Last active
July 3, 2023 18:27
-
-
Save timtomch/a9aa8d1b9079c93159589e51c02d7ef6 to your computer and use it in GitHub Desktop.
Count Smithsonian objects and list rights available in freetext element
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/zsh | |
# This script needs to be run inside the Smithsonian institution folder (where all the 00.txt, 01.txt, ... files are) | |
setopt extendedglob | |
echo "Records of type ead_component: " | |
for file in ^index.txt | |
do | |
cat $file |jq -c '. | select(.type=="ead_component") | .id' | wc -l | |
done | awk '{sum += $1} END {print sum}' | |
echo "\nRecords of type edanmdm with images: " | |
edanrecords=$(for file in ^index.txt | |
do | |
cat $file |jq -c '. | select((.type=="edanmdm") and (.content.descriptiveNonRepeating.online_media.mediaCount>0)) | .id' | wc -l | |
done | awk '{sum += $1} END {print sum}') | |
echo $edanrecords | |
if [ $edanrecords -gt 0 ] | |
then | |
echo "\nRights present for edanmdm records in content.freetext.objectRights:\n" | |
for file in ^index.txt | |
do | |
cat $file |jq -c '. | select((.type=="edanmdm") and (.content.descriptiveNonRepeating.online_media.mediaCount>0) and (.content.freetext.objectRights!=null)) | .content.freetext.objectRights[].content' | |
done | sort | uniq -c | |
echo "\nRights present in content.descriptiveNonRepeating.online_media.media.usage.access:\n" | |
for file in ^index.txt | |
do | |
cat $file |jq -c '. | select((.type=="edanmdm") and (.content.descriptiveNonRepeating.online_media.mediaCount>0) and (.content.descriptiveNonRepeating.online_media.media[].usage!=null)) | .content.descriptiveNonRepeating.online_media.media[].usage.access' | |
done | sort | uniq -c | |
fi |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment