Untitled query #1276

SQL

# See also https://upload.wikimedia.org/wikipedia/commons/f/f7/MediaWiki_1.24.1_database_schema.svg
#
use wikidatawiki_p; 
SELECT SUBSTRING_INDEX(CONCAT(term_text, ' '), ' ', 1) AS label, COUNT(*) As freq,
term_language As lang,
CURRENT_DATE
FROM pagelinks As pl1, wb_terms, wb_entity_per_page

	LEFT JOIN ( SELECT pl_from FROM pagelinks WHERE pl_title = 'P735' AND pl_namespace = 120 ) As allitemswithP735
	ON epp_page_id = allitemswithP735.pl_from WHERE allitemswithP735.pl_from IS NULL
AND pl1.pl_title = 'P27' 
AND pl1.pl_namespace = 120 
AND pl1.pl_from = epp_page_id
AND epp_entity_type = 'item'
AND term_entity_id = epp_entity_id
AND term_type = 'label'
AND term_entity_type = 'item' 
AND term_language = 'fr'

 AND term_text not RLike '^.. .'  #DJ, Li, Wu, Yu, El, Oh, Ma
 AND term_text Not Like 'The %'
# Asian family names
 AND term_text Not Like 'Kim %'
 AND term_text Not Like 'Lee %'
 AND term_text Not Like 'Park %'
 AND term_text Not Like 'Zhang %'
 AND term_text Not Like 'Choi %'
 AND term_text Not Like 'Wang %'
 AND term_text Not Like 'Liu %'
 AND term_text Not Like 'Chen %'
 AND term_text Not Like 'Han %'
 AND term_text Not Like 'Len %'
 AND term_text Not Like 'Rui %'
 AND term_text Not Like 'Cho %'
 AND term_text Not Like 'Lim %'
 AND term_text Not Like 'Yoon %'
 AND term_text Not Like 'Hang %'
 AND term_text Not Like 'Hwang %'
 AND term_text Not Like 'Yang %'


# prefix
 AND term_text Not Like 'Sir %'
 AND term_text Not Like 'Master %'
 AND term_text Not Like 'Prince %'
 AND term_text Not Like 'Junior %'
 AND term_text Not Like 'Lady %'
 AND term_text Not Like 'Saint %'
GROUP BY SUBSTRING_INDEX(CONCAT(term_text, ' '), ' ', 1)
HAVING COUNT(*)>49
SQL

Checking query status...
