Module: Cul::Scv::Hydra::Solrizer::ScvModsFieldable
- Extended by:
- ActiveSupport::Concern
- Includes:
- Solrizer::DefaultDescriptors::Normal
- Included in:
- Datastreams::ModsDocument
- Defined in:
- lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb
Defined Under Namespace
Modules: ClassMethods
Constant Summary collapse
- MODS_NS =
{'mods'=>'http://www.loc.gov/mods/v3'}
Class Method Summary collapse
Instance Method Summary collapse
- #all_subjects(node = mods) ⇒ Object
- #alternative_titles(node = mods) ⇒ Object
- #collections ⇒ Object
- #date_notes(node = mods) ⇒ Object
- #date_range_to_textual_date(start_year, end_year) ⇒ Object
- #dates(node = mods) ⇒ Object
- #formats(node = mods) ⇒ Object
- #item_in_context_url(node = mods) ⇒ Object
- #main_title(node = mods) ⇒ Object
- #mods ⇒ Object
- #names(role_authority = nil, role = nil) ⇒ Object
- #non_date_notes(node = mods) ⇒ Object
- #origin_info_place(node = mods) ⇒ Object
- #origin_info_place_for_display(node = mods) ⇒ Object
- #project_url(node = mods) ⇒ Object
- #projects ⇒ Object
- #repository_code(node = mods) ⇒ Object
- #repository_text(node = mods) ⇒ Object
- #shelf_locators(node = mods) ⇒ Object
- #sort_title(node = mods) ⇒ Object
- #textual_dates(node = mods) ⇒ Object
- #titles(node = mods) ⇒ Object
- #to_solr(solr_doc = {}) ⇒ Object
- #translate_project_title(project_title, type) ⇒ Object
- #translate_repo_marc_code(code, type) ⇒ Object
- #zero_pad_year(year) ⇒ Object
Class Method Details
.normalize(t, strip_punctuation = false) ⇒ Object
397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 397 def self.normalize(t, strip_punctuation=false) # strip whitespace n_t = t.dup.strip # collapse intermediate whitespace n_t.gsub!(/\s+/, ' ') # pull off paired punctuation, and any leading punctuation if strip_punctuation n_t = n_t.sub(/^\((.*)\)$/, "\\1") n_t = n_t.sub(/^\{(.*)\}$/, "\\1") n_t = n_t.sub(/^\[(.*)\]$/, "\\1") n_t = n_t.sub(/^"(.*)"$/, "\\1") n_t = n_t.sub(/^'(.*)'$/, "\\1") n_t = n_t.sub(/^<(.*)>$/, "\\1") #n_t = n_t.sub(/^\p{Ps}(.*)\p{Pe}/u, "\\1") n_t = n_t.sub(/^[[:punct:]]+/, '') # this may have 'created' leading/trailing space, so strip n_t.strip! end n_t end |
Instance Method Details
#all_subjects(node = mods) ⇒ Object
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 233 def all_subjects(node=mods) list_of_subjects = [] node.xpath("./mods:subject/mods:topic", MODS_NS).collect do |n| list_of_subjects << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:subject/mods:geographic", MODS_NS).collect do |n| list_of_subjects << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:subject/mods:name", MODS_NS).collect do |n| list_of_subjects << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:subject/mods:temporal", MODS_NS).collect do |n| list_of_subjects << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:subject/mods:titleInfo", MODS_NS).collect do |n| list_of_subjects << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:subject/mods:genre", MODS_NS).collect do |n| list_of_subjects << ScvModsFieldable.normalize(n.text, true) end return list_of_subjects end |
#alternative_titles(node = mods) ⇒ Object
74 75 76 77 78 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 74 def alternative_titles(node=mods) node.xpath('./mods:titleInfo[@type and (@type="alternative" or @type="abbreviated" or @type="translated" or @type="uniform")]', MODS_NS).collect do |t| ScvModsFieldable.normalize(t.text) end end |
#collections ⇒ Object
36 37 38 39 40 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 36 def collections mods.xpath("./mods:relatedItem[@type='host' and @displayLabel='Collection']", MODS_NS).collect do |p_node| ScvModsFieldable.normalize(main_title(p_node), true) end end |
#date_notes(node = mods) ⇒ Object
201 202 203 204 205 206 207 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 201 def date_notes(node=mods) date_notes = [] node.xpath("./mods:note[@type = 'date' or @type = 'date source']", MODS_NS).collect do |n| date_notes << ScvModsFieldable.normalize(n.text, true) end return date_notes end |
#date_range_to_textual_date(start_year, end_year) ⇒ Object
186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 186 def date_range_to_textual_date(start_year, end_year) start_year = start_year.to_i.to_s # Remove zero-padding if present end_year = end_year.to_i.to_s # Remove zero-padding if present if start_year == end_year return [start_year] else return [('Between ' + (start_year.to_i > 0 ? start_year : start_year[1,start_year.length] + ' BCE') + ' and ' + (end_year.to_i > 0 ? (start_year.to_i > 0 ? end_year : end_year + ' CE') : end_year[1,end_year.length] + ' BCE') )] end end |
#dates(node = mods) ⇒ Object
107 108 109 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 107 def dates(node=mods) # get all the dateIssued with keyDate = 'yes', but not point = 'end' end |
#formats(node = mods) ⇒ Object
111 112 113 114 115 116 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 111 def formats(node=mods) # get all the form values with authority != 'marcform' node.xpath("./mods:physicalDescription/mods:form[@authority != 'marcform']", MODS_NS).collect do |n| ScvModsFieldable.normalize(n.text) end end |
#item_in_context_url(node = mods) ⇒ Object
217 218 219 220 221 222 223 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 217 def item_in_context_url(node=mods) item_in_context_url_val = [] node.xpath("./mods:location/mods:url[@access='object in context' and @usage='primary display']", MODS_NS).collect do |n| item_in_context_url_val << ScvModsFieldable.normalize(n.text, true) end item_in_context_url_val end |
#main_title(node = mods) ⇒ Object
56 57 58 59 60 61 62 63 64 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 56 def main_title(node=mods) # include only the untyped [!@type] titleInfo t = node.xpath('./mods:titleInfo[not(@type)]', MODS_NS).first if t ScvModsFieldable.normalize(t.text) else nil end end |
#mods ⇒ Object
26 27 28 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 26 def mods ng_xml.xpath('/mods:mods', MODS_NS).first end |
#names(role_authority = nil, role = nil) ⇒ 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 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 80 def names(=nil, role=nil) # get all the name nodes # keep all child text except the role terms xpath = "./mods:name" unless .nil? xpath << "/mods:role/mods:roleTerm[@authority='#{.to_s}'" unless role.nil? xpath << " and normalize-space(text()) = '#{role.to_s.strip}'" end xpath << "]/ancestor::mods:name" end names = mods.xpath(xpath, MODS_NS).collect do |node| base_text = node.xpath('./mods:namePart', MODS_NS).collect { |c| c.text }.join(' ') ScvModsFieldable.normalize(base_text, true) end # Note: Removing subject names from name field extraction. # See: https://issues.cul.columbia.edu/browse/DCV-231 and https://issues.cul.columbia.edu/browse/SCV-102 #xpath = "./mods:subject" + xpath[1,xpath.length] #mods.xpath(xpath, MODS_NS).each do |node| # base_text = node.xpath('./mods:namePart', MODS_NS).collect { |c| c.text }.join(' ') # names << ScvModsFieldable.normalize(base_text, true) #end names end |
#non_date_notes(node = mods) ⇒ Object
209 210 211 212 213 214 215 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 209 def non_date_notes(node=mods) non_date_notes = [] node.xpath("./mods:note[not(@type) or (@type != 'date' and @type != 'date source')]", MODS_NS).collect do |n| non_date_notes << ScvModsFieldable.normalize(n.text, true) end return non_date_notes end |
#origin_info_place(node = mods) ⇒ Object
258 259 260 261 262 263 264 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 258 def origin_info_place(node=mods) places = [] node.xpath("./mods:originInfo/mods:place/mods:placeTerm", MODS_NS).collect do |n| places << ScvModsFieldable.normalize(n.text, true) end return places end |
#origin_info_place_for_display(node = mods) ⇒ Object
266 267 268 269 270 271 272 273 274 275 276 277 278 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 266 def origin_info_place_for_display(node=mods) # If there are multiple origin_info place elements, choose only the ones without valueURI attributes. Otherwise show the others. places_with_uri = [] places_without_uri = [] node.xpath("./mods:originInfo/mods:place/mods:placeTerm[@valueURI]", MODS_NS).collect do |n| places_with_uri << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:originInfo/mods:place/mods:placeTerm[not(@valueURI)]", MODS_NS).collect do |n| places_without_uri << ScvModsFieldable.normalize(n.text, true) end return (places_without_uri.length > 0 ? places_without_uri : places_with_uri) end |
#project_url(node = mods) ⇒ Object
225 226 227 228 229 230 231 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 225 def project_url(node=mods) project_url_val = [] node.xpath("./mods:relatedItem[@type='host' and @displayLabel='Project']/mods:location/mods:url", MODS_NS).collect do |n| project_url_val << ScvModsFieldable.normalize(n.text, true) end project_url_val end |
#projects ⇒ Object
30 31 32 33 34 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 30 def projects mods.xpath("./mods:relatedItem[@type='host' and @displayLabel='Project']", MODS_NS).collect do |p_node| ScvModsFieldable.normalize(main_title(p_node), true) end end |
#repository_code(node = mods) ⇒ Object
118 119 120 121 122 123 124 125 126 127 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 118 def repository_code(node=mods) # get the location/physicalLocation[@authority = 'marcorg'] repo_code_node = node.xpath("./mods:location/mods:physicalLocation[@authority = 'marcorg']", MODS_NS).first if repo_code_node ScvModsFieldable.normalize(repo_code_node.text) else return nil end end |
#repository_text(node = mods) ⇒ Object
129 130 131 132 133 134 135 136 137 138 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 129 def repository_text(node=mods) # get the location/physicalLocation[not(@authority)] repo_text_node = node.xpath("./mods:location/mods:physicalLocation[not(@authority)]", MODS_NS).first if repo_text_node ScvModsFieldable.normalize(repo_text_node.text) else return nil end end |
#shelf_locators(node = mods) ⇒ Object
166 167 168 169 170 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 166 def shelf_locators(node=mods) node.xpath("./mods:location/mods:shelfLocator", MODS_NS).collect do |n| ScvModsFieldable.normalize(n.text, true) end end |
#sort_title(node = mods) ⇒ Object
42 43 44 45 46 47 48 49 50 51 52 53 54 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 42 def sort_title(node=mods) # include only the untyped [!@type] titleInfo, exclude noSort base_text = '' t = node.xpath('./mods:titleInfo[not(@type)]', MODS_NS).first if t t.children.each do |child| base_text << child.text unless child.name == 'nonSort' end end base_text = ScvModsFieldable.normalize(base_text, true) base_text = nil if base_text.empty? base_text end |
#textual_dates(node = mods) ⇒ Object
172 173 174 175 176 177 178 179 180 181 182 183 184 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 172 def textual_dates(node=mods) dates = [] node.xpath("./mods:originInfo/mods:dateCreated[not(@keyDate) and not(@point) and not(@w3cdtf)]", MODS_NS).collect do |n| dates << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:originInfo/mods:dateIssued[not(@keyDate) and not(@point) and not(@w3cdtf)]", MODS_NS).collect do |n| dates << ScvModsFieldable.normalize(n.text, true) end node.xpath("./mods:originInfo/mods:dateOther[not(@keyDate) and not(@point) and not(@w3cdtf)]", MODS_NS).collect do |n| dates << ScvModsFieldable.normalize(n.text, true) end return dates end |
#titles(node = mods) ⇒ Object
66 67 68 69 70 71 72 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 66 def titles(node=mods) # all titles without descending into relatedItems # For now, this only includes the main title and selected alternate_titles all_titles = [] all_titles << main_title unless main_title.nil? all_titles += alternative_titles unless alternative_titles.nil? end |
#to_solr(solr_doc = {}) ⇒ Object
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 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 280 def to_solr(solr_doc={}) solr_doc = (defined? super) ? super : solr_doc solr_doc["all_text_teim"] ||= [] solr_doc["title_si"] = sort_title solr_doc["title_ssm"] = titles solr_doc["alternative_title_ssm"] = alternative_titles solr_doc["all_text_teim"] += solr_doc["alternative_title_ssm"] solr_doc["lib_collection_sim"] = collections solr_doc["lib_name_sim"] = names solr_doc["lib_name_teim"] = solr_doc["lib_name_sim"] solr_doc["all_text_teim"] += solr_doc["lib_name_teim"] solr_doc["lib_all_subjects_ssm"] = all_subjects solr_doc["lib_all_subjects_teim"] = solr_doc["lib_all_subjects_ssm"] solr_doc["all_text_teim"] += solr_doc["lib_all_subjects_teim"] solr_doc["lib_name_ssm"] = solr_doc["lib_name_sim"] solr_doc["lib_author_sim"] = names(:marcrelator, 'aut') solr_doc["lib_recipient_sim"] = names(:marcrelator, 'rcp') solr_doc["lib_format_sim"] = formats solr_doc["lib_shelf_sim"] = shelf_locators solr_doc["lib_date_textual_ssm"] = textual_dates solr_doc["lib_date_notes_ssm"] = date_notes solr_doc["lib_non_date_notes_ssm"] = non_date_notes solr_doc["lib_item_in_context_url_ssm"] = item_in_context_url solr_doc["lib_project_url_ssm"] = project_url solr_doc["origin_info_place_ssm"] = origin_info_place solr_doc["origin_info_place_for_display_ssm"] = origin_info_place_for_display repo_marc_code = repository_code unless repo_marc_code.nil? solr_doc["lib_repo_short_ssim"] = [translate_repo_marc_code(repo_marc_code, 'short')] solr_doc["lib_repo_long_sim"] = [translate_repo_marc_code(repo_marc_code, 'long')] solr_doc["lib_repo_full_ssim"] = [translate_repo_marc_code(repo_marc_code, 'full')] end solr_doc["lib_repo_text_ssm"] = repository_text project_titles = projects unless project_titles.nil? solr_doc["lib_project_short_ssim"] = [] solr_doc["lib_project_full_ssim"] = [] project_titles.each {|project_title| solr_doc["lib_project_short_ssim"] << translate_project_title(project_title, 'short') solr_doc["lib_project_full_ssim"] << translate_project_title(project_title, 'full') } solr_doc["lib_project_short_ssim"].uniq! solr_doc["lib_project_full_ssim"].uniq! end # Create convenient start and end date values based on one of the many possible originInfo/dateX elements. possible_start_date_fields = ['origin_info_date_issued_ssm', 'origin_info_date_issued_start_ssm', 'origin_info_date_created_ssm', 'origin_info_date_created_start_ssm', 'origin_info_date_other_ssm', 'origin_info_date_other_start_ssm'] possible_end_date_fields = ['origin_info_date_issued_end_ssm', 'origin_info_date_created_end_ssm', 'origin_info_date_other_end_ssm'] start_date = nil end_date = nil start_year = nil end_year = nil possible_start_date_fields.each{|key| if solr_doc.has_key?(key) start_date = solr_doc[key][0] break end } possible_end_date_fields.each{|key| if solr_doc.has_key?(key) end_date = solr_doc[key][0] break end } if start_date.present? end_date = start_date if end_date.blank? year_regex = /^(-?\d{1,4}).*/ start_year_match = start_date.match(year_regex) if start_year_match && start_year_match.captures.length > 0 start_year = start_year_match.captures[0] start_year = zero_pad_year(start_year) solr_doc["lib_start_date_year_itsi"] = start_year.to_i # TrieInt version for searches end end_year_match = end_date.match(year_regex) if end_year_match && end_year_match.captures.length > 0 end_year = end_year_match.captures[0] end_year = zero_pad_year(end_year) solr_doc["lib_end_date_year_itsi"] = end_year.to_i # TrieInt version for searches end solr_doc["lib_date_year_range_si"] = start_year + '-' + end_year if start_year # When no textual date is available, fall back to other date data (if available) if solr_doc["lib_date_textual_ssm"].blank? solr_doc["lib_date_textual_ssm"] = date_range_to_textual_date(start_year.to_i, end_year.to_i) end end solr_doc.each do |k, v| if self.class.maps_field? k solr_doc[k] = self.class.map_value(k, v) end end solr_doc end |
#translate_project_title(project_title, type) ⇒ Object
154 155 156 157 158 159 160 161 162 163 164 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 154 def translate_project_title(project_title, type) normalized_project_title = ScvModsFieldable.normalize(project_title) if type == 'short' return translate_with_default(SHORT_PROJ, normalized_project_title, normalized_project_title) elsif type == 'full' return translate_with_default(FULL_PROJ, normalized_project_title, normalized_project_title) end return nil end |
#translate_repo_marc_code(code, type) ⇒ Object
140 141 142 143 144 145 146 147 148 149 150 151 152 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 140 def translate_repo_marc_code(code, type) #code = ScvModsFieldable.normalize(code) if type == 'short' return translate_with_default(SHORT_REPO, code, 'Non-Columbia Location') elsif type == 'long' return translate_with_default(LONG_REPO, code, 'Non-Columbia Location') elsif type == 'full' return translate_with_default(FULL_REPO, code, 'Non-Columbia Location') end return nil end |
#zero_pad_year(year) ⇒ Object
386 387 388 389 390 391 392 393 394 395 |
# File 'lib/cul_scv_hydra/solrizer/scv_mods_fieldable.rb', line 386 def zero_pad_year(year) year = year.to_s is_negative = year.start_with?('-') year_without_sign = (is_negative ? year[1, year.length]: year) if year_without_sign.length < 4 year_without_sign = year_without_sign.rjust(4, '0') end return (is_negative ? '-' : '') + year_without_sign end |