Reads in a word list index from http://wordnet.princeton.edu/wordnet/download/current-version/ and filters/transforms to something more usable

WordListProcessor.java

import java.io.*;

public class WordListProcessor {

    public static final char[] EXCLUDE_CHARS = {'_', '-', '.', '\''};

    public static void main(String[] args) throws Exception {


        StringBuilder content = new StringBuilder();

        File file = new File("/Users/shane.witbeck/Downloads/dict/index.adv");
        BufferedReader br = new BufferedReader(new FileReader(file));
        String line;
        int startLine = 50, curLine = 0;
        int maxLen = 6;
        while ((line = br.readLine()) != null) {
            if (curLine >= startLine) {
                String nline = line.substring(0, line.indexOf(' '));
                if (nline.length() > maxLen) {
                    continue;
                }
                char[] nlineArr = nline.toCharArray();
                boolean include = true;
                for (char excludeChar : EXCLUDE_CHARS) {
                    for (char c : nlineArr) {
                        if (c == excludeChar) {
                            include = false;
                            break;
                        }
                    }
                    if (!include) {
                        break;
                    }
                }
                if (include) {
                    content.append(nline).append("\n");
                }
            }
            curLine++;
        }
        br.close();

        File out = new File("/Users/shane.witbeck/Downloads/dict/adverbs.txt");
        FileWriter fw = new FileWriter(out.getAbsoluteFile());
        BufferedWriter bw = new BufferedWriter(fw);
        bw.write(content.toString());
        bw.close();
    }
}