bulk_ops 0.1.19 → 0.1.20

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 980d5fec0bcc94d2199356f379adeb0cee99a748b159a5b7d2934e26bdf53c9d
-  data.tar.gz: c4c6ef9e463d35fd408ac6c477a47bee55eb7833c374269e4bc3a98d881713b2
+  metadata.gz: b0f3d62a2115d7a69c05a8aac7e13f1badda13bc587474884a089e456c460b96
+  data.tar.gz: 3c7027bc6bade6fa01198b4a89675f1fc78b21140042befb52c3219afc92b66d
 SHA512:
-  metadata.gz: d9511dad25f5d1f489ad08415b7750fd2264d214b057ea9b2af0fbd2ee83998cbb25f631b8e1432b958bd0a90c85a4507cbc363e21316e981090aa6b42697215
-  data.tar.gz: 90df61d91db0671690c2fc8199d75feadea833c5ee23e8e4778c855f7a36297cec3ea191741b33d1ad1409e4d43020888fc37f037280de7f0578b9cda285159d
+  metadata.gz: 2f1381ef24e117468a3aa134ae19ed64b50c7d37ae0657fc31e06e830ef33471fc2cd35a407d63d5e362b4ba88f24cdfb8b462da55e957f289be3461b27273ce
+  data.tar.gz: 91f4661e005d422c39417fa9d6b94d0d4f85d3b8b4f5ca5da375294fbba7b02116c01854aaa1cf30e77326eb44d318e205be38aa7ee4f96516c50caa786dad5f

data/lib/bulk_ops/operation.rb

@@ -102,7 +102,7 @@ module BulkOps
         proxy.update(message: "interpreted at #{DateTime.now.strftime("%d/%m/%Y %H:%M")} " + proxy.message)
         data = BulkOps::Parser.new(proxy, @metadata).interpret_data(raw_row: values)
         next unless proxy.proxy_errors.blank?
-        BulkOps::CreateWorkJob.perform_later(proxy.work_type || "Work",
+        BulkOps::WorkJob.perform_later(proxy.work_type || "Work",
                                              user.email,
                                              data,
                                              proxy.id,

data/lib/bulk_ops/parser.rb

@@ -7,8 +7,14 @@ class BulkOps::Parser
 
   def self.is_file_set? metadata, row_number
     return false unless metadata[row_number].present?
-#    If there are any valid fields other than relationship or file fields, it is a work
+    # If the work type is explicitly specified, use that
+    if (type_key = metadata.keys.find{|key| key.downcase.gsub(/[_\-\s]/,"").include?("worktype") })
+      return true if metadata[type_key].downcase == "fileset" 
+      return false if metadata[type_key].present?
+    end
+#    Otherwise, if there are any valid fields other than relationship or file fields, call it a work
     metadata[row_number].each do |field, value|
+      return true if 
       next if BulkOps::Verification.is_file_field?(field)
       next if ["parent", "order"].include?(normalize_relationship_field_name(field))
       next if ["title","label"].include?(field.downcase.strip)
@@ -39,6 +45,7 @@ class BulkOps::Parser
     interpret_file_fields
     interpret_controlled_fields
     interpret_scalar_fields
+    connect_existing_work 
     @proxy.update(status: "ERROR", message: "error parsing spreadsheet line") if @parsing_errors.present?
     @proxy.proxy_errors = (@proxy.proxy_errors || []) + @parsing_errors
     return @metadata
@@ -57,6 +64,21 @@ class BulkOps::Parser
     @raw_row = row
   end
 
+  def connect_existing_work
+    return unless (column_name = operation.options["update_identifier"])
+    return unless (key = @raw_row.keys.find{|key| key.to_s.parameterize.downcase.gsub("_","") == column_name.to_s.parameterize.downcase.gsub("_","")})
+    return unless (value = @raw_row[key])
+    return unless (work_id = find_work_id_from_unique_metadata(key, value)) 
+    proxy.update(work_id: work_id)
+  end
+
+  def find_work_id_from_unique_metadata field_name, value
+    field_solr_name = schema.get_field(field_name).solr_name
+    query = "_query_:\"{!raw f=#{field_name}}#{value}\""
+    response = ActiveFedora::SolrService.instance.conn.get(ActiveFedora::SolrService.select_path, params: { fq: query, rows: 1, start: 0})["response"]
+    return response["docs"][0]["id"]
+  end
+
   def interpret_controlled_fields 
     
     # The labels array tracks the contents of columns marked as labels,

data/lib/bulk_ops/version.rb

@@ -1,3 +1,3 @@
 module BulkOps
-  VERSION = "0.1.19"
+  VERSION = "0.1.20"
 end

data/lib/bulk_ops/work_job.rb

@@ -60,6 +60,20 @@ class BulkOps::WorkJob < ActiveJob::Base
 
   private
 
+
+  def define_work
+    if proxy.work_id.present? && record_exists? proxy.work_id
+      begin
+        @work = ActiveFedora::Base.find(@work_proxy.work_id)
+      rescue ActiveFedora::ObjectNotFoundError
+        report_error "Could not find work to update in Fedora (though it shows up in Solr). Work id: #{@work_proxy.work_id}"
+        return false
+      end
+    else
+      @work = workClass.capitalize.constantize.new
+    end
+  end
+
   def record_exists? id
     begin
       return true if SolrDocument.find(id)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bulk_ops
 version: !ruby/object:Gem::Version
-  version: 0.1.19
+  version: 0.1.20
 platform: ruby
 authors:
 - Ned Henry, UCSC Library Digital Initiatives
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-10-16 00:00:00.000000000 Z
+date: 2019-11-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails