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.

        newIndexWriterConfig(TEST_VERSION_CURRENT,
            new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy()));


    // 0
    Document doc = new Document();
    doc.add(new TextField("description", "A random movie", Field.Store.NO));
    doc.add(new TextField("name", "Movie 1", Field.Store.NO));
    doc.add(new TextField(idField, "1", Field.Store.NO));
    w.addDocument(doc);


    // 1
    doc = new Document();
    doc.add(new TextField("subtitle", "The first subtitle of this movie", Field.Store.NO));
    doc.add(new TextField(idField, "2", Field.Store.NO));
    doc.add(new TextField(toField, "1", Field.Store.NO));
    w.addDocument(doc);


    // 2
    doc = new Document();
    doc.add(new TextField("subtitle", "random subtitle; random event movie", Field.Store.NO));
    doc.add(new TextField(idField, "3", Field.Store.NO));
    doc.add(new TextField(toField, "1", Field.Store.NO));
    w.addDocument(doc);


    // 3
    doc = new Document();
    doc.add(new TextField("description", "A second random movie", Field.Store.NO));
    doc.add(new TextField("name", "Movie 2", Field.Store.NO));
    doc.add(new TextField(idField, "4", Field.Store.NO));
    w.addDocument(doc);
    w.commit();


    // 4
    doc = new Document();
    doc.add(new TextField("subtitle", "a very random event happened during christmas night", Field.Store.NO));
    doc.add(new TextField(idField, "5", Field.Store.NO));
    doc.add(new TextField(toField, "4", Field.Store.NO));
    w.addDocument(doc);


    // 5
    doc = new Document();
    doc.add(new TextField("subtitle", "movie end movie test 123 test 123 random", Field.Store.NO));
    doc.add(new TextField(idField, "6", Field.Store.NO));
    doc.add(new TextField(toField, "4", Field.Store.NO));
    w.addDocument(doc);


    IndexSearcher indexSearcher = new IndexSearcher(w.getReader());
    w.close();

View Full Code Here

    Directory dir = new RAMDirectory();
    IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
    // add the first doc
    Document doc = new Document();
    String dummyTitle = "this is a dummy title ";
    doc.add(new TextField("title", dummyTitle, Field.Store.YES));
    String dummyContent = "there is some content written here";
    doc.add(new TextField("contents", dummyContent, Field.Store.YES));
    writer.addDocument(doc, analyzer);
    writer.commit();


    // try the search over the first doc
    DirectoryReader directoryReader = DirectoryReader.open(dir);
    IndexSearcher indexSearcher = newSearcher(directoryReader);
    TopDocs result = indexSearcher.search(new MatchAllDocsQuery(), 1);
    assertTrue(result.totalHits > 0);
    Document d = indexSearcher.doc(result.scoreDocs[0].doc);
    assertNotNull(d);
    assertNotNull(d.getField("title"));
    assertEquals(dummyTitle, d.getField("title").stringValue());
    assertNotNull(d.getField("contents"));
    assertEquals(dummyContent, d.getField("contents").stringValue());


    // add a second doc
    doc = new Document();
    String dogmasTitle = "dogmas";
    doc.add(new TextField("title", dogmasTitle, Field.Store.YES));
    String dogmasContents = "white men can't jump";
    doc.add(new TextField("contents", dogmasContents, Field.Store.YES));
    writer.addDocument(doc, analyzer);
    writer.commit();


    directoryReader.close();
    directoryReader = DirectoryReader.open(dir);

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 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

    lmp.setMergeFactor(2);
    iwc.setMergePolicy(lmp);


    RandomIndexWriter w = new RandomIndexWriter(random(), dir, iwc);
    Document doc = new Document();
    doc.add(new TextField("a", "foo", Field.Store.NO));
    w.addDocument(doc);
    w.commit();
    w.addDocument(doc);


    // Get a new reader, but this also sets off a merge:

View Full Code Here

   throws Exception
   {
      File file = new File(workDir, fileName);
      Document doc = new Document();
      InputStreamReader is = new InputStreamReader(new FileInputStream(file), "UTF-8");
      doc.add(new TextField("contents", is));
      writer.addDocument(doc);
      writer.commit();
      is.close();
      return writer.newestSegment();
   }

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.