dor-services 5.0.2 → 5.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f18cae14cad4e7d46c99fd2805fb8517ef0d4020
-  data.tar.gz: 853c360a25789be6c4d541e20ddd5f875bf9aaca
+  metadata.gz: 220d7103c61a4210c39dd0a7d7f92f08c1fc3b16
+  data.tar.gz: 7ed5456b52b9d10a701b36a3c82e02189589e806
 SHA512:
-  metadata.gz: 06e4ded70b6d91f0751240b1b122260c6ac0d7994405e9e37b2192e83655235ad807d377a80114449ef3db79741b3d4084cc373d88bee1a495670fbed16822ac
-  data.tar.gz: 1624211169fdcfb9f7da970bb614a0f5e3d9704f9e551acde3d497c4f22b178f8c5a8c92c7aade636cf10c4fdf03387aba196b2d178029a4d8688ff90da665c0
+  metadata.gz: c419b64ebe780589176fa5bd7a9b77bc4b8dbade3899710e9984af0d42469327bfa62efda0d7565e9f59a9792ba82238f9e4a59d4410865c5871bbaa84c488a7
+  data.tar.gz: 074921fed0d04103962f77d87e96d39235ff693a04c7d439b0f76e906f8977a8f47a9c71b37e43607164bfdebc5bffdded6f622b026811329bc36e7685222f03

data/config/dev_console_env.rb

@@ -37,8 +37,8 @@ Dor::Config.configure do
     local_document_cache_root '/purl/document_cache'
   end
 
-  gsearch.url 'https://dor-dev.stanford.edu/solr/gsearch'
-  solrizer.url 'https://dor-dev.stanford.edu/solr'
+  gsearch.url 'https://sul-dor-dev.stanford.edu/solr/gsearch'
+  solrizer.url 'https://sul-dor-dev.stanford.edu/solr'
   workflow.url 'https://lyberservices-dev.stanford.edu/workflow/'
   dor_services.url 'https://dorAdmin:dorAdmin@sul-lyberservices-dev.stanford.edu/dor/v1'
 

data/config/dev_console_env.rb.example

@@ -9,8 +9,8 @@ Dor::Config.configure do
 
   ssl do
     cert_file File.join(cert_dir,"robots-dor-dev.crt")
-    key_file File.join(cert_dir,"robots-dor-dev.key")
-    key_pass ''
+    key_file  File.join(cert_dir,"robots-dor-dev.key")
+    key_pass  ''
   end
 
   suri do
@@ -22,7 +22,7 @@ Dor::Config.configure do
   end
 
   metadata do
-    exist.url 'http://server/exist/rest/'
+    exist.url   'http://server/exist/rest/'
     catalog.url 'http://lyberservices-prod.stanford.edu/catalog/mods'
   end
 
@@ -37,24 +37,24 @@ Dor::Config.configure do
     local_document_cache_root '/purl'
   end
 
-  gsearch.url 'https://host/solr/gsearch'
-  solrizer.url 'https://host/solr'
-  workflow.url 'https://host/workflow/'
+  gsearch.url      'https://host/solr/gsearch'
+  solrizer.url     'https://host/solr'
+  workflow.url     'https://host/workflow/'
   dor_services.url 'https://host/dor/v1'
 
   cleanup do
     local_workspace_root '/dor/workspace'
-    local_export_home '/dor/export'
+    local_export_home    '/dor/export'
   end
 
   sdr do
     local_workspace_root '/dor/workspace'
-    local_export_home '/dor/export'
+    local_export_home    '/dor/export'
     datastreams do
-      contentMetadata 'required'
-      descMetadata 'required'
-      identityMetadata 'required'
-      provenanceMetadata 'required'
+      contentMetadata      'required'
+      descMetadata         'required'
+      identityMetadata     'required'
+      provenanceMetadata   'required'
       relationshipMetadata 'required'
       rightsMetadata 'optional'
       sourceMetadata 'optional'
@@ -63,4 +63,4 @@ Dor::Config.configure do
 
   accessioning_robot_sleep_time 30
 
-end
+end

data/lib/dor/models/governable.rb

@@ -9,7 +9,7 @@ module Dor
     end
 
     def initiate_apo_workflow(name)
-      self.initialize_workflow(name, 'dor', !self.new_object?)
+      self.initialize_workflow(name, !self.new_object?)
     end
 
     # Returns the default lane_id from the item's APO.  Will return 'default' if the item does not have

data/lib/dor/models/processable.rb

@@ -209,14 +209,14 @@ module Dor
     #  It will set the priorty of the new workflow to the current_priority if it is > 0
     #  It will set lane_id from the item's APO default workflow lane
     # @param [String] name of the workflow to be initialized
-    # @param [String] repo name of the repository to create workflow for
     # @param [Boolean] create_ds create a 'workflows' datastream in Fedora for the object
-    def initialize_workflow(name, repo='dor', create_ds=true, priority=0)
+    # @param [Integer] priority the workflow's priority level
+    def initialize_workflow(name, create_ds=true, priority=0)
       priority = workflows.current_priority if priority == 0
       opts = { :create_ds => create_ds }
       opts[:priority] = priority if(priority > 0)
       opts[:lane_id] = default_workflow_lane
-      Dor::WorkflowService.create_workflow(repo, self.pid, name, Dor::WorkflowObject.initial_workflow(name), opts)
+      Dor::WorkflowService.create_workflow(Dor::WorkflowObject.initial_repo(name), self.pid, name, Dor::WorkflowObject.initial_workflow(name), opts)
     end
 
 

data/lib/dor/models/releasable.rb

@@ -1,3 +1,6 @@
+require 'open-uri'
+require 'retries'
+
 module Dor
   module Releasable
     extend ActiveSupport::Concern
@@ -8,7 +11,7 @@ module Dor
     #@return [String] The XML release node as a string, with ReleaseDigest as the root document
     def generate_release_xml
       builder = Nokogiri::XML::Builder.new do |xml|
-        xml.ReleaseDigest {
+        xml.ReleaseData {
           self.released_for.each do |project,released_value|
             xml.release(released_value["release"],:to=>project)
           end  
@@ -52,6 +55,9 @@ module Dor
         end
         
       end
+      
+      #See what the application is currently released for on Purl.  If something is released in purl but not listed here, it needs to be added as a false
+      released_hash = self.add_tags_from_purl(released_hash)
         
       return released_hash
     end
@@ -254,7 +260,7 @@ module Dor
     #
     #@params tag [Boolean] True or false for the release node
     #@params attrs [hash]  A hash of any attributes to be placed onto the tag 
-    # release tag example:
+    #@example
     #  item.add_tag(true,:release,{:tag=>'Fitch : Batch2',:what=>'self',:to=>'Searchworks',:who=>'petucket'})
     def add_release_node(release, attrs={})
       identity_metadata_ds = self.identityMetadata
@@ -305,6 +311,86 @@ module Dor
       end
       return return_hash
     end
+    
+    #Get a list of all release nodes found in a purl document
+    #
+    #@params druid [String]
+    #
+    #@raises [OpenURI::HTTPError]
+    #
+    #Fetches purl xml for a druid
+    #
+    #@return [Nokogiri::HTML::Document] the parsed xml for the druid or an empty document if no purl is found
+    def get_xml_from_purl
+        handler = Proc.new do |exception, attempt_number, total_delay|
+          #We assume a 404 means the document has never been published before and thus has no purl
+          #The strip is needed before the actual message is "404 "
+          return Nokogiri::HTML::Document.new if exception.message.strip == "404"
+        end
+
+        with_retries(:max_retries => 5, :base_sleep_seconds => 3, :max_sleep_seconds=> 5, :rescue => OpenURI::HTTPError, :handler => handler) {
+           #If you change the method used for opening the webpage, you can change the :rescue param to handle the new method's errors
+           return Nokogiri::HTML(open(self.form_purl_url))
+         }
+       
+    end
+    
+    #Since purl does not use the druid: prefix but much of dor does, use this function to strip the druid: if needed
+    #
+    #@return [String] the druid sans the druid: or if there was no druid: prefix, the entire string you passed
+    def remove_druid_prefix
+      druid_prefix = "druid:"
+      return self.id.split(druid_prefix)[1] if self.id.split(druid_prefix).size > 1
+      return druid
+    end
+    
+    #Take the and create the entire purl url that will usable for the open method in open-uri, returns http
+    #
+    #params druid [String], the druid without or without the driud prefix
+    #
+    #return [String], the full url
+    def form_purl_url
+      prefix = "http://" 
+      return prefix + Dor::Config.stacks.document_cache_host + "/#{self.remove_druid_prefix}.xml"
+    end
+    
+    #Pull all release nodes from the public xml obtained via the purl query
+    #
+    #@params druid [Nokogiri::HTML::Document] The druid of the object you want
+    #
+    #@return [Array] An array containing all the release tags 
+    def get_release_tags_from_purl_xml(doc)
+      nodes = doc.xpath("//html/body/publicobject/releasedata").children 
+      #We only want the nodes with a name that isn't text
+      return_array = []
+      nodes.each do |n|
+        return_array << n.attr('to') if n.name != nil and n.name.downcase != "text"
+      end
+      return return_array.uniq 
+    end
+    
+    #Pull all release nodes from the public xml obtained via the purl query
+    #
+    #@return [Array] An array containing all the release tags 
+    def get_release_tags_from_purl
+      xml = self.get_xml_from_purl
+      return self.get_release_tags_from_purl_xml(xml)
+    end
+    
+    #This function calls purl and gets a list of all release tags currently in purl.  It then compares to the list you have generated.
+    #Any tag that is on purl, but not in the newly generated list is added to the new list with a value of false.
+    #
+    #params new_tags [Hash] a hash of all new tags in the form of {Project => Boolean}, where Project is a string
+    #
+    #return [Hash], a hash in the same form as new_tags, with all missing tags not in new_tags, but in current_tag_names, added in with a Boolean value of false
+    def add_tags_from_purl(new_tags) 
+      tags_currently_in_purl = self.get_release_tags_from_purl
+      missing_tags = tags_currently_in_purl.map(&:downcase) - new_tags.keys.map(&:downcase) 
+      missing_tags.each do |missing_tag|
+        new_tags[missing_tag.capitalize] = false
+      end
+      return new_tags
+    end
 
   end
 end

data/lib/dor/models/versionable.rb

@@ -33,7 +33,7 @@ module Dor
       if opts.has_key?(k)
         # During local development, Hydrus (or some other app running Fedora locally)
         # does not want this call to initialize the workflows datastream.
-        initialize_workflow('versioningWF', 'dor', opts[k])
+        initialize_workflow('versioningWF', opts[k])
       else
         initialize_workflow('versioningWF')
       end

data/lib/dor/models/workflow_object.rb

@@ -6,6 +6,7 @@ module Dor
     include SolrDocHelper
     include Governable
     @@xml_cache = {}
+    @@repo_cache = {}
 
     has_object_type 'workflow'
     has_metadata :name => "workflowDefinition", :type => Dor::WorkflowDefinitionDs, :label => 'Workflow Definition'
@@ -13,8 +14,8 @@ module Dor
     def self.find_by_name(name, opts={})
       Dor.find_all(%{#{Solrizer.solr_name "objectType", :facetable}:"#{self.object_type}" #{Solrizer.solr_name "workflow_name", :symbol}:"#{name}"}, opts).first
     end
-    
-    # Searches for the workflow definition object in DOR, then 
+
+    # Searches for the workflow definition object in DOR, then
     # returns an object's initial workflow as defined in the worfklowDefinition datastream
     # It will cache the result for subsequent requests
     # @param [String] name the name of the workflow
@@ -22,19 +23,29 @@ module Dor
     def self.initial_workflow(name)
       return @@xml_cache[name] if(@@xml_cache.include?(name))
 
-      wobj = self.find_by_name(name)
-      wf_xml = wobj.generate_initial_workflow
-      @@xml_cache[name] = wf_xml
+      self.find_and_cache_workflow_xml_and_repo name
+      @@xml_cache[name]
+    end
+
+    # Returns the repository attribute from the workflow definition
+    # It will cache the result for subsequent requests
+    # @param [String] name the name of the workflow
+    # @return [String] the initial workflow xml
+    def self.initial_repo(name)
+      return @@repo_cache[name] if(@@repo_cache.include?(name))
+
+      self.find_and_cache_workflow_xml_and_repo name
+      @@repo_cache[name]
     end
 
     def definition
       datastreams['workflowDefinition']
     end
-    
+
     def graph *args
       self.definition.graph *args
     end
-    
+
     def to_solr solr_doc=Hash.new, *args
       super solr_doc, *args
       client = Dor::WorkflowService.workflow_resource
@@ -50,5 +61,14 @@ module Dor
 
     alias_method :generate_intial_workflow, :generate_initial_workflow
 
+    # Searches DOR for the workflow definition object.  It then caches the workflow repository and xml
+    # @param [String] naem the name of the workflow
+    def self.find_and_cache_workflow_xml_and_repo name
+      wobj = self.find_by_name(name)
+      wf_xml = wobj.generate_initial_workflow
+      @@repo_cache[name] = wobj.definition.repo
+      @@xml_cache[name] = wf_xml
+    end
+
   end
 end

data/lib/dor/services/registration_service.rb

@@ -105,7 +105,7 @@ module Dor
         workflow_priority = params[:workflow_priority] ? params[:workflow_priority].to_i : 0
 
         Array(params[:seed_datastream]).each { |datastream_name| new_item.build_datastream(datastream_name) }
-        Array(params[:initiate_workflow]).each { |workflow_id| new_item.initialize_workflow(workflow_id, 'dor', !new_item.new_object?, workflow_priority)}
+        Array(params[:initiate_workflow]).each { |workflow_id| new_item.initialize_workflow(workflow_id, !new_item.new_object?, workflow_priority)}
 
         new_item.assert_content_model
 

data/lib/dor/services/sdr_ingest_service.rb

@@ -36,7 +36,7 @@ module Dor
       bagger.create_tagfiles
       verify_bag_structure(bag_dir)
       # Now bootstrap SDR workflow. but do not create the workflows datastream
-      dor_item.initialize_workflow('sdrIngestWF', 'sdr', false)
+      dor_item.initialize_workflow('sdrIngestWF', false)
     rescue Exception => e
       raise LyberCore::Exceptions::ItemError.new(druid, "Export failure", e)
     end

data/lib/dor/version.rb

@@ -1,3 +1,3 @@
 module Dor
-  VERSION = '5.0.2'
+  VERSION = '5.1.0'
 end

data/lib/dor/workflow/document.rb

@@ -15,6 +15,7 @@ module Workflow
         t.elapsed(:path=>{:attribute=>"elapsed"})
         t.lifecycle(:path=>{:attribute=>"lifecycle"})
         t.attempts(:path=>{:attribute=>"attempts"}, :index_as => [:not_searchable])
+        t.version(:path=>{:attribute=>"version"})
       }
     end
     @@definitions={}
@@ -30,9 +31,10 @@ module Workflow
     def priority
       processes.map {|proc| proc.priority.to_i }.detect(0) {|p| p > 0}
     end
-    
+
+    # @return [Boolean] if any process node does not have version, returns true, false otherwise (all processes have version)
     def active?
-      processes.any? { |proc| !proc.version }
+      ng_xml.at_xpath("/workflow/process[not(@version)]") ? true : false
     end
 
     def definition
@@ -66,7 +68,8 @@ module Workflow
       if ng_xml.search("/workflow/process").length == 0
         return []
       end
-      @processes ||= if self.definition
+      @processes ||=
+      if self.definition
         self.definition.processes.collect do |process|
           node = ng_xml.at("/workflow/process[@name = '#{process.name}']")
           process.update!(node,self) unless node.nil?

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dor-services
 version: !ruby/object:Gem::Version
-  version: 5.0.2
+  version: 5.1.0
 platform: ruby
 authors:
 - Michael Klein
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-09 00:00:00.000000000 Z
+date: 2015-04-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: active-fedora
@@ -322,6 +322,20 @@ dependencies:
     - - '='
       - !ruby/object:Gem::Version
         version: 2.3.5
+- !ruby/object:Gem::Dependency
+  name: retries
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: dor-workflow-service
   requirement: !ruby/object:Gem::Requirement
@@ -348,14 +362,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '0.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '0.4'
 - !ruby/object:Gem::Dependency
   name: lyber-utils
   requirement: !ruby/object:Gem::Requirement