[SPARK-21646][SQL] Add new type coercion to compatible with Hive #18853
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -20,7 +20,7 @@ package org.apache.spark.sql | |
| import java.io.File | ||
| import java.math.MathContext | ||
| import java.net.{MalformedURLException, URL} | ||
| import java.sql.{Date, Timestamp} | ||
| import java.util.concurrent.atomic.AtomicBoolean | ||
|
|
||
| import org.apache.spark.{AccumulatorSuite, SparkException} | ||
|
|
@@ -2677,4 +2677,142 @@ class SQLQuerySuite extends QueryTest with SharedSQLContext { | |
| checkAnswer(df, Row(1, 1, 1)) | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-21646: CommonTypeForBinaryComparison: StringType vs NumericType") { | ||
| withTempView("v") { | ||
| val str1 = Long.MaxValue.toString + "1" | ||
| val str2 = Int.MaxValue.toString + "1" | ||
| val str3 = "10" | ||
| Seq(str1, str2, str3).toDF("c1").createOrReplaceTempView("v") | ||
| withSQLConf(SQLConf.typeCoercionMode.key -> "hive") { | ||
| checkAnswer(sql("SELECT c1 from v where c1 > 0"), | ||
| Row(str1) :: Row(str2) :: Row(str3) :: Nil) | ||
| checkAnswer(sql("SELECT c1 from v where c1 > 0L"), | ||
| Row(str1) :: Row(str2) :: Row(str3) :: Nil) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.typeCoercionMode.key -> "default") { | ||
| checkAnswer(sql("SELECT c1 from v where c1 > 0"), Row(str3) :: Nil) | ||
| checkAnswer(sql("SELECT c1 from v where c1 > 0L"), Row(str2) :: Row(str3) :: Nil) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-21646: CommonTypeForBinaryComparison: DoubleType vs IntegerType") { | ||
| withTempView("v") { | ||
| Seq(("0", 1), ("-0.4", 2), ("0.6", 3)).toDF("c1", "c2").createOrReplaceTempView("v") | ||
| withSQLConf(SQLConf.typeCoercionMode.key -> "hive") { | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = 0"), Seq(Row("0"))) | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = 0L"), Seq(Row("0"))) | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = 0.0"), Seq(Row("0"))) | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = -0.4"), Seq(Row("-0.4"))) | ||
| checkAnswer(sql("SELECT count(*) FROM v WHERE c1 > 0"), Row(1) :: Nil) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.typeCoercionMode.key -> "default") { | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = 0"), Seq(Row("0"), Row("-0.4"), Row("0.6"))) | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = 0L"), Seq(Row("0"), Row("-0.4"), Row("0.6"))) | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = 0.0"), Seq(Row("0"))) | ||
| checkAnswer(sql("SELECT c1 FROM v WHERE c1 = -0.4"), Seq(Row("-0.4"))) | ||
| checkAnswer(sql("SELECT count(*) FROM v WHERE c1 > 0"), Row(0) :: Nil) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-21646: CommonTypeForBinaryComparison: StringType vs DateType") { | ||
| withTempView("v") { | ||
| val v1 = Date.valueOf("2017-09-22") | ||
| val v2 = Date.valueOf("2017-09-09") | ||
| Seq(v1, v2).toDF("c1").createTempView("v") | ||
| withSQLConf(SQLConf.typeCoercionMode.key -> "hive") { | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Row(v1) :: Row(v2) :: Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as date)"), | ||
| Row(v1) :: Row(v2) :: Nil) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.typeCoercionMode.key -> "default") { | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as date)"), | ||
| Row(v1) :: Row(v2) :: Nil) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-21646: CommonTypeForBinaryComparison: StringType vs TimestampType") { | ||
| withTempView("v") { | ||
| val v1 = Timestamp.valueOf("2017-07-21 23:42:12.123") | ||
| val v2 = Timestamp.valueOf("2017-08-21 23:42:12.123") | ||
| Seq(v1, v2).toDF("c1").createTempView("v") | ||
| withSQLConf(SQLConf.typeCoercionMode.key -> "hive") { | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Row(v2) :: Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as timestamp)"), | ||
| Row(v2) :: Nil) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.typeCoercionMode.key -> "default") { | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as timestamp)"), | ||
| Row(v2) :: Nil) | ||
|
||
| } | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-21646: CommonTypeForBinaryComparison: TimestampType vs DateType") { | ||
| withTempView("v") { | ||
| val v1 = Timestamp.valueOf("2017-07-21 23:42:12.123") | ||
| val v2 = Timestamp.valueOf("2017-08-21 23:42:12.123") | ||
| Seq(v1, v2).toDF("c1").createTempView("v") | ||
| withSQLConf(SQLConf.typeCoercionMode.key -> "Hive") { | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as date)"), Row(v2) :: Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as timestamp)"), | ||
| Row(v2) :: Nil) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.typeCoercionMode.key -> "Default") { | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as date)"), Row(v2) :: Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > cast('2017-8-1' as timestamp)"), | ||
| Row(v2) :: Nil) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-21646: CommonTypeForBinaryComparison: TimestampType vs NumericType") { | ||
| withTempView("v") { | ||
| val v1 = Timestamp.valueOf("2017-07-21 23:42:12.123") | ||
| val v2 = Timestamp.valueOf("2017-08-21 23:42:12.123") | ||
| Seq(v1, v2).toDF("c1").createTempView("v") | ||
| withSQLConf(SQLConf.typeCoercionMode.key -> "hive") { | ||
| checkAnswer(sql("select c1 from v where c1 > 1"), Row(v1) :: Row(v2) :: Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Row(v2) :: Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-08-01'"), Row(v2) :: Nil) | ||
| checkAnswer( | ||
| sql("select * from v where c1 > cast(cast('2017-08-01' as timestamp) as double)"), | ||
| Row(v2) :: Nil) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.typeCoercionMode.key -> "default") { | ||
| val e1 = intercept[AnalysisException] { | ||
| sql("select * from v where c1 > 1") | ||
| } | ||
| assert(e1.getMessage.contains("data type mismatch")) | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-08-01'"), Row(v2) :: Nil) | ||
| val e2 = intercept[AnalysisException] { | ||
| sql("select * from v where c1 > cast(cast('2017-08-01' as timestamp) as double)") | ||
| } | ||
| assert(e2.getMessage.contains("data type mismatch")) | ||
| } | ||
|
|
||
| val e1 = intercept[AnalysisException] { | ||
| sql("select * from v where c1 > 1") | ||
| } | ||
| assert(e1.getMessage.contains("data type mismatch")) | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-8-1'"), Nil) | ||
| checkAnswer(sql("select c1 from v where c1 > '2017-08-01'"), Row(v2) :: Nil) | ||
| val e2 = intercept[AnalysisException] { | ||
| sql("select * from v where c1 > cast(cast('2017-08-01' as timestamp) as double)") | ||
| } | ||
| assert(e2.getMessage.contains("data type mismatch")) | ||
| } | ||
| } | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This description feels inadequate to me. I think most users will think "hive" means "old, legacy way of doing things and "default" means "new, better, spark way of doing things". But I haven't heard an argument in favor of the "default" behavior, just that we don't want to have a breaking change of behavior.
So (a) I'd advocate that we rename "default" to "legacy", or something else along those lines. I do think it should be the default value, to avoid changing behavior.
and (b) I think the doc section here should more clearly indicate the difference, eg. "The 'legacy' typeCoercion mode was used in spark prior to 2.3, and so it continues to be the default to avoid breaking behavior. However, it has logical inconsistencies. The 'hive' mode is preferred for most new applications, though it may require additional manual casting.
I am even wondering if we should have a 3rd option, to not implicit cast across type categories, eg. like postgres, as this avoids nasty surprises for the user. While the casts are convenient, when it doesn't work there is very little indication to the user that anything went wrong -- most likely they'll just keep continue processing data though the results don't actually have the semantics they want.