Package com.atilika.kuromoji.example

Source Code of com.atilika.kuromoji.example.TokenizerExample

/**
* Copyright 2010-2013 Atilika Inc. and contributors (see CONTRIBUTORS.md)
*
* Licensed under the Apache License, Version 2.0 (the "License"); you may
* not use this file except in compliance with the License.  A copy of the
* License is distributed with this work in the LICENSE.md file.  You may
* also obtain a copy of the License from
*
*     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.
*/
package com.atilika.kuromoji.example;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.List;

import com.atilika.kuromoji.AbstractTokenizer;
import com.atilika.kuromoji.Token;
import com.atilika.kuromoji.AbstractTokenizer.Mode;

public class TokenizerExample {

  public static void main(String[] args) throws IOException {
    AbstractTokenizer tokenizer;
    if (args.length == 1) {
      Mode mode = Mode.valueOf(args[0].toUpperCase());
      tokenizer = AbstractTokenizer.builder().mode(mode).build();
    } else if (args.length == 2) {
      Mode mode = Mode.valueOf(args[0].toUpperCase());
      tokenizer = AbstractTokenizer.builder().mode(mode).userDictionary(args[1]).build();
    } else {
      tokenizer = AbstractTokenizer.builder().build();
    }
    System.out.println("AbstractTokenizer ready.  Provide input text and press RET.");
    BufferedReader reader = new BufferedReader(new InputStreamReader(System.in));
    String line;
    while ((line = reader.readLine()) != null) {
      List<Token> result = tokenizer.tokenize(line);
      for (Token token : result) {
        System.out.println(token.getSurfaceForm() + "\t"
            + token.getAllFeatures());
      }
    }
  }
}
TOP

Related Classes of com.atilika.kuromoji.example.TokenizerExample

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.