Examples of org.apache.lucene.document.TextField

org.apache.lucene.document.TextField
A field that is indexed and tokenized, without term vectors. For example this would be used on a 'body' field, that contains the bulk of a document's text.

    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), directory,
                                                     newIndexWriterConfig(TEST_VERSION_CURRENT, new TestPayloadAnalyzer()));


    Document doc = new Document();
    doc.add(new TextField("content", new StringReader("a b c d e f g h i j a k")));
    writer.addDocument(doc);


    IndexReader reader = writer.getReader();
    IndexSearcher is = newSearcher(reader);
    writer.close();

View Full Code Here

    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), directory,
                                                     newIndexWriterConfig(TEST_VERSION_CURRENT, new TestPayloadAnalyzer()));


    Document doc = new Document();
    doc.add(new TextField("content", new StringReader("a b a d k f a h i k a k")));
    writer.addDocument(doc);
    IndexReader reader = writer.getReader();
    IndexSearcher is = newSearcher(reader);
    writer.close();

View Full Code Here

    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), directory,
                                                     newIndexWriterConfig(TEST_VERSION_CURRENT, new TestPayloadAnalyzer()));


    Document doc = new Document();
    doc.add(new TextField("content", new StringReader("j k a l f k k p a t a k l k t a")));
    writer.addDocument(doc);
    IndexReader reader = writer.getReader();
    IndexSearcher is = newSearcher(reader);
    writer.close();

View Full Code Here


          // 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(fis, "UTF-8"))));


          if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
            // New index, so we just add the document (no old document can be there):
            System.out.println("adding " + file);
            writer.addDocument(doc);

View Full Code Here

                @Override
                public void run() {
                    try {
                        for (int j = 0; j < numDocs; j++) {
                            Document d = new Document();
                            d.add(new TextField(field, new PoolingPayloadTokenStream(pool)));
                            writer.addDocument(d);
                        }
                    } catch (Exception e) {
                        e.printStackTrace();
                        fail(e.toString());

View Full Code Here

  public void testAcrossFields() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir,
                                                     new MockAnalyzer(random(), MockTokenizer.WHITESPACE, true));
    Document doc = new Document();
    doc.add(new TextField("hasMaybepayload", "here we go", Field.Store.YES));
    writer.addDocument(doc);
    writer.close();


    writer = new RandomIndexWriter(random(), dir,
                                   new MockAnalyzer(random(), MockTokenizer.WHITESPACE, true));
    doc = new Document();
    doc.add(new TextField("hasMaybepayload2", "here we go", Field.Store.YES));
    writer.addDocument(doc);
    writer.addDocument(doc);
    writer.forceMerge(1);
    writer.close();

View Full Code Here

    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(TEST_VERSION_CURRENT, null);
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir, iwc);
    Document doc = new Document();
    Field field = new TextField("field", "", Field.Store.NO);
    TokenStream ts = new MockTokenizer(new StringReader("here we go"), MockTokenizer.WHITESPACE, true);
    assertFalse(ts.hasAttribute(PayloadAttribute.class));
    field.setTokenStream(ts);
    doc.add(field);
    writer.addDocument(doc);
    Token withPayload = new Token("withPayload", 0, 11);
    withPayload.setPayload(new BytesRef("test"));
    ts = new CannedTokenStream(withPayload);
    assertTrue(ts.hasAttribute(PayloadAttribute.class));
    field.setTokenStream(ts);
    writer.addDocument(doc);
    ts = new MockTokenizer(new StringReader("another"), MockTokenizer.WHITESPACE, true);
    assertFalse(ts.hasAttribute(PayloadAttribute.class));
    field.setTokenStream(ts);
    writer.addDocument(doc);
    DirectoryReader reader = writer.getReader();
    AtomicReader sr = SlowCompositeReaderWrapper.wrap(reader);
    DocsAndPositionsEnum de = sr.termPositionsEnum(new Term("field", "withPayload"));
    de.nextDoc();

View Full Code Here

  /** some field instances have payload att, some not */
  public void testMixupMultiValued() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    Field field = new TextField("field", "", Field.Store.NO);
    TokenStream ts = new MockTokenizer(new StringReader("here we go"), MockTokenizer.WHITESPACE, true);
    assertFalse(ts.hasAttribute(PayloadAttribute.class));
    field.setTokenStream(ts);
    doc.add(field);
    Field field2 = new TextField("field", "", Field.Store.NO);
    Token withPayload = new Token("withPayload", 0, 11);
    withPayload.setPayload(new BytesRef("test"));
    ts = new CannedTokenStream(withPayload);
    assertTrue(ts.hasAttribute(PayloadAttribute.class));
    field2.setTokenStream(ts);
    doc.add(field2);
    Field field3 = new TextField("field", "", Field.Store.NO);
    ts = new MockTokenizer(new StringReader("nopayload"), MockTokenizer.WHITESPACE, true);
    assertFalse(ts.hasAttribute(PayloadAttribute.class));
    field3.setTokenStream(ts);
    doc.add(field3);
    writer.addDocument(doc);
    DirectoryReader reader = writer.getReader();
    SegmentReader sr = getOnlySegmentReader(reader);
    DocsAndPositionsEnum de = sr.termPositionsEnum(new Term("field", "withPayload"));

View Full Code Here


  public void testMoreThan32ProhibitedClauses() throws Exception {
    final Directory d = newDirectory();
    final RandomIndexWriter w = new RandomIndexWriter(random(), d);
    Document doc = new Document();
    doc.add(new TextField("field", "0 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", Field.Store.NO));
    w.addDocument(doc);
    doc = new Document();
    doc.add(new TextField("field", "33", Field.Store.NO));
    w.addDocument(doc);
    final IndexReader r = w.getReader();
    w.close();
    final IndexSearcher s = newSearcher(r);

View Full Code Here

    tokens[2].append("c");
    tokens[2].setPositionIncrement(0);


    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(new TextField("field", new CannedTokenStream(tokens)));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new TextField("field", new CannedTokenStream(tokens)));
    writer.addDocument(doc);
    IndexReader r = writer.getReader();
    writer.close();
    IndexSearcher s = newSearcher(r);
    MultiPhraseQuery mpq = new MultiPhraseQuery();

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.document.TextField

cc.twittertools.index.IndexStatuses

cc.twittertools.search.indexing.IndexStatuses

com.bah.lucene.tools.WriteReadPerformanceTest

com.bericotech.clavin.index.IndexDirectoryBuilder

com.browseengine.bobo.test.BasicIndexingTest

com.foundationdb.server.service.text.IndexedField

com.gitblit.tickets.TicketIndexer

com.mysema.query.lucene.LuceneQueryTest

com.twitter.elephantbird.mapreduce.LuceneIndexingIntegrationTest$IndexOutputFormat

edu.isi.karma.semantictypes.tfIdf.Indexer

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.