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

Introduction

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

Prototype

public abstract int numDocs();

Source Link

Document

Returns the number of documents in this index.

Usage

From source file:org.elasticsearch.search.aggregations.bucket.significant.GlobalOrdinalsSignificantTermsAggregator.java

License:Apache License

@Override
public SignificantStringTerms buildEmptyAggregation() {
    // We need to account for the significance of a miss in our global stats - provide corpus size as context
    ContextIndexSearcher searcher = context.searchContext().searcher();
    IndexReader topReader = searcher.getIndexReader();
    int supersetSize = topReader.numDocs();
    return new SignificantStringTerms(0, supersetSize, name, bucketCountThresholds.getRequiredSize(),
            bucketCountThresholds.getMinDocCount(), termsAggFactory.getSignificanceHeuristic(),
            Collections.<InternalSignificantTerms.Bucket>emptyList(), pipelineAggregators(), metaData());
}

From source file:org.elasticsearch.search.aggregations.bucket.significant.SignificantLongTermsAggregator.java

License:Apache License

@Override
public SignificantLongTerms buildEmptyAggregation() {
    // We need to account for the significance of a miss in our global stats - provide corpus size as context
    ContextIndexSearcher searcher = context.searchContext().searcher();
    IndexReader topReader = searcher.getIndexReader();
    int supersetSize = topReader.numDocs();
    return new SignificantLongTerms(0, supersetSize, name, formatter, bucketCountThresholds.getRequiredSize(),
            bucketCountThresholds.getMinDocCount(), termsAggFactory.getSignificanceHeuristic(),
            Collections.<InternalSignificantTerms.Bucket>emptyList(), pipelineAggregators(), metaData());
}

From source file:org.elasticsearch.search.aggregations.bucket.significant.SignificantTextAggregator.java

License:Apache License

@Override
public SignificantStringTerms buildEmptyAggregation() {
    // We need to account for the significance of a miss in our global stats - provide corpus size as context
    ContextIndexSearcher searcher = context.searcher();
    IndexReader topReader = searcher.getIndexReader();
    int supersetSize = topReader.numDocs();
    return new SignificantStringTerms(name, bucketCountThresholds.getRequiredSize(),
            bucketCountThresholds.getMinDocCount(), pipelineAggregators(), metaData(), format, 0, supersetSize,
            significanceHeuristic, emptyList());
}

From source file:org.elasticsearch.search.query.TopDocsCollectorContext.java

License:Apache License

/**
 * Returns query total hit count if the <code>query</code> is a {@link MatchAllDocsQuery}
 * or a {@link TermQuery} and the <code>reader</code> has no deletions,
 * -1 otherwise./*from   ww  w.j  a v  a  2 s.  c  o  m*/
 */
static int shortcutTotalHitCount(IndexReader reader, Query query) throws IOException {
    while (true) {
        // remove wrappers that don't matter for counts
        // this is necessary so that we don't only optimize match_all
        // queries but also match_all queries that are nested in
        // a constant_score query
        if (query instanceof ConstantScoreQuery) {
            query = ((ConstantScoreQuery) query).getQuery();
        } else if (query instanceof BoostQuery) {
            query = ((BoostQuery) query).getQuery();
        } else {
            break;
        }
    }
    if (query.getClass() == MatchAllDocsQuery.class) {
        return reader.numDocs();
    } else if (query.getClass() == TermQuery.class && reader.hasDeletions() == false) {
        final Term term = ((TermQuery) query).getTerm();
        int count = 0;
        for (LeafReaderContext context : reader.leaves()) {
            count += context.reader().docFreq(term);
        }
        return count;
    } else {
        return -1;
    }
}

From source file:org.elasticsearch.search.query.TopDocsCollectorContext.java

License:Apache License

/**
 * Creates a {@link TopDocsCollectorContext} from the provided <code>searchContext</code>
 *//*from   w w w. j  a  v  a 2  s  .co m*/
static TopDocsCollectorContext createTopDocsCollectorContext(SearchContext searchContext, IndexReader reader,
        boolean shouldCollect) throws IOException {
    final Query query = searchContext.query();
    // top collectors don't like a size of 0
    final int totalNumDocs = Math.max(1, reader.numDocs());
    if (searchContext.size() == 0) {
        // no matter what the value of from is
        return new TotalHitCountCollectorContext(reader, query, shouldCollect);
    } else if (searchContext.scrollContext() != null) {
        // no matter what the value of from is
        int numDocs = Math.min(searchContext.size(), totalNumDocs);
        return new ScrollingTopDocsCollectorContext(searchContext.scrollContext(), searchContext.sort(),
                numDocs, searchContext.trackScores(), searchContext.numberOfShards());
    } else if (searchContext.collapse() != null) {
        int numDocs = Math.min(searchContext.from() + searchContext.size(), totalNumDocs);
        return new CollapsingTopDocsCollectorContext(searchContext.collapse(), searchContext.sort(), numDocs,
                searchContext.trackScores());
    } else {
        int numDocs = Math.min(searchContext.from() + searchContext.size(), totalNumDocs);
        final boolean rescore = searchContext.rescore().isEmpty() == false;
        if (rescore) {
            assert searchContext.sort() == null;
            for (RescoreContext rescoreContext : searchContext.rescore()) {
                numDocs = Math.max(numDocs, rescoreContext.getWindowSize());
            }
        }
        return new SimpleTopDocsCollectorContext(searchContext.sort(), searchContext.searchAfter(), numDocs,
                searchContext.trackScores()) {
            @Override
            boolean shouldRescore() {
                return rescore;
            }
        };
    }
}

From source file:org.elasticsearch.search.suggest.Suggester.java

License:Apache License

public Suggest.Suggestion<? extends Suggest.Suggestion.Entry<? extends Suggest.Suggestion.Entry.Option>> execute(
        String name, T suggestion, IndexReader indexReader, CharsRef spare) throws IOException {
    // #3469 We want to ignore empty shards
    if (indexReader.numDocs() == 0) {
        return null;
    }//from www  .j  a v  a 2  s.  com
    return innerExecute(name, suggestion, indexReader, spare);
}

From source file:org.elbe.relations.indexer.lucene.LuceneIndexer.java

License:Open Source License

@Override
public int numberOfIndexed(final File inIndexDir) throws IOException {
    int outNumber = 0;
    final IndexReader lReader = IndexReader.open(FSDirectory.getDirectory(inIndexDir));
    try {//  w w w  .j  a  va  2 s  .c o m
        outNumber = lReader.numDocs();
    } finally {
        lReader.close();
    }
    return outNumber;
}

From source file:org.exoplatform.services.jcr.impl.core.query.lucene.IndexFormatVersion.java

License:Apache License

/**
 * @return the index format version of the index used by the given
 * index reader./*from w w w . j  a v a  2s  .  c  o m*/
 */
public static IndexFormatVersion getVersion(IndexReader indexReader) {
    Collection fields = indexReader.getFieldNames(IndexReader.FieldOption.ALL);
    if ((fields.contains(FieldNames.INDEX) && fields.contains(FieldNames.PATH)) || indexReader.numDocs() == 0) {
        return IndexFormatVersion.V4;
    } else if (fields.contains(FieldNames.LOCAL_NAME)) {
        return IndexFormatVersion.V3;
    } else if (fields.contains(FieldNames.PROPERTIES_SET)) {
        return IndexFormatVersion.V2;
    } else {
        return IndexFormatVersion.V1;
    }
}

From source file:org.frontcache.cache.impl.LuceneIndexManager.java

License:Apache License

/**
 * //  www  .j a  v a2 s .c  o  m
 * @return
 */
public List<String> getKeys() {

    IndexWriter iWriter = null;
    try {
        iWriter = getIndexWriter();
        if (iWriter == null) {
            return Collections.emptyList();
        }
    } catch (Exception e1) {
        logger.debug("Error during getting indexWriter. " + e1.getMessage());
        return Collections.emptyList();
    }

    List<String> keys = new ArrayList<String>();

    IndexReader reader = null;
    try {
        reader = DirectoryReader.open(iWriter);

        for (int i = 0; i < reader.numDocs(); i++) {
            Document doc = reader.document(i);
            if (null != doc) {
                if (null != doc.get(URL_FIELD))
                    keys.add(doc.get(URL_FIELD));
                else
                    logger.error("URL is null for doc (probably corrupted after/during index time) " + doc);
            }

        }
    } catch (Exception e) {
        logger.error("Error during loading urls/keys from index", e);
    } finally {
        if (reader != null) {
            try {
                reader.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

    return keys;
}

From source file:org.frontcache.cache.impl.LuceneIndexManager.java

License:Apache License

/**
 * Returns index size//  ww w .ja  v a  2 s. co  m
 * @return
 */
public int getIndexSize() {
    int n = -1;
    IndexReader reader = null;
    try {

        Directory dir = FSDirectory.open(Paths.get(INDEX_PATH));
        reader = DirectoryReader.open(dir);
        n = reader.numDocs();

    } catch (IOException e) {

        logger.error(e.getMessage(), e);
    } finally {

        if (null != reader) {
            try {
                reader.close();
            } catch (IOException e) {
                logger.error(e.getMessage(), e);
            }
        }
    }

    return n;
}