Examples with ClusteredDistribution org.apache.spark.sql.connector.distributions.ClusteredDistribution used on opensource projects

Example 1 with ClusteredDistribution

use of org.apache.spark.sql.connector.distributions.ClusteredDistribution in project iceberg by apache.

the class SparkDistributionAndOrderingUtil method buildPositionMergeDistribution.

private static Distribution buildPositionMergeDistribution(Table table, DistributionMode distributionMode) {
    switch(distributionMode) {
        case NONE:
            return Distributions.unspecified();
        case HASH:
            if (table.spec().isUnpartitioned()) {
                Expression[] clustering = new Expression[] { SPEC_ID, PARTITION, FILE_PATH };
                return Distributions.clustered(clustering);
            } else {
                Distribution dataDistribution = buildRequiredDistribution(table, distributionMode);
                Expression[] dataClustering = ((ClusteredDistribution) dataDistribution).clustering();
                Expression[] deleteClustering = new Expression[] { SPEC_ID, PARTITION };
                Expression[] clustering = ObjectArrays.concat(deleteClustering, dataClustering, Expression.class);
                return Distributions.clustered(clustering);
            }
        case RANGE:
            Distribution dataDistribution = buildRequiredDistribution(table, distributionMode);
            SortOrder[] dataOrdering = ((OrderedDistribution) dataDistribution).ordering();
            SortOrder[] deleteOrdering = new SortOrder[] { SPEC_ID_ORDER, PARTITION_ORDER, FILE_PATH_ORDER };
            SortOrder[] ordering = ObjectArrays.concat(deleteOrdering, dataOrdering, SortOrder.class);
            return Distributions.ordered(ordering);
        default:
            throw new IllegalArgumentException("Unexpected distribution mode: " + distributionMode);
    }
}