Class: Mexico::Fiesta::Interfaces::ElanInterface
- Inherits:
-
Object
- Object
- Mexico::Fiesta::Interfaces::ElanInterface
- Includes:
- Mexico::FileSystem, Singleton
- Defined in:
- lib/mexico/fiesta/interfaces/elan_interface.rb
Constant Summary collapse
- CONSTRAINTS =
{ 'Included_In' => "Time alignable annotations within the parent annotation's time interval, gaps are allowed", 'Time_Subdivision' => "Time subdivision of parent annotation's time interval, no time gaps allowed within this interval", 'Symbolic_Subdivision' => 'Symbolic subdivision of a parent annotation. Annotations refering to the same parent are ordered', 'Symbolic_Association' => '1-1 association with a parent annotation' }
Class Method Summary collapse
Instance Method Summary collapse
Class Method Details
.export(doc, io = $stdout, params = {}) ⇒ Object
41 42 43 |
# File 'lib/mexico/fiesta/interfaces/elan_interface.rb', line 41 def self.export(doc, io=$stdout, params = {}) instance.export(doc, io, params) end |
.import(io = $stdin, params = {}) ⇒ Object
36 37 38 39 |
# File 'lib/mexico/fiesta/interfaces/elan_interface.rb', line 36 def self.import(io=$stdin, params = {}) puts 'class method import' instance.import(io, params) end |
Instance Method Details
#export(doc, io = $stdout, params = {}) ⇒ Object
269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 |
# File 'lib/mexico/fiesta/interfaces/elan_interface.rb', line 269 def export(doc, io=$stdout, params = {}) # Create an XML builder object that serialises into an XML structure builder = Nokogiri::XML::Builder.new do |xml| sec_datamodel = doc.head[Mexico::FileSystem::Section::DATA_MODEL] sec_lifecycle = doc.head[Mexico::FileSystem::Section::LIFECYCLE] date = sec_lifecycle['creationDate'].value = sec_lifecycle['authorKey'].value format = sec_datamodel['annotationToolFormat'].value version = sec_datamodel['annotationToolVersion'].value schema_location = sec_datamodel['xsiNoNamespaceSchemaLocation'].value ad_attrs = { DATE: date, AUTHOR: , FORMAT: format, VERSION: version, 'xmlns:xsi'=>'http://www.w3.org/2001/XMLSchema-instance', 'xsi:noNamespaceSchemaLocation' => schema_location } #xml.root() do #end xml.ANNOTATION_DOCUMENT(ad_attrs) do # @TODO implement the export of the header mediaFile = '' mediaFile = doc.head[Mexico::FileSystem::Section::MEDIA_CONTEXT]['primaryMediaUrl'].value unless doc.head[Mexico::FileSystem::Section::MEDIA_CONTEXT]['primaryMediaUrl'].nil? timeUnits = doc.head[Mexico::FileSystem::Section::DATA_MODEL]['timeUnits'].value xml.HEADER({MEDIA_FILE: mediaFile, TIME_UNITS: timeUnits}) do doc.head[Mexico::FileSystem::Section::MEDIA_CONTEXT]['referencedMedia'].property_maps.each do |m| uri = m['uri'].value path = m['path'].value mimeType = m['mimeType'].value xml.MEDIA_DESCRIPTOR({MEDIA_URL: uri, MIME_TYPE: mimeType, RELATIVE_MEDIA_URL: path}) end end # create the time stamp data structure time_hash = Hash.new counter = 1 # @todo #254 rework to use unit conversions! doc.items.each do |item| item.point_links.each do |pl| unless time_hash.has_key?(pl.point) time_hash[pl.point] = "ts#{counter}" counter += 1 end end item.interval_links.each do |il| unless time_hash.has_key?(il.min) time_hash[il.min] = "ts#{counter}" counter += 1 end unless time_hash.has_key?(il.max) time_hash[il.max] = "ts#{counter}" counter += 1 end end end xml.TIME_ORDER do # collect all timestamps # create a hash for them time_hash.each do |tkey, tval| xml.TIME_SLOT({'TIME_SLOT_ID' => tval, 'TIME_VALUE'=>tkey.to_i.to_s}) end end inverted_time_hash = time_hash.invert # read ling types from map ling_types = Hash.new lt_section = doc.head.section(Mexico::FileSystem::Section::LAYER_TYPES) lt_section.property_maps.each do |pm| key = pm.key puts key pm.properties.each do |p| puts " .. %s -> %s" % [p.key, p.value] end # puts pm.size ling_type = Hash.new if pm.has_key?('constraints') ling_type['constraints'] = pm['constraints'].value end if pm.has_key?('graphicReferences') ling_type['graphicReferences'] = pm['graphicReferences'].value end if pm.has_key?('timeAlignable') ling_type['timeAlignable'] = pm['timeAlignable'].value end if pm.has_key?('controlledVocabulary') ling_type['controlledVocabulary'] = pm['controlledVocabulary'].value end ling_types[key] = ling_type end puts ling_types # export layer by layer # caveat: only annotations with at least one layer link will be exported. # caveat 2: annotations with multiple layer links will be exported multiple times. doc.layers.each do |layer| ling_type = layer.properties['elanTierType'].value ling_type_object = doc.head[Mexico::FileSystem::Section::LAYER_TYPES].property_maps.find{|m| m.key == ling_type} puts "ling type object %s" % ling_type_object constraint = ling_type_object['constraints'] unless constraint.nil? constraint = constraint.value end attrs = {TIER_ID: layer.name, LINGUISTIC_TYPE_REF: ling_type} annotator = layer.properties['annotator'].value attrs.merge!({ANNOTATOR: annotator}) unless annotator.nil? # check if this layer is the child of another one. # if yes: add attribute PARENT_REF # find a parent layer parent_id=nil parent_connectors = doc.layer_connectors.select{|c| c.target == layer} if parent_connectors.size>0 parent_id = parent_connectors.first.source.name attrs.merge!({PARENT_REF: parent_id}) end tier = xml.TIER(attrs) do puts "inside tier" layer.items.each do |item| xml.ANNOTATION do # depending on the layer type, use either ALIGNABLE or REF annotations if %w(Symbolic_Subdivision Symbolic_Association).include?(constraint) ref_attrs = {ANNOTATION_ID: item.identifier} parent_ref = item.item_links.find{|l| l.role == Mexico::FileSystem::ItemLink::ROLE_PARENT} unless parent_ref.nil? ref_attrs.merge!({ANNOTATION_REF: parent_ref.target_item.identifier}) end pre_ref = item.item_links.find{|l| l.role == Mexico::FileSystem::ItemLink::ROLE_PREDECESSOR} unless pre_ref.nil? ref_attrs.merge!({PREVIOUS_ANNOTATION: pre_ref.target_item.identifier}) end xml.REF_ANNOTATION(ref_attrs) do xml.ANNOTATION_VALUE item.data.string_value end else tsref1, tsref2 = nil unless item.interval_links.empty? tsref1 = time_hash[item.interval_links.first.min] tsref2 = time_hash[item.interval_links.first.max] end xml.ALIGNABLE_ANNOTATION({'ANNOTATION_ID'=>item.identifier,TIME_SLOT_REF1: tsref1,TIME_SLOT_REF2: tsref2}) do xml.ANNOTATION_VALUE item.data.string_value end end end end end puts "%s :: %s" % [tier["TIER_ID"], layer.identifier] end # @todo #257 a :: LINGUISTIC_TYPE types = doc.head[Mexico::FileSystem::Section::LAYER_TYPES] types.property_maps.each do |tp| puts tp.class.name puts tp.properties.size puts tp.property_maps.size puts "PROPMAP: %s" % tp.properties.collect{|m| "#{m.key}: #{m.value}"}.join(' ') puts "TIME ALIGNABLE? %s" % tp.has_key?('timeAlignable') puts "TIME ALIGNABLE? %s" % tp['timeAlignable'] # puts "TIME ALIGNABLE? %s" % tp['timeAlignable'].value time_alignable = tp.has_key?('timeAlignable') ? tp['timeAlignable'].value : nil graphic_references = tp.has_key?('graphicReferences') ? tp['graphicReferences'].value : nil controlled_vocabulary_ref = tp.has_key?('controlledVocabulary') ? tp['controlledVocabulary'].value : nil constraints = tp.has_key?('constraints') ? tp['constraints'].value : nil puts "TIME ALIGNABLE? %s" % time_alignable attrs = {LINGUISTIC_TYPE_ID: tp.key} attrs.merge!({ TIME_ALIGNABLE: time_alignable}) unless time_alignable.nil? attrs.merge!({ GRAPHIC_REFERENCES: graphic_references}) unless graphic_references.nil? attrs.merge!({CONTROLLED_VOCABULARY_REF: controlled_vocabulary_ref}) unless controlled_vocabulary_ref.nil? attrs.merge!({ CONSTRAINTS: constraints}) unless constraints.nil? xml.LINGUISTIC_TYPE(attrs) end # Exports ELAN constraints. # These are static, so the same for all documents. Mexico::Fiesta::Interfaces::ElanInterface::CONSTRAINTS.each do |conk,conv| xml.CONSTRAINT STEREOTYPE: conk, DESCRIPTION: conv end # CONTROLLED_VOCABULARY vocs = doc.head[Mexico::FileSystem::Section::VOCABULARIES] vocs.property_maps.each do |voc| = voc['info'] datamap = voc['data'] xml.CONTROLLED_VOCABULARY({CV_ID: voc.key, DESCRIPTION: ['description'].value }) do datamap.property_maps.each do |cv_entry| xml.CV_ENTRY(cv_entry['value'].value, {DESCRIPTION: cv_entry['description'].value}) end end end end end io << builder.to_xml end |
#import(io = $stdin, params = {}) ⇒ Object
45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 |
# File 'lib/mexico/fiesta/interfaces/elan_interface.rb', line 45 def import(io=$stdin, params = {}) io.rewind encoding = params.has_key?(:encoding) ? params[:encoding] : 'UTF-8' xmldoc = ::Nokogiri::XML(io) document = Mexico::FileSystem::FiestaDocument.new sec_datamodel = document.head[Mexico::FileSystem::Section::DATA_MODEL] sec_datamodel.properties << Mexico::FileSystem::Property.new('sourceFormat', 'ELAN/EAF') sec_datamodel.properties << Mexico::FileSystem::Property.new('converterClass', 'Mexico::Fiesta::Interfaces::ElanInterface') # import attributes on root element xmldoc.xpath("/ANNOTATION_DOCUMENT").each do |annodoc| # atts: DATE, AUTHOR, VERSION, FORMAT # xmlns:xsi xsi:noNamespaceSchemaLocation puts xmldoc.namespaces sec_lifecycle = document.head[Mexico::FileSystem::Section::LIFECYCLE] date = DateTime.iso8601(annodoc['DATE']) sec_lifecycle.properties << Mexico::FileSystem::Property.new('creationDate', date) puts date.class.name sec_lifecycle.properties << Mexico::FileSystem::Property.new('authorKey', annodoc['AUTHOR']) sec_datamodel.properties << Mexico::FileSystem::Property.new('annotationToolVersion', annodoc['VERSION']) sec_datamodel.properties << Mexico::FileSystem::Property.new('annotationToolFormat', annodoc['FORMAT']) sec_datamodel.properties << Mexico::FileSystem::Property.new('xmlSchemaDeclaration', xmldoc.namespaces['xmlns:xsi']) sec_datamodel.properties << Mexico::FileSystem::Property.new('xsiNoNamespaceSchemaLocation', annodoc['xsi:noNamespaceSchemaLocation']) annodoc.attributes.each do |a| puts a end end # import heaader # - @MEDIA_FILE # - @TIME_UNITS # - MEDIA DESCRIPTOR # - PROPERTY/@name=lastUsedAnnotationId xmldoc.xpath("//HEADER").each do |header| header['MEDIA_FILE'] header['TIME_UNTIS'] document.head[Mexico::FileSystem::Section::MEDIA_CONTEXT].property_maps << Mexico::FileSystem::PropertyMap.new(key: 'referencedMedia') refMediaMap = document.head[Mexico::FileSystem::Section::MEDIA_CONTEXT].property_maps.find{|m| m.key=='referencedMedia'} datModelSec = document.head[Mexico::FileSystem::Section::DATA_MODEL] refMediaMap.properties << Mexico::FileSystem::Property.new('primaryMediaUrl', header['MEDIA_FILE']) # time units should go into another section! datModelSec.properties << Mexico::FileSystem::Property.new('timeUnits', header['TIME_UNITS']) header.xpath('./MEDIA_DESCRIPTOR').each_with_index do |mediafile,n| file_map = Mexico::FileSystem::PropertyMap.new(key: "#{n}") # prop = Mexico::FileSystem::Property.new('path', mediafile['RELATIVE_MEDIA_URL']) #puts " %s : %s" % [prop.key, prop.value] file_map.properties << Mexico::FileSystem::Property.new('path', mediafile['RELATIVE_MEDIA_URL']) file_map.properties << Mexico::FileSystem::Property.new('mimeType', mediafile['MIME_TYPE']) file_map.properties << Mexico::FileSystem::Property.new('uri', mediafile['MEDIA_URL']) refMediaMap.property_maps << file_map end header.xpath('./PROPERTY').each do |property| datModelSec.properties << Mexico::FileSystem::Property.new(property['NAME'], property.text) end end # actual data: # 1. create a standard timeline timeline = document.add_standard_timeline('s') # 2. find time slots, store timeslots = Hash.new xmldoc.xpath("//TIME_ORDER/TIME_SLOT").each do |t| slot = t["TIME_SLOT_ID"] val = t["TIME_VALUE"].to_i timeslots[slot] = val end # read cv entries # cvs = Hash.new xmldoc.xpath("//CONTROLLED_VOCABULARY").each do |c| container_map = Mexico::FileSystem::PropertyMap.new(key: c['CV_ID']) = Mexico::FileSystem::PropertyMap.new(key: 'info') .properties << Mexico::FileSystem::Property.new('identifier', c['CV_ID']) .properties << Mexico::FileSystem::Property.new('description', c['DESCRIPTION']) valuemap = Mexico::FileSystem::PropertyMap.new(key: 'data') c.xpath("./CV_ENTRY").each do |entry| desc = entry['DESCRIPTION'] val = entry.text valprop = Mexico::FileSystem::PropertyMap.new valprop.properties << Mexico::FileSystem::Property.new('description', desc) valprop.properties << Mexico::FileSystem::Property.new('value', val) valuemap.property_maps << valprop end container_map.property_maps << container_map.property_maps << valuemap document.head.section(Mexico::FileSystem::Section::VOCABULARIES).property_maps << container_map end # Read ling type entries lingTypes = Hash.new xmldoc.xpath("//LINGUISTIC_TYPE").each do |lingtype| cnstrs, cntvoc = nil cnstrs = lingtype['CONSTRAINTS'] unless lingtype['CONSTRAINTS'].nil? graphr = lingtype['GRAPHIC_REFERENCES']=="true" ? true : false lngtid = lingtype['LINGUISTIC_TYPE_ID'] timeal = lingtype['TIME_ALIGNABLE']=="true" ? true : false cntvoc = lingtype['CONTROLLED_VOCABULARY_REF'] unless lingtype['CONTROLLED_VOCABULARY_REF'].nil? lingTypeEntry = { constraints: cnstrs, graphicReferences: graphr, timeAlignable: timeal, controlledVocabulary: cntvoc } lingTypes[lngtid] = lingTypeEntry end lingTypes.each do |key,val| sec = document.head[Mexico::FileSystem::Section::LAYER_TYPES] pmap = Mexico::FileSystem::PropertyMap.new(key: key) val.each do |skey,sval| unless sval.nil? pmap.properties << Mexico::FileSystem::Property::new(skey,sval) end end sec.property_maps << pmap end # create temporary hash for storage of layers layerHash = Hash.new xmldoc.xpath("//TIER").each do |t| # @todo (DEFAULT_LOCALE="en") (LINGUISTIC_TYPE_REF="default-lt") tierID = t["TIER_ID"] puts 'Read layers, %s' % tierID layer = document.add_layer(identifier: tierID, name: tierID) #layer.name = tierID #layer.id = ToE::Util::to_xml_id(tierID) layer.add_property Mexico::FileSystem::Property.new('elanTierType', t['LINGUISTIC_TYPE_REF']) if t.attributes.has_key?('ANNOTATOR') layer.add_property Mexico::FileSystem::Property.new('annotator', t['ANNOTATOR']) end # document.layers << layer puts "Attributes: %s" % t.attributes.to_s puts "Parent ref? %s" % t.attributes.has_key?('PARENT_REF') if t.attributes.has_key?('PARENT_REF') # puts "TATT: %s" % t['PARENT_REF'] # document.layers.each do |l| # puts "LAYER %s %s" % [l.identifier, l.name] # end puts 'ID of parent layer %s' % t['PARENT_REF'] puts 'ID, xmlified %s' % Mexico::Util::to_xml_id(t['PARENT_REF']) puts 'available ids: %s' % (document.layers.collect{|l| l.identifier}).join(' ') parent_layer = document.get_layer_by_id(Mexico::Util::to_xml_id(t['PARENT_REF'])) puts "Found parent layer: %s" % parent_layer if parent_layer layer_connector = Mexico::FileSystem::LayerConnector.new parent_layer, layer, { identifier: "#{parent_layer.identifier}_TO_#{layer.identifier}", role: 'PARENT_CHILD', document: document } document.add_layer_connector(layer_connector) end end layerHash[tierID] = layer t.xpath("./ANNOTATION").each do |annoContainer| annoContainer.xpath("child::*").each do |anno| annoVal = anno.xpath("./ANNOTATION_VALUE/text()").first.to_s i = document.add_item identifier: anno["ANNOTATION_ID"] if anno.name == "ALIGNABLE_ANNOTATION" # puts anno.xpath("./ANNOTATION_VALUE/text()").first if annoVal!=nil # && annoVal.strip != "" i.add_interval_link Mexico::FileSystem::IntervalLink.new(identifier: "#{i.identifier}-int", min: timeslots[anno["TIME_SLOT_REF1"]].to_f, max: timeslots[anno["TIME_SLOT_REF2"]].to_f, target_object: timeline) end end if anno.name == "REF_ANNOTATION" #puts pp anno #puts document.items.collect{|x| x.identifier}.join(', ') #puts '-'*80 i.add_item_link Mexico::FileSystem::ItemLink.new(identifier: "#{i.identifier}-itm", target_object: document.items({identifier: anno["ANNOTATION_REF"]}).first, role: Mexico::FileSystem::ItemLink::ROLE_PARENT) # @todo add previous anno if present if anno.has_attribute?('PREVIOUS_ANNOTATION') i.add_item_link Mexico::FileSystem::ItemLink.new(identifier: "#{i.identifier}-pre", target_object: document.items({identifier: anno["PREVIOUS_ANNOTATION"]}).first, role: Mexico::FileSystem::ItemLink::ROLE_PREDECESSOR) end end i.add_layer_link Mexico::FileSystem::LayerLink.new(identifier: "#{i.identifier}-lay", target_object: layer) i.data = Mexico::FileSystem::Data.new(string_value: annoVal) end end #if t["PARENT_REF"] # parent = layerHash[t["PARENT_REF"]] # if parent # document.layer_connectors << Mexico::FileSystem::LayerConnector.new(parent, layer) # # structure.connect(parent, layer) # end #end end puts 'instance method over' document end |