You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by we...@apache.org on 2024/05/29 20:35:12 UTC
(spark) branch master updated: [SPARK-48273][SQL][FOLLOWUP] Explicitly create non-Hive table in identifier-clause.sql
This is an automated email from the ASF dual-hosted git repository.
wenchen pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new cf47293b5fc7 [SPARK-48273][SQL][FOLLOWUP] Explicitly create non-Hive table in identifier-clause.sql
cf47293b5fc7 is described below
commit cf47293b5fc7c80d19e50fda44a01f91d5e34530
Author: Wenchen Fan <we...@databricks.com>
AuthorDate: Wed May 29 13:35:01 2024 -0700
[SPARK-48273][SQL][FOLLOWUP] Explicitly create non-Hive table in identifier-clause.sql
### What changes were proposed in this pull request?
A followup of https://github.com/apache/spark/pull/46580 . It's better to create non-Hive tables in the tests, so that it's backport safe, as old branches creates hive table by default.
### Why are the changes needed?
fix branch-3.5 CI
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
N/A
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #46794 from cloud-fan/test.
Authored-by: Wenchen Fan <we...@databricks.com>
Signed-off-by: Wenchen Fan <we...@databricks.com>
---
.../sql-tests/analyzer-results/identifier-clause.sql.out | 8 ++++----
.../src/test/resources/sql-tests/inputs/identifier-clause.sql | 6 +++---
.../test/resources/sql-tests/results/identifier-clause.sql.out | 6 +++---
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/sql/core/src/test/resources/sql-tests/analyzer-results/identifier-clause.sql.out b/sql/core/src/test/resources/sql-tests/analyzer-results/identifier-clause.sql.out
index f799c19a3bb8..b3e2cd5ada95 100644
--- a/sql/core/src/test/resources/sql-tests/analyzer-results/identifier-clause.sql.out
+++ b/sql/core/src/test/resources/sql-tests/analyzer-results/identifier-clause.sql.out
@@ -732,7 +732,7 @@ org.apache.spark.sql.AnalysisException
-- !query
-CREATE TABLE IDENTIFIER(1)(c1 INT)
+CREATE TABLE IDENTIFIER(1)(c1 INT) USING csv
-- !query analysis
org.apache.spark.sql.AnalysisException
{
@@ -754,7 +754,7 @@ org.apache.spark.sql.AnalysisException
-- !query
-CREATE TABLE IDENTIFIER('a.b.c')(c1 INT)
+CREATE TABLE IDENTIFIER('a.b.c')(c1 INT) USING csv
-- !query analysis
org.apache.spark.sql.AnalysisException
{
@@ -947,7 +947,7 @@ CacheTableAsSelect t1, (select my_col from (values (1), (2), (1) as (my_col)) gr
-- !query
-create table identifier('t2') as (select my_col from (values (1), (2), (1) as (my_col)) group by 1)
+create table identifier('t2') using csv as (select my_col from (values (1), (2), (1) as (my_col)) group by 1)
-- !query analysis
CreateDataSourceTableAsSelectCommand `spark_catalog`.`default`.`t2`, ErrorIfExists, [my_col]
+- Aggregate [my_col#x], [my_col#x]
@@ -959,7 +959,7 @@ CreateDataSourceTableAsSelectCommand `spark_catalog`.`default`.`t2`, ErrorIfExis
-- !query
insert into identifier('t2') select my_col from (values (3) as (my_col)) group by 1
-- !query analysis
-InsertIntoHadoopFsRelationCommand file:[not included in comparison]/{warehouse_dir}/t2, false, Parquet, [path=file:[not included in comparison]/{warehouse_dir}/t2], Append, `spark_catalog`.`default`.`t2`, org.apache.spark.sql.execution.datasources.InMemoryFileIndex(file:[not included in comparison]/{warehouse_dir}/t2), [my_col]
+InsertIntoHadoopFsRelationCommand file:[not included in comparison]/{warehouse_dir}/t2, false, CSV, [path=file:[not included in comparison]/{warehouse_dir}/t2], Append, `spark_catalog`.`default`.`t2`, org.apache.spark.sql.execution.datasources.InMemoryFileIndex(file:[not included in comparison]/{warehouse_dir}/t2), [my_col]
+- Aggregate [my_col#x], [my_col#x]
+- SubqueryAlias __auto_generated_subquery_name
+- SubqueryAlias as
diff --git a/sql/core/src/test/resources/sql-tests/inputs/identifier-clause.sql b/sql/core/src/test/resources/sql-tests/inputs/identifier-clause.sql
index 978b82c331fe..46461dcd048e 100644
--- a/sql/core/src/test/resources/sql-tests/inputs/identifier-clause.sql
+++ b/sql/core/src/test/resources/sql-tests/inputs/identifier-clause.sql
@@ -119,8 +119,8 @@ VALUES(IDENTIFIER(1));
VALUES(IDENTIFIER(SUBSTR('HELLO', 1, RAND() + 1)));
SELECT `IDENTIFIER`('abs')(c1) FROM VALUES(-1) AS T(c1);
-CREATE TABLE IDENTIFIER(1)(c1 INT);
-CREATE TABLE IDENTIFIER('a.b.c')(c1 INT);
+CREATE TABLE IDENTIFIER(1)(c1 INT) USING csv;
+CREATE TABLE IDENTIFIER('a.b.c')(c1 INT) USING csv;
CREATE VIEW IDENTIFIER('a.b.c')(c1) AS VALUES(1);
DROP TABLE IDENTIFIER('a.b.c');
DROP VIEW IDENTIFIER('a.b.c');
@@ -135,7 +135,7 @@ CREATE TEMPORARY VIEW IDENTIFIER('default.v')(c1) AS VALUES(1);
-- SPARK-48273: Aggregation operation in statements using identifier clause for table name
create temporary view identifier('v1') as (select my_col from (values (1), (2), (1) as (my_col)) group by 1);
cache table identifier('t1') as (select my_col from (values (1), (2), (1) as (my_col)) group by 1);
-create table identifier('t2') as (select my_col from (values (1), (2), (1) as (my_col)) group by 1);
+create table identifier('t2') using csv as (select my_col from (values (1), (2), (1) as (my_col)) group by 1);
insert into identifier('t2') select my_col from (values (3) as (my_col)) group by 1;
drop view v1;
drop table t1;
diff --git a/sql/core/src/test/resources/sql-tests/results/identifier-clause.sql.out b/sql/core/src/test/resources/sql-tests/results/identifier-clause.sql.out
index 68aa5956a91c..2aa809324a76 100644
--- a/sql/core/src/test/resources/sql-tests/results/identifier-clause.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/identifier-clause.sql.out
@@ -843,7 +843,7 @@ org.apache.spark.sql.AnalysisException
-- !query
-CREATE TABLE IDENTIFIER(1)(c1 INT)
+CREATE TABLE IDENTIFIER(1)(c1 INT) USING csv
-- !query schema
struct<>
-- !query output
@@ -867,7 +867,7 @@ org.apache.spark.sql.AnalysisException
-- !query
-CREATE TABLE IDENTIFIER('a.b.c')(c1 INT)
+CREATE TABLE IDENTIFIER('a.b.c')(c1 INT) USING csv
-- !query schema
struct<>
-- !query output
@@ -1076,7 +1076,7 @@ struct<>
-- !query
-create table identifier('t2') as (select my_col from (values (1), (2), (1) as (my_col)) group by 1)
+create table identifier('t2') using csv as (select my_col from (values (1), (2), (1) as (my_col)) group by 1)
-- !query schema
struct<>
-- !query output
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org