TokenizeUDF.java

/*
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you 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.
 */
package hivemall.tools.text;

import java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.hive.ql.udf.UDFType;
import org.apache.hadoop.io.Text;

@Description(name = "tokenize", value = "_FUNC_(string englishText [, boolean toLowerCase])"
        + " - Returns tokenized words in array<string>")
@UDFType(deterministic = true, stateful = false)
public final class TokenizeUDF extends UDF {
    private static final String DELIM = " .,?!:;()<>[]\b\t\n\f\r\"\'\\";

    public List<Text> evaluate(Text input) {
        return evaluate(input, false);
    }

    public List<Text> evaluate(Text input, boolean toLowerCase) {
        final List<Text> tokens = new ArrayList<Text>();
        final StringTokenizer tokenizer = new StringTokenizer(input.toString(), DELIM);
        while (tokenizer.hasMoreElements()) {
            String word = tokenizer.nextToken();
            if (toLowerCase) {
                word = word.toLowerCase();
            }
            tokens.add(new Text(word));
        }
        return tokens;
    }

}