Java TextField.TYPE_STORED屬性代碼示例

private IndexReader indexOneDoc(Directory dir, String field, String value, Analyzer analyzer) throws IOException {
    IndexWriterConfig iwc = newIndexWriterConfig(analyzer);
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);

    FieldType ft = new FieldType(TextField.TYPE_STORED);
    ft.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
    Field textField = new Field(field, "", ft);
    Document doc = new Document();
    doc.add(textField);

    textField.setStringValue(value);
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    return ir;
}
 

public void testVectorHighlighter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    FieldType vectorsType = new FieldType(TextField.TYPE_STORED);
    vectorsType.setStoreTermVectors(true);
    vectorsType.setStoreTermVectorPositions(true);
    vectorsType.setStoreTermVectorOffsets(true);
    document.add(new Field("content", "the big bad dog", vectorsType));
    indexWriter.addDocument(document);

    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))),
            reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
    assertThat(fragment, equalTo("the big <b>bad</b> dog"));
}
 

private Document getDocument(File file) throws IOException {
	Document document = new Document();

	// index file contents
	Field contentField = new Field(LuceneConstants.CONTENTS, new FileReader(file), TextField.TYPE_NOT_STORED);
	// index file name
	Field fileNameField = new Field(LuceneConstants.FILE_NAME, file.getName(), TextField.TYPE_STORED);
	// index file path
	Field filePathField = new Field(LuceneConstants.FILE_PATH, file.getCanonicalPath(), TextField.TYPE_STORED);

	document.add(contentField);
	document.add(fileNameField);
	document.add(filePathField);

	return document;
}
 

public void testEmptyDocAfterFlushingRealDoc() throws IOException {
  Directory dir = newDirectory();
  IndexWriter writer  = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())));
  Document doc = new Document();
  FieldType customType = new FieldType(TextField.TYPE_STORED);
  customType.setStoreTermVectors(true);
  customType.setStoreTermVectorPositions(true);
  customType.setStoreTermVectorOffsets(true);
  doc.add(newField("field", "aaa", customType));
  writer.addDocument(doc);
  writer.commit();
  if (VERBOSE) {
    System.out.println("\nTEST: now add empty doc");
  }
  writer.addDocument(new Document());
  writer.close();
  IndexReader reader = DirectoryReader.open(dir);
  assertEquals(2, reader.numDocs());
  reader.close();
  dir.close();
}
 

private void writeEmptyTermVector(TermVectorsResponse outResponse) throws IOException {

        Directory dir = newDirectory();
        IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());
        conf.setOpenMode(OpenMode.CREATE);
        IndexWriter writer = new IndexWriter(dir, conf);
        FieldType type = new FieldType(TextField.TYPE_STORED);
        type.setStoreTermVectorOffsets(true);
        type.setStoreTermVectorPayloads(false);
        type.setStoreTermVectorPositions(true);
        type.setStoreTermVectors(true);
        type.freeze();
        Document d = new Document();
        d.add(new Field("id", "abc", StringField.TYPE_STORED));

        writer.updateDocument(new Term("id", "abc"), d);
        writer.commit();
        writer.close();
        DirectoryReader dr = DirectoryReader.open(dir);
        IndexSearcher s = new IndexSearcher(dr);
        TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
        ScoreDoc[] scoreDocs = search.scoreDocs;
        int doc = scoreDocs[0].doc;
        Fields fields = dr.getTermVectors(doc);
        EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
        outResponse.setFields(fields, null, flags, fields);
        outResponse.setExists(true);
        dr.close();
        dir.close();

    }
 

private void writeStandardTermVector(TermVectorsResponse outResponse) throws IOException {

        Directory dir = newDirectory();
        IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());

        conf.setOpenMode(OpenMode.CREATE);
        IndexWriter writer = new IndexWriter(dir, conf);
        FieldType type = new FieldType(TextField.TYPE_STORED);
        type.setStoreTermVectorOffsets(true);
        type.setStoreTermVectorPayloads(false);
        type.setStoreTermVectorPositions(true);
        type.setStoreTermVectors(true);
        type.freeze();
        Document d = new Document();
        d.add(new Field("id", "abc", StringField.TYPE_STORED));
        d.add(new Field("title", "the1 quick brown fox jumps over  the1 lazy dog", type));
        d.add(new Field("desc", "the1 quick brown fox jumps over  the1 lazy dog", type));

        writer.updateDocument(new Term("id", "abc"), d);
        writer.commit();
        writer.close();
        DirectoryReader dr = DirectoryReader.open(dir);
        IndexSearcher s = new IndexSearcher(dr);
        TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
        ScoreDoc[] scoreDocs = search.scoreDocs;
        int doc = scoreDocs[0].doc;
        Fields termVectors = dr.getTermVectors(doc);
        EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
        outResponse.setFields(termVectors, null, flags, termVectors);
        dr.close();
        dir.close();

    }
 

private Document getDocument(File file) throws IOException {
	Document document = new Document();
	Field contentsField = new TextField(LuceneConstants.CONTENTS, new String(Files.readAllBytes(file.toPath())), Store.YES);
	Field fileNameField = new Field(LuceneConstants.FILE_NAME, file.getName(), TextField.TYPE_STORED);
	Field filePathField = new Field(LuceneConstants.FILE_PATH, file.getCanonicalPath(), TextField.TYPE_STORED);
	document.add(contentsField);
	document.add(fileNameField);
	document.add(filePathField);
	return document;
}
 

private void writeStandardTermVector(TermVectorsResponse outResponse) throws IOException {

        Directory dir = LuceneTestCase.newDirectory();
        IndexWriterConfig conf = new IndexWriterConfig(new StandardAnalyzer());

        conf.setOpenMode(OpenMode.CREATE);
        IndexWriter writer = new IndexWriter(dir, conf);
        FieldType type = new FieldType(TextField.TYPE_STORED);
        type.setStoreTermVectorOffsets(true);
        type.setStoreTermVectorPayloads(false);
        type.setStoreTermVectorPositions(true);
        type.setStoreTermVectors(true);
        type.freeze();
        Document d = new Document();
        d.add(new Field("id", "abc", StringField.TYPE_STORED));
        d.add(new Field("plaintext", "the1 quick brown fox jumps over  the1 lazy dog comment", type));
        d.add(new Field("desc", "the1 quick brown fox jumps over  the1 lazy dog comment", type));

        writer.updateDocument(new Term("id", "abc"), d);
        writer.commit();
        writer.close();
        DirectoryReader dr = DirectoryReader.open(dir);
        IndexSearcher s = new IndexSearcher(dr);
        TopDocs search = s.search(new TermQuery(new Term("id", "abc")), 1);
        ScoreDoc[] scoreDocs = search.scoreDocs;
        int doc = scoreDocs[0].doc;
        Fields termVectors = dr.getTermVectors(doc);
        EnumSet<Flag> flags = EnumSet.of(Flag.Positions, Flag.Offsets);
        outResponse.setFields(termVectors, null, flags, termVectors);
        dr.close();
        dir.close();

    }
 

public void testBuddhism() throws Exception {
  String text = "This eight-volume set brings together seminal papers in Buddhist studies from a vast " +
                "range of academic disciplines published over the last forty years. With a new introduction " + 
                "by the editor, this collection is a unique and unrivalled research resource for both " + 
                "student and scholar. Coverage includes: - Buddhist origins; early history of Buddhism in " + 
                "South and Southeast Asia - early Buddhist Schools and Doctrinal History; Theravada Doctrine " + 
                "- the Origins and nature of Mahayana Buddhism; some Mahayana religious topics - Abhidharma " + 
                "and Madhyamaka - Yogacara, the Epistemological tradition, and Tathagatagarbha - Tantric " + 
                "Buddhism (Including China and Japan); Buddhism in Nepal and Tibet - Buddhism in South and " + 
                "Southeast Asia, and - Buddhism in China, East Asia, and Japan.";
  Directory dir = newDirectory();
  Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true);
  RandomIndexWriter iw = new RandomIndexWriter(random(), dir, analyzer);
  
  FieldType positionsType = new FieldType(TextField.TYPE_STORED);
  positionsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
  Field body = new Field("body", text, positionsType);
  Document document = new Document();
  document.add(body);
  iw.addDocument(document);
  IndexReader ir = iw.getReader();
  iw.close();
  IndexSearcher searcher = newSearcher(ir);
  PhraseQuery query = new PhraseQuery();
  query.add(new Term("body", "buddhist"));
  query.add(new Term("body", "origins"));
  TopDocs topDocs = searcher.search(query, 10);
  assertEquals(1, topDocs.totalHits);
  PostingsHighlighter highlighter = new PostingsHighlighter();
  String snippets[] = highlighter.highlight("body", query, searcher, topDocs, 2);
  assertEquals(1, snippets.length);
  assertTrue(snippets[0].contains("<b>Buddhist</b> <b>origins</b>"));
  ir.close();
  dir.close();
}
 

public void testNoSegmentFile() throws IOException {
  BaseDirectoryWrapper dir = newDirectory();
  dir.setLockFactory(NoLockFactory.getNoLockFactory());
  IndexWriter w = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random()))
                                         .setMaxBufferedDocs(2));

  Document doc = new Document();
  FieldType customType = new FieldType(TextField.TYPE_STORED);
  customType.setStoreTermVectors(true);
  customType.setStoreTermVectorPositions(true);
  customType.setStoreTermVectorOffsets(true);
  doc.add(newField("c", "val", customType));
  w.addDocument(doc);
  w.addDocument(doc);
  IndexWriter w2 = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random()))
                                          .setMaxBufferedDocs(2)
                                          .setOpenMode(OpenMode.CREATE));

  w2.close();
  // If we don't do that, the test fails on Windows
  w.rollback();

  // This test leaves only segments.gen, which causes
  // DirectoryReader.indexExists to return true:
  dir.setCheckIndexOnClose(false);
  dir.close();
}
 

@Override
@Before
public void setUp() throws Exception {
  super.setUp();
  dir = newDirectory();
  RandomIndexWriter indexWriter = new RandomIndexWriter(random(), dir);

  FieldType ft = new FieldType(TextField.TYPE_STORED);
  ft.setStoreTermVectors(true);
  ft.setStoreTermVectorOffsets(true);
  ft.setStoreTermVectorPositions(true);

  Analyzer analyzer = new MockAnalyzer(random());

  Document doc;
  for (int i = 0; i < 10; i++) {
    doc = new Document();
    doc.add(new Field("id", Integer.toString(i), ft));
    doc.add(new Field("text", random().nextInt(10) + " " + random().nextInt(10) + " " + random().nextInt(10), ft));
    indexWriter.addDocument(doc, analyzer);
  }

  indexWriter.commit();

  index = indexWriter.getReader();

  indexWriter.close();
}
 

/** Make sure highlighter returns first N sentences if
 *  there were no hits. */
public void testEmptyHighlights() throws Exception {
  Directory dir = newDirectory();
  IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
  iwc.setMergePolicy(newLogMergePolicy());
  RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
  
  FieldType offsetsType = new FieldType(TextField.TYPE_STORED);
  offsetsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
  Document doc = new Document();

  Field body = new Field("body", "test this is.  another sentence this test has.  far away is that planet.", offsetsType);
  doc.add(body);
  iw.addDocument(doc);
  
  IndexReader ir = iw.getReader();
  iw.close();
  
  IndexSearcher searcher = newSearcher(ir);
  PostingsHighlighter highlighter = new PostingsHighlighter();
  Query query = new TermQuery(new Term("body", "highlighting"));
  int[] docIDs = new int[] {0};
  String snippets[] = highlighter.highlightFields(new String[] {"body"}, query, searcher, docIDs, new int[] { 2 }).get("body");
  assertEquals(1, snippets.length);
  assertEquals("test this is.  another sentence this test has.  ", snippets[0]);

  ir.close();
  dir.close();
}
 

private void addNoProxDoc(IndexWriter writer) throws IOException {
  Document doc = new Document();
  FieldType customType = new FieldType(TextField.TYPE_STORED);
  customType.setIndexOptions(IndexOptions.DOCS_ONLY);
  Field f = new Field("content3", "aaa", customType);
  doc.add(f);
  FieldType customType2 = new FieldType();
  customType2.setStored(true);
  customType2.setIndexOptions(IndexOptions.DOCS_ONLY);
  f = new Field("content4", "aaa", customType2);
  doc.add(f);
  writer.addDocument(doc);
}
 

/** sets b=0 to disable passage length normalization */
public void testCustomB() throws Exception {
  Directory dir = newDirectory();
  IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random(), MockTokenizer.SIMPLE, true));
  iwc.setMergePolicy(newLogMergePolicy());
  RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
  
  FieldType offsetsType = new FieldType(TextField.TYPE_STORED);
  offsetsType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
  Field body = new Field("body", "", offsetsType);
  Document doc = new Document();
  doc.add(body);
  
  body.setStringValue("This is a test.  This test is a better test but the sentence is excruiatingly long, " + 
                      "you have no idea how painful it was for me to type this long sentence into my IDE.");
  iw.addDocument(doc);
  
  IndexReader ir = iw.getReader();
  iw.close();
  
  IndexSearcher searcher = newSearcher(ir);
  PostingsHighlighter highlighter = new PostingsHighlighter(10000) {
      @Override
      protected PassageScorer getScorer(String field) {
        return new PassageScorer(1.2f, 0, 87);
      }
    };
  Query query = new TermQuery(new Term("body", "test"));
  TopDocs topDocs = searcher.search(query, null, 10, Sort.INDEXORDER);
  assertEquals(1, topDocs.totalHits);
  String snippets[] = highlighter.highlight("body", query, searcher, topDocs, 1);
  assertEquals(1, snippets.length);
  assertTrue(snippets[0].startsWith("This <b>test</b> is a better <b>test</b>"));
  
  ir.close();
  dir.close();
}
 

public void testTermVectors() throws Exception {
  Directory d = newDirectory();
  // set up writer
  IndexWriter writer = new IndexWriter(
      d,
      newIndexWriterConfig(new MockAnalyzer(random()))
          .setMergePolicy(newLogMergePolicy())
  );
  // want to get some more segments here
  // new termvector fields
  int mergeFactor = ((LogMergePolicy) writer.getConfig().getMergePolicy()).getMergeFactor();
  FieldType customType5 = new FieldType(TextField.TYPE_STORED);
  customType5.setStoreTermVectors(true);
  FieldType customType6 = new FieldType(TextField.TYPE_STORED);
  customType6.setStoreTermVectors(true);
  customType6.setStoreTermVectorOffsets(true);
  FieldType customType7 = new FieldType(TextField.TYPE_STORED);
  customType7.setStoreTermVectors(true);
  customType7.setStoreTermVectorPositions(true);
  FieldType customType8 = new FieldType(TextField.TYPE_STORED);
  customType8.setStoreTermVectors(true);
  customType8.setStoreTermVectorOffsets(true);
  customType8.setStoreTermVectorPositions(true);
  for (int i = 0; i < 5 * mergeFactor; i++) {
    Document doc = new Document();
      doc.add(new TextField("tvnot", "one two two three three three", Field.Store.YES));
      doc.add(new Field("termvector", "one two two three three three", customType5));
      doc.add(new Field("tvoffset", "one two two three three three", customType6));
      doc.add(new Field("tvposition", "one two two three three three", customType7));
      doc.add(new Field("tvpositionoffset", "one two two three three three", customType8));
      
      writer.addDocument(doc);
  }
  writer.close();
  d.close();
}