org.apache.spark.sql.types.IntegerType Java Examples

public static SegmentSchema sparkSchemaToIndexRSchema(List<StructField> sparkSchema, IsIndexed isIndexed) {
    List<ColumnSchema> columns = new ArrayList<>();
    for (StructField f : sparkSchema) {
        SQLType type;
        if (f.dataType() instanceof IntegerType) {
            type = SQLType.INT;
        } else if (f.dataType() instanceof LongType) {
            type = SQLType.BIGINT;
        } else if (f.dataType() instanceof FloatType) {
            type = SQLType.FLOAT;
        } else if (f.dataType() instanceof DoubleType) {
            type = SQLType.DOUBLE;
        } else if (f.dataType() instanceof StringType) {
            type = SQLType.VARCHAR;
        } else if (f.dataType() instanceof DateType) {
            type = SQLType.DATE;
        } else if (f.dataType() instanceof TimestampType) {
            type = SQLType.DATETIME;
        } else {
            throw new IllegalStateException("Unsupported type: " + f.dataType());
        }
        columns.add(new ColumnSchema(f.name(), type, isIndexed.apply(f.name())));
    }
    return new SegmentSchema(columns);
}
 

public void test16(SparkSession spark, Dataset<Row> schemaFlights, String containerOut, String type)
    throws Exception {
  System.out.println("*********************************");
  System.out.println("T16: Non overwrite mode " + containerOut);
  String o1 = containerOut + "myData/123";
  StructType schema = DataTypes
      .createStructType(new StructField[] { DataTypes.createStructField("NAME", DataTypes.StringType, false),
          DataTypes.createStructField("STRING_VALUE", DataTypes.StringType, false),
          DataTypes.createStructField("NUM_VALUE", DataTypes.IntegerType, false), });
  Row r1 = RowFactory.create("name1", "value1", 1);
  Row r2 = RowFactory.create("name2", "value2", 2);
  List<Row> rowList = ImmutableList.of(r1, r2);
  Dataset<Row> rows = spark.createDataFrame(rowList, schema);
  try {
    if (type.equals(Constants.PARQUET_TYPE)) {
      rows.write().mode(SaveMode.Overwrite).parquet(o1);
    } else if (type.equals(Constants.JSON_TYPE)) {
      rows.write().mode(SaveMode.Overwrite).json(o1);
    }
  } catch (Exception e) {
    deleteData(o1, spark.sparkContext().hadoopConfiguration(), dataCreate);
    throw e;
  } finally {
    deleteData(o1, spark.sparkContext().hadoopConfiguration(), dataCreate);
  }
}
 

@Override
@SuppressWarnings("checkstyle:CyclomaticComplexity")
public Object get(int ordinal, DataType dataType) {
  if (dataType instanceof IntegerType) {
    return getInt(ordinal);
  } else if (dataType instanceof LongType) {
    return getLong(ordinal);
  } else if (dataType instanceof StringType) {
    return getUTF8String(ordinal);
  } else if (dataType instanceof FloatType) {
    return getFloat(ordinal);
  } else if (dataType instanceof DoubleType) {
    return getDouble(ordinal);
  } else if (dataType instanceof DecimalType) {
    DecimalType decimalType = (DecimalType) dataType;
    return getDecimal(ordinal, decimalType.precision(), decimalType.scale());
  } else if (dataType instanceof BinaryType) {
    return getBinary(ordinal);
  } else if (dataType instanceof StructType) {
    return getStruct(ordinal, ((StructType) dataType).size());
  } else if (dataType instanceof ArrayType) {
    return getArray(ordinal);
  } else if (dataType instanceof MapType) {
    return getMap(ordinal);
  } else if (dataType instanceof BooleanType) {
    return getBoolean(ordinal);
  } else if (dataType instanceof ByteType) {
    return getByte(ordinal);
  } else if (dataType instanceof ShortType) {
    return getShort(ordinal);
  }
  return null;
}
 

public static List<StructField> indexrSchemaToSparkSchema(SegmentSchema schema) {
    List<StructField> fields = new ArrayList<>();
    for (ColumnSchema cs : schema.getColumns()) {
        DataType dataType;
        switch (cs.getSqlType()) {
            case INT:
                dataType = DataTypes.IntegerType;
                break;
            case BIGINT:
                dataType = DataTypes.LongType;
                break;
            case FLOAT:
                dataType = DataTypes.FloatType;
                break;
            case DOUBLE:
                dataType = DataTypes.DoubleType;
                break;
            case VARCHAR:
                dataType = DataTypes.StringType;
                break;
            case DATE:
                dataType = DataTypes.DateType;
                break;
            case DATETIME:
                dataType = DataTypes.TimestampType;
                break;
            default:
                throw new IllegalStateException("Unsupported type: " + cs.getSqlType());
        }
        fields.add(new StructField(cs.getName(), dataType, scala.Boolean.box(false), Metadata.empty()));
    }
    return fields;
}
 

@Override
public ColumnVector readBlock(DataType type, ColumnVector vector)
        throws IOException
{
    if (!rowGroupOpen) {
        openRowGroup();
    }

    if (readOffset > 0) {
        if (presentStream != null) {
            // skip ahead the present bit reader, but count the set bits
            // and use this as the skip size for the data reader
            readOffset = presentStream.countBitsSet(readOffset);
        }
        if (readOffset > 0) {
            if (dataStream == null) {
                throw new OrcCorruptionException("Value is not null but data stream is not present");
            }
            dataStream.skip(readOffset);
        }
    }

    if (presentStream == null) {
        if (dataStream == null) {
            throw new OrcCorruptionException("Value is not null but data stream is not present");
        }
        if (type instanceof DateType || type instanceof IntegerType) {
            dataStream.nextIntVector(type, nextBatchSize, vector);
        } else {
            dataStream.nextLongVector(type, nextBatchSize, vector);
        }
    }
    else {
        if (nullVector.length < nextBatchSize) {
            nullVector = new boolean[nextBatchSize];
        }
        int nullValues = presentStream.getUnsetBits(nextBatchSize, nullVector);
        if (nullValues != nextBatchSize) {
            if (dataStream == null) {
                throw new OrcCorruptionException("Value is not null but data stream is not present");
            }
            if (type instanceof DateType || type instanceof IntegerType) {
                dataStream.nextIntVector(type, nextBatchSize, vector, nullVector);
            } else {
                dataStream.nextLongVector(type, nextBatchSize, vector, nullVector);
            }
        }
        else {
            for (int i = 0, j = 0; i < nextBatchSize; i++) {
                while (vector.isNullAt(i+j)) {
                    vector.appendNull();
                    j++;
                }
                vector.appendNull();
            }
        }
    }

    readOffset = 0;
    nextBatchSize = 0;

    return vector;
}