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:com.tamingtext.tagging.LuceneCategoryExtractor.java

License:Apache License

/** dump the values stored in the specified field for each document.
 * /*from   w w  w  . ja  va 2s .co m*/
 *  <pre>term(tab)document_frequency</pre>
 *  
 * @param indexDir the index to read.
 * @param field the name of the field.
 * @param out the print writer output will be written to
 * @throws IOException
 */
public static void dumpDocumentFields(File indexDir, String field, long maxDocs, PrintWriter out)
        throws IOException {
    Directory dir = FSDirectory.open(indexDir);
    IndexReader reader = IndexReader.open(dir, true);
    int max = reader.maxDoc();
    for (int i = 0; i < max; i++) {
        if (!reader.isDeleted(i)) {
            Document d = reader.document(i);
            for (Field f : d.getFields(field)) {
                if (f.isStored() && !f.isBinary()) {
                    String value = f.stringValue();
                    if (value != null) {
                        out.printf("%s\n", value);
                    }
                }
            }
        }
    }
}

---

From source file:com.tamingtext.tagging.LuceneTagExtractor.java

License:Apache License

public static void dumpDocs(File indexDir, PrintWriter out, long maxDocs) throws IOException {
    Directory dir = FSDirectory.open(indexDir);
    IndexReader reader = IndexReader.open(dir, true);
    int max = reader.maxDoc();

    StringBuilder buf = new StringBuilder();

    for (int i = 0; i < max; i++) {
        if (!reader.isDeleted(i)) {
            buf.setLength(0);/*w  w w  . j av  a2 s  .  c  o m*/
            appendVectorTerms(buf, reader.getTermFreqVector(i, "description-clustering"));
            appendVectorTerms(buf, reader.getTermFreqVector(i, "extended-clustering"));
            emitTermsForTags(out, buf, reader, reader.getTermFreqVector(i, "tag"));
        }
    }
}

---

From source file:com.Yasna.forum.database.FieldFilter.java

License:Open Source License

public BitSet bits(IndexReader reader) throws IOException {
    //Create a new BitSet with a capacity equal to the size of the index.
    BitSet bits = new BitSet(reader.maxDoc());
    //Get an enumeration of all the documents that match the specified field
    //value./*from   ww  w.  jav a 2s.c  om*/
    TermDocs matchingDocs = reader.termDocs(searchTerm);
    try {
        while (matchingDocs.next()) {
            bits.set(matchingDocs.doc());
        }
    } finally {
        if (matchingDocs != null) {
            matchingDocs.close();
        }
    }
    return bits;
}

---

From source file:com.zimbra.cs.index.RawIndexEditor.java

License:Open Source License

void dumpAll() throws IOException {
    IndexReader reader = IndexReader.open(luceneDirectory);
    try {/*from www  . jav  a  2s .c om*/
        int maxDoc = reader.maxDoc();
        System.out.println("There are " + maxDoc + " documents in this index.");

        for (int i = 0; i < maxDoc; i++) {
            dumpDocument(reader.document(i), reader.isDeleted(i));
        }
    } finally {
        reader.close();
    }
}

---

From source file:com.zimbra.cs.index.TermsFilter.java

License:Open Source License

/** (non-Javadoc)
 * @see org.apache.lucene.search.Filter#getDocIdSet(org.apache.lucene.index.IndexReader)
 *//*from ww  w.  ja va 2s.com*/
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    OpenBitSet result = new OpenBitSet(reader.maxDoc());
    TermDocs td = reader.termDocs();
    try {
        for (Iterator<Term> iter = terms.iterator(); iter.hasNext();) {
            Term term = iter.next();
            td.seek(term);
            while (td.next()) {
                result.set(td.doc());
            }
        }
    } finally {
        Closeables.closeQuietly(td);
    }
    return result;
}

---

From source file:com.zimbra.cs.rmgmt.RemoteMailQueue.java

License:Open Source License

private void list0(SearchResult result, IndexReader indexReader, int offset, int limit) throws IOException {
    if (ZimbraLog.rmgmt.isDebugEnabled()) {
        ZimbraLog.rmgmt.debug("listing offset=" + offset + " limit=" + limit + " " + this);
    }//from   w ww .java2 s  .co  m
    int max = indexReader.maxDoc();

    int skip = 0;
    int listed = 0;

    for (int i = 0; i < max; i++) {
        if (indexReader.isDeleted(i)) {
            continue;
        }

        if (skip < offset) {
            skip++;
            continue;
        }

        Document doc = indexReader.document(i);
        Map<QueueAttr, String> qitem = docToQueueItem(doc);
        result.qitems.add(qitem);

        listed++;
        if (listed == limit) {
            break;
        }
    }
    result.hits = getNumMessages();
}

---

From source file:db.infiniti.config.HighFreqTerms.java

License:Apache License

private String getTheBestMatchingTerm(IndexReader indexReader, TermStats[] terms, ArrayList<String> sentQueries,
        ArrayList<String> initialQuery) {
    String specificFreqTerm = "";
    if (sentQueries.size() == 0 && terms.length > 0) {
        String temp = terms[0].term + "";
        temp = temp.substring(temp.indexOf(":") + 1, temp.length());
        return temp;
    }/*from  w ww  .ja  v  a 2s. co m*/

    HashMap<String, Integer> averageOfEach = new HashMap<String, Integer>();
    for (int i = 0; i < terms.length; i++) {
        String temp = terms[i].term + "";
        String queryATerm = temp.substring(temp.indexOf(":") + 1, temp.length());
        try {
            // indexReader = IndexReader.open(indexDirectory);
            IndexSearcher indexSearcher = new IndexSearcher(indexReader);
            // int n = w.numDocs();
            BooleanQuery bq = new BooleanQuery();
            int totalNumberOfResults = 0;
            // double average = 0;
            for (String queryB : sentQueries) {
                Term term1 = new Term("text", queryATerm);
                TermQuery query1 = new TermQuery(term1);
                Term term2 = new Term("text", queryB);
                TermQuery query2 = new TermQuery(term2);

                bq.add(query1, BooleanClause.Occur.MUST);
                bq.add(query2, BooleanClause.Occur.MUST);
                int numberOfResults = 0;
                HitCollector results;
                int n = indexReader.maxDoc();
                TopDocs hits = indexSearcher.search(bq, n);

                /*   if (hits.totalHits > 0 ){
                      System.out.println();
                   }*/
                totalNumberOfResults = totalNumberOfResults + hits.totalHits;
            }
            averageOfEach.put(queryATerm, totalNumberOfResults);
            // average = (double) totalNumberOfResults / (double)
            // sentQueries.size();

        } catch (CorruptIndexException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    Set<Entry<String, Integer>> set = averageOfEach.entrySet();
    List<Entry<String, Integer>> list = new ArrayList<Entry<String, Integer>>(set);
    Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
        public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2) {
            return (o2.getValue()).compareTo(o1.getValue());
        }
    });
    System.out.println("sorted by relevance to previous submitted queries: ");
    for (Map.Entry<String, Integer> entry : list) {
        System.out.println(entry.getKey() + " ==== " + entry.getValue());
    }
    int i = list.size() - 1;
    while (i >= 0) {
        specificFreqTerm = list.get(i).getKey();
        if (!initialQuery.contains(specificFreqTerm)) {
            return specificFreqTerm;
        } else {
            i--;
        }
    }

    return specificFreqTerm;
}

---

From source file:de.ks.flatadocdb.index.GlobalIndexTest.java

License:Apache License

@Test
public void testRecreateLuceneIndex() throws Exception {
    IndexReader indexReader = luceneIndex.getIndexReader();
    assertEquals(0, indexReader.maxDoc());

    luceneIndex.recreate();//  ww  w .  j a va2 s  . co  m

    indexReader = luceneIndex.getIndexReader();
    assertEquals(COUNT, indexReader.maxDoc());
}

---

From source file:de.mirkosertic.desktopsearch.LuceneIndexHandler.java

License:Open Source License

public void cleanupDeadContent() throws IOException {
    searcherManager.maybeRefreshBlocking();
    IndexSearcher theSearcher = searcherManager.acquire();

    try {//from   w  w  w.j a  va 2  s. c o m
        IndexReader theReader = theSearcher.getIndexReader();
        for (int i = 0; i < theReader.maxDoc(); i++) {
            Document theDocument = theReader.document(i);
            File theFile = new File(theDocument.getField(IndexFields.FILENAME).stringValue());
            if (!theFile.exists()) {
                LOGGER.info("Removing file " + theFile + " from index as it does not exist anymore.");
                String theUniqueID = theDocument.getField(IndexFields.UNIQUEID).stringValue();
                indexWriter.deleteDocuments(new Term(IndexFields.UNIQUEID, theUniqueID));
            }
        }
    } finally {
        searcherManager.release(theSearcher);
    }
}

---

From source file:de.tudarmstadt.ukp.teaching.uima.nounDecompounding.ranking.TotalFreqAmout.java

License:Open Source License

/**
 * Adds all frequency values for a special directory
 * @return/*  www.ja  va  2s  . c o m*/
 * @throws IOException
 */
protected BigInteger countFreq(FSDirectory dir) throws IOException {
    BigInteger count = BigInteger.valueOf(0);

    IndexReader reader = IndexReader.open(dir);
    for (int i = 0; i < reader.maxDoc(); i++) {
        if (reader.isDeleted(i)) {
            continue;
        }

        Document doc = reader.document(i);
        count = count.add(new BigInteger(doc.get("freq")));
    }

    return count;
}

---

• «
• 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
• »