kangpinghuang commented on a change in pull request #3296: URL: https://github.com/apache/incubator-doris/pull/3296#discussion_r421972254
########## File path: fe/src/main/java/org/apache/doris/load/loadv2/dpp/DppUtils.java ########## @@ -0,0 +1,252 @@ +// 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.doris.load.loadv2.dpp; + +import io.fabric8.openshift.api.model.User; +import org.apache.doris.common.UserException; +import org.apache.doris.load.loadv2.etl.EtlJobConfig; + +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.sql.Row; + +import com.google.common.collect.Lists; + +import java.math.BigDecimal; +import java.math.BigInteger; +import java.nio.ByteBuffer; +import java.nio.ByteOrder; +import java.util.ArrayList; +import java.util.Collections; +import java.util.Date; +import java.util.List; +import java.util.zip.CRC32; + +public class DppUtils { + public static final String BUCKET_ID = "__bucketId__"; + public static Class getClassFromDataType(DataType dataType) { + if (dataType == null) { + return null; + } + if (dataType.equals(DataTypes.BooleanType)) { + return Boolean.class; + } else if (dataType.equals(DataTypes.ShortType)) { + return Short.class; + } else if (dataType.equals(DataTypes.IntegerType)) { + return Integer.class; + } else if (dataType.equals(DataTypes.LongType)) { + return Long.class; + } else if (dataType.equals(DataTypes.FloatType)) { + return Float.class; + } else if (dataType.equals(DataTypes.DoubleType)) { + return Double.class; + } else if (dataType.equals(DataTypes.DateType)) { + return Date.class; + } else if (dataType.equals(DataTypes.StringType)) { + return String.class; + } else if (dataType instanceof DecimalType) { + DecimalType decimalType = (DecimalType)dataType; + return BigDecimal.valueOf(decimalType.precision(), decimalType.scale()).getClass(); + } else if (dataType.equals(DataTypes.TimestampType)) { + return Long.class; + } + return null; + } + + public static Class getClassFromColumn(EtlJobConfig.EtlColumn column) throws UserException { + switch (column.columnType) { + case "BOOLEAN": + return Boolean.class; + case "TINYINT": + case "SMALLINT": + return Short.class; + case "INT": + return Integer.class; + case "DATETIME": + case "BIGINT": + return Long.class; + case "LARGEINT": + throw new UserException("LARGEINT is not supported now"); + case "FLOAT": + return Float.class; + case "DOUBLE": + return Double.class; + case "DATE": + return Date.class; + case "HLL": + case "CHAR": + case "VARCHAR": + case "BITMAP": + case "OBJECT": + return String.class; + case "DECIMALV2": + return BigDecimal.valueOf(column.precision, column.scale).getClass(); + default: + return String.class; + } + } + + public static DataType getDataTypeFromColumn(EtlJobConfig.EtlColumn column) throws UserException { + DataType dataType = DataTypes.StringType; + switch (column.columnType) { + case "BOOLEAN": + dataType = DataTypes.StringType; + break; + case "TINYINT": + case "SMALLINT": + dataType = DataTypes.ShortType; + break; + case "INT": + dataType = DataTypes.IntegerType; + break; + case "DATETIME": + dataType = DataTypes.TimestampType; + break; + case "BIGINT": + dataType = DataTypes.LongType; + break; + case "LARGEINT": + dataType = DataTypes.StringType; + break; + case "FLOAT": + dataType = DataTypes.FloatType; + break; + case "DOUBLE": + dataType = DataTypes.DoubleType; + break; + case "DATE": + dataType = DataTypes.DateType; + break; + case "CHAR": + case "VARCHAR": + case "HLL": + case "BITMAP": + case "OBJECT": + dataType = DataTypes.StringType; + break; + case "DECIMALV2": + dataType = DecimalType.apply(column.precision, column.scale); + break; + default: + throw new UserException("Reason: invalid column type:" + column); + } + return dataType; + } + + public static ByteBuffer getHashValue(Object o, DataType type) { + ByteBuffer buffer = ByteBuffer.allocate(8); + buffer.order(ByteOrder.LITTLE_ENDIAN); + if (o == null) { + buffer.putInt(0); + return buffer; + } + if (type.equals(DataTypes.ShortType)) { + buffer.putShort((Short)o); + } else if (type.equals(DataTypes.IntegerType)) { + buffer.putInt((Integer) o); + } else if (type.equals(DataTypes.LongType)) { + buffer.putLong((Long)o); + } else if (type.equals(DataTypes.StringType)) { + try { + String str = (String)o; Review comment: now largeint is not supported in spark dpp. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org
