Adds doc and more tests

docs/developer-guide/ksqldb-reference/scalar-functions.md

@@ -42,6 +42,7 @@ keywords: ksqlDB, function, scalar
   - [MASK_RIGHT](#mask_right)
   - [REPLACE](#replace)
   - [REGEXP_EXTRACT](#regexp_extract)
+  - [REGEXP_SPLIT](#regexp_split)
   - [SPLIT](#split)
   - [SUBSTRING](#substring)
   - [TRIM](#trim)
@@ -413,6 +414,23 @@ the entire substring is returned by default.
 For example, `REGEXP_EXTRACT("(.*) (.*)", 'hello there', 2)`
 returns "there".
 
+REGEXP_SPLIT
+-----
+
+`REGEXP_SPLIT(col1, 'a.b+')`
+
+Splits a string into an array of substrings based
+on a regular expression. If there is no match,
+then the original string is returned as the only
+element in the array. If the regular expression is empty,
+then all characters in the string are split.
+If either, string or regular expression, are NULL, then a
+NULL value is returned.
+
+If the regular expression is found at the beginning or end
+of the string, or there are contiguous delimiters,
+then an empty space is added to the array.
+
 SPLIT
 -----
 

ksqldb-functional-tests/src/test/resources/query-validation-tests/split.json

@@ -84,6 +84,25 @@
         {"topic": "OUTPUT", "key": "3", "value": {"S1": "A", "S2": "A"}, "timestamp": 0},
         {"topic": "OUTPUT", "key": "4", "value": {"S1": "1", "S2": "3"}, "timestamp": 0}
       ]
+    },
+    {
+      "name": "regexp_split",
+      "statements": [
+        "CREATE STREAM TEST (K STRING KEY, input_string VARCHAR) WITH (kafka_topic='test_topic', value_format='JSON');",
+        "CREATE STREAM OUTPUT AS SELECT K, REGEXP_SPLIT(input_string, '(ab|cd)') AS EXTRACTED FROM TEST;"
+      ],
+      "inputs": [
+        {"topic": "test_topic", "value": {"input_string": "aabcda"}},
+        {"topic": "test_topic", "value": {"input_string": "aabdcda"}},
+        {"topic": "test_topic", "value": {"input_string": "zxy"}},
+        {"topic": "test_topic", "value": {"input_string": null}}
+      ],
+      "outputs": [
+        {"topic": "OUTPUT", "value": {"EXTRACTED": ["a", "", "a"]}},
+        {"topic": "OUTPUT", "value": {"EXTRACTED": ["a", "d", "a"]}},
+        {"topic": "OUTPUT", "value": {"EXTRACTED": ["zxy"]}},
+        {"topic": "OUTPUT", "value": {"EXTRACTED": null}}
+      ]
     }
   ]
 }