[HUDI-5533] Support spark columns comments #8683
+203
−57
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -45,7 +45,7 @@ private[sql] object SchemaConverters { | |
| * | ||
| * @since 2.4.0 | ||
| */ | ||
| case class SchemaType(dataType: DataType, nullable: Boolean, doc: Option[String]) | ||
|
|
||
| /** | ||
| * Converts an Avro schema to a corresponding Spark SQL schema. | ||
|
|
@@ -59,32 +59,32 @@ private[sql] object SchemaConverters { | |
| private val unionFieldMemberPrefix = "member" | ||
|
|
||
| private def toSqlTypeHelper(avroSchema: Schema, existingRecordNames: Set[String]): SchemaType = { | ||
| (avroSchema.getType, Option(avroSchema.getDoc)) match { | ||
|
There was a problem hiding this comment. The conversion tool is copied from Spark: https://github.com/apache/spark/blob/dd4db21cb69a9a9c3715360673a76e6f150303d4/connector/avro/src/main/scala/org/apache/spark/sql/avro/SchemaConverters.scala#L58, just noticed that Spark also does not support keeping comments from Avro fields while doing the converison. There was a problem hiding this comment. Likely spark also have this limitation when retrieving schema from avro. But spark don't usually infer spark schema from avro. Hudi does, and that's the reason of the patch. There was a problem hiding this comment. Can you write a test case for it, especially for creating table. There was a problem hiding this comment. @danny0405 added a test There was a problem hiding this comment. Kind of feel there is no need to change each match for every data types, can we write another method similiar with There was a problem hiding this comment.
Any columns including nested columns also may have comments, so I don't see why we should'nt look after all avro content for doc.
This would lead to walk thought the avro schema two times, and also lead to complex merge of results. Am i missing something ? |
||
| case (INT, doc) => avroSchema.getLogicalType match { | ||
| case _: Date => SchemaType(DateType, nullable = false, doc) | ||
| case _ => SchemaType(IntegerType, nullable = false, doc) | ||
| } | ||
| case (STRING, doc) => SchemaType(StringType, nullable = false, doc) | ||
| case (BOOLEAN, doc) => SchemaType(BooleanType, nullable = false, doc) | ||
| case (BYTES | FIXED, doc) => avroSchema.getLogicalType match { | ||
| // For FIXED type, if the precision requires more bytes than fixed size, the logical | ||
| // type will be null, which is handled by Avro library. | ||
| case d: Decimal => SchemaType(DecimalType(d.getPrecision, d.getScale), nullable = false, doc) | ||
| case _ => SchemaType(BinaryType, nullable = false, doc) | ||
| } | ||
|
|
||
| case (DOUBLE, doc) => SchemaType(DoubleType, nullable = false, doc) | ||
| case (FLOAT, doc) => SchemaType(FloatType, nullable = false, doc) | ||
| case (LONG, doc) => avroSchema.getLogicalType match { | ||
| case _: TimestampMillis | _: TimestampMicros => SchemaType(TimestampType, nullable = false, doc) | ||
| case _ => SchemaType(LongType, nullable = false, doc) | ||
| } | ||
|
|
||
| case (ENUM, doc) => SchemaType(StringType, nullable = false, doc) | ||
|
|
||
| case (NULL, doc) => SchemaType(NullType, nullable = true, doc) | ||
|
|
||
| case (RECORD, doc) => | ||
| if (existingRecordNames.contains(avroSchema.getFullName)) { | ||
| throw new IncompatibleSchemaException( | ||
| s""" | ||
|
|
@@ -95,24 +95,25 @@ private[sql] object SchemaConverters { | |
| val newRecordNames = existingRecordNames + avroSchema.getFullName | ||
| val fields = avroSchema.getFields.asScala.map { f => | ||
| val schemaType = toSqlTypeHelper(f.schema(), newRecordNames) | ||
| val metadata = if(f.doc != null) new MetadataBuilder().putString("comment", f.doc).build() else Metadata.empty | ||
| StructField(f.name, schemaType.dataType, schemaType.nullable, metadata) | ||
| } | ||
|
|
||
| SchemaType(StructType(fields.toSeq), nullable = false, doc) | ||
|
|
||
| case (ARRAY, doc) => | ||
| val schemaType = toSqlTypeHelper(avroSchema.getElementType, existingRecordNames) | ||
| SchemaType( | ||
| ArrayType(schemaType.dataType, containsNull = schemaType.nullable), | ||
| nullable = false, doc) | ||
|
|
||
| case (MAP, doc) => | ||
| val schemaType = toSqlTypeHelper(avroSchema.getValueType, existingRecordNames) | ||
| SchemaType( | ||
| MapType(StringType, schemaType.dataType, valueContainsNull = schemaType.nullable), | ||
| nullable = false, doc) | ||
|
|
||
| case (UNION, doc) => | ||
| if (avroSchema.getTypes.asScala.exists(_.getType == NULL)) { | ||
| // In case of a union with null, eliminate it and make a recursive call | ||
| val remainingUnionTypes = avroSchema.getTypes.asScala.filterNot(_.getType == NULL) | ||
|
|
@@ -126,20 +127,21 @@ private[sql] object SchemaConverters { | |
| case Seq(t1) => | ||
| toSqlTypeHelper(avroSchema.getTypes.get(0), existingRecordNames) | ||
| case Seq(t1, t2) if Set(t1, t2) == Set(INT, LONG) => | ||
| SchemaType(LongType, nullable = false, doc) | ||
| case Seq(t1, t2) if Set(t1, t2) == Set(FLOAT, DOUBLE) => | ||
| SchemaType(DoubleType, nullable = false, doc) | ||
| case _ => | ||
| // Convert complex unions to struct types where field names are member0, member1, etc. | ||
| // This is consistent with the behavior when converting between Avro and Parquet. | ||
| val fields = avroSchema.getTypes.asScala.zipWithIndex.map { | ||
| case (s, i) => | ||
| val schemaType = toSqlTypeHelper(s, existingRecordNames) | ||
| // All fields are nullable because only one of them is set at a time | ||
| val metadata = if(schemaType.doc.isDefined) new MetadataBuilder().putString("comment", schemaType.doc.get).build() else Metadata.empty | ||
| StructField(s"$unionFieldMemberPrefix$i", schemaType.dataType, nullable = true, metadata) | ||
| } | ||
|
|
||
| SchemaType(StructType(fields.toSeq), nullable = false, doc) | ||
| } | ||
|
|
||
| case other => throw new IncompatibleSchemaException(s"Unsupported type $other") | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,83 @@ | ||
| /* | ||
| * 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.functional | ||
|
|
||
| import org.apache.spark.sql._ | ||
| import org.apache.spark.sql.hudi.HoodieSparkSessionExtension | ||
| import org.apache.spark.SparkContext | ||
| import org.apache.hudi.testutils.HoodieClientTestUtils.getSparkConfForTest | ||
| import org.apache.hudi.DataSourceWriteOptions | ||
| import org.apache.hudi.config.HoodieWriteConfig | ||
| import org.apache.hudi.common.model.{HoodieTableType} | ||
| import org.apache.spark.sql.types.StructType | ||
| import org.junit.jupiter.api.Assertions.assertEquals | ||
| import org.junit.jupiter.api.BeforeEach | ||
| import org.junit.jupiter.params.ParameterizedTest | ||
| import org.junit.jupiter.params.provider.EnumSource | ||
|
|
||
|
|
||
| class TestColumnComments { | ||
| var spark : SparkSession = _ | ||
| var sqlContext: SQLContext = _ | ||
| var sc : SparkContext = _ | ||
|
|
||
| def initSparkContext(): Unit = { | ||
| val sparkConf = getSparkConfForTest(getClass.getSimpleName) | ||
| spark = SparkSession.builder() | ||
| .withExtensions(new HoodieSparkSessionExtension) | ||
| .config(sparkConf) | ||
| .getOrCreate() | ||
| sc = spark.sparkContext | ||
| sc.setLogLevel("ERROR") | ||
| sqlContext = spark.sqlContext | ||
| } | ||
|
|
||
| @BeforeEach | ||
| def setUp() { | ||
| initSparkContext() | ||
| } | ||
|
|
||
| @ParameterizedTest | ||
| @EnumSource(value = classOf[HoodieTableType], names = Array("COPY_ON_WRITE", "MERGE_ON_READ")) | ||
| def testColumnCommentWithSparkDatasource(tableType: HoodieTableType): Unit = { | ||
| val basePath = java.nio.file.Files.createTempDirectory("hoodie_comments_path").toAbsolutePath.toString | ||
| val opts = Map( | ||
| HoodieWriteConfig.TBL_NAME.key -> "hoodie_comments", | ||
| DataSourceWriteOptions.TABLE_TYPE.key -> tableType.toString, | ||
| DataSourceWriteOptions.OPERATION.key -> "bulk_insert", | ||
| DataSourceWriteOptions.RECORDKEY_FIELD.key -> "_row_key", | ||
| DataSourceWriteOptions.PARTITIONPATH_FIELD.key -> "partition" | ||
| ) | ||
| val inputDF = spark.sql("select '0' as _row_key, '1' as content, '2' as partition, '3' as ts") | ||
| val struct = new StructType() | ||
| .add("_row_key", "string", true, "dummy comment") | ||
| .add("content", "string", true) | ||
| .add("partition", "string", true) | ||
| .add("ts", "string", true) | ||
| spark.createDataFrame(inputDF.rdd, struct) | ||
| .write.format("hudi") | ||
| .options(opts) | ||
| .mode(SaveMode.Overwrite) | ||
| .save(basePath) | ||
| spark.read.format("hudi").load(basePath).registerTempTable("test_tbl") | ||
|
|
||
| // now confirm the comment is present at read time | ||
| assertEquals(1, spark.sql("desc extended test_tbl") | ||
| .filter("col_name = '_row_key' and comment = 'dummy comment'").count) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Collections.emptyList() ?