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:org.dbpedia.spotlight.lucene.similarity.TermCache.java

License:Apache License

public OpenBitSet createDocIdSet(IndexReader reader, Term term) throws IOException {
    OpenBitSet result = new OpenBitSet(reader.maxDoc());
    TermDocs td = reader.termDocs();//from ww  w.j a  v  a 2 s  . co m
    int c = 0;
    td.seek(term);
    while (td.next()) {
        c++;
        result.set(td.doc());
    }
    return result;
}

---

From source file:org.dbpedia.spotlight.lucene.similarity.TermsFilter.java

License:Apache License

@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    OpenBitSet result = new OpenBitSet(reader.maxDoc());
    TermDocs td = reader.termDocs();/*from   w  ww.  ja  v a2s  .  co  m*/
    try {
        int c = 0;
        for (Iterator<Term> iter = terms.iterator(); iter.hasNext();) {
            Term term = iter.next();
            td.seek(term);
            while (td.next()) {
                c++;
                result.set(td.doc());
            }
        }
    } finally {
        td.close();
    }
    return result;
}

---

From source file:org.drftpd.vfs.index.lucene.LuceneEngine.java

License:Open Source License

public void renameInode(ImmutableInodeHandle fromInode, ImmutableInodeHandle toInode) throws IndexException {
    IndexSearcher iSearcher = null;//from  w w  w. java 2s  . co  m
    IndexReader iReader = null;
    try {
        Term fromInodeTerm = makeFullPathTermFromInode(fromInode);
        synchronized (INDEX_DOCUMENT) {
            _iWriter.updateDocument(fromInodeTerm, makeDocumentFromInode(toInode));
        }
        if (toInode.isDirectory()) {
            PrefixQuery prefixQuery = new PrefixQuery(fromInodeTerm);

            iReader = IndexReader.open(_iWriter, true);
            iSearcher = new IndexSearcher(iReader);

            final BitSet bits = new BitSet(iReader.maxDoc());
            iSearcher.search(prefixQuery, new Collector() {
                private int docBase;

                // ignore scorer
                public void setScorer(Scorer scorer) {
                }

                // accept docs out of order (for a BitSet it doesn't matter)
                public boolean acceptsDocsOutOfOrder() {
                    return true;
                }

                public void collect(int doc) {
                    bits.set(doc + docBase);
                }

                public void setNextReader(IndexReader reader, int docBase) {
                    this.docBase = docBase;
                }
            });

            for (int i = bits.nextSetBit(0); i >= 0; i = bits.nextSetBit(i + 1)) {
                Document doc = iSearcher.doc(i, SIMPLE_FIELD_SELECTOR);

                String oldPath = doc.getFieldable(FIELD_FULL_PATH.name()).stringValue();
                String newPath = toInode.getPath() + oldPath.substring(fromInode.getPath().length());
                doc.removeField(FIELD_FULL_PATH.name());
                doc.removeField(FIELD_PARENT_PATH.name());

                synchronized (INDEX_DOCUMENT) {
                    FIELD_FULL_PATH.setValue(newPath);
                    if (newPath.equals(VirtualFileSystem.separator)) {
                        FIELD_PARENT_PATH.setValue("");
                    } else {
                        FIELD_PARENT_PATH
                                .setValue(VirtualFileSystem.stripLast(newPath) + VirtualFileSystem.separator);
                    }
                    doc.add(FIELD_FULL_PATH);
                    doc.add(FIELD_PARENT_PATH);
                    _iWriter.updateDocument(makeFullPathTermFromString(oldPath), doc);
                }
            }
        }
    } catch (CorruptIndexException e) {
        throw new IndexException(
                "Unable to rename " + fromInode.getPath() + " to " + toInode.getPath() + " in the index", e);
    } catch (IOException e) {
        throw new IndexException(
                "Unable to rename " + fromInode.getPath() + " to " + toInode.getPath() + " in the index", e);
    } finally {
        if (iSearcher != null) {
            try {
                iSearcher.close();
            } catch (IOException e) {
                logger.error("IOException closing IndexSearcher", e);
            }
        }
        if (iReader != null) {
            try {
                iReader.close();
            } catch (IOException e) {
                logger.error("IOException closing IndexReader obtained from the IndexWriter", e);
            }
        }
    }
}

---

From source file:org.dyndns.andreasbaumann.LuceneAnalyzer.java

License:Open Source License

private static void printGlobalInfo(IndexReader indexReader, boolean printHeaders, boolean isSolr,
        SolrIndexSearcher solrSearch) throws IOException {
    if (printHeaders) {
        System.out.println("Global Information:");
        System.out.println("===================");
    }// www  .  jav a2  s. c o m

    System.out.println("\tnumber of documents: " + indexReader.numDocs());

    // we should get the number of features differently, this is inefficient, but Lucene
    // has no notion of global statistics (because the default weighting schema doesn't
    // make use of it!)
    int nofFeatures = 0;
    int nofTokens = 0;
    TermEnum terms = indexReader.terms();
    while (terms.next()) {
        Term term = terms.term();
        int df = terms.docFreq();
        nofFeatures++;
        nofTokens += df;
    }
    System.out.println("\ttotal number of features: " + nofFeatures);
    System.out.println("\ttotal number of tokens: " + nofTokens);

    System.out.println("\tversion: " + indexReader.getVersion());
    System.out.println("\tstill current: " + indexReader.isCurrent());

    //TODO: we don't get segment information!
    //System.out.println( "is optimized:" + segmentInfos.size( ) == 1 && !indexReader.hasDeletions( ) );
    System.out.println("\tmaximal document number: " + indexReader.maxDoc());
    System.out.println("\thas deletions: " + indexReader.hasDeletions());

    if (isSolr) {
        System.out.println("\tSolr version: " + solrSearch.getVersion());
    }

    System.out.println("");
}

---

From source file:org.eclipse.che.api.search.server.impl.LuceneSearcher.java

License:Open Source License

private void printStatistic() throws IOException {
    if (LOG.isDebugEnabled()) {
        IndexSearcher luceneSearcher = null;
        try {/*from  w  ww  .  ja  v  a 2  s . c o  m*/
            searcherManager.maybeRefresh();
            luceneSearcher = searcherManager.acquire();
            IndexReader reader = luceneSearcher.getIndexReader();
            LOG.debug(
                    "IndexReader numDocs={} numDeletedDocs={} maxDoc={} hasDeletions={}. Writer numDocs={} numRamDocs={} hasPendingMerges={}  hasUncommittedChanges={} hasDeletions={}",
                    reader.numDocs(), reader.numDeletedDocs(), reader.maxDoc(), reader.hasDeletions(),
                    luceneIndexWriter.numDocs(), luceneIndexWriter.numRamDocs(),
                    luceneIndexWriter.hasPendingMerges(), luceneIndexWriter.hasUncommittedChanges(),
                    luceneIndexWriter.hasDeletions());
        } finally {
            searcherManager.release(luceneSearcher);
        }
    }
}

---

From source file:org.eclipse.rdf4j.sail.lucene.LuceneIndex.java

License:Open Source License

private void logIndexStats() {
    try {/*ww  w .j  a v  a2  s  . co m*/
        IndexReader reader = null;
        try {
            reader = getIndexReader();

            Document doc;
            int totalFields = 0;

            Set<String> ids = new HashSet<String>();
            String[] idArray;
            int count = 0;
            for (int i = 0; i < reader.maxDoc(); i++) {
                if (isDeleted(reader, i))
                    continue;
                doc = readDocument(reader, i, null);
                totalFields += doc.getFields().size();
                count++;
                idArray = doc.getValues("id");
                for (String id : idArray)
                    ids.add(id);

            }

            logger.info("Total documents in the index: " + reader.numDocs()
                    + ", number of deletable documents in the index: " + reader.numDeletedDocs()
                    + ", valid documents: " + count + ", total fields in all documents: " + totalFields
                    + ", average number of fields per document: " + ((double) totalFields) / reader.numDocs());
            logger.info("Distinct ids in the index: " + ids.size());

        } finally {
            ReaderMonitor toCloseCurrentMonitor = currentMonitor;
            currentMonitor = null;
            if (toCloseCurrentMonitor != null) {
                toCloseCurrentMonitor.closeWhenPossible();
            }
        }
    } catch (IOException e) {
        logger.warn(e.getMessage(), e);
    }

}

---

From source file:org.elasticsearch.action.fieldstats.TransportFieldStatsTransportAction.java

License:Apache License

@Override
protected FieldStatsShardResponse shardOperation(FieldStatsShardRequest request) {
    ShardId shardId = request.shardId();
    Map<String, FieldStats> fieldStats = new HashMap<>();
    IndexService indexServices = indicesService.indexServiceSafe(shardId.getIndex());
    MapperService mapperService = indexServices.mapperService();
    IndexShard shard = indexServices.shardSafe(shardId.id());
    try (Engine.Searcher searcher = shard.acquireSearcher("fieldstats")) {
        for (String field : request.getFields()) {
            MappedFieldType fieldType = mapperService.fullName(field);
            if (fieldType != null) {
                IndexReader reader = searcher.reader();
                Terms terms = MultiFields.getTerms(reader, field);
                if (terms != null) {
                    fieldStats.put(field, fieldType.stats(terms, reader.maxDoc()));
                }//from  w w  w.  j  av a 2 s .c om
            } else {
                throw new IllegalArgumentException("field [" + field + "] doesn't exist");
            }
        }
    } catch (IOException e) {
        throw ExceptionsHelper.convertToElastic(e);
    }
    return new FieldStatsShardResponse(shardId, fieldStats);
}

---

From source file:org.elasticsearch.common.lucene.docset.DocIdSetCollector.java

License:Apache License

public DocIdSetCollector(Collector collector, IndexReader reader) {
    this.collector = collector;
    this.docIdSet = new OpenBitSetDISI(reader.maxDoc());
}

---

From source file:org.elasticsearch.common.lucene.docset.DocSets.java

License:Apache License

public static DocSet convert(IndexReader reader, DocIdSet docIdSet) throws IOException {
    if (docIdSet == null) {
        return DocSet.EMPTY_DOC_SET;
    } else if (docIdSet instanceof DocSet) {
        return (DocSet) docIdSet;
    } else if (docIdSet instanceof OpenBitSet) {
        return new OpenBitDocSet((OpenBitSet) docIdSet);
    } else {/*from  w w w .  j  a va  2s  .com*/
        final DocIdSetIterator it = docIdSet.iterator();
        // null is allowed to be returned by iterator(),
        // in this case we wrap with the empty set,
        // which is cacheable.
        return (it == null) ? DocSet.EMPTY_DOC_SET : new OpenBitDocSet(it, reader.maxDoc());
    }
}

---

From source file:org.elasticsearch.common.lucene.docset.DocSets.java

License:Apache License

/**
 * Returns a cacheable version of the doc id set (might be the same instance provided as a parameter).
 *//*  w w  w.  j a  va2 s. c  o m*/
public static DocSet cacheable(IndexReader reader, DocIdSet docIdSet) throws IOException {
    if (docIdSet == null) {
        return DocSet.EMPTY_DOC_SET;
    } else if (docIdSet.isCacheable() && (docIdSet instanceof DocSet)) {
        return (DocSet) docIdSet;
    } else if (docIdSet instanceof OpenBitSet) {
        return new OpenBitDocSet((OpenBitSet) docIdSet);
    } else {
        final DocIdSetIterator it = docIdSet.iterator();
        // null is allowed to be returned by iterator(),
        // in this case we wrap with the empty set,
        // which is cacheable.
        return (it == null) ? DocSet.EMPTY_DOC_SET : new OpenBitDocSet(it, reader.maxDoc());
    }
}

---

• «
• 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
• »