Example usage for org.apache.lucene.index DirectoryReader open

List of usage examples for org.apache.lucene.index DirectoryReader open

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. DirectoryReader
  6. open

Introduction

In this page you can find the example usage for org.apache.lucene.index DirectoryReader open.

Prototype

public static DirectoryReader open(final IndexCommit commit) throws IOException

Source Link

Document

Expert: returns an IndexReader reading the index in the given IndexCommit .

Usage

From source file:com.czw.search.lucene.example.facet.SimpleFacetsExample.java

License:Apache License

/**
 * User drills down on 'Publish Date/2012', and we
 * return facets for both 'Publish Date' and 'Author',
 * using DrillSideways.// w ww.  ja  v a2s  . c  o m
 */
private List<FacetResult> drillSideways() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    TaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);

    // Passing no baseQuery means we drill down on all
    // documents ("browse only"):
    DrillDownQuery q = new DrillDownQuery(config);

    // Now user drills down on Publish Date/2010:
    q.add("Publish Date", "2010");

    DrillSideways ds = new DrillSideways(searcher, config, taxoReader);
    DrillSidewaysResult result = ds.search(q, 10);

    // Retrieve results
    List<FacetResult> facets = result.facets.getAllDims(10);
    System.out.println("totalHits:" + result.hits.totalHits);
    ScoreDoc[] docs = result.hits.scoreDocs;
    System.out.println(searcher.doc(docs[0].doc));

    indexReader.close();
    taxoReader.close();

    return facets;
}

From source file:com.czw.search.lucene.example.facet.SimpleSortedSetFacetsExample.java

License:Apache License

/**
 * User runs a query and counts facets.//  ww  w.j  av a2s  . co  m
 */
private List<FacetResult> search() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    SortedSetDocValuesReaderState state = new DefaultSortedSetDocValuesReaderState(indexReader);

    // Aggregatses the facet counts
    FacetsCollector fc = new FacetsCollector();

    // MatchAllDocsQuery is for "browsing" (counts facets
    // for all non-deleted docs in the index); normally
    // you'd use a "normal" query:
    FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);

    // Retrieve results
    Facets facets = new SortedSetDocValuesFacetCounts(state, fc);

    List<FacetResult> results = new ArrayList<>();
    results.add(facets.getTopChildren(10, "Author"));
    results.add(facets.getTopChildren(10, "Publish Year"));
    indexReader.close();

    return results;
}

From source file:com.czw.search.lucene.example.facet.SimpleSortedSetFacetsExample.java

License:Apache License

/**
 * User drills down on 'Publish Year/2010'.
 *//*w  w w . ja va  2 s .c  o m*/
private FacetResult drillDown() throws IOException {
    DirectoryReader indexReader = DirectoryReader.open(indexDir);
    IndexSearcher searcher = new IndexSearcher(indexReader);
    SortedSetDocValuesReaderState state = new DefaultSortedSetDocValuesReaderState(indexReader);

    // Now user drills down on Publish Year/2010:
    DrillDownQuery q = new DrillDownQuery(config);
    q.add("Publish Year", "2010");
    FacetsCollector fc = new FacetsCollector();
    FacetsCollector.search(searcher, q, 10, fc);

    // Retrieve results
    Facets facets = new SortedSetDocValuesFacetCounts(state, fc);
    FacetResult result = facets.getTopChildren(10, "Author");
    indexReader.close();

    return result;
}

From source file:com.czw.search.lucene.example.xmlparser.FormBasedXmlQueryDemo.java

License:Apache License

private void openExampleIndex() throws IOException {
    //Create a RAM-based index from our test data file
    RAMDirectory rd = new RAMDirectory();
    IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer);
    IndexWriter writer = new IndexWriter(rd, iwConfig);
    InputStream dataIn = getServletContext().getResourceAsStream("/WEB-INF/data.tsv");
    BufferedReader br = new BufferedReader(new InputStreamReader(dataIn, StandardCharsets.UTF_8));
    String line = br.readLine();/*from w  w  w  .  ja  v a  2 s  .c o  m*/
    final FieldType textNoNorms = new FieldType(TextField.TYPE_STORED);
    textNoNorms.setOmitNorms(true);
    while (line != null) {
        line = line.trim();
        if (line.length() > 0) {
            //parse row and create a document
            StringTokenizer st = new StringTokenizer(line, "\t");
            Document doc = new Document();
            doc.add(new Field("location", st.nextToken(), textNoNorms));
            doc.add(new Field("salary", st.nextToken(), textNoNorms));
            doc.add(new Field("type", st.nextToken(), textNoNorms));
            doc.add(new Field("description", st.nextToken(), textNoNorms));
            writer.addDocument(doc);
        }
        line = br.readLine();
    }
    writer.close();

    //open searcher
    // this example never closes it reader!
    IndexReader reader = DirectoryReader.open(rd);
    searcher = new IndexSearcher(reader);
}

From source file:com.daniel.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.che.org/java/4_0/demo.html 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  . ja  va2 s  . c o m
    }

    String index = "index";
    String field = "contents";
    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(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:com.devb.search.IndicSearcher.java

License:Apache License

private void callSearch(boolean j) {
    System.out.println("Servlet Ctx " + servletContext.getRealPath("/"));
    String indexPath = servletContext.getRealPath("/") + "/hindex/";
    String docsPath = servletContext.getRealPath("/") + "/hdocs/";

    final File docDir = new File(docsPath);
    if (!docDir.exists() || !docDir.canRead()) {
        System.out.println("Document directory '" + docDir.getAbsolutePath()
                + "' does not exist or is not readable, " + "please check the path\n");
        return;//from  w  ww . j  a  v a2 s  .  co m
    }

    IndexReader reader = null;
    IndexSearcher searcher = null;
    Analyzer analyzer = null;
    String field = "contents";

    try {
        reader = DirectoryReader.open(FSDirectory.open(new File(indexPath)));
        searcher = new IndexSearcher(reader);
        analyzer = new HindiAnalyzer();
    } catch (IOException ioe) {
        ioe.printStackTrace();
    }

    QueryParser parser = new QueryParser(field, analyzer);
    String /*ByteBuffer*/ line = null;
    Query query = null;

    try {
        // line = Charset.forName("UTF-8").encode(this.id);
        line = this.id;

        // line = line.trim();
        if (line == null) {
            return;
        }
        System.out.println("Hindi StandardSearcher / callSearch Line " + line);
        query = parser.parse(line);
        System.out.println("Hindi StandardSearcher / callSearch Hindi Query " + query);
        final int maxHits = 10;
        ScoreDoc[] hits = searcher.search(query, null, maxHits).scoreDocs;
        try {
            // Iterate through the results:
            for (int i = 0; i < hits.length; i++) {
                Document hitDoc = searcher.doc(hits[i].doc);

                if (j) {
                    JSONObject jo = new JSONObject();
                    jo.put("query", query.toString(field));
                    jo.put("path", hitDoc.get("path"));
                    jo.put("line", hitDoc.get("linenumber"));
                    jo.put("contents", hitDoc.get("contents"));

                    ja.put(jo);
                } else {
                    SearchResult ns = new SearchResult();
                    ns.setQuery(query.toString(field));
                    ns.setDocPath(hitDoc.get("path"));
                    ns.setLineNum(hitDoc.get("linenumber"));
                    ns.setContents(hitDoc.get("contents"));
                    contentProvider.put(String.valueOf(i), ns);
                }
            }
        } catch (Exception ito) {
            ito.printStackTrace();
        }

    } catch (Exception ex) {
        ex.printStackTrace();
    }
    try {
        reader.close();
    } catch (IOException ioe) {

    }
}

From source file:com.devb.search.StandardSearcher.java

License:Apache License

private void callSearch(boolean j) {
    System.out.println("Servlet Ctx " + servletContext.getRealPath("/"));
    String indexPath = servletContext.getRealPath("/") + "/index/";
    String docsPath = servletContext.getRealPath("/") + "/docs/";

    final File docDir = new File(docsPath);
    if (!docDir.exists() || !docDir.canRead()) {
        System.out.println("Document directory '" + docDir.getAbsolutePath()
                + "' does not exist or is not readable, " + "please check the path\n");
        return;/* w  ww  .j  a v a 2  s.c  o m*/
    }

    IndexReader reader = null;
    IndexSearcher searcher = null;
    Analyzer analyzer = null;
    String field = "contents";

    try {
        reader = DirectoryReader.open(FSDirectory.open(new File(indexPath)));
        searcher = new IndexSearcher(reader);
        analyzer = new StandardAnalyzer();
    } catch (IOException ioe) {
        ioe.printStackTrace();
    }

    QueryParser parser = new QueryParser(field, analyzer);
    String line = null;
    Query query = null;

    try {
        line = this.id;

        line = line.trim();
        if (line.length() == 0) {
            return;
        }
        query = parser.parse(line);
        final int maxHits = 10;
        ScoreDoc[] hits = searcher.search(query, null, maxHits).scoreDocs;
        try {
            // Iterate through the results:
            for (int i = 0; i < hits.length; i++) {
                Document hitDoc = searcher.doc(hits[i].doc);

                if (j) {
                    JSONObject jo = new JSONObject();
                    jo.put("query", query.toString(field));
                    jo.put("path", hitDoc.get("path"));
                    jo.put("line", hitDoc.get("linenumber"));
                    jo.put("contents", hitDoc.get("contents"));

                    ja.put(jo);
                } else {
                    SearchResult ns = new SearchResult();
                    ns.setQuery(query.toString(field));
                    ns.setDocPath(hitDoc.get("path"));
                    ns.setLineNum(hitDoc.get("linenumber"));
                    ns.setContents(hitDoc.get("contents"));
                    contents.put(String.valueOf(i), ns);
                }
            }
        } catch (Exception ito) {
            ito.printStackTrace();
        }

    } catch (Exception ex) {
        ex.printStackTrace();
    }
    try {
        reader.close();
    } catch (IOException ioe) {

    }
}

From source file:com.doculibre.constellio.lucene.BaseLuceneIndexHelper.java

License:Open Source License

@Override
public synchronized boolean isEmpty() {
    boolean empty;
    try {/*  ww w. j a v a 2s .co m*/
        Directory directory = FSDirectory.open(indexDir);
        IndexReader indexReader = DirectoryReader.open(directory);
        empty = indexReader.numDocs() <= 1;
        indexReader.close();
        directory.close();
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
    return empty;
}

From source file:com.doculibre.constellio.lucene.BaseLuceneIndexHelper.java

License:Open Source License

protected synchronized int getDocNum(T object) {
    int docNum;//from   w w  w  .  ja va  2  s.  co m
    String uniqueIndexFieldName = getUniqueIndexFieldName();
    String uniqueIndexFieldValue = getUniqueIndexFieldValue(object);
    if (uniqueIndexFieldValue != null) {
        String query = uniqueIndexFieldName + ":" + uniqueIndexFieldValue;
        try {
            Analyzer analyzer = analyzerProvider.getAnalyzer(Locale.FRENCH);
            QueryParser multiFielsQP = new QueryParser(Version.LUCENE_44, uniqueIndexFieldName, analyzer);
            Query luceneQuery = multiFielsQP.parse(query);

            Directory directory = FSDirectory.open(indexDir);
            IndexReader reader = DirectoryReader.open(directory);
            IndexSearcher indexSearcher = new IndexSearcher(reader);
            TopDocs topDocs = indexSearcher.search(luceneQuery, reader.maxDoc());
            if (topDocs.totalHits > 0) {
                docNum = topDocs.scoreDocs[0].doc;
            } else {
                docNum = -1;
            }
            //               indexSearcher.close();
            // TODO add finally
            reader.close();
            directory.close();
        } catch (ParseException e) {
            throw new RuntimeException(e);
        } catch (CorruptIndexException e) {
            throw new RuntimeException(e);
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    } else {
        docNum = -1;
    }
    return docNum;
}

From source file:com.doculibre.constellio.lucene.BaseLuceneIndexHelper.java

License:Open Source License

public String highlight(String strToHighlight, String fieldName, Query luceneQuery) {
    String highlightedText;//  ww  w. j  a v a 2 s. c o  m
    Analyzer analyzer = analyzerProvider.getAnalyzer(Locale.FRENCH);
    try {
        Directory directory = FSDirectory.open(indexDir);
        IndexReader indexReader = DirectoryReader.open(directory);
        Query rewrittenLuceneQuery = luceneQuery.rewrite(indexReader);
        QueryScorer luceneScorer = new QueryScorer(rewrittenLuceneQuery);
        SimpleHTMLFormatter luceneFormatter = new SimpleHTMLFormatter("<span class=\"hit\">", "</span>");
        Highlighter luceneHighlighter = new Highlighter(luceneFormatter, luceneScorer);

        Fragmenter luceneFragmenter;
        // Si la chaine  highlighter est sup  250 carac
        if (strToHighlight.length() > TAILLE_CHAINE_NON_FRAGMENTEE) {
            // Cration de best fragments de 100 carac chaque
            luceneFragmenter = new SimpleFragmenter(TAILLE_FRAGMENT);
        } else {
            // Toute la chaine est highlight
            luceneFragmenter = new SimpleFragmenter(Integer.MAX_VALUE);
        }
        luceneHighlighter.setTextFragmenter(luceneFragmenter);

        TokenStream luceneTokenStream = analyzer.tokenStream(fieldName, new StringReader(strToHighlight));
        String fragment = null;
        if (strToHighlight.length() > TAILLE_CHAINE_NON_FRAGMENTEE) {
            fragment = luceneHighlighter.getBestFragments(luceneTokenStream, strToHighlight, NB_BEST_FRAGMENT,
                    FRAGMENT_SEP);
        } else {
            fragment = luceneHighlighter.getBestFragment(luceneTokenStream, strToHighlight);
        }

        if (StringUtils.isBlank(fragment) && fieldName.equalsIgnoreCase("titre")) {
            fragment = strToHighlight;
        }
        indexReader.close();
        directory.close();

        highlightedText = fragment;
    } catch (IOException e) {
        throw new RuntimeException(e);
    } catch (InvalidTokenOffsetsException e) {
        throw new RuntimeException(e);
    }
    return highlightedText;
}