Parser.java
package edu.odu.cs.cs350.acmClassifier;
//import java.util.ArrayList;
public class Parser {
/**
*
**/
public void Parse(){
//using apache tika read in file and output text
}
//tokenize function(s)
//termWeighting function(s)
/**
*
* //param document object
**/
//public ArrayList<Integer> normalize(ArrayList<Integer> signatures){
/*
public static ArrayList<Integer > normalize(Document d){
for (int i = 0; i < d.wordCounts.size(); i++) {
if (d.wordCounts.get(i) >= 4){
d.wordCounts.set(i, 1);
}
else{
d.wordCounts.set(i, 0);
}
}
return d.wordCounts;
}
*/
public static void normalize(Document d){
for (int i = 0; i < d.wordCounts.size(); i++){
if (d.wordCounts.get(i) >= 4){
d.normalizedWordCounts.add(1.0);
}
else{
d.normalizedWordCounts.add(0.0);
}
}
}
}