Skip to content

[SPARK-34244][SQL] Remove the Scala function version of regexp_extract_all #31346

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.

Sign up for GitHub

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

Closed
beliefer wants to merge 1 commit into from
Closed

[SPARK-34244][SQL] Remove the Scala function version of regexp_extract_all #31346

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 0 additions & 13 deletions sql/core/src/main/scala/org/apache/spark/sql/functions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2637,19 +2637,6 @@ object functions {
RegExpExtract(e.expr, lit(exp).expr, lit(groupIdx).expr)
}

/**
* Extract all specific groups matched by a Java regex, from the specified string column.
* If the regex did not match, or the specified group did not match, return an empty array.
* if the specified group index exceeds the group count of regex, an IllegalArgumentException
* will be thrown.
*
* @group string_funcs
* @since 3.1.0
*/
def regexp_extract_all(e: Column, exp: String, groupIdx: Int): Column = withExpr {
RegExpExtractAll(e.expr, lit(exp).expr, lit(groupIdx).expr)
}

/**
* Replace all substrings of the specified string value that match regexp with rep.
*
Expand Down
26 changes: 0 additions & 26 deletions sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,25 +154,9 @@ class StringFunctionsSuite extends QueryTest with SharedSparkSession {
Row("300", "100") :: Row("400", "100") :: Row("400-400", "100") :: Nil)
}

test("string regex_extract_all") {
val df = Seq(
("100-200,300-400", "(\\d+)-(\\d+)"),
("101-201,301-401", "(\\d+)-(\\d+)"),
("102-202,302-402", "(\\d+)")).toDF("a", "b")

checkAnswer(
df.select(
regexp_extract_all($"a", "(\\d+)-(\\d+)", 1),
regexp_extract_all($"a", "(\\d+)-(\\d+)", 2)),
Row(Seq("100", "300"), Seq("200", "400")) ::
Row(Seq("101", "301"), Seq("201", "401")) ::
Row(Seq("102", "302"), Seq("202", "402")) :: Nil)
}

test("non-matching optional group") {
val df = Seq(Tuple1("aaaac")).toDF("s")

// regexp_extract
checkAnswer(
df.select(regexp_extract($"s", "(foo)", 1)),
Row("")
Expand All @@ -181,16 +165,6 @@ class StringFunctionsSuite extends QueryTest with SharedSparkSession {
df.select(regexp_extract($"s", "(a+)(b)?(c)", 2)),
Row("")
)

// regexp_extract_all
checkAnswer(
df.select(regexp_extract_all($"s", "(foo)", 1)),
Row(Seq())
)
checkAnswer(
df.select(regexp_extract_all($"s", "(a+)(b)?(c)", 2)),
Row(Seq(""))
)
}

test("string ascii function") {
Expand Down