Created
October 31, 2013 14:23
-
-
Save cjcolvar/7250652 to your computer and use it in GitHub Desktop.
A script which will clean up an exported avalon fedora object to prepare it to become a fixture
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
require 'nokogiri' | |
require 'open-uri' | |
require 'base64' | |
filename = ARGV[0] | |
f = File.new filename | |
doc = Nokogiri::XML::Document.parse f | |
f.close | |
#Get rid of Audit trail | |
doc.xpath("//foxml:datastream[@ID='AUDIT']").each {|n| n.remove()} | |
#Keep only the last version of a datastream | |
doc.xpath("//foxml:datastreamVersion[position() < last()]").each {|n| n.remove()} | |
doc.xpath("//foxml:datastreamVersion").each do |n| | |
n.remove_attribute("CREATED") | |
n.remove_attribute("SIZE") | |
n["ID"] = n["ID"].gsub(/\.[1-9]+/,".0") | |
end | |
#set all datastreams versionable false | |
doc.xpath("//foxml:datastream").each {|n| n["VERSIONABLE"] = "false"} | |
#change M datastreams to X for type xml | |
doc.xpath("//foxml:datastreamVersion[@MIMETYPE='text/xml']/..").each {|ds| ds["CONTROL_GROUP"] = "X"} | |
#Decode binaryContent | |
nodeset = doc.xpath("//foxml:datastreamVersion[@MIMETYPE='text/xml']/foxml:binaryContent/..") | |
nodeset.each do |node| | |
childdoc = Nokogiri::XML::DocumentFragment.parse Base64.decode64(node.content.gsub(/\s+/,'')) | |
node.children = '<xmlContent>' #This is getting transformed to xmlcontent and fedora is complaining!!! | |
node.child.children = childdoc | |
node.child.child.traverse {|n| n.namespace = nil} | |
end | |
#HACK mods datastreams don't have xsi namespace declared | |
doc.xpath("//mods").each {|ds| ds["xmlns:xsi"] = "http://www.w3.org/2001/XMLSchema-instance"} | |
newfilename = "#{File.dirname(filename)}/#{File.basename(filename, File.extname(filename))}.edit#{File.extname(filename)}" | |
f2 = File.new newfilename, 'w+' | |
f2.write doc.to_s.gsub('xmlcontent','xmlContent').gsub(/^\s*$\n/, '') #HACK fix for xmlContent and cleanup nokogiri's blank lines | |
f2.close |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment