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

List of usage examples for org.apache.lucene.search IndexSearcher IndexSearcher

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.*
  5. IndexSearcher
  6. 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.ecyrd.jspwiki.search.LuceneSearchProvider.java

License:Apache License

/**
 *  Searches pages using a particular combination of flags.
 *
 *  @param query The query to perform in Lucene query language
 *  @param flags A set of flags/*from  w  w w . ja  v a2 s .  co  m*/
 *  @return A Collection of SearchResult instances
 *  @throws ProviderException if there is a problem with the backend
 */
public Collection findPages(String query, int flags) throws ProviderException {
    Searcher searcher = null;
    ArrayList<SearchResult> list = null;
    Highlighter highlighter = null;

    try {
        String[] queryfields = { LUCENE_PAGE_CONTENTS, LUCENE_PAGE_NAME, LUCENE_AUTHOR, LUCENE_ATTACHMENTS };
        QueryParser qp = new MultiFieldQueryParser(queryfields, getLuceneAnalyzer());

        //QueryParser qp = new QueryParser( LUCENE_PAGE_CONTENTS, getLuceneAnalyzer() );
        Query luceneQuery = qp.parse(query);

        if ((flags & FLAG_CONTEXTS) != 0) {
            highlighter = new Highlighter(new SimpleHTMLFormatter("<span class=\"searchmatch\">", "</span>"),
                    new SimpleHTMLEncoder(), new QueryScorer(luceneQuery));
        }

        try {
            searcher = new IndexSearcher(m_luceneDirectory);
        } catch (Exception ex) {
            log.info("Lucene not yet ready; indexing not started", ex);
            return null;
        }

        Hits hits = searcher.search(luceneQuery);

        list = new ArrayList<SearchResult>(hits.length());
        for (int curr = 0; curr < hits.length(); curr++) {
            Document doc = hits.doc(curr);
            String pageName = doc.get(LUCENE_ID);
            WikiPage page = m_engine.getPage(pageName, WikiPageProvider.LATEST_VERSION);

            if (page != null) {
                if (page instanceof Attachment) {
                    // Currently attachments don't look nice on the search-results page
                    // When the search-results are cleaned up this can be enabled again.
                }

                int score = (int) (hits.score(curr) * 100);

                // Get highlighted search contexts
                String text = doc.get(LUCENE_PAGE_CONTENTS);

                String[] fragments = new String[0];
                if (text != null && highlighter != null) {
                    TokenStream tokenStream = getLuceneAnalyzer().tokenStream(LUCENE_PAGE_CONTENTS,
                            new StringReader(text));
                    fragments = highlighter.getBestFragments(tokenStream, text, MAX_FRAGMENTS);

                }

                SearchResult result = new SearchResultImpl(page, score, fragments);
                list.add(result);
            } else {
                log.error("Lucene found a result page '" + pageName
                        + "' that could not be loaded, removing from Lucene cache");
                pageRemoved(new WikiPage(m_engine, pageName));
            }
        }
    } catch (IOException e) {
        log.error("Failed during lucene search", e);
    } catch (InstantiationException e) {
        log.error("Unable to get a Lucene analyzer", e);
    } catch (IllegalAccessException e) {
        log.error("Unable to get a Lucene analyzer", e);
    } catch (ClassNotFoundException e) {
        log.error("Specified Lucene analyzer does not exist", e);
    } catch (ParseException e) {
        log.info("Broken query; cannot parse", e);

        throw new ProviderException("You have entered a query Lucene cannot process: " + e.getMessage());
    } finally {
        if (searcher != null) {
            try {
                searcher.close();
            } catch (IOException e) {
            }
        }
    }

    return list;
}

From source file:com.eden.lucene.SearchFiles.java

License:Apache License

/** 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]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
    if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
        System.out.println(usage);
        System.exit(0);//  w w  w . ja va  2 s.  co  m
    }

    String basePath = "D:/test/lucene";

    String index = basePath + "/index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;

    /*  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++;
        }
      }*/

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);

    BufferedReader in = null;
    if (queries != null) {
        in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
    }
    QueryParser parser = new QueryParser(Version.LUCENE_46, 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, null, 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.edgenius.test.lucene.TestLucene.java

License:Open Source License

@Before
public void setUp() throws Exception {
    initWriter();//from  ww w .ja v  a 2  s  . c  om
    buildIndex();
    writer.optimize();
    writer.close();

    //searcher initial must after writer close!
    searcher = new IndexSearcher(FSDirectory.open(new File(indexDir)));
}

From source file:com.edu.lucene.SearchFiles.java

License:Apache License

/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
    String usage = "Usage:search [-index dir] [-field f] [-repeat n] [-queries file] [-raw] [-norms field] [-paging hitsPerPage]";
    usage += "\n\tSpecify 'false' for hitsPerPage to use streaming instead of paging search.";
    if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
        System.out.println(usage);
        System.exit(0);// w  ww .  j a  v a 2s . co m
    }

    String index = "index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String normsField = null;
    boolean paging = true;
    int hitsPerPage = 10;

    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 ("-repeat".equals(args[i])) {
            repeat = Integer.parseInt(args[i + 1]);
            i++;
        } else if ("-raw".equals(args[i])) {
            raw = true;
        } else if ("-norms".equals(args[i])) {
            normsField = args[i + 1];
            i++;
        } else if ("-paging".equals(args[i])) {
            if (args[i + 1].equals("false")) {
                paging = false;
            } else {
                hitsPerPage = Integer.parseInt(args[i + 1]);
                if (hitsPerPage == 0) {
                    paging = false;
                }
            }
            i++;
        }
    }

    IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)), true); // only searching, so
    // read-only=true

    if (normsField != null)
        reader = new OneNormsReader(reader, normsField);

    Searcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);

    BufferedReader in = null;
    if (queries != null) {
        in = new BufferedReader(new FileReader(queries));
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
    }
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, field, analyzer);
    while (true) {
        if (queries == null) // prompt the user
            System.out.println("Enter query: ");

        String line = 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, null, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        if (paging) {

            doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null);
        } else {
            doStreamingSearch(searcher, query);
        }
    }
    reader.close();
}

From source file:com.emental.mindraider.core.search.SearchEngine.java

License:Apache License

/**
 * Execute search using index./*ww  w . ja  v a 2s . co m*/
 * 
 * @param indexPath
 *            the index path
 * @param queryString
 *            the query string
 * @return Returns an array of <code>SearchResultEntry</code> otherwise
 *         null.
 */
public SearchResultEntry[] search(String queryString) {
    ArrayList<SearchResultEntry> result = new ArrayList<SearchResultEntry>();

    try {
        Searcher searcher = new IndexSearcher(indexPath);
        Analyzer analyzer = new StandardAnalyzer();

        String line = queryString;

        logger.debug("Query: " + line);
        QueryParser queryParser = new QueryParser("contents", analyzer);
        Query query = queryParser.parse(line);

        logger.debug("\nSearching for: '" + query.toString("contents") + "'");
        Hits hits = searcher.search(query);
        logger.debug("Search result: " + hits.length() + " total matching documents");

        for (int i = 0; i < hits.length(); i++) {
            Document doc = hits.doc(i);
            String path = doc.get("path");

            if (path != null) {
                logger.debug(i + ". " + path);
                // i'm interested only in concepts so filter out
                // non-concepts (HACK)
                // TODO this filter is here because of obsolete indexes -
                // there should be deleted
                if (path.indexOf(File.separator + "concepts" + File.separator) >= 0) {
                    result.add(new SearchResultEntry(doc.get("outlineLabel"), doc.get("conceptLabel"),
                            doc.get("path")));
                    //                   logger.debug("path:\n"+doc.get("path"));
                    //                   logger.debug("modified:\n"+doc.get("modified"));
                    //                   logger.debug("notebook:\n"+doc.get("outlineLabel"));
                    //                   logger.debug("concept:\n"+doc.get("conceptLabel"));
                }

            } else {
                String url = doc.get("url");
                if (url != null) {
                    logger.debug(i + ". " + url);
                    logger.debug("   - " + doc.get("title"));
                } else {
                    logger.debug(i + ". " + "No path nor URL for this document");
                }
            }
        }
        searcher.close();

        return (SearchResultEntry[]) result.toArray(new SearchResultEntry[result.size()]);
    } catch (Exception e) {
        logger.error("Caught a " + e.getClass() + "\n with message: " + e.getMessage(), e);
    }
    return null;
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Queries a feature index of a project, specified by ID
 *
 * @param projectId ID of a project, which index to work with
 * @param query a query to search in index
 * @return a {List} of {@code FeatureIndexEntry} objects that satisfy index query
 * @deprecated/*from w  w  w .  ja v  a2  s .  c  o m*/
 * @throws IOException
 */
@Deprecated
private IndexSearchResult searchLuceneIndexForProject(final long projectId, Query query,
        List<String> vcfInfoFields, Integer maxResultsCount, Sort sort) throws IOException {
    Map<Integer, FeatureIndexEntry> entryMap = new LinkedHashMap<>();

    int totalHits = 0;
    try (Directory index = fileManager.getIndexForProject(projectId);
            IndexReader reader = DirectoryReader.open(index)) {
        if (reader.numDocs() == 0) {
            return new IndexSearchResult(Collections.emptyList(), false, 0);
        }

        IndexSearcher searcher = new IndexSearcher(reader);
        final TopDocs docs;
        int resultsCount = maxResultsCount == null ? reader.numDocs() : maxResultsCount;
        if (sort == null) {
            docs = searcher.search(query, resultsCount);
        } else {
            docs = searcher.search(query, resultsCount, sort);
        }

        totalHits = docs.totalHits;
        final ScoreDoc[] hits = docs.scoreDocs;

        Map<Long, BookmarkIndexEntry> foundBookmarkEntries = new HashMap<>(); // for batch bookmarks loading
        createIndexEntries(hits, entryMap, foundBookmarkEntries, searcher, vcfInfoFields);
        setBookmarks(foundBookmarkEntries);
    } catch (IOException e) {
        LOGGER.error(MessageHelper.getMessage(MessagesConstants.ERROR_FEATURE_INDEX_SEARCH_FAILED), e);
        return new IndexSearchResult(Collections.emptyList(), false, 0);
    }

    return new IndexSearchResult(new ArrayList<>(entryMap.values()),
            maxResultsCount != null && totalHits > maxResultsCount, totalHits);
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Queries a feature index of a list of files
 *
 * @param files a {@link List} of {@link FeatureFile}, which indexes to search
 * @param query a query to search in index
 * @param vcfInfoFields list of info fields to retrieve
 * @param maxResultsCount specifies a maximum number of search results to get
 * @param sort specifies sorting// w ww.  j a va  2s  . c  o m
 * @return a {List} of {@code FeatureIndexEntry} objects that satisfy index query
 * @throws IOException if something is wrong in the filesystem
 */
public <T extends FeatureIndexEntry> IndexSearchResult<T> searchFileIndexes(List<? extends FeatureFile> files,
        Query query, List<String> vcfInfoFields, Integer maxResultsCount, Sort sort) throws IOException {
    if (CollectionUtils.isEmpty(files)) {
        return new IndexSearchResult<>(Collections.emptyList(), false, 0);
    }

    Map<Integer, FeatureIndexEntry> entryMap = new LinkedHashMap<>();

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return new IndexSearchResult<>(Collections.emptyList(), false, 0);
        }

        IndexSearcher searcher = new IndexSearcher(reader);
        final TopDocs docs = performSearch(searcher, query, reader, maxResultsCount, sort);

        int totalHits = docs.totalHits;
        final ScoreDoc[] hits = docs.scoreDocs;

        Map<Long, BookmarkIndexEntry> foundBookmarkEntries = new HashMap<>(); // for batch bookmarks loading
        createIndexEntries(hits, entryMap, foundBookmarkEntries, searcher, vcfInfoFields);
        setBookmarks(foundBookmarkEntries);

        return new IndexSearchResult<>(new ArrayList<T>((Collection<? extends T>) entryMap.values()),
                maxResultsCount != null && totalHits > maxResultsCount, totalHits);
    } finally {
        for (SimpleFSDirectory index : indexes) {
            IOUtils.closeQuietly(index);
        }
    }
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Queries a feature index of a list of files, returning specified page of specified size.
 * If no paging parameters are passed, returns all results
 *
 * @param files a {@link List} of {@link FeatureFile}, which indexes to search
 * @param query a query to search in index
 * @param vcfInfoFields list of info fields to retrieve
 * @param page number of a page to display
 * @param pageSize number of entries per page
 * @param orderBy object, that specifies sorting
 * @return a {List} of {@code FeatureIndexEntry} objects that satisfy index query
 * @throws IOException if something is wrong in the filesystem
 *///from   w  w  w . j av a 2 s. c o m
public <T extends FeatureIndexEntry> IndexSearchResult<T> searchFileIndexesPaging(
        List<? extends FeatureFile> files, Query query, List<String> vcfInfoFields, Integer page,
        Integer pageSize, List<VcfFilterForm.OrderBy> orderBy) throws IOException {

    if (CollectionUtils.isEmpty(files)) {
        return new IndexSearchResult<>(Collections.emptyList(), false, 0);
    }

    List<FeatureIndexEntry> entries;

    int totalHits = 0;
    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return new IndexSearchResult<>(Collections.emptyList(), false, 0);
        }

        IndexSearcher searcher = new IndexSearcher(reader);
        GroupingSearch groupingSearch = new GroupingSearch(FeatureIndexFields.UID.fieldName);
        setSorting(orderBy, groupingSearch, files);

        TopGroups<String> topGroups = groupingSearch.search(searcher, query,
                page == null ? 0 : (page - 1) * pageSize, page == null ? reader.numDocs() : pageSize);

        final ScoreDoc[] hits = new ScoreDoc[topGroups.groups.length];
        for (int i = 0; i < topGroups.groups.length; i++) {
            hits[i] = topGroups.groups[i].scoreDocs[0];
        }

        entries = new ArrayList<>(hits.length);
        for (ScoreDoc hit : hits) {
            entries.add(createIndexEntry(hit, new HashMap<>(), searcher, vcfInfoFields));
        }
    } finally {
        for (SimpleFSDirectory index : indexes) {
            IOUtils.closeQuietly(index);
        }
    }

    return new IndexSearchResult<>((List<T>) entries, false, totalHits);
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

public int getTotalVariationsCountFacet(List<? extends FeatureFile> files, Query query) throws IOException {
    if (CollectionUtils.isEmpty(files)) {
        return 0;
    }/*  www. ja va 2  s. com*/

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return 0;
        }

        FacetsCollector facetsCollector = new FacetsCollector();
        IndexSearcher searcher = new IndexSearcher(reader);
        searcher.search(query, facetsCollector);

        Facets facets = new SortedSetDocValuesFacetCounts(
                new DefaultSortedSetDocValuesReaderState(reader, FeatureIndexFields.FACET_UID.fieldName),
                facetsCollector);
        FacetResult res = facets.getTopChildren(reader.numDocs(), FeatureIndexFields.F_UID.getFieldName());
        if (res == null) {
            return 0;
        }

        return res.childCount;
    } finally {
        for (SimpleFSDirectory index : indexes) {
            IOUtils.closeQuietly(index);
        }
    }
}

From source file:com.epam.catgenome.dao.index.FeatureIndexDao.java

License:Open Source License

/**
 * Groups variations from specified {@link List} of {@link VcfFile}s by specified field
 * @param files a {@link List} of {@link FeatureFile}, which indexes to search
 * @param query a query to search in index
 * @param groupBy a field to perform grouping
 * @return a {@link List} of {@link Group}s, mapping field value to number of variations, having this value
 * @throws IOException if something goes wrong with the file system
 *///from w  ww  . ja  va  2s.  co  m
public List<Group> groupVariations(List<VcfFile> files, Query query, String groupBy) throws IOException {
    List<Group> res = new ArrayList<>();

    if (CollectionUtils.isEmpty(files)) {
        return Collections.emptyList();
    }

    SimpleFSDirectory[] indexes = fileManager.getIndexesForFiles(files);

    try (MultiReader reader = openMultiReader(indexes)) {
        if (reader.numDocs() == 0) {
            return Collections.emptyList();
        }

        IndexSearcher searcher = new IndexSearcher(reader);
        AbstractGroupFacetCollector groupedFacetCollector = TermGroupFacetCollector
                .createTermGroupFacetCollector(FeatureIndexFields.UID.fieldName,
                        getGroupByField(files, groupBy), false, null, GROUP_INITIAL_SIZE);
        searcher.search(query, groupedFacetCollector); // Computing the grouped facet counts
        TermGroupFacetCollector.GroupedFacetResult groupedResult = groupedFacetCollector
                .mergeSegmentResults(reader.numDocs(), 1, false);
        List<AbstractGroupFacetCollector.FacetEntry> facetEntries = groupedResult.getFacetEntries(0,
                reader.numDocs());
        for (AbstractGroupFacetCollector.FacetEntry facetEntry : facetEntries) {
            res.add(new Group(facetEntry.getValue().utf8ToString(), facetEntry.getCount()));
        }
    } finally {
        for (SimpleFSDirectory index : indexes) {
            IOUtils.closeQuietly(index);
        }
    }

    return res;
}