This is an automated email from the ASF dual-hosted git repository.
maxgekk 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 bbc80430dfce [SPARK-51563][SQL] Support the fully qualified type name
TIME(n) WITHOUT TIME ZONE
bbc80430dfce is described below
commit bbc80430dfce72336c5ff5184f9d3d935c3ca850
Author: Max Gekk <[email protected]>
AuthorDate: Sat Jun 14 16:03:25 2025 +0300
[SPARK-51563][SQL] Support the fully qualified type name TIME(n) WITHOUT
TIME ZONE
### What changes were proposed in this pull request?
In the PR, I propose to recognize the optional suffix `WITHOUT TIME ZONE`
of the type `TIME(n)`, and consider `TIME(n) WITHOUT TIME ZONE` and `TIME(n)`
as synonyms.
### Why are the changes needed?
To conform to the ANSI SQL standard.
### Does this PR introduce _any_ user-facing change?
No. It just extends the existing syntax.
### How was this patch tested?
By running the affected test suites:
```
$ build/sbt "test:testOnly *DataTypeParserSuite"
$ build/sbt "sql/testOnly org.apache.spark.sql.SQLQueryTestSuite -- -z
keywords.sql"
$ build/sbt "sql/testOnly org.apache.spark.sql.SQLQueryTestSuite -- -z
keywords-enforced.sql"
```
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #51177 from MaxGekk/time-without-timezone.
Authored-by: Max Gekk <[email protected]>
Signed-off-by: Max Gekk <[email protected]>
---
docs/sql-ref-ansi-compliance.md | 1 +
.../spark/sql/catalyst/parser/SqlBaseLexer.g4 | 1 +
.../spark/sql/catalyst/parser/SqlBaseParser.g4 | 4 +++
.../sql/catalyst/parser/DataTypeAstBuilder.scala | 14 ++++++++--
.../sql/catalyst/parser/DataTypeParserSuite.scala | 30 ++++++++++++++++++++++
.../sql-tests/results/keywords-enforced.sql.out | 1 +
.../resources/sql-tests/results/keywords.sql.out | 1 +
.../sql-tests/results/nonansi/keywords.sql.out | 1 +
.../org/apache/spark/sql/JsonFunctionsSuite.scala | 2 +-
.../org/apache/spark/sql/XmlFunctionsSuite.scala | 2 +-
.../ThriftServerWithSparkContextSuite.scala | 2 +-
11 files changed, 54 insertions(+), 5 deletions(-)
diff --git a/docs/sql-ref-ansi-compliance.md b/docs/sql-ref-ansi-compliance.md
index ef79ef187136..acef717ef40a 100644
--- a/docs/sql-ref-ansi-compliance.md
+++ b/docs/sql-ref-ansi-compliance.md
@@ -794,6 +794,7 @@ Below is a list of all the keywords in Spark SQL.
|WINDOW|non-reserved|non-reserved|reserved|
|WITH|reserved|non-reserved|reserved|
|WITHIN|reserved|non-reserved|reserved|
+|WITHOUT|non-reserved|non-reserved|non-reserved|
|X|non-reserved|non-reserved|non-reserved|
|YEAR|non-reserved|non-reserved|non-reserved|
|YEARS|non-reserved|non-reserved|non-reserved|
diff --git
a/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseLexer.g4
b/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseLexer.g4
index c698f2696eb4..d3a1958f2b47 100644
---
a/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseLexer.g4
+++
b/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseLexer.g4
@@ -507,6 +507,7 @@ WHILE: 'WHILE';
WINDOW: 'WINDOW';
WITH: 'WITH';
WITHIN: 'WITHIN';
+WITHOUT: 'WITHOUT';
YEAR: 'YEAR';
YEARS: 'YEARS';
ZONE: 'ZONE';
diff --git
a/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4
b/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4
index 08f222b2f412..b56a7d39f628 100644
---
a/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4
+++
b/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4
@@ -1343,6 +1343,8 @@ dataType
| INTERVAL from=(YEAR | MONTH) (TO to=MONTH)?
#yearMonthIntervalDataType
| INTERVAL from=(DAY | HOUR | MINUTE | SECOND)
(TO to=(HOUR | MINUTE | SECOND))?
#dayTimeIntervalDataType
+ | TIME (LEFT_PAREN precision=INTEGER_VALUE RIGHT_PAREN)?
+ (WITHOUT TIME ZONE)? #timeDataType
| type (LEFT_PAREN INTEGER_VALUE
(COMMA INTEGER_VALUE)* RIGHT_PAREN)?
#primitiveDataType
;
@@ -2013,6 +2015,7 @@ ansiNonReserved
| WEEKS
| WHILE
| WINDOW
+ | WITHOUT
| YEAR
| YEARS
| ZONE
@@ -2423,6 +2426,7 @@ nonReserved
| WINDOW
| WITH
| WITHIN
+ | WITHOUT
| YEAR
| YEARS
| ZONE
diff --git
a/sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala
b/sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala
index bf9a250d6499..b18b783c7bc8 100644
---
a/sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala
+++
b/sql/api/src/main/scala/org/apache/spark/sql/catalyst/parser/DataTypeAstBuilder.scala
@@ -65,6 +65,18 @@ class DataTypeAstBuilder extends
SqlBaseParserBaseVisitor[AnyRef] {
ctx.parts.asScala.map(_.getText).toSeq
}
+ /**
+ * Resolve/create the TIME primitive type.
+ */
+ override def visitTimeDataType(ctx: TimeDataTypeContext): DataType =
withOrigin(ctx) {
+ val precision = if (ctx.precision == null) {
+ TimeType.MICROS_PRECISION
+ } else {
+ ctx.precision.getText.toInt
+ }
+ TimeType(precision)
+ }
+
/**
* Resolve/create a primitive type.
*/
@@ -79,8 +91,6 @@ class DataTypeAstBuilder extends
SqlBaseParserBaseVisitor[AnyRef] {
case (FLOAT | REAL, Nil) => FloatType
case (DOUBLE, Nil) => DoubleType
case (DATE, Nil) => DateType
- case (TIME, Nil) => TimeType(TimeType.MICROS_PRECISION)
- case (TIME, precision :: Nil) => TimeType(precision.getText.toInt)
case (TIMESTAMP, Nil) => SqlApiConf.get.timestampType
case (TIMESTAMP_NTZ, Nil) => TimestampNTZType
case (TIMESTAMP_LTZ, Nil) => TimestampType
diff --git
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/DataTypeParserSuite.scala
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/DataTypeParserSuite.scala
index 8b61328a0099..bf15e184b650 100644
---
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/DataTypeParserSuite.scala
+++
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/DataTypeParserSuite.scala
@@ -58,8 +58,11 @@ class DataTypeParserSuite extends SparkFunSuite with
SQLHelper {
checkDataType("deC", DecimalType.USER_DEFAULT)
checkDataType("DATE", DateType)
checkDataType("TimE", TimeType())
+ checkDataType("TimE WiTHOUT TiME ZoNE", TimeType())
checkDataType("time(0)", TimeType(0))
+ checkDataType("time(0) without time zone", TimeType(0))
checkDataType("TIME(6)", TimeType(6))
+ checkDataType("TIME(6) WITHOUT TIME ZONE", TimeType(6))
checkDataType("timestamp", TimestampType)
checkDataType("timestamp_ntz", TimestampNTZType)
checkDataType("timestamp_ltz", TimestampType)
@@ -183,11 +186,38 @@ class DataTypeParserSuite extends SparkFunSuite with
SQLHelper {
},
condition = "UNSUPPORTED_TIME_PRECISION",
parameters = Map("precision" -> "9"))
+ checkError(
+ exception = intercept[SparkException] {
+ CatalystSqlParser.parseDataType("time(8) without time zone")
+ },
+ condition = "UNSUPPORTED_TIME_PRECISION",
+ parameters = Map("precision" -> "8"))
checkError(
exception = intercept[ParseException] {
CatalystSqlParser.parseDataType("time(-1)")
},
condition = "PARSE_SYNTAX_ERROR",
parameters = Map("error" -> "'('", "hint" -> ""))
+ checkError(
+ exception = intercept[ParseException] {
+ CatalystSqlParser.parseDataType("time(-100) WITHOUT TIME ZONE")
+ },
+ condition = "PARSE_SYNTAX_ERROR",
+ parameters = Map("error" -> "'('", "hint" -> ""))
+ }
+
+ test("invalid TIME suffix") {
+ checkError(
+ exception = intercept[ParseException] {
+ CatalystSqlParser.parseDataType("time(0) WITHOUT TIMEZONE")
+ },
+ condition = "PARSE_SYNTAX_ERROR",
+ parameters = Map("error" -> "'WITHOUT'", "hint" -> ""))
+ checkError(
+ exception = intercept[ParseException] {
+ CatalystSqlParser.parseDataType("time(0) WITH TIME ZONE")
+ },
+ condition = "PARSE_SYNTAX_ERROR",
+ parameters = Map("error" -> "'WITH'", "hint" -> ""))
}
}
diff --git
a/sql/core/src/test/resources/sql-tests/results/keywords-enforced.sql.out
b/sql/core/src/test/resources/sql-tests/results/keywords-enforced.sql.out
index a72b2c4dc8da..ef17566850e3 100644
--- a/sql/core/src/test/resources/sql-tests/results/keywords-enforced.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/keywords-enforced.sql.out
@@ -390,6 +390,7 @@ WHILE false
WINDOW false
WITH true
WITHIN true
+WITHOUT false
X false
YEAR false
YEARS false
diff --git a/sql/core/src/test/resources/sql-tests/results/keywords.sql.out
b/sql/core/src/test/resources/sql-tests/results/keywords.sql.out
index 59f860eb7ef4..97309774cc37 100644
--- a/sql/core/src/test/resources/sql-tests/results/keywords.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/keywords.sql.out
@@ -390,6 +390,7 @@ WHILE false
WINDOW false
WITH false
WITHIN false
+WITHOUT false
X false
YEAR false
YEARS false
diff --git
a/sql/core/src/test/resources/sql-tests/results/nonansi/keywords.sql.out
b/sql/core/src/test/resources/sql-tests/results/nonansi/keywords.sql.out
index 59f860eb7ef4..97309774cc37 100644
--- a/sql/core/src/test/resources/sql-tests/results/nonansi/keywords.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/nonansi/keywords.sql.out
@@ -390,6 +390,7 @@ WHILE false
WINDOW false
WITH false
WITHIN false
+WITHOUT false
X false
YEAR false
YEARS false
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
index ea185b6b4901..68d98cd0d182 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/JsonFunctionsSuite.scala
@@ -559,7 +559,7 @@ class JsonFunctionsSuite extends QueryTest with
SharedSparkSession {
sqlState = "42601",
parameters = Map(
"error" -> "'InvalidType'",
- "hint" -> ": extra input 'InvalidType'"
+ "hint" -> ""
),
context = ExpectedContext(
fragment = "from_json(value, 'time InvalidType')",
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/XmlFunctionsSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/XmlFunctionsSuite.scala
index afb0ceac5b50..51509cc5ec3e 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/XmlFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/XmlFunctionsSuite.scala
@@ -366,7 +366,7 @@ class XmlFunctionsSuite extends QueryTest with
SharedSparkSession {
sqlState = "42601",
parameters = Map(
"error" -> "'InvalidType'",
- "hint" -> ": extra input 'InvalidType'"
+ "hint" -> ""
),
context = ExpectedContext(
fragment = "from_xml(value, 'time InvalidType')",
diff --git
a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/ThriftServerWithSparkContextSuite.scala
b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/ThriftServerWithSparkContextSuite.scala
index 33ac3ebc6c95..a394295360f5 100644
---
a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/ThriftServerWithSparkContextSuite.scala
+++
b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/ThriftServerWithSparkContextSuite.scala
@@ -214,7 +214,7 @@ trait ThriftServerWithSparkContextSuite extends
SharedThriftServer {
val sessionHandle = client.openSession(user, "")
val infoValue = client.getInfo(sessionHandle,
GetInfoType.CLI_ODBC_KEYWORDS)
// scalastyle:off line.size.limit
- assert(infoValue.getStringValue ==
"ADD,AFTER,AGGREGATE,ALL,ALTER,ALWAYS,ANALYZE,AND,ANTI,ANY,ANY_VALUE,ARCHIVE,ARRAY,AS,ASC,AT,ATOMIC,AUTHORIZATION,BEGIN,BETWEEN,BIGINT,BINARY,BINDING,BOOLEAN,BOTH,BUCKET,BUCKETS,BY,BYTE,CACHE,CALL,CALLED,CASCADE,CASE,CAST,CATALOG,CATALOGS,CHANGE,CHAR,CHARACTER,CHECK,CLEAR,CLUSTER,CLUSTERED,CODEGEN,COLLATE,COLLATION,COLLECTION,COLUMN,COLUMNS,COMMENT,COMMIT,COMPACT,COMPACTIONS,COMPENSATION,COMPUTE,CONCATENATE,CONDITION,CONSTRAINT,CONTAINS,CONTINUE,C
[...]
+ assert(infoValue.getStringValue ==
"ADD,AFTER,AGGREGATE,ALL,ALTER,ALWAYS,ANALYZE,AND,ANTI,ANY,ANY_VALUE,ARCHIVE,ARRAY,AS,ASC,AT,ATOMIC,AUTHORIZATION,BEGIN,BETWEEN,BIGINT,BINARY,BINDING,BOOLEAN,BOTH,BUCKET,BUCKETS,BY,BYTE,CACHE,CALL,CALLED,CASCADE,CASE,CAST,CATALOG,CATALOGS,CHANGE,CHAR,CHARACTER,CHECK,CLEAR,CLUSTER,CLUSTERED,CODEGEN,COLLATE,COLLATION,COLLECTION,COLUMN,COLUMNS,COMMENT,COMMIT,COMPACT,COMPACTIONS,COMPENSATION,COMPUTE,CONCATENATE,CONDITION,CONSTRAINT,CONTAINS,CONTINUE,C
[...]
// scalastyle:on line.size.limit
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
