Example usage for org.apache.lucene.index IndexReader document

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexReader document.

Prototype

public final Document document(int docID) throws IOException 

Source Link

Document

Returns the stored fields of the n^th Document in this index.

Usage

From source file:org.musicbrainz.search.index.ReleaseGroupIndexTest.java

License:Open Source License

/**
 * Checks record with multiple releases/*from ww  w .j  a v a  2 s  .  co  m*/
 *
 * @throws Exception
 */
@Test
public void testIndexReleaseGroupWithMultipleReleases() throws Exception {

    addReleaseGroupThree();
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

    IndexReader ir = DirectoryReader.open(ramDir);
    assertEquals(2, ir.numDocs());
    {
        Document doc = ir.document(1);
        assertEquals(2, doc.getFields(ReleaseGroupIndexField.RELEASE.getName()).length);
        String val1 = doc.getFields(ReleaseGroupIndexField.RELEASE.getName())[0].stringValue();
        String val2 = doc.getFields(ReleaseGroupIndexField.RELEASE.getName())[1].stringValue();

        assertTrue("Crocodiles (Bonus disc)".equals(val1) || "Crocodiles (Bonus disc)".equals(val2));
        assertTrue("Crocodiles (Special disc)".equals(val1) || "Crocodiles (Special disc)".equals(val2));
    }
    ir.close();
}

---

From source file:org.musicbrainz.search.index.ReleaseGroupIndexTest.java

License:Open Source License

@Test
public void testIndexReleaseGroupMultipleArtists() throws Exception {

    addReleaseGroupFour();//from www  .  j  a v a  2 s .  c  o m
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

    IndexReader ir = DirectoryReader.open(ramDir);
    assertEquals(2, ir.numDocs());
    {
        Document doc = ir.document(1);

        Fields fields = MultiFields.getFields(ir);
        Terms terms = fields.terms(ReleaseGroupIndexField.ARTIST_NAME.getName());
        TermsEnum tr = terms.iterator(null);
        tr.next();
        assertEquals(1, tr.docFreq());
        assertEquals("cincinnati", tr.term().utf8ToString());
        tr.next();
        assertEquals("erich", tr.term().utf8ToString());
        tr.next();
        assertEquals("kunzel", tr.term().utf8ToString());
        tr.next();
        assertEquals("kunzstel", tr.term().utf8ToString());
        tr.next();
        assertEquals("kunzstelein", tr.term().utf8ToString());
        tr.next();
        assertEquals("orchestra", tr.term().utf8ToString());
        tr.next();
        assertEquals("pops", tr.term().utf8ToString());
        tr.next();
        assertEquals("the", tr.term().utf8ToString());

        terms = fields.terms(ReleaseGroupIndexField.ARTIST_ID.getName());
        tr = terms.iterator(null);
        tr.next();
        assertEquals(1, tr.docFreq());
        assertEquals("99845d0c-f239-4051-a6b1-4b5e9f7ede0b", tr.term().utf8ToString());
        tr.next();
        assertEquals("d8fbd94c-cd06-4e8b-a559-761ad969d07e", tr.term().utf8ToString());
        tr.next();

        terms = fields.terms(ReleaseGroupIndexField.ARTIST_NAMECREDIT.getName());
        tr = terms.iterator(null);
        tr.next();
        assertEquals(1, tr.docFreq());
        assertEquals("cincinnati", tr.term().utf8ToString());
        tr.next();
        assertEquals("erich", tr.term().utf8ToString());
        tr.next();
        assertEquals("kunzel", tr.term().utf8ToString());
        tr.next();
        assertEquals("pops", tr.term().utf8ToString());

        assertEquals("Epics", doc.getFields(ReleaseGroupIndexField.RELEASEGROUP.getName())[0].stringValue());
        assertEquals("efd2ace2-b3b9-305f-8a53-9803595c0e37",
                doc.getFields(ReleaseGroupIndexField.RELEASEGROUP_ID.getName())[0].stringValue());

        ArtistCredit ac = ArtistCreditHelper
                .unserialize(doc.get(ReleaseGroupIndexField.ARTIST_CREDIT.getName()));
        assertNotNull(ac);
        assertEquals("Erich Kunzel", ac.getNameCredit().get(0).getArtist().getName());
        assertEquals("Cincinnati Pops", ac.getNameCredit().get(1).getName());
        assertEquals("The Cincinnati Pops Orchestra", ac.getNameCredit().get(1).getArtist().getName());
        assertEquals(2, ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().size());
        assertNull(ac.getNameCredit().get(1).getArtist().getAliasList());
        assertEquals("Erich Kunzstel",
                ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().get(0).getContent());
        assertEquals("Erich Kunzstelein",
                ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().get(1).getContent());
        assertEquals("Kunzstel, Erich",
                ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().get(0).getSortName());
        assertEquals("Kunzstelein, Erich",
                ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().get(1).getSortName());
        assertEquals("en", ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().get(0).getLocale());
        assertEquals("de", ac.getNameCredit().get(0).getArtist().getAliasList().getAlias().get(1).getLocale());

    }
    ir.close();

}

---

From source file:org.musicbrainz.search.index.ReleaseGroupIndexTest.java

License:Open Source License

@Test
public void testIndexReleaseGroupWithTag() throws Exception {

    addReleaseGroupFour();/*from w w  w  .  j  av  a  2 s  .co m*/
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

    IndexReader ir = DirectoryReader.open(ramDir);
    assertEquals(2, ir.numDocs());
    {
        Document doc = ir.document(1);
        assertEquals(1, doc.getFields(ReleaseGroupIndexField.RELEASEGROUP.getName()).length);
        assertEquals(1, doc.getFields(ReleaseGroupIndexField.TAG.getName()).length);
        assertEquals("punk", doc.getField(ReleaseGroupIndexField.TAG.getName()).stringValue());
    }
    ir.close();
}

---

From source file:org.musicbrainz.search.index.ReleaseGroupIndexTest.java

License:Open Source License

@Test
public void testIndexReleaseGroupWithStatus() throws Exception {

    addReleaseGroupFour();/*  w w w  .  java 2  s.  co  m*/
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

    IndexReader ir = DirectoryReader.open(ramDir);
    assertEquals(2, ir.numDocs());
    {
        Document doc = ir.document(1);
        assertEquals(1, doc.getFields(ReleaseGroupIndexField.RELEASESTATUS.getName()).length);
        assertEquals("Official", doc.getField(ReleaseGroupIndexField.RELEASESTATUS.getName()).stringValue());
    }
    ir.close();
}

---

From source file:org.musicbrainz.search.index.ReleaseGroupIndexTest.java

License:Open Source License

@Test
public void testIndexReleaseGroupWithSecondaryTypes() throws Exception {

    addReleaseGroupFour();/*  w w  w . j a v a  2s. c o m*/
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

    IndexReader ir = DirectoryReader.open(ramDir);
    assertEquals(2, ir.numDocs());
    {
        Document doc = ir.document(1);
        assertEquals(1, doc.getFields(ReleaseGroupIndexField.PRIMARY_TYPE.getName()).length);
        assertEquals("Album", doc.getFields(ReleaseGroupIndexField.PRIMARY_TYPE.getName())[0].stringValue());

        //NOte old type field maps secondary type to compilation
        assertEquals(1, doc.getFields(ReleaseGroupIndexField.TYPE.getName()).length);
        assertEquals("Compilation", doc.getFields(ReleaseGroupIndexField.TYPE.getName())[0].stringValue());

        assertEquals(1, doc.getFields(ReleaseGroupIndexField.RELEASEGROUP.getName()).length);
        assertEquals(2, doc.getFields(ReleaseGroupIndexField.SECONDARY_TYPE.getName()).length);
        assertEquals("Compilation",
                doc.getFields(ReleaseGroupIndexField.SECONDARY_TYPE.getName())[0].stringValue());
        assertEquals("Interview",
                doc.getFields(ReleaseGroupIndexField.SECONDARY_TYPE.getName())[1].stringValue());

    }
    ir.close();
}

---

From source file:org.neo4j.index.lucene.repair.IndexHandler.java

License:Open Source License

public void deleteFieldFromNodeDocument(long nodeId, String fieldName) throws Exception {
    IndexReader reader = IndexReader.open(dir, false);
    Document newDoc = null;/* ww w. ja v a2  s .c o  m*/
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs searchResult = searcher.search(new TermQuery(new Term("_id_", Long.toString(nodeId))), 2);

    if (searchResult.totalHits > 1) {
        throw new IllegalStateException(
                "There should be only one hit for node id " + nodeId + ", i got at least 2");
    }

    int docId = searchResult.scoreDocs[0].doc;
    Document original = reader.document(docId);

    newDoc = new Document();
    for (Fieldable f : original.getFields()) {
        if (!f.name().equals(fieldName)) {
            newDoc.add(f);
        }
    }
    reader.deleteDocument(docId);
    reader.commit(null);
    reader.close();

    IndexWriter writer = new IndexWriter(dir,
            new IndexWriterConfig(Version.LUCENE_35, new WhitespaceAnalyzer(Version.LUCENE_35)));
    writer.addDocument(newDoc);
    writer.commit();
    writer.close();
}

---

From source file:org.netbeans.modules.jackpot30.ide.usages.hints.RemotelyUnused.java

License:Open Source License

@TriggerTreeKind({ Kind.VARIABLE, Kind.METHOD })
public static ErrorDescription hint(HintContext ctx) throws URISyntaxException, IOException {
    Element toSearch = ctx.getInfo().getTrees().getElement(ctx.getPath());

    if (toSearch == null)
        return null;
    if (!toSearch.getKind().isField() && toSearch.getKind() != ElementKind.METHOD
            && toSearch.getKind() != ElementKind.CONSTRUCTOR)
        return null;
    if (toSearch.getKind() == ElementKind.METHOD
            && ctx.getInfo().getElementUtilities().overridesMethod((ExecutableElement) toSearch))
        return null;

    final String serialized = JavaUtils.serialize(ElementHandle.create(toSearch));

    for (RemoteIndex idx : RemoteIndex.loadIndices()) {
        String result = LocalCache.runOverLocalCache(idx, new Task<IndexReader, String>() {
            @Override//from   ww  w  .  jav  a 2  s .  c  o m
            public String run(IndexReader reader, AtomicBoolean cancel) throws IOException {
                Query query = new TermQuery(new Term("usagesSignature", serialized));
                Searcher s = new IndexSearcher(reader);
                BitSet matchingDocuments = new BitSet(reader.maxDoc());
                Collector c = new BitSetCollector(matchingDocuments);

                s.search(query, c);

                for (int docNum = matchingDocuments.nextSetBit(0); docNum >= 0; docNum = matchingDocuments
                        .nextSetBit(docNum + 1)) {
                    if (cancel.get())
                        return VAL_UNKNOWN;

                    final Document doc = reader.document(docNum);

                    return doc.get("usagesUsages");
                }

                return VAL_UNKNOWN;
            }
        }, null, new AtomicBoolean()/*XXX*/);

        if (result == null) {
            URI resolved = new URI(idx.remote.toExternalForm() + "/usages/search?path="
                    + WebUtilities.escapeForQuery(idx.remoteSegment) + "&signatures="
                    + WebUtilities.escapeForQuery(serialized));
            String response = WebUtilities.requestStringResponse(resolved, new AtomicBoolean());

            if (response != null) {
                result = response.trim().isEmpty() ? VAL_UNUSED : VAL_USED;
            } else {
                result = VAL_UNKNOWN;
            }
            final String resultFin = result;
            LocalCache.saveToLocalCache(idx, new Task<IndexWriter, Void>() {
                @Override
                public Void run(IndexWriter p, AtomicBoolean cancel) throws IOException {
                    Document doc = new Document();
                    doc.add(new Field("usagesSignature", serialized, Store.NO, Index.NOT_ANALYZED));
                    doc.add(new Field("usagesUsages", resultFin, Store.YES, Index.NO));
                    p.addDocument(doc);
                    return null;
                }
            });
        }
        if (!VAL_UNUSED.equals(result))
            return null;
    }

    return ErrorDescriptionFactory.forName(ctx, ctx.getPath(), Bundle.ERR_NoUsages());
}

---

From source file:org.netbeans.modules.jackpot30.impl.duplicates.indexing.RemoteDuplicatesIndex.java

License:Open Source License

private static Map<String, Collection<? extends String>> containsHash(IndexReader reader,
        Iterable<? extends String> hashes, AtomicBoolean cancel) throws IOException {
    Map<String, Collection<? extends String>> result = new LinkedHashMap<String, Collection<? extends String>>();

    for (String hash : hashes) {
        if (cancel.get())
            return Collections.emptyMap();

        Collection<String> found = new LinkedList<String>();
        Query query = new TermQuery(new Term("hash", hash));
        Searcher s = new IndexSearcher(reader);
        BitSet matchingDocuments = new BitSet(reader.maxDoc());
        Collector c = new BitSetCollector(matchingDocuments);

        s.search(query, c);//from   www . j  ava  2 s . c o  m

        boolean wasFound = false;

        for (int docNum = matchingDocuments.nextSetBit(0); docNum >= 0; docNum = matchingDocuments
                .nextSetBit(docNum + 1)) {
            if (cancel.get())
                return Collections.emptyMap();

            final Document doc = reader.document(docNum);

            found.addAll(Arrays.asList(doc.getValues("path")));
            wasFound = true;
        }

        if (wasFound) {
            result.put(hash, found);
        }
    }

    return result;
}

---

From source file:org.netbeans.modules.jackpot30.indexer.usages.IndexerImplTest.java

License:Open Source License

public void testSubdirIndexing() throws IOException {
    final FileObject root = FileUtil.toFileObject(getWorkDir());
    FileObject aFile = FileUtil.createData(root, "a/A.java");
    copyToFile(aFile, "public class A {}");
    FileObject bFile = FileUtil.createData(root, "b/B.java");
    copyToFile(bFile, "public class B {}");

    Directory store = new RAMDirectory();
    IndexWriter iw = new IndexWriter(store, new KeywordAnalyzer(), IndexWriter.MaxFieldLength.UNLIMITED);
    IndexAccessor.current = new IndexAccessor(iw, root.getFileObject("a"));

    doIndex(root, aFile, bFile);/*  w  w w .j a  va  2  s  .  co  m*/

    iw.close();

    IndexReader ir = IndexReader.open(store);
    int maxDocs = ir.maxDoc();
    boolean foundA = false;

    for (int i = 0; i < maxDocs; i++) {
        Fieldable f = ir.document(i).getFieldable("file");

        if (f != null) {
            assertFalse(f.stringValue(), f.stringValue().contains("B"));
            if (f.stringValue().contains("A.java")) {
                foundA = true;
            }
        }
    }

    assertTrue(foundA);
}

---

From source file:org.ohdsi.usagi.tests.TestLucene.java

License:Apache License

public static void main(String[] args) throws IOException, ParseException {
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_4_9);
    //Analyzer analyzer = new UsagiAnalyzer();
    FieldType textVectorField = new FieldType();
    textVectorField.setIndexed(true);//w  ww  .  j a  va2s  .co m
    textVectorField.setTokenized(true);
    textVectorField.setStoreTermVectors(true);
    textVectorField.setStoreTermVectorPositions(false);
    textVectorField.setStoreTermVectorPayloads(false);
    textVectorField.setStoreTermVectorOffsets(false);
    textVectorField.setStored(true);
    textVectorField.freeze();

    File indexFolder = new File(folder);
    if (indexFolder.exists())
        DirectoryUtilities.deleteDir(indexFolder);

    Directory dir = FSDirectory.open(indexFolder);

    IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_4_9, analyzer);
    iwc.setOpenMode(OpenMode.CREATE);
    iwc.setRAMBufferSizeMB(256.0);
    IndexWriter writer = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new Field("F", "word1 word2 w3 word4", textVectorField));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new Field("F", "word1 word2 w3", textVectorField));
    writer.addDocument(doc);

    writer.close();

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(folder)));
    for (int i = 0; i < reader.numDocs(); i++) {
        TermsEnum termsEnum = reader.getTermVector(i, "F").iterator(null);
        BytesRef text;
        while ((text = termsEnum.next()) != null) {
            System.out.print(text.utf8ToString() + ",");
        }
        System.out.println();
    }
    IndexSearcher searcher = new IndexSearcher(reader);

    // MoreLikeThis mlt = new MoreLikeThis(searcher.getIndexReader());
    // mlt.setMinTermFreq(0);
    // mlt.setMinDocFreq(0);
    // mlt.setMaxDocFreq(9999);
    // mlt.setMinWordLen(0);
    // mlt.setMaxWordLen(9999);
    // mlt.setMaxDocFreqPct(100);
    // mlt.setMaxNumTokensParsed(9999);
    // mlt.setMaxQueryTerms(9999);
    // mlt.setStopWords(null);
    // mlt.setFieldNames(new String[] { "F" });
    // mlt.setAnalyzer(new UsagiAnalyzer());
    // Query query = mlt.like("F", new StringReader("Systolic blood pressure"));
    QueryParser parser = new QueryParser(Version.LUCENE_4_9, "F", analyzer);
    Query query = parser.parse("word1");

    Explanation explanation = searcher.explain(query, 0);
    print(explanation);
    System.out.println();
    explanation = searcher.explain(query, 1);
    print(explanation);
    System.out.println();

    TopDocs topDocs = searcher.search(query, 99);
    for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
        System.out.println(scoreDoc.score + "\t" + reader.document(scoreDoc.doc).get("F"));
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• »