[HUDI-2456] support 'show partitions' sql

hudi-client/hudi-client-common/src/main/java/org/apache/hudi/keygen/KeyGenUtils.java

@@ -40,7 +40,7 @@ public class KeyGenUtils {
   protected static final String NULL_RECORDKEY_PLACEHOLDER = "__null__";
   protected static final String EMPTY_RECORDKEY_PLACEHOLDER = "__empty__";
 
-  protected static final String DEFAULT_PARTITION_PATH = "default";
+  protected static final String DEFAULT_PARTITION_PATH = PartitionPathEncodeUtils.HUDI_DEFAULT_PARTITION_PATH;
   public static final String DEFAULT_PARTITION_PATH_SEPARATOR = "/";
 
   /**

hudi-common/src/main/java/org/apache/hudi/common/util/PartitionPathEncodeUtils.java

@@ -25,6 +25,8 @@
  */
 public class PartitionPathEncodeUtils {
 
+  public static final String HUDI_DEFAULT_PARTITION_PATH = "default";
+
   static BitSet charToEscape = new BitSet(128);
   static {
     for (char c = 0; c < ' '; c++) {
@@ -71,7 +73,7 @@ public static String escapePathName(String path, String defaultPath) {
       if (defaultPath == null) {
         //previously, when path is empty or null and no default path is specified,
         // __HIVE_DEFAULT_PARTITION__ was the return value for escapePathName
-        return "__HIVE_DEFAULT_PARTITION__";
+        return HUDI_DEFAULT_PARTITION_PATH;
       } else {
         return defaultPath;
       }
@@ -111,4 +113,12 @@ public static String unescapePathName(String path) {
     }
     return sb.toString();
   }
+
+  public static String escapePartitionValue(String value) {
+    if (value == null || value.isEmpty()) {
+      return HUDI_DEFAULT_PARTITION_PATH;
+    } else {
+      return escapePathName(value);
+    }
+  }
 }

hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/analysis/HoodieAnalysis.scala

@@ -29,13 +29,13 @@ import org.apache.spark.sql.catalyst.expressions.AttributeReference
 import org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute
 import org.apache.spark.sql.catalyst.expressions.{Alias, Expression, Literal, NamedExpression}
 import org.apache.spark.sql.catalyst.plans.Inner
-import org.apache.spark.sql.catalyst.plans.logical.{Assignment, CompactionPath, CompactionShowOnPath, CompactionShowOnTable, CompactionTable, DeleteAction, DeleteFromTable, InsertAction, LogicalPlan, MergeIntoTable, Project, UpdateAction, UpdateTable}
+import org.apache.spark.sql.catalyst.plans.logical._
 import org.apache.spark.sql.catalyst.rules.Rule
-import org.apache.spark.sql.execution.command.{AlterTableAddColumnsCommand, AlterTableChangeColumnCommand, AlterTableRenameCommand, CreateDataSourceTableCommand, TruncateTableCommand}
+import org.apache.spark.sql.execution.command._
 import org.apache.spark.sql.execution.datasources.{CreateTable, LogicalRelation}
 import org.apache.spark.sql.hudi.{HoodieOptionConfig, HoodieSqlUtils}
 import org.apache.spark.sql.hudi.HoodieSqlUtils._
-import org.apache.spark.sql.hudi.command.{AlterHoodieTableAddColumnsCommand, AlterHoodieTableChangeColumnCommand, AlterHoodieTableRenameCommand, CompactionHoodiePathCommand, CompactionHoodieTableCommand, CompactionShowHoodiePathCommand, CompactionShowHoodieTableCommand, CreateHoodieTableAsSelectCommand, CreateHoodieTableCommand, DeleteHoodieTableCommand, InsertIntoHoodieTableCommand, MergeIntoHoodieTableCommand, TruncateHoodieTableCommand, UpdateHoodieTableCommand}
+import org.apache.spark.sql.hudi.command._
 import org.apache.spark.sql.types.StringType
 
 object HoodieAnalysis {
@@ -417,6 +417,9 @@ case class HoodiePostAnalysisRule(sparkSession: SparkSession) extends Rule[Logic
       case AlterTableChangeColumnCommand(tableName, columnName, newColumn)
         if isHoodieTable(tableName, sparkSession) =>
         AlterHoodieTableChangeColumnCommand(tableName, columnName, newColumn)
+      case ShowPartitionsCommand(tableName, specOpt)
+        if isHoodieTable(tableName, sparkSession) =>
+         ShowHoodieTablePartitionsCommand(tableName, specOpt)
       // Rewrite TruncateTableCommand to TruncateHoodieTableCommand
       case TruncateTableCommand(tableName, partitionSpec)
         if isHoodieTable(tableName, sparkSession) =>

hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/CreateHoodieTableCommand.scala

@@ -54,7 +54,7 @@ import scala.collection.mutable
  * Command for create hoodie table.
  */
 case class CreateHoodieTableCommand(table: CatalogTable, ignoreIfExists: Boolean)
-  extends RunnableCommand with SparkAdapterSupport {
+  extends RunnableCommand with HoodieCommand with SparkAdapterSupport {
 
   override def run(sparkSession: SparkSession): Seq[Row] = {
     val tableName = table.identifier.unquotedString
@@ -129,9 +129,9 @@ case class CreateHoodieTableCommand(table: CatalogTable, ignoreIfExists: Boolean
         (addMetaFields(tableSchema.get), options)
       } else if (userSpecifiedSchema.nonEmpty) {
         (addMetaFields(userSpecifiedSchema), options)
-    } else {
+      } else {
         throw new IllegalArgumentException(s"Missing schema for Create Table: $tableName")
-     }
+      }
     } else {
       assert(table.schema.nonEmpty, s"Missing schema for Create Table: $tableName")
       // SPARK-19724: the default location of a managed table should be non-existent or empty.
@@ -319,16 +319,6 @@ case class CreateHoodieTableCommand(table: CatalogTable, ignoreIfExists: Boolean
     }
   }
 
-  private def getAllPartitionPaths(spark: SparkSession, table: CatalogTable): Seq[String] = {
-    val sparkEngine = new HoodieSparkEngineContext(new JavaSparkContext(spark.sparkContext))
-    val metadataConfig = {
-      val properties = new Properties()
-      properties.putAll((spark.sessionState.conf.getAllConfs ++ table.storage.properties).asJava)
-      HoodieMetadataConfig.newBuilder.fromProperties(properties).build()
-    }
-    FSUtils.getAllPartitionPaths(sparkEngine, metadataConfig, getTableLocation(table, spark)).asScala
-  }
-
   /**
    * This method is used to compatible with the old non-hive-styled partition table.
    * By default we enable the "hoodie.datasource.write.hive_style_partitioning"

hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/HoodieCommand.scala

@@ -0,0 +1,47 @@
+/*
+ * 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.spark.sql.hudi.command
+
+import java.util.Properties
+
+import org.apache.hudi.client.common.HoodieSparkEngineContext
+import org.apache.hudi.common.config.HoodieMetadataConfig
+import org.apache.hudi.common.fs.FSUtils
+import org.apache.spark.api.java.JavaSparkContext
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.catalog.CatalogTable
+import org.apache.spark.sql.hudi.HoodieSqlUtils
+
+import scala.collection.JavaConverters._
+
+/**
+ * Helper trait for all hoodie commands.
+ */
+trait HoodieCommand {
+
+  protected def getAllPartitionPaths(spark: SparkSession, table: CatalogTable): Seq[String] = {
+    val sparkEngine = new HoodieSparkEngineContext(new JavaSparkContext(spark.sparkContext))
+    val metadataConfig = {
+      val properties = new Properties()
+      properties.putAll((spark.sessionState.conf.getAllConfs ++ table.storage.properties).asJava)
+      HoodieMetadataConfig.newBuilder.fromProperties(properties).build()
+    }
+    FSUtils.getAllPartitionPaths(sparkEngine, metadataConfig, HoodieSqlUtils.getTableLocation(table, spark)).asScala
+  }
+
+}

hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/ShowHoodieTablePartitionsCommand.scala

@@ -0,0 +1,76 @@
+/*
+ * 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.spark.sql.hudi.command
+
+import org.apache.hudi.common.table.HoodieTableMetaClient
+import org.apache.hudi.common.util.PartitionPathEncodeUtils
+import org.apache.spark.sql.{Row, SparkSession}
+import org.apache.spark.sql.catalyst.{InternalRow, TableIdentifier}
+import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
+import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference}
+import org.apache.spark.sql.execution.command.RunnableCommand
+import org.apache.spark.sql.execution.datasources.PartitioningUtils
+import org.apache.spark.sql.hudi.HoodieSqlUtils
+import org.apache.spark.sql.types.StringType
+
+/**
+ * Command for show hudi table's partitions.
+ */
+case class ShowHoodieTablePartitionsCommand(
+    tableName: TableIdentifier,
+    specOpt: Option[TablePartitionSpec])
+extends RunnableCommand with HoodieCommand {
+
+  override val output: Seq[Attribute] = {
+    AttributeReference("partition", StringType, nullable = false)() :: Nil
+  }
+
+  override def run(sparkSession: SparkSession): Seq[Row] = {
+    val catalog = sparkSession.sessionState.catalog
+    val resolver = sparkSession.sessionState.conf.resolver
+    val catalogTable = catalog.getTableMetadata(tableName)
+    val tablePath = HoodieSqlUtils.getTableLocation(catalogTable, sparkSession)
+
+    val hadoopConf = sparkSession.sessionState.newHadoopConf()
+    val metaClient = HoodieTableMetaClient.builder().setBasePath(tablePath)
+      .setConf(hadoopConf).build()
+    val schemaOpt = HoodieSqlUtils.getTableSqlSchema(metaClient)
+    val partitionColumnNamesOpt = metaClient.getTableConfig.getPartitionFields
+    if (partitionColumnNamesOpt.isPresent && partitionColumnNamesOpt.get.nonEmpty
+        && schemaOpt.isDefined && schemaOpt.nonEmpty) {
+
+      val partitionColumnNames = partitionColumnNamesOpt.get
+      val schema = schemaOpt.get
+      val allPartitionPaths: Seq[String] = getAllPartitionPaths(sparkSession, catalogTable)
+
+      if (specOpt.isEmpty) {
+        allPartitionPaths.map(Row(_))
+      } else {
+        val spec = specOpt.get
+        allPartitionPaths.filter { partitionPath =>
+          val part = PartitioningUtils.parsePathFragment(partitionPath)
+          spec.forall { case (col, value) =>
+            PartitionPathEncodeUtils.escapePartitionValue(value) == part.getOrElse(col, null)
+          }
+        }.map(Row(_))
+      }
+    } else {
+      Seq.empty[Row]
+    }
+  }
+}