BuildIndices.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 org.tallison.lucene.syns;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * This runs the three indexing steps in order.
 * 1) create the ngram+1 indices
 * 2) create the context index
 * 3) create the final word vector index
 */
class BuildIndices {


    public static void main(String[] args) throws IOException {
        Path sourceLuceneIndexPath = Paths.get(args[0]);
        String contentField = args[1];
        Path indexRoot = Paths.get(args[2]);
        SyntacticSynsConfig synsConfig = new SyntacticSynsConfig(indexRoot);
        boolean deleteIntermediateIndices = false;
        //parameters
        //column index in the csv file that should be treated as the narrative column
        int narrInd = 8;

        //maximum ngram for the target size
        synsConfig.setMaxKeyPhraseLength(3);

        //minimum number of times that the key phrase must occur
        synsConfig.setMinKeyPhraseTermFrequency(5);

        //this should weed out stop words from being targets
        int maxTargetCount = 10000;

        //minimum number of times that the target + a given context must occur
        int minTargetContextCount = 1;
        /*
		
		//add target pre and post stop sets
		*/


        //build NgramIndex
        NGramIndexBuilder ngramBuilder = new NGramIndexBuilder();
        ngramBuilder.execute(sourceLuceneIndexPath, contentField, synsConfig);
        System.out.println("finished building ngram index");

        //build context index
        ContextIndexBuilder contextBuilder = new ContextIndexBuilder();
//		contextBuilder.execute(synsConfig);
        System.out.println("finished building context index");
        //build syns index

        SynsIndexBuilder indexer = new SynsIndexBuilder(synsConfig);
        indexer.execute();
		/*if (deleteIntermediateIndices){
			FileUtil.rmdir(synsConfig.getNGramIndex());
			FileUtil.rmdir(synsConfig.getContextIndex());
		}
		*/
        System.out.println("Done with all three steps!");

    }
}