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.mycompany.mavenproject1.Main.java

public static void main(String[] args) throws IOException, ParseException {
    StandardAnalyzer analyzer = new StandardAnalyzer();
    //        Directory index = new RAMDirectory();
    Directory index = new SimpleFSDirectory(Paths.get(
            "C:\\Users\\slete\\Documents\\NetBeansProjects\\mavenproject1\\src\\main\\java\\com\\mycompany\\mavenproject1\\data"));
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    //config.setOpenMode(OpenMode.CREATE);
    IndexWriter w = new IndexWriter(index, config);
    try (ItemProvider provider = new ItemProvider(
            "C:\\Users\\slete\\Documents\\NetBeansProjects\\mavenproject1\\src\\main\\java\\com\\mycompany\\mavenproject1\\items.xml")) {

        while (provider.hasNext()) {
            Item item = provider.next();
            addItem(w, item);/*www  . ja  v  a  2s  .c  o  m*/

        }
    } catch (XMLStreamException | IOException ex) {
        ex.getMessage();
    }
    //        w.commit();
    w.close();

    //        String queryStr = "id:1* NOT id:19*";
    String a = "id:1* NOT id:19*";
    String b = "name:Dekielek AND description:(ty AND obiektywu)";
    String c = "category:Dek*";
    String ds = "id:1232~2";
    String e = "price:[0.0 TO 100.0]";

    Query q = new QueryParser("name", analyzer).parse(ds);

    int hitsPerPage = 10;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs docs = searcher.search(q, hitsPerPage);
    ScoreDoc[] hits = docs.scoreDocs;

    System.out.println("Found " + hits.length + " hits.");
    for (int i = 0; i < hits.length; ++i) {
        int docId = hits[i].doc;
        Document d = searcher.doc(docId);
        System.out
                .println(d.get("id") + "\t" + d.get("price") + "\t" + d.get("name") + "\t" + d.get("category"));//+"\t" + d.get("description"));
    }
}

From source file:com.mylucene.basiclucene.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 ww  .  j a v  a  2  s.  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_44);

    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_44, 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.nec.scg.senseRanking.CountTextSimilarity.java

private void init() {
    analyzer = new StandardAnalyzer(Version.LUCENE_43);
    try {//from w  w  w.  ja  va  2  s .co  m
        directory = FSDirectory.open(new File("D:\\KBTextIndex"));
        ireader = DirectoryReader.open(directory);
        isearcher = new IndexSearcher(ireader);
    } catch (IOException e) {
        e.printStackTrace();
    }
    cache = new StringIntegerCache(cache_file);
    cache.readCache();
}

From source file:com.netcrest.pado.index.provider.lucene.LuceneSearch.java

License:Open Source License

protected Set<Object> getIdentityKeySet(String queryString, Directory dir) {
    Set<Object> identityKeySet = new HashSet<Object>();
    DirectoryReader reader;/*from  ww w .  j  ava 2s  .c  o  m*/
    try {
        reader = DirectoryReader.open(dir);
    } catch (CorruptIndexException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    } catch (IOException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    }

    Query query;
    try {
        StandardQueryParser parser = new StandardQueryParser(new StandardAnalyzer(LUCENE_VERSION));
        query = parser.parse(queryString.replaceAll("\\-", "\\\\-"), "__doc");
    } catch (Exception ex) {
        // Lucene bug. Unable to serialize exception. Log the message and
        // throw a new exception with the string message.
        ex.printStackTrace();
        throw new PadoException(ex.getMessage());
    }
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results;
    try {
        results = searcher.search(query, null, Integer.MAX_VALUE);

        for (ScoreDoc hit : results.scoreDocs) {
            Document doc;
            try {
                doc = searcher.doc(hit.doc);
            } catch (CorruptIndexException e) {
                e.printStackTrace();
                throw new RuntimeException(e);
            } catch (IOException e) {
                e.printStackTrace();
                throw new RuntimeException(e);
            }
            //            IndexableField field = doc.getField("IdentityKey");
            //            if (field == null) {
            //               continue;
            //            }
            //            Object identityKey = field.stringValue();
            //            if (identityKey == null) {
            //               identityKey = field.numericValue();
            //            }
            //            if (identityKey == null) {
            //               BytesRef br = field.binaryValue();
            //               if (br != null) {
            //                  byte[] blob = br.bytes;
            //                  try {
            //                     identityKey = BlobHelper.deserializeBlob(blob);
            //                     identityKeySet.add(identityKey);
            //                  } catch (Exception ex) {
            //                     Logger.warning("Identity key deserialization error", ex);
            //                  }
            //               } else {
            //                  identityKey = field.toString();
            //               }
            //            }
            LuceneField luceneField = new LuceneField();
            ITemporalKey temporalKey = luceneField.getTemporalKey(doc);
            if (temporalKey != null) {
                identityKeySet.add(temporalKey.getIdentityKey());
            }
        }
    } catch (IOException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    }
    return identityKeySet;
}

From source file:com.netcrest.pado.index.provider.lucene.LuceneSearch.java

License:Open Source License

protected Set<ITemporalKey> getTemporalKeySet(String queryString, Directory dir) {
    Set<ITemporalKey> temporalKeySet = new HashSet<ITemporalKey>();
    DirectoryReader reader;/*from   w  ww.  j  a va2s.com*/
    try {
        reader = DirectoryReader.open(dir);
    } catch (CorruptIndexException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    } catch (IOException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    }
    Query query;
    try {
        StandardQueryParser parser = new StandardQueryParser(new StandardAnalyzer(LUCENE_VERSION));
        query = parser.parse(queryString.replaceAll("\\-", "\\\\-"), "__doc");
    } catch (Exception ex) {
        // Lucene 4.7 bug, internal message not serializable
        // Send message instead of nesting the cause.
        throw new RuntimeException(ex.getMessage());
    }

    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results;
    try {
        results = searcher.search(query, null, Integer.MAX_VALUE);

        for (ScoreDoc hit : results.scoreDocs) {
            Document doc;
            try {
                doc = searcher.doc(hit.doc);
            } catch (CorruptIndexException e) {
                e.printStackTrace();
                throw new RuntimeException(e);
            } catch (IOException e) {
                e.printStackTrace();
                throw new RuntimeException(e);
            }
            LuceneField luceneField = new LuceneField();
            ITemporalKey temporalKey = luceneField.getTemporalKey(doc);
            if (temporalKey != null) {
                temporalKeySet.add(temporalKey);
            }
        }
    } catch (IOException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    }
    return temporalKeySet;
}

From source file:com.netcrest.pado.index.provider.lucene.TopNLuceneSearch.java

License:Open Source License

protected Set<Object> getIdentityKeySet(String queryString, Directory dir) {
    Set<Object> identityKeySet = new HashSet<Object>();
    DirectoryReader reader;//ww w .  j a  v  a 2s  . c  o m
    try {
        reader = DirectoryReader.open(dir);
    } catch (CorruptIndexException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    } catch (IOException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    }

    Query query;
    try {
        StandardQueryParser parser = new StandardQueryParser(new StandardAnalyzer(LUCENE_VERSION));
        query = parser.parse(queryString.replaceAll("\\-", "\\\\-"), "__doc");
    } catch (Exception ex) {
        // Lucene bug. Unable to serialize exception. Log the message and
        // throw a new exception with the string message.
        ex.printStackTrace();
        throw new PadoException(ex.getMessage());
    }
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs results;
    try {
        results = searcher.search(query, null, Integer.MAX_VALUE);
        for (ScoreDoc hit : results.scoreDocs) {
            Document doc;
            try {
                doc = searcher.doc(hit.doc);
            } catch (CorruptIndexException e) {
                e.printStackTrace();
                throw new RuntimeException(e);
            } catch (IOException e) {
                e.printStackTrace();
                throw new RuntimeException(e);
            }
            // IndexableField field = doc.getField("IdentityKey");
            // if (field == null) {
            // continue;
            // }
            // Object identityKey = field.stringValue();
            // if (identityKey == null) {
            // identityKey = field.numericValue();
            // }
            // if (identityKey == null) {
            // BytesRef br = field.binaryValue();
            // if (br != null) {
            // byte[] blob = br.bytes;
            // try {
            // identityKey = BlobHelper.deserializeBlob(blob);
            // identityKeySet.add(identityKey);
            // } catch (Exception ex) {
            // Logger.warning("Identity key deserialization error", ex);
            // }
            // } else {
            // identityKey = field.toString();
            // }
            // }
            LuceneField luceneField = new LuceneField();
            ITemporalKey temporalKey = luceneField.getTemporalKey(doc);

            if (temporalKey != null) {
                float docScore = hit.score;
                identityKeySet.add(temporalKey.getIdentityKey());
            }
        }
    } catch (IOException e1) {
        e1.printStackTrace();
        throw new RuntimeException(e1);
    }
    return identityKeySet;
}

From source file:com.nuvolect.deepdive.lucene.Index.java

public static JSONObject index(final String volumeId, final String searchPath, final boolean forceIndex) {

    if (m_interrupt[0]) {

        LogUtil.log(LogUtil.LogType.INDEX, "Index canceled post interrupt");

        m_interrupt[0] = false;//from   ww w  .jav a  2 s  .  c om
        return responseInterruptIndexing();
    }

    OmniFile cacheDir = IndexUtil.getCacheDir(volumeId, searchPath);
    boolean cacheDirCreated = false;
    try {
        cacheDirCreated = OmniUtil.forceMkdir(cacheDir);
    } catch (IOException e) {
        return responseFolderCreateError(searchPath);
    }

    final String luceneDirPath = cacheDir.getAbsolutePath();

    boolean cacheDirExists = !cacheDirCreated;
    boolean indexingOngoing = m_indexThread != null && m_indexThread.isAlive();
    boolean indexingRequired = !cacheDirExists || forceIndex;

    synchronized (m_lock) {

        if (indexingOngoing) {

            if (m_fileTreeActive)
                m_index_state = INDEX_STATE.filetree;
            else
                m_index_state = INDEX_STATE.indexing;
        } else {
            if (indexingRequired)
                m_index_state = INDEX_STATE.indexing;
            else
                m_index_state = INDEX_STATE.complete;
        }
    }

    if (indexingRequired || indexingOngoing) {

        if (indexingOngoing) {

            // Nothing to do, let the background process run. Monitor m_indexedDocs for progress.
        } else {

            synchronized (m_lock) {
                m_index_state = INDEX_STATE.filetree;
                m_totalDocs[0] = 0;
                m_indexedDocs[0] = 0;
                m_error[0] = "";
            }
            m_threadGroup = new ThreadGroup(INDEX_THREAD_GROUP);
            m_indexThread = new Thread(m_threadGroup, new Runnable() {
                @Override
                public void run() {

                    //                        Analyzer analyzer = new org.apache.lucene.analysis.core.WhitespaceAnalyzer();
                    //                        Analyzer analyzer = new org.apache.lucene.analysis.core.KeywordAnalyzer();
                    //                        Analyzer analyzer = new org.apache.lucene.analysis.standard.StandardAnalyzer();
                    Analyzer analyzer = new org.apache.lucene.analysis.core.SimpleAnalyzer();
                    IndexWriterConfig config = new IndexWriterConfig(analyzer);
                    IndexWriter iwriter = null;

                    try {
                        Directory m_directory = FSDirectory.open(Paths.get(luceneDirPath));
                        iwriter = new IndexWriter(m_directory, config);
                        iwriter.deleteAll();
                        iwriter.commit();
                    } catch (IOException e) {
                        LogUtil.logException(LogUtil.LogType.INDEX, e);
                        m_error[0] = "IndexWriter constructor exception";
                    }

                    synchronized (m_lock) {
                        m_fileTreeActive = true;
                        m_index_state = INDEX_STATE.filetree;
                    }
                    Collection<OmniFile> files = IndexUtil.getFilePaths(volumeId, searchPath);

                    synchronized (m_lock) {
                        m_index_state = INDEX_STATE.indexing;
                        m_fileTreeActive = false;
                        m_totalDocs[0] = files.size();
                        m_indexedDocs[0] = 0;
                    }

                    try {

                        for (OmniFile file : files) {

                            if (m_interrupt[0]) {
                                LogUtil.log(LogUtil.LogType.INDEX, "Iterator loop canceled");
                                break;
                            }

                            String path = file.getPath();

                            //                                LogUtil.log(LogUtil.LogType.INDEX, "indexing: " + path);// this is a bit excessive
                            iwriter.addDocument(makeDoc(volumeId, path));
                            synchronized (m_lock) {
                                ++m_indexedDocs[0];
                            }
                        }

                        iwriter.commit();
                        iwriter.close();
                        synchronized (m_lock) {
                            m_index_state = m_interrupt[0] ? INDEX_STATE.interrupted : INDEX_STATE.complete;
                            m_totalDocs[0] = m_indexedDocs[0];
                        }

                    } catch (Exception e) {
                        LogUtil.logException(LogUtil.LogType.INDEX, e);
                        m_error[0] = "IndexWriter addDocument exception";
                    }
                }
            }, INDEX_THREAD, STACK_SIZE);

            m_indexThread.setPriority(Thread.MAX_PRIORITY);
            m_indexThread.start();
        }
    } else {

        // Indexing is complete
        // Get number of documents indexed
        try {
            Directory directory = FSDirectory.open(Paths.get(luceneDirPath));
            DirectoryReader ireader = DirectoryReader.open(directory);
            synchronized (m_lock) {
                m_indexedDocs[0] = ireader.numDocs();
                m_totalDocs[0] = m_indexedDocs[0];
                m_index_state = INDEX_STATE.complete;
            }
            ireader.close();
            directory.close();
        } catch (IOException e) {
            LogUtil.logException(LogUtil.LogType.INDEX, e);
        }
    }

    JSONObject result = new JSONObject();
    try {
        synchronized (m_lock) {
            result.put("index_state", m_index_state.toString());
            result.put("error", m_error[0]);
            result.put("indexed_docs", m_indexedDocs[0]);
            result.put("total_docs", m_totalDocs[0]);
            //                result.put("full_path", cacheDir.getAbsolutePath());
            result.put("search_path", searchPath);
        }
    } catch (JSONException e) {
        e.printStackTrace();
    }

    return result;
}

From source file:com.nuvolect.deepdive.lucene.Search.java

/**
 * Return results for a search along a specific path.  If the path is changed or new
 * create an index.//w  ww .  j av  a  2s .com
 * @param searchQuery
 * @param searchPath
 * @return
 */
public static JSONObject search(String searchQuery, String volumeId, String searchPath) {

    JSONObject result = new JSONObject();
    JSONArray jsonArray = new JSONArray();
    Context ctx = App.getContext();

    DirectoryReader ireader = null;
    ScoreDoc[] scoreDocs = null;
    String error = "";

    preSearch(volumeId, searchPath);
    try {
        ireader = DirectoryReader.open(m_directory);
    } catch (IOException e) {
        LogUtil.logException(LogUtil.LogType.SEARCH, e);
        error += e.toString();
    }
    IndexSearcher isearcher = new IndexSearcher(ireader);
    Query query = null;

    try {

        LogUtil.log(LogUtil.LogType.SEARCH,
                "query: " + searchQuery + ", vid: " + volumeId + ", path: " + searchPath);

        // Parse a simple query that searches for "text":
        QueryParser parser = new QueryParser(CConst.FIELD_CONTENT, m_analyzer);
        query = parser.parse(searchQuery);
        TopScoreDocCollector collector = TopScoreDocCollector.create(MAX_HITS);
        isearcher.search(query, collector);
        scoreDocs = collector.topDocs().scoreDocs;

    } catch (ParseException | IOException e) {
        LogUtil.logException(LogUtil.LogType.SEARCH, e);
        error += e.toString();
    }
    // Iterate through the results creating an object for each file
    HashMap<String, Integer> hitCounts = new HashMap<>();
    HashMap<String, Integer> hitIndexes = new HashMap<>();

    /**
     * First iterate the hit list and count duplicates based on file path.
     */
    for (int ii = 0; scoreDocs != null && ii < scoreDocs.length; ++ii) {

        Document hitDoc = null;
        int fileHits = 1;
        try {
            hitDoc = isearcher.doc(scoreDocs[ii].doc);

            Explanation explanation = isearcher.explain(query, scoreDocs[ii].doc);
            Explanation[] details = explanation.getDetails();
            String description = details[0].getDescription();

            /**
             * FIXME, find a better way to count hits in each file
             */
            if (description.contains("=")) {

                String[] lineParts = description.split("=");
                String[] elementParts = lineParts[2].split(Pattern.quote(")"));
                if (elementParts.length > 0) {

                    fileHits = ((int) Double.parseDouble(elementParts[0]));
                }
            }

        } catch (IOException e) {
            LogUtil.logException(LogUtil.LogType.SEARCH, e);
            error += e.toString();
        }
        String filePath = hitDoc.get((CConst.FIELD_PATH));

        if (hitCounts.containsKey(filePath)) {

            hitCounts.put(filePath, hitCounts.get(filePath) + fileHits);
        } else {
            hitCounts.put(filePath, fileHits);
            hitIndexes.put(filePath, ii);
        }
    }

    /**
     * Iterate over each unique hit and save the results
     */
    for (Map.Entry<String, Integer> uniqueHit : hitIndexes.entrySet()) {

        Document hitDoc = null;
        try {
            hitDoc = isearcher.doc(scoreDocs[uniqueHit.getValue()].doc);
        } catch (IOException e) {
            LogUtil.logException(LogUtil.LogType.SEARCH, e);
            error += e.toString();
        }
        String file_name = hitDoc.get((CConst.FIELD_FILENAME));
        String file_path = hitDoc.get((CConst.FIELD_PATH));
        try {
            String folder_url = OmniHash.getStartPathUrl(ctx, volumeId, file_path);

            JSONObject hitObj = new JSONObject();
            hitObj.put("volume_id", volumeId);
            hitObj.put("file_path", file_path);
            hitObj.put("file_name", file_name);
            hitObj.put("folder_url", folder_url);
            hitObj.put("num_hits", hitCounts.get(file_path));
            hitObj.put("error", error);
            jsonArray.put(hitObj);

        } catch (Exception e) {
            LogUtil.logException(LogUtil.LogType.SEARCH, e);
        }
    }
    int num_hits = scoreDocs != null ? scoreDocs.length : 0;

    try {
        result.put("hits", jsonArray != null ? jsonArray : new JSONArray());
        result.put("num_hits", num_hits);
        result.put("error", error);

        ireader.close();
        m_directory.close();

    } catch (JSONException | IOException e) {
        LogUtil.logException(LogUtil.LogType.SEARCH, e);
    }

    return result;
}

From source file:com.o19s.es.explore.ExplorerQueryTests.java

License:Apache License

@Before
public void setupIndex() throws Exception {
    dir = new RAMDirectory();

    try (IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER))) {
        for (int i = 0; i < docs.length; i++) {
            Document doc = new Document();
            doc.add(new Field("_id", Integer.toString(i + 1), StoredField.TYPE));
            doc.add(newTextField("text", docs[i], Field.Store.YES));
            indexWriter.addDocument(doc);
        }//from   w  w w .  j  a  v  a 2 s.co  m
    }

    reader = DirectoryReader.open(dir);
    searcher = new IndexSearcher(reader);
}

From source file:com.o19s.es.ltr.logging.LoggingFetchSubPhaseTests.java

License:Apache License

@BeforeClass
public static void init() throws Exception {
    directory = newDirectory(random());/* w  ww. j a  v  a  2  s  .  c  om*/

    try (IndexWriter writer = new IndexWriter(directory, newIndexWriterConfig(new StandardAnalyzer()))) {
        int nDoc = TestUtil.nextInt(random(), 20, 100);
        docs = new HashMap<>();
        for (int i = 0; i < nDoc; i++) {
            Document d = buildDoc(random().nextBoolean() ? "foo" : "bar", random().nextFloat());
            writer.addDocument(d);
            if (random().nextInt(4) == 0) {
                writer.commit();
            }
            docs.put(d.get("id"), d);
        }
        writer.commit();
    }
    IndexReader reader = closeAfterSuite(DirectoryReader.open(directory));
    searcher = new IndexSearcher(reader);
}