ANSI 合規性

-- `spark.sql.ansi.enabled=true`
SELECT 2147483647 + 1;
org.apache.spark.SparkArithmeticException: [ARITHMETIC_OVERFLOW] integer overflow. Use 'try_add' to tolerate overflow and return NULL instead. If necessary set spark.sql.ansi.enabled to "false" to bypass this error.
== SQL(line 1, position 8) ==
SELECT 2147483647 + 1
       ^^^^^^^^^^^^^^

SELECT abs(-2147483648);
org.apache.spark.SparkArithmeticException: [ARITHMETIC_OVERFLOW] integer overflow. If necessary set spark.sql.ansi.enabled to "false" to bypass this error.

-- `spark.sql.ansi.enabled=false`
SELECT 2147483647 + 1;
+----------------+
|(2147483647 + 1)|
+----------------+
|     -2147483648|
+----------------+

SELECT abs(-2147483648);
+----------------+
|abs(-2147483648)|
+----------------+
|     -2147483648|
+----------------+

-- Examples of explicit casting

-- `spark.sql.ansi.enabled=true`
SELECT CAST('a' AS INT);
org.apache.spark.SparkNumberFormatException: [CAST_INVALID_INPUT] The value 'a' of the type "STRING" cannot be cast to "INT" because it is malformed. Correct the value as per the syntax, or change its target type. Use `try_cast` to tolerate malformed input and return NULL instead. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.
== SQL(line 1, position 8) ==
SELECT CAST('a' AS INT)
       ^^^^^^^^^^^^^^^^

SELECT CAST(2147483648L AS INT);
org.apache.spark.SparkArithmeticException: [CAST_OVERFLOW] The value 2147483648L of the type "BIGINT" cannot be cast to "INT" due to an overflow. Use `try_cast` to tolerate overflow and return NULL instead. If necessary set "spark.sql.ansi.enabled" to "false" to bypass this error.

SELECT CAST(DATE'2020-01-01' AS INT);
org.apache.spark.sql.AnalysisException: cannot resolve 'CAST(DATE '2020-01-01' AS INT)' due to data type mismatch: cannot cast date to int.
To convert values from date to int, you can use function UNIX_DATE instead.

-- `spark.sql.ansi.enabled=false` (This is a default behaviour)
SELECT CAST('a' AS INT);
+--------------+
|CAST(a AS INT)|
+--------------+
|          null|
+--------------+

SELECT CAST(2147483648L AS INT);
+-----------------------+
|CAST(2147483648 AS INT)|
+-----------------------+
|            -2147483648|
+-----------------------+

SELECT CAST(DATE'2020-01-01' AS INT)
+------------------------------+
|CAST(DATE '2020-01-01' AS INT)|
+------------------------------+
|                          null|
+------------------------------+

-- Examples of store assignment rules
CREATE TABLE t (v INT);

-- `spark.sql.storeAssignmentPolicy=ANSI`
INSERT INTO t VALUES ('1');
org.apache.spark.sql.AnalysisException: [INCOMPATIBLE_DATA_FOR_TABLE.CANNOT_SAFELY_CAST] Cannot write incompatible data for table `spark_catalog`.`default`.`t`: Cannot safely cast `v`: "STRING" to "INT".

-- `spark.sql.storeAssignmentPolicy=LEGACY` (This is a legacy behaviour until Spark 2.x)
INSERT INTO t VALUES ('1');
SELECT * FROM t;
+---+
|  v|
+---+
|  1|
+---+

CREATE TABLE test(i INT);

INSERT INTO test VALUES (2147483648L);
org.apache.spark.SparkArithmeticException: [CAST_OVERFLOW_IN_TABLE_INSERT] Fail to insert a value of "BIGINT" type into the "INT" type column `i` due to an overflow. Use `try_cast` on the input value to tolerate overflow and return NULL instead.

-- The coalesce function accepts any set of argument types as long as they share a least common type. 
-- The result type is the least common type of the arguments.
> SET spark.sql.ansi.enabled=true;
> SELECT typeof(coalesce(1Y, 1L, NULL));
BIGINT
> SELECT typeof(coalesce(1, DATE'2020-01-01'));
Error: Incompatible types [INT, DATE]

> SELECT typeof(coalesce(ARRAY(1Y), ARRAY(1L)));
ARRAY<BIGINT>
> SELECT typeof(coalesce(1, 1F));
DOUBLE
> SELECT typeof(coalesce(1L, 1F));
DOUBLE
> SELECT (typeof(coalesce(1BD, 1F)));
DOUBLE

> SELECT typeof(coalesce(1, '2147483648'))
BIGINT
> SELECT typeof(coalesce(1.0, '2147483648'))
DOUBLE
> SELECT typeof(coalesce(DATE'2021-01-01', '2022-01-01'))
DATE

> SET spark.sql.ansi.enabled=true;
-- implicitly cast Int to String type
> SELECT concat('total number: ', 1);
total number: 1
-- implicitly cast Timestamp to Date type
> select datediff(now(), current_date);
0

-- implicitly cast String to Double type
> SELECT ceil('0.1');
1
-- special rule: implicitly cast NULL to Date type
> SELECT year(null);
NULL

> CREATE TABLE t(s string);
-- Can't store String column as Numeric types.
> SELECT ceil(s) from t;
Error in query: cannot resolve 'CEIL(spark_catalog.default.t.s)' due to data type mismatch
-- Can't store String column as Date type.
> select year(s) from t;
Error in query: cannot resolve 'year(spark_catalog.default.t.s)' due to data type mismatch