Examples of TeeSinkTokenFilter

org.apache.lucene.analysis.TeeSinkTokenFilter
This TokenFilter provides the ability to set aside attribute states that have already been analyzed. This is useful in situations where multiple fields share many common analysis steps and then go their separate ways.
It is also useful for doing things like entity extraction or proper noun analysis as part of the analysis workflow and saving off those tokens for use in another field.
```
 TeeSinkTokenFilter source1 = new TeeSinkTokenFilter(new WhitespaceTokenizer(reader1)); TeeSinkTokenFilter.SinkTokenStream sink1 = source1.newSinkTokenStream(); TeeSinkTokenFilter.SinkTokenStream sink2 = source1.newSinkTokenStream(); TeeSinkTokenFilter source2 = new TeeSinkTokenFilter(new WhitespaceTokenizer(reader2)); source2.addSinkTokenStream(sink1); source2.addSinkTokenStream(sink2); TokenStream final1 = new LowerCaseFilter(source1); TokenStream final2 = source2; TokenStream final3 = new EntityDetect(sink1); TokenStream final4 = new URLDetect(sink2); d.add(new Field("f1", final1)); d.add(new Field("f2", final2)); d.add(new Field("f3", final3)); d.add(new Field("f4", final4)); 
```
In this example, sink1 and sink2 will both get tokens from both reader1 and reader2 after whitespace tokenizer and now we can further wrap any of these in extra analysis, and more "sources" can be inserted if desired. It is important, that tees are consumed before sinks (in the above example, the field names must be less the sink's field names). If you are not sure, which stream is consumed first, you can simply add another sink and then pass all tokens to the sinks at once using {@link #consumeAllTokens}. This TokenFilter is exhausted after this. In the above example, change the example above to:
```
 ... TokenStream final1 = new LowerCaseFilter(source1.newSinkTokenStream()); TokenStream final2 = source2.newSinkTokenStream(); sink1.consumeAllTokens(); sink2.consumeAllTokens(); ... 
```
In this case, the fields can be added in any order, because the sources are not used anymore and all sinks are ready.
Note, the EntityDetect and URLDetect TokenStreams are for the example and do not currently exist in Lucene.

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

  public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception {
    MockRAMDirectory dir = new MockRAMDirectory();
    Analyzer analyzer = new WhitespaceAnalyzer();
    IndexWriter w = new IndexWriter(dir, analyzer, IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(analyzer.tokenStream("field", new StringReader("abcd   ")));
    TokenStream sink = tee.newSinkTokenStream();
    Field f1 = new Field("field", tee, Field.TermVector.WITH_POSITIONS_OFFSETS);
    Field f2 = new Field("field", sink, Field.TermVector.WITH_POSITIONS_OFFSETS);
    doc.add(f1);
    doc.add(f2);
    w.addDocument(doc);

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

  public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception {
    MockRAMDirectory dir = new MockRAMDirectory();
    Analyzer analyzer = new WhitespaceAnalyzer();
    IndexWriter w = new IndexWriter(dir, analyzer, IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(analyzer.tokenStream("field", new StringReader("abcd   ")));
    TokenStream sink = tee.newSinkTokenStream();
    Field f1 = new Field("field", tee, Field.TermVector.WITH_POSITIONS_OFFSETS);
    Field f2 = new Field("field", sink, Field.TermVector.WITH_POSITIONS_OFFSETS);
    doc.add(f1);
    doc.add(f2);
    w.addDocument(doc);

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter


  public void test() throws IOException {
    TokenTypeSinkFilter sinkFilter = new TokenTypeSinkFilter("D");
    String test = "The quick red fox jumped over the lazy brown dogs";


    TeeSinkTokenFilter ttf = new TeeSinkTokenFilter(new WordTokenFilter(new WhitespaceTokenizer(new StringReader(test))));
    SinkTokenStream sink = ttf.newSinkTokenStream(sinkFilter);
    
    boolean seenDogs = false;


    TermAttribute termAtt = ttf.addAttribute(TermAttribute.class);
    TypeAttribute typeAtt = ttf.addAttribute(TypeAttribute.class);
    ttf.reset();
    while (ttf.incrementToken()) {
      if (termAtt.term().equals("dogs")) {
        seenDogs = true;
        assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().equals("D") == true);
      } else {
        assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().equals("word"));

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

  public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception {
    MockDirectoryWrapper dir = newDirectory();
    Analyzer analyzer = new WhitespaceAnalyzer(TEST_VERSION_CURRENT);
    IndexWriter w = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
    Document doc = new Document();
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(analyzer.tokenStream("field", new StringReader("abcd   ")));
    TokenStream sink = tee.newSinkTokenStream();
    Field f1 = new Field("field", tee, Field.TermVector.WITH_POSITIONS_OFFSETS);
    Field f2 = new Field("field", sink, Field.TermVector.WITH_POSITIONS_OFFSETS);
    doc.add(f1);
    doc.add(f2);
    w.addDocument(doc);

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

  public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception {
    MockRAMDirectory dir = new MockRAMDirectory();
    Analyzer analyzer = new WhitespaceAnalyzer();
    IndexWriter w = new IndexWriter(dir, analyzer, IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(analyzer.tokenStream("field", new StringReader("abcd   ")));
    TokenStream sink = tee.newSinkTokenStream();
    Field f1 = new Field("field", tee, Field.TermVector.WITH_POSITIONS_OFFSETS);
    Field f2 = new Field("field", sink, Field.TermVector.WITH_POSITIONS_OFFSETS);
    doc.add(f1);
    doc.add(f2);
    w.addDocument(doc);

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

  public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception {
    MockRAMDirectory dir = new MockRAMDirectory();
    Analyzer analyzer = new WhitespaceAnalyzer();
    IndexWriter w = new IndexWriter(dir, analyzer, IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(analyzer.tokenStream("field", new StringReader("abcd   ")));
    TokenStream sink = tee.newSinkTokenStream();
    Field f1 = new Field("field", tee, Field.TermVector.WITH_POSITIONS_OFFSETS);
    Field f2 = new Field("field", sink, Field.TermVector.WITH_POSITIONS_OFFSETS);
    doc.add(f1);
    doc.add(f2);
    w.addDocument(doc);

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

public class TokenRangeSinkTokenizerTest extends BaseTokenStreamTestCase {


  public void test() throws IOException {
    TokenRangeSinkFilter sinkFilter = new TokenRangeSinkFilter(2, 4);
    String test = "The quick red fox jumped over the lazy brown dogs";
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
    SinkTokenStream rangeToks = tee.newSinkTokenStream(sinkFilter);
    
    int count = 0;
    tee.reset();
    while(tee.incrementToken()) {
      count++;
    }
    
    int sinkCount = 0;
    rangeToks.reset();

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

public class DateRecognizerSinkTokenizerTest extends BaseTokenStreamTestCase {


  public void test() throws IOException {
    DateRecognizerSinkFilter sinkFilter = new DateRecognizerSinkFilter(new SimpleDateFormat("MM/dd/yyyy", Locale.US));
    String test = "The quick red fox jumped over the lazy brown dogs on 7/11/2006  The dogs finally reacted on 7/12/2006";
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
    SinkTokenStream sink = tee.newSinkTokenStream(sinkFilter);
    int count = 0;
    
    tee.reset();
    while (tee.incrementToken()) {
      count++;
    }
    assertTrue(count + " does not equal: " + 18, count == 18);
    
    int sinkCount = 0;

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter


  public void test() throws IOException {
    TokenTypeSinkFilter sinkFilter = new TokenTypeSinkFilter("D");
    String test = "The quick red fox jumped over the lazy brown dogs";


    TeeSinkTokenFilter ttf = new TeeSinkTokenFilter(new WordTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false)));
    SinkTokenStream sink = ttf.newSinkTokenStream(sinkFilter);
    
    boolean seenDogs = false;


    CharTermAttribute termAtt = ttf.addAttribute(CharTermAttribute.class);
    TypeAttribute typeAtt = ttf.addAttribute(TypeAttribute.class);
    ttf.reset();
    while (ttf.incrementToken()) {
      if (termAtt.toString().equals("dogs")) {
        seenDogs = true;
        assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().equals("D") == true);
      } else {
        assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().equals("word"));

View Full Code Here

Examples of org.apache.lucene.analysis.TeeSinkTokenFilter

  }


  public void test() throws IOException {
    TokenRangeSinkFilter sinkFilter = new TokenRangeSinkFilter(2, 4);
    String test = "The quick red fox jumped over the lazy brown dogs";
    TeeSinkTokenFilter tee = new TeeSinkTokenFilter(new WhitespaceTokenizer(new StringReader(test)));
    SinkTokenStream rangeToks = tee.newSinkTokenStream(sinkFilter);
    
    int count = 0;
    tee.reset();
    while(tee.incrementToken()) {
      count++;
    }
    
    int sinkCount = 0;
    rangeToks.reset();

View Full Code Here

0 1 2

TOP

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.