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

Introduction

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

Prototype

public abstract int maxDoc();

Source Link

Document

Returns one greater than the largest possible document number.

Usage

From source file:aos.lucene.search.advanced.CategorizerTest.java

License:Apache License

private void buildCategoryVectors() throws IOException {
    IndexReader reader = DirectoryReader.open(TestUtil.getBookIndexDirectory());

    int maxDoc = reader.maxDoc();

    for (int i = 0; i < maxDoc; i++) {
        if (!reader.isDeleted(i)) {
            Document doc = reader.document(i);
            String category = doc.get("category");

            Map vectorMap = (Map) categoryMap.get(category);
            if (vectorMap == null) {
                vectorMap = new TreeMap();
                categoryMap.put(category, vectorMap);
            }/*from  w  w  w  .j  a v a  2 s .  c om*/

            TermFreqVector termFreqVector = reader.getTermFreqVector(i, "subject");

            addTermFreqToMap(vectorMap, termFreqVector);
        }
    }
}

---

From source file:aos.lucene.search.ext.filters.SpecialsFilter.java

License:Apache License

public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    OpenBitSet bits = new OpenBitSet(reader.maxDoc());

    String[] isbns = accessor.isbns(); //

    int[] docs = new int[1];
    int[] freqs = new int[1];

    for (String isbn : isbns) {
        if (isbn != null) {
            TermDocs termDocs = reader.termDocs(new Term("isbn", isbn)); //
            int count = termDocs.read(docs, freqs);
            if (count == 1) {
                bits.set(docs[0]);//from  www. j a va  2  s  . c  o m
            }
        }
    }

    return bits;
}

---

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);// w w  w  .  j a  v  a 2s .c  o  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:br.bireme.ngrams.NGrams.java

public static void export(NGIndex index, final NGSchema schema, final String outFile,
        final String outFileEncoding) throws IOException {
    if (index == null) {
        throw new NullPointerException("index");
    }//w  ww.j a  v a 2  s.  co  m
    if (schema == null) {
        throw new NullPointerException("schema");
    }
    if (outFile == null) {
        throw new NullPointerException("outFile");
    }
    if (outFileEncoding == null) {
        throw new NullPointerException("outFileEncoding");
    }
    final Parameters parameters = schema.getParameters();
    final TreeMap<Integer, String> fields = new TreeMap<>();
    final IndexReader reader = index.getIndexSearcher().getIndexReader();
    final int maxdoc = reader.maxDoc();
    //final Bits liveDocs = MultiFields.getLiveDocs(reader);
    final Bits liveDocs = MultiBits.getLiveDocs(reader);
    final BufferedWriter writer = Files.newBufferedWriter(Paths.get(outFile), Charset.forName(outFileEncoding),
            StandardOpenOption.CREATE, StandardOpenOption.WRITE);

    boolean first = true;

    for (Map.Entry<Integer, br.bireme.ngrams.Field> entry : parameters.sfields.entrySet()) {
        fields.put(entry.getKey(), entry.getValue().name + NOT_NORMALIZED_FLD);
    }

    for (int docID = 0; docID < maxdoc; docID++) {
        if ((liveDocs != null) && (!liveDocs.get(docID)))
            continue;
        final Document doc = reader.document(docID);

        if (first) {
            first = false;
        } else {
            writer.newLine();
        }
        writer.append(doc2pipe(doc, fields));
    }
    writer.close();
    reader.close();
}

---

From source file:br.bireme.ngrams.TestIndex.java

public static boolean test(final IndexReader ireader, final NGSchema schema)
        throws IOException, ParserConfigurationException, SAXException {
    final Parameters parameters = schema.getParameters();
    final Map<String, Field> fields = parameters.getNameFields();
    boolean bad = false;

    for (int id = 0; id < ireader.maxDoc(); id++) {
        final Document doc = ireader.document(id);

        if (id % 100000 == 0)
            System.out.println("+++ " + id);
        bad = badDocument(doc, fields);//from   ww  w . java  2s. com
        if (bad) {
            System.out.println("BAD DOCUMENT => id: " + doc.get("id"));
            break;
        }
    }
    ireader.close();

    return !bad;
}

---

From source file:ca.gnewton.lusql.core.ViewIndex.java

License:Apache License

/**
 * Describe <code>main</code> method here.
 *
 * @param args a <code>String</code> value
 */// w  ww.j a v  a  2 s  . co m
public static final void main(final String[] args) {
    try {
        IndexReader reader = IndexReader.open(FSDirectory.open(new File(args[0])));
        System.out.println("# of documents indexed: " + (reader.maxDoc() - 1));

        int maxDoc = reader.maxDoc();
        for (int i = 0; i < maxDoc; i++) {
            Document doc = reader.document(i);
            printDoc(doc, i);

        }

        reader.close();
    } catch (Throwable t) {
        t.printStackTrace();
    }

}

---

From source file:cc.twittertools.index.ExtractTweetidsFromIndex.java

License:Apache License

@SuppressWarnings("static-access")
public static void main(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(//from w ww.j av  a 2 s. co m
            OptionBuilder.withArgName("dir").hasArg().withDescription("index location").create(INDEX_OPTION));

    CommandLine cmdline = null;
    CommandLineParser parser = new GnuParser();
    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        System.exit(-1);
    }

    if (!cmdline.hasOption(INDEX_OPTION)) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(ExtractTweetidsFromIndex.class.getName(), options);
        System.exit(-1);
    }

    File indexLocation = new File(cmdline.getOptionValue(INDEX_OPTION));
    if (!indexLocation.exists()) {
        System.err.println("Error: " + indexLocation + " does not exist!");
        System.exit(-1);
    }

    IndexReader reader = DirectoryReader.open(FSDirectory.open(indexLocation));
    PrintStream out = new PrintStream(System.out, true, "UTF-8");
    for (int i = 0; i < reader.maxDoc(); i++) {
        Document doc = reader.document(i);
        out.println(doc.getField(StatusField.ID.name).stringValue() + "\t"
                + doc.getField(StatusField.SCREEN_NAME.name).stringValue());
    }
    out.close();
    reader.close();
}

---

From source file:ccc.plugins.search.lucene.AclFilter.java

License:Open Source License

/** {@inheritDoc} */
@Override/*from www  . j  av  a  2  s.  co  m*/
public DocIdSet getDocIdSet(final IndexReader reader) throws IOException {

    // Assume all documents are invalid.
    final OpenBitSet docs = new OpenBitSet(reader.maxDoc());

    // Validate accessible documents.
    for (int i = 0; i < reader.maxDoc(); i++) {
        final Document d = reader.document(i);
        final Field aclField = d.getField(_field);
        if (null != aclField && _ac.canRead(deserialise(aclField.getBinaryValue()))) {
            docs.set(i);
        }
    }

    return docs;
}

---

From source file:com.appspot.socialinquirer.server.service.impl.AnalysisServiceImpl.java

License:Apache License

@Override
public List<Tag> getTermVector(String title, String text) {
    RAMDirectory directory = null;/*from   w  w w.  j  a  va  2 s . co m*/
    IndexReader reader = null;
    Map<String, Tag> tagsMap = new HashMap<String, Tag>();

    try {
        directory = new RAMDirectory();

        IndexWriter writer = new IndexWriter(directory, new StandardAnalyzer(Version.LUCENE_CURRENT), true,
                MaxFieldLength.UNLIMITED);
        Document doc = new Document();

        doc.add(new Field("title", title, Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.YES));
        doc.add(new Field("body", stripHtmlTags(text, true), Field.Store.YES, Field.Index.ANALYZED,
                Field.TermVector.YES));
        writer.addDocument(doc);

        writer.close();
        reader = IndexReader.open(directory, true);
        int numDocs = reader.maxDoc();
        for (int i = 0; i < numDocs; i++) {
            TermFreqVector termFreqVector = reader.getTermFreqVector(i, "title");
            pullTags(termFreqVector, tagsMap);
            termFreqVector = reader.getTermFreqVector(i, "body");
            pullTags(termFreqVector, tagsMap);
        }

    } catch (Exception e) {
        logger.log(Level.SEVERE, "An error occured while pulling tags from text.", e);
    } finally {
        closeIndexReader(reader);
        closeRAMDirectory(directory);
    }
    ArrayList<Tag> tagsList = new ArrayList<Tag>(tagsMap.values());
    Collections.sort(tagsList, new Comparator<Tag>() {
        @Override
        public int compare(Tag o1, Tag o2) {
            return o2.getFreqency() - o1.getFreqency();
        }
    });

    return tagsList;
}

---

From source file:com.bloatit.data.search.DaoFeatureSearchFilter.java

License:Open Source License

@Override
public DocIdSet getDocIdSet(final IndexReader reader) throws IOException {
    final OpenBitSet bitSet = new OpenBitSet(reader.maxDoc());
    bitSet.set(0, reader.maxDoc()); // Set all document ok

    if (filteredTerms != null) {
        for (final Pair<String, String> pair : filteredTerms) {
            final TermDocs termDocs = reader.termDocs(new Term(pair.key, pair.value.toLowerCase()));
            while (termDocs.next()) {
                bitSet.clear(termDocs.doc());
            }/*from  w w w  .  j  av a  2s .  c  o  m*/
        }
    }
    return bitSet;
}

---

• «
• 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
• »