uk.ac.glasgow.scclippy.plugin.lucene.IndexFiles.java Source code

Java tutorial

Introduction

Here is the source code for uk.ac.glasgow.scclippy.plugin.lucene.IndexFiles.java

Source

package uk.ac.glasgow.scclippy.plugin.lucene;

/*
 * 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.
 */

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.document.*;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.*;
import java.nio.file.attribute.BasicFileAttributes;

/**
 * Index all text files under a directory.
 * <p>
 * This is a command-line application demonstrating simple Lucene indexing.
 * Run it with no command-line arguments for usage information.
 */
public class IndexFiles {

    static int filesIndexed;

    /**
     * Index all text files under a directory.
     *
     * @param indexPath   path to the index
     * @param dataPath    path to the data
     * @param updateIndex update the index or create new instead
     * @return successful/unsuccessful creation of index
     */
    public static boolean index(String indexPath, String dataPath, boolean updateIndex) throws IOException {
        filesIndexed = 0;

        if (dataPath == null)
            return false;

        final Path docDir = Paths.get(dataPath);
        if (!Files.isReadable(docDir))
            return false;

        Directory dir = FSDirectory.open(Paths.get(indexPath));
        Analyzer analyzer = new StandardAnalyzer(CharArraySet.EMPTY_SET);
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);

        if (updateIndex) {
            // Create a new index in the directory
            iwc.setOpenMode(OpenMode.CREATE);
        } else {
            // Add new documents to an existing index:
            iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
        }

        IndexWriter writer = new IndexWriter(dir, iwc);
        indexDocs(writer, docDir);

        writer.close();

        return true;
    }

    /**
     * Indexes the given file using the given writer, or if a directory is given,
     * recurses over files and directories found under the given directory.
     * <p>
     * NOTE: This method indexes one document per inputArea file.  This is slow.  For good
     * throughput, put multiple documents into your inputArea file(s).  An example of this is
     * in the benchmark module, which can create "line doc" files, one document per line,
     * using the
     * <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html"
     * >WriteLineDocTask</a>.
     *
     * @param writer Writer to the index where the given file/dir info will be stored
     * @param path   The file to index, or the directory to recurse into to find files to index
     * @throws IOException If there is a low-level I/O error
     */
    static void indexDocs(final IndexWriter writer, Path path) throws IOException {
        if (Files.isDirectory(path)) {
            Files.walkFileTree(path, new SimpleFileVisitor<Path>() {
                @Override
                public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
                    try {
                        indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
                    } catch (IOException ignore) {
                        // don't index files that can't be read.
                    }
                    return FileVisitResult.CONTINUE;
                }
            });
        } else {
            indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
        }
    }

    /**
     * Indexes a single document
     */
    static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
        try (InputStream stream = Files.newInputStream(file)) {
            // make a new, empty document
            Document doc = new Document();

            // Add the path of the file as a field named "path".  Use a
            // field that is indexed (i.e. searchable), but don't tokenize
            // the field into separate words and don't index term frequency
            // or positional information:
            Field pathField = new StringField("path", file.toString(), Field.Store.YES);
            doc.add(pathField);

            // Add the last modified date of the file a field named "modified".
            // Use a LongField that is indexed (i.e. efficiently filterable with
            // NumericRangeFilter).  This indexes to milli-second resolution, which
            // is often too fine.  You could instead create a number based on
            // year/month/day/hour/minutes/seconds, down the resolution you require.
            // For example the long value 2011021714 would mean
            // February 17, 2011, 2-3 PM.
            doc.add(new LongField("modified", lastModified, Field.Store.NO));

            // Add the contents of the file to a field named "contents".  Specify a Reader,
            // so that the text of the file is tokenized and indexed, but not stored.
            // Note that FileReader expects the file to be in UTF-8 encoding.
            // If that's not the case searching for special characters will fail.
            doc.add(new TextField("contents",
                    new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));

            if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
                // New index, so we just add the document (no old document can be there):
                writer.addDocument(doc);
            } else {
                // Existing index (an old copy of this document may have been indexed) so
                // we use updateDocument instead to replace the old one matching the exact
                // path, if present:
                writer.updateDocument(new Term("path", file.toString()), doc);
            }
            filesIndexed++;
        }
    }

    public static int getFilesIndexed() {
        return filesIndexed;
    }
}