From e4696552a7213e0a7dca3898769681c19515fac8 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Mon, 5 Aug 2024 16:15:29 -0400
Subject: [PATCH 01/11] Added
 regexp_extract,signum,substring_index,collect_list

1) Added regexp_extract,signum,substring_index,collect_list to functions.scala .
2) Added test cases for the same
---
 .../com/snowflake/snowpark/functions.scala    | 106 ++++++++++++++++++
 .../snowpark_test/FunctionSuite.scala         |  38 +++++++
 2 files changed, 144 insertions(+)

diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index a7fd9ff0..cc3ca323 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3140,6 +3140,112 @@ object functions {
    */
   def listagg(col: Column): Column = listagg(col, "", isDistinct = false)
 
+  /**
+   * This function receives a column and extracts the groupIdx from the string
+   * after applying the exp regex. Returns empty string when the string doesn't
+   *  match and null if the input is null.
+   *
+   * This function applies the `case sensitive` and `extract` flags.
+   * It doesn't apply multiline nor .* matches newlines.
+   * If these flags need to be applied, use `builtin("REGEXP_SUBSTR")`
+   * instead and apply the desired flags.
+   *
+   * Note: non-greedy tokens such as `.*?` are not supported
+   * @since 1.12.1
+   * @param colName Column to apply regex.
+   * @param exp Regex expression to apply.
+   * @param grpIdx Group to extract.
+   * @return Column object.
+   */
+  def regexp_extract(
+      colName: Column,
+      exp: String,
+      position: Int,
+      Occurences: Int,
+      grpIdx: Int): Column = {
+    when(colName.is_null, lit(null))
+      .otherwise(
+        coalesce(
+          builtin("REGEXP_SUBSTR")(
+            colName,
+            lit(exp),
+            lit(position),
+            lit(Occurences),
+            lit("ce"),
+            lit(grpIdx)),
+          lit("")))
+  }
+
+  /**
+   * Returns the sign of the given column. Returns either 1 for positive,
+   * 0 for 0 or
+   * NaN, -1 for negative and null for null.
+   * NOTE: if string values are provided snowflake will attempts to cast.
+   *  If it casts correctly, returns the calculation,
+   *  if not an error will be thrown
+   * @since 1.12.1
+   * @param e Column to calculate the sign.
+   * @return Column object.
+   */
+  def signum(colName: Column): Column = {
+    builtin("SIGN")(colName)
+  }
+
+  /**
+   * Returns the sign of the given column. Returns either 1 for positive,
+   *  0 for 0 or
+   * NaN, -1 for negative and null for null.
+   * NOTE: if string values are provided snowflake will attempts to cast.
+   *  If it casts correctly, returns the calculation,
+   *  if not an error will be thrown
+   * @since 1.12.1
+   * @param columnName Name of the column to calculate the sign.
+   * @return Column object.
+   */
+  def signum(columnName: String): Column = {
+    signum(col(columnName))
+  }
+
+  /**
+   * Returns the substring from string str before count occurrences
+   * of the delimiter delim. If count is positive,
+   * everything the left of the final delimiter (counting from left)
+   *  is returned. If count is negative, every to the right of the
+   * final delimiter (counting from the right) is returned.
+   * substring_index performs a case-sensitive match when searching for delim.
+   *   @since 1.12.1
+   */
+  def substring_index(str: Column, delim: String, count: Int): Column = {
+    when(
+      lit(count) < lit(0),
+      callBuiltin(
+        "substring",
+        lit(str),
+        callBuiltin("regexp_instr", sqlExpr(s"reverse(${str}, ${delim}, 1, abs(${count}), 0"))))
+      .otherwise(
+        callBuiltin(
+          "substring",
+          lit(str),
+          1,
+          callBuiltin("regexp_instr", col("str"), lit(delim), 1, lit(count), 1)))
+  }
+
+  /**
+   * Wrapper for Snowflake built-in collect_list function. Get the values of array column.
+   * @since 1.10.0
+   * @param c Column to be collect.
+   * @return The array.
+   */
+  def collect_list(c: Column): Column = array_agg(c)
+
+  /**
+   * Wrapper for Snowflake built-in collect_list function. Get the values of array column.
+   * @since 1.10.0
+   * @param s Column name to be collected.
+   * @return The array.
+   */
+  def collect_list(s: String): Column = array_agg(col(s))
+
   /**
    * Invokes a built-in snowflake function with the specified name and arguments.
    * Arguments can be of two types
diff --git a/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala b/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
index e473de12..21304cf7 100644
--- a/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
+++ b/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
@@ -2177,7 +2177,45 @@ trait FunctionSuite extends TestData {
       expected,
       sort = false)
   }
+  test("regexp_extract") {
+    val data = Seq("A MAN A PLAN A CANAL").toDF("a")
+    var expected = Seq(Row("MAN"))
+    checkAnswer(
+      data.select(regexp_extract(col("a"), "A\\W+(\\w+)", 1, 1, 1)),
+      expected,
+      sort = false)
+    expected = Seq(Row("PLAN"))
+    checkAnswer(
+      data.select(regexp_extract(col("a"), "A\\W+(\\w+)", 1, 2, 1)),
+      expected,
+      sort = false)
+    expected = Seq(Row("CANAL"))
+    checkAnswer(
+      data.select(regexp_extract(col("a"), "A\\W+(\\w+)", 1, 3, 1)),
+      expected,
+      sort = false)
+
+    expected = Seq(Row(null))
+    checkAnswer(
+      data.select(regexp_extract(col("a"), "A\\W+(\\w+)", 1, 4, 1)),
+      expected,
+      sort = false)
+  }
+  test("signum") {
+    val df = Seq(1, -2, 0).toDF("a")
+    checkAnswer(df.select(signum(col("a"))), Seq(Row(1), Row(-1), Row(0)), sort = false)
+  }
 
+  test("collect_list") {
+    assert(monthlySales.select(collect_list(col("amount"))).collect()(0).get(0).toString ==
+      "[\n  10000,\n  400,\n  4500,\n  35000,\n  5000,\n  3000,\n  200,\n  90500,\n  6000,\n  " +
+        "5000,\n  2500,\n  9500,\n  8000,\n  10000,\n  800,\n  4500\n]")
+
+  }
+  test("substring_index") {
+    val df = Seq("It was the best of times, it was the worst of times").toDF("a")
+    checkAnswer(df.select(substring_index(col("a"), "was", 1)), Seq(Row(7)), sort = false)
+  }
 }
 
 class EagerFunctionSuite extends FunctionSuite with EagerSession

From 72c63b4175415b70a9d50c709e99276a645b2f24 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Tue, 6 Aug 2024 10:15:02 -0400
Subject: [PATCH 02/11] Added examples and updated the description

---
 .../com/snowflake/snowpark/functions.scala    | 66 ++++++++++++++-----
 1 file changed, 48 insertions(+), 18 deletions(-)

diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index cc3ca323..94f9f9d5 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3141,20 +3141,24 @@ object functions {
   def listagg(col: Column): Column = listagg(col, "", isDistinct = false)
 
   /**
-   * This function receives a column and extracts the groupIdx from the string
-   * after applying the exp regex. Returns empty string when the string doesn't
-   *  match and null if the input is null.
-   *
-   * This function applies the `case sensitive` and `extract` flags.
-   * It doesn't apply multiline nor .* matches newlines.
-   * If these flags need to be applied, use `builtin("REGEXP_SUBSTR")`
-   * instead and apply the desired flags.
-   *
+   * Signature - snowflake.snowpark.functions.regexp_extract
+   * (value: Union[Column, str], regexp: Union[Column, str], idx: int)
+   *  → Column
+   * Extract a specific group matched by a regex, from the specified string 
+   * column. If the regex did not match, or the specified group did not match, 
+   * an empty string is returned.
+   * Example:
+   * from snowflake.snowpark.functions import regexp_extract
+   * df = session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]], ["id", "age"])
+   * df.select(regexp_extract("id", r"(\d+)", 1).alias("RES")).show()
+   *        ---------
+   *         |"RES"  |
+   *        ---------
+   *        |20     |
+   *        |40     |
+   *        ---------
    * Note: non-greedy tokens such as `.*?` are not supported
    * @since 1.12.1
-   * @param colName Column to apply regex.
-   * @param exp Regex expression to apply.
-   * @param grpIdx Group to extract.
    * @return Column object.
    */
   def regexp_extract(
@@ -3177,12 +3181,23 @@ object functions {
   }
 
   /**
-   * Returns the sign of the given column. Returns either 1 for positive,
-   * 0 for 0 or
-   * NaN, -1 for negative and null for null.
-   * NOTE: if string values are provided snowflake will attempts to cast.
-   *  If it casts correctly, returns the calculation,
-   *  if not an error will be thrown
+   *    Returns the sign of its argument:
+   *
+   *     - -1 if the argument is negative.
+   *     - 1 if it is positive.
+   *     - 0 if it is 0.
+   *
+   * Args:
+   *     col: The column to evaluate its sign
+   *
+   * Example::
+   *     >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"])
+   *     >>> df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"), sign("c").alias("c_sign")).show()
+   *     ----------------------------------
+   *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
+   *     ----------------------------------
+   *     |-1        |1         |0         |
+   *     ----------------------------------
    * @since 1.12.1
    * @param e Column to calculate the sign.
    * @return Column object.
@@ -3232,6 +3247,21 @@ object functions {
 
   /**
    * Wrapper for Snowflake built-in collect_list function. Get the values of array column.
+   * Returns the input values, pivoted into an ARRAY. If the input is empty, an empty
+   * ARRAY is returned.
+   *
+   * Example::
+   *     >>> df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"])
+   *     >>> df.select(array_agg("a", True).alias("result")).show()
+   *     ------------
+   *     |"RESULT"  |
+   *     ------------
+   *     |[         |
+   *     |  1,      |
+   *     |  2,      |
+   *     |  3       |
+   *     |]         |
+   *     ------------
    * @since 1.10.0
    * @param c Column to be collect.
    * @return The array.

From 1e50ed571869ab3201794b42646bd6b13ef5773a Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Wed, 7 Aug 2024 14:22:29 -0400
Subject: [PATCH 03/11] Fixed format

---
 src/main/scala/com/snowflake/snowpark/functions.scala | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 94f9f9d5..83865414 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3144,8 +3144,8 @@ object functions {
    * Signature - snowflake.snowpark.functions.regexp_extract
    * (value: Union[Column, str], regexp: Union[Column, str], idx: int)
    *  → Column
-   * Extract a specific group matched by a regex, from the specified string 
-   * column. If the regex did not match, or the specified group did not match, 
+   * Extract a specific group matched by a regex, from the specified string
+   * column. If the regex did not match, or the specified group did not match,
    * an empty string is returned.
    * Example:
    * from snowflake.snowpark.functions import regexp_extract
@@ -3192,7 +3192,8 @@ object functions {
    *
    * Example::
    *     >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"])
-   *     >>> df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"), sign("c").alias("c_sign")).show()
+   *     >>> df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
+   * sign("c").alias("c_sign")).show()
    *     ----------------------------------
    *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
    *     ----------------------------------

From 17e50690f05c78fabee61352f11d63650e926779 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Wed, 7 Aug 2024 14:29:39 -0400
Subject: [PATCH 04/11] formatted the comments

---
 .../scala/com/snowflake/snowpark/functions.scala  | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 83865414..4adf4165 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3143,21 +3143,22 @@ object functions {
   /**
    * Signature - snowflake.snowpark.functions.regexp_extract
    * (value: Union[Column, str], regexp: Union[Column, str], idx: int)
-   *  → Column
+   *   Column
    * Extract a specific group matched by a regex, from the specified string
    * column. If the regex did not match, or the specified group did not match,
    * an empty string is returned.
    * Example:
    * from snowflake.snowpark.functions import regexp_extract
-   * df = session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]], ["id", "age"])
+   * df = session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]],
+   *  ["id", "age"])
    * df.select(regexp_extract("id", r"(\d+)", 1).alias("RES")).show()
-   *        ---------
-   *         |"RES"  |
-   *        ---------
+   *
+   *         "RES"  |
+   *
    *        |20     |
    *        |40     |
-   *        ---------
-   * Note: non-greedy tokens such as `.*?` are not supported
+   *
+   * Note: non-greedy tokens such as  are not supported
    * @since 1.12.1
    * @return Column object.
    */

From dc7dd4a7a3afa067e733cb39a52ddd90b383c26e Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Wed, 7 Aug 2024 16:24:13 -0400
Subject: [PATCH 05/11] Added java functions and unit test cases for java

---
 .../snowflake/snowpark_java/Functions.java    | 72 +++++++++++++++++++
 .../com/snowflake/snowpark/functions.scala    | 21 +++++-
 .../snowpark_test/JavaFunctionSuite.java      | 44 ++++++++++++
 3 files changed, 134 insertions(+), 3 deletions(-)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index 56d8d08b..ef3c9718 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3880,6 +3880,78 @@ public static Column listagg(Column col) {
     return new Column(com.snowflake.snowpark.functions.listagg(col.toScalaColumn()));
   }
 
+  /**
+   * Signature - snowflake.snowpark.functions.regexp_extract (value: Union[Column, str], regexp:
+   * Union[Column, str], idx: int) Column Extract a specific group matched by a regex, from the
+   * specified string column. If the regex did not match, or the specified group did not match, an
+   * empty string is returned. Example: from snowflake.snowpark.functions import regexp_extract df =
+   * session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]], ["id", "age"])
+   * df.select(regexp_extract("id", r"(\d+)", 1).alias("RES")).show()
+   *
+   * <p>"RES" |
+   *
+   * <p>|20 | |40 |
+   *
+   * <p>Note: non-greedy tokens such as are not supported
+   *
+   * @since 1.12.1
+   * @return Column object.
+   */
+  public static Column regexp_extract(
+      Column col, String exp, Integer position, Integer Occurences, Integer grpIdx) {
+    return new Column(
+        com.snowflake.snowpark.functions.regexp_extract(
+            col.toScalaColumn(), exp, position, Occurences, grpIdx));
+  }
+
+  /**
+   * Returns the sign of its argument:
+   *
+   * <p>- -1 if the argument is negative. - 1 if it is positive. - 0 if it is 0.
+   *
+   * <p>Args: col: The column to evaluate its sign
+   *
+   * <p>Example:: >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
+   * df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
+   * sign("c").alias("c_sign")).show() ---------------------------------- |"A_SIGN" |"B_SIGN"
+   * |"C_SIGN" | ---------------------------------- |-1 |1 |0 | ----------------------------------
+   *
+   * @since 1.12.1
+   * @param e Column to calculate the sign.
+   * @return Column object.
+   */
+  public static Column signum(Column col) {
+    return new Column(com.snowflake.snowpark.functions.signum(col.toScalaColumn()));
+  }
+
+  /**
+   * Returns the substring from string str before count occurrences of the delimiter delim. If count
+   * is positive, everything the left of the final delimiter (counting from left) is returned. If
+   * count is negative, every to the right of the final delimiter (counting from the right) is
+   * returned. substring_index performs a case-sensitive match when searching for delim.
+   *
+   * @since 1.12.1
+   */
+  public static Column substring_index(Column col, String delim, Integer count) {
+    return new Column(
+        com.snowflake.snowpark.functions.substring_index(col.toScalaColumn(), delim, count));
+  }
+
+  /**
+   * Wrapper for Snowflake built-in collect_list function. Get the values of array column. Returns
+   * the input values, pivoted into an ARRAY. If the input is empty, an empty ARRAY is returned.
+   *
+   * <p>Example:: >>> df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"]) >>>
+   * df.select(array_agg("a", True).alias("result")).show() ------------ |"RESULT" | ------------ |[
+   * | | 1, | | 2, | | 3 | |] | ------------
+   *
+   * @since 1.10.0
+   * @param c Column to be collect.
+   * @return The array.
+   */
+  public static Column collect_list(Column col) {
+    return new Column(com.snowflake.snowpark.functions.collect_list(col.toScalaColumn()));
+  }
   /**
    * Calls a user-defined function (UDF) by name.
    *
diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 4adf4165..65ed38cf 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3171,7 +3171,7 @@ object functions {
     when(colName.is_null, lit(null))
       .otherwise(
         coalesce(
-          builtin("REGEXP_SUBSTR")(
+          builtin("REGEX_SUBSTR")(
             colName,
             lit(exp),
             lit(position),
@@ -3248,7 +3248,7 @@ object functions {
   }
 
   /**
-   * Wrapper for Snowflake built-in collect_list function. Get the values of array column.
+   *
    * Returns the input values, pivoted into an ARRAY. If the input is empty, an empty
    * ARRAY is returned.
    *
@@ -3271,7 +3271,22 @@ object functions {
   def collect_list(c: Column): Column = array_agg(c)
 
   /**
-   * Wrapper for Snowflake built-in collect_list function. Get the values of array column.
+   *
+   * Returns the input values, pivoted into an ARRAY. If the input is empty, an empty
+   * ARRAY is returned.
+   *
+   * Example::
+   *     >>> df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"])
+   *     >>> df.select(array_agg("a", True).alias("result")).show()
+   *     ------------
+   *     |"RESULT"  |
+   *     ------------
+   *     |[         |
+   *     |  1,      |
+   *     |  2,      |
+   *     |  3       |
+   *     |]         |
+   *     ------------
    * @since 1.10.0
    * @param s Column name to be collected.
    * @return The array.
diff --git a/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java b/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
index 6ee298d3..0fafaf0c 100644
--- a/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
+++ b/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
@@ -2764,4 +2764,48 @@ public void any_value() {
     assert result.length == 1;
     assert result[0].getInt(0) == 1 || result[0].getInt(0) == 2 || result[0].getInt(0) == 3;
   }
+
+  @Test
+  public void regexp_extract() {
+    DataFrame df = getSession().sql("select * from values('A MAN A PLAN A CANAL') as T(a)");
+    Row[] expected = {Row.create("MAN")};
+    checkAnswer(
+        df.select(Functions.regexp_extract(df.col("a"), "A\\W+(\\w+)", 1, 1, 1)), expected, false);
+    Row[] expected2 = {Row.create("PLAN")};
+    checkAnswer(
+        df.select(Functions.regexp_extract(df.col("a"), "A\\W+(\\w+)", 1, 2, 1)), expected2, false);
+    Row[] expected3 = {Row.create("CANAL")};
+    checkAnswer(
+        df.select(Functions.regexp_extract(df.col("a"), "A\\W+(\\w+)", 1, 2, 1)), expected3, false);
+    Row[] expected4 = {Row.create(null)};
+    checkAnswer(
+        df.select(Functions.regexp_extract(df.col("a"), "A\\W+(\\w+)", 1, 3, 1)), expected4, false);
+  }
+
+  @Test
+  public void signum() {
+    DataFrame df = getSession().sql("select * from values(1,-2,0) as T(a)");
+    checkAnswer(df.select(Functions.signum(df.col("a"))), new Row[] {Row.create(1, -1, 0)}, false);
+  }
+
+  @Test
+  public void collect_list() {
+    DataFrame df = getSession().sql("select * from values(10000,400,450) as T(a)");
+    checkAnswer(
+        df.select(Functions.collect_list(df.col("a"))),
+        new Row[] {Row.create("[\n  \"10000,400,450\"\n]")},
+        false);
+  }
+
+  @Test
+  public void substring_index() {
+    DataFrame df =
+        getSession()
+            .sql(
+                "select * from values ('It was the best of times,it was the worst of times') as T(a)");
+    checkAnswer(
+        df.select(Functions.substring_index(df.col("a"), "was", 1)),
+        new Row[] {Row.create(7)},
+        false);
+  }
 }

From 34da52d4ce0c22f3a54cb68a44ddde59b6d3ac23 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Wed, 7 Aug 2024 16:29:21 -0400
Subject: [PATCH 06/11] Added sign function

---
 .../snowflake/snowpark_java/Functions.java    | 20 ++++++++++++++
 .../com/snowflake/snowpark/functions.scala    | 27 +++++++++++++++++++
 .../snowpark_test/JavaFunctionSuite.java      |  6 +++++
 .../snowpark_test/FunctionSuite.scala         |  4 +++
 4 files changed, 57 insertions(+)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index ef3c9718..f7d199d5 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3924,6 +3924,26 @@ public static Column signum(Column col) {
     return new Column(com.snowflake.snowpark.functions.signum(col.toScalaColumn()));
   }
 
+  /**
+   * Returns the sign of its argument:
+   *
+   * <p>- -1 if the argument is negative. - 1 if it is positive. - 0 if it is 0.
+   *
+   * <p>Args: col: The column to evaluate its sign
+   *
+   * <p>Example:: >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
+   * df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
+   * sign("c").alias("c_sign")).show() ---------------------------------- |"A_SIGN" |"B_SIGN"
+   * |"C_SIGN" | ---------------------------------- |-1 |1 |0 | ----------------------------------
+   *
+   * @since 1.12.1
+   * @param e Column to calculate the sign.
+   * @return Column object.
+   */
+  public static Column sign(Column col) {
+    return new Column(com.snowflake.snowpark.functions.sign(col.toScalaColumn()));
+  }
+
   /**
    * Returns the substring from string str before count occurrences of the delimiter delim. If count
    * is positive, everything the left of the final delimiter (counting from left) is returned. If
diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 65ed38cf..43c26cf1 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3181,6 +3181,33 @@ object functions {
           lit("")))
   }
 
+  /**
+   *    Returns the sign of its argument:
+   *
+   *     - -1 if the argument is negative.
+   *     - 1 if it is positive.
+   *     - 0 if it is 0.
+   *
+   * Args:
+   *     col: The column to evaluate its sign
+   *
+   * Example::
+   *     >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"])
+   *     >>> df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
+   * sign("c").alias("c_sign")).show()
+   *     ----------------------------------
+   *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
+   *     ----------------------------------
+   *     |-1        |1         |0         |
+   *     ----------------------------------
+   * @since 1.12.1
+   * @param e Column to calculate the sign.
+   * @return Column object.
+   */
+  def sign(colName: Column): Column = {
+    builtin("SIGN")(colName)
+  }
+
   /**
    *    Returns the sign of its argument:
    *
diff --git a/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java b/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
index 0fafaf0c..e4e2a34d 100644
--- a/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
+++ b/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
@@ -2788,6 +2788,12 @@ public void signum() {
     checkAnswer(df.select(Functions.signum(df.col("a"))), new Row[] {Row.create(1, -1, 0)}, false);
   }
 
+  @Test
+  public void sign() {
+    DataFrame df = getSession().sql("select * from values(1,-2,0) as T(a)");
+    checkAnswer(df.select(Functions.sign(df.col("a"))), new Row[] {Row.create(1, -1, 0)}, false);
+  }
+
   @Test
   public void collect_list() {
     DataFrame df = getSession().sql("select * from values(10000,400,450) as T(a)");
diff --git a/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala b/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
index 21304cf7..ea28cc5b 100644
--- a/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
+++ b/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
@@ -2205,6 +2205,10 @@ trait FunctionSuite extends TestData {
     val df = Seq(1, -2, 0).toDF("a")
     checkAnswer(df.select(signum(col("a"))), Seq(Row(1), Row(-1), Row(0)), sort = false)
   }
+  test("sign") {
+    val df = Seq(1, -2, 0).toDF("a")
+    checkAnswer(df.select(sign(col("a"))), Seq(Row(1), Row(-1), Row(0)), sort = false)
+  }
 
   test("collect_list") {
     assert(monthlySales.select(collect_list(col("amount"))).collect()(0).get(0).toString ==

From 330f36077ab815e856006a2bd4894580bb505fad Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Thu, 8 Aug 2024 12:53:03 -0400
Subject: [PATCH 07/11] Modified the alignment

---
 .../snowflake/snowpark_java/Functions.java    | 66 ++++++++++++-------
 .../com/snowflake/snowpark/functions.scala    | 26 +++++---
 2 files changed, 58 insertions(+), 34 deletions(-)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index f7d199d5..ae5363e5 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3884,15 +3884,19 @@ public static Column listagg(Column col) {
    * Signature - snowflake.snowpark.functions.regexp_extract (value: Union[Column, str], regexp:
    * Union[Column, str], idx: int) Column Extract a specific group matched by a regex, from the
    * specified string column. If the regex did not match, or the specified group did not match, an
-   * empty string is returned. Example: from snowflake.snowpark.functions import regexp_extract df =
-   * session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]], ["id", "age"])
+   * empty string is returned. 
+   * Example: 
+   *  <pre>{@code 
+   * from snowflake.snowpark.functions import regexp_extract
+   * df = session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]], ["id", "age"])
    * df.select(regexp_extract("id", r"(\d+)", 1).alias("RES")).show()
-   *
-   * <p>"RES" |
-   *
-   * <p>|20 | |40 |
-   *
-   * <p>Note: non-greedy tokens such as are not supported
+   *    ---------
+   *     |"RES"  |
+   *     ---------
+   *     |20     |
+   *     |40     |
+   *     ---------
+   * }</pr>
    *
    * @since 1.12.1
    * @return Column object.
@@ -3909,12 +3913,18 @@ public static Column regexp_extract(
    *
    * <p>- -1 if the argument is negative. - 1 if it is positive. - 0 if it is 0.
    *
-   * <p>Args: col: The column to evaluate its sign
-   *
-   * <p>Example:: >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
+   * <p>Args: col: The column to evaluate its sign 
+   *  Example:: 
+   * * <pre>{@code df =
+   * session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
    * df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
-   * sign("c").alias("c_sign")).show() ---------------------------------- |"A_SIGN" |"B_SIGN"
-   * |"C_SIGN" | ---------------------------------- |-1 |1 |0 | ----------------------------------
+   * sign("c").alias("c_sign")).show() 
+   *   ----------------------------------
+   *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
+   *     ----------------------------------
+   *     |-1        |1         |0         |
+   *     ----------------------------------
+   * }</pr>
    *
    * @since 1.12.1
    * @param e Column to calculate the sign.
@@ -3929,12 +3939,18 @@ public static Column signum(Column col) {
    *
    * <p>- -1 if the argument is negative. - 1 if it is positive. - 0 if it is 0.
    *
-   * <p>Args: col: The column to evaluate its sign
-   *
-   * <p>Example:: >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
+   * <p>Args: col: The column to evaluate its sign  
+   * Example:: 
+   * <pre>{@code df =
+   * session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
    * df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
-   * sign("c").alias("c_sign")).show() ---------------------------------- |"A_SIGN" |"B_SIGN"
-   * |"C_SIGN" | ---------------------------------- |-1 |1 |0 | ----------------------------------
+   * sign("c").alias("c_sign")).show() 
+   *   ----------------------------------
+   *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
+   *     ----------------------------------
+   *     |-1        |1         |0         |
+   *     ----------------------------------
+   * }</pr>
    *
    * @since 1.12.1
    * @param e Column to calculate the sign.
@@ -3958,12 +3974,14 @@ public static Column substring_index(Column col, String delim, Integer count) {
   }
 
   /**
-   * Wrapper for Snowflake built-in collect_list function. Get the values of array column. Returns
-   * the input values, pivoted into an ARRAY. If the input is empty, an empty ARRAY is returned.
-   *
-   * <p>Example:: >>> df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"]) >>>
-   * df.select(array_agg("a", True).alias("result")).show() ------------ |"RESULT" | ------------ |[
-   * | | 1, | | 2, | | 3 | |] | ------------
+   * Returns the input values, pivoted into an ARRAY. If the input is empty, an empty ARRAY is
+   * returned. 
+   * <p> Example:: 
+   *  <pre>{@code
+   * df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"])
+   * df.select(array_agg("a", True).alias("result")).show() 
+   * "RESULT" [ 1, 2, 3 ] 
+   * }</pre>
    *
    * @since 1.10.0
    * @param c Column to be collect.
diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 43c26cf1..995931a2 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3147,17 +3147,20 @@ object functions {
    * Extract a specific group matched by a regex, from the specified string
    * column. If the regex did not match, or the specified group did not match,
    * an empty string is returned.
-   * Example:
+   * <pr>Example:
    * from snowflake.snowpark.functions import regexp_extract
    * df = session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]],
    *  ["id", "age"])
    * df.select(regexp_extract("id", r"(\d+)", 1).alias("RES")).show()
-   *
-   *         "RES"  |
-   *
-   *        |20     |
-   *        |40     |
-   *
+   *</pr>
+   *<pr>
+   *     ---------
+   *     |"RES"  |
+   *     ---------
+   *     |20     |
+   *     |40     |
+   *     ---------
+   *</pr>
    * Note: non-greedy tokens such as  are not supported
    * @since 1.12.1
    * @return Column object.
@@ -3190,7 +3193,7 @@ object functions {
    *
    * Args:
    *     col: The column to evaluate its sign
-   *
+   *<pr>
    * Example::
    *     >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"])
    *     >>> df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
@@ -3200,6 +3203,7 @@ object functions {
    *     ----------------------------------
    *     |-1        |1         |0         |
    *     ----------------------------------
+   * </pr>
    * @since 1.12.1
    * @param e Column to calculate the sign.
    * @return Column object.
@@ -3217,7 +3221,7 @@ object functions {
    *
    * Args:
    *     col: The column to evaluate its sign
-   *
+   *<pr>
    * Example::
    *     >>> df = session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"])
    *     >>> df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
@@ -3227,6 +3231,7 @@ object functions {
    *     ----------------------------------
    *     |-1        |1         |0         |
    *     ----------------------------------
+   * </pr>
    * @since 1.12.1
    * @param e Column to calculate the sign.
    * @return Column object.
@@ -3278,7 +3283,7 @@ object functions {
    *
    * Returns the input values, pivoted into an ARRAY. If the input is empty, an empty
    * ARRAY is returned.
-   *
+   *<pr>
    * Example::
    *     >>> df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"])
    *     >>> df.select(array_agg("a", True).alias("result")).show()
@@ -3291,6 +3296,7 @@ object functions {
    *     |  3       |
    *     |]         |
    *     ------------
+   * </pr>
    * @since 1.10.0
    * @param c Column to be collect.
    * @return The array.

From 2fe1b0ddff7a5737abd1951bf8b74c5d5cd8dcf5 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Thu, 8 Aug 2024 13:11:56 -0400
Subject: [PATCH 08/11] Added examples

---
 .../java/com/snowflake/snowpark_java/Functions.java   | 11 +++++++++++
 src/main/scala/com/snowflake/snowpark/functions.scala | 11 +++++++++++
 2 files changed, 22 insertions(+)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index ae5363e5..54f104b1 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3965,6 +3965,17 @@ public static Column sign(Column col) {
    * is positive, everything the left of the final delimiter (counting from left) is returned. If
    * count is negative, every to the right of the final delimiter (counting from the right) is
    * returned. substring_index performs a case-sensitive match when searching for delim.
+   * Example
+   * <pr>{@code
+   * select id, string1,
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 1, 0, 'e', 1) as "POSITION1",
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 2, 0, 'e', 1) as "POSITION2",
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 3, 0, 'e', 1) as "POSITION3",
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 4, 0, 'e', 1) as "POSITION4"
+   * from demo3;
+   * ID	STRING1	         POSITION1	POSITION2	POSITION3	POSITION4
+   * 5	A MAN A PLAN A CANAL	3	       9	      16	       0
+   * </pr>}
    *
    * @since 1.12.1
    */
diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 995931a2..8e6a5455 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3262,6 +3262,17 @@ object functions {
    *  is returned. If count is negative, every to the right of the
    * final delimiter (counting from the right) is returned.
    * substring_index performs a case-sensitive match when searching for delim.
+   * Example
+   * <pr> 
+   * select id, string1,
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 1, 0, 'e', 1) as "POSITION1",
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 2, 0, 'e', 1) as "POSITION2",
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 3, 0, 'e', 1) as "POSITION3",
+   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 4, 0, 'e', 1) as "POSITION4"
+   * from demo3;
+   * ID	STRING1	         POSITION1	POSITION2	POSITION3	POSITION4
+   * 5	A MAN A PLAN A CANAL	3	       9	      16	       0
+   * </pr>
    *   @since 1.12.1
    */
   def substring_index(str: Column, delim: String, count: Int): Column = {

From 457d493a2c3e97846b7808fb00caba6efad5b2e0 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Thu, 8 Aug 2024 13:25:28 -0400
Subject: [PATCH 09/11] adjusted comments

---
 .../java/com/snowflake/snowpark_java/Functions.java | 13 +------------
 .../scala/com/snowflake/snowpark/functions.scala    | 11 -----------
 2 files changed, 1 insertion(+), 23 deletions(-)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index 54f104b1..ef75c513 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3965,18 +3965,7 @@ public static Column sign(Column col) {
    * is positive, everything the left of the final delimiter (counting from left) is returned. If
    * count is negative, every to the right of the final delimiter (counting from the right) is
    * returned. substring_index performs a case-sensitive match when searching for delim.
-   * Example
-   * <pr>{@code
-   * select id, string1,
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 1, 0, 'e', 1) as "POSITION1",
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 2, 0, 'e', 1) as "POSITION2",
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 3, 0, 'e', 1) as "POSITION3",
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 4, 0, 'e', 1) as "POSITION4"
-   * from demo3;
-   * ID	STRING1	         POSITION1	POSITION2	POSITION3	POSITION4
-   * 5	A MAN A PLAN A CANAL	3	       9	      16	       0
-   * </pr>}
-   *
+   * 
    * @since 1.12.1
    */
   public static Column substring_index(Column col, String delim, Integer count) {
diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index 8e6a5455..995931a2 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3262,17 +3262,6 @@ object functions {
    *  is returned. If count is negative, every to the right of the
    * final delimiter (counting from the right) is returned.
    * substring_index performs a case-sensitive match when searching for delim.
-   * Example
-   * <pr> 
-   * select id, string1,
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 1, 0, 'e', 1) as "POSITION1",
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 2, 0, 'e', 1) as "POSITION2",
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 3, 0, 'e', 1) as "POSITION3",
-   * regexp_instr( string1, 'A\\W+(\\w+)', 1, 4, 0, 'e', 1) as "POSITION4"
-   * from demo3;
-   * ID	STRING1	         POSITION1	POSITION2	POSITION3	POSITION4
-   * 5	A MAN A PLAN A CANAL	3	       9	      16	       0
-   * </pr>
    *   @since 1.12.1
    */
   def substring_index(str: Column, delim: String, count: Int): Column = {

From 4ad7078dbfad7e7574bb2df6648f0eccb4c41ae7 Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Mon, 12 Aug 2024 12:59:59 -0400
Subject: [PATCH 10/11] Update Functions.java

---
 .../snowflake/snowpark_java/Functions.java    | 32 ++++++++++---------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index ef75c513..a9102548 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3884,9 +3884,9 @@ public static Column listagg(Column col) {
    * Signature - snowflake.snowpark.functions.regexp_extract (value: Union[Column, str], regexp:
    * Union[Column, str], idx: int) Column Extract a specific group matched by a regex, from the
    * specified string column. If the regex did not match, or the specified group did not match, an
-   * empty string is returned. 
-   * Example: 
-   *  <pre>{@code 
+   * empty string is returned.
+   * Example:
+   *  <pre>{@code
    * from snowflake.snowpark.functions import regexp_extract
    * df = session.createDataFrame([["id_20_30", 10], ["id_40_50", 30]], ["id", "age"])
    * df.select(regexp_extract("id", r"(\d+)", 1).alias("RES")).show()
@@ -3913,12 +3913,12 @@ public static Column regexp_extract(
    *
    * <p>- -1 if the argument is negative. - 1 if it is positive. - 0 if it is 0.
    *
-   * <p>Args: col: The column to evaluate its sign 
-   *  Example:: 
+   * <p>Args: col: The column to evaluate its sign
+   *  Example::
    * * <pre>{@code df =
    * session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
    * df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
-   * sign("c").alias("c_sign")).show() 
+   * sign("c").alias("c_sign")).show()
    *   ----------------------------------
    *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
    *     ----------------------------------
@@ -3939,12 +3939,12 @@ public static Column signum(Column col) {
    *
    * <p>- -1 if the argument is negative. - 1 if it is positive. - 0 if it is 0.
    *
-   * <p>Args: col: The column to evaluate its sign  
-   * Example:: 
+   * <p>Args: col: The column to evaluate its sign
+   * Example::
    * <pre>{@code df =
    * session.create_dataframe([(-2, 2, 0)], ["a", "b", "c"]) >>>
    * df.select(sign("a").alias("a_sign"), sign("b").alias("b_sign"),
-   * sign("c").alias("c_sign")).show() 
+   * sign("c").alias("c_sign")).show()
    *   ----------------------------------
    *     |"A_SIGN"  |"B_SIGN"  |"C_SIGN"  |
    *     ----------------------------------
@@ -3965,7 +3965,7 @@ public static Column sign(Column col) {
    * is positive, everything the left of the final delimiter (counting from left) is returned. If
    * count is negative, every to the right of the final delimiter (counting from the right) is
    * returned. substring_index performs a case-sensitive match when searching for delim.
-   * 
+   *
    * @since 1.12.1
    */
   public static Column substring_index(Column col, String delim, Integer count) {
@@ -3975,12 +3975,14 @@ public static Column substring_index(Column col, String delim, Integer count) {
 
   /**
    * Returns the input values, pivoted into an ARRAY. If the input is empty, an empty ARRAY is
-   * returned. 
-   * <p> Example:: 
-   *  <pre>{@code
+   * returned.
+   *
+   * <p>Example::
+   *
+   * <pre>{@code
    * df = session.create_dataframe([[1], [2], [3], [1]], schema=["a"])
-   * df.select(array_agg("a", True).alias("result")).show() 
-   * "RESULT" [ 1, 2, 3 ] 
+   * df.select(array_agg("a", True).alias("result")).show()
+   * "RESULT" [ 1, 2, 3 ]
    * }</pre>
    *
    * @since 1.10.0

From 2669d2392540b93343ffb512996319d1e4ed60ea Mon Sep 17 00:00:00 2001
From: Shyamala Jayabalan <shyamala.jayabalan@snowflake.com>
Date: Tue, 13 Aug 2024 14:29:07 -0400
Subject: [PATCH 11/11] Fixed indentation issues

---
 src/main/java/com/snowflake/snowpark_java/Functions.java     | 5 ++---
 src/main/scala/com/snowflake/snowpark/functions.scala        | 3 +--
 .../java/com/snowflake/snowpark_test/JavaFunctionSuite.java  | 5 +++--
 .../scala/com/snowflake/snowpark_test/FunctionSuite.scala    | 4 +---
 4 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/src/main/java/com/snowflake/snowpark_java/Functions.java b/src/main/java/com/snowflake/snowpark_java/Functions.java
index 41c38135..4b3bdb1d 100644
--- a/src/main/java/com/snowflake/snowpark_java/Functions.java
+++ b/src/main/java/com/snowflake/snowpark_java/Functions.java
@@ -3882,7 +3882,7 @@ public static Column listagg(Column col) {
   }
 
   /**
-
+   *
    * Signature - snowflake.snowpark.functions.regexp_extract (value: Union[Column, str], regexp:
    * Union[Column, str], idx: int) Column Extract a specific group matched by a regex, from the
    * specified string column. If the regex did not match, or the specified group did not match, an
@@ -3995,7 +3995,7 @@ public static Column collect_list(Column col) {
     return new Column(com.snowflake.snowpark.functions.collect_list(col.toScalaColumn()));
   }
 
-   * Returns a Column expression with values sorted in descending order.
+  /* Returns a Column expression with values sorted in descending order.
    *
    * <p>Example: order column values in descending
    *
@@ -4166,7 +4166,6 @@ public static Column last(Column col) {
     return new Column(functions.last(col.toScalaColumn()));
   }
 
-
   /**
    * Calls a user-defined function (UDF) by name.
    *
diff --git a/src/main/scala/com/snowflake/snowpark/functions.scala b/src/main/scala/com/snowflake/snowpark/functions.scala
index a28be119..588d8290 100644
--- a/src/main/scala/com/snowflake/snowpark/functions.scala
+++ b/src/main/scala/com/snowflake/snowpark/functions.scala
@@ -3328,7 +3328,7 @@ object functions {
    */
   def collect_list(s: String): Column = array_agg(col(s))
 
-   * Returns a Column expression with values sorted in descending order.
+  /* Returns a Column expression with values sorted in descending order.
    * Example:
    * {{{
    *   val df = session.createDataFrame(Seq(1, 2, 3)).toDF("id")
@@ -3498,7 +3498,6 @@ object functions {
   def last(c: Column): Column =
     builtin("LAST_VALUE")(c)
 
-
   /**
    * Invokes a built-in snowflake function with the specified name and arguments.
    * Arguments can be of two types
diff --git a/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java b/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
index 954cb278..33f2904a 100644
--- a/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
+++ b/src/test/java/com/snowflake/snowpark_test/JavaFunctionSuite.java
@@ -2766,7 +2766,6 @@ public void any_value() {
   }
 
   @Test
-
   public void regexp_extract() {
     DataFrame df = getSession().sql("select * from values('A MAN A PLAN A CANAL') as T(a)");
     Row[] expected = {Row.create("MAN")};
@@ -2813,7 +2812,10 @@ public void substring_index() {
     checkAnswer(
         df.select(Functions.substring_index(df.col("a"), "was", 1)),
         new Row[] {Row.create(7)},
+        false);
+  }
 
+  @Test
   public void test_asc() {
     DataFrame df = getSession().sql("select * from values(3),(1),(2) as t(a)");
     Row[] expected = {Row.create(1), Row.create(2), Row.create(3)};
@@ -2874,7 +2876,6 @@ public void last() {
             Functions.last(df.col("name"))
                 .over(Window.partitionBy(df.col("grade")).orderBy(df.col("score").desc()))),
         expected,
-
         false);
   }
 }
diff --git a/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala b/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
index 22f474ea..1420bb10 100644
--- a/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
+++ b/src/test/scala/com/snowflake/snowpark_test/FunctionSuite.scala
@@ -2195,7 +2195,6 @@ trait FunctionSuite extends TestData {
       expected,
       sort = false)
 
-
     expected = Seq(Row(null))
     checkAnswer(
       data.select(regexp_extract(col("a"), "A\\W+(\\w+)", 1, 4, 1)),
@@ -2221,7 +2220,7 @@ trait FunctionSuite extends TestData {
     val df = Seq("It was the best of times, it was the worst of times").toDF("a")
     checkAnswer(df.select(substring_index(col("a"), "was", 1)), Seq(Row(7)), sort = false)
   }
-  
+
   test("desc column order") {
     val input = Seq(1, 2, 3).toDF("data")
     val expected = Seq(3, 2, 1).toDF("data")
@@ -2289,7 +2288,6 @@ trait FunctionSuite extends TestData {
       sort = false)
   }
 
-
 }
 
 class EagerFunctionSuite extends FunctionSuite with EagerSession