import java.lang.*;
import java.io.*;
import java.util.*;
import java.lang.Math;
import java.util.Collection;
import java.util.HashMap;
import java.util.Iterator;



public class HW4_2 {

    public static void main(String[] args) throws IOException {
        //---- Definitions ----//

        HashMap<String, List<String>> indexDocID = new HashMap<String, List<String>>();
        HashMap<String, List<String>> indexTF = new HashMap<String, List<String>>();
        HashMap<String, String> indexTC = new HashMap<String, String>();

        String indexFileLocation = "assignment_3_index//unigram_task2.txt";
        String tokenMapFileLocation = "assignment_3_index//token_map_task2.txt";

        //---- Code ----//

        try (BufferedReader br = new BufferedReader(new FileReader(indexFileLocation))) {
            String line;
            int position = 0;
            while ((line = br.readLine()) != null) {
                List<List<String>> valueList = new ArrayList<List<String>>();

                String[] term = line.split(" -~- ");

                //Grab Key
                String key = term[0];
                key = key.replace(" ", "");

                //Grab values and put them in a list of lists
                String indexValue = term[1];
                indexValue = indexValue.replace("\n"," ");
                String[] values = indexValue.split(" ");

                List<String> tfList = new ArrayList<String>();
                List<String> docIDList = new ArrayList<String>();
                for(int i = 0; i < values.length; ++i) {
                    String temporary = values[i].replaceAll("[()]","");
                    String[] individualValues = temporary.split(",");
                    String docid = individualValues[0];
                    docIDList.add(docid);
                    String tf = individualValues[1];
                    tfList.add(tf);


                }
                position =+ 1;
                indexDocID.put(key, docIDList);
                indexTF.put(key, tfList);
            }

        } catch (IOException e) {
            e.printStackTrace();
        }

        try (BufferedReader br = new BufferedReader(new FileReader(tokenMapFileLocation))) {
            String line;
            int position = 0;
            while ((line = br.readLine()) != null) {
                String[] entries = line.split("--");
                String docID = entries[0];
                docID = docID.replace(" ", "");
                String tokenCount = entries[1];
                indexTC.put(docID, tokenCount);

            }

        } catch (IOException e) {
            e.printStackTrace();
        }


        //System.out.print(indexDocID.size());

        Scanner in = new Scanner(System.in);

        System.out.println("Please enter a query:");
        String query_input = in.nextLine();
        query_input = query_input.toLowerCase();


        try {

            List<String> listDocumentsForTerm = new ArrayList<>();
            listDocumentsForTerm = indexDocID.get(query_input);

            List<String> listOfTFForTerm = new ArrayList<>();
            listOfTFForTerm = indexDocID.get(query_input);

            //Calculate normalized TF, DF and IDF for term
            for(int i = 0; i < listDocumentsForTerm.size(); ++i) {
                String documentid = listDocumentsForTerm.get(i);
                double tokenCount = Double.parseDouble(indexTC.get(documentid));
                double tfCount = Double.parseDouble(listOfTFForTerm.get(i));


                double normalizedTF = calcNormalizeTF(tfCount, tokenCount);
                System.out.println("Normalized TF is " + normalizedTF);


                Double IDF = calcIDF(listDocumentsForTerm.size(), indexTC.size());
                System.out.println("IDF  is " + IDF);

                Double TFIDF = calcTFIDF(normalizedTF, IDF);

                System.out.println("TF-IDF  is " + IDF);

            }




        } catch (Throwable e) {

        }

    }


    public static double calcIDF(int documentFrequency, int totalDocuments) {
        double IDF = 0;
        IDF = 1 + Math.log(totalDocuments / documentFrequency);
        return IDF;

    }

    public static double calcNormalizeTF(double tfCount, double tokenCount) {
        double normalizedTF = 0;
        normalizedTF = 1 + Math.log(tfCount / tokenCount);
        return normalizedTF;
    }

    public static double calcTFIDF(double normalizedTF, double IDF) {
        return normalizedTF * IDF;
    }


}