org.deeplearning4j.text.tokenization.tokenizer.NGramTokenizer Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of deeplearning4j-nlp Show documentation
The newest version!
/*
 *  ******************************************************************************
 *  *
 *  *
 *  * This program and the accompanying materials are made available under the
 *  * terms of the Apache License, Version 2.0 which is available at
 *  * https://www.apache.org/licenses/LICENSE-2.0.
 *  *
 *  *  See the NOTICE file distributed with this work for additional
 *  *  information regarding copyright ownership.
 *  * 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.
 *  *
 *  * SPDX-License-Identifier: Apache-2.0
 *  *****************************************************************************
 */

package org.deeplearning4j.text.tokenization.tokenizer;

import org.apache.commons.lang3.StringUtils;

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

/**
 * @author sonali
 */
public class NGramTokenizer implements Tokenizer {
    private List tokens;
    private List originalTokens;
    private int index;
    private TokenPreProcess preProcess;
    private Tokenizer tokenizer;

    public NGramTokenizer(Tokenizer tokenizer, Integer minN, Integer maxN) {
        this.tokens = new ArrayList<>();
        while (tokenizer.hasMoreTokens()) {
            String nextToken = tokenizer.nextToken();
            this.tokens.add(nextToken);
        }
        if (maxN != 1) {
            this.originalTokens = this.tokens;
            this.tokens = new ArrayList<>();
            Integer nOriginalTokens = this.originalTokens.size();
            Integer min = Math.min(maxN + 1, nOriginalTokens + 1);
            for (int i = minN; i < min; i++) {
                for (int j = 0; j < nOriginalTokens - i + 1; j++) {
                    List originalTokensSlice = this.originalTokens.subList(j, j + i);
                    this.tokens.add(StringUtils.join(originalTokensSlice, " "));
                }
            }
        }
    }

    @Override
    public boolean hasMoreTokens() {
        return index < tokens.size();
    }

    @Override
    public int countTokens() {
        return tokens.size();
    }

    @Override
    public String nextToken() {
        String ret = tokens.get(index);
        index++;
        return ret;
    }

    @Override
    public List getTokens() {
        List tokens = new ArrayList<>();
        while (hasMoreTokens()) {
            tokens.add(nextToken());
        }
        return tokens;
    }

    @Override
    public void setTokenPreProcessor(TokenPreProcess tokenPreProcessor) {
        this.preProcess = tokenPreProcessor;
    }
}