Created
April 9, 2014 15:43
-
-
Save thesurlydev/10284561 to your computer and use it in GitHub Desktop.
Reads in a word list index from http://wordnet.princeton.edu/wordnet/download/current-version/ and filters/transforms to something more usable
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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(); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment