Created
November 30, 2012 16:18
-
-
Save dbasch/4176756 to your computer and use it in GitHub Desktop.
Quick and dirty text indexer
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.File; | |
import java.util.regex.Pattern; | |
import java.util.Scanner; | |
import com.google.common.collect.ArrayListMultimap; | |
/** create in-memory mappings from words to the files that contain them */ | |
public class Indexer { | |
public static ArrayListMultimap<String,String> buildIndex(String dirName) throws java.io.IOException { | |
ArrayListMultimap<String,String> map = ArrayListMultimap.create(); | |
Pattern p = Pattern.compile("[\\s#&!:,;\\.\\\\+-]+"); | |
for (File f : new File(dirName).listFiles()) { | |
String contents = new Scanner(f).useDelimiter("\\Z").next(); | |
for (String word : p.split(contents.toLowerCase())) { | |
map.put(word, f.getName()); | |
} | |
} | |
return map; | |
} | |
//for testing | |
public static void main(String args[]) throws java.io.IOException { | |
ArrayListMultimap<String,String> index = Indexer.buildIndex(args[0]); | |
System.out.println(index.get(args[1])); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment