-- Migrated from DuckDB test: test/sql/function/string/test_string_split.test
-- String split function tests
-- Test basic string_split functionality
SELECT string_to_array(NULL, NULL);

+----------------------------+
| string_to_array(NULL,NULL) |
+----------------------------+
|                            |
+----------------------------+

SELECT string_to_array('hello world', ' ');

+------------------------------------------------+
| string_to_array(Utf8("hello world"),Utf8(" ")) |
+------------------------------------------------+
| [hello, world]                                 |
+------------------------------------------------+

SELECT string_to_array(NULL, ' ');

+---------------------------------+
| string_to_array(NULL,Utf8(" ")) |
+---------------------------------+
|                                 |
+---------------------------------+

SELECT string_to_array('a b c', NULL);

+-------------------------------------+
| string_to_array(Utf8("a b c"),NULL) |
+-------------------------------------+
| [a,  , b,  , c]                     |
+-------------------------------------+

SELECT string_to_array('a b c', ' ');

+------------------------------------------+
| string_to_array(Utf8("a b c"),Utf8(" ")) |
+------------------------------------------+
| [a, b, c]                                |
+------------------------------------------+

-- Test with table data
CREATE TABLE split_test(s VARCHAR, ts TIMESTAMP TIME INDEX);

Affected Rows: 0

INSERT INTO split_test VALUES
    ('hello,world,test', 1000),
    ('a|b|c|d', 2000),
    ('no-separator', 3000),
    ('', 4000),
    (NULL, 5000);

Affected Rows: 5

-- Test splitting with different separators
SELECT s, string_to_array(s, ',') FROM split_test ORDER BY ts;

+------------------+-----------------------------------------+
| s                | string_to_array(split_test.s,Utf8(",")) |
+------------------+-----------------------------------------+
| hello,world,test | [hello, world, test]                    |
| a|b|c|d          | [a|b|c|d]                               |
| no-separator     | [no-separator]                          |
|                  | []                                      |
|                  |                                         |
+------------------+-----------------------------------------+

SELECT s, string_to_array(s, '|') FROM split_test ORDER BY ts;

+------------------+-----------------------------------------+
| s                | string_to_array(split_test.s,Utf8("|")) |
+------------------+-----------------------------------------+
| hello,world,test | [hello,world,test]                      |
| a|b|c|d          | [a, b, c, d]                            |
| no-separator     | [no-separator]                          |
|                  | []                                      |
|                  |                                         |
+------------------+-----------------------------------------+

SELECT s, string_to_array(s, '-') FROM split_test ORDER BY ts;

+------------------+-----------------------------------------+
| s                | string_to_array(split_test.s,Utf8("-")) |
+------------------+-----------------------------------------+
| hello,world,test | [hello,world,test]                      |
| a|b|c|d          | [a|b|c|d]                               |
| no-separator     | [no, separator]                         |
|                  | []                                      |
|                  |                                         |
+------------------+-----------------------------------------+

-- Test splitting with multi-character separator
CREATE TABLE multi_sep_test(s VARCHAR, ts TIMESTAMP TIME INDEX);

Affected Rows: 0

INSERT INTO multi_sep_test VALUES
    ('hello::world::test', 1000),
    ('a---b---c', 2000),
    ('single', 3000);

Affected Rows: 3

SELECT s, string_to_array(s, '::') FROM multi_sep_test ORDER BY ts;

+--------------------+----------------------------------------------+
| s                  | string_to_array(multi_sep_test.s,Utf8("::")) |
+--------------------+----------------------------------------------+
| hello::world::test | [hello, world, test]                         |
| a---b---c          | [a---b---c]                                  |
| single             | [single]                                     |
+--------------------+----------------------------------------------+

SELECT s, string_to_array(s, '---') FROM multi_sep_test ORDER BY ts;

+--------------------+-----------------------------------------------+
| s                  | string_to_array(multi_sep_test.s,Utf8("---")) |
+--------------------+-----------------------------------------------+
| hello::world::test | [hello::world::test]                          |
| a---b---c          | [a, b, c]                                     |
| single             | [single]                                      |
+--------------------+-----------------------------------------------+

-- Test with Unicode separators
CREATE TABLE unicode_split_test(s VARCHAR, ts TIMESTAMP TIME INDEX);

Affected Rows: 0

INSERT INTO unicode_split_test VALUES
    ('hello世world世test', 1000),
    ('a🦆b🦆c', 2000);

Affected Rows: 2

SELECT s, string_to_array(s, '世') FROM unicode_split_test ORDER BY ts;

+--------------------+--------------------------------------------------+
| s                  | string_to_array(unicode_split_test.s,Utf8("世")) |
+--------------------+--------------------------------------------------+
| hello世world世test | [hello, world, test]                             |
| a🦆b🦆c            | [a🦆b🦆c]                                        |
+--------------------+--------------------------------------------------+

SELECT s, string_to_array(s, '🦆') FROM unicode_split_test ORDER BY ts;

+--------------------+--------------------------------------------------+
| s                  | string_to_array(unicode_split_test.s,Utf8("🦆")) |
+--------------------+--------------------------------------------------+
| hello世world世test | [hello世world世test]                             |
| a🦆b🦆c            | [a, b, c]                                        |
+--------------------+--------------------------------------------------+

-- Test edge cases
-- Empty string
SELECT string_to_array('', ',');

+-------------------------------------+
| string_to_array(Utf8(""),Utf8(",")) |
+-------------------------------------+
| []                                  |
+-------------------------------------+

-- Empty separator
SELECT string_to_array('hello', '');

+-----------------------------------------+
| string_to_array(Utf8("hello"),Utf8("")) |
+-----------------------------------------+
| [hello]                                 |
+-----------------------------------------+

-- Multiple consecutive separators
SELECT string_to_array(',,hello,,world,,', ',');

+-----------------------------------------------------+
| string_to_array(Utf8(",,hello,,world,,"),Utf8(",")) |
+-----------------------------------------------------+
| [, , hello, , world, , ]                            |
+-----------------------------------------------------+

-- Trailing separator
SELECT string_to_array('hello,', ',');

+-------------------------------------------+
| string_to_array(Utf8("hello,"),Utf8(",")) |
+-------------------------------------------+
| [hello, ]                                 |
+-------------------------------------------+

-- Leading separator
SELECT string_to_array(',hello', ',');

+-------------------------------------------+
| string_to_array(Utf8(",hello"),Utf8(",")) |
+-------------------------------------------+
| [, hello]                                 |
+-------------------------------------------+

DROP TABLE split_test;

Affected Rows: 0

DROP TABLE multi_sep_test;

Affected Rows: 0

DROP TABLE unicode_split_test;

Affected Rows: 0