diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala index c8782df146df6c93466d870de9a8aa528c687f8e..45d5d05d9f3f38a96c0352ba8eb0f2a37b317b6c 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala @@ -2193,6 +2193,16 @@ object functions { RegExpReplace(e.expr, lit(pattern).expr, lit(replacement).expr) } + /** + * Replace all substrings of the specified string value that match regexp with rep. + * + * @group string_funcs + * @since 2.1.0 + */ + def regexp_replace(e: Column, pattern: Column, replacement: Column): Column = withExpr { + RegExpReplace(e.expr, pattern.expr, replacement.expr) + } + /** * Decodes a BASE64 encoded string column and returns it as a binary column. * This is the reverse of base64. diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala index dff4226051494ed9678cd6b2ea1b3ef18b7a8b9f..3edd9884961bc29528c416f43f07bd4b21b0906f 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala @@ -77,8 +77,10 @@ class StringFunctionsSuite extends QueryTest with SharedSQLContext { checkAnswer( df.select( regexp_replace($"a", "(\\d+)", "num"), + regexp_replace($"a", $"b", $"c"), regexp_extract($"a", "(\\d+)-(\\d+)", 1)), - Row("num-num", "100") :: Row("num-num", "100") :: Row("num-num", "100") :: Nil) + Row("num-num", "300", "100") :: Row("num-num", "400", "100") :: + Row("num-num", "400-400", "100") :: Nil) // for testing the mutable state of the expression in code gen. // This is a hack way to enable the codegen, thus the codegen is enable by default,