edu.stanford.nlp.process.Tokenizer Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of stanford-parser Show documentation

Stanford Parser processes raw text in English, Chinese, German, Arabic, and French, and extracts constituency parse trees.

The newest version!

package edu.stanford.nlp.process;


import java.util.Iterator;
import java.util.List;

/**
 * Tokenizers break up text into individual Objects. These objects may be
 * Strings, Words, or other Objects.  A Tokenizer extends the Iterator
 * interface, but provides a lookahead operation {@code peek()}.  An
 * implementation of this interface is expected to have a constructor that
 * takes a single argument, a Reader.
 *
 * @author Teg Grenager ([email protected])
 */
public interface Tokenizer extends Iterator {

  /* Provides the standard Iterator methods: next(), hasNext().
   * remove() will normally not be implemented.
   */

  /**
   * Returns the next token, without removing it, from the Tokenizer, so
   * that the same token will be again returned on the next call to
   * next() or peek().
   *
   * @return the next token in the token stream.
   * @throws java.util.NoSuchElementException If the token stream has no more tokens.
   */
  T peek();

  /**
   * Returns all tokens of this Tokenizer as a List for convenience.
   *
   * @return A list of all the tokens
   */
  List tokenize();

}