Class: Dor::ContentMetadataDS
- Inherits:
-
ActiveFedora::OmDatastream
- Object
- ActiveFedora::OmDatastream
- Dor::ContentMetadataDS
- Includes:
- Upgradable, SolrDocHelper
- Defined in:
- lib/dor/datastreams/content_metadata_ds.rb
Instance Method Summary collapse
- #add_file(file, resource_name) ⇒ Object
- #add_resource(files, resource_name, position, type = "file") ⇒ Object
- #move_resource(resource_name, new_position) ⇒ Object
- #public_xml ⇒ Object
- #remove_file(file_name) ⇒ Object
- #remove_resource(resource_name) ⇒ Object
- #rename_file(old_name, new_name) ⇒ Object
-
#set_content_type(old_type, old_resource_type, new_type, new_resource_type) ⇒ Object
Set the content type to and the resource types for all resources.
-
#to_solr(solr_doc = Hash.new, *args) ⇒ Object
Terminology-based solrization is going to be painfully slow for large contentMetadata streams.
- #update_attributes(file_name, publish, shelve, preserve) ⇒ Object
- #update_file(file, old_file_id) ⇒ Object
- #update_resource_label(resource_name, new_label) ⇒ Object
- #update_resource_type(resource, new_type) ⇒ Object
Methods included from SolrDocHelper
Methods included from Upgradable
add_upgrade_callback, included, run_upgrade_callbacks, #upgrade!
Instance Method Details
#add_file(file, resource_name) ⇒ Object
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 44 def add_file(file, resource_name) xml=self.ng_xml resource_nodes = xml.search('//resource[@id=\''+resource_name+'\']') if resource_nodes.length==0 raise 'resource doesnt exist.' end node=resource_nodes.first file_node=Nokogiri::XML::Node.new('file',xml) file_node['id']=file[:name] file_node['shelve']=file[:shelve] ? file[:shelve] : '' file_node['publish']=file[:publish] ? file[:publish] : '' file_node['preserve']=file[:preserve] ? file[:preserve] : '' node.add_child(file_node) if file[:md5] checksum_node=Nokogiri::XML::Node.new('checksum',xml) checksum_node['type']='md5' checksum_node.content=file[:md5] file_node.add_child(checksum_node) end if file[:sha1] checksum_node=Nokogiri::XML::Node.new('checksum',xml) checksum_node['type']='sha1' checksum_node.content=file[:sha1] file_node.add_child(checksum_node) end if file[:size] file_node['size']=file[:size] end if file[:mime_type] file_node['mimetype']=file[:mime_type] end self.content=xml.to_s self.save end |
#add_resource(files, resource_name, position, type = "file") ⇒ Object
80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 80 def add_resource(files,resource_name, position,type="file") xml=self.ng_xml if xml.search('//resource[@id=\''+resource_name+'\']').length>0 raise 'resource '+resource_name+' already exists' end node=nil max=-1 xml.search('//resource').each do |node| if node['sequence'].to_i>max max=node['sequence'].to_i end end #renumber all of the resources that will come after the newly added one while max>position do node=xml.search('//resource[@sequence=\'' + position + '\']') if node.length>0 node=node.first node[sequence]=max+1 end max=max-1 end node=Nokogiri::XML::Node.new('resource',xml) node['sequence']=position.to_s node['id']=resource_name node['type']=type files.each do |file| file_node=Nokogiri::XML::Node.new('file',xml) %w[shelve publish preserve].each {|x| file_node[x] = file[x.to_sym] ? file[x.to_sym] : '' } file_node['id'] = file[:name] node.add_child(file_node) [:md5, :sha1].each { |algo| next if file[algo].nil? checksum_node = Nokogiri::XML::Node.new('checksum',xml) checksum_node['type'] = algo.to_s checksum_node.content = file[algo] file_node.add_child(checksum_node) } file_node['size'] = file[:size] if file[:size] end xml.search('//contentMetadata').first.add_child(node) self.content=xml.to_s self.save end |
#move_resource(resource_name, new_position) ⇒ Object
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 268 def move_resource resource_name, new_position xml=self.ng_xml file_node=xml.search('//resource[@id=\''+resource_name+'\']') if(file_node.length!=1) raise 'Resource not found or duplicate found.' end position=file_node.first['sequence'].to_i #is the resource being moved earlier in the sequence or later? new_position=new_position.to_i if new_position>position counter=position while true if counter == position break end item=xml.search('/resource[@id=\''+counter.to_s+'\']').first counter=counter+1 item['sequence']=counter.to_s end else counter=position while true if counter == new_position break end item=xml.search('/resource[@id=\''+counter.to_s+'\']').first counter=counter-1 item['sequence']=counter.to_s end end end |
#public_xml ⇒ Object
36 37 38 39 40 41 42 43 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 36 def public_xml result = self.ng_xml.clone result.xpath('/contentMetadata/resource[not(file[(@deliver="yes" or @publish="yes")])]').each { |n| n.remove } result.xpath('/contentMetadata/resource/file[not(@deliver="yes" or @publish="yes")]').each { |n| n.remove } result.xpath('/contentMetadata/resource/file').xpath('@preserve|@shelve|@publish|@deliver').each { |n| n.remove } result.xpath('/contentMetadata/resource/file/checksum').each { |n| n.remove } result end |
#remove_file(file_name) ⇒ Object
149 150 151 152 153 154 155 156 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 149 def remove_file file_name xml=self.ng_xml xml.search('//file[@id=\''+file_name+'\']').each do |node| node.remove end self.content=xml.to_s self.save end |
#remove_resource(resource_name) ⇒ Object
126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 126 def remove_resource resource_name xml=self.ng_xml position=-1 resources=xml.search('//resource[@id=\''+resource_name+'\']') if resources.length!=1 raise 'Resource is missing or duplicated!' end position=resources.first['sequence'] resources.first.remove position=position.to_i+1 while true res=xml.search('//resource[@sequence=\''+position.to_s+'\']') if(res.length==0) break end res['sequence']=position.to_s position=position+1 end self.content=xml.to_s self.save end |
#rename_file(old_name, new_name) ⇒ Object
235 236 237 238 239 240 241 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 235 def rename_file old_name, new_name xml=self.ng_xml file_node=xml.search('//file[@id=\''+old_name+'\']').first file_node['id']=new_name self.content=xml.to_s self.save end |
#set_content_type(old_type, old_resource_type, new_type, new_resource_type) ⇒ Object
Set the content type to and the resource types for all resources
302 303 304 305 306 307 308 309 310 311 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 302 def set_content_type old_type, old_resource_type, new_type, new_resource_type xml=self.ng_xml xml.search('/contentMetadata[@type=\''+old_type+'\']').each do |node| node['type']=new_type xml.search('//resource[@type=\''+old_resource_type+'\']').each do |resource| resource['type']=new_resource_type end end self.content=xml.to_s end |
#to_solr(solr_doc = Hash.new, *args) ⇒ Object
Terminology-based solrization is going to be painfully slow for large contentMetadata streams. Just select the relevant elements instead.
189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 189 def to_solr(solr_doc=Hash.new, *args) doc = self.ng_xml if doc.root['type'] shelved_file_count=0 content_file_count=0 resource_type_counts={} resource_count=0 preserved_size=0 first_shelved_image=nil add_solr_value(solr_doc, "content_type", doc.root['type'], :string, [:facetable, :symbol]) doc.xpath('contentMetadata/resource').sort { |a,b| a['sequence'].to_i <=> b['sequence'].to_i }.each do |resource| resource_count+=1 if(resource['type']) if resource_type_counts[resource['type']] resource_type_counts[resource['type']]+=1 else resource_type_counts[resource['type']]=1 end end resource.xpath('file').each do |file| content_file_count+=1 if file['shelve'] == 'yes' shelved_file_count+=1 if first_shelved_image.nil? && file['id'].match(/jp2$/) first_shelved_image=file['id'] end end if file['preserve'] == 'yes' preserved_size += file['size'].to_i end end end add_solr_value(solr_doc, "content_file_count", content_file_count.to_s, :string, [:searchable, :displayable]) add_solr_value(solr_doc, "shelved_content_file_count", shelved_file_count.to_s, :string, [:searchable, :displayable]) add_solr_value(solr_doc, "resource_count", resource_count.to_s, :string, [:searchable, :displayable]) add_solr_value(solr_doc, "preserved_size", preserved_size.to_s, :string, [:searchable, :displayable]) resource_type_counts.each do |key, count| add_solr_value(solr_doc, "resource_types", key, :string, [:symbol]) add_solr_value(solr_doc, key+"_resource_count", count.to_s, :string, [:searchable, :displayable]) end unless first_shelved_image.nil? add_solr_value(solr_doc, "first_shelved_image", first_shelved_image, :string, [:displayable]) end end solr_doc end |
#update_attributes(file_name, publish, shelve, preserve) ⇒ Object
157 158 159 160 161 162 163 164 165 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 157 def update_attributes file_name, publish, shelve, preserve xml=self.ng_xml file_node=xml.search('//file[@id=\''+file_name+'\']').first file_node['shelve' ]=shelve file_node['publish' ]=publish file_node['preserve']=preserve self.content=xml.to_s self.save end |
#update_file(file, old_file_id) ⇒ Object
166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 166 def update_file file, old_file_id xml=self.ng_xml file_node=xml.search('//file[@id=\''+old_file_id+'\']').first file_node['id']=file[:name] [:md5, :sha1].each { |algo| next if file[algo].nil? checksum_node = xml.search('//file[@id=\''+old_file_id+'\']/checksum[@type=\'' + algo.to_s + '\']').first if checksum_node.nil? checksum_node = Nokogiri::XML::Node.new('checksum',xml) file_node.add_child(checksum_node) end checksum_node['type'] = algo.to_s checksum_node.content = file[algo] } [:size, :shelve, :preserve, :publish].each{ |x| file_node[x.to_s] = file[x] if file[x] } self.content=xml.to_s self.save end |
#update_resource_label(resource_name, new_label) ⇒ Object
243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 243 def update_resource_label resource_name, new_label xml=self.ng_xml resource_node=xml.search('//resource[@id=\''+resource_name+'\']') if(resource_node.length!=1) raise 'Resource not found or duplicate found.' end labels=xml.search('//resource[@id=\''+resource_name+'\']/label') if(labels.length==0) #create a label label_node = Nokogiri::XML::Node.new('label',xml) label_node.content=new_label resource_node.first.add_child(label_node) else labels.first.content=new_label end end |
#update_resource_type(resource, new_type) ⇒ Object
259 260 261 262 263 264 265 266 |
# File 'lib/dor/datastreams/content_metadata_ds.rb', line 259 def update_resource_type resource, new_type xml=self.ng_xml resource_node=xml.search('//resource[@id=\''+resource_name+'\']') if(resource_node.length!=1) raise 'Resource not found or duplicate found.' end resource_node.first['type']=new_type end |