MySQL处理重复数据的学习笔记

CREATE TABLE person_tbl
(
  first_name CHAR(20),
  last_name CHAR(20),
  sex CHAR(10)
);

CREATE TABLE person_tbl
(
  first_name CHAR(20) NOT NULL,
  last_name CHAR(20) NOT NULL,
  sex CHAR(10),
  PRIMARY KEY (last_name, first_name)
);

mysql> INSERT IGNORE INTO person_tbl (last_name, first_name)
  -> VALUES( 'Jay', 'Thomas');
Query OK, 1 row affected (0.00 sec)
mysql> INSERT IGNORE INTO person_tbl (last_name, first_name)
  -> VALUES( 'Jay', 'Thomas');
Query OK, 0 rows affected (0.00 sec)

CREATE TABLE person_tbl
(
  first_name CHAR(20) NOT NULL,
  last_name CHAR(20) NOT NULL,
  sex CHAR(10),
  UNIQUE (last_name, first_name)
);

mysql> SELECT COUNT(*) as repetitions, last_name, first_name
  -> FROM person_tbl
  -> GROUP BY last_name, first_name
  -> HAVING repetitions > 1;

mysql> SELECT DISTINCT last_name, first_name
  -> FROM person_tbl;

mysql> SELECT last_name, first_name
  -> FROM person_tbl
  -> GROUP BY (last_name, first_name);

mysql> CREATE TABLE tmp SELECT last_name, first_name, sex FROM person_tbl GROUP BY (last_name, first_name, sex);
mysql> DROP TABLE person_tbl;
mysql> ALTER TABLE tmp RENAME TO person_tbl;

mysql> ALTER IGNORE TABLE person_tbl
  -> ADD PRIMARY KEY (last_name, first_name);