Spark SQL----WHERE子句

一、描述

WHERE子句用于根据指定的条件限制查询或子查询的FROM子句的结果。

二、语法

WHERE boolean_expression

三、参数

• boolean_expression
  指定计算结果类型为boolean的任何表达式。两个或多个表达式可以使用逻辑操作符(AND, OR)组合在一起。

四、例子

CREATE TABLE person (id INT, name STRING, age INT);
INSERT INTO person VALUES
    (100, 'John', 30),
    (200, 'Mary', NULL),
    (300, 'Mike', 80),
    (400, 'Dan',  50);

-- Comparison operator in `WHERE` clause.
SELECT * FROM person WHERE id > 200 ORDER BY id;
+---+----+---+
| id|name|age|
+---+----+---+
|300|Mike| 80|
|400| Dan| 50|
+---+----+---+

-- Comparison and logical operators in `WHERE` clause.
SELECT * FROM person WHERE id = 200 OR id = 300 ORDER BY id;
+---+----+----+
| id|name| age|
+---+----+----+
|200|Mary|null|
|300|Mike|  80|
+---+----+----+

-- IS NULL expression in `WHERE` clause.
SELECT * FROM person WHERE id > 300 OR age IS NULL ORDER BY id;
+---+----+----+
| id|name| age|
+---+----+----+
|200|Mary|null|
|400| Dan|  50|
+---+----+----+

-- Function expression in `WHERE` clause.
SELECT * FROM person WHERE length(name) > 3 ORDER BY id;
+---+----+----+
| id|name| age|
+---+----+----+
|100|John|  30|
|200|Mary|null|
|300|Mike|  80|
+---+----+----+

-- `BETWEEN` expression in `WHERE` clause.
SELECT * FROM person WHERE id BETWEEN 200 AND 300 ORDER BY id;
+---+----+----+
| id|name| age|
+---+----+----+
|200|Mary|null|
|300|Mike|  80|
+---+----+----+

-- Scalar Subquery in `WHERE` clause.
SELECT * FROM person WHERE age > (SELECT avg(age) FROM person);
+---+----+---+
| id|name|age|
+---+----+---+
|300|Mike| 80|
+---+----+---+

-- Correlated Subquery in `WHERE` clause.
SELECT * FROM person AS parent
    WHERE EXISTS (
        SELECT 1 FROM person AS child
        WHERE parent.id = child.id AND child.age IS NULL
    );
+---+----+----+
|id |name|age |
+---+----+----+
|200|Mary|null|
+---+----+----+