Last active
April 17, 2021 08:59
-
-
Save yuiseki/ca02942c588912815880f358568707a9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# wikibase-dump-filter claim transformer | |
# Requirements | |
# - jq | |
# - wikidata-cli | |
# Usage: | |
# ./wdfc.sh '国籍:日本&職業:政治家&~死亡年月日' | |
# cat humans.ndjson | wikibase-dump-filter --claim `./wdfc.sh '国籍:日本&職業:政治家&~死亡年月日'` > politicians_japan.ndjson | |
# See also: | |
# wikibase-dump-filter | |
# https://github.com/maxlath/wikibase-dump-filter | |
# wikidata-cli | |
# https://github.com/maxlath/wikibase-cli | |
# TODO: support or operator | |
#if [[ $1 == *"|"* ]] || [[ $1 == *","* ]]; then | |
#fi | |
declare -a claims=(); | |
claims=$(echo $1 | tr '&' ' '); | |
transformed=; | |
wdprop () { | |
wd props -l ja $1 | jq -r 'to_entries[] | select(.value == "'$1'") | .key' | |
} | |
for claim in ${claims[@]}; | |
do | |
declare -a claim_split=(); | |
declare property; | |
declare qualifier; | |
if [[ $claim == *":"* ]]; then | |
claim_split=($(echo $claim | tr ':' ' ')); | |
property="${claim_split[0]}"; | |
qualifier="${claim_split[1]}"; | |
property_id=`wdprop $property` | |
qualifier_id=`wd id -l ja $qualifier` | |
if [ -z "$transformed" ]; then | |
transformed="$property_id:$qualifier_id" | |
else | |
transformed="$transformed&$property_id:$qualifier_id" | |
fi | |
else | |
if [[ $claim == *"~"* ]]; then | |
property=$(echo $claim | tr -d '~'); | |
property_id=`wdprop $property` | |
if [ -z "$transformed" ]; then | |
transformed="~$property_id" | |
else | |
transformed="$transformed&~$property_id" | |
fi | |
fi | |
fi | |
done | |
echo $transformed | |
exit 0; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment