whitespacetokenizer.java

来自「中文分词,中科院分词的改装版。使用java调用dll来实现的。」· Java 代码 · 共 36 行

package org.apache.lucene.analysis;

/**
 * Copyright 2004 The Apache Software Foundation
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import java.io.Reader;

/** A WhitespaceTokenizer is a tokenizer that divides text at whitespace.
 * Adjacent sequences of non-Whitespace characters form tokens. */

public class WhitespaceTokenizer extends CharTokenizer {
  /** Construct a new WhitespaceTokenizer. */
  public WhitespaceTokenizer(Reader in) {
    super(in);
  }

  /** Collects only characters which do not satisfy
   * {@link Character#isWhitespace(char)}.*/
  protected boolean isTokenChar(char c) {
    return !Character.isWhitespace(c);
  }
}