[GitHub] [hudi] YannByron commented on a diff in pull request #6734: [HUDI-3478][HUDI-4887] Use Avro as the format of persisted cdc data

[GitBox <gi...@apache.org>]

YannByron commented on code in PR #6734:
URL: https://github.com/apache/hudi/pull/6734#discussion_r977710374


##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/cdc/TestCDCDataFrameSuite.scala:
##########
@@ -0,0 +1,238 @@
+/*
+ * 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.cdc
+
+import org.apache.avro.Schema
+import org.apache.avro.generic.IndexedRecord
+
+import org.apache.hadoop.fs.Path
+
+import org.apache.hudi.DataSourceWriteOptions._
+import org.apache.hudi.common.config.HoodieMetadataConfig
+import org.apache.hudi.common.model.{HoodieCommitMetadata, HoodieLogFile}
+import org.apache.hudi.common.table.cdc.{HoodieCDCSupplementalLoggingMode, HoodieCDCUtils}
+import org.apache.hudi.common.table.log.HoodieLogFormat
+import org.apache.hudi.common.table.log.block.{HoodieDataBlock, HoodieLogBlock}
+import org.apache.hudi.common.table.{HoodieTableConfig, HoodieTableMetaClient, TableSchemaResolver}
+import org.apache.hudi.common.table.timeline.HoodieInstant
+import org.apache.hudi.common.testutils.RawTripTestPayload.{deleteRecordsToStrings, recordsToStrings}
+import org.apache.hudi.config.{HoodieCleanConfig, HoodieWriteConfig}
+import org.apache.hudi.testutils.HoodieClientTestBase
+
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.SaveMode
+
+import org.junit.jupiter.api.{AfterEach, BeforeEach}
+import org.junit.jupiter.api.Assertions.{assertEquals, assertFalse, assertTrue}
+import org.junit.jupiter.params.ParameterizedTest
+import org.junit.jupiter.params.provider.CsvSource
+
+import scala.collection.JavaConversions._
+import scala.collection.JavaConverters._
+
+class TestCDCDataFrameSuite extends HoodieClientTestBase {
+
+  var spark: SparkSession = _
+
+  val commonOpts = Map(
+    HoodieTableConfig.CDC_ENABLED.key -> "true",
+    "hoodie.insert.shuffle.parallelism" -> "4",
+    "hoodie.upsert.shuffle.parallelism" -> "4",
+    "hoodie.bulkinsert.shuffle.parallelism" -> "2",
+    "hoodie.delete.shuffle.parallelism" -> "1",
+    RECORDKEY_FIELD.key -> "_row_key",
+    PRECOMBINE_FIELD.key -> "timestamp",
+    HoodieWriteConfig.TBL_NAME.key -> "hoodie_test",
+    HoodieMetadataConfig.COMPACT_NUM_DELTA_COMMITS.key -> "1",
+    HoodieCleanConfig.AUTO_CLEAN.key -> "false"
+  )
+
+  @BeforeEach override def setUp(): Unit = {
+    setTableName("hoodie_test")
+    initPath()
+    initSparkContexts()
+    spark = sqlContext.sparkSession
+    initTestDataGenerator()
+    initFileSystem()
+  }
+
+  @AfterEach override def tearDown(): Unit = {
+    cleanupSparkContexts()
+    cleanupTestDataGenerator()
+    cleanupFileSystem()
+  }
+
+  @ParameterizedTest
+  @CsvSource(Array("cdc_op_key", "cdc_data_before", "cdc_data_before_after"))
+  def testCOWDataSourceWrite(cdcSupplementalLoggingMode: String): Unit = {
+    val options = commonOpts ++ Map(
+      HoodieTableConfig.CDC_SUPPLEMENTAL_LOGGING_MODE.key -> cdcSupplementalLoggingMode
+    )
+
+    // Insert Operation
+    val records1 = recordsToStrings(dataGen.generateInserts("000", 100)).toList
+    val inputDF1 = spark.read.json(spark.sparkContext.parallelize(records1, 2))
+    inputDF1.write.format("org.apache.hudi")
+      .options(options)
+      .mode(SaveMode.Overwrite)
+      .save(basePath)
+
+    // init meta client
+    metaClient = HoodieTableMetaClient.builder()
+      .setBasePath(basePath)
+      .setConf(spark.sessionState.newHadoopConf)
+      .build()
+    val instant1 = metaClient.reloadActiveTimeline.lastInstant().get()
+    assertEquals(spark.read.format("hudi").load(basePath).count(), 100)
+    // all the data is new-coming, it will write out cdc log files.
+    assertFalse(hasCDCLogFile(instant1))
+
+    val schemaResolver = new TableSchemaResolver(metaClient)
+    val dataSchema = schemaResolver.getTableAvroSchema(false)
+    val cdcSchema = HoodieCDCUtils.schemaBySupplementalLoggingMode(
+      HoodieCDCSupplementalLoggingMode.parse(cdcSupplementalLoggingMode), dataSchema)
+
+    // Upsert Operation
+    val records2 = recordsToStrings(dataGen.generateUniqueUpdates("001", 50)).toList
+    val inputDF2 = spark.read.json(spark.sparkContext.parallelize(records2, 2))
+    inputDF2.write.format("org.apache.hudi")
+      .options(options)
+      .mode(SaveMode.Append)
+      .save(basePath)
+    val instant2 = metaClient.reloadActiveTimeline.lastInstant().get()
+    assertEquals(spark.read.format("hudi").load(basePath).count(), 100)
+
+    // part of data are updated, it will write out cdc log files
+    assertTrue(hasCDCLogFile(instant2))
+    val cdcData2 = getCDCLogFIle(instant2).flatMap(readCDCLogFile(_, cdcSchema))
+    assertEquals(cdcData2.size, 50)

Review Comment:
   done



##########
hudi-common/src/main/java/org/apache/hudi/avro/AvroSchemaUtils.java:
##########
@@ -109,6 +109,11 @@ public static Schema createNullableSchema(Schema.Type avroType) {
     return Schema.createUnion(Schema.create(Schema.Type.NULL), Schema.create(avroType));

Review Comment:
   done.



-- 
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: commits-unsubscribe@hudi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org