import streamlit as st
import re
import nltk
from nltk.corpus import stopwords
from nltk import FreqDist
from graphviz import Digraph

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

def remove_timestamps(text):
    return re.sub(r'\d{1,2}:\d{2}\n.*\n', '', text)  # Updated regex pattern

def process_text(text):
    lines = text.split("\n")
    processed_lines = []

    for line in lines:
        if line:
            processed_lines.append(line)

    outline = ""
    for i, line in enumerate(processed_lines):
        if i % 2 == 0:
            outline += f"**{line}**\n"
        else:
            outline += f"- {line} 😄\n"

    return outline

def extract_high_information_words(text, top_n=10):
    words = nltk.word_tokenize(text)
    words = [word.lower() for word in words if word.isalpha()]

    stop_words = set(stopwords.words('english'))
    filtered_words = [word for word in words if word not in stop_words]

    freq_dist = FreqDist(filtered_words)
    high_information_words = [word for word, _ in freq_dist.most_common(top_n)]

    return high_information_words

def create_relationship_graph(words):
    graph = Digraph()

    for index, word in enumerate(words):
        graph.node(str(index), word)

        if index > 0:
            graph.edge(str(index - 1), str(index), label=str(index))

    return graph

def display_relationship_graph(words):
    graph = create_relationship_graph(words)
    st.graphviz_chart(graph)

uploaded_file = st.file_uploader("Choose a .txt file", type=['txt'])

if uploaded_file:
    file_text = uploaded_file.read().decode("utf-8")
    text_without_timestamps = remove_timestamps(file_text)

    top_words = extract_high_information_words(text_without_timestamps, 10)
    st.markdown("**Top 10 High Information Words:**")
    st.write(top_words)

    st.markdown("**Relationship Graph:**")
    display_relationship_graph(top_words)