trwiki: distribution of article size

SQL

USE trwiki_p;

-- articles and disambiguation pages
-- SELECT ROUND(page_len, -2) AS bucket, COUNT(page_id) AS cnt FROM page WHERE page_is_redirect!=1 AND page_namespace=0 GROUP BY bucket;

-- articles only
-- SELECT ROUND(page_len, -2) AS bucket, COUNT(page_id) AS cnt FROM page WHERE page_namespace=0 AND page_is_redirect!=1 AND page_id NOT IN (SELECT pp_page FROM page_props WHERE pp_propname='disambiguation') GROUP BY bucket;
SELECT page_len AS bucket, COUNT(page_id) AS cnt FROM page WHERE page_namespace=0 AND page_is_redirect!=1 AND page_id NOT IN (SELECT pp_page FROM page_props WHERE pp_propname='disambiguation') GROUP BY bucket;

-- disambiguation pages only
-- SELECT ROUND(page_len, -2) AS bucket, COUNT(page_id) AS cnt FROM page WHERE page_namespace=0 AND page_is_redirect!=1 AND page_id IN (SELECT pp_page FROM page_props WHERE pp_propname='disambiguation') GROUP BY bucket;
SQL

Checking query status...
