From db8784feaa605adcbd37af4bc8b7146479b631f8 Mon Sep 17 00:00:00 2001
From: Wenchen Fan <wenchen@databricks.com>
Date: Thu, 13 Oct 2016 03:26:29 -0400
Subject: [SPARK-17899][SQL] add a debug mode to keep raw table properties in
 HiveExternalCatalog

## What changes were proposed in this pull request?

Currently `HiveExternalCatalog` will filter out the Spark SQL internal table properties, e.g. `spark.sql.sources.provider`, `spark.sql.sources.schema`, etc. This is reasonable for external users as they don't want to see these internal properties in `DESC TABLE`.

However, as a Spark developer, sometimes we do wanna see the raw table properties. This PR adds a new internal SQL conf, `spark.sql.debug`, to enable debug mode and keep these raw table properties.

This config can also be used in similar places where we wanna retain debug information in the future.

## How was this patch tested?

new test in MetastoreDataSourcesSuite

Author: Wenchen Fan <wenchen@databricks.com>

Closes #15458 from cloud-fan/debug.
---
 .../org/apache/spark/sql/hive/HiveExternalCatalog.scala |  9 +++++++--
 .../spark/sql/hive/MetastoreDataSourcesSuite.scala      | 17 ++++++++++++++++-
 2 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'sql/hive')

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala
index e1c0cad907..ed189724a2 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala
@@ -37,7 +37,7 @@ import org.apache.spark.sql.execution.command.{ColumnStatStruct, DDLUtils}
 import org.apache.spark.sql.execution.datasources.CaseInsensitiveMap
 import org.apache.spark.sql.hive.client.HiveClient
 import org.apache.spark.sql.internal.HiveSerDe
-import org.apache.spark.sql.internal.StaticSQLConf.SCHEMA_STRING_LENGTH_THRESHOLD
+import org.apache.spark.sql.internal.StaticSQLConf._
 import org.apache.spark.sql.types.{DataType, StructType}
 
 
@@ -461,13 +461,18 @@ private[spark] class HiveExternalCatalog(conf: SparkConf, hadoopConf: Configurat
         } else {
           table.storage
         }
+        val tableProps = if (conf.get(DEBUG_MODE)) {
+          table.properties
+        } else {
+          getOriginalTableProperties(table)
+        }
         table.copy(
           storage = storage,
           schema = getSchemaFromTableProperties(table),
           provider = Some(provider),
           partitionColumnNames = getPartitionColumnsFromTableProperties(table),
           bucketSpec = getBucketSpecFromTableProperties(table),
-          properties = getOriginalTableProperties(table))
+          properties = tableProps)
       } getOrElse {
         table.copy(provider = Some("hive"))
       }
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
index 0477122fc6..7cc6179d44 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/MetastoreDataSourcesSuite.scala
@@ -23,6 +23,7 @@ import scala.collection.mutable.ArrayBuffer
 
 import org.apache.hadoop.fs.Path
 
+import org.apache.spark.SparkContext
 import org.apache.spark.sql._
 import org.apache.spark.sql.catalyst.TableIdentifier
 import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, CatalogTable, CatalogTableType}
@@ -31,7 +32,7 @@ import org.apache.spark.sql.hive.HiveExternalCatalog._
 import org.apache.spark.sql.hive.client.HiveClient
 import org.apache.spark.sql.hive.test.TestHiveSingleton
 import org.apache.spark.sql.internal.SQLConf
-import org.apache.spark.sql.internal.StaticSQLConf.SCHEMA_STRING_LENGTH_THRESHOLD
+import org.apache.spark.sql.internal.StaticSQLConf._
 import org.apache.spark.sql.test.SQLTestUtils
 import org.apache.spark.sql.types._
 import org.apache.spark.util.Utils
@@ -1324,4 +1325,18 @@ class MetastoreDataSourcesSuite extends QueryTest with SQLTestUtils with TestHiv
       hiveClient.dropTable("default", "t", ignoreIfNotExists = true, purge = true)
     }
   }
+
+  test("should keep data source entries in table properties when debug mode is on") {
+    val previousValue = sparkSession.sparkContext.conf.get(DEBUG_MODE)
+    try {
+      sparkSession.sparkContext.conf.set(DEBUG_MODE, true)
+      val newSession = sparkSession.newSession()
+      newSession.sql("CREATE TABLE abc(i int) USING json")
+      val tableMeta = newSession.sessionState.catalog.getTableMetadata(TableIdentifier("abc"))
+      assert(tableMeta.properties(DATASOURCE_SCHEMA_NUMPARTS).toInt == 1)
+      assert(tableMeta.properties(DATASOURCE_PROVIDER) == "json")
+    } finally {
+      sparkSession.sparkContext.conf.set(DEBUG_MODE, previousValue)
+    }
+  }
 }
-- 
cgit v1.2.3