sql >> Databáze >  >> RDS >> Mysql

MYSQL – rozdělení dat do více řádků

K vyřešení tohoto problému můžete použít uloženou proceduru, která používá kurzor, ale není to příliš elegantní, ale ani seznam zapisovatelů oddělených čárkami!

Měl následující kód ležet kolem z podobné otázky, ale raději byste jej důkladně zkontrolujte.

Doufám, že to pomůže :)

mysql> select * from movies_unf;
+---------+-------------+------------------------------------------------------+
| movieID | movie_title | written_by                                           |
+---------+-------------+------------------------------------------------------+
|       1 | movie1      | person1, person2                                     |
|       2 | movie2      | person3                                              |
|       3 | movie3      | person4, person2, person6                            |
|       4 | movie4      | person4, person4, person1, person2, person1,person8, |
|       5 | movie1      | person1, person2                                     |
+---------+-------------+------------------------------------------------------+
5 rows in set (0.00 sec)

call normalise_movies_unf();

mysql> select * from movies;
+----------+--------+
| movie_id | title  |
+----------+--------+
|        1 | movie1 |
|        2 | movie2 |
|        3 | movie3 |
|        4 | movie4 |
+----------+--------+
4 rows in set (0.00 sec)

mysql> select * from writers;
+-----------+---------+
| writer_id | name    |
+-----------+---------+
|         1 | person1 |
|         2 | person2 |
|         3 | person3 |
|         4 | person4 |
|         6 | person6 |
|        12 | person8 |
+-----------+---------+
6 rows in set (0.00 sec)

mysql> select * from movie_writers;
+----------+-----------+
| movie_id | writer_id |
+----------+-----------+
|        1 |         1 |
|        1 |         2 |
|        2 |         3 |
|        3 |         2 |
|        3 |         4 |
|        3 |         6 |
|        4 |         1 |
|        4 |         2 |
|        4 |         4 |
|        4 |        12 |
+----------+-----------+
10 rows in set (0.00 sec)

Příklady tabulek

drop table if exists movies_unf;
create table movies_unf
(
movieID int unsigned not null primary key,
movie_title varchar(255) not null,
written_by varchar(1024) not null
)engine=innodb;

insert into movies_unf values 
(1,'movie1','person1, person2'),
(2,'movie2','person3'),
(3,'movie3','person4, person2, person6'),
(4,'movie4','person4, person4, person1, person2, person1,person8,'), -- dodgy writers
(5,'movie1','person1, person2'); -- dodgy movie

drop table if exists movies;
create table movies
(
movie_id int unsigned not null auto_increment primary key,
title varchar(255) unique not null
)engine=innodb;

drop table if exists writers;
create table writers
(
writer_id int unsigned not null auto_increment primary key,
name varchar(255) unique not null
)engine=innodb;

drop table if exists movie_writers;
create table movie_writers
(
movie_id int unsigned not null,
writer_id int unsigned not null,
primary key (movie_id, writer_id)
)engine=innodb;

Uložená procedura

drop procedure if exists normalise_movies_unf;

delimiter #

create procedure normalise_movies_unf()
begin

declare v_movieID int unsigned default 0;
declare v_movie_title varchar(255);
declare v_writers varchar(1024);

declare v_movie_id int unsigned default 0;
declare v_writer_id int unsigned default 0;
declare v_name varchar(255);

declare v_csv_done tinyint unsigned default 0;
declare v_csv_idx int unsigned default 0;

declare v_done tinyint default 0;
declare v_cursor cursor for 
    select distinct movieID, movie_title, written_by from movies_unf;

declare continue handler for not found set v_done = 1;

start transaction;

open v_cursor;
repeat
  fetch v_cursor into v_movieID, v_movie_title, v_writers;

  set v_movie_title = trim(v_movie_title);
  set v_writers = replace(v_writers,' ', '');

  -- insert the movie
  insert ignore into movies (title) values (v_movie_title);
  select movie_id into v_movie_id from movies where title = v_movie_title;  

  -- split the out the writers and insert
  set v_csv_done = 0;       
  set v_csv_idx = 1;

  while not v_csv_done do
    set v_name = substring(v_writers, v_csv_idx, 
      if(locate(',', v_writers, v_csv_idx) > 0, 
        locate(',', v_writers, v_csv_idx) - v_csv_idx, 
        length(v_writers)));

      set v_name = trim(v_name);

      if length(v_name) > 0 then
        set v_csv_idx = v_csv_idx + length(v_name) + 1;

        insert ignore into writers (name) values (v_name);
        select writer_id into v_writer_id from writers where name = v_name; 
        insert ignore into movie_writers (movie_id, writer_id) values (v_movie_id, v_writer_id);
      else
        set v_csv_done = 1;
      end if;

  end while;

until v_done end repeat;
close v_cursor;

commit;

truncate table movies_unf;

end#

delimiter ;

UPRAVIT

Upraveno sproc tak, aby nepřeskakoval klíčové hodnoty!

drop procedure if exists normalise_movies_unf;

delimiter #

create procedure normalise_movies_unf()
begin

declare v_movieID int unsigned default 0;
declare v_movie_title varchar(255);
declare v_writers varchar(1024);

declare v_movie_id int unsigned default 0;
declare v_writer_id int unsigned default 0;
declare v_name varchar(255);

declare v_csv_done tinyint unsigned default 0;
declare v_csv_idx int unsigned default 0;

declare v_done tinyint default 0;
declare v_cursor cursor for 
    select distinct movieID, movie_title, written_by from movies_unf;

declare continue handler for not found set v_done = 1;

start transaction;

open v_cursor;
repeat
  fetch v_cursor into v_movieID, v_movie_title, v_writers;

  set v_movie_title = trim(v_movie_title);
  set v_writers = replace(v_writers,' ', '');

  -- insert the movie

  if not exists (select 1 from movies where title = v_movie_title) then
    insert ignore into movies (title) values (v_movie_title);
  end if;  
  select movie_id into v_movie_id from movies where title = v_movie_title;  

  -- split the out the writers and insert
  set v_csv_done = 0;       
  set v_csv_idx = 1;

  while not v_csv_done do
    set v_name = substring(v_writers, v_csv_idx, 
      if(locate(',', v_writers, v_csv_idx) > 0, 
        locate(',', v_writers, v_csv_idx) - v_csv_idx, 
        length(v_writers)));

      set v_name = trim(v_name);

      if length(v_name) > 0 then
        set v_csv_idx = v_csv_idx + length(v_name) + 1;


        if not exists (select 1 from writers where name = v_name) then
          insert ignore into writers (name) values (v_name);
        end if;
        select writer_id into v_writer_id from writers where name = v_name; 
        insert ignore into movie_writers (movie_id, writer_id) values (v_movie_id, v_writer_id);
      else
        set v_csv_done = 1;
      end if;

  end while;

until v_done end repeat;
close v_cursor;

commit;

truncate table movies_unf;

end#

delimiter ;


  1. 2017 @ Somenines:Oslava příběhů našich zákazníků

  2. Uživatelé Wordpress a uživatelská meta - spojení více řádků v jedné tabulce do jednoho řádku v jiné tabulce

  3. Jak RPAD() funguje v MariaDB

  4. Dotaz na prvky pole uvnitř typu JSON