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

List of usage examples for org.apache.lucene.index IndexReader document

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. IndexReader
  6. 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 nth Document in this index.

Usage

From source file:net.semanticmetadata.lire.searchers.forevaluations.GenericFastImageSearcherForEvaluation.java

License:Open Source License

public ImageDuplicates findDuplicates(IndexReader reader) throws IOException {
    // get the first document:
    SimpleImageDuplicates simpleImageDuplicates = null;
    //        try {
    //            if (!IndexReader.indexExists(reader.directory()))
    //                throw new FileNotFoundException("No index found at this specific location.");
    Document doc = reader.document(0);

    LireFeature lireFeature = extractorItem.getFeatureInstance();
    if (doc.getField(fieldName).binaryValue() != null && doc.getField(fieldName).binaryValue().length > 0)
        lireFeature.setByteArrayRepresentation(doc.getField(fieldName).binaryValue().bytes,
                doc.getField(fieldName).binaryValue().offset, doc.getField(fieldName).binaryValue().length);

    HashMap<Double, List<String>> duplicates = new HashMap<Double, List<String>>();

    // Needed for check whether the document is deleted.
    Bits liveDocs = MultiFields.getLiveDocs(reader);

    int docs = reader.numDocs();
    int numDuplicates = 0;
    for (int i = 0; i < docs; i++) {
        if (reader.hasDeletions() && !liveDocs.get(i))
            continue; // if it is deleted, just ignore it.

        Document d = reader.document(i);
        double distance = getDistance(d, lireFeature);

        if (!duplicates.containsKey(distance)) {
            duplicates.put(distance, new LinkedList<String>());
        } else {/*from ww w.  j ava2  s . c o  m*/
            numDuplicates++;
        }
        duplicates.get(distance).add(d.getField(DocumentBuilder.FIELD_NAME_IDENTIFIER).stringValue());
    }

    if (numDuplicates == 0)
        return null;

    LinkedList<List<String>> results = new LinkedList<List<String>>();
    for (double d : duplicates.keySet()) {
        if (duplicates.get(d).size() > 1) {
            results.add(duplicates.get(d));
        }
    }
    simpleImageDuplicates = new SimpleImageDuplicates(results);
    //        } catch (InstantiationException e) {
    //            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
    //        } catch (IllegalAccessException e) {
    //            logger.log(Level.SEVERE, "Error instantiating class for generic image searcher: " + e.getMessage());
    //        }
    return simpleImageDuplicates;

}

From source file:net.semanticmetadata.lire.searchers.GenericFastImageSearcher.java

License:Open Source License

/**
 * @param reader//from  w  w  w.  j  a  v  a  2 s. c o  m
 * @param lireFeature
 * @return the maximum distance found for normalizing.
 * @throws IOException
 */
protected double findSimilar(IndexReader reader, LireFeature lireFeature) throws IOException {
    maxDistance = -1d;

    // clear result set ...
    docs.clear();
    // Needed for check whether the document is deleted.
    Bits liveDocs = MultiFields.getLiveDocs(reader);
    Document d;
    double tmpDistance;
    int docs = reader.numDocs();
    if (!isCaching) {
        // we read each and every document from the index and then we compare it to the query.
        for (int i = 0; i < docs; i++) {
            if (reader.hasDeletions() && !liveDocs.get(i))
                continue; // if it is deleted, just ignore it.

            d = reader.document(i);
            tmpDistance = getDistance(d, lireFeature);
            assert (tmpDistance >= 0);
            // if the array is not full yet:
            if (this.docs.size() < maxHits) {
                this.docs.add(new SimpleResult(tmpDistance, i));
                if (tmpDistance > maxDistance)
                    maxDistance = tmpDistance;
            } else if (tmpDistance < maxDistance) {
                // if it is nearer to the sample than at least on of the current set:
                // remove the last one ...
                this.docs.remove(this.docs.last());
                // add the new one ...
                this.docs.add(new SimpleResult(tmpDistance, i));
                // and set our new distance border ...
                maxDistance = this.docs.last().getDistance();
            }
        }
    } else {
        LinkedList<Consumer> tasks = new LinkedList<Consumer>();
        LinkedList<Thread> threads = new LinkedList<Thread>();
        Consumer consumer;
        Thread thread;
        Thread p = new Thread(new Producer());
        p.start();
        for (int i = 0; i < numThreads; i++) {
            consumer = new Consumer(lireFeature);
            thread = new Thread(consumer);
            thread.start();
            tasks.add(consumer);
            threads.add(thread);
        }
        for (Thread next : threads) {
            try {
                next.join();
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }
        TreeSet<SimpleResult> tmpDocs;
        boolean flag;
        SimpleResult simpleResult;
        for (Consumer task : tasks) {
            tmpDocs = task.getResult();
            flag = true;
            while (flag && (tmpDocs.size() > 0)) {
                simpleResult = tmpDocs.pollFirst();
                if (this.docs.size() < maxHits) {
                    this.docs.add(simpleResult);
                    if (simpleResult.getDistance() > maxDistance)
                        maxDistance = simpleResult.getDistance();
                } else if (simpleResult.getDistance() < maxDistance) {
                    //                        this.docs.remove(this.docs.last());
                    this.docs.pollLast();
                    this.docs.add(simpleResult);
                    maxDistance = this.docs.last().getDistance();
                } else
                    flag = false;
            }
        }
    }
    return maxDistance;
}

From source file:net.semanticmetadata.lire.searchers.LshImageSearcher.java

License:Open Source License

private ImageSearchHits search(String[] hashes, GlobalFeature queryFeature, IndexReader reader)
        throws IOException {
    // first search by text:
    IndexSearcher searcher = new IndexSearcher(reader);
    searcher.setSimilarity(new ClassicSimilarity() {
        @Override//from   ww w.jav a 2 s  .  c o  m
        public float tf(float freq) {
            return 1;
        }

        @Override
        public float idf(long docFreq, long numDocs) {
            return 1;
        }

        @Override
        public float coord(int overlap, int maxOverlap) {
            return 1;
        }

        @Override
        public float queryNorm(float sumOfSquaredWeights) {
            return 1;
        }

        @Override
        public float sloppyFreq(int distance) {
            return 1;
        }

        @Override
        public float lengthNorm(FieldInvertState state) {
            return 1;
        }
    });
    BooleanQuery.Builder queryBuilder = new BooleanQuery.Builder();
    for (int i = 0; i < hashes.length; i++) {
        // be aware that the hashFunctionsFileName of the field must match the one you put the hashes in before.
        queryBuilder.add(new BooleanClause(new TermQuery(new Term(hashesFieldName, hashes[i] + "")),
                BooleanClause.Occur.SHOULD));
    }
    TopDocs docs = searcher.search(queryBuilder.build(), maxResultsHashBased);
    // then re-rank
    TreeSet<SimpleResult> resultScoreDocs = new TreeSet<SimpleResult>();
    double maxDistance = 0d;
    double tmpScore = 0d;
    for (int i = 0; i < docs.scoreDocs.length; i++) {
        feature.setByteArrayRepresentation(
                reader.document(docs.scoreDocs[i].doc).getBinaryValue(featureFieldName).bytes,
                reader.document(docs.scoreDocs[i].doc).getBinaryValue(featureFieldName).offset,
                reader.document(docs.scoreDocs[i].doc).getBinaryValue(featureFieldName).length);
        tmpScore = queryFeature.getDistance(feature);
        if (resultScoreDocs.size() < maximumHits) {
            resultScoreDocs.add(new SimpleResult(tmpScore, docs.scoreDocs[i].doc));
            maxDistance = Math.max(maxDistance, tmpScore);
        } else if (tmpScore < maxDistance) {
            resultScoreDocs.add(new SimpleResult(tmpScore, docs.scoreDocs[i].doc));
        }
        while (resultScoreDocs.size() > maximumHits) {
            resultScoreDocs.remove(resultScoreDocs.last());
            maxDistance = resultScoreDocs.last().getDistance();
        }
        //            resultScoreDocs.add(new SimpleResult(tmpScore, reader.document(docs.scoreDocs[i].doc), docs.scoreDocs[i].doc));
    }
    return new SimpleImageSearchHits(resultScoreDocs, maxDistance);
}

From source file:net.semanticmetadata.lire.searchers.MetricSpacesImageSearcher.java

License:Open Source License

private ImageSearchHits search(String hashes, GlobalFeature queryFeature, IndexReader reader)
        throws IOException {
    // first search by text:
    IndexSearcher searcher = new IndexSearcher(reader);
    searcher.setSimilarity(new BaseSimilarity());
    QueryParser qp = new QueryParser(hashesFieldName, new WhitespaceAnalyzer());
    Query query = null;/*from   w  w w .j  a  v a 2s.c  om*/
    try {
        query = qp.parse(hashes);
    } catch (ParseException e) {
        e.printStackTrace();
    }
    if (query == null)
        return null;
    TopDocs docs = searcher.search(query, maxResultsHashBased);
    //        System.out.println(docs.totalHits);
    // then re-rank
    TreeSet<SimpleResult> resultScoreDocs = new TreeSet<SimpleResult>();
    double maxDistance = -1d;
    double tmpScore;
    for (int i = 0; i < docs.scoreDocs.length; i++) {
        feature.setByteArrayRepresentation(
                reader.document(docs.scoreDocs[i].doc).getBinaryValue(featureFieldName).bytes,
                reader.document(docs.scoreDocs[i].doc).getBinaryValue(featureFieldName).offset,
                reader.document(docs.scoreDocs[i].doc).getBinaryValue(featureFieldName).length);
        tmpScore = queryFeature.getDistance(feature);
        assert (tmpScore >= 0);
        if (resultScoreDocs.size() < maximumHits) {
            resultScoreDocs.add(new SimpleResult(tmpScore, docs.scoreDocs[i].doc));
            maxDistance = Math.max(maxDistance, tmpScore);
        } else if (tmpScore < maxDistance) {
            // if it is nearer to the sample than at least one of the current set:
            // remove the last one ...
            resultScoreDocs.remove(resultScoreDocs.last());
            // add the new one ...
            resultScoreDocs.add(new SimpleResult(tmpScore, docs.scoreDocs[i].doc));
            // and set our new distance border ...
            maxDistance = resultScoreDocs.last().getDistance();
        }
    }
    assert (resultScoreDocs.size() <= maximumHits);
    return new SimpleImageSearchHits(resultScoreDocs, maxDistance);
}

From source file:net.semanticmetadata.lire.searchers.TestSearching.java

License:Open Source License

public void testSearch() throws IOException, IllegalAccessException, InstantiationException {
    Cluster[] cvsurf512 = Cluster.readClusters(codebookPath + "CvSURF512");
    Cluster[] simpleceddcvsurf512 = Cluster.readClusters(codebookPath + "SIMPLEdetCVSURFCEDD512");

    ParallelIndexer parallelIndexer = new ParallelIndexer(DocumentBuilder.NUM_OF_THREADS, indexPath,
            testExtensive, numOfClusters, numOfDocsForVocabulary, aggregatorClass);
    parallelIndexer.addExtractor(globalFeatureClass);
    parallelIndexer.addExtractor(localFeatureClass, cvsurf512);
    parallelIndexer.addExtractor(globalFeatureClass, keypointDetector, simpleceddcvsurf512);
    parallelIndexer.run();/* ww w  .  j  a  va 2  s. co  m*/

    BufferedImage image = ImageIO.read(new FileInputStream(imageToSearch));

    IndexReader reader = DirectoryReader
            .open(new RAMDirectory(FSDirectory.open(Paths.get(indexPath)), IOContext.READONCE));
    System.out.println("Documents in the reader: " + reader.maxDoc());

    GenericFastImageSearcher ceddSearcher = new GenericFastImageSearcher(10, globalFeatureClass, true, reader);
    ImageSearchHits ceddhits = ceddSearcher.search(image, reader);
    String hitFile;
    for (int y = 0; y < ceddhits.length(); y++) {
        hitFile = reader.document(ceddhits.documentID(y)).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
        System.out.println(y + ". " + hitFile + " " + ceddhits.score(y));
    }
    System.out.println();

    GenericFastImageSearcher cvsurfsearcher = new GenericFastImageSearcher(10, localFeatureClass,
            aggregatorClass.newInstance(), 512, true, reader, indexPath + ".config");
    ImageSearchHits cvsurfhits = cvsurfsearcher.search(image, reader);
    for (int y = 0; y < cvsurfhits.length(); y++) {
        hitFile = reader.document(cvsurfhits.documentID(y)).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
        System.out.println(y + ". " + hitFile + " " + cvsurfhits.score(y));
    }
    System.out.println();

    GenericFastImageSearcher simpleceddcvsurfsearcher = new GenericFastImageSearcher(10, globalFeatureClass,
            keypointDetector, aggregatorClass.newInstance(), 512, true, reader, indexPath + ".config");
    ImageSearchHits simpleceddcvsurfhits = simpleceddcvsurfsearcher.search(image, reader);
    for (int y = 0; y < simpleceddcvsurfhits.length(); y++) {
        hitFile = reader.document(simpleceddcvsurfhits.documentID(y))
                .getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
        System.out.println(y + ". " + hitFile + " " + simpleceddcvsurfhits.score(y));
    }
    System.out.println();
}

From source file:net.semanticmetadata.lire.searchers.TestSearching.java

License:Open Source License

public void testSearchMulImages() throws IOException, IllegalAccessException, InstantiationException {
    Cluster[] cvsurf512 = Cluster.readClusters(codebookPath + "CvSURF512");
    Cluster[] simpleceddcvsurf512 = Cluster.readClusters(codebookPath + "SIMPLEdetCVSURFCEDD512");

    ParallelIndexer parallelIndexer = new ParallelIndexer(DocumentBuilder.NUM_OF_THREADS, indexPath,
            testExtensive, numOfClusters, numOfDocsForVocabulary, aggregatorClass);
    parallelIndexer.addExtractor(globalFeatureClass);
    parallelIndexer.addExtractor(localFeatureClass, cvsurf512);
    parallelIndexer.addExtractor(globalFeatureClass, keypointDetector, simpleceddcvsurf512);
    parallelIndexer.run();//from   w  ww  .j  a v a2 s  .c  o m

    ArrayList<String> images = FileUtils.readFileLines(new File(testExtensive), true);

    IndexReader reader = DirectoryReader
            .open(new RAMDirectory(FSDirectory.open(Paths.get(indexPath)), IOContext.READONCE));
    System.out.println("Documents in the reader: " + reader.maxDoc());

    GenericFastImageSearcher ceddSearcher = new GenericFastImageSearcher(1, globalFeatureClass, true, reader);
    GenericFastImageSearcher cvsurfsearcher = new GenericFastImageSearcher(1, localFeatureClass,
            aggregatorClass.newInstance(), 512, true, reader, indexPath + ".config");
    GenericFastImageSearcher simpleceddcvsurfsearcher = new GenericFastImageSearcher(1, globalFeatureClass,
            keypointDetector, aggregatorClass.newInstance(), 512, true, reader, indexPath + ".config");

    BufferedImage image;
    ImageSearchHits ceddhits, cvsurfhits, simpleceddcvsurfhits;
    String hitFile;
    int counter = 0;
    for (String next : images) {
        image = ImageIO.read(new FileInputStream(next));
        next = next.substring(next.lastIndexOf('\\') + 1);
        System.out.println(counter + " ~ " + next);

        ceddhits = ceddSearcher.search(image, reader);
        hitFile = reader.document(ceddhits.documentID(0)).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
        if (next.equals(hitFile))
            System.out.println(0 + ". " + hitFile + " " + ceddhits.score(0));
        else
            System.err.println("ERROR " + hitFile + " " + ceddhits.score(0) + " ERROR");

        cvsurfhits = cvsurfsearcher.search(image, reader);
        hitFile = reader.document(cvsurfhits.documentID(0)).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
        if (next.equals(hitFile))
            System.out.println(0 + ". " + hitFile + " " + cvsurfhits.score(0));
        else
            System.err.println("ERROR " + hitFile + " " + cvsurfhits.score(0) + " ERROR");

        simpleceddcvsurfhits = simpleceddcvsurfsearcher.search(image, reader);
        hitFile = reader.document(simpleceddcvsurfhits.documentID(0))
                .getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
        if (next.equals(hitFile))
            System.out.println(0 + ". " + hitFile + " " + simpleceddcvsurfhits.score(0));
        else
            System.err.println("ERROR " + hitFile + " " + simpleceddcvsurfhits.score(0) + " ERROR");

        counter++;
        System.out.println();
    }
}

From source file:net.semanticmetadata.lire.searchers.TestSearching.java

License:Open Source License

public void testSeparateIndex() throws IOException, IllegalAccessException, InstantiationException {
    Cluster[] cvsurf512 = Cluster.readClusters(codebookPath + "CvSURF512");
    Cluster[] simpleceddcvsurf512 = Cluster.readClusters(codebookPath + "SIMPLEdetCVSURFCEDD512");

    ParallelIndexer parallelIndexer = new ParallelIndexer(DocumentBuilder.NUM_OF_THREADS, indexPath,
            testExtensiveRed, numOfClusters, numOfDocsForVocabulary, aggregatorClass);
    parallelIndexer.addExtractor(globalFeatureClass);
    parallelIndexer.addExtractor(localFeatureClass, cvsurf512);
    parallelIndexer.addExtractor(globalFeatureClass, keypointDetector, simpleceddcvsurf512);
    parallelIndexer.run();/*w w  w  .ja v  a2  s  .c  o  m*/

    ParallelIndexer parallelIndexerSeparate = new ParallelIndexer(DocumentBuilder.NUM_OF_THREADS,
            indexPathSeparate, testExtensiveBlack, indexPath);
    parallelIndexerSeparate.run();

    IndexReader readerIndex = DirectoryReader
            .open(new RAMDirectory(FSDirectory.open(Paths.get(indexPath)), IOContext.READONCE));
    System.out.println("Documents in the reader: " + readerIndex.maxDoc());

    IndexReader readerQueries = DirectoryReader
            .open(new RAMDirectory(FSDirectory.open(Paths.get(indexPathSeparate)), IOContext.READONCE));
    System.out.println("Documents in the reader: " + readerQueries.maxDoc());

    GenericFastImageSearcher ceddSearcher = new GenericFastImageSearcher(5, globalFeatureClass, true,
            readerIndex);
    GenericFastImageSearcher cvsurfsearcher = new GenericFastImageSearcher(5, localFeatureClass,
            aggregatorClass.newInstance(), 512, true, readerIndex, indexPath + ".config");
    GenericFastImageSearcher simpleceddcvsurfsearcher = new GenericFastImageSearcher(5, globalFeatureClass,
            keypointDetector, aggregatorClass.newInstance(), 512, true, readerIndex, indexPath + ".config");

    Bits liveDocs = MultiFields.getLiveDocs(readerQueries);

    ImageSearchHits ceddhits, cvsurfhits, simpleceddcvsurfhits;
    Document queryDoc;
    String queryfile, hitFile;
    int counter = 0;
    for (int i = 0; i < readerQueries.maxDoc(); i++) {
        if (readerQueries.hasDeletions() && !liveDocs.get(i))
            continue;

        queryDoc = readerQueries.document(i);
        queryfile = queryDoc.getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        queryfile = queryfile.substring(queryfile.lastIndexOf('\\') + 1);
        System.out.println(counter + ". Query image: " + queryfile);
        ceddhits = ceddSearcher.search(queryDoc, readerIndex);
        cvsurfhits = cvsurfsearcher.search(queryDoc, readerIndex);
        simpleceddcvsurfhits = simpleceddcvsurfsearcher.search(queryDoc, readerIndex);

        System.out.println("Global:");
        for (int y = 0; y < ceddhits.length(); y++) {
            hitFile = readerIndex.document(ceddhits.documentID(y))
                    .getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
            hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
            System.out.println(y + ". " + hitFile + " " + ceddhits.score(y));
        }

        System.out.println("Local:");
        for (int y = 0; y < cvsurfhits.length(); y++) {
            hitFile = readerIndex.document(cvsurfhits.documentID(y))
                    .getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
            hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
            System.out.println(y + ". " + hitFile + " " + cvsurfhits.score(y));
        }

        System.out.println("Simple:");
        for (int y = 0; y < simpleceddcvsurfhits.length(); y++) {
            hitFile = readerIndex.document(simpleceddcvsurfhits.documentID(y))
                    .getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
            hitFile = hitFile.substring(hitFile.lastIndexOf('\\') + 1);
            System.out.println(y + ". " + hitFile + " " + simpleceddcvsurfhits.score(y));
        }
        System.out.println();
        counter++;
    }
}

From source file:net.semanticmetadata.lire.TestImageSearcher.java

License:Open Source License

public void testCachingSearcher() throws IOException {
    IndexReader ir = DirectoryReader.open(FSDirectory.open(new File("C:\\Temp\\test-100k-cedd-idx")));
    GenericFastImageSearcher is = new GenericFastImageSearcher(1, CEDD.class, true, ir);
    SingleNddCeddImageSearcher nis = new SingleNddCeddImageSearcher(ir);
    LinkedList<Document> q = new LinkedList<Document>();
    for (int i = 0; i < Math.min(1000, ir.maxDoc()); i++) {
        q.add(ir.document(i));
    }//from   ww w .j a  va 2  s  .  c  om

    long time = System.currentTimeMillis();
    int count = 0;
    for (Iterator<Document> iterator = q.iterator(); iterator.hasNext();) {
        Document next = iterator.next();
        String id = is.search(next, ir).doc(0).getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        CEDD cedd = new CEDD();
        BytesRef binaryValue = next.getBinaryValue(cedd.getFieldName());
        cedd.setByteArrayRepresentation(binaryValue.bytes, binaryValue.offset, binaryValue.length);

        String s = nis.findMostSimilar(cedd).getDocument().getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        String qID = next.getValues(DocumentBuilder.FIELD_NAME_IDENTIFIER)[0];
        System.out.println(s.equals(id) + " " + id.equals(qID) + " " + qID.equals(s));
        count++;
        if (count > 100)
            break;
    }
    long l = System.currentTimeMillis() - time;
    System.out.printf("Tested %d search requests on %d documents: overall time of %d:%02d, %.2f ms per search",
            count, ir.maxDoc(), l / (1000 * 60), (l / 1000) % 60, ((float) l / (float) count));

}

From source file:net.semanticmetadata.lire.TestImageSearcher.java

License:Open Source License

public void testCustomCachingSearcher() throws IOException {
    IndexReader ir = DirectoryReader.open(FSDirectory.open(new File("C:\\Temp\\test-100k-cedd-idx")));
    SingleNddCeddImageSearcher is = new SingleNddCeddImageSearcher(ir);

    LinkedList<LireFeature> q = new LinkedList<LireFeature>();
    for (int i = 0; i < ir.maxDoc(); i++) {
        Document d = ir.document(i);
        CEDD cedd = new CEDD();
        BytesRef binaryValue = d.getBinaryValue(cedd.getFieldName());
        cedd.setByteArrayRepresentation(binaryValue.bytes, binaryValue.offset, binaryValue.length);
        q.add(cedd);/* w w  w  .  j  av a2s . c o  m*/
    }

    long time = System.currentTimeMillis();
    int count = 0;
    for (Iterator<LireFeature> iterator = q.iterator(); iterator.hasNext();) {
        LireFeature next = iterator.next();
        is.findMostSimilar(next);
        count++;
        if (count > 100)
            break;
    }
    long l = System.currentTimeMillis() - time;
    System.out.printf("Tested %d search requests on %d documents: overall time of %d:%02d, %.2f ms per search",
            count, ir.maxDoc(), l / (1000 * 60), (l / 1000) % 60, ((float) l / (float) count));
}

From source file:net.semanticmetadata.lire.TestImageSearcher.java

License:Open Source License

public void testCachingSearcherParallel() throws IOException, InterruptedException {
    final IndexReader ir = DirectoryReader.open(FSDirectory.open(new File("C:\\Temp\\test-100k-cedd-idx")));
    SingleNddCeddImageSearcher is = new SingleNddCeddImageSearcher(ir);

    LinkedList<LireFeature> q = new LinkedList<LireFeature>();
    for (int i = 0; i < ir.maxDoc(); i++) {
        Document d = ir.document(i);
        CEDD cedd = new CEDD();
        BytesRef binaryValue = d.getBinaryValue(cedd.getFieldName());
        cedd.setByteArrayRepresentation(binaryValue.bytes, binaryValue.offset, binaryValue.length);
        q.add(cedd);//from w ww  .j  a  v  a  2s  .  c  om
    }

    int count = 0;
    Thread[] searchers = new Thread[3];
    final LinkedBlockingQueue<LireFeature> queryQueue = new LinkedBlockingQueue<LireFeature>(1000);
    for (int i = 0; i < searchers.length; i++) {
        searchers[i] = new Thread(new Runnable() {
            @Override
            public void run() {
                SingleNddCeddImageSearcher is = new SingleNddCeddImageSearcher(ir);
                LireFeature remove;
                while ((remove = queryQueue.remove()) instanceof CEDD) {
                    try {
                        is.findMostSimilar(remove);
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
            }

        });
        searchers[i].start();
    }
    long time = System.currentTimeMillis();
    for (Iterator<LireFeature> iterator = q.iterator(); iterator.hasNext() && count < 1000;) {
        LireFeature next = iterator.next();
        try {
            queryQueue.put(next);
            count++;
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
    }
    for (int i = 0; i < 8; i++) {
        queryQueue.put(new ScalableColor());
    }
    for (int i = 0; i < searchers.length; i++) {
        searchers[i].join();
    }
    long l = System.currentTimeMillis() - time;
    System.out.printf("Tested %d search requests on %d documents: overall time of %d:%02d, %.2f ms per search",
            count, ir.maxDoc(), l / (1000 * 60), (l / 1000) % 60, ((float) l / (float) count));
}