DBA：负责组织同步和导入

1.在哪里发货？

1.1。临时表（TEMPORARY TABLE）

到数据库的每个连接都有自己的名称空间

断开连接的“自毁”

非复制

1.2。未记录表（UNLOGGED TABLE）

• 使用最大随机名称创建“他”表，以免与任何人交叉
• 提取：将来自外部源的数据倒入其中
• 转换：转换后，填写关键绑定字段
• 加载：将完成的数据倒入目标表
• 删除“我的”表

. , , (. 29), . , ; . , . , , .

1.3。提交{删除行| 下降}

1.4。喜欢...包括...

CREATE TEMPORARY TABLE import_table(
  LIKE target_table
);

2.怎么写？

3.如何处理？

• 您的数据库中有一个包含100万条记录的客户数据的标牌
• 客户每天都会向您发送新的完整“图片”
• 根据经验，您会不时更改超过1万条记录

3.1。全同步算法

• 删除不再存在的所有内容
• 更新所有已存在的内容，您需要更新
• 插入所有尚未

从dst删除

• 完全删除（DELETE）
• 粘贴新图像中的所有内容

截断dst

• 清除（TRUNCATE）整个表
• 粘贴新图像中的所有内容

• 我们开始长期交易
• TRUNCATE施加AccessExclusive -Lock
• 我们做了很长时间的插入，此时其他所有人甚至无法SELECT

ALTER TABLE ...重命名... / DROP TABLE ...

• AccessExclusive也是如此，尽管时间大大减少了
• 该表的所有查询计划/统计信息均已重置，需要驱动ANALYZE
• 桌上的所有外键（FK）都中断了

删除，更新，插入

--     ,     "" 
BEGIN;

--      
CREATE TEMPORARY TABLE tmp(
  LIKE dst INCLUDING INDEXES --    ,   
) ON COMMIT DROP; --       

-- -     COPY
COPY tmp FROM STDIN;
-- ...
-- \.

--  
DELETE FROM
  dst D
USING
  dst X
LEFT JOIN
  tmp Y
    USING(pk1, pk2) --   
WHERE
  (D.pk1, D.pk2) = (X.pk1, X.pk2) AND
  Y IS NOT DISTINCT FROM NULL; -- ""

--  
UPDATE
  dst D
SET
  (f1, f2, f3) = (T.f1, T.f2, T.f3)
FROM
  tmp T
WHERE
  (D.pk1, D.pk2) = (T.pk1, T.pk2) AND
  (D.f1, D.f2, D.f3) IS DISTINCT FROM (T.f1, T.f2, T.f3); --   

--  
INSERT INTO
  dst
SELECT
  T.*
FROM
  tmp T
LEFT JOIN
  dst D
    USING(pk1, pk2)
WHERE
  D IS NOT DISTINCT FROM NULL;

COMMIT;

3.2。导入后处理

--  
CREATE TABLE kladr(...);
CREATE TABLE kladr_house(...);

--    
CREATE TABLE kladr$log(
  ro kladr, --      /
  rn kladr
);

CREATE TABLE kladr_house$log(
  ro kladr_house,
  rn kladr_house
);

--    
CREATE OR REPLACE FUNCTION diff$log() RETURNS trigger AS $$
DECLARE
  dst varchar = TG_TABLE_NAME || '$log';
  stmt text = '';
BEGIN
  --      
  IF TG_OP = 'UPDATE' THEN
    IF NEW IS NOT DISTINCT FROM OLD THEN
      RETURN NEW;
    END IF;
  END IF;
  --   
  stmt = 'INSERT INTO ' || dst::text || '(ro,rn)VALUES(';
  CASE TG_OP
    WHEN 'INSERT' THEN
      EXECUTE stmt || 'NULL,$1)' USING NEW;
    WHEN 'UPDATE' THEN
      EXECUTE stmt || '$1,$2)' USING OLD, NEW;
    WHEN 'DELETE' THEN
      EXECUTE stmt || '$1,NULL)' USING OLD;
  END CASE;
  RETURN NEW;
END;
$$ LANGUAGE plpgsql;

CREATE TRIGGER log
  AFTER INSERT OR UPDATE OR DELETE
  ON kladr
    FOR EACH ROW
      EXECUTE PROCEDURE diff$log();

CREATE TRIGGER log
  AFTER INSERT OR UPDATE OR DELETE
  ON kladr_house
    FOR EACH ROW
      EXECUTE PROCEDURE diff$log();

3.3。导入相关集

CREATE TABLE client(
  client_id
    serial
      PRIMARY KEY
, inn
    varchar
      UNIQUE
, name
    varchar
);

CREATE TABLE invoice(
  invoice_id
    serial
      PRIMARY KEY
, client_id
    integer
      REFERENCES client(client_id)
, number
    varchar
, dt
    date
, sum
    numeric(32,2)
);

CREATE TEMPORARY TABLE invoice_import(
  client_inn
    varchar
, client_name
    varchar
, invoice_number
    varchar
, invoice_dt
    date
, invoice_sum
    numeric(32,2)
);

0123456789;;A-01;2020-03-16;1000.00
9876543210;;A-02;2020-03-16;666.00
0123456789;;B-03;2020-03-16;9999.00

INSERT INTO invoice_import
VALUES
  ('0123456789', '', 'A-01', '2020-03-16', 1000.00)
, ('9876543210', '', 'A-02', '2020-03-16', 666.00)
, ('0123456789', '', 'B-03', '2020-03-16', 9999.00);

CREATE TEMPORARY TABLE client_import AS
SELECT DISTINCT ON(client_inn)
--   SELECT DISTINCT,    
  client_inn inn
, client_name "name"
FROM
  invoice_import;

ALTER TABLE invoice_import ADD COLUMN client_id integer;
ALTER TABLE client_import ADD COLUMN client_id integer;

--     ID   
UPDATE
  client_import T
SET
  client_id = D.client_id
FROM
  client D
WHERE
  T.inn = D.inn; -- unique key

--       ID
WITH ins AS (
  INSERT INTO client(
    inn
  , name
  )
  SELECT
    inn
  , name
  FROM
    client_import
  WHERE
    client_id IS NULL --  ID  
  RETURNING *
)
UPDATE
  client_import T
SET
  client_id = D.client_id
FROM
  ins D
WHERE
  T.inn = D.inn; -- unique key

--  ID    
UPDATE
  invoice_import T
SET
  client_id = D.client_id
FROM
  client_import D
WHERE
  T.client_inn = D.inn; --