Example usage for org.apache.lucene.search IndexSearcher IndexSearcher

Introduction

In this page you can find the example usage for org.apache.lucene.search IndexSearcher IndexSearcher.

Prototype

public IndexSearcher(IndexReaderContext context) 

Source Link

Document

Creates a searcher searching the provided top-level IndexReaderContext .

Usage

From source file:com.aurel.track.lucene.search.LuceneSearcher.java

License:Open Source License

/**
 * Prepares an Indexsearcher object for an Index
 * @param index/*from   www .ja  va  2  s.co  m*/
 * @return
 */
public static IndexSearcher getIndexSearcher(int index) {
    Directory indexDir = LuceneUtil.getIndexDirectory(index);
    if (indexDir == null) {
        LOGGER.error("The index directory for " + index + " doesn't exist or is not a directory");
        return null;
    }
    //initialize the searcher
    //we will initialize always a new searcher because the data should be up to date
    /*
     *    Lucene FAQ: 
     *    1.   Make sure to open a new IndexSearcher after adding documents. 
     *       An IndexSearcher will only see the documents that were in the index in the moment it was opened.
     *    2.   It is recommended to use only one IndexSearcher from all threads in order to save memory
     *    Thanks for your help :) 
     */
    IndexSearcher is = null;
    try {
        IndexReader indexReader = DirectoryReader.open(indexDir);
        is = new IndexSearcher(indexReader);
    } catch (IOException e) {
        LOGGER.warn("Initializing the IndexSearcher for index " + index + " failed with " + e.getMessage());
        LOGGER.debug(ExceptionUtils.getStackTrace(e));
    }
    return is;
}

---

From source file:com.bah.lucene.BaseDirectoryTestSuite.java

License:Apache License

@Test
public void testCreateIndex() throws IOException {
    long s = System.nanoTime();
    IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_43, new KeywordAnalyzer());
    FSDirectory control = FSDirectory.open(fileControl);
    Directory dir = getControlDir(control, directory);
    // The serial merge scheduler can be useful for debugging.
    // conf.setMergeScheduler(new SerialMergeScheduler());
    IndexWriter writer = new IndexWriter(dir, conf);
    int numDocs = 10000;
    DirectoryReader reader = null;/*  www  .  j  a  va2s . c  om*/
    for (int i = 0; i < 100; i++) {
        if (reader == null) {
            reader = DirectoryReader.open(writer, true);
        } else {
            DirectoryReader old = reader;
            reader = DirectoryReader.openIfChanged(old, writer, true);
            if (reader == null) {
                reader = old;
            } else {
                old.close();
            }
        }
        assertEquals(i * numDocs, reader.numDocs());
        IndexSearcher searcher = new IndexSearcher(reader);
        NumericRangeQuery<Integer> query = NumericRangeQuery.newIntRange("id", 42, 42, true, true);
        TopDocs topDocs = searcher.search(query, 10);
        assertEquals(i, topDocs.totalHits);
        addDocuments(writer, numDocs);
    }
    writer.close(false);
    reader.close();
    long e = System.nanoTime();
    System.out.println("Total time [" + (e - s) / 1000000.0 + " ms]");
}

---

From source file:com.bah.lucene.blockcache_v2.CacheDirectoryTest.java

License:Apache License

@Test
public void test3() throws IOException, InterruptedException {
    // Thread.sleep(30000);
    IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_43, new KeywordAnalyzer());
    IndexWriter writer = new IndexWriter(_cacheDirectory, conf);
    int docs = 100000;
    for (int i = 0; i < docs; i++) {
        if (i % 500 == 0) {
            System.out.println(i);
        }/*from   w  w  w  .  j a va  2s  . c  o m*/
        writer.addDocument(newDoc());
        // Thread.sleep(1);
    }
    writer.close();
    System.out.println("done writing");

    DirectoryReader reader = DirectoryReader.open(_cacheDirectory);
    System.out.println("done opening");
    assertEquals(docs, reader.numDocs());

    Document document = reader.document(0);
    System.out.println("done fetching");
    System.out.println(document);

    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("test", "test")), 10);
    System.out.println("done searching");
    assertEquals(docs, topDocs.totalHits);

    reader.close();
}

---

From source file:com.basistech.lucene.tools.LuceneQueryTool.java

License:Apache License

private void runQuery(String queryString, final PrintStream out)
        throws IOException, org.apache.lucene.queryparser.classic.ParseException {
    final IndexSearcher searcher = new IndexSearcher(indexReader);
    docsPrinted = 0;/*  w w w.j av a  2  s . co m*/
    Query query;
    if (queryString == null) {
        query = new MatchAllDocsQuery();
    } else {
        if (!queryString.contains(":") && defaultField == null) {
            throw new RuntimeException("query has no ':' and no query-field defined");
        }
        QueryParser queryParser = new QueryParser(defaultField, analyzer);
        queryParser.setLowercaseExpandedTerms(false);
        query = queryParser.parse(queryString).rewrite(indexReader);
        Set<Term> terms = Sets.newHashSet();
        query.createWeight(searcher, false).extractTerms(terms);
        List<String> invalidFieldNames = Lists.newArrayList();
        for (Term term : terms) {
            if (!allFieldNames.contains(term.field())) {
                invalidFieldNames.add(term.field());
            }
        }
        if (!invalidFieldNames.isEmpty()) {
            throw new RuntimeException("Invalid field names: " + invalidFieldNames);
        }
    }

    final Set<String> fieldSet = Sets.newHashSet(fieldNames);

    // use a Collector instead of TopDocs for memory efficiency, especially
    // for the %all query
    class MyCollector extends SimpleCollector {
        private Scorer scorer;
        private long totalHits;
        private int docBase;

        @Override
        protected void doSetNextReader(LeafReaderContext context) throws IOException {
            docBase = context.docBase;
        }

        @Override
        public void collect(int id) throws IOException {
            totalHits++;
            if (docsPrinted >= outputLimit) {
                return;
            }

            id += docBase;
            Document doc = fieldSet.isEmpty() ? searcher.doc(id) : searcher.doc(id, fieldSet);
            boolean passedFilter = regexField == null;
            if (regexField != null) {
                String value = doc.get(regexField);
                if (value != null && regex.matcher(value).matches()) {
                    passedFilter = true;
                }
            }
            if (passedFilter) {
                float score = scorer.score();
                printDocument(doc, id, score, out);
            }
        }

        @Override
        public boolean needsScores() {
            return true;
        }

        @Override
        public void setScorer(Scorer scorer) throws IOException {
            this.scorer = scorer;
        }
    }

    MyCollector collector = new MyCollector();
    searcher.search(query, collector);
    if (showHits) {
        out.println("totalHits: " + collector.totalHits);
        out.println();
    }
}

---

From source file:com.bdaum.zoom.lal.internal.lucene.Lucene.java

License:Open Source License

private static Document getDocumentById(IndexReader indexReader, String searchString) throws IOException {
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);
    Analyzer analyzer = new KeywordAnalyzer();
    QueryParser queryParser = new QueryParser(DocumentBuilder.FIELD_NAME_IDENTIFIER, analyzer);
    try {/*  ww  w .j  a v  a2 s  .  co  m*/
        Query query = queryParser.parse(searchString);
        TopDocs topdocs = indexSearcher.search(query, 1);
        if (topdocs.totalHits > 0)
            return indexReader.document(topdocs.scoreDocs[0].doc);
    } catch (org.apache.lucene.queryparser.classic.ParseException e) {
        // should never happen
    }
    return null;
}

---

From source file:com.bdaum.zoom.lal.internal.lucene.Lucene.java

License:Open Source License

@Override
public ISearchHits search(File indexPath, TextSearchOptions_type options) throws IOException, ParseException {
    Object readerToken = null;//from   w  w w  .j  a  va 2 s. c  o  m
    try {
        if (indexPath != null) {
            readerToken = getIndexReaderToken(indexPath);
            if (readerToken != null) {
                IndexReader indexReader = readerMap.get(readerToken);
                if (indexReader != null) {
                    IndexSearcher searcher = searcherMap.get(readerToken);
                    if (searcher == null)
                        searcherMap.put(readerToken, searcher = new IndexSearcher(indexReader));
                    return new SearchHits(indexReader,
                            performSearch(searcher,
                                    LireActivator.getDefault().parseQuery(options.getQueryString()),
                                    options.getMaxResults(), Sort.RELEVANCE, true, true));
                }
            }
        }
        return null;
    } finally {
        if (readerToken != null)
            releaseIndexReader(indexPath, readerToken);
    }
}

---

From source file:com.berico.clavin.resolver.impl.lucene.LuceneComponentsFactory.java

License:Apache License

/**
 * Initialize the SearcherManager (and other components).
 * @return This object (it's needlessly fluent!).
 * @throws IOException /*from w w w .j  a  v a  2  s  .com*/
 */
public LuceneComponentsFactory initializeSearcher() throws IOException {

    initializeCommon();

    // instantiate an index searcher
    indexSearcher = new IndexSearcher(DirectoryReader.open(index));

    // override default TF/IDF score to ignore multiple appearances
    indexSearcher.setSimilarity(new BinarySimilarity());

    // Instantiate the searcher manager.
    searcherManager = new SearcherManager(index, null);

    // Do it.
    return this;
}

---

From source file:com.berico.clavin.resolver.lucene.LuceneLocationResolver.java

License:Apache License

/**
 * Builds a {@link LuceneLocationResolver} by loading a pre-built Lucene
 * index from disk and setting configuration parameters for
 * resolving location names to GeoName objects.
 * //from w  ww.  j a v a 2s  . c  om
 * @param indexDir            Lucene index directory to be loaded
 * @param maxHitDepth         number of candidate matches to consider
 * @param maxContextWindow      how much context to consider when resolving
 * @throws IOException
 * @throws ParseException
 */
public LuceneLocationResolver(File indexDir, int maxHitDepth, int maxContextWindow)
        throws IOException, ParseException {

    // load the Lucene index directory from disk
    index = FSDirectory.open(indexDir);

    // index employs simple lower-casing & tokenizing on whitespace
    indexAnalyzer = new WhitespaceLowerCaseAnalyzer();
    indexSearcher = new IndexSearcher(DirectoryReader.open(index));

    // override default TF/IDF score to ignore multiple appearances
    indexSearcher.setSimilarity(new BinarySimilarity());

    this.maxHitDepth = maxHitDepth;
    this.maxContextWindow = maxContextWindow;

    // run an initial throw-away query just to "prime the pump" for
    // the cache, so we can accurately measure performance speed
    // per: http://wiki.apache.org/lucene-java/ImproveSearchingSpeed
    indexSearcher.search(
            new AnalyzingQueryParser(Version.LUCENE_40, "indexName", indexAnalyzer).parse("Reston"), null,
            maxHitDepth, populationSort);
}

---

From source file:com.bericotech.clavin.gazetteer.query.LuceneGazetteer.java

License:Apache License

/**
 * Builds a {@link LuceneGazetteer} by loading a pre-built Lucene
 * index from disk and setting configuration parameters for
 * resolving location names to GeoName objects.
 *
 * @param indexDir              Lucene index directory to be loaded
 * @throws ClavinException      if an error occurs opening the index
 *//*from w w w .j a v  a 2  s .co  m*/
public LuceneGazetteer(final File indexDir) throws ClavinException {
    try {
        // load the Lucene index directory from disk
        index = FSDirectory.open(indexDir);

        indexSearcher = new IndexSearcher(DirectoryReader.open(index));

        // override default TF/IDF score to ignore multiple appearances
        indexSearcher.setSimilarity(new BinarySimilarity());

        // run an initial throw-away query just to "prime the pump" for
        // the cache, so we can accurately measure performance speed
        // per: http://wiki.apache.org/lucene-java/ImproveSearchingSpeed
        indexSearcher.search(
                new AnalyzingQueryParser(Version.LUCENE_4_9, INDEX_NAME.key(), INDEX_ANALYZER).parse("Reston"),
                null, DEFAULT_MAX_RESULTS, POPULATION_SORT);
    } catch (ParseException pe) {
        throw new ClavinException("Error executing priming query.", pe);
    } catch (IOException ioe) {
        throw new ClavinException("Error opening gazetteer index.", ioe);
    }
}

---

From source file:com.bewsia.script.LuceneHandler.java

License:Open Source License

public boolean exists(String id) {
    boolean tag = false;
    if (id.length() == 0)
        return tag;
    try {/*  ww w .  ja  v a 2s  . co  m*/
        IndexReader reader = IndexReader.open(FSDirectory.open(new File(dirIndex)));
        IndexSearcher searcher = new IndexSearcher(reader);
        TopDocs td = searcher.search(new TermQuery(new Term(SEntity.ID, id)), 1);
        if (td.totalHits > 0) {
            tag = true;
        }
        searcher.close();
        reader.close();
    } catch (Exception e) {
    }

    return tag;
}

---

• «
• 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
• 45
• 46
• 47
• 48
• »