Skip to content

Fix Wikidata subclass query #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 12 additions & 11 deletions wikidata/2019_subclassof_tree.sql
Original file line number Diff line number Diff line change
@@ -1,34 +1,35 @@
CREATE OR REPLACE TABLE `wikidata.subclasses_20190822`
CREATE OR REPLACE TABLE `wikidata.subclasses_2019`
AS

SELECT a.*, b.en_label subclass_of_label, 1 level
FROM (
SELECT a.numeric_id, en_label, b.numeric_id subclass_of_numeric_id
FROM `fh-bigquery.wikidata.wikidata_latest_20190822` a, UNNEST(a.subclass_of) b
FROM `fh-bigquery.wikidata.wikidata_2019` a, UNNEST(a.subclass_of) b
WHERE a.type = 'item'
) a
JOIN `fh-bigquery.wikidata.wikidata_latest_20190822` b
ON a.subclass_of_numeric_id=b.numeric_id
JOIN `fh-bigquery.wikidata.wikidata_2019` b
ON a.subclass_of_numeric_id = b.numeric_id AND b.type = 'item'
;

LOOP
BEGIN
DECLARE row_count INT64;
DECLARE row_diff INT64;
SET row_count = (SELECT COUNT(*) FROM `wikidata.subclasses_20190822`)
SET row_count = (SELECT COUNT(*) FROM `wikidata.subclasses_2019`)
;


INSERT INTO `wikidata.subclasses_20190822`
INSERT INTO `wikidata.subclasses_2019`

SELECT a.numeric_id, a.en_label, b.subclass_of_numeric_id, b.subclass_of_label, MIN(b.level+1) level
FROM `wikidata.subclasses_20190822` a
JOIN `wikidata.subclasses_20190822` b
SELECT a.numeric_id, a.en_label, b.subclass_of_numeric_id, b.subclass_of_label, MIN(a.level + b.level) level
FROM `wikidata.subclasses_2019` a
JOIN `wikidata.subclasses_2019` b
ON a.subclass_of_numeric_id = b.numeric_id
WHERE STRUCT(a.numeric_id,b.subclass_of_numeric_id) NOT IN (SELECT STRUCT(numeric_id,subclass_of_numeric_id) FROM `wikidata.subclasses_20190822`)
WHERE STRUCT(a.numeric_id,b.subclass_of_numeric_id) NOT IN (SELECT STRUCT(numeric_id,subclass_of_numeric_id) FROM `wikidata.subclasses_2019`)
GROUP BY 1,2,3,4
;

SET row_diff = (SELECT COUNT(*) FROM `wikidata.subclasses_20190822`) - row_count;
SET row_diff = (SELECT COUNT(*) FROM `wikidata.subclasses_2019`) - row_count;
IF row_diff = 0 THEN
LEAVE;
END IF;
Expand Down