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

Introduction

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

Prototype

public <C extends Collector, T> T search(Query query, CollectorManager<C, T> collectorManager)
        throws IOException 

Source Link

Document

Lower-level search API.

Usage

From source file:be.ugent.tiwi.sleroux.newsrec.newsreclib.termExtract.LuceneTopTermExtract.java

License:Apache License

/**
 * Returns the 10 most important terms in the document with the specified
 * id./*from w ww .j ava2  s  .c  o  m*/
 *
 * @param id
 * @param reader
 * @param numberOfTerms
 * @return
 */
public Map<String, Double> getTopTerms(String id, IndexReader reader, int numberOfTerms) {
    try {
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector collector = TopScoreDocCollector.create(1, true);
        Query q = new TermQuery(new Term("id", id));
        searcher.search(q, collector);
        if (collector.getTotalHits() > 0) {
            int docNr = collector.topDocs().scoreDocs[0].doc;
            return getTopTerms(docNr, reader, numberOfTerms);
        } else {
            logger.warn("No document found with id=" + id);
        }
    } catch (IOException ex) {
        logger.error(ex);
    }
    return new HashMap<>(0);
}

---

From source file:be.ugent.tiwi.sleroux.newsrec.recommendationstester.LuceneTopTermExtract.java

License:Apache License

public Map<String, Double> getTopTerms(String id, IndexReader reader, int numberOfTerms) {
    try {//from w w  w . j  a va2  s  . c  o m
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector collector = TopScoreDocCollector.create(1, true);
        Query q = new TermQuery(new Term("id", id));
        searcher.search(q, collector);
        if (collector.getTotalHits() > 0) {
            int docNr = collector.topDocs().scoreDocs[0].doc;
            return getTopTerms(docNr, reader, numberOfTerms);
        } else {
            logger.warn("No document found with id=" + id);
        }
    } catch (IOException ex) {
        logger.error(ex);
    }
    return new HashMap<>(0);
}

---

From source file:be.ugent.tiwi.sleroux.newsrec.stormNewsFetch.storm.bolts.NewsItemToTermsBolt.java

License:Apache License

private void updateTermMap(DirectoryReader reader, IndexSearcher searcher, Map<String, Double> termMap, long id,
        String field, double weight) throws IOException {
    Query query = NumericRangeQuery.newLongRange("id", id, id, true, true);
    TopDocs topdocs = searcher.search(query, 1);

    if (topdocs.totalHits > 0) {
        int docNr = topdocs.scoreDocs[0].doc;
        Terms vector = reader.getTermVector(docNr, field);
        if (vector != null) {
            TermsEnum termsEnum;/*from   w  w  w. j a v a 2s. c o m*/
            termsEnum = vector.iterator(TermsEnum.EMPTY);
            BytesRef text;
            while ((text = termsEnum.next()) != null) {
                String term = text.utf8ToString();
                int docFreq = reader.docFreq(new Term(field, text));
                // ignore really rare terms and really common terms
                //double minFreq = reader.numDocs() * 0.0001;
                //double maxFreq = reader.numDocs() / 3;
                double minFreq = 0;
                double maxFreq = Double.MAX_VALUE;

                if (docFreq > minFreq && docFreq < maxFreq) {
                    double tf = 1 + ((double) termsEnum.totalTermFreq()) / reader.getSumTotalTermFreq(field);
                    double idf = Math.log((double) reader.numDocs() / docFreq);
                    if (!Double.isInfinite(idf)) {
                        if (!termMap.containsKey(term)) {
                            termMap.put(term, tf * idf * weight);
                        } else {
                            termMap.put(term, termMap.get(term) + tf * idf * weight);
                        }
                    }
                }
            }
        } else {
            logger.debug("no term available for doc=" + docNr + " and field=" + field);
        }
    } else {
        logger.warn("No documents found with id=" + id);
    }
}

---

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  w w w. jav a 2  s  . com

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

---

From source file:bostoncase.widgets.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);//from  w ww.  j  av  a2s.com
    }

    String index = "/Users/michaelhundt/Documents/Meine/Studium/MASTER/MasterProject/data/lucene_index/";
    String field = "content";
    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(Paths.get(index)));
    //      IndexReader reader = StandardDirectoryReader.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);
        if (line.equals("geo")) {
            //            query = new GeoPointInBBoxQuery("geo", 42.2279, 42.3969, -70.9235, -71.1908);
            //            query = new GeoPointInBBoxQuery("geo", -71.1908, -70.9235, 42.2279, 42.3969);
            query = new GeoPointInBBoxQuery("geo", 42.2279, 42.3969, -71.1908, -70.9235);
        }

        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: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   ww w. ja v a2s .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  .ja va2  s . c  o  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.  jav  a2s.  c  om

    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);
    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);
    }//from  w w w  .j av a2s .  c om
    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;/*from w w w  .  j  a  va 2 s  .  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));
    }

}

---

• «
• 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
• »