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 2024/07/12 02:16:26 UTC
(spark) branch master updated: [SPARK-48841][SQL] Include `collationName` to `sql()` of `Collate`
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 73eab92d30bf [SPARK-48841][SQL] Include `collationName` to `sql()` of `Collate`
73eab92d30bf is described below
commit 73eab92d30bf78d39c80dd5af03b052fe9fc5211
Author: panbingkun <pa...@baidu.com>
AuthorDate: Fri Jul 12 10:16:11 2024 +0800
[SPARK-48841][SQL] Include `collationName` to `sql()` of `Collate`
### What changes were proposed in this pull request?
In the PR, I propose to fix the `sql()` method of the `Collate` expression, and append the `collationName` clause.
### Why are the changes needed?
To distinguish column names when the `collationName` argument is used by `collate`. Before the changes, columns might conflict like the example below, and that could confuse users:
```
sql("CREATE TEMP VIEW tbl as (SELECT collate('A', 'UTF8_BINARY'), collate('A', 'UTF8_LCASE'))")
```
- Before:
```
[COLUMN_ALREADY_EXISTS] The column `collate(a)` already exists. Choose another name or rename the existing column. SQLSTATE: 42711
org.apache.spark.sql.AnalysisException: [COLUMN_ALREADY_EXISTS] The column `collate(a)` already exists. Choose another name or rename the existing column. SQLSTATE: 42711
at org.apache.spark.sql.errors.QueryCompilationErrors$.columnAlreadyExistsError(QueryCompilationErrors.scala:2595)
at org.apache.spark.sql.util.SchemaUtils$.checkColumnNameDuplication(SchemaUtils.scala:115)
at org.apache.spark.sql.util.SchemaUtils$.checkColumnNameDuplication(SchemaUtils.scala:97)
```
- After:
```
describe extended tbl;
+-----------------------+-------------------------+-------+
|col_name |data_type |comment|
+-----------------------+-------------------------+-------+
|collate(A, UTF8_BINARY)|string |NULL |
|collate(A, UTF8_LCASE) |string collate UTF8_LCASE|NULL |
+-----------------------+-------------------------+-------+
```
### Does this PR introduce _any_ user-facing change?
Should not.
### How was this patch tested?
Update existed UT.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #47265 from panbingkun/SPARK-48841.
Authored-by: panbingkun <pa...@baidu.com>
Signed-off-by: Wenchen Fan <we...@databricks.com>
---
.../explain-results/function_collate.explain | 2 +-
.../expressions/collationExpressions.scala | 4 +
.../sql-functions/sql-expression-schema.md | 2 +-
.../sql-tests/analyzer-results/collations.sql.out | 60 ++---
.../resources/sql-tests/results/collations.sql.out | 50 ++--
.../spark/sql/CollationExpressionWalkerSuite.scala | 4 +-
.../apache/spark/sql/CollationSQLRegexpSuite.scala | 292 ++++++++++++++++-----
.../org/apache/spark/sql/CollationSuite.scala | 4 +-
8 files changed, 296 insertions(+), 122 deletions(-)
diff --git a/connect/common/src/test/resources/query-tests/explain-results/function_collate.explain b/connect/common/src/test/resources/query-tests/explain-results/function_collate.explain
index c736abf67b11..e4e6aedc34de 100644
--- a/connect/common/src/test/resources/query-tests/explain-results/function_collate.explain
+++ b/connect/common/src/test/resources/query-tests/explain-results/function_collate.explain
@@ -1,2 +1,2 @@
-Project [collate(g#0, UNICODE) AS collate(g)#0]
+Project [collate(g#0, UNICODE) AS collate(g, UNICODE)#0]
+- LocalRelation <empty>, [id#0L, a#0, b#0, d#0, e#0, f#0, g#0]
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collationExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collationExpressions.scala
index c528b523c5e7..c7fbb39ea285 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collationExpressions.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collationExpressions.scala
@@ -92,6 +92,10 @@ case class Collate(child: Expression, collationName: String)
override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode =
defineCodeGen(ctx, ev, (in) => in)
+
+ override def sql: String = s"$prettyName(${child.sql}, $collationName)"
+
+ override def toString: String = s"$prettyName($child, $collationName)"
}
// scalastyle:off line.contains.tab
diff --git a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
index cf218becdf1d..bf4622accf41 100644
--- a/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
+++ b/sql/core/src/test/resources/sql-functions/sql-expression-schema.md
@@ -81,7 +81,7 @@
| org.apache.spark.sql.catalyst.expressions.Chr | char | SELECT char(65) | struct<char(65):string> |
| org.apache.spark.sql.catalyst.expressions.Chr | chr | SELECT chr(65) | struct<chr(65):string> |
| org.apache.spark.sql.catalyst.expressions.Coalesce | coalesce | SELECT coalesce(NULL, 1, NULL) | struct<coalesce(NULL, 1, NULL):int> |
-| org.apache.spark.sql.catalyst.expressions.CollateExpressionBuilder | collate | SELECT COLLATION('Spark SQL' collate UTF8_LCASE) | struct<collation(collate(Spark SQL)):string> |
+| org.apache.spark.sql.catalyst.expressions.CollateExpressionBuilder | collate | SELECT COLLATION('Spark SQL' collate UTF8_LCASE) | struct<collation(collate(Spark SQL, UTF8_LCASE)):string> |
| org.apache.spark.sql.catalyst.expressions.Collation | collation | SELECT collation('Spark SQL') | struct<collation(Spark SQL):string> |
| org.apache.spark.sql.catalyst.expressions.Concat | concat | SELECT concat('Spark', 'SQL') | struct<concat(Spark, SQL):string> |
| org.apache.spark.sql.catalyst.expressions.ConcatWs | concat_ws | SELECT concat_ws(' ', 'Spark', 'SQL') | struct<concat_ws( , Spark, SQL):string> |
diff --git a/sql/core/src/test/resources/sql-tests/analyzer-results/collations.sql.out b/sql/core/src/test/resources/sql-tests/analyzer-results/collations.sql.out
index e6409806bad7..6f9cb3b75971 100644
--- a/sql/core/src/test/resources/sql-tests/analyzer-results/collations.sql.out
+++ b/sql/core/src/test/resources/sql-tests/analyzer-results/collations.sql.out
@@ -159,9 +159,9 @@ DropTable false, false
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') except select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query analysis
Except false
-:- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
+:- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
: +- LocalRelation [col1#x]
-+- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
++- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
+- LocalRelation [col1#x]
@@ -169,9 +169,9 @@ Except false
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') except all select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query analysis
Except All true
-:- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
+:- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
: +- LocalRelation [col1#x]
-+- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
++- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
+- LocalRelation [col1#x]
@@ -180,9 +180,9 @@ select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), (
-- !query analysis
Distinct
+- Union false, false
- :- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
+ :- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
: +- LocalRelation [col1#x]
- +- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
+ +- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
+- LocalRelation [col1#x]
@@ -190,9 +190,9 @@ Distinct
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') union all select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query analysis
Union false, false
-:- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
+:- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
: +- LocalRelation [col1#x]
-+- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
++- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
+- LocalRelation [col1#x]
@@ -200,9 +200,9 @@ Union false, false
select col1 collate utf8_lcase from values ('aaa'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') intersect select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query analysis
Intersect false
-:- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
+:- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
: +- LocalRelation [col1#x]
-+- Project [collate(col1#x, utf8_lcase) AS collate(col1)#x]
++- Project [collate(col1#x, utf8_lcase) AS collate(col1, utf8_lcase)#x]
+- LocalRelation [col1#x]
@@ -254,138 +254,138 @@ DropTable false, false
-- !query
select array_contains(ARRAY('aaa' collate utf8_lcase),'AAA' collate utf8_lcase)
-- !query analysis
-Project [array_contains(array(collate(aaa, utf8_lcase)), collate(AAA, utf8_lcase)) AS array_contains(array(collate(aaa)), collate(AAA))#x]
+Project [array_contains(array(collate(aaa, utf8_lcase)), collate(AAA, utf8_lcase)) AS array_contains(array(collate(aaa, utf8_lcase)), collate(AAA, utf8_lcase))#x]
+- OneRowRelation
-- !query
select array_position(ARRAY('aaa' collate utf8_lcase, 'bbb' collate utf8_lcase),'BBB' collate utf8_lcase)
-- !query analysis
-Project [array_position(array(collate(aaa, utf8_lcase), collate(bbb, utf8_lcase)), collate(BBB, utf8_lcase)) AS array_position(array(collate(aaa), collate(bbb)), collate(BBB))#xL]
+Project [array_position(array(collate(aaa, utf8_lcase), collate(bbb, utf8_lcase)), collate(BBB, utf8_lcase)) AS array_position(array(collate(aaa, utf8_lcase), collate(bbb, utf8_lcase)), collate(BBB, utf8_lcase))#xL]
+- OneRowRelation
-- !query
select nullif('aaa' COLLATE utf8_lcase, 'AAA' COLLATE utf8_lcase)
-- !query analysis
-Project [nullif(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase)) AS nullif(collate(aaa), collate(AAA))#x]
+Project [nullif(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase)) AS nullif(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase))#x]
+- OneRowRelation
-- !query
select least('aaa' COLLATE utf8_lcase, 'AAA' collate utf8_lcase, 'a' collate utf8_lcase)
-- !query analysis
-Project [least(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase), collate(a, utf8_lcase)) AS least(collate(aaa), collate(AAA), collate(a))#x]
+Project [least(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase), collate(a, utf8_lcase)) AS least(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase), collate(a, utf8_lcase))#x]
+- OneRowRelation
-- !query
select arrays_overlap(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query analysis
-Project [arrays_overlap(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS arrays_overlap(array(collate(aaa)), array(collate(AAA)))#x]
+Project [arrays_overlap(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS arrays_overlap(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase)))#x]
+- OneRowRelation
-- !query
select array_distinct(array('aaa' collate utf8_lcase, 'AAA' collate utf8_lcase))
-- !query analysis
-Project [array_distinct(array(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase))) AS array_distinct(array(collate(aaa), collate(AAA)))#x]
+Project [array_distinct(array(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase))) AS array_distinct(array(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase)))#x]
+- OneRowRelation
-- !query
select array_union(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query analysis
-Project [array_union(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS array_union(array(collate(aaa)), array(collate(AAA)))#x]
+Project [array_union(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS array_union(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase)))#x]
+- OneRowRelation
-- !query
select array_intersect(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query analysis
-Project [array_intersect(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS array_intersect(array(collate(aaa)), array(collate(AAA)))#x]
+Project [array_intersect(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS array_intersect(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase)))#x]
+- OneRowRelation
-- !query
select array_except(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query analysis
-Project [array_except(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS array_except(array(collate(aaa)), array(collate(AAA)))#x]
+Project [array_except(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))) AS array_except(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase)))#x]
+- OneRowRelation
-- !query
select 'a' collate unicode < 'A'
-- !query analysis
-Project [(collate(a, unicode) < cast(A as string collate UNICODE)) AS (collate(a) < A)#x]
+Project [(collate(a, unicode) < cast(A as string collate UNICODE)) AS (collate(a, unicode) < A)#x]
+- OneRowRelation
-- !query
select 'a' collate unicode_ci = 'A'
-- !query analysis
-Project [(collate(a, unicode_ci) = cast(A as string collate UNICODE_CI)) AS (collate(a) = A)#x]
+Project [(collate(a, unicode_ci) = cast(A as string collate UNICODE_CI)) AS (collate(a, unicode_ci) = A)#x]
+- OneRowRelation
-- !query
select 'a' collate unicode_ai = 'å'
-- !query analysis
-Project [(collate(a, unicode_ai) = cast(å as string collate UNICODE_AI)) AS (collate(a) = å)#x]
+Project [(collate(a, unicode_ai) = cast(å as string collate UNICODE_AI)) AS (collate(a, unicode_ai) = å)#x]
+- OneRowRelation
-- !query
select 'a' collate unicode_ci_ai = 'Å'
-- !query analysis
-Project [(collate(a, unicode_ci_ai) = cast(Å as string collate UNICODE_CI_AI)) AS (collate(a) = Å)#x]
+Project [(collate(a, unicode_ci_ai) = cast(Å as string collate UNICODE_CI_AI)) AS (collate(a, unicode_ci_ai) = Å)#x]
+- OneRowRelation
-- !query
select 'a' collate en < 'A'
-- !query analysis
-Project [(collate(a, en) < cast(A as string collate en)) AS (collate(a) < A)#x]
+Project [(collate(a, en) < cast(A as string collate en)) AS (collate(a, en) < A)#x]
+- OneRowRelation
-- !query
select 'a' collate en_ci = 'A'
-- !query analysis
-Project [(collate(a, en_ci) = cast(A as string collate en_CI)) AS (collate(a) = A)#x]
+Project [(collate(a, en_ci) = cast(A as string collate en_CI)) AS (collate(a, en_ci) = A)#x]
+- OneRowRelation
-- !query
select 'a' collate en_ai = 'å'
-- !query analysis
-Project [(collate(a, en_ai) = cast(å as string collate en_AI)) AS (collate(a) = å)#x]
+Project [(collate(a, en_ai) = cast(å as string collate en_AI)) AS (collate(a, en_ai) = å)#x]
+- OneRowRelation
-- !query
select 'a' collate en_ci_ai = 'Å'
-- !query analysis
-Project [(collate(a, en_ci_ai) = cast(Å as string collate en_CI_AI)) AS (collate(a) = Å)#x]
+Project [(collate(a, en_ci_ai) = cast(Å as string collate en_CI_AI)) AS (collate(a, en_ci_ai) = Å)#x]
+- OneRowRelation
-- !query
select 'Kypper' collate sv < 'Köpfe'
-- !query analysis
-Project [(collate(Kypper, sv) < cast(Köpfe as string collate sv)) AS (collate(Kypper) < Köpfe)#x]
+Project [(collate(Kypper, sv) < cast(Köpfe as string collate sv)) AS (collate(Kypper, sv) < Köpfe)#x]
+- OneRowRelation
-- !query
select 'Kypper' collate de > 'Köpfe'
-- !query analysis
-Project [(collate(Kypper, de) > cast(Köpfe as string collate de)) AS (collate(Kypper) > Köpfe)#x]
+Project [(collate(Kypper, de) > cast(Köpfe as string collate de)) AS (collate(Kypper, de) > Köpfe)#x]
+- OneRowRelation
-- !query
select 'I' collate tr_ci = 'ı'
-- !query analysis
-Project [(collate(I, tr_ci) = cast(ı as string collate tr_CI)) AS (collate(I) = ı)#x]
+Project [(collate(I, tr_ci) = cast(ı as string collate tr_CI)) AS (collate(I, tr_ci) = ı)#x]
+- OneRowRelation
diff --git a/sql/core/src/test/resources/sql-tests/results/collations.sql.out b/sql/core/src/test/resources/sql-tests/results/collations.sql.out
index 89e6665df9d0..37fb6c4e114e 100644
--- a/sql/core/src/test/resources/sql-tests/results/collations.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/collations.sql.out
@@ -170,7 +170,7 @@ struct<>
-- !query
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') except select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query schema
-struct<collate(col1):string collate UTF8_LCASE>
+struct<collate(col1, utf8_lcase):string collate UTF8_LCASE>
-- !query output
zzz
@@ -178,7 +178,7 @@ zzz
-- !query
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') except all select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query schema
-struct<collate(col1):string collate UTF8_LCASE>
+struct<collate(col1, utf8_lcase):string collate UTF8_LCASE>
-- !query output
aaa
bbb
@@ -189,7 +189,7 @@ zzz
-- !query
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') union select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query schema
-struct<collate(col1):string collate UTF8_LCASE>
+struct<collate(col1, utf8_lcase):string collate UTF8_LCASE>
-- !query output
aaa
bbb
@@ -199,7 +199,7 @@ zzz
-- !query
select col1 collate utf8_lcase from values ('aaa'), ('AAA'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') union all select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query schema
-struct<collate(col1):string collate UTF8_LCASE>
+struct<collate(col1, utf8_lcase):string collate UTF8_LCASE>
-- !query output
AAA
BBB
@@ -214,7 +214,7 @@ zzz
-- !query
select col1 collate utf8_lcase from values ('aaa'), ('bbb'), ('BBB'), ('zzz'), ('ZZZ') intersect select col1 collate utf8_lcase from values ('aaa'), ('bbb')
-- !query schema
-struct<collate(col1):string collate UTF8_LCASE>
+struct<collate(col1, utf8_lcase):string collate UTF8_LCASE>
-- !query output
aaa
bbb
@@ -272,7 +272,7 @@ struct<>
-- !query
select array_contains(ARRAY('aaa' collate utf8_lcase),'AAA' collate utf8_lcase)
-- !query schema
-struct<array_contains(array(collate(aaa)), collate(AAA)):boolean>
+struct<array_contains(array(collate(aaa, utf8_lcase)), collate(AAA, utf8_lcase)):boolean>
-- !query output
true
@@ -280,7 +280,7 @@ true
-- !query
select array_position(ARRAY('aaa' collate utf8_lcase, 'bbb' collate utf8_lcase),'BBB' collate utf8_lcase)
-- !query schema
-struct<array_position(array(collate(aaa), collate(bbb)), collate(BBB)):bigint>
+struct<array_position(array(collate(aaa, utf8_lcase), collate(bbb, utf8_lcase)), collate(BBB, utf8_lcase)):bigint>
-- !query output
2
@@ -288,7 +288,7 @@ struct<array_position(array(collate(aaa), collate(bbb)), collate(BBB)):bigint>
-- !query
select nullif('aaa' COLLATE utf8_lcase, 'AAA' COLLATE utf8_lcase)
-- !query schema
-struct<nullif(collate(aaa), collate(AAA)):string collate UTF8_LCASE>
+struct<nullif(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase)):string collate UTF8_LCASE>
-- !query output
NULL
@@ -296,7 +296,7 @@ NULL
-- !query
select least('aaa' COLLATE utf8_lcase, 'AAA' collate utf8_lcase, 'a' collate utf8_lcase)
-- !query schema
-struct<least(collate(aaa), collate(AAA), collate(a)):string collate UTF8_LCASE>
+struct<least(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase), collate(a, utf8_lcase)):string collate UTF8_LCASE>
-- !query output
a
@@ -304,7 +304,7 @@ a
-- !query
select arrays_overlap(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query schema
-struct<arrays_overlap(array(collate(aaa)), array(collate(AAA))):boolean>
+struct<arrays_overlap(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))):boolean>
-- !query output
true
@@ -312,7 +312,7 @@ true
-- !query
select array_distinct(array('aaa' collate utf8_lcase, 'AAA' collate utf8_lcase))
-- !query schema
-struct<array_distinct(array(collate(aaa), collate(AAA))):array<string collate UTF8_LCASE>>
+struct<array_distinct(array(collate(aaa, utf8_lcase), collate(AAA, utf8_lcase))):array<string collate UTF8_LCASE>>
-- !query output
["aaa"]
@@ -320,7 +320,7 @@ struct<array_distinct(array(collate(aaa), collate(AAA))):array<string collate UT
-- !query
select array_union(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query schema
-struct<array_union(array(collate(aaa)), array(collate(AAA))):array<string collate UTF8_LCASE>>
+struct<array_union(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))):array<string collate UTF8_LCASE>>
-- !query output
["aaa"]
@@ -328,7 +328,7 @@ struct<array_union(array(collate(aaa)), array(collate(AAA))):array<string collat
-- !query
select array_intersect(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query schema
-struct<array_intersect(array(collate(aaa)), array(collate(AAA))):array<string collate UTF8_LCASE>>
+struct<array_intersect(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))):array<string collate UTF8_LCASE>>
-- !query output
["aaa"]
@@ -336,7 +336,7 @@ struct<array_intersect(array(collate(aaa)), array(collate(AAA))):array<string co
-- !query
select array_except(array('aaa' collate utf8_lcase), array('AAA' collate utf8_lcase))
-- !query schema
-struct<array_except(array(collate(aaa)), array(collate(AAA))):array<string collate UTF8_LCASE>>
+struct<array_except(array(collate(aaa, utf8_lcase)), array(collate(AAA, utf8_lcase))):array<string collate UTF8_LCASE>>
-- !query output
[]
@@ -344,7 +344,7 @@ struct<array_except(array(collate(aaa)), array(collate(AAA))):array<string colla
-- !query
select 'a' collate unicode < 'A'
-- !query schema
-struct<(collate(a) < A):boolean>
+struct<(collate(a, unicode) < A):boolean>
-- !query output
true
@@ -352,7 +352,7 @@ true
-- !query
select 'a' collate unicode_ci = 'A'
-- !query schema
-struct<(collate(a) = A):boolean>
+struct<(collate(a, unicode_ci) = A):boolean>
-- !query output
true
@@ -360,7 +360,7 @@ true
-- !query
select 'a' collate unicode_ai = 'å'
-- !query schema
-struct<(collate(a) = å):boolean>
+struct<(collate(a, unicode_ai) = å):boolean>
-- !query output
true
@@ -368,7 +368,7 @@ true
-- !query
select 'a' collate unicode_ci_ai = 'Å'
-- !query schema
-struct<(collate(a) = Å):boolean>
+struct<(collate(a, unicode_ci_ai) = Å):boolean>
-- !query output
true
@@ -376,7 +376,7 @@ true
-- !query
select 'a' collate en < 'A'
-- !query schema
-struct<(collate(a) < A):boolean>
+struct<(collate(a, en) < A):boolean>
-- !query output
true
@@ -384,7 +384,7 @@ true
-- !query
select 'a' collate en_ci = 'A'
-- !query schema
-struct<(collate(a) = A):boolean>
+struct<(collate(a, en_ci) = A):boolean>
-- !query output
true
@@ -392,7 +392,7 @@ true
-- !query
select 'a' collate en_ai = 'å'
-- !query schema
-struct<(collate(a) = å):boolean>
+struct<(collate(a, en_ai) = å):boolean>
-- !query output
true
@@ -400,7 +400,7 @@ true
-- !query
select 'a' collate en_ci_ai = 'Å'
-- !query schema
-struct<(collate(a) = Å):boolean>
+struct<(collate(a, en_ci_ai) = Å):boolean>
-- !query output
true
@@ -408,7 +408,7 @@ true
-- !query
select 'Kypper' collate sv < 'Köpfe'
-- !query schema
-struct<(collate(Kypper) < Köpfe):boolean>
+struct<(collate(Kypper, sv) < Köpfe):boolean>
-- !query output
true
@@ -416,7 +416,7 @@ true
-- !query
select 'Kypper' collate de > 'Köpfe'
-- !query schema
-struct<(collate(Kypper) > Köpfe):boolean>
+struct<(collate(Kypper, de) > Köpfe):boolean>
-- !query output
true
@@ -424,6 +424,6 @@ true
-- !query
select 'I' collate tr_ci = 'ı'
-- !query schema
-struct<(collate(I) = ı):boolean>
+struct<(collate(I, tr_ci) = ı):boolean>
-- !query output
true
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/CollationExpressionWalkerSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/CollationExpressionWalkerSuite.scala
index a639367e8ca5..e4f4bb6e8557 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/CollationExpressionWalkerSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/CollationExpressionWalkerSuite.scala
@@ -568,8 +568,8 @@ class CollationExpressionWalkerSuite extends SparkFunSuite with SharedSparkSessi
case st if utf8BinaryResultChecked != null && utf8BinaryLcaseResultChecked != null &&
hasStringType(st) =>
// scalastyle:off caselocale
- assert(utf8BinaryResultChecked.getRows(1, 0).map(_.map(_.toLowerCase)) ===
- utf8BinaryLcaseResultChecked.getRows(1, 0).map(_.map(_.toLowerCase)))
+ assert(utf8BinaryResultChecked.getRows(1, 0).map(_.map(_.toLowerCase))(1) ===
+ utf8BinaryLcaseResultChecked.getRows(1, 0).map(_.map(_.toLowerCase))(1))
// scalastyle:on caselocale
case _ =>
assert(utf8BinaryResultChecked.getRows(1, 0)(1) ===
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLRegexpSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLRegexpSuite.scala
index 885ed3709868..8ff7bed60bbc 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLRegexpSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLRegexpSuite.scala
@@ -50,10 +50,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT like(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"collate(ABC, UNICODE_CI) LIKE %b%\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABC, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"like(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 47)
+ )
})
}
@@ -132,10 +144,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT ilike(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"ilike(collate(ABC, UNICODE_CI), %b%)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABC, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"ilike(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 48)
+ )
})
}
@@ -160,10 +184,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT collate('${t.s}', '${t.c}') LIKE ALL ('${t.p.mkString("','")}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"likeall(collate(Foo, UNICODE_CI))\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(Foo, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"LIKE ALL ('${t.p.mkString("','")}')",
+ start = 36,
+ stop = 59)
+ )
})
}
@@ -188,10 +224,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT collate('${t.s}', '${t.c}') NOT LIKE ALL ('${t.p.mkString("','")}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"notlikeall(collate(Foo, UNICODE_CI))\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(Foo, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"NOT LIKE ALL ('${t.p.mkString("','")}')",
+ start = 36,
+ stop = 63)
+ )
})
}
@@ -216,10 +264,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT collate('${t.s}', '${t.c}') LIKE ANY ('${t.p.mkString("','")}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"likeany(collate(Foo, UNICODE_CI))\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(Foo, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"LIKE ANY ('${t.p.mkString("','")}')",
+ start = 36,
+ stop = 59)
+ )
})
}
@@ -244,10 +304,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT collate('${t.s}', '${t.c}') NOT LIKE ANY ('${t.p.mkString("','")}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"notlikeany(collate(Foo, UNICODE_CI))\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(Foo, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"NOT LIKE ANY ('${t.p.mkString("','")}')",
+ start = 36,
+ stop = 63)
+ )
})
}
@@ -272,10 +344,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT rlike(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"RLIKE(collate(ABC, UNICODE_CI), .b.)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABC, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"rlike(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 48)
+ )
})
}
@@ -300,10 +384,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT split(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"split(collate(ABC, UNICODE_CI), [b], -1)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABC, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"split(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 48)
+ )
})
}
@@ -329,10 +425,13 @@ class CollationSQLRegexpSuite
})
// Collation mismatch
val (c1, c2) = ("UTF8_BINARY", "UTF8_LCASE")
- val collationMismatch = intercept[AnalysisException] {
- sql(s"SELECT regexp_replace(collate('ABCDE','$c1'), '.c.', collate('FFF','$c2'))")
- }
- assert(collationMismatch.getErrorClass === "COLLATION_MISMATCH.EXPLICIT")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(s"SELECT regexp_replace(collate('ABCDE','$c1'), '.c.', collate('FFF','$c2'))")
+ },
+ errorClass = "COLLATION_MISMATCH.EXPLICIT",
+ parameters = Map("explicitTypes" -> "`string`.`string collate UTF8_LCASE`")
+ )
// Unsupported collations
case class RegExpReplaceTestFail(l: String, r: String, c: String)
val failCases = Seq(
@@ -341,10 +440,22 @@ class CollationSQLRegexpSuite
failCases.foreach(t => {
val query =
s"SELECT regexp_replace(collate('${t.l}', '${t.c}'), '${t.r}', 'FFF')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"regexp_replace(collate(ABCDE, UNICODE_CI), .c., FFF, 1)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABCDE, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"regexp_replace(collate('${t.l}', '${t.c}'), '${t.r}', 'FFF')",
+ start = 7,
+ stop = 66)
+ )
})
}
@@ -371,10 +482,22 @@ class CollationSQLRegexpSuite
failCases.foreach(t => {
val query =
s"SELECT regexp_extract(collate('${t.l}', '${t.c}'), '${t.r}', 0)"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"regexp_extract(collate(ABCDE, UNICODE_CI), .c., 0)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABCDE, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"regexp_extract(collate('${t.l}', '${t.c}'), '${t.r}', 0)",
+ start = 7,
+ stop = 62)
+ )
})
}
@@ -401,10 +524,22 @@ class CollationSQLRegexpSuite
failCases.foreach(t => {
val query =
s"SELECT regexp_extract_all(collate('${t.l}', '${t.c}'), '${t.r}', 0)"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"regexp_extract_all(collate(ABCDE, UNICODE_CI), .c., 0)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABCDE, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"regexp_extract_all(collate('${t.l}', '${t.c}'), '${t.r}', 0)",
+ start = 7,
+ stop = 66)
+ )
})
}
@@ -429,10 +564,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT regexp_count(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"regexp_count(collate(ABCDE, UNICODE_CI), .c.)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABCDE, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"regexp_count(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 57)
+ )
})
}
@@ -457,10 +604,22 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT regexp_substr(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"regexp_substr(collate(ABCDE, UNICODE_CI), .c.)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABCDE, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"regexp_substr(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 58)
+ )
})
}
@@ -485,12 +644,23 @@ class CollationSQLRegexpSuite
)
failCases.foreach(t => {
val query = s"SELECT regexp_instr(collate('${t.l}', '${t.c}'), '${t.r}')"
- val unsupportedCollation = intercept[AnalysisException] {
- sql(query)
- }
- assert(unsupportedCollation.getErrorClass === "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE")
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(query)
+ },
+ errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
+ parameters = Map(
+ "sqlExpr" -> "\"regexp_instr(collate(ABCDE, UNICODE_CI), .c., 0)\"",
+ "paramIndex" -> "first",
+ "inputSql" -> "\"collate(ABCDE, UNICODE_CI)\"",
+ "inputType" -> "\"STRING COLLATE UNICODE_CI\"",
+ "requiredType" -> "\"STRING\""),
+ context = ExpectedContext(
+ fragment = s"regexp_instr(collate('${t.l}', '${t.c}'), '${t.r}')",
+ start = 7,
+ stop = 57)
+ )
})
}
-
}
// scalastyle:on nonascii
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala
index f662b86eaf81..af3169932bfc 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala
@@ -135,7 +135,7 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {
errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
sqlState = "42K09",
parameters = Map(
- "sqlExpr" -> "\"collate(1)\"",
+ "sqlExpr" -> "\"collate(1, UTF8_BINARY)\"",
"paramIndex" -> "first",
"inputSql" -> "\"1\"",
"inputType" -> "\"INT\"",
@@ -1026,7 +1026,7 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {
exception = intercept[AnalysisException](sql(query)),
errorClass = "DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE",
parameters = Map(
- "sqlExpr" -> "\"map(collate(aaa), 1, collate(AAA), 2)[AaA]\"",
+ "sqlExpr" -> "\"map(collate(aaa, utf8_lcase), 1, collate(AAA, utf8_lcase), 2)[AaA]\"",
"paramIndex" -> "second",
"inputSql" -> "\"AaA\"",
"inputType" -> toSQLType(StringType),
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org