Example usage for org.apache.lucene.index IndexWriter addDocument

Introduction

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

Prototype

public long addDocument(Iterable<? extends IndexableField> doc) throws IOException 

Source Link

Document

Adds a document to this index.

Usage

From source file:de.hybris.platform.lucenesearch.jalo.LuceneTest.java

License:Open Source License

@Test
public void testReindex() throws IOException {
    assertTermSearch(set(docA, docB, docC), "text");

    final IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_40,
            new StandardAnalyzer(Version.LUCENE_40)).setOpenMode(OpenMode.APPEND);
    final IndexWriter changewriter = new IndexWriter(directory, indexWriterConfig);

    changewriter.deleteDocuments(new Term("key", "b"));

    final Document docB2 = new Document();
    docB2.add(new Field("key", "b", Field.Store.YES, Field.Index.NOT_ANALYZED));
    docB2.add(new Field("text", "neuer texxxt zum zweiten document", Field.Store.YES, Field.Index.ANALYZED));
    changewriter.addDocument(docB2);
    changewriter.close();//www. j a va  2 s .  c o  m
    assertTermSearch(set(docA, docB2, docC), "zum");
    assertTermSearch(set(docA, docC), "text");
    assertTermSearch(set(docB2), "texxxt");
}

---

From source file:de.ingrid.search.utils.facet.DummyIndex.java

License:EUPL

private static File createTestIndex() {
    File indexDirectory = new File("./test_index");
    if (!indexDirectory.exists()) {
        try {/*from  w w w. j ava 2 s  .  c o m*/
            IndexWriter writer = new IndexWriter(FSDirectory.getDirectory(indexDirectory),
                    new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
            for (Object[][] doc : IndexDef) {
                Document document = new Document();
                for (Object[] fields : doc) {
                    document.add(new Field((String) fields[0], (String) fields[1], (Field.Store) fields[2],
                            (Field.Index) fields[3]));
                }
                writer.addDocument(document);
            }
            writer.close();
        } catch (CorruptIndexException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    return indexDirectory;
}

---

From source file:de.ingrid.upgrader.service.ManifestIndexer.java

License:EUPL

private void index(final List<File> files) throws Exception {
    // create tmp index folder
    LOG.debug("  create tmp index folder");
    final File tmp = new File(_targetFolder, IKeys.TEMP_FOLDER);
    if (!tmp.exists()) {
        tmp.mkdirs();//from w  w  w.j  a  va 2 s .  c o m
    }

    // indexer
    LOG.debug("  initialize index writer");
    final StandardAnalyzer analyzer = new StandardAnalyzer();
    final IndexWriter writer = new IndexWriter(tmp, analyzer, true);

    // add files to index
    LOG.debug("  adding documents");
    for (final File file : files) {
        final Document doc = fileToDocument(file);
        if (doc != null) {
            writer.addDocument(doc);
        }
    }

    // optimize
    LOG.debug("  optimizing and closing writer");
    writer.optimize();
    writer.close();

    // close searcher
    final LuceneSearcher searcher = LuceneSearcher.getInstance();
    if (searcher != null) {
        searcher.closeReader();
    }

    // rename index
    LOG.debug("  renaming tmp index folder");
    final File folder = new File(_targetFolder, IKeys.INDEX_FOLDER);
    delete(folder);
    tmp.renameTo(folder);

    // open new searcher
    if (searcher == null) {
        LuceneSearcher.createInstance(folder);
    } else {
        searcher.openReader(folder);
    }
}

---

From source file:de.jetsli.lumeo.util.LuceneHelperTest.java

License:Apache License

@Test
public void testTermMatching() throws Exception {
    RAMDirectory dir = new RAMDirectory();
    IndexWriter w = new IndexWriter(dir, new IndexWriterConfig(RawLucene.VERSION, new KeywordAnalyzer()));
    Document d = new Document();

    FieldType ft = Mapping.getLongFieldType(true, true);
    d.add(new LongField("id", 1234, ft));
    d.add(new LongField("tmp", 1111, ft));
    w.addDocument(d);

    d = new Document();
    d.add(new LongField("id", 1234, ft));
    d.add(new LongField("tmp", 2222, ft));
    w.updateDocument(getTerm("id", 1234), d);

    d = new Document();
    d.add(new LongField("id", 0, ft));
    w.addDocument(d);/*from  w  w  w . j  a v a 2  s.  c  o m*/
    w.commit();

    IndexReader reader = DirectoryReader.open(w, true);
    IndexSearcher searcher = new IndexSearcher(reader);

    BytesRef bytes = new BytesRef();
    NumericUtils.longToPrefixCoded(1234, 0, bytes);
    TopDocs td = searcher.search(new TermQuery(new Term("id", bytes)), 10);
    assertEquals(1, td.totalHits);
    assertEquals(1234L, searcher.doc(td.scoreDocs[0].doc).getField("id").numericValue());
    assertEquals(2222L, searcher.doc(td.scoreDocs[0].doc).getField("tmp").numericValue());
    w.close();
}

---

From source file:de.ks.flatadocdb.index.LuceneIndex.java

License:Apache License

protected void writeEntry(SessionEntry sessionEntry, IndexWriter writer) throws IOException {
    LuceneDocumentExtractor luceneExtractor = sessionEntry.getEntityDescriptor().getLuceneExtractor();
    @SuppressWarnings("unchecked")
    Document document = luceneExtractor.createDocument(sessionEntry.getObject());
    if (document == null) {
        document = new Document();
    }//from  w  w w .j av a2s .  c  om
    String id = sessionEntry.getId();
    String fileName = sessionEntry.getFileName();
    NaturalId naturalId = sessionEntry.getNaturalId();
    appendStandardFields(document, id, fileName, naturalId);

    if (log.isTraceEnabled()) {
        document.getFields().forEach(f -> log.trace("Extracted field {} from {}({}). Vaue={}", //
                f.name(), sessionEntry.getObject(), sessionEntry.getFileName(), //
                f.stringValue().length() > 70 ? f.stringValue().substring(0, 70) : f.stringValue()));
    }
    writer.addDocument(document);
}

---

From source file:de.ks.lucene.LuceneTaggingTest.java

License:Apache License

@Test
public void testTags() throws Exception {
    IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(analyzer));

    List<String> allTags = Arrays.asList("Bla Blubb", "Blubb", "Blubber Huhu", "Bla Huhu", "Haha");
    for (String tag : allTags) {
        Document doc = new Document();
        doc.add(new TextField("tags", tag, Field.Store.YES));
        writer.addDocument(doc);
    }//from   www  .j a v  a 2s  .c  o m
    writer.close();

    DirectoryReader directoryReader = DirectoryReader.open(directory);
    IndexSearcher searcher = new IndexSearcher(directoryReader);
    String term = "blubb";
    TermQuery termQuery = new TermQuery(new Term("tags", term));
    TopDocs search = searcher.search(termQuery, 50);
    log("TermQuery", searcher, search);

    FuzzyQuery fuzzyQuery = new FuzzyQuery(new Term("tags", term));
    search = searcher.search(fuzzyQuery, 50);
    log("FuzzyQuery", searcher, search);

    BooleanQuery.Builder builder = new BooleanQuery.Builder();
    builder.add(new TermQuery(new Term("tags", "blubb")), BooleanClause.Occur.SHOULD);
    builder.add(new TermQuery(new Term("tags", "bla")), BooleanClause.Occur.SHOULD);
    BooleanQuery query = builder.build();
    search = searcher.search(query, 50);
    log("BooleanQuery", searcher, search);
}

---

From source file:de.lmu.ifi.dbs.elki.application.lucene.SimpleTextLoader.java

License:Open Source License

@Override
public void run() {
    try {//w w  w. ja va 2 s . c  om
        final Directory dir = FSDirectory.open(index);
        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_36,
                new StandardAnalyzer(Version.LUCENE_36));
        IndexWriter writer = new IndexWriter(dir, config);

        final URI suri = source.toURI();
        for (File inf : source.listFiles()) {
            Document doc = new Document();
            String id = suri.relativize(inf.toURI()).getPath();
            String text = FileUtil.slurp(new FileInputStream(inf));
            doc.add(new Field("id", id, Field.Store.YES, Field.Index.NOT_ANALYZED));
            doc.add(new Field("contents", text, Field.Store.YES, Field.Index.ANALYZED));
            writer.addDocument(doc);
        }
        writer.close();
    } catch (IOException e) {
        throw new AbortException("I/O error in lucene.", e);
    }
}

---

From source file:de.nava.informa.search.ChannelIndexer.java

License:Open Source License

/**
 * Index all given news items.//from w w  w  .j  av a2  s.  c  o m
 *
 * @param createNewIndex - Wether a new index should be generated or
 *                       an existant one should be taken into account.
 * @param items          - A collection of ItemIF objects.
 */
public void indexItems(boolean createNewIndex, Collection<ItemIF> items) throws java.io.IOException {
    if (LOG.isDebugEnabled()) {
        LOG.debug("Start writing index.");
    }
    IndexWriter writer = new IndexWriter(indexDir, analyzer, createNewIndex);
    try {
        for (ItemIF item1 : items) {
            if (LOG.isDebugEnabled()) {
                LOG.debug("Add item " + item1 + " to index.");
            }
            writer.addDocument(ItemDocument.makeDocument(item1));
        }
        writer.optimize();
        nrOfIndexedItems = writer.docCount();
    } finally {
        writer.close();
    }
    if (LOG.isDebugEnabled()) {
        LOG.info("Finished writing index.");
    }
}

---

From source file:de.qaware.chronix.lucene.client.add.LuceneAddingService.java

License:Apache License

/**
 * Adds the given collection of time series to the lucene index.
 * Converts the time series using the default object types of java and available lucene fields.
 * If an attribute of a time series is user defined data type then it is ignored.
 * <p>/*w  ww.  ja  v a 2 s  .c  om*/
 * Note: The add method do not commit the time series.
 *
 * @param converter   the converter to converter the time series into a lucene document
 * @param timeSeries  the collection with time series
 * @param indexWriter the lucene index writer
 * @return true if successful, otherwise false
 */
public static <T> boolean add(TimeSeriesConverter<T> converter, Collection<T> timeSeries,
        IndexWriter indexWriter) {

    if (timeSeries == null || timeSeries.isEmpty()) {
        LOGGER.debug("Collection is empty. Nothing to commit");
        return true;
    }

    timeSeries.parallelStream().forEach(ts -> {
        try {
            indexWriter.addDocument(convert(ts, converter));
        } catch (IOException e) {
            LOGGER.error("Could not add documents to lucene.", e);
        }
    });
    return true;
}

---

From source file:de.tuberlin.dima.cuttlefish.preprocessing.indexing.Indexer.java

License:Open Source License

public void index(File indexDir) throws Exception {
    Directory index = new SimpleFSDirectory(indexDir);
    Analyzer analyzer = featureExtraction.analyzerToUse();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_42, analyzer);
    final IndexWriter writer = new IndexWriter(index, config);

    final AtomicInteger numDocsIndexed = new AtomicInteger(0);

    try {/*from   w ww.jav  a 2  s  .  c  o m*/

        newsItemExtractor.extract(new NewsItemProcessor() {
            @Override
            public void process(NewsItem newsItem) {

                try {
                    writer.addDocument(featureExtraction.asDocument(newsItem));
                    int numDocs = numDocsIndexed.incrementAndGet();
                    if (numDocs % 100 == 0) {
                        log.info("Indexed {} news articles", numDocs);
                    }

                } catch (IOException e) {
                    log.error("Failed to index news item", e);
                }
            }
        });

    } finally {
        writer.close(true);
    }

    log.info("Indexed {} news articles", numDocsIndexed.get());
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »