompt Evaluation")
    
    # File upload
    uploaded_file = st.file_uploader("Upload a zip file with .md files", type="zip")
    
    if uploaded_file is not None:
        # Unzip the uploaded file
        with zipfile.ZipFile(uploaded_file, 'r') as zip_ref:
            zip_ref.extractall('uploaded_files')
        
        # Get the list of .md files from the uploaded directory
        md_files = [os.path.join('uploaded_files', file) for file in os.listdir('uploaded_files') if file.endswith('.md')]
        
        # Show the list of files
        st.subheader("Uploaded Files")
        for file in md_files:
            st.write(file)
        
        # Prompt input
        prompt = st.session_state.get('prompt', 'What are the main use cases of generative AI in healthcare that are currently unsolved?')
        prompt = st.text_area("Enter your prompt", value=prompt, key='prompt')
        
        # Evaluate the files for the prompt
        if st.button("Evaluate"):
            outline, context_prompt = get_context_files(prompt, md_files)
            st.subheader("Outline")
            st.markdown(outline)
            st.subheader("Context Prompt")
            st.markdown(context_prompt)

if __name__ == '__main__':
    main()