[SPARK-34214][SQL][PYTHON] Expose regexp_extract_all in PySpark

python/pyspark/sql/functions.py

@@ -2754,11 +2754,22 @@ def split(str, pattern, limit=-1):
 
 
 def regexp_extract(str, pattern, idx):
-    r"""Extract a specific group matched by a Java regex, from the specified string column.
+    r"""Extract the first match of the given group in 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.
 
     .. versionadded:: 1.5.0
 
+    Parameters
+    ----------
+    str : :class:`Column` or str
+        a string expression to extract from
+    pattern : str
+        a string representing a regular expression. The regex string should be a Java regular
+        expression.
+    idx : int
+        the regex group from which to extract a potential match. 0 stands for the entire regex, and
+        only non-negative numbers are allowed.
+
     Examples
     --------
     >>> df = spark.createDataFrame([('100-200',)], ['str'])
@@ -2776,6 +2787,40 @@ def regexp_extract(str, pattern, idx):
     return Column(jc)
 
 
+def regexp_extract_all(str, pattern, idx):
+    r"""Extract all matches of the given group in a regex, from the specified string column.
+    If the regex did not match, or the specified group did not match, an empty array is returned.
+
+    .. versionadded:: 3.1.0
+
+    Parameters
+    ----------
+    str : :class:`Column` or str
+        a string expression to extract from
+    pattern : str
+        a string representing a regular expression. The regex string should be a Java regular
+        expression.
+    idx : int
+        the regex group from which to extract all matches. 0 stands for the entire regex, and only
+        non-negative numbers are allowed.
+
+    Examples
+    --------
+    >>> df = spark.createDataFrame([('100-200, 300-400',)], ['str'])
+    >>> df.select(regexp_extract_all('str', r'(\d+)-(\d+)', 1).alias('d')).collect()
+    [Row(d=['100', '300'])]
+    >>> df = spark.createDataFrame([('foo',)], ['str'])
+    >>> df.select(regexp_extract_all('str', r'(\d+)', 1).alias('d')).collect()
+    [Row(d=[])]
+    >>> df = spark.createDataFrame([('aaaac',)], ['str'])
+    >>> df.select(regexp_extract_all('str', '(a+)(b)?(c)', 2).alias('d')).collect()
+    [Row(d=[''])]
+    """
+    sc = SparkContext._active_spark_context
+    jc = sc._jvm.functions.regexp_extract_all(_to_java_column(str), pattern, idx)
+    return Column(jc)
+
+
 def regexp_replace(str, pattern, replacement):
     r"""Replace all substrings of the specified string value that match regexp with rep.