Example usage for org.apache.lucene.index IndexWriterConfig IndexWriterConfig

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexWriterConfig IndexWriterConfig.

Prototype

public IndexWriterConfig(Analyzer analyzer) 

Source Link

Document

Creates a new config that with the provided Analyzer .

Usage

From source file:com.shaie.suggest.ContextSuggestDemo.java

License:Apache License

private void buildSearchIndex() throws IOException {
    final IndexWriterConfig conf = new IndexWriterConfig(analyzer);
    try (IndexWriter writer = new IndexWriter(indexDir, conf)) {
        Document doc = new Document();
        doc.add(new StringField("username", USER1_CONTEXT.utf8ToString(), Store.YES));
        doc.add(new TextField("content", USER1_TEXT.utf8ToString(), Store.YES));
        writer.addDocument(doc);/*from  w  w w  .  ja va2 s .  c o  m*/

        doc = new Document();
        doc.add(new StringField("username", USER2_CONTEXT.utf8ToString(), Store.YES));
        doc.add(new TextField("content", USER2_TEXT.utf8ToString(), Store.YES));
        writer.addDocument(doc);
    }
}

---

From source file:com.shaie.UTF8Indexing.java

License:Apache License

@SuppressWarnings("resource")
public static void main(String[] args) throws Exception {
    final Directory dir = new RAMDirectory();
    final StandardAnalyzer analyzer = new StandardAnalyzer();
    final IndexWriterConfig conf = new IndexWriterConfig(analyzer);
    final IndexWriter writer = new IndexWriter(dir, conf);

    final Document doc = new Document();
    doc.add(new TextField("f", "Russia\u2013United States relations", Store.YES));
    writer.addDocument(doc);//from   w  ww  . ja  va  2 s.c  om
    writer.close();

    final DirectoryReader reader = DirectoryReader.open(dir);
    final IndexSearcher searcher = new IndexSearcher(reader);
    final QueryParser qp = new QueryParser("f", analyzer);
    search(searcher, qp, "Russia United States relations");
    search(searcher, qp, "\"Russia United states relations\"");
    search(searcher, qp, "\"Russia-United states relations\"");
    search(searcher, qp, "\"Russia\u2013United states relations\"");
    reader.close();

    dir.close();
}

---

From source file:com.spike.text.lucene.util.LuceneTestBookIndexingUtil.java

License:Apache License

public static void main(String[] args) throws IOException {
    String dataDir = LuceneAppConstants.BOOK_DATA_DIR;
    String indexDir = LuceneAppConstants.BOOK_INDEX_DIR;

    List<File> results = new ArrayList<File>();
    findFiles(results, new File(dataDir));
    System.out.println(results.size() + " books to index");
    Directory directory = FSDirectory.open(Paths.get(indexDir));

    IndexWriterConfig config = new IndexWriterConfig(new MyStandardAnalyzer());
    config.setCommitOnClose(true);/*from   ww w.  j  a  v a2 s  .  co m*/
    IndexWriter indexWriter = new IndexWriter(directory, config);

    for (File file : results) {
        Document document = getDocument(dataDir, file);
        indexWriter.addDocument(document);
    }

    indexWriter.close();
    directory.close();
}

---

From source file:com.stratio.cassandra.lucene.index.DocumentIteratorTest.java

License:Apache License

@Test
public void testConstructorWithPageEqualsZero() throws IOException {
    IndexWriterConfig iwConfig = new IndexWriterConfig(new AnalyzerMock());
    SearcherManager searcherManager = new SearcherManager(new IndexWriterMock(new DirectoryMock(), iwConfig),
            true, null);/*from   w  ww  .  ja v  a2s . c  o  m*/
    DocumentIterator docIterator = new DocumentIterator(searcherManager, new Sort(), null, new QueryMock(),
            new Sort(), 0, new HashSet<>());

    assertEquals("document Iterator page is invalid", 1, docIterator.page);
}

---

From source file:com.stratio.cassandra.lucene.index.DocumentIteratorTest.java

License:Apache License

@Test
public void testConstructorWithPageEqualsOne() throws IOException {
    IndexWriterConfig iwConfig = new IndexWriterConfig(new AnalyzerMock());
    SearcherManager searcherManager = new SearcherManager(new IndexWriterMock(new DirectoryMock(), iwConfig),
            true, null);/*from  ww w  .j  a  v a 2  s. c  o m*/
    DocumentIterator docIterator = new DocumentIterator(searcherManager, new Sort(), null, new QueryMock(),
            new Sort(), 1, new HashSet<>());

    assertEquals("document Iterator page is invalid", 2, docIterator.page);
}

---

From source file:com.stratio.cassandra.lucene.index.DocumentIteratorTest.java

License:Apache License

@Test
public void testConstructorWithPageEqualsMaxValue() throws IOException {
    IndexWriterConfig iwConfig = new IndexWriterConfig(new AnalyzerMock());
    SearcherManager searcherManager = new SearcherManager(new IndexWriterMock(new DirectoryMock(), iwConfig),
            true, null);/*from  ww  w  .jav a2s  .co m*/
    DocumentIterator docIterator = new DocumentIterator(searcherManager, new Sort(), null, new QueryMock(),
            new Sort(), DocumentIterator.MAX_PAGE_SIZE, new HashSet<>());

    assertEquals("document Iterator page is invalid", DocumentIterator.MAX_PAGE_SIZE + 1, docIterator.page);
}

---

From source file:com.stratio.cassandra.lucene.index.DocumentIteratorTest.java

License:Apache License

@Test
public void testConstructorWithPageOverMaxValue() throws IOException {
    IndexWriterConfig iwConfig = new IndexWriterConfig(new AnalyzerMock());
    SearcherManager searcherManager = new SearcherManager(new IndexWriterMock(new DirectoryMock(), iwConfig),
            true, null);//from   w  w  w  .  j  ava 2s. c  o  m
    DocumentIterator docIterator = new DocumentIterator(searcherManager, new Sort(), null, new QueryMock(),
            new Sort(), 10000000, new HashSet<>());

    assertEquals("document Iterator page is invalid", DocumentIterator.MAX_PAGE_SIZE + 1, docIterator.page);
}

---

From source file:com.stratio.cassandra.lucene.index.FSIndex.java

License:Apache License

/**
 * Builds a new {@link FSIndex}.//  w w w  .ja v a  2s. c o m
 *
 * @param name the index name
 * @param mbeanName the JMX MBean object name
 * @param path the directory path
 * @param analyzer the index writer analyzer
 * @param refresh the index reader refresh frequency in seconds
 * @param ramBufferMB the index writer RAM buffer size in MB
 * @param maxMergeMB the directory max merge size in MB
 * @param maxCachedMB the directory max cache size in MB
 * @param refreshTask action to be done during refresh
 */
public FSIndex(String name, String mbeanName, Path path, Analyzer analyzer, double refresh, int ramBufferMB,
        int maxMergeMB, int maxCachedMB, Runnable refreshTask) {
    try {
        this.path = path;
        this.name = name;

        // Open or create directory
        FSDirectory fsDirectory = FSDirectory.open(path);
        directory = new NRTCachingDirectory(fsDirectory, maxMergeMB, maxCachedMB);

        // Setup index writer
        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
        indexWriterConfig.setRAMBufferSizeMB(ramBufferMB);
        indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
        indexWriterConfig.setUseCompoundFile(true);
        indexWriterConfig.setMergePolicy(new TieredMergePolicy());
        indexWriter = new IndexWriter(directory, indexWriterConfig);

        // Setup NRT search
        SearcherFactory searcherFactory = new SearcherFactory() {
            @Override
            public IndexSearcher newSearcher(IndexReader reader, IndexReader previousReader) {
                if (refreshTask != null) {
                    refreshTask.run();
                }
                IndexSearcher searcher = new IndexSearcher(reader);
                searcher.setSimilarity(new NoIDFSimilarity());
                return searcher;
            }
        };
        TrackingIndexWriter trackingWriter = new TrackingIndexWriter(indexWriter);
        searcherManager = new SearcherManager(indexWriter, true, searcherFactory);
        searcherReopener = new ControlledRealTimeReopenThread<>(trackingWriter, searcherManager, refresh,
                refresh);
        searcherReopener.start();

        // Register JMX MBean
        mbean = new ObjectName(mbeanName);
        ManagementFactory.getPlatformMBeanServer().registerMBean(this, this.mbean);

    } catch (Exception e) {
        throw new IndexException(logger, e, "Error while creating index %s", name);
    }
}

---

From source file:com.stratio.cassandra.lucene.index.RAMIndex.java

License:Apache License

/**
 * Builds a new {@link RAMIndex}./*ww  w .  java 2s .co m*/
 *
 * @param analyzer the index writer analyzer
 */
public RAMIndex(Analyzer analyzer) {
    try {
        directory = new RAMDirectory();
        indexWriter = new IndexWriter(directory, new IndexWriterConfig(analyzer));
    } catch (Exception e) {
        throw new IndexException(logger, e, "Error while creating index");
    }
}

---

From source file:com.stratio.cassandra.lucene.service.LuceneIndex.java

License:Apache License

/**
 * Builds a new {@code RowDirectory} using the specified directory path and analyzer.
 *
 * @param keyspace        The keyspace name.
 * @param table           The table name.
 * @param name            The index name.
 * @param path            The path of the directory in where the Lucene files will be stored.
 * @param ramBufferMB     The index writer buffer size in MB.
 * @param maxMergeMB      NRTCachingDirectory max merge size in MB.
 * @param maxCachedMB     NRTCachingDirectory max cached MB.
 * @param analyzer        The default {@link Analyzer}.
 * @param refreshSeconds  The index readers refresh time in seconds. Writings are not visible until this time.
 * @param refreshCallback A runnable to be run on index refresh.
 * @throws IOException If Lucene throws IO errors.
 *//*  ww  w  .j av a  2 s. c o  m*/
public LuceneIndex(String keyspace, String table, String name, Path path, Integer ramBufferMB,
        Integer maxMergeMB, Integer maxCachedMB, Analyzer analyzer, Double refreshSeconds,
        Runnable refreshCallback) throws IOException {
    this.path = path;
    this.refreshCallback = refreshCallback;
    this.logName = String.format("Lucene index %s.%s.%s", keyspace, table, name);

    // Open or create directory
    FSDirectory fsDirectory = FSDirectory.open(path);
    directory = new NRTCachingDirectory(fsDirectory, maxMergeMB, maxCachedMB);

    // Setup index writer
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    config.setRAMBufferSizeMB(ramBufferMB);
    config.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
    config.setUseCompoundFile(true);
    config.setMergePolicy(new TieredMergePolicy());
    indexWriter = new IndexWriter(directory, config);

    // Setup NRT search
    SearcherFactory searcherFactory = new SearcherFactory() {
        public IndexSearcher newSearcher(IndexReader reader) throws IOException {
            LuceneIndex.this.refreshCallBack();
            IndexSearcher searcher = new IndexSearcher(reader);
            searcher.setSimilarity(new NoIDFSimilarity());
            return searcher;
        }
    };
    TrackingIndexWriter trackingIndexWriter = new TrackingIndexWriter(indexWriter);
    searcherManager = new SearcherManager(indexWriter, true, searcherFactory);
    searcherReopener = new ControlledRealTimeReopenThread<>(trackingIndexWriter, searcherManager,
            refreshSeconds, refreshSeconds);
    searcherReopener.start(); // Start the refresher thread

    // Register JMX MBean
    try {
        objectName = new ObjectName(
                String.format("com.stratio.cassandra.lucene:type=LuceneIndexes,keyspace=%s,table=%s,index=%s",
                        keyspace, table, name));
        ManagementFactory.getPlatformMBeanServer().registerMBean(this, objectName);
    } catch (MBeanException | OperationsException e) {
        Log.error(e, "Error while registering MBean");
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• »