Postgresql - Rent sätt att infoga poster om de inte finns, uppdatera om de gör det

Ok, jag lyckades skapa ett testcase. Resultatet är att uppdateringsdelen alltid körs, även på en ny inlaga. COPY verkar gå förbi regelsystemet.[För tydlighetens skull har jag lagt detta i ett separat svar]

DROP TABLE pages CASCADE;
CREATE TABLE pages
    ( url VARCHAR NOT NULL  PRIMARY KEY
    , html VARCHAR
    , last TIMESTAMP
    );

INSERT INTO pages(url,html,last) VALUES ('www.example.com://page1' , 'meuk1' , '2001-09-18 23:30:00'::timestamp );

CREATE RULE Pages_Upsert AS ON INSERT TO pages
  WHERE EXISTS (SELECT 1 from pages P where NEW.url = P.url)
     DO INSTEAD (
     UPDATE pages SET html=new.html , last = NOW() WHERE url = NEW.url
    );

INSERT INTO pages(url,html,last) VALUES ('www.example.com://page2' , 'meuk2' , '2002-09-18 23:30:00':: timestamp );
INSERT INTO pages(url,html,last) VALUES ('www.example.com://page3' , 'meuk3' , '2003-09-18 23:30:00':: timestamp );

INSERT INTO pages(url,html,last) SELECT pp.url || '/added'::text, pp.html || '.html'::text , pp.last + interval '20 years' FROM pages pp;

COPY pages(url,html,last) FROM STDIN;
www.example.com://pageX     stdin   2000-09-18 23:30:00
\.

SELECT * FROM pages;

Resultatet:

              url              |    html    |            last            
-------------------------------+------------+----------------------------
 www.example.com://page1       | meuk1      | 2001-09-18 23:30:00
 www.example.com://page2       | meuk2      | 2011-09-18 23:48:30.775373
 www.example.com://page3       | meuk3      | 2011-09-18 23:48:30.783758
 www.example.com://page1/added | meuk1.html | 2011-09-18 23:48:30.792097
 www.example.com://page2/added | meuk2.html | 2011-09-18 23:48:30.792097
 www.example.com://page3/added | meuk3.html | 2011-09-18 23:48:30.792097
 www.example.com://pageX       | stdin      | 2000-09-18 23:30:00
 (7 rows)

UPPDATERING:Bara för att bevisa att det går att göra:

INSERT INTO pages(url,html,last) VALUES ('www.example.com://page1' , 'meuk1' , '2001-09-18 23:30:00'::timestamp );
CREATE VIEW vpages AS (SELECT * from pages);

CREATE RULE Pages_Upsert AS ON INSERT TO vpages
  DO INSTEAD (
     UPDATE pages p0
     SET html=NEW.html , last = NOW() WHERE p0.url = NEW.url
    ;
     INSERT INTO pages (url,html,last)
    SELECT NEW.url, NEW.html, NEW.last
        WHERE NOT EXISTS ( SELECT * FROM pages p1 WHERE p1.url = NEW.url)
    );

CREATE RULE Pages_Indate AS ON UPDATE TO vpages
  DO INSTEAD (
     INSERT INTO pages (url,html,last)
    SELECT NEW.url, NEW.html, NEW.last
        WHERE NOT EXISTS ( SELECT * FROM pages p1 WHERE p1.url = OLD.url)
        ;
     UPDATE pages p0
     SET html=NEW.html , last = NEW.last WHERE p0.url = NEW.url
        ;
    );

INSERT INTO vpages(url,html,last) VALUES ('www.example.com://page2' , 'meuk2' , '2002-09-18 23:30:00':: timestamp );
INSERT INTO vpages(url,html,last) VALUES ('www.example.com://page3' , 'meuk3' , '2003-09-18 23:30:00':: timestamp );

INSERT INTO vpages(url,html,last) SELECT pp.url || '/added'::text, pp.html || '.html'::text , pp.last + interval '20 years' FROM vpages pp;
UPDATE vpages SET last = last + interval '-10 years' WHERE url = 'www.example.com://page1' ;

-- Copy does NOT work on views
-- COPY vpages(url,html,last) FROM STDIN;
-- www.example.com://pageX    stdin    2000-09-18 23:30:00
-- \.

SELECT * FROM vpages;

Resultat:

INSERT 0 1
INSERT 0 1
INSERT 0 3
UPDATE 1
              url              |    html    |        last         
-------------------------------+------------+---------------------
 www.example.com://page2       | meuk2      | 2002-09-18 23:30:00
 www.example.com://page3       | meuk3      | 2003-09-18 23:30:00
 www.example.com://page1/added | meuk1.html | 2021-09-18 23:30:00
 www.example.com://page2/added | meuk2.html | 2022-09-18 23:30:00
 www.example.com://page3/added | meuk3.html | 2023-09-18 23:30:00
 www.example.com://page1       | meuk1      | 1991-09-18 23:30:00
(6 rows)

Vyn är nödvändig för att förhindra att omskrivningssystemet går in i rekursion. Konstruktionen av en DELETE-regel lämnas som en övning till läsaren.