Java Document.add方法代码示例

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testSimpleNumericOps() 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));
    document.add(new LegacyIntField("test", 2, LegacyIntField.TYPE_STORED));
    indexWriter.addDocument(document);

    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    Document doc = searcher.doc(topDocs.scoreDocs[0].doc);
    IndexableField f = doc.getField("test");
    assertThat(f.stringValue(), equalTo("2"));

    BytesRefBuilder bytes = new BytesRefBuilder();
    LegacyNumericUtils.intToPrefixCoded(2, 0, bytes);
    topDocs = searcher.search(new TermQuery(new Term("test", bytes.get())), 1);
    doc = searcher.doc(topDocs.scoreDocs[0].doc);
    f = doc.getField("test");
    assertThat(f.stringValue(), equalTo("2"));

    indexWriter.close();
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
private Document eventToDocument(Event newEvent) {
	Document d = new Document ();
	
	String eventId = newEvent.getId ();
	String eventText = newEvent.getText();
	
	String eventStartDate = newEvent.getStartDate() != null ? new SimpleDateFormat ("yyyy-MM-dd").format(newEvent.getStartDate().getDate()) : null;
	
	String eventStartTime = newEvent.getTimeString();
	
	if (eventStartDate != null) eventStartTime = eventStartDate + " @ " + eventStartTime;

	d.add (new StringField ("id", eventId, Field.Store.YES));
	d.add (new TextField ("text", eventText, Field.Store.YES));
	d.add (new TextField ("text_cs", eventText, Field.Store.YES));
	d.add (new StoredField ("original_start_date", eventStartTime != null ? eventStartTime : ""));
	return d;
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void addIndex(UUser user) throws Exception {
  IndexWriter writer = getWriter();
  Document doc = new Document();
  /*
 * yes是会将数据存进索引，如果查询结果中需要将记录显示出来就要存进去，如果查询结果
 * 只是显示标题之类的就可以不用存，而且内容过长不建议存进去
 * 使用TextField类是可以用于查询的。
 */
  try {
    doc.add(new StringField("userid", String.valueOf(user.getId()), Field.Store.YES));
    doc.add(new TextField("username", user.getUsername(), Field.Store.YES));

    writer.addDocument(doc);
  } catch (Exception e) {
    e.printStackTrace();
    throw e;
  } finally {
    writer.close();
  }
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testMinDocCount() throws Exception {
    try (Directory dir = newDirectory();
            RandomIndexWriter w = new RandomIndexWriter(random(), dir)) {
        for (long value : new long[] {7, 3, -10, -6, 5, 50}) {
            Document doc = new Document();
            doc.add(new SortedNumericDocValuesField("field", value));
            w.addDocument(doc);
        }

        HistogramAggregationBuilder aggBuilder = new HistogramAggregationBuilder("my_agg")
                .field("field")
                .interval(10)
                .minDocCount(2);
        MappedFieldType fieldType = new NumberFieldMapper.NumberFieldType(NumberFieldMapper.NumberType.LONG);
        fieldType.setName("field");
        try (IndexReader reader = w.getReader()) {
            IndexSearcher searcher = new IndexSearcher(reader);
            Histogram histogram = searchAndReduce(searcher, new MatchAllDocsQuery(), aggBuilder, fieldType);
            assertEquals(2, histogram.getBuckets().size());
            assertEquals(-10d, histogram.getBuckets().get(0).getKey());
            assertEquals(2, histogram.getBuckets().get(0).getDocCount());
            assertEquals(0d, histogram.getBuckets().get(1).getKey());
            assertEquals(3, histogram.getBuckets().get(1).getDocCount());
        }
    }
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testNoTokens() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.KEYWORD_ANALYZER));

    FieldType allFt = getAllFieldType();
    Document doc = new Document();
    doc.add(new Field("_id", "1", StoredField.TYPE));
    doc.add(new AllField("_all", "", 2.0f, allFt));
    indexWriter.addDocument(doc);

    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);

    TopDocs docs = searcher.search(new MatchAllDocsQuery(), 10);
    assertThat(docs.totalHits, equalTo(1));
    assertThat(docs.scoreDocs[0].doc, equalTo(0));
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
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"));
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testNRTSearchOnClosedWriter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    DirectoryReader reader = DirectoryReader.open(indexWriter);

    for (int i = 0; i < 100; i++) {
        Document document = new Document();
        TextField field = new TextField("_id", Integer.toString(i), Field.Store.YES);
        field.setBoost(i);
        document.add(field);
        indexWriter.addDocument(document);
    }
    reader = refreshReader(reader);

    indexWriter.close();

    TermsEnum termDocs = SlowCompositeReaderWrapper.wrap(reader).terms("_id").iterator();
    termDocs.next();
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testEmpty() throws Exception {
    Document d = new Document();
    d.add(new StringField("field", "value", Field.Store.NO));
    writer.addDocument(d);
    refreshReader();

    IndexFieldData fieldData = getForField("non_existing_field");
    int max = randomInt(7);
    for (LeafReaderContext readerContext : readerContexts) {
        AtomicFieldData previous = null;
        for (int i = 0; i < max; i++) {
            AtomicFieldData current = fieldData.load(readerContext);
            assertThat(current.ramBytesUsed(), equalTo(0L));
            if (previous != null) {
                assertThat(current, not(sameInstance(previous)));
            }
            previous = current;
        }
    }
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
private void addAppsToIndexerWriter(List<App> list, IndexWriter indexerWriter) {
    Field name = new Field(fieldName, "", Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS);
    NumericField catalog = new NumericField("catalog", Field.Store.NO, true);
    NumericField downloadRank = new NumericField("downloadRank", Field.Store.NO, true);
    for (App a : list) {
        try {
            Document doc = new Document();
            name.setValue(a.getName().toLowerCase());
            doc.add(name);
            downloadRank.setIntValue(a.getDownloadRank());
            doc.add(downloadRank);
            catalog.setIntValue(a.getCatalog());
            doc.add(catalog);
            indexerWriter.addDocument(doc);
        } catch (Exception e) {
            logger.error("Exception", e);
        }
    }
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
@Override
public List<Document> getDoc(List<IfcProductRecordText> items) {
	
	List<Document> docs = new ArrayList<Document>();  
       FieldType storedType = new FieldType();  
       storedType.setIndexed(true);  
       storedType.setStored(true);  
       storedType.setTokenized(true); 
       
       FieldType unTokeType = new FieldType();
       unTokeType.setIndexed(true);  
       unTokeType.setStored(true);   
       unTokeType.setTokenized(false); 
       
       for (IfcProductRecordText record : items) {
       	Document doc = new Document();
       	
       	Field oid = genStringFieldCheckNull(Key_Oid, record.getOid(), unTokeType);
       	Field type = genStringFieldCheckNull(Key_Type, record.getType(), storedType);
       	Field name = genStringFieldCheckNull(Key_Name, record.getName(), storedType);
       	Field detail = genStringFieldCheckNull(Key_Detail, record.getDetail(), storedType);
       	
       	doc.add(oid);
       	doc.add(type);
       	doc.add(name);
       	doc.add(detail);
       	
       	docs.add(doc);
       }
	return docs;
	
	
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
@Override public void updateDocument(ArtifactInfo ai, Document doc) {
    if (classDeps == null || classDeps.isEmpty()) {
        return;
    }
    if (ai.getClassNames() == null) {
        // Might be *.hpi, *.war, etc. - so JarFileContentsIndexCreator ignores it (and our results would anyway be wrong due to WEB-INF/classes/ prefix)
        LOG.log(Level.FINE, "no class names in index for {0}; therefore cannot store class usages", ai);
        return;
    }
    StringBuilder b = new StringBuilder();
    String[] classNamesSplit = ai.getClassNames().split("\n");
    for (String referrerTopLevel : classNamesSplit) {
        Set<String> referees = classDeps.remove(referrerTopLevel.substring(1));
        if (referees != null) {
            for (String referee : referees) {
                b.append(crc32base64(referee));
                b.append(' ');
            }
        }
        b.append(' ');
    }
    if (!classDeps.isEmpty()) {
        // E.g. findbugs-1.2.0.jar has TigerSubstitutes.class, TigerSubstitutesTest$Foo.class, etc., but no TigerSubstitutesTest.class (?)
        // Or guice-3.0-rc2.jar has e.g. $Transformer.class with no source equivalent.
        LOG.log(Level.FINE, "found dependencies for {0} from classes {1} not among {2}", new Object[] {ai, classDeps.keySet(), Arrays.asList(classNamesSplit)});
    }
    LOG.log(Level.FINER, "Class dependencies index field: {0}", b);
    // XXX is it possible to _store_ something more compact (binary) using a custom tokenizer?
    // seems like DefaultIndexingContext hardcodes NexusAnalyzer
    doc.add(FLD_NB_DEPENDENCY_CLASS.toField(b.toString()));
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testDoubles() throws Exception {
    try (Directory dir = newDirectory();
            RandomIndexWriter w = new RandomIndexWriter(random(), dir)) {
        for (double value : new double[] {9.3, 3.2, -10, -6.5, 5.3, 50.1}) {
            Document doc = new Document();
            doc.add(new SortedNumericDocValuesField("field", NumericUtils.doubleToSortableLong(value)));
            w.addDocument(doc);
        }

        HistogramAggregationBuilder aggBuilder = new HistogramAggregationBuilder("my_agg")
                .field("field")
                .interval(5);
        MappedFieldType fieldType = new NumberFieldMapper.NumberFieldType(NumberFieldMapper.NumberType.DOUBLE);
        fieldType.setName("field");
        try (IndexReader reader = w.getReader()) {
            IndexSearcher searcher = new IndexSearcher(reader);
            Histogram histogram = search(searcher, new MatchAllDocsQuery(), aggBuilder, fieldType);
            assertEquals(4, histogram.getBuckets().size());
            assertEquals(-10d, histogram.getBuckets().get(0).getKey());
            assertEquals(2, histogram.getBuckets().get(0).getDocCount());
            assertEquals(0d, histogram.getBuckets().get(1).getKey());
            assertEquals(1, histogram.getBuckets().get(1).getDocCount());
            assertEquals(5d, histogram.getBuckets().get(2).getKey());
            assertEquals(2, histogram.getBuckets().get(2).getDocCount());
            assertEquals(50d, histogram.getBuckets().get(3).getKey());
            assertEquals(1, histogram.getBuckets().get(3).getDocCount());
        }
    }
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testRangeQuery() throws IOException {
    // make sure the accuracy loss of scaled floats only occurs at index time
    // this test checks that searching scaled floats yields the same results as
    // searching doubles that are rounded to the closest half float
    ScaledFloatFieldMapper.ScaledFloatFieldType ft = new ScaledFloatFieldMapper.ScaledFloatFieldType();
    ft.setName("scaled_float");
    ft.setScalingFactor(0.1 + randomDouble() * 100);
    Directory dir = newDirectory();
    IndexWriter w = new IndexWriter(dir, new IndexWriterConfig(null));
    final int numDocs = 1000;
    for (int i = 0; i < numDocs; ++i) {
        Document doc = new Document();
        double value = (randomDouble() * 2 - 1) * 10000;
        long scaledValue = Math.round(value * ft.getScalingFactor());
        double rounded = scaledValue / ft.getScalingFactor();
        doc.add(new LongPoint("scaled_float", scaledValue));
        doc.add(new DoublePoint("double", rounded));
        w.addDocument(doc);
    }
    final DirectoryReader reader = DirectoryReader.open(w);
    w.close();
    IndexSearcher searcher = newSearcher(reader);
    final int numQueries = 1000;
    for (int i = 0; i < numQueries; ++i) {
        Double l = randomBoolean() ? null : (randomDouble() * 2 - 1) * 10000;
        Double u = randomBoolean() ? null : (randomDouble() * 2 - 1) * 10000;
        boolean includeLower = randomBoolean();
        boolean includeUpper = randomBoolean();
        Query doubleQ = NumberFieldMapper.NumberType.DOUBLE.rangeQuery("double", l, u, includeLower, includeUpper, false);
        Query scaledFloatQ = ft.rangeQuery(l, u, includeLower, includeUpper, null);
        assertEquals(searcher.count(doubleQ), searcher.count(scaledFloatQ));
    }
    IOUtils.close(reader, dir);
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
public void testMissing() throws Exception {
    try (Directory dir = newDirectory();
            RandomIndexWriter w = new RandomIndexWriter(random(), dir)) {
        for (long value : new long[] {7, 3, -10, -6, 5, 50}) {
            Document doc = new Document();
            doc.add(new SortedNumericDocValuesField("field", value));
            w.addDocument(doc);
            w.addDocument(new Document());
        }

        HistogramAggregationBuilder aggBuilder = new HistogramAggregationBuilder("my_agg")
                .field("field")
                .interval(5)
                .missing(2d);
        MappedFieldType fieldType = new NumberFieldMapper.NumberFieldType(NumberFieldMapper.NumberType.LONG);
        fieldType.setName("field");
        try (IndexReader reader = w.getReader()) {
            IndexSearcher searcher = new IndexSearcher(reader);
            Histogram histogram = search(searcher, new MatchAllDocsQuery(), aggBuilder, fieldType);
            assertEquals(4, histogram.getBuckets().size());
            assertEquals(-10d, histogram.getBuckets().get(0).getKey());
            assertEquals(2, histogram.getBuckets().get(0).getDocCount());
            assertEquals(0d, histogram.getBuckets().get(1).getKey());
            assertEquals(7, histogram.getBuckets().get(1).getDocCount());
            assertEquals(5d, histogram.getBuckets().get(2).getKey());
            assertEquals(2, histogram.getBuckets().get(2).getDocCount());
            assertEquals(50d, histogram.getBuckets().get(3).getKey());
            assertEquals(1, histogram.getBuckets().get(3).getDocCount());
        }
    }
}
 

import org.apache.lucene.document.Document; //导入方法依赖的package包/类
/**
 * Uses the sampler aggregation to find the minimum value of a field out of the top 3 scoring documents in a search.
 */
public void testSampler() throws IOException {
    TextFieldType textFieldType = new TextFieldType();
    textFieldType.setIndexAnalyzer(new NamedAnalyzer("foo", AnalyzerScope.GLOBAL, new StandardAnalyzer()));
    MappedFieldType numericFieldType = new NumberFieldMapper.NumberFieldType(NumberFieldMapper.NumberType.LONG);
    numericFieldType.setName("int");

    IndexWriterConfig indexWriterConfig = newIndexWriterConfig();
    indexWriterConfig.setMaxBufferedDocs(100);
    indexWriterConfig.setRAMBufferSizeMB(100); // flush on open to have a single segment with predictable docIds
    try (Directory dir = newDirectory();
            IndexWriter w = new IndexWriter(dir, indexWriterConfig)) {
        for (long value : new long[] {7, 3, -10, -6, 5, 50}) {
            Document doc = new Document();
            StringBuilder text = new StringBuilder();
            for (int i = 0; i < value; i++) {
                text.append("good ");
            }
            doc.add(new Field("text", text.toString(), textFieldType));
            doc.add(new SortedNumericDocValuesField("int", value));
            w.addDocument(doc);
        }

        SamplerAggregationBuilder aggBuilder = new SamplerAggregationBuilder("sampler")
                .shardSize(3)
                .subAggregation(new MinAggregationBuilder("min")
                        .field("int"));
        try (IndexReader reader = DirectoryReader.open(w)) {
            assertEquals("test expects a single segment", 1, reader.leaves().size());
            IndexSearcher searcher = new IndexSearcher(reader);
            Sampler sampler = searchAndReduce(searcher, new TermQuery(new Term("text", "good")), aggBuilder, textFieldType,
                    numericFieldType);
            Min min = sampler.getAggregations().get("min");
            assertEquals(5.0, min.getValue(), 0);
        }
    }
}