dor-services 4.23.0 → 4.24.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d050e71f1ce1735d4e070bd9c0691eedd1595a15
-  data.tar.gz: 82d30bbd2dff8a7f134438d637c5b552ac11e0f0
+  metadata.gz: ff429d637d033e04e1198d20958bcbd6a472629c
+  data.tar.gz: 4622fda379fcf8ee34a99a5814194dbe27145d52
 SHA512:
-  metadata.gz: 9b76b3ab3b360bb28904d6391c0e325694b036be58195dd84d6952a3ef3bd1d723dae7c49bbd18fc9380e05af088297184f6bdaea2e1f896555ab7dd7e657db2
-  data.tar.gz: 4b29c83f8f57629d9003033e454055114f1abb530c6d5f515081fc71937d158593a30dd5d86b0d712d7907085b27356f3770049c40590bfeaa1d17941815de23
+  metadata.gz: ec37f7bc75c22027ccb685ef9addd75845f0e09d943ed829a5aa9a2f1bc5a666672761cb0f8a5eafeda0f30576f41a48eddcb5b00cbce18aa6883423ef85b85b
+  data.tar.gz: b6b11408363316db445e6114ebbed7e991d21d44bfcd790060218bb72b41af591ce918b21a8ccde0e53524d32607a80cd24cf7b853b8c1bc87ba3adf5bec442f

data/config/config_defaults.yml

@@ -65,3 +65,7 @@
   :shift_age: weekly
 :dor_services:
   :url:
+:indexing_svc:
+  :log: 'log/indexing_svc.log'
+  :log_date_format_str: '%Y-%m-%d %H:%M:%S.%L'
+  :log_rotation_interval: 'daily'

data/lib/dor-services.rb

@@ -132,6 +132,7 @@ module Dor
 
   # Services
   autoload :SearchService, 'dor/services/search_service'
+  autoload :IndexingService, 'dor/services/indexing_service'
   autoload :MetadataService, 'dor/services/metadata_service'
   autoload :RegistrationService, 'dor/services/registration_service'
   autoload :SuriService, 'dor/services/suri_service'

data/lib/dor/datastreams/content_metadata_ds.rb

@@ -143,8 +143,10 @@ module Dor
     # @return [Nokogiri::XML::Element] the new resource that was added to the contentMetadata
     #
     def add_virtual_resource(child_druid, child_resource)
+      fail ArgumentError, 'Parent must have existing contentMetadata' if self.ng_xml.nil? || self.ng_xml.root.nil?
+
       # create a virtual resource element with attributes linked to the child and omit label
-      sequence_max = self.ng_xml.search('//resource').map{ |node| node[:sequence].to_i }.max
+      sequence_max = self.ng_xml.search('//resource').map{ |node| node[:sequence].to_i }.max || 0
       resource = Nokogiri::XML::Element.new('resource', self.ng_xml)
       resource[:sequence] = sequence_max + 1
       resource[:id] = "#{self.pid.gsub(/^druid:/, '')}_#{resource[:sequence]}"
@@ -157,7 +159,7 @@ module Dor
       resource << generate_also_available_as_node(child_druid)
       
       # save the virtual resource as a sibling and return
-      self.ng_xml.root << resource
+      self.content = (self.ng_xml.root << resource).to_xml
       resource
     end
 

data/lib/dor/services/indexing_service.rb

@@ -0,0 +1,64 @@
+module Dor
+  class IndexingService
+    ##
+    # Returns a Logger instance for recording info about indexing attempts
+    # @yield attempt to execute 'entry_id_block' and use the result as an extra identifier for the log
+    #   entry.  a placeholder will be used otherwise. 'request.uuid' might be useful in a Rails app.
+    def self.generate_index_logger(&entry_id_block)
+      index_logger = Logger.new(Config.indexing_svc.log, Config.indexing_svc.log_rotation_interval)
+      index_logger.formatter = proc do |severity, datetime, progname, msg|
+        date_format_str = Config.indexing_svc.log_date_format_str
+        entry_id = begin entry_id_block.call rescue '---' end
+        "[#{entry_id}] [#{datetime.utc.strftime(date_format_str)}] #{msg}\n"
+      end
+      index_logger
+    end
+
+    # memoize the loggers we create in a hash, init with a nil default logger
+    @@loggers = { default: nil }
+
+    def self.default_index_logger
+      @@loggers[:default] ||= generate_index_logger
+    end
+
+    # takes a Dor object and indexes it to solr.  doesn't commit automatically.
+    def self.reindex_object(obj)
+      solr_doc = obj.to_solr
+      Dor::SearchService.solr.add(solr_doc)
+      solr_doc
+    end
+
+    # retrieves a single Dor object by pid, indexes the object to solr, does some logging
+    # (will use a defualt logger if one is not provided).  doesn't commit automatically.
+    #
+    # WARNING/TODO:  the tests indicate that the "rescue Exception" block at the end will
+    # get skipped, and the thrown exception (e.g. SystemStackError) will not be logged.  since
+    # that's the only consequence, and the exception bubbles up as we would want anyway, it
+    # doesn't seem worth blocking refactoring.  see https://github.com/sul-dlss/dor-services/issues/156
+    # extra logging in this case would be nice, but centralized indexing that's otherwise
+    # fully functional is nicer.
+    def self.reindex_pid(pid, index_logger = nil, should_raise_errors = true)
+      index_logger ||= default_index_logger
+      obj = Dor.load_instance pid
+      solr_doc = reindex_object obj
+      index_logger.info "updated index for #{pid}"
+      solr_doc
+    rescue StandardError => se
+      if se.is_a? ActiveFedora::ObjectNotFoundError
+        index_logger.warn "failed to update index for #{pid}, object not found in Fedora"
+      else
+        index_logger.warn "failed to update index for #{pid}, unexpected StandardError, see main app log: #{se.backtrace}"
+      end
+      raise se if should_raise_errors
+    rescue Exception => ex
+      index_logger.error "failed to update index for #{pid}, unexpected Exception, see main app log: #{ex.backtrace}"
+      raise ex # don't swallow anything worse than StandardError
+    end
+
+    # given a list of pids, retrieve those objects from fedora, index each to solr, optionally commit
+    def self.reindex_pid_list(pid_list, should_commit = false)
+      pid_list.each { |pid| reindex_pid pid, nil, false } # use the default logger, don't let individual errors nuke the rest of the batch
+      ActiveFedora.solr.conn.commit if should_commit
+    end
+  end
+end

data/lib/dor/version.rb

@@ -1,3 +1,3 @@
 module Dor
-  VERSION = '4.23.0'
+  VERSION = '4.24.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dor-services
 version: !ruby/object:Gem::Version
-  version: 4.23.0
+  version: 4.24.0
 platform: ruby
 authors:
 - Michael Klein
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-02-08 00:00:00.000000000 Z
+date: 2016-02-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: active-fedora
@@ -591,6 +591,7 @@ files:
 - lib/dor/services/cleanup_reset_service.rb
 - lib/dor/services/cleanup_service.rb
 - lib/dor/services/digital_stacks_service.rb
+- lib/dor/services/indexing_service.rb
 - lib/dor/services/merge_service.rb
 - lib/dor/services/metadata_handlers/catalog_handler.rb
 - lib/dor/services/metadata_handlers/mdtoolkit_handler.rb