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

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

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.*
  5. IndexSearcher
  6. 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:aos.lucene.tools.BooksMoreLikeThis.java

License:Apache License

public static void main(String[] args) throws Throwable {

    String indexDir = System.getProperty("index.dir");
    FSDirectory directory = FSDirectory.open(new File(indexDir));
    IndexReader reader = DirectoryReader.open(directory);

    IndexSearcher searcher = new IndexSearcher(reader);

    int numDocs = reader.maxDoc();

    MoreLikeThis mlt = new MoreLikeThis(reader);
    mlt.setFieldNames(new String[] { "title", "author" });
    mlt.setMinTermFreq(1);//from   ww w  .  j  a va2 s  .  co  m
    mlt.setMinDocFreq(1);

    for (int docID = 0; docID < numDocs; docID++) {
        LOGGER.info();
        Document doc = reader.document(docID);
        LOGGER.info(doc.get("title"));

        Query query = mlt.like(docID);
        LOGGER.info("  query=" + query);

        TopDocs similarDocs = searcher.search(query, 10);
        if (similarDocs.totalHits == 0)
            LOGGER.info("  None like this");
        for (int i = 0; i < similarDocs.scoreDocs.length; i++) {
            if (similarDocs.scoreDocs[i].doc != docID) {
                doc = reader.document(similarDocs.scoreDocs[i].doc);
                LOGGER.info("  -> " + doc.getField("title").stringValue());
            }
        }
    }

    reader.close();
    directory.close();
}

From source file:aos.lucene.tools.ChainedFilterTest.java

License:Apache License

@Override
public void setUp() throws Exception {

    directory = new RAMDirectory();

    IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(Version.LUCENE_46),
            IndexWriter.MaxFieldLength.UNLIMITED);

    Calendar cal = Calendar.getInstance();
    cal.set(2009, 1, 1, 0, 0);//  w w w  .  j a  va2s  .  c o  m

    for (int i = 0; i < MAX; i++) {
        Document doc = new Document();
        doc.add(new Field("key", "" + (i + 1), Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("owner", (i < MAX / 2) ? "bob" : "sue", Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("date", DateTools.timeToString(cal.getTimeInMillis(), DateTools.Resolution.DAY),
                Field.Store.YES, Field.Index.NOT_ANALYZED));
        writer.addDocument(doc);

        cal.add(Calendar.DATE, 1);
    }

    writer.close();

    searcher = new IndexSearcher(directory);

    BooleanQuery bq = new BooleanQuery();
    bq.add(new TermQuery(new Term("owner", "bob")), BooleanClause.Occur.SHOULD);
    bq.add(new TermQuery(new Term("owner", "sue")), BooleanClause.Occur.SHOULD);
    query = bq;

    cal.set(2099, 1, 1, 0, 0);
    dateFilter = TermRangeFilter.Less("date",
            DateTools.timeToString(cal.getTimeInMillis(), DateTools.Resolution.DAY));// C

    bobFilter = new CachingWrapperFilter(new QueryWrapperFilter(new TermQuery(new Term("owner", "bob"))));

    sueFilter = new CachingWrapperFilter(new QueryWrapperFilter(new TermQuery(new Term("owner", "sue"))));
}

From source file:aos.lucene.tools.FastVectorHighlighterSample.java

License:Apache License

static void searchIndex(String filename) throws Exception {
    QueryParser parser = new QueryParser(Version.LUCENE_46, F, analyzer);
    Query query = parser.parse(QUERY);
    FastVectorHighlighter highlighter = getHighlighter(); // #C
    FieldQuery fieldQuery = highlighter.getFieldQuery(query); // #D
    IndexSearcher searcher = new IndexSearcher(dir);
    TopDocs docs = searcher.search(query, 10);

    FileWriter writer = new FileWriter(filename);
    writer.write("<html>");
    writer.write("<body>");
    writer.write("<p>QUERY : " + QUERY + "</p>");
    for (ScoreDoc scoreDoc : docs.scoreDocs) {
        String snippet = highlighter.getBestFragment( // #E
                fieldQuery, searcher.getIndexReader(), // #E
                scoreDoc.doc, F, 100); // #E
        if (snippet != null) {
            writer.write(scoreDoc.doc + " : " + snippet + "<br/>");
        }/*from w  w  w .j  a  v  a  2s.  co  m*/
    }
    writer.write("</body></html>");
    writer.close();
}

From source file:aos.lucene.tools.HighlightTest.java

License:Apache License

public void testHits() throws Exception {
    IndexSearcher searcher = new IndexSearcher(TestUtil.getBookIndexDirectory());
    TermQuery query = new TermQuery(new Term("title", "action"));
    TopDocs hits = searcher.search(query, 10);

    QueryScorer scorer = new QueryScorer(query, "title");
    Highlighter highlighter = new Highlighter(scorer);
    highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));

    Analyzer analyzer = new SimpleAnalyzer();

    for (ScoreDoc sd : hits.scoreDocs) {
        Document doc = searcher.doc(sd.doc);
        String title = doc.get("title");

        TokenStream stream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, "title", doc,
                analyzer);// w  w w  .j a  v a2s .c  om
        String fragment = highlighter.getBestFragment(stream, title);

        LOGGER.info(fragment);
    }
}

From source file:aos.lucene.tools.RegexQueryTest.java

License:Apache License

public void testRegexQuery() throws Exception {
    Directory directory = TestUtil.getBookIndexDirectory();
    IndexSearcher searcher = new IndexSearcher(directory);
    RegexQuery q = new RegexQuery(new Term("title", ".*st.*"));
    TopDocs hits = searcher.search(q, 10);
    assertEquals(2, hits.totalHits);// w w w  .j  a  v  a2s  .  c om
    assertTrue(TestUtil.hitsIncludeTitle(searcher, hits, "Tapestry in Action"));
    assertTrue(
            TestUtil.hitsIncludeTitle(searcher, hits, "Mindstorms: Children, Computers, And Powerful Ideas"));
    searcher.close();
    directory.close();
}

From source file:aos.lucene.tools.SpatialLuceneExample.java

License:Apache License

public void findNear(String what, double latitude, double longitude, double radius)
        throws CorruptIndexException, IOException {
    IndexSearcher searcher = new IndexSearcher(directory);

    DistanceQueryBuilder dq;/*from   ww  w.j  a  v a2  s.c o m*/
    dq = new DistanceQueryBuilder(latitude, // #A
            longitude, // #A
            radius, // #A
            latField, // #A
            lngField, // #A
            tierPrefix, // #A
            true); // #A

    Query tq;
    if (what == null)
        tq = new TermQuery(new Term("metafile", "doc")); // #B
    else
        tq = new TermQuery(new Term("name", what));

    DistanceFieldComparatorSource dsort; // #C
    dsort = new DistanceFieldComparatorSource( // #C
            dq.getDistanceFilter()); // #C
    Sort sort = new Sort(new SortField("foo", dsort)); // #C

    TopDocs hits = searcher.search(tq, dq.getFilter(), 10, sort);

    Map<Integer, Double> distances = // #D
            dq.getDistanceFilter().getDistances(); // #D

    LOGGER.info("Number of results: " + hits.totalHits);
    LOGGER.info("Found:");
    for (ScoreDoc sd : hits.scoreDocs) {
        int docID = sd.doc;
        Document d = searcher.doc(docID);

        String name = d.get("name");
        double rsLat = NumericUtils.prefixCodedToDouble(d.get(latField));
        double rsLng = NumericUtils.prefixCodedToDouble(d.get(lngField));
        Double geo_distance = distances.get(docID);

        System.out.printf(name + ": %.2f Miles\n", geo_distance);
        LOGGER.info("\t\t(" + rsLat + "," + rsLng + ")");
    }
}

From source file:aplicacion.sistema.indexer.test.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] [-raw] [-norms field] [-paging hitsPerPage]";
    usage += "\n\tSpecify 'false' for hitsPerPage to use streaming instead of paging search.";
    if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
        System.out.println(usage);
        System.exit(0);//from   w w  w .jav a  2s  .  c om
    }

    String index = "e:/index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String normsField = null;
    boolean paging = true;
    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 ("-repeat".equals(args[i])) {
            repeat = Integer.parseInt(args[i + 1]);
            i++;
        } else if ("-raw".equals(args[i])) {
            raw = true;
        } else if ("-norms".equals(args[i])) {
            normsField = args[i + 1];
            i++;
        } else if ("-paging".equals(args[i])) {
            if (args[i + 1].equals("false")) {
                paging = false;
            } else {
                hitsPerPage = Integer.parseInt(args[i + 1]);
                if (hitsPerPage == 0) {
                    paging = false;
                }
            }
            i++;
        }
    }

    IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)), true); // only searching, so read-only=true

    if (normsField != null)
        reader = new OneNormsReader(reader, normsField);

    Searcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);

    BufferedReader in = null;
    if (queries != null) {
        in = new BufferedReader(new FileReader(queries));
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
    }
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, field, analyzer);
    while (true) {
        if (queries == null) // prompt the user
            System.out.println("Enter query: ");

        String line = in.readLine();

        if (line == null || line.length() == -1)
            break;

        line = line.trim();
        if (line.length() == 0)
            break;

        Query query = parser.parse(line);
        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, null, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        if (paging) {
            doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null);
        } else {
            doStreamingSearch(searcher, query);
        }
    }
    reader.close();
}

From source file:app.finder.topicsource.service.SearchFiles.java

License:Apache License

public List<TopicSource> getTopicSources(String queryString) throws IOException, ParseException {
    String field = "contents";
    String queries = null;/*from w  ww . jav  a2  s. c  o  m*/
    int repeat = 0;
    boolean raw = false;

    int hitsPerPage = SEARCH_MAX_SIZE; // 100;
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(indexDir)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    QueryParser parser = new QueryParser(field, analyzer);

    Query query = parser.parse(queryString);

    //System.out.println("Searching for: " + query.toString(field));
    searcher.search(query, null, SEARCH_MAX_SIZE);

    List<String> list = doSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

    reader.close();

    List<TopicSource> topicSourceList = new ArrayList<TopicSource>();
    TopicSource topicSource = null;
    int counter = 0;
    for (String fileName : list) {
        topicSource = new TopicSource();
        File file = new File(fileName);

        topicSource.setFileName("" + (++counter) + ". " + file.getName());
        topicSource.setPath(file.getCanonicalPath());
        topicSource.setText(readFile(file));
        topicSourceList.add(topicSource);
    }

    return topicSourceList;
}

From source file:app.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);//  w w  w .ja  v  a  2s .  c om
    }

    String index = "index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = true;
    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(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);

    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"));
    }
    QueryParser parser = new QueryParser(Version.LUCENE_40, 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);
        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, null, 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:Application.mediaIndexer.java

public static void SearchFiles(String index, String queryString, String selected, TextArea results)
        throws IOException, ParseException {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();
    BufferedReader in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    QueryParser parser = new QueryParser(selected, analyzer);
    String line = queryString != null ? queryString : in.readLine();
    line = line.trim();/*  w ww .  j  a va  2s  . co  m*/
    Query query = parser.parse(line);
    int maxHits = 100;
    TopDocs docsResults = searcher.search(query, maxHits);
    ScoreDoc[] hits = docsResults.scoreDocs;
    for (int i = 0; i < hits.length; i++) {
        Document doc = searcher.doc(hits[i].doc);
        results.appendText("Title: " + doc.get("title") + "\n");
        results.appendText("Artists: " + doc.get("xmpDM:artist") + "\n");
        results.appendText("Genre: " + doc.get("xmpDM:genre") + "\n");
        results.appendText("Year: " + doc.get("xmpDM:releaseDate") + "\n");
    }
    // Playlist.
    playlist.clear();
    for (int i = 0; i < hits.length; i++) {
        Document doc = searcher.doc(hits[i].doc);
        String path = doc.get("path");
        if (path != null)
            playlist.add(new File(path));
    }
    reader.close();
}