Example usage for org.apache.lucene.index DirectoryReader open

List of usage examples for org.apache.lucene.index DirectoryReader open

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. DirectoryReader
  6. open

Introduction

In this page you can find the example usage for org.apache.lucene.index DirectoryReader open.

Prototype

public static DirectoryReader open(final IndexCommit commit) throws IOException

Source Link

Document

Expert: returns an IndexReader reading the index in the given IndexCommit .

Usage

From source file:com.mathworks.xzheng.tools.HighlightTest.java

License:Apache License

public void testHits() throws Exception {
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(TestUtil.getBookIndexDirectory()));
    TermQuery query = new TermQuery(new Term("title", "action"));
    TopDocs hits = searcher.search(query, 10);

    QueryScorer scorer = new QueryScorer(query, "title");
    Highlighter highlighter = new Highlighter(scorer);
    highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));

    Analyzer analyzer = new SimpleAnalyzer(Version.LUCENE_46);

    for (ScoreDoc sd : hits.scoreDocs) {
        Document doc = searcher.doc(sd.doc);
        String title = doc.get("title");

        TokenStream stream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, "title", doc,
                analyzer);/*from  w ww  .j  a v a  2s  .c  o m*/
        String fragment = highlighter.getBestFragment(stream, title);

        System.out.println(fragment);
    }
}

From source file:com.mathworks.xzheng.tools.RegexQueryTest.java

License:Apache License

public void testRegexQuery() throws Exception {
    Directory directory = TestUtil.getBookIndexDirectory();
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(directory));
    RegexQuery q = new RegexQuery(new Term("title", ".*st.*"));
    TopDocs hits = searcher.search(q, 10);
    assertEquals(2, hits.totalHits);/*from  w ww  .  j  a v  a  2  s . c  o m*/
    assertTrue(TestUtil.hitsIncludeTitle(searcher, hits, "Tapestry in Action"));
    assertTrue(
            TestUtil.hitsIncludeTitle(searcher, hits, "Mindstorms: Children, Computers, And Powerful Ideas"));

    directory.close();
}

From source file:com.mathworks.xzheng.tools.remote.SearchServer.java

License:Apache License

public static void main(String[] args) throws Exception {
    if (args.length != 1) {
        System.err.println("Usage: SearchServer <basedir>");
        System.exit(-1);//  w ww .  java 2 s  . c  o  m
    }

    String basedir = args[0]; //1
    Directory[] dirs = new Directory[ALPHABET.length()];
    IndexReader[] searchables = new IndexReader[ALPHABET.length()];
    for (int i = 0; i < ALPHABET.length(); i++) {
        dirs[i] = FSDirectory.open(new File(basedir, "" + ALPHABET.charAt(i)));
        searchables[i] = DirectoryReader.open(dirs[i]); //2
    }

    LocateRegistry.createRegistry(1099); //3

    IndexSearcher multiSearcher = new IndexSearcher(new MultiReader(searchables)); //4

    ExecutorService pool = Executors.newFixedThreadPool(nThreads);

    IndexSearcher multiImpl = //4
            new IndexSearcher(multiSearcher); //4
    Naming.rebind("//localhost/LIA_Multi", multiImpl); //4

    Searcher parallelSearcher = //5
            new ParallelMultiSearcher(searchables); //5
    RemoteSearchable parallelImpl = //5
            new RemoteSearchable(parallelSearcher); //5
    Naming.rebind("//localhost/LIA_Parallel", parallelImpl);//5

    System.out.println("Server started");

    for (int i = 0; i < ALPHABET.length(); i++) {
        dirs[i].close();
    }
}

From source file:com.meizu.nlp.classification.utils.DataSplitterTest.java

License:Apache License

public static void assertSplit(LeafReader originalIndex, double testRatio, double crossValidationRatio,
        String... fieldNames) throws Exception {

    BaseDirectoryWrapper trainingIndex = newDirectory();
    BaseDirectoryWrapper testIndex = newDirectory();
    BaseDirectoryWrapper crossValidationIndex = newDirectory();

    try {/*from w  ww.j a  va2  s . c  o m*/
        DatasetSplitter datasetSplitter = new DatasetSplitter(testRatio, crossValidationRatio);
        datasetSplitter.split(originalIndex, trainingIndex, testIndex, crossValidationIndex,
                new MockAnalyzer(random()), fieldNames);

        assertNotNull(trainingIndex);
        assertNotNull(testIndex);
        assertNotNull(crossValidationIndex);

        DirectoryReader trainingReader = DirectoryReader.open(trainingIndex);
        assertTrue((int) (originalIndex.maxDoc() * (1d - testRatio - crossValidationRatio)) == trainingReader
                .maxDoc());
        DirectoryReader testReader = DirectoryReader.open(testIndex);
        assertTrue((int) (originalIndex.maxDoc() * testRatio) == testReader.maxDoc());
        DirectoryReader cvReader = DirectoryReader.open(crossValidationIndex);
        assertTrue((int) (originalIndex.maxDoc() * crossValidationRatio) == cvReader.maxDoc());

        trainingReader.close();
        testReader.close();
        cvReader.close();
        closeQuietly(trainingReader);
        closeQuietly(testReader);
        closeQuietly(cvReader);
    } finally {
        if (trainingIndex != null) {
            trainingIndex.close();
        }
        if (testIndex != null) {
            testIndex.close();
        }
        if (crossValidationIndex != null) {
            crossValidationIndex.close();
        }
    }
}

From source file:com.meltmedia.cadmium.search.SearchContentPreprocessor.java

License:Apache License

@Override
public synchronized void processFromDirectory(String metaDir) throws Exception {
    SearchHolder newStagedSearcher = new SearchHolder();
    indexDir = new File(metaDir, "lucene-index");
    dataDir = new File(metaDir).getParentFile();
    newStagedSearcher.directory = new NIOFSDirectory(indexDir);
    IndexWriter iwriter = null;//  w  w w .j a v  a 2s  .  c  om
    try {
        iwriter = new IndexWriter(newStagedSearcher.directory,
                new IndexWriterConfig(Version.LUCENE_43, analyzer).setRAMBufferSizeMB(5));
        iwriter.deleteAll();
        writeIndex(iwriter, dataDir);
    } finally {
        IOUtils.closeQuietly(iwriter);
        iwriter = null;
    }
    newStagedSearcher.indexReader = DirectoryReader.open(newStagedSearcher.directory);
    SearchHolder oldStage = stagedSearch;
    stagedSearch = newStagedSearcher;
    if (oldStage != null) {
        oldStage.close();
    }
    log.info("About to call processSearchPreprocessors()");
    processSearchPreprocessors(newStagedSearcher.indexReader, analyzer, "content");
}

From source file:com.meltwater.elasticsearch.index.BatchPercolatorService.java

License:Apache License

private Map<String, QueryAndSource> filterQueriesToSearchWith(
        ConcurrentMap<String, QueryAndSource> percolateQueries, Directory directory) throws IOException {
    Map<String, QueryAndSource> filteredQueries = new HashMap<>();

    try (DirectoryReader reader = DirectoryReader.open(directory)) {
        for (Map.Entry<String, QueryAndSource> entry : percolateQueries.entrySet()) {
            if (hasDocumentMatchingFilter(reader, entry.getValue().getLimitingFilter())) {
                filteredQueries.put(entry.getKey(), entry.getValue());
            }/*from ww  w  .  j a va  2 s  . com*/
        }
    }
    return filteredQueries;
}

From source file:com.meltwater.elasticsearch.index.BatchPercolatorService.java

License:Apache License

private SearchContext createSearchContext(BatchPercolateShardRequest request,
        IndexService percolateIndexService, IndexShard indexShard, Directory directory) throws IOException {
    SearchShardTarget searchShardTarget = new SearchShardTarget(clusterService.localNode().id(),
            request.shardId().getIndex(), request.shardId().id());
    return new DefaultSearchContext(0,
            new ShardSearchLocalRequest(new ShardId("local_index", 0), 0, SearchType.QUERY_AND_FETCH, null,
                    null, false),/*  ww  w  .  ja v a  2 s . c om*/
            searchShardTarget, new DocSearcher(new IndexSearcher(DirectoryReader.open(directory))),
            percolateIndexService, indexShard, scriptService, cacheRecycler, pageCacheRecycler, bigArrays,
            Counter.newCounter());
}

From source file:com.mikeqian.search.SearchFiles.java

License:Apache License

/**
 * Simple command-line based search demo.
 *//*from w w  w .j  ava  2  s .  c  o m*/
public static void main(String[] args) throws Exception {
    String index = System.getProperty("java.io.tmpdir", "tmp") + System.getProperty("file.separator")
            + "index-dir";

    System.out.println(index);
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);

    WordConfTools.set("dic.path", "classpath:dic.txt,classpath:dic_CN.txt");
    Analyzer analyzer = new ChineseWordAnalyzer();

    BufferedReader in = null;
    if (queries != null) {
        in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8);
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    }
    QueryParser parser = new QueryParser(field, analyzer);
    while (true) {
        if (queries == null && queryString == null) { // prompt the user
            System.out.println("Enter query: ");
        }

        String line = queryString != null ? queryString : in.readLine();

        if (line == null || line.length() == -1) {
            break;
        }

        line = line.trim();
        if (line.length() == 0) {
            break;
        }

        Query query = parser.parse(line);
        System.out.println("Searching for: " + query.toString(field));

        if (repeat > 0) { // repeat & time as benchmark
            Date start = new Date();
            for (int i = 0; i < repeat; i++) {
                searcher.search(query, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

        if (queryString != null) {
            break;
        }
    }
    reader.close();
}

From source file:com.miliworks.virgo.test.LuceneIndexAndSearchDemo.java

License:Apache License

/**
 * //  w w  w .  ja v a 2  s  . co m
 * ???
 * @param args
 */
public static void main(String[] args) {
    //Lucene Document??
    String fieldName = "text";
    //
    String text = "IK Analyzer???????";

    //IKAnalyzer?
    Analyzer analyzer = new IKAnalyzer(true);

    Directory directory = null;
    IndexWriter iwriter = null;
    IndexReader ireader = null;
    IndexSearcher isearcher = null;
    try {
        //
        directory = new RAMDirectory();

        //?IndexWriterConfig
        IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_40, analyzer);
        iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
        iwriter = new IndexWriter(directory, iwConfig);
        //
        Document doc = new Document();
        doc.add(new StringField("ID", "10000", Field.Store.YES));
        doc.add(new TextField(fieldName, text, Field.Store.YES));
        iwriter.addDocument(doc);
        iwriter.close();

        //?**********************************
        //?   
        ireader = DirectoryReader.open(directory);
        isearcher = new IndexSearcher(ireader);

        String keyword = "?";
        //QueryParser?Query
        QueryParser qp = new QueryParser(Version.LUCENE_40, fieldName, analyzer);
        qp.setDefaultOperator(QueryParser.AND_OPERATOR);
        Query query = qp.parse(keyword);
        System.out.println("Query = " + query);

        //?5?
        TopDocs topDocs = isearcher.search(query, 5);
        System.out.println("" + topDocs.totalHits);
        //
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (int i = 0; i < topDocs.totalHits; i++) {
            Document targetDoc = isearcher.doc(scoreDocs[i].doc);
            System.out.println("" + targetDoc.toString());
        }

    } catch (CorruptIndexException e) {
        e.printStackTrace();
    } catch (LockObtainFailedException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    } catch (ParseException e) {
        e.printStackTrace();
    } finally {
        if (ireader != null) {
            try {
                ireader.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        if (directory != null) {
            try {
                directory.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

From source file:com.mycompany.lucenedemo.SearchFiles.java

/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
    String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage] [-sim vsm or bm25]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
    if (args.length == 0 || (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0])))) {
        System.out.println(usage);
        System.exit(0);/*ww  w  . j a v a 2 s . co  m*/
    }

    String index = "index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;
    SimilarityScore score = SimilarityScore.DEFAULT;

    for (int i = 0; i < args.length; i++) {
        if ("-index".equals(args[i])) {
            index = args[i + 1];
            i++;
        } else if ("-field".equals(args[i])) {
            field = args[i + 1];
            i++;
        } else if ("-queries".equals(args[i])) {
            queries = args[i + 1];
            i++;
        } else if ("-query".equals(args[i])) {
            queryString = args[i + 1];
            i++;
        } else if ("-repeat".equals(args[i])) {
            repeat = Integer.parseInt(args[i + 1]);
            i++;
        } else if ("-raw".equals(args[i])) {
            raw = true;
        } else if ("-paging".equals(args[i])) {
            hitsPerPage = Integer.parseInt(args[i + 1]);
            if (hitsPerPage <= 0) {
                System.err.println("There must be at least 1 hit per page.");
                System.exit(1);
            }
            i++;
        } else if ("-sim".equals(args[i])) {
            if (args[i + 1].equals("vsm")) {
                score = SimilarityScore.VSM;
            } else {
                score = SimilarityScore.BM25;
            }
        }
    }

    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    if (queries != null) {
        in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8);
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    }
    QueryParser parser = new QueryParser(field, analyzer);

    while (true) {
        if (queries == null && queryString == null) { // prompt the user
            System.out.println("Enter query: ");
        }

        String line = queryString != null ? queryString : in.readLine();

        if (line == null || line.length() == -1) {
            break;
        }

        line = line.trim();
        if (line.length() == 0) {
            break;
        }

        Query query = parser.parse(line);
        System.out.println("Searching for: " + query.toString(field));

        switch (score) {
        case DEFAULT:
            break;
        case VSM:
            searcher.setSimilarity(new ClassicSimilarity());
            break;
        case BM25:
            searcher.setSimilarity(new BM25Similarity());
            break;
        }

        if (repeat > 0) { // repeat & time as benchmark
            Date start = new Date();
            for (int i = 0; i < repeat; i++) {
                searcher.search(query, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

        if (queryString != null) {
            break;
        }
    }
    reader.close();
}