nlwiki Pages with the same content

SQL

SELECT p2.page_namespace, p2.page_title, r2.rev_len, r2.rev_timestamp, s2.rev_sha1
FROM `page` p2, `revision` r2, (
	SELECT rev_sha1, COUNT(rev_sha1) 
	FROM (
		SELECT rev_sha1
		FROM `page` p1,`revision` r1
		WHERE 
			page_namespace!=2 AND
      		NOT (page_namespace=4 AND page_title REGEXP 
                 '^Snelcursus_\([A-Za-z_]+\)/Header$|^NeTTies_|^Coachingsprogramma/preload/Coachverzoek/') AND
      		page_latest=rev_id AND 
			rev_len>0 AND
			page_is_redirect=0 AND
			(page_namespace MOD 2)=0 AND
			(page_namespace!=2 OR page_content_model NOT IN ('css','javascript')) AND
			page_namespace!=14) s1
	GROUP BY rev_sha1
	HAVING COUNT(rev_sha1) > 1) s2
WHERE 
	p2.page_latest=r2.rev_id AND
	r2.rev_sha1=s2.rev_sha1
ORDER BY r2.rev_len DESC, s2.rev_sha1, r2.rev_timestamp
LIMIT 1000
SQL

Checking query status...
