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.

      t1.setPayload(new BytesRef(new byte[] { 0x1 } ));
    }
    TokenStream overflowingTokenStream = new CannedTokenStream(
        new Token[] { t1 }
    );
    Field field = new TextField("foo", overflowingTokenStream);
    doc.add(field);
    iw.addDocument(doc);
    iw.close();
    dir.close();
  }

View Full Code Here

    IndexWriterConfig iwc = new IndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random()));
    iwc.setMergePolicy(newLogMergePolicy());
    IndexWriter iw = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new StringField("field1", "sometext", Field.Store.YES));
    doc.add(new TextField("field2", "sometext", Field.Store.NO));
    doc.add(new StringField("foo", "bar", Field.Store.NO));
    iw.addDocument(doc); // add an 'ok' document
    try {
      doc = new Document();
      // try to boost with norms omitted

View Full Code Here

    };


    Directory dir = newDirectory();
    IndexWriter w = new IndexWriter(dir, newIndexWriterConfig( TEST_VERSION_CURRENT, new MockAnalyzer(random())));
    Document doc = new Document();
    doc.add(new TextField("field", tokens));
    try {
      w.addDocument(doc);
      fail("did not hit expected exception");
    } catch (IllegalArgumentException iea) {
      // expected

View Full Code Here

    final String bigTerm = new String(chars);
    final BytesRef bigTermBytesRef = new BytesRef(bigTerm);


    // This contents produces a too-long term:
    String contents = "abc xyz x" + bigTerm + " another term";
    doc.add(new TextField("content", contents, Field.Store.NO));
    w.addDocument(doc);


    // Make sure we can add another normal document
    doc = new Document();
    doc.add(new TextField("content", "abc bbb ccc", Field.Store.NO));
    w.addDocument(doc);


    IndexReader reader = w.getReader();
    w.close();

View Full Code Here

        return new TokenStreamComponents(tokenizer, stream);
      }
    };
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, a);
    Document doc = new Document();
    doc.add(new TextField("body", "just a", Field.Store.NO));
    doc.add(new TextField("body", "test of gaps", Field.Store.NO));
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher is = newSearcher(ir);
    PhraseQuery pq = new PhraseQuery();

View Full Code Here

        return new TokenStreamComponents(tokenizer, stream);
      }
    };
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, a);
    Document doc = new Document();
    doc.add(new TextField("body", "just a foobar", Field.Store.NO));
    doc.add(new TextField("body", "test of gaps", Field.Store.NO));
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher is = newSearcher(ir);
    PhraseQuery pq = new PhraseQuery();

View Full Code Here

  public void testDeleteSameTermAcrossFields() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random()));
    IndexWriter w = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new TextField("a", "foo", Field.Store.NO));
    w.addDocument(doc);


    // Should not delete the document; with LUCENE-5239 the
    // "foo" from the 2nd delete term would incorrectly
    // match field a's "foo":

View Full Code Here

                (format.equals("SimpleText") || format.equals("Memory") || format.equals("Direct")));


    Directory dir = newDirectory();
    IndexWriter w = new IndexWriter(dir, conf);
    Document doc = new Document();
    doc.add(new TextField("f", "val", Field.Store.NO));
    w.addDocument(doc);
    SegmentReader r = getOnlySegmentReader(DirectoryReader.open(w, true));
    try {
      _TestUtil.docs(random(), r, "f", new BytesRef("val"), null, null, DocsEnum.FLAG_NONE);
      fail("should have failed to seek since terms index was not loaded.");

View Full Code Here

  }


  private void addDoc(IndexWriter writer, int id) throws IOException
  {
    Document doc = new Document();
    doc.add(new TextField("content", "aaa", Field.Store.NO));
    doc.add(new StringField("id", Integer.toString(id), Field.Store.YES));
    FieldType customType2 = new FieldType(TextField.TYPE_STORED);
    customType2.setStoreTermVectors(true);
    customType2.setStoreTermVectorPositions(true);
    customType2.setStoreTermVectorOffsets(true);

View Full Code Here

    directory = newDirectory();
    IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));


    Document doc;
    doc = new Document();
    doc.add(new TextField("content", "please divide this sentence into shingles", Field.Store.YES));
    writer.addDocument(doc);


    doc = new Document();
    doc.add(new TextField("content", "just another test sentence", Field.Store.YES));
    writer.addDocument(doc);


    doc = new Document();
    doc.add(new TextField("content", "a sentence which contains no test", Field.Store.YES));
    writer.addDocument(doc);


    writer.close();


    reader = DirectoryReader.open(directory);

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.