-
Notifications
You must be signed in to change notification settings - Fork 28.9k
[SQL] Miscellaneous SQL/DF expression changes. #6754
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -110,7 +110,20 @@ class DataFrameFunctionsSuite extends QueryTest { | |
| testData2.collect().toSeq.map(r => Row(~r.getInt(0)))) | ||
| } | ||
|
|
||
| test("length") { | ||
| test("if function") { | ||
|
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. how about put the |
||
| val df = Seq((1, 2)).toDF("a", "b") | ||
| checkAnswer( | ||
| df.selectExpr("if(a = 1, 'one', 'not_one')", "if(b = 1, 'one', 'not_one')"), | ||
| Row("one", "not_one")) | ||
| } | ||
|
|
||
| test("nvl function") { | ||
| checkAnswer( | ||
| ctx.sql("SELECT nvl(null, 'x'), nvl('y', 'x'), nvl(null, null)"), | ||
| Row("x", "y", null)) | ||
| } | ||
|
|
||
| test("string length function") { | ||
| checkAnswer( | ||
| nullStrings.select(strlen($"s"), strlen("s")), | ||
| nullStrings.collect().toSeq.map { r => | ||
|
|
@@ -127,18 +140,4 @@ class DataFrameFunctionsSuite extends QueryTest { | |
| Row(l) | ||
| }) | ||
| } | ||
|
|
||
| test("log2 functions test") { | ||
| val df = Seq((1, 2)).toDF("a", "b") | ||
| checkAnswer( | ||
| df.select(log2("b") + log2("a")), | ||
| Row(1)) | ||
|
|
||
| checkAnswer( | ||
| ctx.sql("SELECT LOG2(8)"), | ||
| Row(3)) | ||
| checkAnswer( | ||
| ctx.sql("SELECT LOG2(null)"), | ||
| Row(null)) | ||
| } | ||
| } | ||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -18,6 +18,7 @@ | |
| package org.apache.spark.sql | ||
|
|
||
| import org.apache.spark.sql.functions._ | ||
| import org.apache.spark.sql.functions.{log => logarithm} | ||
|
|
||
|
|
||
| private object MathExpressionsTestData { | ||
|
|
@@ -151,20 +152,31 @@ class MathExpressionsSuite extends QueryTest { | |
| testOneToOneMathFunction(tanh, math.tanh) | ||
| } | ||
|
|
||
| test("toDeg") { | ||
| test("toDegrees") { | ||
| testOneToOneMathFunction(toDegrees, math.toDegrees) | ||
| checkAnswer( | ||
| ctx.sql("SELECT degrees(0), degrees(1), degrees(1.5)"), | ||
| Seq((1, 2)).toDF().select(toDegrees(lit(0)), toDegrees(lit(1)), toDegrees(lit(1.5))) | ||
|
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Should these tests not be using the same code path to generate the correct answer?
Contributor
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. This was mainly testing function registry. The above one (testOneToOneMathFunction) tests correctness |
||
| ) | ||
| } | ||
|
|
||
| test("toRad") { | ||
| test("toRadians") { | ||
| testOneToOneMathFunction(toRadians, math.toRadians) | ||
| checkAnswer( | ||
| ctx.sql("SELECT radians(0), radians(1), radians(1.5)"), | ||
| Seq((1, 2)).toDF().select(toRadians(lit(0)), toRadians(lit(1)), toRadians(lit(1.5))) | ||
| ) | ||
| } | ||
|
|
||
| test("cbrt") { | ||
| testOneToOneMathFunction(cbrt, math.cbrt) | ||
| } | ||
|
|
||
| test("ceil") { | ||
| test("ceil and ceiling") { | ||
| testOneToOneMathFunction(ceil, math.ceil) | ||
| checkAnswer( | ||
| ctx.sql("SELECT ceiling(0), ceiling(1), ceiling(1.5)"), | ||
| Row(0.0, 1.0, 2.0)) | ||
| } | ||
|
|
||
| test("floor") { | ||
|
|
@@ -183,12 +195,21 @@ class MathExpressionsSuite extends QueryTest { | |
| testOneToOneMathFunction(expm1, math.expm1) | ||
| } | ||
|
|
||
| test("signum") { | ||
| test("signum / sign") { | ||
| testOneToOneMathFunction[Double](signum, math.signum) | ||
|
|
||
| checkAnswer( | ||
| ctx.sql("SELECT sign(10), signum(-11)"), | ||
| Row(1, -1)) | ||
| } | ||
|
|
||
| test("pow") { | ||
| test("pow / power") { | ||
| testTwoToOneMathFunction(pow, pow, math.pow) | ||
|
|
||
| checkAnswer( | ||
| ctx.sql("SELECT pow(1, 2), power(2, 1)"), | ||
| Seq((1, 2)).toDF().select(pow(lit(1), lit(2)), pow(lit(2), lit(1))) | ||
| ) | ||
| } | ||
|
|
||
| test("hypot") { | ||
|
|
@@ -199,8 +220,12 @@ class MathExpressionsSuite extends QueryTest { | |
| testTwoToOneMathFunction(atan2, atan2, math.atan2) | ||
| } | ||
|
|
||
| test("log") { | ||
| test("log / ln") { | ||
| testOneToOneNonNegativeMathFunction(org.apache.spark.sql.functions.log, math.log) | ||
| checkAnswer( | ||
| ctx.sql("SELECT ln(0), ln(1), ln(1.5)"), | ||
| Seq((1, 2)).toDF().select(logarithm(lit(0)), logarithm(lit(1)), logarithm(lit(1.5))) | ||
| ) | ||
| } | ||
|
|
||
| test("log10") { | ||
|
|
@@ -211,4 +236,18 @@ class MathExpressionsSuite extends QueryTest { | |
| testOneToOneNonNegativeMathFunction(log1p, math.log1p) | ||
| } | ||
|
|
||
| test("log2") { | ||
| val df = Seq((1, 2)).toDF("a", "b") | ||
|
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I agree that we need to add tests here since they are math expressions, but I think we'd better keep tests in this suite consistent. These tests added here are in the style of DataFrameFunctionsSuite.
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think this change is a great idea, as it's more straightforward when reading the code, otherwise we probably need to jump back and forth.
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Sort of...
Contributor
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think it makes sense to put all math stuff in here, all string stuff into its own suite, etc basically if we group expressions into files; we should also group test suites in the same way.
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. That makes sense. |
||
| checkAnswer( | ||
| df.select(log2("b") + log2("a")), | ||
| Row(1)) | ||
|
|
||
| checkAnswer(ctx.sql("SELECT LOG2(8), LOG2(null)"), Row(3, null)) | ||
| } | ||
|
|
||
| test("negative") { | ||
| checkAnswer( | ||
| ctx.sql("SELECT negative(1), negative(0), negative(-1)"), | ||
| Row(-1, 0, 1)) | ||
| } | ||
| } | ||
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.
Why this special case? Also, I'd just use
Ifinstead of makeCopy here and above. Make copy is nice when you are matching on different but structurally similar expression, but looses compile time checks for arguments.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.
"if(null, true, false)" gets a nulltype.
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.
what about
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.
+1