edu.berkeley.nlp.io.PTBLineLexer Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of berkeleyparser Show documentation

The Berkeley parser analyzes the grammatical structure of natural language using probabilistic context-free grammars (PCFGs).

The newest version!

/**
 * 
 */
package edu.berkeley.nlp.io;

import java.io.IOException;
import java.util.Arrays;
import java.util.LinkedList;
import java.util.List;

/**
 * Similar to PTBLexer. However, instead of reading from a Reader this class is given a line
 * and returns a list of tokenized Strings.
 * @author petrov
 *
 */
public class PTBLineLexer extends PTBLexer {
	
	public PTBLineLexer(){
		super((java.io.Reader)null);
	}
	
	public List tokenizeLine(String line) throws IOException{
		LinkedList tokenized = new LinkedList();
		if (line==null) return tokenized;
		int nEl = line.length();
		char[] array = line.toCharArray();
		zzBuffer = line.toCharArray();//new char[nEl+1];
		//for(int i=0;i