#!/usr/bin/env awk -f

BEGIN {
    # Initialize stop words
    split("the and of to a in is that it on for as was with at by an be this are from or can your layout", words)
    for (i in words) stopwords[tolower(words[i])] = 1
    
    # Track the query
    query = tolower(ENVIRON["QUERY"])
    patsplit(query, query_tokens, /[a-zA-Z0-9]+/)
    for (i in query_tokens) {
        if (!stopwords[query_tokens[i]]) {
            query_weights[query_tokens[i]]++
        }
    }
    
    # Configuration: How many lines per chunk
    lines_per_chunk = 5
    current_chunk = ""
}

{
    # Accumulate lines into a chunk
    current_chunk = current_chunk " " $0
    
    # Process the chunk once we hit our line limit or reach the End-of-File
    if (NR % lines_per_chunk == 0) {
        process_chunk(current_chunk)
        current_chunk = ""
    }
}

# Catch any remaining text at the very end of the file
END {
    if (current_chunk != "") {
        process_chunk(current_chunk)
    }

    # Output the absolute best match found
    if (max_score == 0) {
        print "Context: (No highly relevant context found in documents.)"
    } else {
        print "Context: " best_paragraph
    }
    print "Question: " ENVIRON["QUERY"]
    print "Answer: "
}

function process_chunk(paragraph) {
    gsub(/[ \t\r\n]+/, " ", paragraph) # Clean spacing
    score = 0
    
    patsplit(tolower(paragraph), p_tokens, /[a-zA-Z0-9]+/)
    
    delete tf
    for (i in p_tokens) {
        if (!stopwords[p_tokens[i]]) tf[p_tokens[i]]++
    }
    
    for (token in query_weights) {
        if (token in tf) {
            score += query_weights[token] * tf[token]
        }
    }
    
    if (score > max_score) {
        max_score = score
        best_paragraph = paragraph
    }
}