Example usage for org.apache.lucene.index IndexReader close

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexReader close.

Prototype

@Override
public final synchronized void close() throws IOException 

Source Link

Document

Closes files associated with this index.

Usage

From source file:edu.coeia.tasks.ExtensionFrequencyTask.java

License:Open Source License

private int getFactor() throws IOException {
    Directory directory = FSDirectory.open(new File(this.caseFacade.getCaseIndexFolderLocation()));

    IndexReader indexReader = IndexReader.open(directory);

    int factor = indexReader.maxDoc() / 200;
    indexReader.close();

    return factor;
}

---

From source file:edu.coeia.tasks.MultimediaLoadingTask.java

License:Open Source License

private void loadItems() throws IOException {
    String indexDir = this.caseFacade.getCaseIndexFolderLocation();
    Directory dir = FSDirectory.open(new File(indexDir));
    IndexReader indexReader = IndexReader.open(dir);

    for (int i = 0; i < indexReader.maxDoc(); i++) {
        if (this.isCancelledTask())
            break;

        Document document = indexReader.document(i);

        if (document != null) {
            Field field = document.getField(IndexingConstant.FILE_MIME);

            if (field != null && field.stringValue() != null) {
                String documentExtension = field.stringValue();
                final StringBuilder fullpath = new StringBuilder();

                if (type == MultimediaViewerPanel.TYPE.IMAGE && isImage(documentExtension)) {
                    fullpath.append(this.caseFacade.getFullPath(document.get(IndexingConstant.FILE_PATH)));
                } else if (type == MultimediaViewerPanel.TYPE.AUDIO && isAudio(documentExtension)) {
                    fullpath.append(this.caseFacade.getFullPath(document.get(IndexingConstant.FILE_PATH)));
                } else if (type == MultimediaViewerPanel.TYPE.ARCHIVE && isArchieve(documentExtension)) {
                    fullpath.append(this.caseFacade.getFullPath(document.get(IndexingConstant.FILE_PATH)));
                } else if (type == MultimediaViewerPanel.TYPE.VIDEO && isVideo(documentExtension)) {
                    fullpath.append(this.caseFacade.getFullPath(document.get(IndexingConstant.FILE_PATH)));
                }//from   w  w w.  ja  va2 s.c  o m

                if (!fullpath.toString().isEmpty()) {
                    EventQueue.invokeLater(new Runnable() {
                        @Override
                        public void run() {
                            File file = new File(fullpath.toString());
                            Object[] data = { file.getAbsolutePath(), FileUtil.getExtension(file),
                                    file.lastModified(), file.isHidden(), file.length() };
                            JTableUtil.addRowToJTable(panel.getTable(), data);
                        }
                    });
                }
            }
        }
    }

    indexReader.close();
}

---

From source file:edu.cuhk.hccl.cmd.AppSearchEngine.java

License:Apache License

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

    // Get parameters
    CommandLineParser parser = new BasicParser();
    Options options = createOptions();/*from ww  w  . j  a  v a  2 s . co m*/

    File dataFolder = null;
    String queryStr = null;
    int topK = 0;
    File resultFile = null;
    String queryType = null;
    File similarityFile = null;

    try {
        CommandLine line = parser.parse(options, args);

        dataFolder = new File(line.getOptionValue('d'));
        queryStr = line.getOptionValue('q');
        queryType = line.getOptionValue('t');

        topK = Integer.parseInt(line.getOptionValue('k'));
        resultFile = new File(line.getOptionValue('f'));
        similarityFile = new File(line.getOptionValue('s'));

        if (line.hasOption('m')) {
            String modelPath = line.getOptionValue('m');

            if (queryType.equalsIgnoreCase("WordVector")) {
                expander = new WordVectorExpander(modelPath);
            } else if (queryType.equalsIgnoreCase("WordNet")) {
                expander = new WordNetExpander(modelPath);
            } else {
                System.out.println("Please choose a correct expander: WordNet or WordVector!");
                System.exit(-1);
            }
        }

    } catch (ParseException exp) {
        System.out.println("Error in parameters: \n" + exp.getMessage());
        System.exit(-1);
    }

    // Create Index
    StandardAnalyzer analyzer = new StandardAnalyzer();
    Directory index = createIndex(dataFolder, analyzer);

    // Build query
    Query query = buildQuery(analyzer, queryStr, queryType);

    // Search index for topK hits
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopScoreDocCollector collector = TopScoreDocCollector.create(topK, true);
    searcher.search(query, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    // Show search results
    System.out.println("\n[INFO] " + hits.length + " hits were returned:");
    List<String> hitLines = new ArrayList<String>();

    for (int i = 0; i < hits.length; i++) {
        int docId = hits[i].doc;
        Document d = searcher.doc(docId);

        String line = (i + 1) + "\t" + d.get(PATH_FIELD) + "\t" + hits[i].score;

        System.out.println(line);

        hitLines.add(line);
    }

    // Compute cosine similarity between documents
    List<String> simLines = new ArrayList<String>();
    for (int m = 0; m < hits.length; m++) {
        int doc1 = hits[m].doc;
        Terms terms1 = reader.getTermVector(doc1, CONTENT_FIELD);

        for (int n = m + 1; n < hits.length; n++) {
            int doc2 = hits[n].doc;
            Terms terms2 = reader.getTermVector(doc2, CONTENT_FIELD);

            CosineDocumentSimilarity cosine = new CosineDocumentSimilarity(terms1, terms2);
            double similarity = cosine.getCosineSimilarity();
            String line = searcher.doc(doc1).get(PATH_FIELD) + "\t" + searcher.doc(doc2).get(PATH_FIELD) + "\t"
                    + similarity;
            simLines.add(line);
        }
    }

    // Release resources
    reader.close();
    if (expander != null) {
        expander.close();
    }

    // Save search results
    System.out.println("\n[INFO] Search results are saved in file: " + resultFile.getPath());
    FileUtils.writeLines(resultFile, hitLines, false);

    System.out.println("\n[INFO] Cosine similarities are saved in file: " + similarityFile.getPath());
    FileUtils.writeLines(similarityFile, simLines, false);
}

---

From source file:edu.ehu.galan.lite.algorithms.ranked.supervised.tfidf.corpus.lucene.CorpusHighFreqTerms.java

License:Open Source License

/**
 *
 * Extracts the top n most frequent terms (by document frequency ) from an existing Lucene index
 * (the dir must be specified via args or via tfidfTester on
 * /resources/lite/configs/general.conf) in this case the Wikipedia corpus) and reports their
 * document frequency./*ww  w  .  j ava  2s .  c o m*/
 *
 * @param args
 * @throws java.lang.Exception
 */
public static void main(String[] args) throws Exception {
    try {
        Properties prop = new Properties();
        InputStream is = new FileInputStream("resources/lite/configs/general.conf");
        FSDirectory dir;
        if (args.length == 1) {
            if (Paths.get(args[0]).toFile().isDirectory()) {
                dir = FSDirectory.open(new File(args[0]));
            } else {
                System.out.println("The specified directory does not exist\n"
                        + " backing to load the lucene index specified in the config files");
                dir = FSDirectory.open(new File(prop.getProperty("tfidfTester")));
            }
        } else if (args.length > 1) {
            System.out.println("The args only need one parameter, the directory of the Lucene Index\n "
                    + "backing to load the lucene index specified in the config files");
            dir = FSDirectory.open(new File(prop.getProperty("tfidfTester")));
        } else {
            dir = FSDirectory.open(new File(prop.getProperty("tfidfTester")));
        }
        IndexReader reader = null;
        String field = null;
        boolean IncludeTermFreqs = false;
        prop.load(is);
        IncludeTermFreqs = true;
        reader = DirectoryReader.open(dir);
        System.out.println("num Docs " + reader.numDocs());
        TermStats[] terms = getHighFreqTerms(reader, numTerms, field);
        if (!IncludeTermFreqs) {
            //default HighFreqTerms behavior
            for (int i = 0; i < terms.length; i++) {
                System.out.printf("%s:%s %,d \n", terms[i].field, terms[i].termtext.utf8ToString(),
                        terms[i].docFreq);
            }
        } else {
            TermStats[] termsWithTF = sortByTotalTermFreq(reader, terms);
            for (int i = 0; i < termsWithTF.length; i++) {
                System.out.printf("%s:%s \t totalTF = %,d \t doc freq = %,d \n", termsWithTF[i].field,
                        termsWithTF[i].termtext.utf8ToString(), termsWithTF[i].totalTermFreq,
                        termsWithTF[i].docFreq);
            }
        }
        reader.close();
    } catch (Exception ex) {
        logger.error("The directory specified contains a Lucene index?", ex);
    }
}

---

From source file:edu.harvard.iq.dvn.core.index.Indexer.java

License:Apache License

public void deleteVersionDocuments(long studyId) {
    try {/*  w  w w .j  a v  a  2 s . c  o m*/
        IndexReader reader = IndexReader.open(dir, false);
        reader.deleteDocuments(new Term("versionStudyId", Long.toString(studyId)));
        reader.close();
    } catch (IOException ex) {
        ex.printStackTrace();
    }
}

---

From source file:edu.harvard.iq.dvn.core.index.Indexer.java

License:Apache License

protected void updateStudyDocument(long studyId, String field, String value) throws IOException {
    IndexReader reader = IndexReader.open(dir, false);

    try {//from w ww .  jav a2s  . c om
        if (reader != null) {
            TermDocs matchingDocuments = reader.termDocs();

            if (matchingDocuments != null) {
                int c = 1;
                if (matchingDocuments.next()) {
                    // We only expect 1 document when searching by study id.
                    Document studyDocument = reader.document(matchingDocuments.doc());

                    logger.fine("processing matching document number " + c++);
                    if (studyDocument != null) {
                        logger.fine("got a non-zero doc;");

                        reader.close();
                        reader = null;

                        logger.fine("deleted the document;");

                        //updateDocument(studyDocument, studyId);
                        IndexWriter localWriter = new IndexWriter(dir, getAnalyzer(), isIndexEmpty(),
                                IndexWriter.MaxFieldLength.UNLIMITED);
                        localWriter.updateDocument(new Term("id", Long.toString(studyId)), studyDocument);

                        localWriter.commit();
                        localWriter.close();
                        logger.fine("wrote the updated version of the document;");

                    }
                }
            }
        }

    } catch (IOException ex) {
        ex.printStackTrace();
    } finally {
        if (reader != null) {
            reader.close();
        }
    }
}

---

From source file:edu.mit.ll.vizlinc.highlight.WeightedSpanTermExtractor.java

License:Apache License

private void closeReaders() {
    Collection<IndexReader> readerSet = readers.values();

    for (final IndexReader reader : readerSet) {
        try {/*ww w. j a v  a  2  s.  c om*/
            reader.close();
        } catch (IOException e) {
            // alert?
        }
    }
}

---

From source file:edu.siena.cs.sawus.search.Searcher.java

License:Apache License

/** Simple command-line based search demo. */
public static void search(String index) throws Exception {

    String field = "contents";
    String queries = null;// w ww  .  ja  v  a2 s  .co  m
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;

    IndexReader reader = IndexReader.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;
        }
    }
    //searcher.close();
    reader.close();
}

---

From source file:edu.stanford.muse.index.Indexer.java

License:Apache License

private synchronized Directory copyDirectoryExcludeFields(Directory dir, String out_basedir, String out_name,
        String... fields_to_be_removed) throws IOException {
    IndexReader reader = DirectoryReader.open(dir); // IndexReader.open(dir, true); // read-only=true

    Directory newDir = createDirectory(out_basedir, out_name);
    IndexWriter writer = openIndexWriter(newDir);
    //log.info("Removing field(s) " + Util.join(fields_to_be_removed, ", ") + " from index.");

    for (int i = 0; i < reader.numDocs(); i++) {
        org.apache.lucene.document.Document doc = reader.document(i);
        for (String field : fields_to_be_removed)
            doc.removeFields(field);//from  w  w  w .j av  a  2 s .  c  o  m
        writer.addDocument(doc);
    }

    writer.close();
    reader.close();

    return newDir;
}

---

From source file:edu.stanford.muse.index.Indexer.java

License:Apache License

private synchronized Directory copyDirectoryWithDocFilter(Directory dir, String out_basedir, String out_name,
        FilterFunctor filter_func) throws IOException {
    long startTime = System.currentTimeMillis();
    IndexReader reader = DirectoryReader.open(dir); // IndexReader.open(dir, true); // read-only=true

    Directory newDir = createDirectory(out_basedir, out_name);
    IndexWriter writer = openIndexWriter(newDir);
    //log.info("Removing field(s) " + Util.join(fields_to_be_removed, ", ") + " from index.");

    int count = 0;
    for (int i = 0; i < reader.numDocs(); i++) {
        org.apache.lucene.document.Document doc = reader.document(i);
        if (filter_func == null || filter_func.filter(doc)) {
            writer.addDocument(doc);//w  ww . ja  va 2  s.  c om
            count++;
        }
    }

    writer.close();
    reader.close();

    log.info("CopyDirectoryWithtDocFilter to dir:" + out_basedir + " name: " + baseDir + " time: "
            + (System.currentTimeMillis() - startTime) + " ms docs: " + count);
    return newDir;
}

---

• «
• 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
• 49
• 50
• »