Examples with ColumnAnalysis io.druid.query.metadata.metadata.ColumnAnalysis used on opensource projects

Example 21 with ColumnAnalysis

use of io.druid.query.metadata.metadata.ColumnAnalysis in project druid by druid-io.

the class SegmentAnalyzer method analyzeStringColumn.

private ColumnAnalysis analyzeStringColumn(final ColumnCapabilities capabilities, final StorageAdapter storageAdapter, final String columnName) {
    int cardinality = 0;
    long size = 0;
    Comparable min = null;
    Comparable max = null;
    if (analyzingCardinality()) {
        cardinality = storageAdapter.getDimensionCardinality(columnName);
    }
    if (analyzingSize()) {
        final long start = storageAdapter.getMinTime().getMillis();
        final long end = storageAdapter.getMaxTime().getMillis();
        final Sequence<Cursor> cursors = storageAdapter.makeCursors(null, new Interval(start, end), VirtualColumns.EMPTY, Granularities.ALL, false);
        size = cursors.accumulate(0L, new Accumulator<Long, Cursor>() {

            @Override
            public Long accumulate(Long accumulated, Cursor cursor) {
                DimensionSelector selector = cursor.makeDimensionSelector(new DefaultDimensionSpec(columnName, columnName));
                if (selector == null) {
                    return accumulated;
                }
                long current = accumulated;
                while (!cursor.isDone()) {
                    final IndexedInts vals = selector.getRow();
                    for (int i = 0; i < vals.size(); ++i) {
                        final String dimVal = selector.lookupName(vals.get(i));
                        if (dimVal != null && !dimVal.isEmpty()) {
                            current += StringUtils.estimatedBinaryLengthAsUTF8(dimVal);
                        }
                    }
                    cursor.advance();
                }
                return current;
            }
        });
    }
    if (analyzingMinMax()) {
        min = storageAdapter.getMinValue(columnName);
        max = storageAdapter.getMaxValue(columnName);
    }
    return new ColumnAnalysis(capabilities.getType().name(), capabilities.hasMultipleValues(), size, cardinality, min, max, null);
}

Example 22 with ColumnAnalysis

use of io.druid.query.metadata.metadata.ColumnAnalysis in project druid by druid-io.

the class SegmentMetadataQueryQueryToolChest method mergeAnalyses.

@VisibleForTesting
public static SegmentAnalysis mergeAnalyses(final SegmentAnalysis arg1, final SegmentAnalysis arg2, boolean lenientAggregatorMerge) {
    if (arg1 == null) {
        return arg2;
    }
    if (arg2 == null) {
        return arg1;
    }
    List<Interval> newIntervals = null;
    if (arg1.getIntervals() != null) {
        newIntervals = Lists.newArrayList();
        newIntervals.addAll(arg1.getIntervals());
    }
    if (arg2.getIntervals() != null) {
        if (newIntervals == null) {
            newIntervals = Lists.newArrayList();
        }
        newIntervals.addAll(arg2.getIntervals());
    }
    final Map<String, ColumnAnalysis> leftColumns = arg1.getColumns();
    final Map<String, ColumnAnalysis> rightColumns = arg2.getColumns();
    Map<String, ColumnAnalysis> columns = Maps.newTreeMap();
    Set<String> rightColumnNames = Sets.newHashSet(rightColumns.keySet());
    for (Map.Entry<String, ColumnAnalysis> entry : leftColumns.entrySet()) {
        final String columnName = entry.getKey();
        columns.put(columnName, entry.getValue().fold(rightColumns.get(columnName)));
        rightColumnNames.remove(columnName);
    }
    for (String columnName : rightColumnNames) {
        columns.put(columnName, rightColumns.get(columnName));
    }
    final Map<String, AggregatorFactory> aggregators = Maps.newHashMap();
    if (lenientAggregatorMerge) {
        // Merge each aggregator individually, ignoring nulls
        for (SegmentAnalysis analysis : ImmutableList.of(arg1, arg2)) {
            if (analysis.getAggregators() != null) {
                for (Map.Entry<String, AggregatorFactory> entry : analysis.getAggregators().entrySet()) {
                    final String aggregatorName = entry.getKey();
                    final AggregatorFactory aggregator = entry.getValue();
                    AggregatorFactory merged = aggregators.get(aggregatorName);
                    if (merged != null) {
                        try {
                            merged = merged.getMergingFactory(aggregator);
                        } catch (AggregatorFactoryNotMergeableException e) {
                            merged = null;
                        }
                    } else {
                        merged = aggregator;
                    }
                    aggregators.put(aggregatorName, merged);
                }
            }
        }
    } else {
        final AggregatorFactory[] aggs1 = arg1.getAggregators() != null ? arg1.getAggregators().values().toArray(new AggregatorFactory[arg1.getAggregators().size()]) : null;
        final AggregatorFactory[] aggs2 = arg2.getAggregators() != null ? arg2.getAggregators().values().toArray(new AggregatorFactory[arg2.getAggregators().size()]) : null;
        final AggregatorFactory[] merged = AggregatorFactory.mergeAggregators(Arrays.asList(aggs1, aggs2));
        if (merged != null) {
            for (AggregatorFactory aggregator : merged) {
                aggregators.put(aggregator.getName(), aggregator);
            }
        }
    }
    final TimestampSpec timestampSpec = TimestampSpec.mergeTimestampSpec(Lists.newArrayList(arg1.getTimestampSpec(), arg2.getTimestampSpec()));
    final Granularity queryGranularity = Granularity.mergeGranularities(Lists.newArrayList(arg1.getQueryGranularity(), arg2.getQueryGranularity()));
    final String mergedId;
    if (arg1.getId() != null && arg2.getId() != null && arg1.getId().equals(arg2.getId())) {
        mergedId = arg1.getId();
    } else {
        mergedId = "merged";
    }
    final Boolean rollup;
    if (arg1.isRollup() != null && arg2.isRollup() != null && arg1.isRollup().equals(arg2.isRollup())) {
        rollup = arg1.isRollup();
    } else {
        rollup = null;
    }
    return new SegmentAnalysis(mergedId, newIntervals, columns, arg1.getSize() + arg2.getSize(), arg1.getNumRows() + arg2.getNumRows(), aggregators.isEmpty() ? null : aggregators, timestampSpec, queryGranularity, rollup);
}

Example 23 with ColumnAnalysis

use of io.druid.query.metadata.metadata.ColumnAnalysis in project druid by druid-io.

the class SegmentMetadataQueryRunnerFactory method createRunner.

@Override
public QueryRunner<SegmentAnalysis> createRunner(final Segment segment) {
    return new QueryRunner<SegmentAnalysis>() {

        @Override
        public Sequence<SegmentAnalysis> run(Query<SegmentAnalysis> inQ, Map<String, Object> responseContext) {
            SegmentMetadataQuery query = (SegmentMetadataQuery) inQ;
            final SegmentAnalyzer analyzer = new SegmentAnalyzer(query.getAnalysisTypes());
            final Map<String, ColumnAnalysis> analyzedColumns = analyzer.analyze(segment);
            final long numRows = analyzer.numRows(segment);
            long totalSize = 0;
            if (analyzer.analyzingSize()) {
                // Initialize with the size of the whitespace, 1 byte per
                totalSize = analyzedColumns.size() * numRows;
            }
            Map<String, ColumnAnalysis> columns = Maps.newTreeMap();
            ColumnIncluderator includerator = query.getToInclude();
            for (Map.Entry<String, ColumnAnalysis> entry : analyzedColumns.entrySet()) {
                final String columnName = entry.getKey();
                final ColumnAnalysis column = entry.getValue();
                if (!column.isError()) {
                    totalSize += column.getSize();
                }
                if (includerator.include(columnName)) {
                    columns.put(columnName, column);
                }
            }
            List<Interval> retIntervals = query.analyzingInterval() ? Arrays.asList(segment.getDataInterval()) : null;
            final Map<String, AggregatorFactory> aggregators;
            Metadata metadata = null;
            if (query.hasAggregators()) {
                metadata = segment.asStorageAdapter().getMetadata();
                if (metadata != null && metadata.getAggregators() != null) {
                    aggregators = Maps.newHashMap();
                    for (AggregatorFactory aggregator : metadata.getAggregators()) {
                        aggregators.put(aggregator.getName(), aggregator);
                    }
                } else {
                    aggregators = null;
                }
            } else {
                aggregators = null;
            }
            final TimestampSpec timestampSpec;
            if (query.hasTimestampSpec()) {
                if (metadata == null) {
                    metadata = segment.asStorageAdapter().getMetadata();
                }
                timestampSpec = metadata != null ? metadata.getTimestampSpec() : null;
            } else {
                timestampSpec = null;
            }
            final Granularity queryGranularity;
            if (query.hasQueryGranularity()) {
                if (metadata == null) {
                    metadata = segment.asStorageAdapter().getMetadata();
                }
                queryGranularity = metadata != null ? metadata.getQueryGranularity() : null;
            } else {
                queryGranularity = null;
            }
            Boolean rollup = null;
            if (query.hasRollup()) {
                if (metadata == null) {
                    metadata = segment.asStorageAdapter().getMetadata();
                }
                rollup = metadata != null ? metadata.isRollup() : null;
                if (rollup == null) {
                    // in this case, this segment is built before no-rollup function is coded,
                    // thus it is built with rollup
                    rollup = Boolean.TRUE;
                }
            }
            return Sequences.simple(Arrays.asList(new SegmentAnalysis(segment.getIdentifier(), retIntervals, columns, totalSize, numRows, aggregators, timestampSpec, queryGranularity, rollup)));
        }
    };
}