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

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

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.*
  5. IndexSearcher
  6. doc

Introduction

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

Prototype

public Document doc(int docID) throws IOException

Source Link

Document

Sugar for .getIndexReader().document(docID)

Usage

From source file:be.ugent.tiwi.sleroux.newsrec.newsreclib.recommend.recommenders.LuceneTermRecommender.java

License:Apache License

@Override
public List<RecommendedNewsItem> recommend(long userid, int start, int count) throws RecommendationException {
    IndexSearcher searcher = null;
    try {// w w w  .  java2 s .co  m
        Map<String, Double> terms = ratingsDao.getRatings(userid);
        Query query = buildQuery(terms);
        int hitsPerPage = count;

        TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);

        Filter filter = new SeenArticlesFilter(viewsDao, userid);
        searcher = manager.acquire();
        manager.maybeRefresh();
        searcher.search(query, filter, collector);

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

        int stop = (start + count < hits.length ? start + count : hits.length);
        List<RecommendedNewsItem> results = new ArrayList<>(stop - start);

        for (int i = start; i < stop; i++) {
            int docId = hits[i].doc;
            Document d = searcher.doc(docId);
            results.add(toNewsitem(d, docId, hits[i].score, "termRecommender"));
            //System.out.println(docId);
            //System.out.println(searcher.explain(query, docId).toString());
        }

        return results;

    } catch (RatingsDaoException | IOException ex) {
        logger.error(ex);
        throw new RecommendationException(ex);
    } finally {
        try {
            manager.release(searcher);
        } catch (IOException ex) {
            logger.error(ex);
        }
        searcher = null;
    }
}

From source file:be.ugent.tiwi.sleroux.newsrec.newsreclib.recommend.recommenders.PersonalAndTrendingRecommender.java

License:Apache License

@Override
public List<RecommendedNewsItem> recommend(long userid, int start, int count) throws RecommendationException {
    count = count / 2;//from   ww w.  ja v a  2  s.co m

    List<RecommendedNewsItem> results = super.recommend(userid, start, count);

    IndexSearcher searcher = null;
    try {
        Map<String, Double> terms = ratingsDao.getRatings(userid);
        Query query = buildQuery(terms);
        int hitsPerPage = start + count;

        TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);

        Filter f1 = new UniqueResultsFilter(results);
        Filter f2 = new RecentFilter("timestamp", 1000 * 60 * 60 * 24);
        Filter f = new ChainedFilter(new Filter[] { f1, f2 }, ChainedFilter.AND);

        searcher = manager.acquire();
        manager.maybeRefresh();
        searcher.search(query, f, collector);

        ScoreDoc[] hits = collector.topDocs(start, count).scoreDocs;

        for (ScoreDoc s : hits) {
            int docId = s.doc;
            Document d = searcher.doc(docId);
            RecommendedNewsItem item = toNewsitem(d, docId, s.score, "personal");
            results.add(item);
        }
        //Collections.sort(results);
    } catch (RatingsDaoException | IOException ex) {
        logger.error(ex);
        throw new RecommendationException(ex);
    }
    return results;
}

From source file:be.ugent.tiwi.sleroux.newsrec.newsreclib.recommend.recommenders.TopNRecommender.java

License:Apache License

@Override
public List<RecommendedNewsItem> recommend(long userid, int start, int count) throws RecommendationException {
    IndexSearcher searcher = null;
    try {/*from ww w  . j  av a  2  s  .c o  m*/
        List<Long> ids = viewsDao.getNMostSeenArticles(start, start + count);
        Query query = buildQuery(ids);
        int hitsPerPage = count;

        TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);

        Filter filter = new SeenArticlesFilter(viewsDao, userid);
        searcher = manager.acquire();
        searcher.search(query, filter, collector);

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

        int stop = (start + count < hits.length ? start + count : hits.length);
        List<RecommendedNewsItem> results = new ArrayList<>(stop - start);

        for (int i = start; i < stop; i++) {
            int docId = hits[i].doc;
            Document d = searcher.doc(docId);
            results.add(toNewsitem(d, docId, hits[i].score, "topN"));
        }

        return results;

    } catch (ViewsDaoException | IOException ex) {

        throw new RecommendationException(ex);
    } finally {
        if (searcher != null) {
            try {
                manager.release(searcher);
            } catch (IOException ex) {
                logger.error(ex);
            }
            searcher = null;
        }
    }
}

From source file:be.ugent.tiwi.sleroux.newsrec.newsreclib.recommend.recommenders.TrendingTopicRecommender.java

License:Apache License

@Override
public List<RecommendedNewsItem> recommend(long userid, int start, int count) throws RecommendationException {
    IndexSearcher searcher = null;
    try {//from   www  . j a va 2  s .co m
        String[] trends = trendsDao.getTrends(250);
        Query query = buildQuery(trends);
        int hitsPerPage = start + count;

        TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);

        //Filter filter = new SeenArticlesFilter(viewsDao, userid);
        Filter f = new RecentFilter("timestamp", 1000 * 60 * 60 * 24);

        manager.maybeRefresh();
        searcher = manager.acquire();

        searcher.search(query, f, collector);

        ScoreDoc[] hits = collector.topDocs(start, count).scoreDocs;

        List<RecommendedNewsItem> results = new ArrayList<>(hits.length);

        for (ScoreDoc hit : hits) {
            int docId = hit.doc;
            Document d = searcher.doc(docId);
            RecommendedNewsItem item = toNewsitem(d, docId, hit.score, "trending");
            results.add(item);
        }

        return results;

    } catch (TrendsDaoException | IOException ex) {
        logger.error(ex);
        throw new RecommendationException(ex);
    } finally {
        try {
            if (searcher != null) {
                manager.release(searcher);
            }
        } catch (IOException ex) {
            logger.error(ex);
        }
        searcher = null;
    }
}

From source file:book.Searcher.java

License:Apache License

public static void search(String indexDir, String q) throws IOException, ParseException {

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexDir).toPath()));
    IndexSearcher is = new IndexSearcher(reader);

    //alt: Directory dir = FSDirectory.open(new File(indexDir)); // 3
    //alt: IndexSearcher is = IndexSearcher(dir); // 3

    QueryParser parser = new QueryParser("contents", // 4
            new StandardAnalyzer()); // 4
    Query query = parser.parse(q); // 4
    long start = System.currentTimeMillis();
    TopDocs hits = is.search(query, 10); // 5
    long end = System.currentTimeMillis();

    System.err.println("Found " + hits.totalHits + // 6
            " document(s) (in " + (end - start) + // 6
            " milliseconds) that matched query '" + // 6
            q + "':"); // 6

    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc); // 7
        System.out.println(doc.get("fullpath")); // 8
    }/*from   ww w . ja  v a 2 s  . c o  m*/

    //was: is.close(); // 9
}

From source file:br.andrew.lucene.testing.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  2s .  co  m
 * 
 * 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(final BufferedReader in, final IndexSearcher searcher, final Query query,
        final int hitsPerPage, final boolean raw, final boolean interactive) throws IOException {

    // Collect enough docs to show 5 pages
    final TopDocs results = searcher.search(query, 5 * hitsPerPage);
    ScoreDoc[] hits = results.scoreDocs;

    final int numTotalHits = results.totalHits;
    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) ?");
            final String line = in.readLine();
            if (line.length() == 0 || line.charAt(0) == 'n') {
                break;
            }

            hits = searcher.search(query, numTotalHits).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;
            }

            final Document doc = searcher.doc(hits[i].doc);
            final String path = doc.get("path");
            if (path != null) {
                System.out.println((i + 1) + ". " + path);
                final 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 || end == 0) {
            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.");

                final 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 {
                    final 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:br.bireme.ngrams.CompareResults.java

private static void checkDocs(final String similarity, final String docId1, final String docId2,
        final IndexSearcher isearcher, final BufferedWriter bwriter) throws IOException {
    assert similarity != null;
    assert docId1 != null;
    assert docId2 != null;
    assert isearcher != null;
    assert bwriter != null;

    final Query query1 = new TermQuery(new Term("id", docId1));
    final Query query2 = new TermQuery(new Term("id", docId2));
    final TopDocs top1 = isearcher.search(query1, 1);
    final TopDocs top2 = isearcher.search(query2, 1);
    final ScoreDoc[] scores1 = top1.scoreDocs;
    final ScoreDoc[] scores2 = top2.scoreDocs;

    if ((scores1.length > 0) && (scores2.length > 0)) {
        final Document doc1 = isearcher.doc(scores1[0].doc);
        final Document doc2 = isearcher.doc(scores2[0].doc);

        writeDocDifferences(similarity, doc1, doc2, bwriter);
    }//from www  . jav a  2  s .  co  m
}

From source file:br.bireme.ngrams.NGrams.java

private static void searchRaw(final Parameters parameters, final IndexSearcher searcher,
        final NGAnalyzer analyzer, final NGramDistance ngDistance, final String text,
        final boolean useSimilarity, final Set<String> id_id, final Set<Result> results)
        throws IOException, ParseException {
    assert parameters != null;
    assert searcher != null;
    assert analyzer != null;
    assert ngDistance != null;
    assert id_id != null;
    assert results != null;

    if (text == null) {
        throw new NullPointerException("text");
    }// w ww . ja  v a  2s  .  c o m

    final String text2 = StringEscapeUtils.unescapeHtml4(text);
    final String[] param = text2.trim().split(" *\\| *", Integer.MAX_VALUE);
    if (param.length != parameters.nameFields.size()) {
        throw new IOException(text);
    }
    final String fname = parameters.indexed.name;
    final QueryParser parser = new QueryParser(fname, analyzer);
    final String ntext = Tools
            .limitSize(Tools.normalize(param[parameters.indexed.pos], OCC_SEPARATOR), MAX_NG_TEXT_SIZE).trim();
    final int MAX_RESULTS = 20;

    if (!ntext.isEmpty()) {
        final Query query = parser.parse(QueryParser.escape(ntext));
        final TopDocs top = searcher.search(query, MAX_RESULTS);
        final float lower = parameters.scores.first().minValue;
        ScoreDoc[] scores = top.scoreDocs;
        int remaining = MAX_RESULTS;

        for (ScoreDoc sdoc : scores) {
            if (remaining-- <= 0) {
                break; // Only for performance
            }
            final Document doc = searcher.doc(sdoc.doc);
            if (useSimilarity) {
                final String dname = doc.get(fname);
                if (dname == null) {
                    throw new IOException("dname");
                }
                final float similarity = ngDistance.getDistance(ntext, doc.get(fname));
                if (similarity < lower) {
                    if (remaining > 3) {
                        remaining = 3;
                        //System.out.println("Atualizando tot=" + tot + " score=" + sdoc.score + " similarity=" + similarity+ " text=" + doc.get(fname));
                    }
                } else {
                    final Result out = createResult(id_id, parameters, param, doc, ngDistance, similarity,
                            sdoc.score);
                    if (out != null) {
                        results.add(out);
                    }
                }
            } else {
                if (sdoc.score < 1.0) {
                    System.out.println("Saindo score=" + sdoc.score);
                    break; // Only for performance
                }
                final Result out = createResult(id_id, parameters, param, doc, ngDistance, 0, sdoc.score);
                if (out != null) {
                    results.add(out);
                }
            }
        }
    }
}

From source file:br.com.crawlerspring.model.Searcher.java

public List<br.com.crawlerspring.model.Document> parametrizeDocuments(String parameters) throws Exception {
    List<br.com.crawlerspring.model.Document> parametrizedDocuments = new ArrayList<br.com.crawlerspring.model.Document>();

    RegexQuery q = new RegexQuery(new Term("title", ".*" + parameters + ".*"));
    int hitsPerPage = 10;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
    searcher.search(q, collector);/* w w w .  ja  v  a2 s.  co m*/
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    for (int cont = 0; cont < hits.length; ++cont) {
        br.com.crawlerspring.model.Document document = new br.com.crawlerspring.model.Document();
        int docId = hits[cont].doc;
        org.apache.lucene.document.Document luceneDocument = searcher.doc(docId);
        document.setTitle(luceneDocument.get("title"));
        document.setContent(luceneDocument.get("content"));

        parametrizedDocuments.add(document);
    }
    return parametrizedDocuments;
}

From source file:br.usp.icmc.gazetteer.SemanticSearchTest.LuceneSearcher.java

License:Open Source License

public void busca(IndexSearcher reader, String q) throws ParseException, IOException {

    QueryParser parser = new QueryParser(Version.LUCENE_36, "content", a);
    Query query = parser.parse(q);
    TopDocs hits = reader.search(query, topK);
    ScoreDoc[] docs = hits.scoreDocs;// w w w .j av a2s.  c o  m
    // Iterate through the results:
    int i = 0;
    for (ScoreDoc d : docs) {

        Document doc = reader.doc(d.doc);
        documentospesquisados.add(new Documento(numQ, doc.get("filename"), 0));
    }

}