Check the Wikidata Lexeme JSON dumps each Thursday

check-lexeme-json-dumps

#!/bin/bash

set -e

cd "$HOME/wikibase-validate-dump"

export https_proxy=http://webproxy:8080
git fetch
if [[ ! "$(git log HEAD..origin/master)" == "" ]]; then
	echo "New commits, please rebase:"
	git log --format=oneline HEAD..origin/master
fi

echo
echo

dumpDate="$(date --date 'last Wednesday' +"%Y%m%d")"
php validateJsonDump.php compress.zlib:///mnt/data/xmldatadumps/public/other/wikibase/wikidatawiki/"$dumpDate"/wikidata-"$dumpDate"-lexemes.json.gz

crontab

[email protected]
30 10 * * 4 nice -n19 bash $HOME/bin/check-lexeme-json-dumps