[GitHub] [hudi] pengzhiwei2018 commented on a change in pull request #3120: [HUDI-2045] Support Read Hoodie As DataSource Table For Flink And DeltaStreamer

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

pengzhiwei2018 commented on a change in pull request #3120:
URL: https://github.com/apache/hudi/pull/3120#discussion_r667609527



##########
File path: hudi-sync/hudi-hive-sync/src/main/java/org/apache/hudi/hive/HiveSyncTool.java
##########
@@ -236,6 +247,71 @@ private void syncSchema(String tableName, boolean tableExists, boolean useRealTi
     }
   }
 
+  /**
+   * Get Spark Sql related table properties. This is used for spark datasource table.
+   * @param schema  The schema to write to the table.
+   * @return A new parameters added the spark's table properties.
+   */
+  private Map<String, String> getSparkTableProperties(int schemaLengthThreshold, MessageType schema)  {
+    // Convert the schema and partition info used by spark sql to hive table properties.
+    // The following code refers to the spark code in
+    // https://github.com/apache/spark/blob/master/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala
+    GroupType originGroupType = schema.asGroupType();
+    List<String> partitionNames = cfg.partitionFields;
+    List<Type> partitionCols = new ArrayList<>();
+    List<Type> dataCols = new ArrayList<>();
+    Map<String, Type> column2Field = new HashMap<>();
+
+    for (Type field : originGroupType.getFields()) {
+      column2Field.put(field.getName(), field);
+    }
+    // Get partition columns and data columns.
+    for (String partitionName : partitionNames) {
+      // Default the unknown partition fields to be String.
+      // Keep the same logical with HiveSchemaUtil#getPartitionKeyType.
+      partitionCols.add(column2Field.getOrDefault(partitionName,
+              new PrimitiveType(Type.Repetition.REQUIRED, BINARY, partitionName, UTF8)));
+    }
+    for (Type field : originGroupType.getFields()) {

Review comment:
       fixed

##########
File path: hudi-sync/hudi-hive-sync/src/test/java/org/apache/hudi/hive/TestParquet2SparkSchemaUtils.java
##########
@@ -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.hive;
+
+import org.apache.hudi.hive.util.Parquet2SparkSchemaUtils;
+import org.apache.spark.sql.execution.SparkSqlParser;
+import org.apache.spark.sql.execution.datasources.parquet.SparkToParquetSchemaConverter;
+import org.apache.spark.sql.internal.SQLConf;
+import org.apache.spark.sql.types.ArrayType;
+import org.apache.spark.sql.types.MapType;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.IntegerType$;
+import org.apache.spark.sql.types.StringType$;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+import org.junit.jupiter.api.Test;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+public class TestParquet2SparkSchemaUtils {

Review comment:
       done!

##########
File path: hudi-sync/hudi-hive-sync/src/test/java/org/apache/hudi/hive/TestHiveSyncTool.java
##########
@@ -70,6 +69,10 @@
     return Arrays.asList(new Object[][] {{true, true, true}, {true, false, false}, {false, true, true}, {false, false, false}});
   }
 
+  private static Iterable<Object[]> useJdbcAndSchemaFromCommitMetadataAndSyncAsDataSource() {

Review comment:
       Yes, will rename it.




-- 
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