Example usage for org.apache.lucene.index DirectoryReader 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:collene.Freedb.java

License:Apache License

public static void DoSearch(Directory directory) throws Exception {

    out.println("I think these are the files:");
    for (String s : directory.listAll()) {
        out.println(s);//from w w w  .j  a  v a2  s  . c  om
    }

    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(directory));
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_4_9);
    QueryParser parser = new QueryParser(Version.LUCENE_4_9, "any", analyzer);
    for (int i = 0; i < 5; i++) {
        long searchStart = System.currentTimeMillis();
        Query query = parser.parse("morrissey");
        //Query query = parser.parse("Dance");
        TopDocs docs = searcher.search(query, 10);
        long searchEnd = System.currentTimeMillis();
        out.println(String.format("%s %d total hits in %d", directory.getClass().getSimpleName(),
                docs.totalHits, searchEnd - searchStart));
        long lookupStart = System.currentTimeMillis();
        for (ScoreDoc d : docs.scoreDocs) {
            Document doc = searcher.doc(d.doc);
            out.println(String.format("%d %.2f %d %s", d.doc, d.score, d.shardIndex,
                    doc.getField("any").stringValue()));
        }
        long lookupEnd = System.currentTimeMillis();
        out.println(String.format("Document lookup took %d ms for %d documents", lookupEnd - lookupStart,
                docs.scoreDocs.length));
    }

    directory.close();
}

---

From source file:com.adanac.module.blog.search.LuceneHelper.java

License:Apache License

private static List<Map<String, String>> search(String searchText, String path, String title,
        LoadQuery loadQuery) {/*from w w w  .j av  a2 s .  c  o m*/
    try {
        IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(INDEX_PATH + path)));
        IndexSearcher searcher = new IndexSearcher(reader);
        Analyzer analyzer = new SmartChineseAnalyzer();
        QueryParser parser = new QueryParser("indexedContent", analyzer);
        Query query = parser.parse(searchText);
        TopDocs resultDocs = searcher.search(query, 100);
        ScoreDoc[] scoreDocs = resultDocs.scoreDocs;
        //
        SimpleHTMLFormatter simpleHtmlFormatter = new SimpleHTMLFormatter("<span style=\"color:red;\">",
                "</span>");
        Highlighter highlighter = new Highlighter(simpleHtmlFormatter, new QueryScorer(query));
        highlighter.setTextFragmenter(new SimpleFragmenter(150));
        List<Map<String, String>> result = new ArrayList<>();
        List<Integer> idList = new ArrayList<>();
        for (int i = 0; i < scoreDocs.length; i++) {
            Document doc = searcher.doc(scoreDocs[i].doc);
            Integer id = Integer.valueOf(doc.get("id"));
            if (!idList.contains(id)) {
                String indexedContent = doc.get("indexedContent");
                TokenStream tokenStream = analyzer.tokenStream("indexedContent", indexedContent);
                Map<String, String> data = loadQuery.getById(id);
                String highlighterString = highlighter.getBestFragment(tokenStream, indexedContent);
                if (highlighterString.contains(SEPARATOR)) {
                    String[] array = highlighterString.split(SEPARATOR);
                    data.put(title, array[0]);
                    if (array.length > 1) {
                        data.put("summary", array[1]);
                    }
                } else {
                    data.put("summary", highlighterString);
                }
                result.add(data);
                idList.add(id);
            }
        }
        return result;
    } catch (Exception e) {
        logger.error("search failed ...", e);
    }
    return new ArrayList<>();
}

---

From source file:com.admarketplace.isg.lucene.demo.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  .jav a  2s . co 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.aurel.track.lucene.search.LuceneSearcher.java

License:Open Source License

/**
 * Prepares an Indexsearcher object for an Index
 * @param index/*from   ww w  . j a  v  a  2 s . c  o m*/
 * @return
 */
public static IndexSearcher getIndexSearcher(int index) {
    Directory indexDir = LuceneUtil.getIndexDirectory(index);
    if (indexDir == null) {
        LOGGER.error("The index directory for " + index + " doesn't exist or is not a directory");
        return null;
    }
    //initialize the searcher
    //we will initialize always a new searcher because the data should be up to date
    /*
     *    Lucene FAQ: 
     *    1.   Make sure to open a new IndexSearcher after adding documents. 
     *       An IndexSearcher will only see the documents that were in the index in the moment it was opened.
     *    2.   It is recommended to use only one IndexSearcher from all threads in order to save memory
     *    Thanks for your help :) 
     */
    IndexSearcher is = null;
    try {
        IndexReader indexReader = DirectoryReader.open(indexDir);
        is = new IndexSearcher(indexReader);
    } catch (IOException e) {
        LOGGER.warn("Initializing the IndexSearcher for index " + index + " failed with " + e.getMessage());
        LOGGER.debug(ExceptionUtils.getStackTrace(e));
    }
    return is;
}

---

From source file:com.b2international.index.lucene.NullIndexSearcher.java

License:Apache License

private static DirectoryReader createRamReader() throws IOException {

    final RAMDirectory directory = new RAMDirectory();
    if (!DirectoryReader.indexExists(directory)) {

        final IndexWriterConfig conf = new IndexWriterConfig(new WhitespaceAnalyzer());
        final IndexWriter writer = new IndexWriter(directory, conf);
        writer.commit();/*from   w  w w.j av a  2 s. com*/
        writer.close();
    }

    return DirectoryReader.open(directory);

}

---

From source file:com.bah.lucene.blockcache_v2.CacheDirectoryTest.java

License:Apache License

@Test
public void test3() throws IOException, InterruptedException {
    // Thread.sleep(30000);
    IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_43, new KeywordAnalyzer());
    IndexWriter writer = new IndexWriter(_cacheDirectory, conf);
    int docs = 100000;
    for (int i = 0; i < docs; i++) {
        if (i % 500 == 0) {
            System.out.println(i);
        }//from w  w w  .ja  v a 2s. c  om
        writer.addDocument(newDoc());
        // Thread.sleep(1);
    }
    writer.close();
    System.out.println("done writing");

    DirectoryReader reader = DirectoryReader.open(_cacheDirectory);
    System.out.println("done opening");
    assertEquals(docs, reader.numDocs());

    Document document = reader.document(0);
    System.out.println("done fetching");
    System.out.println(document);

    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("test", "test")), 10);
    System.out.println("done searching");
    assertEquals(docs, topDocs.totalHits);

    reader.close();
}

---

From source file:com.basistech.lucene.tools.LuceneQueryTool.java

License:Apache License

public static void main(String[] args)
        throws IOException, org.apache.lucene.queryparser.classic.ParseException {
    String charsetName = Charset.defaultCharset().name();
    if (!"UTF-8".equals(charsetName)) {
        // Really only a problem on mac, where the default charset is MacRoman,
        // and it cannot be changed via the system Locale.
        System.err.println(String.format("defaultCharset is %s, but we require UTF-8.", charsetName));
        System.err.println("Set -Dfile.encoding=UTF-8 on the Java command line, or");
        System.err.println("set JAVA_TOOL_OPTIONS=-Dfile.encoding=UTF-8 in the environment.");
        System.exit(1);/* w  w w. j  a va2 s . c o  m*/
    }

    Options options = LuceneQueryTool.createOptions();
    CommandLineParser parser = new GnuParser();
    CommandLine cmdline = null;
    try {
        cmdline = parser.parse(options, args);
        validateOptions(options, args);
    } catch (org.apache.commons.cli.ParseException e) {
        System.err.println(e.getMessage());
        usage(options);
        System.exit(1);
    }
    String[] remaining = cmdline.getArgs();
    if (remaining != null && remaining.length > 0) {
        System.err.println("unknown extra args found: " + Lists.newArrayList(remaining));
        usage(options);
        System.exit(1);
    }

    String[] indexPaths = cmdline.getOptionValues("index");
    IndexReader[] readers = new IndexReader[indexPaths.length];
    for (int i = 0; i < indexPaths.length; i++) {
        Path path = FileSystems.getDefault().getPath(indexPaths[i]);
        readers[i] = DirectoryReader.open(FSDirectory.open(path));
    }
    IndexReader reader = new MultiReader(readers, true);

    LuceneQueryTool that = new LuceneQueryTool(reader);

    String opt;
    opt = cmdline.getOptionValue("query-limit");
    if (opt != null) {
        that.setQueryLimit(Integer.parseInt(opt));
    }
    opt = cmdline.getOptionValue("output-limit");
    if (opt != null) {
        that.setOutputLimit(Integer.parseInt(opt));
    }
    opt = cmdline.getOptionValue("analyzer");
    if (opt != null) {
        that.setAnalyzer(opt);
    }
    opt = cmdline.getOptionValue("query-field");
    if (opt != null) {
        that.setDefaultField(opt);
    }
    opt = cmdline.getOptionValue("output");
    PrintStream out = null;
    if (opt != null) {
        out = new PrintStream(new FileOutputStream(new File(opt)), true);
        that.setOutputStream(out);
    }
    if (cmdline.hasOption("show-id")) {
        that.setShowId(true);
    }
    if (cmdline.hasOption("show-hits")) {
        that.setShowHits(true);
    }
    if (cmdline.hasOption("show-score")) {
        that.setShowScore(true);
    }
    if (cmdline.hasOption("sort-fields")) {
        that.setSortFields(true);
    }

    boolean suppressNames = cmdline.hasOption("suppress-names");
    Formatter.Format format = Formatter.Format.MULTILINE;
    opt = cmdline.getOptionValue("format");
    if (opt != null) {
        format = Formatter.Format.fromName(opt);
    }
    if (cmdline.hasOption("tabular")) {
        // compatibility option
        format = Formatter.Format.TABULAR;
    }
    that.setFormatter(Formatter.newInstance(format, suppressNames));

    String[] opts;
    opts = cmdline.getOptionValues("fields");
    if (opts != null) {
        that.setFieldNames(Lists.newArrayList(opts));
    }
    opt = cmdline.getOptionValue("regex");
    if (opt != null) {
        Pattern p = Pattern.compile("^(.*?):/(.*)/$");
        Matcher m = p.matcher(opt);
        if (m.matches()) {
            that.setRegex(m.group(1), Pattern.compile(m.group(2)));
        } else {
            System.err.println("Invalid regex, should be field:/regex/");
            usage(options);
            System.exit(1);
        }
    }
    opts = cmdline.getOptionValues("query");
    that.run(opts);
    if (out != null) {
        out.close();
    }
    reader.close();
}

---

From source file:com.basistech.lucene.tools.LuceneQueryToolTest.java

License:Apache License

@BeforeClass
public static void oneTimeSetup() throws IOException, ParseException {
    LuceneQueryToolTest.showOutput = false; // for debugging tests
    Directory dir = new RAMDirectory();
    Analyzer analyzer = new StandardAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    IndexWriter writer = new IndexWriter(dir, config);
    Document doc = new Document();
    doc.add(new Field("longest-mention", "Bill Clinton", StringField.TYPE_STORED));
    doc.add(new Field("context", "Hillary Clinton Arkansas", TextField.TYPE_NOT_STORED));
    writer.addDocument(doc);/*from   w w w  . java2s.  c  om*/
    doc = new Document();
    doc.add(new Field("longest-mention", "George W. Bush", StringField.TYPE_STORED));
    doc.add(new Field("context", "Texas Laura Bush", TextField.TYPE_NOT_STORED));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new Field("longest-mention", "George H. W. Bush", StringField.TYPE_STORED));
    doc.add(new Field("context", "Barbara Bush Texas", TextField.TYPE_NOT_STORED));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new Field("bbb", "foo", StringField.TYPE_STORED));
    doc.add(new Field("bbb", "bar", StringField.TYPE_STORED));
    doc.add(new Field("aaa", "foo", StringField.TYPE_STORED));
    FieldType typeUnindexed = new FieldType(StringField.TYPE_STORED);
    typeUnindexed.setIndexOptions(IndexOptions.NONE);
    doc.add(new Field("zzz", "foo", typeUnindexed));
    writer.addDocument(doc);
    writer.close();
    reader = DirectoryReader.open(dir);
}

---

From source file:com.basistech.lucene.tools.LuceneQueryToolTest.java

License:Apache License

@Test
public void testBinaryField() throws IOException, ParseException {
    Directory dir = new RAMDirectory();
    Analyzer analyzer = new StandardAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    IndexWriter writer = new IndexWriter(dir, config);
    Document doc = new Document();
    doc.add(new Field("id", "1", StringField.TYPE_STORED));
    doc.add(new Field("binary-field", "ABC".getBytes(Charsets.UTF_8), StoredField.TYPE));
    writer.addDocument(doc);/*w ww  . ja v a 2  s  . c o  m*/
    writer.close();
    reader = DirectoryReader.open(dir);

    ByteArrayOutputStream bytes = new ByteArrayOutputStream();
    PrintStream out = new PrintStream(bytes);
    LuceneQueryTool lqt = new LuceneQueryTool(reader, out);
    lqt.run(new String[] { "id:1" });
    String result = Joiner.on('\n').join(getOutput(bytes));
    assertTrue(result.contains("0x414243")); // binary rep of "ABC"
}

---

From source file:com.bdaum.zoom.lal.internal.LireActivator.java

License:Open Source License

public IndexReader createBaseIndexReader(File indexPath) throws IOException {
    return DirectoryReader.open(SimpleFSDirectory.open(indexPath.toPath()));
}

---

• «
• 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
• »