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.kimios.kernel.index.SearchQuery.java

License:Open Source License

public Vector<Document> execute(IndexReader reader) throws IndexException {
    try {//from   w  w w  .ja va 2 s  .  c  o  m
        if (this.searchRoot != null) {
            this.clauses.add(new DocumentParentClause(this.searchRoot.getPath()));
        }
        Query[] q = new Query[this.clauses.size()];
        for (int i = 0; i < this.clauses.size(); i++) {
            q[i] = this.clauses.get(i).getLuceneQuery();
        }
        Query query = IndexHelper.mergeQueries(IndexHelper.getAnalyzer(), q);
        IndexSearcher searcher = new IndexSearcher(reader);
        final Vector<Document> results = new Vector<Document>();
        final IndexReader readerCpy = reader;
        TopScoreDocCollector dcColl = TopScoreDocCollector.create(Integer.MAX_VALUE, true);
        searcher.search(query, dcColl);
        for (ScoreDoc it : dcColl.topDocs().scoreDocs) {
            try {
                long uid = Long.parseLong(readerCpy.document(it.doc).get("DocumentUid"));
                Document r = FactoryInstantiator.getInstance().getDocumentFactory().getDocument(uid);
                if (r != null) {
                    results.add(r);
                }
            } catch (Exception ex) {
            }
        }
        return results;
    } catch (Exception ex) {
        throw new IndexException(ex, "Error during query parsing : " + ex.getMessage());
    }
}

---

From source file:org.languagetool.dev.bigdata.GermanUppercasePhraseFinder.java

License:Open Source License

private static long getOccurrenceCount(IndexReader reader, IndexSearcher searcher, String term)
        throws IOException {
    TopDocs topDocs = searcher.search(new TermQuery(new Term("ngram", term)), 5);
    if (topDocs.totalHits == 0) {
        return 0;
    }//from  w  w  w  .  j ava 2 s . c  om
    int docId = topDocs.scoreDocs[0].doc;
    Document document = reader.document(docId);
    return Long.parseLong(document.get("count"));
}

---

From source file:org.languagetool.dev.bigdata.LargestNGramFinder.java

License:Open Source License

public static void main(String[] args) throws IOException {
    if (args.length != 1) {
        System.out.println("Usage: " + LargestNGramFinder.class.getSimpleName() + " <ngramIndexDir>");
        System.exit(1);//from  w  ww .j  a  va2 s  . co  m
    }
    FSDirectory fsDir = FSDirectory.open(new File(args[0]).toPath());
    IndexReader reader = DirectoryReader.open(fsDir);
    IndexSearcher searcher = new IndexSearcher(reader);
    Fields fields = MultiFields.getFields(reader);
    long max = 0;
    String maxTerm = "";
    Terms terms = fields.terms("ngram");
    TermsEnum termsEnum = terms.iterator();
    int count = 0;
    BytesRef next;
    while ((next = termsEnum.next()) != null) {
        String term = next.utf8ToString();
        TopDocs topDocs = searcher.search(new TermQuery(new Term("ngram", term)), 5);
        int docId = topDocs.scoreDocs[0].doc;
        Document document = reader.document(docId);
        long thisCount = Long.parseLong(document.get("count"));
        if (max < thisCount) {
            max = thisCount;
            maxTerm = term;
        }
        if (count % 10_000 == 0) {
            System.out.println(count + " -> " + topDocs.totalHits + " for " + term + " -> " + thisCount
                    + ", max so far: " + max + " for '" + maxTerm + "'");
        }
        count++;
    }
    System.out.println("Max: " + max + " for " + maxTerm);
}

---

From source file:org.meresco.lucene.MerescoClustererTest.java

License:Open Source License

@Test
public void testClusteringOnVectorsMultipleStrategies() throws IOException, Exception {
    ClusterConfig clusterConfig = new ClusterConfig(42);
    clusterConfig.addStrategy(new ClusterStrategy(0.5, 2).addField("termvector.field", 1.0, "vuur"));
    clusterConfig.addStrategy(new ClusterStrategy(0.4, 1).addField("termvector.field", 1.0, null));
    clusterConfig.addStrategy(new ClusterStrategy(0.4, 2).addField("termvector.field", 1.0, "anders"));

    InterpolateEpsilon interpolateEpsilon = new InterpolateEpsilon() {
        @Override//  w ww .j  a  v a2  s. co  m
        public double interpolateEpsilon(int hits, int sliceSize, double clusteringEps,
                int clusterMoreRecords) {
            assertEquals(100, hits);
            assertEquals(10, sliceSize);
            assertTrue(clusteringEps >= 0.4);
            assertEquals(42, clusterMoreRecords);
            return clusteringEps;
        }
    };
    IndexReader indexReader = getIndexReader();
    MerescoClusterer merescoClusterer = new MerescoClusterer(indexReader, clusterConfig, interpolateEpsilon,
            100, 10);
    for (int i = 0; i < 15; i++) {
        merescoClusterer.collect(i);
    }
    merescoClusterer.finish();

    assertEquals(3, merescoClusterer.clusters.size());
    for (int i = 0; i < 15; i++) {
        String theID = indexReader.document(i).get(Lucene.ID_FIELD);
        MerescoCluster cluster = merescoClusterer.cluster(i);
        Set<String> ids = new HashSet<>();
        for (DocScore ds : cluster.topDocs) {
            ids.add(indexReader.document(ds.docId).get(Lucene.ID_FIELD));
        }
        assertTrue(ids.contains(theID));
        int idOrd = Integer.valueOf(theID.split(":")[1]);
        if (0 <= idOrd && idOrd <= 4) {
            assertEquals(new HashSet<String>(Arrays.asList("id:4", "id:0", "id:1", "id:2", "id:3")), ids);
        } else if (5 <= idOrd && idOrd <= 9) {
            assertEquals(new HashSet<String>(Arrays.asList("id:8", "id:7", "id:6", "id:5", "id:9")), ids);
        } else {
            assertEquals(new HashSet<String>(Arrays.asList("id:10", "id:11", "id:12", "id:13", "id:14")), ids);
        }
    }
}

---

From source file:org.metaservice.core.maven.MavenIndexCrawler.java

License:Apache License

public void perform() throws IOException, ComponentLookupException, InvalidVersionSpecificationException {
    // Files where local cache is (if any) and Lucene Index should be located
    File centralLocalCache = new File("target/central-cache");
    File centralIndexDir = new File("target/central-index");

    // Creators we want to use (search for fields it defines)
    List<IndexCreator> indexers = new ArrayList<>();
    indexers.add(plexusContainer.lookup(IndexCreator.class, "min"));
    indexers.add(plexusContainer.lookup(IndexCreator.class, "jarContent"));
    indexers.add(plexusContainer.lookup(IndexCreator.class, "maven-plugin"));

    // Create context for central repository index
    centralContext = indexer.createIndexingContext("central-context", "central", centralLocalCache,
            centralIndexDir, "http://repo1.maven.org/maven2", null, true, true, indexers);

    // Update the index (incremental update will happen if this is not 1st run and files are not deleted)
    // This whole block below should not be executed on every app start, but rather controlled by some configuration
    // since this block will always emit at least one HTTP GET. Central indexes are updated once a week, but
    // other index sources might have different index publishing frequency.
    // Preferred frequency is once a week.
    if (true) {//from w w  w  .  j  av a 2 s.c  o  m
        System.out.println("Updating Index...");
        System.out.println("This might take a while on first run, so please be patient!");
        // Create ResourceFetcher implementation to be used with IndexUpdateRequest
        // Here, we use Wagon based one as shorthand, but all we need is a ResourceFetcher implementation
        TransferListener listener = new AbstractTransferListener() {
            public void transferStarted(TransferEvent transferEvent) {
                System.out.print(" Downloading " + transferEvent.getResource().getName());
            }

            public void transferProgress(TransferEvent transferEvent, byte[] buffer, int length) {
            }

            public void transferCompleted(TransferEvent transferEvent) {
                System.out.println(" - Done");
            }
        };
        ResourceFetcher resourceFetcher = new WagonHelper.WagonFetcher(httpWagon, listener, null, null);

        Date centralContextCurrentTimestamp = centralContext.getTimestamp();
        IndexUpdateRequest updateRequest = new IndexUpdateRequest(centralContext, resourceFetcher);
        IndexUpdateResult updateResult = indexUpdater.fetchAndUpdateIndex(updateRequest);
        if (updateResult.isFullUpdate()) {
            System.out.println("Full update happened!");
        } else if (updateResult.getTimestamp().equals(centralContextCurrentTimestamp)) {
            System.out.println("No update needed, index is up to date!");
        } else {
            System.out.println("Incremental update happened, change covered " + centralContextCurrentTimestamp
                    + " - " + updateResult.getTimestamp() + " period.");
        }

        System.out.println();
    }

    System.out.println();
    System.out.println("Using index");
    System.out.println("===========");
    System.out.println();

    // ====
    // Case:
    // dump all the GAVs
    // NOTE: will not actually execute do this below, is too long to do (Central is HUGE), but is here as code
    // example

    int j = 0;
    if (true) {

        final IndexSearcher searcher = centralContext.acquireIndexSearcher();
        try {
            final IndexReader ir = searcher.getIndexReader();
            for (int i = 0; i < ir.maxDoc(); i++) {
                if (!ir.isDeleted(i)) {
                    j++;
                    final Document doc = ir.document(i);
                    final ArtifactInfo ai = IndexUtils.constructArtifactInfo(doc, centralContext);
                    if (ai != null && "pom".equals(ai.fextension))
                        System.out.println(ai.groupId + ":" + ai.artifactId + ":" + ai.version + ":"
                                + ai.classifier + " (sha1=" + ai.sha1 + ")");

                }
            }
        } finally {
            centralContext.releaseIndexSearcher(searcher);
        }
    }
    System.err.println(j);
    if (j > 0)
        return;

    // ====
    // Case:
    // Search for all GAVs with known G and A and having version greater than V

    final GenericVersionScheme versionScheme = new GenericVersionScheme();
    final String versionString = "1.5.0";
    final Version version = versionScheme.parseVersion(versionString);

    // construct the query for known GA
    final Query groupIdQ = indexer.constructQuery(MAVEN.GROUP_ID,
            new SourcedSearchExpression("org.sonatype.nexus"));
    final Query artifactIdQ = indexer.constructQuery(MAVEN.ARTIFACT_ID,
            new SourcedSearchExpression("nexus-api"));
    final BooleanQuery query = new BooleanQuery();
    query.add(groupIdQ, BooleanClause.Occur.MUST);
    query.add(artifactIdQ, BooleanClause.Occur.MUST);

    // we want "jar" artifacts only
    query.add(indexer.constructQuery(MAVEN.PACKAGING, new SourcedSearchExpression("jar")),
            BooleanClause.Occur.MUST);
    // we want main artifacts only (no classifier)
    // Note: this below is unfinished API, needs fixing
    query.add(indexer.constructQuery(MAVEN.CLASSIFIER, new SourcedSearchExpression(Field.NOT_PRESENT)),
            BooleanClause.Occur.MUST_NOT);

    // construct the filter to express "V greater than"
    final ArtifactInfoFilter versionFilter = new ArtifactInfoFilter() {
        public boolean accepts(final IndexingContext ctx, final ArtifactInfo ai) {
            try {
                final Version aiV = versionScheme.parseVersion(ai.version);
                // Use ">=" if you are INCLUSIVE
                return aiV.compareTo(version) > 0;
            } catch (InvalidVersionSpecificationException e) {
                // do something here? be safe and include?
                return true;
            }
        }
    };

    System.out.println(
            "Searching for all GAVs with G=org.sonatype.nexus and nexus-api and having V greater than 1.5.0");
    final IteratorSearchRequest request = new IteratorSearchRequest(query,
            Collections.singletonList(centralContext), versionFilter);
    final IteratorSearchResponse response = indexer.searchIterator(request);
    for (ArtifactInfo ai : response) {
        System.out.println(ai.toString());
    }

    // Case:
    // Use index
    // Searching for some artifact
    Query gidQ = indexer.constructQuery(MAVEN.GROUP_ID,
            new SourcedSearchExpression("org.apache.maven.indexer"));
    Query aidQ = indexer.constructQuery(MAVEN.ARTIFACT_ID, new SourcedSearchExpression("indexer-artifact"));

    BooleanQuery bq = new BooleanQuery();
    bq.add(gidQ, BooleanClause.Occur.MUST);
    bq.add(aidQ, BooleanClause.Occur.MUST);

    searchAndDump(indexer, "all artifacts under GA org.apache.maven.indexer:indexer-artifact", bq);

    // Searching for some main artifact
    bq = new BooleanQuery();
    bq.add(gidQ, BooleanClause.Occur.MUST);
    bq.add(aidQ, BooleanClause.Occur.MUST);
    // bq.add( nexusIndexer.constructQuery( MAVEN.CLASSIFIER, new SourcedSearchExpression( "*" ) ), Occur.MUST_NOT
    // );

    searchAndDump(indexer, "main artifacts under GA org.apache.maven.indexer:indexer-artifact", bq);

    // doing sha1 search
    searchAndDump(indexer, "SHA1 7ab67e6b20e5332a7fb4fdf2f019aec4275846c2", indexer.constructQuery(MAVEN.SHA1,
            new SourcedSearchExpression("7ab67e6b20e5332a7fb4fdf2f019aec4275846c2")));

    searchAndDump(indexer, "SHA1 7ab67e6b20 (partial hash)",
            indexer.constructQuery(MAVEN.SHA1, new UserInputSearchExpression("7ab67e6b20")));

    // doing classname search (incomplete classname)
    searchAndDump(indexer,
            "classname DefaultNexusIndexer (note: Central does not publish classes in the index)",
            indexer.constructQuery(MAVEN.CLASSNAMES, new UserInputSearchExpression("DefaultNexusIndexer")));

    // doing search for all "canonical" maven plugins latest versions
    bq = new BooleanQuery();
    bq.add(indexer.constructQuery(MAVEN.PACKAGING, new SourcedSearchExpression("maven-plugin")),
            BooleanClause.Occur.MUST);
    bq.add(indexer.constructQuery(MAVEN.GROUP_ID, new SourcedSearchExpression("org.apache.maven.plugins")),
            BooleanClause.Occur.MUST);
    searchGroupedAndDump(indexer, "all \"canonical\" maven plugins", bq, new GAGrouping());

    // close cleanly
    indexer.closeIndexingContext(centralContext, false);
}

---

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

License:Open Source License

/**
 * Basic test of all fields//from   w  w w  . j a  v  a 2 s  .  c om
 *
 * @throws Exception
 */
@Test
public void testIndexReleaseGroupFields() throws Exception {

    addReleaseGroupTwo();
    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("Crocodiles", doc.getField(ReleaseGroupIndexField.RELEASEGROUP.getName()).stringValue());
        assertEquals("efd2ace2-b3b9-305f-8a53-9803595c0e37",
                doc.getField(ReleaseGroupIndexField.RELEASEGROUP_ID.getName()).stringValue());
        assertEquals(1, doc.getFields(ReleaseGroupIndexField.RELEASE.getName()).length);
        assertEquals("Crocodiles (bonus disc)",
                doc.getField(ReleaseGroupIndexField.RELEASE.getName()).stringValue());
        checkTerm(ir, ReleaseGroupIndexField.ARTIST_ID, "ccd4879c-5e88-4385-b131-bf65296bf245");

    }
    ir.close();

}

---

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

License:Open Source License

/**
 * Basic test of all fields//www.j a v  a 2  s.co  m
 *
 * @throws Exception
 */
@Test
public void testIndexReleaseGroupAlias() throws Exception {

    addReleaseGroupTwo();
    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);
        checkTerm(ir, ReleaseGroupIndexField.ARTIST_NAME, "aliastest");
        checkTermX(ir, ReleaseGroupIndexField.ARTIST_NAME, "and", 1);
        checkTermX(ir, ReleaseGroupIndexField.ARTIST_NAME, "bunnymen", 2);
        checkTermX(ir, ReleaseGroupIndexField.ARTIST_NAME, "echo", 3);
    }
    ir.close();

}

---

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

License:Open Source License

@Test
public void testIndexReleaseGroupWithType() throws Exception {

    addReleaseGroupOne();//  w  w  w  .j  a v a  2s .c  om
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

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

        assertEquals("Album", doc.getField(ReleaseGroupIndexField.PRIMARY_TYPE.getName()).stringValue());
    }
    ir.close();
}

---

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

License:Open Source License

@Test
public void testIndexReleaseGroupWithComment() throws Exception {

    addReleaseGroupOne();//from  ww w . ja va2 s. 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.COMMENT.getName()).length);
        assertEquals("demo", doc.getField(ReleaseGroupIndexField.COMMENT.getName()).stringValue());
    }
    ir.close();
}

---

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

License:Open Source License

@Test
public void testIndexReleaseGroupSortname() throws Exception {

    addReleaseGroupOne();/*  ww  w . j  av  a2s .  co m*/
    RAMDirectory ramDir = new RAMDirectory();
    createIndex(ramDir);

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

        ArtistCredit ac = ArtistCreditHelper
                .unserialize(doc.get(ReleaseGroupIndexField.ARTIST_CREDIT.getName()));
        assertNotNull(ac);
        assertEquals("Echo and The Bunnymen", ac.getNameCredit().get(0).getArtist().getSortName());
    }
    ir.close();

}

---

• «
• 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
• »