[GitHub] carbondata pull request #842: [CARBONDATA-937] Data loading for partition ta...

[qiuchenjian-2]

Github user QiangCai commented on a diff in the pull request:

    https://github.com/apache/carbondata/pull/842#discussion_r116036523
 
    --- Diff: core/src/main/java/org/apache/carbondata/core/scan/partition/RangePartitioner.java ---
    @@ -0,0 +1,132 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *    http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.carbondata.core.scan.partition;
    +
    +import java.io.Serializable;
    +import java.math.BigDecimal;
    +import java.util.List;
    +
    +import org.apache.carbondata.core.metadata.datatype.DataType;
    +import org.apache.carbondata.core.metadata.schema.PartitionInfo;
    +import org.apache.carbondata.core.util.ByteUtil;
    +
    +/**
    + * Range Partitioner
    + */
    +public class RangePartitioner implements Partitioner {
    +
    +  private int partitions;
    +  private Object[] bounds;
    +  private Comparator comparator;
    +
    +  public RangePartitioner(PartitionInfo partitionInfo) {
    +    List<String> values = partitionInfo.getRangeInfo();
    +    DataType partitionColumnDataType = partitionInfo.getColumnSchemaList().get(0).getDataType();
    +    partitions = values.size();
    +    bounds = new Object[partitions];
    +    if (partitionColumnDataType == DataType.STRING) {
    +      for (int i = 0; i < partitions; i++) {
    +        bounds[i] = ByteUtil.toBytes(values.get(i));
    +      }
    +    } else {
    +      for (int i = 0; i < partitions; i++) {
    +        bounds[i] = PartitionUtil.getDataBasedOnDataType(values.get(i), partitionColumnDataType);
    +      }
    +    }
    +
    +    switch (partitionColumnDataType) {
    +      case INT:
    +        comparator = new IntComparator();
    +        break;
    +      case SHORT:
    +        comparator = new ShortComparator();
    +        break;
    +      case DOUBLE:
    +        comparator = new DoubleComparator();
    +        break;
    +      case LONG:
    +      case DATE:
    +      case TIMESTAMP:
    +        comparator = new LongComparator();
    +        break;
    +      case DECIMAL:
    +        comparator = new BigDecimalComparator();
    +        break;
    +      default:
    +        comparator = new ByteArrayComparator();
    +    }
    +  }
    +
    +  @Override public int numPartitions() {
    +    return partitions + 1;
    +  }
    +
    +  @Override public int getPartition(Object key) {
    +    if (key == null) {
    +      return partitions;
    +    } else {
    +      for (int i = 0; i < partitions; i++) {
    +        if (comparator.compareTo(key, bounds[i])) {
    +          return i;
    +        }
    +      }
    +      return partitions;
    +    }
    +  }
    +
    +  interface Comparator extends Serializable {
    --- End diff --
   
    fixed
    spark task need the comparator is serializable.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [hidden email] or file a JIRA ticket
with INFRA.
---