Example usage for org.apache.lucene.search TopScoreDocCollector create

Introduction

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

Prototype

public static TopScoreDocCollector create(int numHits, int totalHitsThreshold) 

Source Link

Document

Creates a new TopScoreDocCollector given the number of hits to collect and the number of hits to count accurately.

Usage

From source file:com.leavesfly.lia.advsearching.TimeLimitingCollectorTest.java

License:Apache License

public void testTimeLimitingCollector() throws Exception {
    Directory dir = TestUtil.getBookIndexDirectory();
    IndexSearcher searcher = new IndexSearcher(dir);
    Query q = new MatchAllDocsQuery();
    int numAllBooks = TestUtil.hitCount(searcher, q);

    TopScoreDocCollector topDocs = TopScoreDocCollector.create(10, false);
    Collector collector = new TimeLimitingCollector(topDocs, // #A
            1000); // #A
    try {/* www  .ja  v a2  s .  c o m*/
        searcher.search(q, collector);
        assertEquals(numAllBooks, topDocs.getTotalHits()); // #B
    } catch (TimeExceededException tee) { // #C
        System.out.println("Too much time taken."); // #C
    } // #C
    searcher.close();
    dir.close();
}

---

From source file:com.mathworks.xzheng.advsearching.TimeLimitingCollectorTest.java

License:Apache License

public void testTimeLimitingCollector() throws Exception {
    Directory dir = TestUtil.getBookIndexDirectory();
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
    Query q = new MatchAllDocsQuery();
    int numAllBooks = TestUtil.hitCount(searcher, q);

    TopScoreDocCollector topDocs = TopScoreDocCollector.create(10, false);
    Collector collector = new TimeLimitingCollector(topDocs, // #A
            null, 1000); // #A
    try {//from  w  w w  . java  2  s  . c  o m
        searcher.search(q, collector);
        assertEquals(numAllBooks, topDocs.getTotalHits()); // #B
    } catch (TimeExceededException tee) { // #C
        System.out.println("Too much time taken."); // #C
    } // #C

    dir.close();
}

---

From source file:com.paladin.action.SearchAction.java

License:Apache License

/**
 * search using lucene//from   ww w.  j  a v a 2  s .  c  o  m
 *
 * @param jsonObject
 * @param request
 * @param _query
 * @throws IOException
 * @throws ParseException
 */

private void _search(JSONObject jsonObject, HttpServletRequest request, String _query, String _table)
        throws IOException, ParseException, InvalidTokenOffsetsException {

    //  Bean ???
    final String index_dir = Constants.LUCENE_INDEX_ROOT + _table;

    IndexSearcher searcher = new IndexSearcher(FSDirectory.open(new File(index_dir)));
    QueryParser parser = new QueryParser(Version.LUCENE_33, INDEX_FIELDS, new IKAnalyzer(false));
    TopScoreDocCollector collector = TopScoreDocCollector.create(10000, true);

    for (String key : _query.split(" ")) {
        Query query = parser.parse(key);
        searcher.search(query, collector);

        //    IKSimilarity  
        searcher.setSimilarity(new IKSimilarity());

        // 
        int size = collector.getTotalHits();
        total_pages = (size + Constants.NUM_PER_PAGE_SEARCH - 1) / Constants.NUM_PER_PAGE_SEARCH;

        curr_page_number = getCurrentPage(request, 1, total_pages);

        // ?
        first_page = curr_page_number - 5 > 0 ? curr_page_number - 5 : 1;
        last_page = first_page + 10 >= total_pages ? total_pages : first_page + 10;

        // ?
        int begin = (curr_page_number - 1) * Constants.NUM_PER_PAGE_SEARCH;
        ScoreDoc[] score_docs = collector.topDocs(begin, Constants.NUM_PER_PAGE_SEARCH).scoreDocs;

        List<Document> doc_list = new ArrayList<Document>();
        for (ScoreDoc score_doc : score_docs)
            doc_list.add(searcher.doc(score_doc.doc));

        List<Map<String, String>> blog_list = getBlogListFromDocList(query, doc_list);

        jsonObject.put(_table + "_list", blog_list);
        jsonObject.put("p_start_" + _table, first_page);
        jsonObject.put("p_end_" + _table, last_page);
        jsonObject.put("curr_page_" + _table, curr_page_number);
        jsonObject.put("total_page_" + _table, total_pages);
        jsonObject.put("total_count_" + _table, size);
    }
}

---

From source file:com.partydj.search.LuceneSearchProvider.java

License:Open Source License

@Override
public Collection<MediaFile> find(Map<String, Collection<String>> queryParameters) {
    StringBuilder queryString = new StringBuilder();
    if (queryString == null || queryString.length() == 0) {
        return Collections.emptyList();
    } else {// w ww. j  a  v a2  s  .c  om
        String any = getFirst(queryParameters, ANY);
        if (any != null) {
            queryString.append(INDEX_ENCODER.encode(any));
        } else {
            //$MR todo
        }
        List<MediaFile> found = new ArrayList();
        try {
            Query query = new QueryParser(Version.LUCENE_CURRENT, ANY, analyzer).parse(queryString.toString());
            Integer hitsPerPage = getFirstInteger(queryParameters, MAX_RESULTS);
            if (hitsPerPage == null) {
                hitsPerPage = DEFAULT_MAX_RESULTS;
            }
            IndexSearcher searcher = new IndexSearcher(index, true);
            TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
            //$MR jaro-winlker scorer
            searcher.search(query, collector);
            ScoreDoc[] hits = collector.topDocs().scoreDocs;

            for (ScoreDoc hit : hits) {
                Document d = searcher.doc(hit.doc);
                found.add(indexToMediaFile.get(d));
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return found;
    }
}

---

From source file:com.scsb.crpro.lucene.SearchFiles.java

License:Apache License

/**
 * This demonstrates a typical paging search scenario, where the search engine presents 
 * pages of size n to the user. The user can then go to the next page if interested in
 * the next hits.//from w  ww .  j a  v  a 2 s  .  com
 * 
 * When the query is executed for the first time, then only enough results are collected
 * to fill 5 result pages. If the user wants to page beyond this limit, then the query
 * is executed another time and all hits are collected.
 * 
 */
public static void doPagingSearch(BufferedReader in, Searcher searcher, Query query, int hitsPerPage,
        boolean raw, boolean interactive) throws IOException {

    // Collect enough docs to show 5 pages
    TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false);
    searcher.search(query, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    int numTotalHits = collector.getTotalHits();
    System.out.println(numTotalHits + " total matching documents");

    int start = 0;
    int end = Math.min(numTotalHits, hitsPerPage);

    while (true) {
        if (end > hits.length) {
            System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
                    + " total matching documents collected.");
            System.out.println("Collect more (y/n) ?");
            String line = in.readLine();
            if (line.length() == 0 || line.charAt(0) == 'n') {
                break;
            }

            collector = TopScoreDocCollector.create(numTotalHits, false);
            searcher.search(query, collector);
            hits = collector.topDocs().scoreDocs;
        }

        end = Math.min(hits.length, start + hitsPerPage);

        for (int i = start; i < end; i++) {
            if (raw) { // output raw format
                System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
                continue;
            }

            Document doc = searcher.doc(hits[i].doc);
            String path = doc.get("path");
            if (path != null) {
                System.out.println((i + 1) + ". " + path);
                String title = doc.get("title");
                if (title != null) {
                    System.out.println("   Title: " + doc.get("title"));
                }
            } else {
                System.out.println((i + 1) + ". " + "No path for this document");
            }

        }

        if (!interactive) {
            break;
        }

        if (numTotalHits >= end) {
            boolean quit = false;
            while (true) {
                System.out.print("Press ");
                if (start - hitsPerPage >= 0) {
                    System.out.print("(p)revious page, ");
                }
                if (start + hitsPerPage < numTotalHits) {
                    System.out.print("(n)ext page, ");
                }
                System.out.println("(q)uit or enter number to jump to a page.");

                String line = in.readLine();
                if (line.length() == 0 || line.charAt(0) == 'q') {
                    quit = true;
                    break;
                }
                if (line.charAt(0) == 'p') {
                    start = Math.max(0, start - hitsPerPage);
                    break;
                } else if (line.charAt(0) == 'n') {
                    if (start + hitsPerPage < numTotalHits) {
                        start += hitsPerPage;
                    }
                    break;
                } else {
                    int page = Integer.parseInt(line);
                    if ((page - 1) * hitsPerPage < numTotalHits) {
                        start = (page - 1) * hitsPerPage;
                        break;
                    } else {
                        System.out.println("No such page");
                    }
                }
            }
            if (quit)
                break;
            end = Math.min(numTotalHits, start + hitsPerPage);
        }

    }

}

---

From source file:com.searchlocal.lucene.ContentSearcher.java

License:Open Source License

/** 
 * ? /*from   w w w .j av a 2s . c om*/
 * 
 * @param param ?
 * @param indexlocal ?
 * @return list 
 */
public static List<ResultBean> query(SearchParam param) throws IOException, LogicException {
    // ?
    String indexPath = param.getIndexPath();
    // 
    if (null == fsd) {
        fsd = SimpleFSDirectory.open(new File(indexPath));
    }
    List<ResultBean> beanList = new ArrayList<ResultBean>();
    try {
        // ?KeyWord
        Analyzer analyzer = new PaodingAnalyzer();
        QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content", analyzer);
        Query query;
        query = parser.parse(param.getKeyWord());

        TopScoreDocCollector collector = TopScoreDocCollector.create(100, true);
        // ?
        if (null == is) {
            is = new IndexSearcher(fsd, true);
        }
        is.search(query, collector);

        ScoreDoc[] scoreDoc = collector.topDocs().scoreDocs;

        SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color=\"red\">", "</font>");

        Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));
        highlighter.setTextFragmenter(new SimpleFragmenter(CONTENTS_SHOW_LENGTH));

        if (scoreDoc.length == 0) {
            return beanList;
        }
        int startRow = param.getStartRow();
        int endRow = param.getEndRow();
        endRow = scoreDoc.length > endRow ? endRow : scoreDoc.length;
        for (int i = startRow; i < endRow; i++) {
            Document doc = is.doc(scoreDoc[i].doc);
            String content = doc.get("content");
            // 
            TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(content));
            content = highlighter.getBestFragment(tokenStream, content);
            ResultBean bean = BeanUtil.getBean(doc, content);
            beanList.add(bean);
        }
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (InvalidTokenOffsetsException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (ParseException e) {
        e.printStackTrace();
    }
    return beanList;
}

---

From source file:com.searchlocal.lucene.ContentSearcher.java

License:Open Source License

/** 
 * ?//from ww w .  j a v a  2  s . c  o  m
 * 
 * @param param ?
 * @return int 
 */
public static int getCount(SearchParam param) throws IOException {
    // ?
    String indexPath = param.getIndexPath();
    FSDirectory fsd = SimpleFSDirectory.open(new File(indexPath));
    int count = 0;
    try {
        // ?
        Analyzer analyzer = new PaodingAnalyzer();
        QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "content", analyzer);

        // 
        Query query = parser.parse(param.getKeyWord());

        TopScoreDocCollector collector = TopScoreDocCollector.create(100, true);
        IndexSearcher is = new IndexSearcher(fsd, true);
        is.search(query, collector);
        ScoreDoc[] scoreDoc = collector.topDocs().scoreDocs;
        count = scoreDoc.length;
    } catch (ParseException e) {
        e.printStackTrace();
    }
    return count;
}

---

From source file:com.tilab.ca.sse.core.lucene.SimpleSearcher.java

License:Open Source License

private ScoreDoc[] getTopResults(Query query, int numResults) throws IOException {
    ScoreDoc[] hits;//ww w.  ja v a  2  s .c o  m
    LOG.debug("[getTopResults] - BEGIN");
    TopScoreDocCollector collector = TopScoreDocCollector.create(numResults, false);
    indexSearcher.search(query, collector);
    hits = collector.topDocs().scoreDocs;
    LOG.debug("[getTopResults] - END");
    return hits;
}

---

From source file:com.wrmsr.search.dsl.SearcherImpl.java

License:Apache License

@Override
public ScoreDoc[] search(Query query, Supplier<Float> scoreSupplier, int maxHits) throws IOException {
    Query scoredQuery = new ComputedScoreQuery(new DocSpecific.Composite(docSpecificSet), scoreSupplier, query);
    TopDocsCollector topDocsCollector = TopScoreDocCollector.create(maxHits, true);
    indexSearcher.search(scoredQuery, topDocsCollector);
    return topDocsCollector.topDocs().scoreDocs;
}

---

From source file:com.xiaomi.linden.core.search.LindenCoreImpl.java

License:Apache License

public LindenResult search(LindenSearchRequest request) throws IOException {
    SearcherTaxonomyManager.SearcherAndTaxonomy searcherAndTaxonomy = lindenNRTSearcherManager.acquire();
    try {/*  w w w  .jav  a  2s.c o m*/
        IndexSearcher indexSearcher = searcherAndTaxonomy.searcher;
        Filter filter = FilterConstructor.constructFilter(request.getFilter(), config);
        Sort sort = SortConstructor.constructSort(request, indexSearcher, config);
        indexSearcher.setSimilarity(config.getSearchSimilarityInstance());

        Query query = QueryConstructor.constructQuery(request.getQuery(), config);
        if (filter != null) {
            query = new FilteredQuery(query, filter);
        }

        int from = request.getOffset();
        int size = request.getLength();
        LindenResultParser resultParser = new LindenResultParser(config, request, indexSearcher,
                snippetGenerator, query, filter, sort);
        // very common search, no group, no facet, no early termination, no search time limit
        if (!request.isSetGroupParam() && !request.isSetFacet() && !request.isSetEarlyParam()
                && config.getSearchTimeLimit() <= 0) {
            TopDocs docs;
            if (sort != null) {
                docs = indexSearcher.search(query, from + size, sort);
            } else {
                docs = indexSearcher.search(query, from + size);
            }
            return resultParser.parse(docs, null, null, null);
        }

        // group param will suppress facet, group, early termination and search time limit parameters
        if (request.isSetGroupParam()) {
            String groupField = request.getGroupParam().getGroupField();
            GroupingSearch groupingSearch = new GroupingSearch(groupField);
            groupingSearch.setGroupDocsLimit(request.getGroupParam().getGroupInnerLimit());
            if (sort != null) {
                groupingSearch.setGroupSort(sort);
                groupingSearch.setSortWithinGroup(sort);
                groupingSearch.setFillSortFields(true);
            }
            groupingSearch.setCachingInMB(8.0, true);
            groupingSearch.setAllGroups(true);
            TopGroups<TopDocs> topGroupedDocs = groupingSearch.search(indexSearcher, query, 0, from + size);
            return resultParser.parse(null, topGroupedDocs, null, null);
        }

        TopDocsCollector topDocsCollector;
        if (sort != null) {
            topDocsCollector = TopFieldCollector.create(sort, from + size, null, true, false, false, false);
        } else {
            topDocsCollector = TopScoreDocCollector.create(from + size, false);
        }

        LindenDocsCollector lindenDocsCollector;
        if (request.isSetEarlyParam()) {
            MergePolicy mergePolicy = indexWriter.getConfig().getMergePolicy();
            Sort mergePolicySort = null;
            if (mergePolicy instanceof SortingMergePolicyDecorator) {
                mergePolicySort = ((SortingMergePolicyDecorator) mergePolicy).getSort();
            }
            EarlyTerminationCollector earlyTerminationCollector = new EarlyTerminationCollector(
                    topDocsCollector, mergePolicySort, request.getEarlyParam().getMaxNum());
            lindenDocsCollector = new LindenDocsCollector(earlyTerminationCollector);
        } else {
            lindenDocsCollector = new LindenDocsCollector(topDocsCollector);
        }

        Collector collector = lindenDocsCollector;
        if (config.getSearchTimeLimit() > 0) {
            collector = new TimeLimitingCollector(lindenDocsCollector, TimeLimitingCollector.getGlobalCounter(),
                    config.getSearchTimeLimit());
        }

        // no facet param
        if (!request.isSetFacet()) {
            indexSearcher.search(query, collector);
            return resultParser.parse(lindenDocsCollector.topDocs(), null, null, null);
        }

        // facet search
        LindenFacet facetRequest = request.getFacet();
        FacetsCollector facetsCollector = new FacetsCollector();
        lindenDocsCollector.wrap(facetsCollector);

        Facets facets = null;
        if (facetRequest.isSetDrillDownDimAndPaths()) {
            // drillDown or drillSideways
            DrillDownQuery drillDownQuery = new DrillDownQuery(facetsConfig, query);
            List<LindenFacetDimAndPath> drillDownDimAndPaths = facetRequest.getDrillDownDimAndPaths();
            for (int i = 0; i < drillDownDimAndPaths.size(); ++i) {
                String fieldName = drillDownDimAndPaths.get(i).dim;
                if (drillDownDimAndPaths.get(i).path != null) {
                    drillDownQuery.add(fieldName, drillDownDimAndPaths.get(i).path.split("/"));
                } else {
                    drillDownQuery.add(fieldName);
                }
            }

            // drillSideways
            if (facetRequest.getFacetDrillingType() == FacetDrillingType.DRILLSIDEWAYS) {
                DrillSideways dillSideways = new DrillSideways(indexSearcher, facetsConfig,
                        searcherAndTaxonomy.taxonomyReader);
                DrillSideways.DrillSidewaysResult drillSidewaysResult = dillSideways.search(drillDownQuery,
                        collector);
                facets = drillSidewaysResult.facets;
            } else {
                // drillDown
                indexSearcher.search(drillDownQuery, collector);
                facets = new FastTaxonomyFacetCounts(searcherAndTaxonomy.taxonomyReader, facetsConfig,
                        facetsCollector);
            }
        } else {
            indexSearcher.search(query, collector);
            // Simple facet browsing
            if (facetRequest.isSetFacetParams()) {
                facets = new FastTaxonomyFacetCounts(searcherAndTaxonomy.taxonomyReader, facetsConfig,
                        facetsCollector);
            }
        }
        return resultParser.parse(lindenDocsCollector.topDocs(), null, facets, facetsCollector);
    } catch (Exception e) {
        throw new IOException(Throwables.getStackTraceAsString(e));
    } finally {
        lindenNRTSearcherManager.release(searcherAndTaxonomy);
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• »