@VisibleForTesting
public static SegmentAnalysis finalizeAnalysis(SegmentAnalysis analysis) {
return new SegmentAnalysis(
analysis.getId(),
analysis.getIntervals() != null
? JodaUtils.condenseIntervals(analysis.getIntervals())
: null,
analysis.getColumns(),
analysis.getSize(),
analysis.getNumRows(),
analysis.getAggregators(),
analysis.getQueryGranularity());
}
@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 (AggregatorFactory aggregator : analysis.getAggregators().values()) {
AggregatorFactory merged = aggregators.get(aggregator.getName());
if (merged != null) {
try {
merged = merged.getMergingFactory(aggregator);
} catch (AggregatorFactoryNotMergeableException e) {
merged = null;
}
} else {
merged = aggregator;
}
aggregators.put(aggregator.getName(), 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 QueryGranularity queryGranularity =
QueryGranularity.mergeQueryGranularities(
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";
}
return new SegmentAnalysis(
mergedId,
newIntervals,
columns,
arg1.getSize() + arg2.getSize(),
arg1.getNumRows() + arg2.getNumRows(),
aggregators.isEmpty() ? null : aggregators,
queryGranularity);
}