Created
April 22, 2019 19:49
-
-
Save aelkiss/df6a4fd0117c15e6abceadf102c2edc7 to your computer and use it in GitHub Desktop.
Convert HathiTrust IDs to GRIN volume IDs
This file contains hidden or 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
#!ruby | |
grin_ids = { | |
'uc1' => 'UCAL', | |
'hvd' => 'Harvard', | |
'uva' => 'UVA', | |
'mdp' => 'UOM', | |
'nnc1' => 'Columbia', | |
'uiug' => 'UIUC', | |
'pur1' => 'PURD', | |
'chi' => 'CHI', | |
'wu' => 'Wisc', | |
'nyp' => 'NYPL', | |
'pst' => 'PSU', | |
'ucm' => 'UCM', | |
'coo' => 'Cornell', | |
'ien' => 'NWU', | |
'njp' => 'PRNC', | |
'inu' => 'IND', | |
'umn' => 'MINN', | |
'keio' => 'Keio', | |
'osu' => 'OSU', | |
'msu' => 'MSU', | |
'iau' => 'IOWA' | |
} | |
STDIN.each do |line| | |
fields = line.strip.split("\t") | |
namespace = fields.shift | |
id = fields.shift | |
next unless grin_ids[namespace] | |
grin_id = case id | |
when /^31822\d{9}$/ then 'UCSD' | |
when /^l\d{10}$/, /^31158\d{9}$/ then 'UCLA' | |
when /^32106\d{9}$/ then 'UCSC' | |
when /^31378\d{9}$/ then 'UCSF' | |
when /^31175\d{9}$/ then 'UCD' | |
when /^31210\d{9}$/ then 'UCD' | |
when /^[bcd]\d{9}$/ then 'UCBK' | |
when /^(a{1,3}|ax|[bcd]|cc)\d{10}$/ then 'SRLF' | |
else grin_ids[namespace] | |
end | |
puts "#{grin_id}:#{id.upcase} " + fields.join("\t") | |
end | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment