NGramIndexBuilder.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;
import java.util.HashSet;
import java.util.Set;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.miscellaneous.LimitTokenCountAnalyzer;
import org.apache.lucene.analysis.shingle.ShingleAnalyzerWrapper;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Bits;
import org.tallison.lucene.syns.contextifiers.Contextifier;

/**
 * Builds the initial ngram index from another Lucene index
 */
class NGramIndexBuilder {
    private static final Logger LOGGER = LogManager.getLogger();

    public static void main(String[] args) throws IOException {
        Path luceneIndexDir = Paths.get(args[0]);
        String contentField = args[1];
        Path synsIndexDir = Paths.get(args[2]);

        SyntacticSynsConfig config = new SyntacticSynsConfig(synsIndexDir);
        config.setMaxKeyPhraseLength(3);
        NGramIndexBuilder builder = new NGramIndexBuilder();
    }

    public boolean execute(Path sourceLuceneIndexDir, String contentField, SyntacticSynsConfig synsConfig) throws IOException {
        try (Directory directory = FSDirectory.open(sourceLuceneIndexDir)) {
            try (IndexReader indexReader = DirectoryReader.open(directory)) {
                return _execute(indexReader, contentField, synsConfig);
            }
        }
    }

    private boolean _execute(IndexReader indexReader, String contentField, SyntacticSynsConfig synsConfig) throws IOException {
        int actualMaxNGram = synsConfig.getMaxKeyPhraseLength() + Math.max(synsConfig.getPreContextSize(), synsConfig.getPostContextSize());
        //adding an empty hashset to the standardanalyzer is necessary to prevent stopword removal
        Analyzer wrapped = synsConfig.getBaseAnalyzer();
        Analyzer analyzer = new ShingleAnalyzerWrapper(wrapped, 2, actualMaxNGram, Contextifier.NGRAM_DELIMITER,
                false, false, Contextifier.FILLER_TOKEN);
        analyzer = new LimitTokenCountAnalyzer(analyzer, synsConfig.getMaxTokenToReadCount());
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        config.setOpenMode(OpenMode.CREATE);
        config.setRAMBufferSizeMB(150.0);

        IndexWriter writer = new IndexWriter(FSDirectory.open(synsConfig.getNGramIndex()), config);


        Document d = new Document();
        TextField field = new TextField(SyntacticSynsConfig.getNgramField(), "", Field.Store.NO);
        d.add(field);
        StringBuilder sb = new StringBuilder();
        Set<String> fieldsToLoad = new HashSet<>();
        fieldsToLoad.add(contentField);
        Bits liveDocs = MultiFields.getLiveDocs(indexReader);
        int cnt = 0;
        for (int i = 0; i < indexReader.maxDoc(); i++) {
            if (! liveDocs.get(i)) {
                continue;
            }
            Document doc = indexReader.document(i, fieldsToLoad);
            //can it ever be null?
            if (doc == null) {
                continue;
            }

            for (String s : doc.getValues(contentField)) {
                sb.append(s).append(" ");
            }
            field.setStringValue(sb.toString());
            sb.setLength(0);
            writer.addDocument(d);
            if (++i % 100 == 0) {
                LOGGER.info("processed " + cnt++ + " docs");
            }
        }
        writer.close();
        LOGGER.info("Finished.  Processed "+cnt+" docs total.");
        return true;
    }
}