Spark存储Parquet数据到Hive，对map、array、struct字段类型的处理

-- 创建存储格式为parquet的Hive非分区表
CREATE EXTERNAL TABLE `t1`(
`id` STRING,
`map_col` MAP<STRING, STRING>,
`arr_col` ARRAY<STRING>,
`struct_col` STRUCT<A:STRING,B:STRING>)
STORED AS PARQUET
LOCATION '/home/spark/test/tmp/t1';

-- 创建存储格式为parquet的Hive分区表
CREATE EXTERNAL TABLE `t2`(
`id` STRING,
`map_col` MAP<STRING, STRING>,
`arr_col` ARRAY<STRING>,
`struct_col` STRUCT<A:STRING,B:STRING>)
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/home/spark/test/tmp/t2';

Caused by: parquet.io.ParquetEncodingException: empty fields are illegal, the field should be ommited completely instead
at parquet.io.MessageColumnIO$MessageColumnIORecordConsumer.endField(MessageColumnIO.java:244)
    at org.apache.hadoop.hive.ql.io.parquet.write.DataWritableWriter.writeMap(DataWritableWriter.java:241)
    at org.apache.hadoop.hive.ql.io.parquet.write.DataWritableWriter.writeValue(DataWritableWriter.java:116)
    at org.apache.hadoop.hive.ql.io.parquet.write.DataWritableWriter.writeGroupFields(DataWritableWriter.java:89)
    at org.apache.hadoop.hive.ql.io.parquet.write.DataWritableWriter.write(DataWritableWriter.java:60)
    ... 23 more

public void startField(String field, int index) {
  try {
  if (MessageColumnIO.DEBUG) {
    this.log("startField(" + field + ", " + index + ")");
  }

  this.currentColumnIO = ((GroupColumnIO)this.currentColumnIO).getChild(index);
  //MessageColumnIO中，startField方法中首先会将emptyField设置为true
  this.emptyField = true;
  if (MessageColumnIO.DEBUG) {
      this.printState();
  }

  } catch (RuntimeException var4) {
 throw new ParquetEncodingException("error starting field " + field + " at " + index, var4);
    }
}

//endField方法中会针对emptyField是否为true来决定是否抛出异常
public void endField(String field, int index) {
   if (MessageColumnIO.DEBUG) {
       this.log("endField(" + field + ", " + index + ")");
   }

   this.currentColumnIO = this.currentColumnIO.getParent();
   //如果到这里仍为true，则抛异常
   if (this.emptyField) {
       throw new ParquetEncodingException("empty fields are illegal, the field should be ommited completely instead");
     } else {
         this.fieldsWritten[this.currentLevel].markWritten(index);
         this.r[this.currentLevel] = this.currentLevel == 0 ? 0 : this.r[this.currentLevel - 1];
        if (MessageColumnIO.DEBUG) {
            this.printState();
        }

    }
}

private void writeMap(final Object value, final MapObjectInspector inspector, final GroupType type) {
    // Get the internal map structure (MAP_KEY_VALUE)
    GroupType repeatedType = type.getType(0).asGroupType();

    recordConsumer.startGroup();
    recordConsumer.startField(repeatedType.getName(), 0);

    Map<?, ?> mapValues = inspector.getMap(value);

    Type keyType = repeatedType.getType(0);
    String keyName = keyType.getName();
    ObjectInspector keyInspector = inspector.getMapKeyObjectInspector();

    Type valuetype = repeatedType.getType(1);
    String valueName = valuetype.getName();
    ObjectInspector valueInspector = inspector.getMapValueObjectInspector();

    for (Map.Entry<?, ?> keyValue : mapValues.entrySet()) {
      recordConsumer.startGroup();
      if (keyValue != null) {
        // write key element
        Object keyElement = keyValue.getKey();
        //recordConsumer此处对应的是MessageColumnIO中的MessageColumnIORecordConsumer
        //查看其中的startField和endField的处理
        recordConsumer.startField(keyName, 0);
        //查看writeValue中对原始数据类型的处理，如int、boolean、varchar
        writeValue(keyElement, keyInspector, keyType);
        recordConsumer.endField(keyName, 0);

        // write value element
        Object valueElement = keyValue.getValue();
        if (valueElement != null) {
          //同上
          recordConsumer.startField(valueName, 1);
          writeValue(valueElement, valueInspector, valuetype);
          recordConsumer.endField(valueName, 1);
        }
      }
      recordConsumer.endGroup();
    }

    recordConsumer.endField(repeatedType.getName(), 0);
    recordConsumer.endGroup();
}

private void writePrimitive(final Object value, final PrimitiveObjectInspector inspector) {
  //value为null，则return
  if (value == null) {
    return;
  }

  switch (inspector.getPrimitiveCategory()) {
    //PrimitiveCategory为VOID，则return
    case VOID:
      return;
    case DOUBLE:
      recordConsumer.addDouble(((DoubleObjectInspector) inspector).get(value));
      break;
    //下面是对double、boolean、float、byte、int等数据类型做的处理，这里不在贴出
    ....

-- 这种方式本质上还是用ParquetFileFormat，并且是内部表，生产中不建议直接使用这种方式
CREATE TABLE `test`(
`id` STRING,
`map_col` MAP<STRING, STRING>,
`arr_col` ARRAY<STRING>,
`struct_col` STRUCT<A:STRING,B:STRING>)
USING parquet
OPTIONS(`serialization.format` '1');