Example usage for org.apache.lucene.search IndexSearcher 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:br.bireme.mlts.MoreLikeThat.java

License:Open Source License

/**
 * Constructor of the class//ww w.j  a v  a 2  s .c  o m
 * @param dir directory of the Lucene index
 * @param analyz  analyzer used during search and similar
 * @throws IOException
 */
public MoreLikeThat(final File dir, final Analyzer analyz) throws IOException {
    if (dir == null) {
        throw new NullPointerException("dir");
    }
    if (analyz == null) {
        throw new NullPointerException("analyz");
    }

    if (!dir.isDirectory()) {
        throw new IllegalArgumentException(dir.getCanonicalPath() + " is not a directory");
    }
    directory = new SimpleFSDirectory(dir); /* RAMDirectory(new SimpleFSDirectory(dir)); //MMapDirectory(dir);*/
    ir = IndexReader.open(directory);
    if (ir.numDocs() == 0) {
        throw new IllegalArgumentException("zero document index");
    }
    is = new IndexSearcher(ir);
    analyzer = analyz;
    stopwords = (analyzer instanceof StopwordAnalyzerBase) ? ((StopwordAnalyzerBase) analyzer).getStopwordSet()
            : null;
    defaultValues();
}

---

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

private static void compare(final String resultFile, final String indexPath, final String outputFile,
        final String encoding) throws IOException {
    assert resultFile != null;
    assert indexPath != null;
    assert outputFile != null;
    assert encoding != null;

    try (DirectoryReader ireader = DirectoryReader.open(new MMapDirectory(new File(indexPath).toPath()))) {
        final IndexSearcher isearcher = new IndexSearcher(ireader);

        try (BufferedReader breader = Files.newBufferedReader(new File(resultFile).toPath(),
                Charset.forName(encoding));
                BufferedWriter bwriter = Files.newBufferedWriter(new File(outputFile).toPath(),
                        Charset.forName(encoding))) {
            boolean first = true; // first line

            while (true) {
                final String line = breader.readLine();
                if (line == null)
                    break;
                if (first) {
                    first = false; // drop header line (first)
                } else {
                    final String line2 = line.trim();
                    if (!line2.isEmpty()) {
                        final String[] split = line2.split("\\|");
                        checkDocs(split[1], split[2], split[3], isearcher, bwriter);
                    }//from  w  w  w .j a v  a2s.com
                }
            }
        }
    }
}

---

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

private IndexSearcher getIndexSearcher(final String indexPath) throws IOException {

    final DirectoryReader ireader = DirectoryReader.open(
            //FSDirectory.open(new File(indexPath).toPath()));
            new MMapDirectory(new File(indexPath).toPath()));
    //new RAMDirectory(FSDirectory.open(new File(indexPath).toPath()), IOContext.DEFAULT));
    //new RAMDirectory(FSDirectory.open(new File(indexPath).toPath()), IOContext.READONCE));

    return new IndexSearcher(ireader);
}

---

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);/*from   ww  w .j a v a  2s.c om*/
    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.ufmt.harmonizacao.implementer.PatenteeSearcher.java

public void setPath(String path) {
    try {//ww w.  java2 s .c o  m
        this.path = path + dirName;
        System.out.println(this.path);
        dir = new SimpleFSDirectory(new File(this.path));
        reader = DirectoryReader.open(dir);
        searcher = new IndexSearcher(reader);
    } catch (IOException ex) {
        Logger.getLogger(PatenteeSearcher.class.getName()).log(Level.SEVERE, null, ex);
    }

}

---

From source file:br.ufmt.harmonizacao.implementer.StandardSearcher.java

public void setPath(String path) {
    try {/*from   w  w  w .  ja  v a2s .c om*/
        this.path = path + dirName;
        System.out.println(this.path);
        dir = new SimpleFSDirectory(new File(this.path));
        reader = DirectoryReader.open(dir);
        searcher = new IndexSearcher(reader);
    } catch (IOException ex) {
        Logger.getLogger(PatenteeSearcher.class.getName()).log(Level.SEVERE, null, ex);
    }
}

---

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

License:Open Source License

public void search1(String q) throws IOException, ParseException {
    IndexReader ireader = IndexReader.open(dir); // read-only=true
    IndexSearcher reader = new IndexSearcher(ireader);
    reader.setSimilarity(similarityltc()); //ddd.qqq
    busca(reader, q);/*from  w  w  w. jav a  2 s .co m*/
    numQ++;
}

---

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);//from   w  w  w. java  2 s . 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:bzh.terrevirtuelle.navisu.gazetteer.impl.lucene.GeoNameResolver.java

License:Apache License

/**
 * Returns a list of location near a certain coordinate.
 *
 * @param latitude, @param longitude - Center of search area
 * @param distanceInMiles - Search Radius in miles
 * @param indexerPath - Path to Lucene index
 * @param count - Upper bound to number of results
 * @return - List of locations sorted by population
 * @throws IOException//from ww w . j a va 2s .co m
 */
public List<Location> searchNearby(Double latitude, Double longitude, Double distanceInMiles,
        String indexerPath, int count) throws IOException {

    double distanceInDeg = DistanceUtils.dist2Degrees(distanceInMiles,
            DistanceUtils.EARTH_EQUATORIAL_RADIUS_MI);
    SpatialArgs spatialArgs = new SpatialArgs(SpatialOperation.IsWithin,
            ctx.makeCircle(longitude, latitude, distanceInDeg));

    String key = latitude + "-" + longitude;
    Filter filter = strategy.makeFilter(spatialArgs);

    IndexSearcher searcher = new IndexSearcher(createIndexReader(indexerPath));
    Sort sort = new Sort(populationSort);
    TopDocs topDocs = searcher.search(new MatchAllDocsQuery(), filter, count, sort);

    ScoreDoc[] scoreDocs = topDocs.scoreDocs;
    HashMap<String, List<Location>> allCandidates = new HashMap<String, List<Location>>();

    getMatchingCandidates(searcher, allCandidates, key, scoreDocs);
    List<Location> results = allCandidates.get(key);

    return results;
}

---

From source file:bzh.terrevirtuelle.navisu.gazetteer.impl.lucene.GeoNameResolver.java

License:Apache License

private HashMap<String, List<Location>> resolveEntities(List<String> locationNames, int count,
        IndexReader reader) throws IOException {
    if (locationNames.size() >= 200) {
        hitsPerPage = 5; // avoid heavy computation
    }// ww  w  . j av a2 s.co m
    IndexSearcher searcher = new IndexSearcher(reader);
    Query q = null;

    HashMap<String, List<Location>> allCandidates = new HashMap<String, List<Location>>();

    for (String name : locationNames) {

        if (!allCandidates.containsKey(name)) {
            try {
                //query is wrapped in additional quotes (") to avoid query tokenization on space
                q = new MultiFieldQueryParser(new String[] { FIELD_NAME_NAME, FIELD_NAME_ALTERNATE_NAMES },
                        analyzer).parse(String.format("\"%s\"", name));

                Sort sort = new Sort(populationSort);
                //Fetch 3 times desired values, these will be sorted on code and only desired number will be kept
                ScoreDoc[] hits = searcher.search(q, hitsPerPage * 3, sort).scoreDocs;

                getMatchingCandidates(searcher, allCandidates, name, hits);
            } catch (org.apache.lucene.queryparser.classic.ParseException e) {
                e.printStackTrace();
            }
        }
    }

    HashMap<String, List<Location>> resolvedEntities = new HashMap<String, List<Location>>();
    pickBestCandidates(resolvedEntities, allCandidates, count);
    return resolvedEntities;
}

---

• «
• 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
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• »