xiarixiaoyao commented on a change in pull request #3668: URL: https://github.com/apache/hudi/pull/3668#discussion_r715470600
########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/utils/SparkSchemaUtils.java ########## @@ -0,0 +1,283 @@ +/* + * 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.hudi.client.utils; + +import org.apache.hudi.internal.schema.InternalSchema; +import org.apache.hudi.internal.schema.Type; +import org.apache.hudi.internal.schema.Types; +import org.apache.hudi.internal.schema.utils.InternalSchemaUtils; +import org.apache.spark.sql.types.ArrayType; +import org.apache.spark.sql.types.ArrayType$; +import org.apache.spark.sql.types.BinaryType; +import org.apache.spark.sql.types.BinaryType$; +import org.apache.spark.sql.types.BooleanType; +import org.apache.spark.sql.types.BooleanType$; +import org.apache.spark.sql.types.ByteType; +import org.apache.spark.sql.types.CharType; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DateType; +import org.apache.spark.sql.types.DateType$; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.sql.types.DecimalType$; +import org.apache.spark.sql.types.DoubleType; +import org.apache.spark.sql.types.DoubleType$; +import org.apache.spark.sql.types.FloatType; +import org.apache.spark.sql.types.FloatType$; +import org.apache.spark.sql.types.IntegerType; +import org.apache.spark.sql.types.IntegerType$; +import org.apache.spark.sql.types.LongType; +import org.apache.spark.sql.types.LongType$; +import org.apache.spark.sql.types.MapType; +import org.apache.spark.sql.types.MapType$; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.ShortType; +import org.apache.spark.sql.types.StringType; +import org.apache.spark.sql.types.StringType$; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.sql.types.StructType$; +import org.apache.spark.sql.types.TimestampType; +import org.apache.spark.sql.types.TimestampType$; +import org.apache.spark.sql.types.UserDefinedType; +import org.apache.spark.sql.types.VarcharType; + +import java.util.ArrayList; +import java.util.Deque; +import java.util.HashSet; +import java.util.LinkedList; +import java.util.List; +import java.util.concurrent.atomic.AtomicInteger; +import java.util.stream.Collectors; + +public class SparkSchemaUtils { + private SparkSchemaUtils() { + + } + + public static final String HOODIE_QUERY_SCHEMA = "hadoop.hoodie.querySchema"; + public static final String HOODIE_TABLE_PATH = "hadoop.hoodie.tablePath"; + + /** + * Converts a spark schema to an hudi internal schema. Fields without IDs are kept and assigned fallback IDs. + * + * @param sparkSchema a spark schema + * @return a matching internal schema for the provided spark schema + */ + public static InternalSchema convertStructTypeToInternalSchema(StructType sparkSchema) { + Type newType = buildTypeFromStructType(sparkSchema, true, new AtomicInteger(0)); + return new InternalSchema(((Types.RecordType)newType).fields()); + } + + public static Type buildTypeFromStructType(DataType sparkType, Boolean firstVisitRoot, AtomicInteger nextId) { Review comment: no, we just need a class which wrapper the increment id。 -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
