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:buscador.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);// www  .  j av a 2s.co m
    }

    String index = "Zaguan1";
    String[] fields = { "title", "description", "identifier", "date", "creator" };
    BooleanClause.Occur[] flags = { BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD,
            BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD };

    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 ("-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 SpanishAnalyzer(Version.LATEST);

    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"));
    }

    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 = MultiFieldQueryParser.parse(line, fields, flags, analyzer);

        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:buscador.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  .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, IndexSearcher searcher, Query query, int hitsPerPage,
        boolean raw, boolean interactive) throws IOException {

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

    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) ?");
            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;
            }

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

                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:ca.mcgill.cs.creco.logic.search.CategorySearch.java

License:Apache License

@Override
public List<Category> queryCategories(String pQueryString) {
    List<Category> searchResult = new ArrayList<Category>();
    try {//from   w  w  w  .j ava2  s .  co  m
        DirectoryReader reader = DirectoryReader.open(aDirectory);
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector results = TopScoreDocCollector.create(MAX_NUM_RESULTS, true);

        // Search category names
        Query categoryNameQuery = new QueryParser(VERSION, CATEGORY_NAME, aAnalyzer).parse(pQueryString);
        searcher.search(categoryNameQuery, results);

        // Search flattened text (only product names for now)
        Query flattenedTextQuery = new QueryParser(VERSION, FLATTENED_TEXT, aAnalyzer).parse(pQueryString);
        searcher.search(flattenedTextQuery, results);

        for (ScoreDoc scoredResult : results.topDocs().scoreDocs) {
            Document doc = searcher.doc(scoredResult.doc);
            Category resultCategory = aDataStore.getCategory(doc.get(CATEGORY_ID));

            if (!searchResult.contains(resultCategory) && resultCategory.getNumberOfProducts() > 0) {
                searchResult.add(resultCategory);
            }
        }
    } catch (IOException e) {
        LOG.error(e.getMessage());
    } catch (ParseException e) {
        LOG.error(e.getMessage());
    }
    return searchResult;
}

---

From source file:ca.pgon.freenetknowledge.search.impl.LuceneSearchEngine.java

License:Apache License

@Override
public List<SearchResultEntry> searchTerm(String term) {
    IndexSearcher indexSearcher = null;
    try {//from  w  ww  . j  a  v  a2  s  . c om
        // Init the needed components
        IndexReader indexReader = IndexReader.open(directory);
        indexSearcher = new IndexSearcher(indexReader);
        QueryParser queryParser = new QueryParser(LUCENE_VERSION, INDEX_CONTENT, analyzer);

        // Create the query
        Query query;
        query = queryParser.parse(term);

        // Get the search result
        TopDocs topDocs = indexSearcher.search(query, LUCENE_MAX_HITS);
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;

        // Change them to urls
        Map<String, SearchResultEntry> alreadyIn = new HashMap<>();
        List<SearchResultEntry> results = new ArrayList<>();
        for (ScoreDoc sd : scoreDocs) {
            // Get the url
            Document document = indexSearcher.doc(sd.doc);
            String urlId = document.get(INDEX_FOR_URL);

            SearchResultEntry sre;
            if (alreadyIn.containsKey(urlId)) {
                sre = alreadyIn.get(urlId);
            } else {
                sre = new SearchResultEntry();
                UrlEntity ue = urlDAO.get(Integer.valueOf(urlId));
                sre.urlEntity = ue;

                if (ue == null) {
                    continue;
                }
                if (ue.isError()) {
                    continue;
                }

                alreadyIn.put(urlId, sre);
                results.add(sre);
            }

            // Add the description
            String fullDescription = document.get(INDEX_CONTENT);
            String partialDescription = SearchTools.getPartAround(fullDescription,
                    SearchTools.findWordPosition(fullDescription, term), LUCENE_MAX_DESCRIPTION_CARACTERS);
            partialDescription = partialDescription.replace('\n', ' ');
            partialDescription = partialDescription.replace('\r', ' ');
            if (!sre.description.contains(partialDescription)) {
                sre.description.add(partialDescription);
            }
        }

        return results;
    } catch (ParseException e) {
        logger.log(Level.SEVERE, "Error while parsing the search term", e);
    } catch (IOException e) {
        logger.log(Level.SEVERE, "Error while searching", e);
    } finally {
        if (indexSearcher != null) {
            try {
                indexSearcher.close();
            } catch (IOException e) {
            }
        }
    }

    return null;
}

---

From source file:calliope.search.AeseSearch.java

License:Open Source License

/**
 * Search the index for the given expression
 * @param expr the expression to be parsed
 * @param langCode the language of the expression and index
 * @param profile the hit profile (where to start from etc)
 * @return the result docs/*from  ww w.jav a  2  s .c o  m*/
 */
public static String searchIndex(String expr, String langCode, HitProfile profile) {
    StringBuilder sb = new StringBuilder();
    try {
        Analyzer analyzer = AeseSearch.createAnalyzer(langCode);
        DirectoryReader reader = DirectoryReader.open(AeseSearch.index);
        if (reader != null) {
            IndexSearcher searcher = new IndexSearcher(reader);
            QueryParser qp = new QueryParser(Version.LUCENE_45, "text", analyzer);
            Query q = qp.parse(expr);
            TopDocs hits = searcher.search(q, AeseSearch.maxHits);
            ScoreDoc[] docs = hits.scoreDocs;
            for (int j = profile.from; j < profile.to && j < docs.length; j++) {
                Document doc = searcher.doc(docs[j].doc);
                String vid = doc.get(LuceneFields.VID);
                String docID = doc.get(LuceneFields.DOCID);
                Highlighter h = new Highlighter(new QueryScorer(q));
                String text = getCorTexVersion(docID, vid);
                sb.append(formatDocID(docID));
                sb.append(" ");
                sb.append(formatVersionID(vid));
                sb.append(" ");
                String frag = h.getBestFragment(analyzer, "text", text);
                sb.append("<span class=\"found\">");
                sb.append(frag);
                sb.append("</span>\n");
            }
            profile.numHits = docs.length;
        }
        reader.close();
    } catch (Exception e) {
        sb.append(e.getMessage());
    }
    return sb.toString();
}

---

From source file:cc.pp.analyzer.ik.demo.IKAnalyzerDemo.java

License:Apache License

public static void main(String[] args) {

    //Lucene Document??
    String fieldName = "text";
    ///*w w  w . j a  va  2s.c  o m*/
    String text = "IK Analyzer???????";

    //IKAnalyzer?
    Analyzer analyzer = new IKAnalyzer(Version.LUCENE_48, true);

    Directory directory = null;
    IndexWriter iwriter = null;
    DirectoryReader ireader = null;
    IndexSearcher isearcher = null;
    try {
        //
        directory = new RAMDirectory();

        //?IndexWriterConfig
        IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_48, analyzer);
        iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
        iwriter = new IndexWriter(directory, iwConfig);
        //
        Document doc = new Document();
        doc.add(new LongField("ID", 1000, Field.Store.YES));
        doc.add(new TextField(fieldName, text, Field.Store.YES));
        iwriter.addDocument(doc);
        iwriter.close();

        //?**********************************
        //?
        ireader = DirectoryReader.open(directory);
        isearcher = new IndexSearcher(ireader);

        String keyword = "?";
        //         String keyword = "";
        //QueryParser?Query
        QueryParser qp = new QueryParser(Version.LUCENE_48, fieldName, analyzer);
        qp.setDefaultOperator(QueryParser.AND_OPERATOR);
        Query query = qp.parse(keyword);
        System.out.println("Query = " + query);

        //?5?
        TopDocs topDocs = isearcher.search(query, 5);
        System.out.println("" + topDocs.totalHits);
        //
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (int i = 0; i < topDocs.totalHits; i++) {
            Document targetDoc = isearcher.doc(scoreDocs[i].doc);
            System.out.println("" + targetDoc.toString());
        }

    } catch (CorruptIndexException e) {
        e.printStackTrace();
    } catch (LockObtainFailedException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    } catch (ParseException e) {
        e.printStackTrace();
    } finally {
        if (ireader != null) {
            try {
                ireader.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        if (directory != null) {
            try {
                directory.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

---

From source file:ccc.plugins.search.lucene.SimpleLuceneFS.java

License:Open Source License

private void similar(final String uuid, final int maxHits, final CapturingHandler ch) {
    if (uuid == null) {
        return;//  www .j a v a  2  s .c o m
    }
    IndexReader ir = null;
    IndexSearcher searcher = null;
    try {
        ir = IndexReader.open(createDirectory());
        searcher = new IndexSearcher(ir);
        final int docNum = docNumber(uuid, searcher);

        if (docNum == -1) {
            return;
        }
        final MoreLikeThis mlt = new MoreLikeThis(ir);
        mlt.setFieldNames(new String[] { DEFAULT_FIELD });
        mlt.setMinDocFreq(2);
        final Query query = mlt.like(docNum);
        ch.handle(searcher, searcher.search(query, maxHits));
    } catch (final IOException e) {
        LOG.warn("Error performing query.", e);
    } finally {
        if (searcher != null) {
            try {
                searcher.close();
            } catch (final IOException e) {
                Exceptions.swallow(e);
            }
        }
        if (ir != null) {
            try {
                ir.close();
            } catch (final IOException e) {
                Exceptions.swallow(e);
            }
        }
    }
}

---

From source file:ccc.plugins.search.lucene.SimpleLuceneFS.java

License:Open Source License

/**
 * Retrieves lucene document for given page.
 *
 * @param uuid UUID to search./*from  w w  w. j  a  v a 2s  . co m*/
 * @param searcher IndexSearcher object.
 * @return Document number.
 * @throws IOException If search fails
 */
private int docNumber(final String uuid, final IndexSearcher searcher) throws IOException {
    final Query q = new TermQuery(new Term("id", uuid));
    final TopDocs hits = searcher.search(q, 1);

    if (hits.scoreDocs.length < 1) {
        return -1;
    }
    return hits.scoreDocs[0].doc;
}

---

From source file:ch.algotrader.rest.index.SecurityIndexer.java

License:Open Source License

public List<SecurityVO> search(String queryStr) throws ParseException {
    try (IndexReader reader = DirectoryReader.open(index)) {
        IndexSearcher searcher = new IndexSearcher(reader);
        QueryParser queryParser = new MultiFieldQueryParser(FIELDS, new StandardAnalyzer());
        queryParser.setAllowLeadingWildcard(true);
        Query query = queryParser.parse(queryStr);

        TopDocs results = searcher.search(query, 10);
        return Arrays.asList(results.scoreDocs).stream().map(sd -> searchDocument(searcher, sd))
                .mapToLong(d -> d.getField("id").numericValue().longValue()).mapToObj(securityCache::get)
                .collect(Collectors.toList());

    } catch (IOException ioe) {
        throw new UnrecoverableCoreException("Unexpected I/O error accessing security index", ioe);
    }// ww w  .j  a v a  2  s . co m
}

---

From source file:ch.sentric.hbase.prospective.Percolator.java

License:Apache License

/**
* Tries to find a set of queries that match the given document.
* 
* @param doc// w ww  .  j ava2  s.  co m
*            the Lucene document
* @return the matching queries
* @throws IOException
*             if an I/O error occurs
*/
public Response<T> percolate(final Document doc, final Map<T, Query> queries) throws IOException {
    // first, parse the source doc into a MemoryIndex
    final MemoryIndex memoryIndex = new MemoryIndex();

    for (final Fieldable field : doc.getFields()) {
        if (!field.isIndexed()) {
            continue;
        }

        final TokenStream tokenStream = field.tokenStreamValue();
        if (tokenStream != null) {
            memoryIndex.addField(field.name(), tokenStream, field.getBoost());
        } else {
            final Reader reader = field.readerValue();
            if (reader != null) {
                memoryIndex.addField(field.name(), analyzer.reusableTokenStream(field.name(), reader),
                        field.getBoost());
            } else {
                final String value = field.stringValue();
                if (value != null) {
                    memoryIndex.addField(field.name(),
                            analyzer.reusableTokenStream(field.name(), new CharSequenceReader(value)),
                            field.getBoost());
                }
            }
        }
    }

    // do the search
    final IndexSearcher searcher = memoryIndex.createSearcher();
    final Map<T, Query> matches = new HashMap<T, Query>(0);

    if (queries != null && !queries.isEmpty()) {
        final ExistsCollector collector = new ExistsCollector();
        for (final Map.Entry<T, Query> entry : queries.entrySet()) {
            collector.reset();
            searcher.search(entry.getValue(), collector);
            if (collector.exists()) {
                matches.put(entry.getKey(), entry.getValue());
            }
        }
    }

    return new Response<T>(matches);
}

---

• «
• 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
• »