Class: Stanford::Mods::Record
- Inherits:
-
Mods::Record
- Object
- Mods::Record
- Stanford::Mods::Record
- Defined in:
- lib/stanford-mods.rb,
lib/stanford-mods/searchworks.rb
Instance Method Summary collapse
-
#additional_authors_w_dates ⇒ Object
all names, in display form, except the main_author names will be the display_value_w_date form see Mods::Record.name in nom_terminology for details on the display_value algorithm.
-
#catkey ⇒ String
Value with the numeric catkey in it, or nil if none exists.
- #druid ⇒ Object
- #druid=(new_druid) ⇒ Object
-
#era_facet ⇒ Array<String>
subject/temporal values with trailing comma, semicolon, and backslash (and any preceding spaces) removed.
-
#format ⇒ Array[String]
deprecated
Deprecated.
-
kept for backwards compatibility but not part of SW UI redesign work Summer 2014
-
-
#format_main ⇒ Array[String]
select one or more format values from the controlled vocabulary per JVine Summer 2014 searchworks-solr-lb.stanford.edu:8983/solr/select?facet.field=format_main_ssim&rows=0&facet.sort=index.
-
#geographic_facet ⇒ Array<String>
geographic_search values with trailing comma, semicolon, and backslash (and any preceding spaces) removed.
-
#geographic_search ⇒ Array<String>
Values are the contents of: subject/geographic subject/hierarchicalGeographic subject/geographicCode (only include the translated value if it isn’t already present from other mods geo fields).
-
#get_bc_year(dates) ⇒ Object
get the 3 digit BC year, return it as a negative, so -700 for 300 BC.
-
#get_double_digit_century(dates) ⇒ Object
get a double digit century like ‘12th century’ from the date array.
-
#get_plain_four_digit_year(dates) ⇒ Object
get a 4 digit year like 1865 from the date array.
-
#get_single_digit_century(dates) ⇒ Object
get a single digit century like ‘9th century’ from the date array.
-
#get_three_digit_year(dates) ⇒ Object
get a 3 digit year like 965 from the date array.
-
#get_u_year(dates) ⇒ Object
If a year has a “u” in it, replace instances of u with 0.
- #is_date?(object) ⇒ Boolean
- #is_number?(object) ⇒ Boolean
-
#main_author_w_date ⇒ String
the first encountered <mods><name> element with marcrelator flavor role of ‘Creator’ or ‘Author’.
- #main_author_w_date_test ⇒ Object
-
#place ⇒ Object
—- PUBLICATION (place, year) —-.
-
#pub_date ⇒ String
The year the object was published, , filtered based on max_pub_date and min_pub_date from the config file.
- #pub_date_display ⇒ Object
-
#pub_date_facet ⇒ Array[String]
Values for the pub date facet.
- #pub_date_groups(year) ⇒ Array<String> deprecated Deprecated.
-
#pub_date_sort ⇒ Object
creates a date suitable for sorting.
-
#pub_dates ⇒ Array<String>
get the dates from dateIssued, and dateCreated merged into 1 array.
-
#pub_year ⇒ String
Get the publish year from mods.
-
#subject_all_search ⇒ Array<String>
Values are the contents of: all subject subelements except subject/cartographic plus genre top level element.
-
#subject_names ⇒ Object
convenience method for subject/name/namePart values (to avoid parsing the mods for the same thing multiple times).
-
#subject_occupations ⇒ Object
convenience method for subject/occupation values (to avoid parsing the mods for the same thing multiple times).
-
#subject_other_search ⇒ Array<String>
Values are the contents of: subject/name subject/occupation - no subelements subject/titleInfo.
-
#subject_other_subvy_search ⇒ Array<String>
Values are the contents of: subject/temporal subject/genre.
-
#subject_temporal ⇒ Object
convenience method for subject/temporal values (to avoid parsing the mods for the same thing multiple times).
-
#subject_titles ⇒ Object
convenience method for subject/titleInfo values (to avoid parsing the mods for the same thing multiple times).
-
#subject_topics ⇒ Object
convenience method for subject/topic values (to avoid parsing the mods for the same thing multiple times).
-
#sw_addl_authors ⇒ Array<String>
Values for author_7xx_search field.
-
#sw_addl_titles ⇒ Array<String>
this includes all titles except.
-
#sw_corporate_authors ⇒ Array<String>
Values for author_corp_display.
-
#sw_full_title ⇒ String
Value for title_245_search, title_full_display.
-
#sw_full_title_without_commas ⇒ Object
deprecated
Deprecated.
in favor of sw_title_display
-
#sw_genre ⇒ Array[String]
return values for the genre facet in SearchWorks.
-
#sw_geographic_search(sep = ' ') ⇒ Array<String>
Values are the contents of: subject/geographic subject/hierarchicalGeographic subject/geographicCode (only include the translated value if it isn’t already present from other mods geo fields).
-
#sw_impersonal_authors ⇒ Array<String>
return the display_value_w_date for all <mods><name> elements that do not have type=‘personal’.
-
#sw_language_facet ⇒ Object
include langagues known to SearchWorks; try to error correct when possible (e.g. when ISO-639 disagrees with MARC standard).
-
#sw_logger ⇒ Object
—- end PUBLICATION (place, year) —-.
-
#sw_main_author ⇒ String
Value for author_1xx_search field.
-
#sw_meeting_authors ⇒ Array<String>
Values for author_meeting_display.
-
#sw_person_authors ⇒ Array<String>
Values for author_person_facet, author_person_display.
-
#sw_short_title ⇒ String
Value for title_245a_search field.
-
#sw_sort_author ⇒ String
Returns a sortable version of the main_author: main_author + sorting title which is the mods approximation of the value created for a marc record.
-
#sw_sort_title ⇒ String
Returns a sortable version of the main title.
-
#sw_subject_names(sep = ', ') ⇒ Array<String>
Values are the contents of: subject/name/namePart “Values from namePart subelements should be concatenated in the order they appear (e.g. ”Shakespeare, William, 1564-1616“)”.
-
#sw_subject_titles(sep = ' ') ⇒ Array<String>
Values are the contents of: subject/titleInfo/(subelements).
-
#sw_title_display ⇒ String
like sw_full_title without trailing ,/;:.
-
#topic_facet ⇒ Array<String>
Values are the contents of: subject/topic subject/name subject/title subject/occupation with trailing comma, semicolon, and backslash (and any preceding spaces) removed.
-
#topic_search ⇒ Array<String>
Values are the contents of: mods/genre mods/subject/topic.
Instance Method Details
#additional_authors_w_dates ⇒ Object
all names, in display form, except the main_author
names will be the display_value_w_date form
see Mods::Record.name in nom_terminology for details on the display_value algorithm
39 40 41 42 43 44 45 46 |
# File 'lib/stanford-mods.rb', line 39 def results = [] @mods_ng_xml.plain_name.each { |n| results << n.display_value_w_date } results.delete() results end |
#catkey ⇒ String
Returns value with the numeric catkey in it, or nil if none exists.
664 665 666 667 668 669 670 |
# File 'lib/stanford-mods/searchworks.rb', line 664 def catkey catkey=self.term_values([:record_info,:recordIdentifier]) if catkey and catkey.length>0 return catkey.first.gsub('a','') #need to ensure catkey is numeric only end nil end |
#druid ⇒ Object
674 675 676 |
# File 'lib/stanford-mods/searchworks.rb', line 674 def druid @druid ? @druid : 'Unknown item' end |
#druid=(new_druid) ⇒ Object
671 672 673 |
# File 'lib/stanford-mods/searchworks.rb', line 671 def druid= new_druid @druid=new_druid end |
#era_facet ⇒ Array<String>
subject/temporal values with trailing comma, semicolon, and backslash (and any preceding spaces) removed
303 304 305 |
# File 'lib/stanford-mods/searchworks.rb', line 303 def era_facet subject_temporal.map { |val| val.sub(/[\\,;]$/, '').strip } unless !subject_temporal end |
#format ⇒ Array[String]
-
kept for backwards compatibility but not part of SW UI redesign work Summer 2014
select one or more format values from the controlled vocabulary here:
http://searchworks-solr-lb.stanford.edu:8983/solr/select?facet.field=format&rows=0&facet.sort=index
532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 |
# File 'lib/stanford-mods/searchworks.rb', line 532 def format val = [] types = self.term_values(:typeOfResource) if types genres = self.term_values(:genre) issuance = self.term_values([:origin_info,:issuance]) types.each do |type| case type when 'cartographic' val << 'Map/Globe' when 'mixed material' val << 'Manuscript/Archive' when 'moving image' val << 'Video' when 'notated music' val << 'Music - Score' when 'software, multimedia' val << 'Computer File' when 'sound recording-musical' val << 'Music - Recording' when 'sound recording-nonmusical', 'sound recording' val << 'Sound Recording' when 'still image' val << 'Image' when 'text' val << 'Book' if issuance and issuance.include? 'monographic' book_genres = ['book chapter', 'Book chapter', 'Book Chapter', 'issue brief', 'Issue brief', 'Issue Brief', 'librettos', 'Librettos', 'project report', 'Project report', 'Project Report', 'technical report', 'Technical report', 'Technical Report', 'working paper', 'Working paper', 'Working Paper'] val << 'Book' if genres and !(genres & book_genres).empty? conf_pub = ['conference publication', 'Conference publication', 'Conference Publication'] val << 'Conference Proceedings' if genres and !(genres & conf_pub).empty? val << 'Journal/Periodical' if issuance and issuance.include? 'continuing' article = ['article', 'Article'] val << 'Journal/Periodical' if genres and !(genres & article).empty? stu_proj_rpt = ['student project report', 'Student project report', 'Student Project report', 'Student Project Report'] val << 'Other' if genres and !(genres & stu_proj_rpt).empty? thesis = ['thesis', 'Thesis'] val << 'Thesis' if genres and !(genres & thesis).empty? when 'three dimensional object' val << 'Other' end end end val.uniq end |
#format_main ⇒ Array[String]
select one or more format values from the controlled vocabulary per JVine Summer 2014
http://searchworks-solr-lb.stanford.edu:8983/solr/select?facet.field=format_main_ssim&rows=0&facet.sort=index
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 |
# File 'lib/stanford-mods/searchworks.rb', line 585 def format_main val = [] types = self.term_values(:typeOfResource) if types genres = self.term_values(:genre) issuance = self.term_values([:origin_info,:issuance]) types.each do |type| case type when 'cartographic' val << 'Map' when 'mixed material' val << 'Archive/Manuscript' when 'moving image' val << 'Video' when 'notated music' val << 'Music score' when 'software, multimedia' if genres and (genres.include?('dataset') || genres.include?('Dataset')) val << 'Dataset' else val << 'Software/Multimedia' end when 'sound recording-musical' val << 'Music recording' when 'sound recording-nonmusical', 'sound recording' val << 'Sound recording' when 'still image' val << 'Image' when 'text' article_genres = ['article', 'Article', 'book chapter', 'Book chapter', 'Book Chapter', 'issue brief', 'Issue brief', 'Issue Brief', 'project report', 'Project report', 'Project Report', 'student project report', 'Student project report', 'Student Project report', 'Student Project Report', 'technical report', 'Technical report', 'Technical Report', 'working paper', 'Working paper', 'Working Paper' ] val << 'Book' if genres and !(genres & article_genres).empty? val << 'Book' if issuance and issuance.include? 'monographic' book_genres = ['conference publication', 'Conference publication', 'Conference Publication', 'instruction', 'Instruction', 'librettos', 'Librettos', 'thesis', 'Thesis' ] val << 'Book' if genres and !(genres & book_genres).empty? val << 'Journal/Periodical' if issuance and issuance.include? 'continuing' when 'three dimensional object' val << 'Object' end end end val.uniq end |
#geographic_facet ⇒ Array<String>
geographic_search values with trailing comma, semicolon, and backslash (and any preceding spaces) removed
297 298 299 |
# File 'lib/stanford-mods/searchworks.rb', line 297 def geographic_facet geographic_search.map { |val| val.sub(/[\\,;]$/, '').strip } unless !geographic_search end |
#geographic_search ⇒ Array<String>
Values are the contents of:
subject/geographic
subject/hierarchicalGeographic
subject/geographicCode (only include the translated value if it isn't already present from other mods geo fields)
312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 |
# File 'lib/stanford-mods/searchworks.rb', line 312 def geographic_search @geographic_search ||= begin result = self.sw_geographic_search # TODO: this should go into stanford-mods ... but then we have to set that gem up with a Logger # print a message for any unrecognized encodings xvals = self.subject.geographicCode.translated_value codes = self.term_values([:subject, :geographicCode]) if codes && codes.size > xvals.size self.subject.geographicCode.each { |n| if n. != 'marcgac' && n. != 'marccountry' sw_logger.info("#{druid} has subject geographicCode element with untranslated encoding (#{n.}): #{n.to_xml}") end } end # FIXME: stanford-mods should be returning [], not nil ... return nil if !result || result.empty? result end end |
#get_bc_year(dates) ⇒ Object
get the 3 digit BC year, return it as a negative, so -700 for 300 BC. Other methods will translate it to proper display, this is good for sorting.
783 784 785 786 787 788 789 790 791 792 |
# File 'lib/stanford-mods/searchworks.rb', line 783 def get_bc_year dates dates.each do |f_date| matches=f_date.scan(/\d{3} B.C./) if matches.length > 0 bc_year=matches.first[0..2] return (bc_year.to_i-1000).to_s end end return nil end |
#get_double_digit_century(dates) ⇒ Object
get a double digit century like ‘12th century’ from the date array
749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 |
# File 'lib/stanford-mods/searchworks.rb', line 749 def get_double_digit_century dates dates.each do |f_date| matches=f_date.scan(/\d{2}th/) if matches.length == 1 @pub_year=((matches.first[0,2].to_i)-1).to_s+'--' return @pub_year end #if there are multiples, check for ones with CE after them if matches.length > 0 matches.each do |match| pos = f_date.index(Regexp.new(match+'...CE')) pos = pos ? pos.to_i : f_date.index(Regexp.new(match+' century CE')) pos = pos ? pos.to_i : 0 if f_date.include?(match+' CE') or pos > 0 @pub_year=((match[0,2].to_i) - 1).to_s+'--' return @pub_year end end end end return nil end |
#get_plain_four_digit_year(dates) ⇒ Object
get a 4 digit year like 1865 from the date array
706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 |
# File 'lib/stanford-mods/searchworks.rb', line 706 def get_plain_four_digit_year dates dates.each do |f_date| matches=f_date.scan(/\d{4}/) if matches.length == 1 @pub_year=matches.first return matches.first else #if there are multiples, check for ones with CE after them matches.each do |match| #look for things like '1865-6 CE' pos = f_date.index(Regexp.new(match+'...CE')) pos = pos ? pos.to_i : 0 if f_date.include?(match+' CE') or pos > 0 @pub_year=match return match end end return matches.first end end return nil end |
#get_single_digit_century(dates) ⇒ Object
get a single digit century like ‘9th century’ from the date array
795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 |
# File 'lib/stanford-mods/searchworks.rb', line 795 def get_single_digit_century dates dates.each do |f_date| matches=f_date.scan(/\d{1}th/) if matches.length == 1 @pub_year=((matches.first[0,2].to_i)-1).to_s+'--' return @pub_year end #if there are multiples, check for ones with CE after them if matches.length > 0 matches.each do |match| pos = f_date.index(Regexp.new(match+'...CE')) pos = pos ? pos.to_i : f_date.index(Regexp.new(match+' century CE')) pos = pos ? pos.to_i : 0 if f_date.include?(match+' CE') or pos > 0 @pub_year=((match[0,1].to_i) - 1).to_s+'--' return @pub_year end end end end return nil end |
#get_three_digit_year(dates) ⇒ Object
get a 3 digit year like 965 from the date array
773 774 775 776 777 778 779 780 781 |
# File 'lib/stanford-mods/searchworks.rb', line 773 def get_three_digit_year dates dates.each do |f_date| matches=f_date.scan(/\d{3}/) if matches.length > 0 return matches.first end end return nil end |
#get_u_year(dates) ⇒ Object
If a year has a “u” in it, replace instances of u with 0
732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 |
# File 'lib/stanford-mods/searchworks.rb', line 732 def get_u_year dates dates.each do |f_date| # Single digit u notation matches = f_date.scan(/\d{3}u/) if matches.length == 1 return matches.first.gsub('u','0') end # Double digit u notation matches = f_date.scan(/\d{2}u{2}/) if matches.length == 1 return matches.first.gsub('u','-') end end return nil end |
#is_date?(object) ⇒ Boolean
437 438 439 |
# File 'lib/stanford-mods/searchworks.rb', line 437 def is_date?(object) true if Date.parse(object) rescue false end |
#is_number?(object) ⇒ Boolean
434 435 436 |
# File 'lib/stanford-mods/searchworks.rb', line 434 def is_number?(object) true if Integer(object) rescue false end |
#main_author_w_date ⇒ String
the first encountered <mods><name> element with marcrelator flavor role of ‘Creator’ or ‘Author’. if no marcrelator ‘Creator’ or ‘Author’, the first name without a role. if no name without a role, then nil see Mods::Record.name in nom_terminology for details on the display_value algorithm
16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 |
# File 'lib/stanford-mods.rb', line 16 def result = nil first_wo_role = nil @mods_ng_xml.plain_name.each { |n| if n.role.size == 0 first_wo_role ||= n end n.role.each { |r| if r..include?('marcrelator') && (r.value.include?('Creator') || r.value.include?('Author')) result ||= n.display_value_w_date end } } if !result && first_wo_role result = first_wo_role.display_value_w_date end result end |
#main_author_w_date_test ⇒ Object
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
# File 'lib/stanford-mods/searchworks.rb', line 97 def result = nil first_wo_role = nil self.plain_name.each { |n| if n.role.size == 0 first_wo_role ||= n end n.role.each { |r| if r..include?('marcrelator') && (r.value.include?('Creator') || r.value.include?('Author')) result ||= n.display_value_w_date end } } if !result && first_wo_role result = first_wo_role.display_value_w_date end result end |
#place ⇒ Object
—- PUBLICATION (place, year) —-
381 382 383 384 |
# File 'lib/stanford-mods/searchworks.rb', line 381 def place vals = self.term_values([:origin_info,:place,:placeTerm]) vals end |
#pub_date ⇒ String
The year the object was published, , filtered based on max_pub_date and min_pub_date from the config file
494 495 496 497 498 499 500 |
# File 'lib/stanford-mods/searchworks.rb', line 494 def pub_date val=pub_year if val return val end nil end |
#pub_date_display ⇒ Object
386 387 388 389 390 391 392 |
# File 'lib/stanford-mods/searchworks.rb', line 386 def pub_date_display if pub_dates pub_dates.first else nil end end |
#pub_date_facet ⇒ Array[String]
Values for the pub date facet. This is less strict than the 4 year date requirements for pub_date
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 |
# File 'lib/stanford-mods/searchworks.rb', line 504 def pub_date_facet if pub_date if pub_date.start_with?('-') return (pub_date.to_i + 1000).to_s + ' B.C.' end if pub_date.include? '--' cent=pub_date[0,2].to_i cent+=1 cent=cent.to_s+'th century' return cent else return pub_date end else nil end end |
#pub_date_groups(year) ⇒ Array<String>
Returns values for the pub_date_group_facet.
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 |
# File 'lib/stanford-mods/searchworks.rb', line 396 def pub_date_groups year if not year return nil end year=year.to_i current_year=Time.new.year.to_i result = [] if year >= current_year - 1 result << "This year" else if year >= current_year - 3 result << "Last 3 years" else if year >= current_year - 10 result << "Last 10 years" else if year >= current_year - 50 result << "Last 50 years" else result << "More than 50 years ago" end end end end end |
#pub_date_sort ⇒ Object
creates a date suitable for sorting. Guarnteed to be 4 digits or nil
479 480 481 482 483 484 485 486 487 488 489 490 |
# File 'lib/stanford-mods/searchworks.rb', line 479 def pub_date_sort pd=nil if pub_date pd=pub_date if pd.length == 3 pd='0'+pd end pd=pd.gsub('--','00') end raise "pub_date_sort was about to return a non 4 digit value #{pd}!" if pd and pd.length !=4 pd end |
#pub_dates ⇒ Array<String>
get the dates from dateIssued, and dateCreated merged into 1 array.
424 425 426 427 428 429 430 431 432 |
# File 'lib/stanford-mods/searchworks.rb', line 424 def pub_dates vals = self.term_values([:origin_info,:dateIssued]) if vals vals = vals.concat self.term_values([:origin_info,:dateCreated]) unless not self.term_values([:origin_info,:dateCreated]) else vals = self.term_values([:origin_info,:dateCreated]) end vals and vals.empty? ? nil : vals end |
#pub_year ⇒ String
Get the publish year from mods
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 |
# File 'lib/stanford-mods/searchworks.rb', line 443 def pub_year #use the cached year if there is one if @pub_year if @pub_year == '' return nil end return @pub_year end dates = pub_dates if dates year = [] pruned_dates = [] dates.each do |f_date| #remove ? and [] pruned_dates << f_date.gsub('?','').gsub('[','').gsub(']','') end #try to find a date starting with the most normal date formats and progressing to more wonky ones @pub_year = get_plain_four_digit_year pruned_dates return @pub_year if @pub_year # Check for years in u notation, e.g., 198u @pub_year = get_u_year pruned_dates return @pub_year if @pub_year @pub_year = get_double_digit_century pruned_dates return @pub_year if @pub_year @pub_year = get_bc_year pruned_dates return @pub_year if @pub_year @pub_year = get_three_digit_year pruned_dates return @pub_year if @pub_year @pub_year = get_single_digit_century pruned_dates return @pub_year if @pub_year end @pub_year='' return nil end |
#subject_all_search ⇒ Array<String>
Values are the contents of:
all subject subelements except subject/cartographic plus genre top level element
370 371 372 373 374 375 376 |
# File 'lib/stanford-mods/searchworks.rb', line 370 def subject_all_search vals = topic_search ? Array.new(topic_search) : [] vals.concat(geographic_search) if geographic_search vals.concat(subject_other_search) if subject_other_search vals.concat(subject_other_subvy_search) if subject_other_subvy_search vals.empty? ? nil : vals end |
#subject_names ⇒ Object
convenience method for subject/name/namePart values (to avoid parsing the mods for the same thing multiple times)
681 682 683 |
# File 'lib/stanford-mods/searchworks.rb', line 681 def subject_names @subject_names ||= self.sw_subject_names end |
#subject_occupations ⇒ Object
convenience method for subject/occupation values (to avoid parsing the mods for the same thing multiple times)
686 687 688 |
# File 'lib/stanford-mods/searchworks.rb', line 686 def subject_occupations @subject_occupations ||= self.term_values([:subject, :occupation]) end |
#subject_other_search ⇒ Array<String>
Values are the contents of:
subject/name
subject/occupation - no subelements
subject/titleInfo
339 340 341 342 343 344 345 346 |
# File 'lib/stanford-mods/searchworks.rb', line 339 def subject_other_search @subject_other_search ||= begin vals = subject_occupations ? Array.new(subject_occupations) : [] vals.concat(subject_names) if subject_names vals.concat(subject_titles) if subject_titles vals.empty? ? nil : vals end end |
#subject_other_subvy_search ⇒ Array<String>
Values are the contents of:
subject/temporal
subject/genre
352 353 354 355 356 357 358 359 360 361 362 363 364 365 |
# File 'lib/stanford-mods/searchworks.rb', line 352 def subject_other_subvy_search @subject_other_subvy_search ||= begin vals = subject_temporal ? Array.new(subject_temporal) : [] gvals = self.term_values([:subject, :genre]) vals.concat(gvals) if gvals # print a message for any temporal encodings self.subject.temporal.each { |n| sw_logger.info("#{druid} has subject temporal element with untranslated encoding: #{n.to_xml}") if !n.encoding.empty? } vals.empty? ? nil : vals end end |
#subject_temporal ⇒ Object
convenience method for subject/temporal values (to avoid parsing the mods for the same thing multiple times)
691 692 693 |
# File 'lib/stanford-mods/searchworks.rb', line 691 def subject_temporal @subject_temporal ||= self.term_values([:subject, :temporal]) end |
#subject_titles ⇒ Object
convenience method for subject/titleInfo values (to avoid parsing the mods for the same thing multiple times)
696 697 698 |
# File 'lib/stanford-mods/searchworks.rb', line 696 def subject_titles @subject_titles ||= self.sw_subject_titles end |
#subject_topics ⇒ Object
convenience method for subject/topic values (to avoid parsing the mods for the same thing multiple times)
701 702 703 |
# File 'lib/stanford-mods/searchworks.rb', line 701 def subject_topics @subject_topics ||= self.term_values([:subject, :topic]) end |
#sw_addl_authors ⇒ Array<String>
Returns values for author_7xx_search field.
61 62 63 |
# File 'lib/stanford-mods/searchworks.rb', line 61 def end |
#sw_addl_titles ⇒ Array<String>
this includes all titles except
177 178 179 |
# File 'lib/stanford-mods/searchworks.rb', line 177 def sw_addl_titles full_titles.select { |s| s !~ Regexp.new(Regexp.escape(sw_short_title)) } end |
#sw_corporate_authors ⇒ Array<String>
Returns values for author_corp_display.
77 78 79 80 |
# File 'lib/stanford-mods/searchworks.rb', line 77 def val = @mods_ng_xml.plain_name.select {|n| n.type_at == 'corporate'}.map { |n| n.display_value_w_date } val end |
#sw_full_title ⇒ String
Returns value for title_245_search, title_full_display.
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 |
# File 'lib/stanford-mods/searchworks.rb', line 127 def sw_full_title outer_nodes = @mods_ng_xml.title_info outer_node = outer_nodes ? outer_nodes.first : nil if outer_node nonSort = outer_node.nonSort.text.strip.empty? ? nil : outer_node.nonSort.text.strip title = outer_node.title.text.strip.empty? ? nil: outer_node.title.text.strip preSubTitle = nonSort ? [nonSort, title].compact.join(" ") : title preSubTitle.sub!(/:$/, '') if preSubTitle # remove trailing colon subTitle = outer_node.subTitle.text.strip preParts = subTitle.empty? ? preSubTitle : preSubTitle + " : " + subTitle preParts.sub!(/\.$/, '') if preParts # remove trailing period partName = outer_node.partName.text.strip unless outer_node.partName.text.strip.empty? partNumber = outer_node.partNumber.text.strip unless outer_node.partNumber.text.strip.empty? partNumber.sub!(/,$/, '') if partNumber # remove trailing comma if partNumber && partName parts = partNumber + ", " + partName elsif partNumber parts = partNumber elsif partName parts = partName end parts.sub!(/\.$/, '') if parts result = parts ? preParts + ". " + parts : preParts result += "." if !result.match(/[[:punct:]]$/) result.strip! result = nil if result.empty? result else nil end end |
#sw_full_title_without_commas ⇒ Object
in favor of sw_title_display
remove trailing commas
199 200 201 202 203 |
# File 'lib/stanford-mods/searchworks.rb', line 199 def sw_full_title_without_commas result = self.sw_full_title result.sub!(/,$/, '') if result result end |
#sw_genre ⇒ Array[String]
return values for the genre facet in SearchWorks
641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 |
# File 'lib/stanford-mods/searchworks.rb', line 641 def sw_genre val = [] genres = self.term_values(:genre) if genres val << genres.map(&:capitalize) val.flatten! if !val.empty? if genres.include?('thesis') || genres.include?('Thesis') val << 'Thesis/Dissertation' val.delete 'Thesis' end conf_pub = ['conference publication', 'Conference publication', 'Conference Publication'] if !(genres & conf_pub).empty? types = self.term_values(:typeOfResource) if types && types.include?('text') val << 'Conference proceedings' val.delete 'Conference publication' end end end val.uniq end |
#sw_geographic_search(sep = ' ') ⇒ Array<String>
Values are the contents of:
subject/geographic
subject/hierarchicalGeographic
subject/geographicCode (only include the translated value if it isn't already present from other mods geo fields)
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 |
# File 'lib/stanford-mods/searchworks.rb', line 215 def sw_geographic_search(sep = ' ') result = term_values([:subject, :geographic]) || [] # hierarchicalGeographic has sub elements @mods_ng_xml.subject.hierarchicalGeographic.each { |hg_node| hg_vals = [] hg_node.element_children.each { |e| hg_vals << e.text unless e.text.empty? } result << hg_vals.join(sep) unless hg_vals.empty? } trans_code_vals = @mods_ng_xml.subject.geographicCode.translated_value if trans_code_vals trans_code_vals.each { |val| result << val if !result.include?(val) } end result end |
#sw_impersonal_authors ⇒ Array<String>
return the display_value_w_date for all <mods><name> elements that do not have type=‘personal’
72 73 74 |
# File 'lib/stanford-mods/searchworks.rb', line 72 def @mods_ng_xml.plain_name.select {|n| n.type_at != 'personal'}.map { |n| n.display_value_w_date } end |
#sw_language_facet ⇒ Object
include langagues known to SearchWorks; try to error correct when possible (e.g. when ISO-639 disagrees with MARC standard)
11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
# File 'lib/stanford-mods/searchworks.rb', line 11 def sw_language_facet result = [] @mods_ng_xml.language.each { |n| # get languageTerm codes and add their translations to the result n.code_term.each { |ct| if ct..match(/^iso639/) begin vals = ct.text.split(/[,|\ ]/).reject {|x| x.strip.length == 0 } vals.each do |v| iso639_val = ISO_639.find(v.strip).english_name if SEARCHWORKS_LANGUAGES.has_value?(iso639_val) result << iso639_val else result << SEARCHWORKS_LANGUAGES[v.strip] end end rescue => e # TODO: this should be written to a logger p "Couldn't find english name for #{ct.text}" end else vals = ct.text.split(/[,|\ ]/).reject {|x| x.strip.length == 0 } vals.each do |v| result << SEARCHWORKS_LANGUAGES[v.strip] end end } # add languageTerm text values n.text_term.each { |tt| val = tt.text.strip result << val if val.length > 0 && SEARCHWORKS_LANGUAGES.has_value?(val) } # add language values that aren't in languageTerm subelement if n.languageTerm.size == 0 result << n.text if SEARCHWORKS_LANGUAGES.has_value?(n.text) end } result.uniq end |
#sw_logger ⇒ Object
—- end PUBLICATION (place, year) —-
524 525 526 |
# File 'lib/stanford-mods/searchworks.rb', line 524 def sw_logger @logger ||= Logger.new(STDOUT) end |
#sw_main_author ⇒ String
Returns value for author_1xx_search field.
56 57 58 |
# File 'lib/stanford-mods/searchworks.rb', line 56 def end |
#sw_meeting_authors ⇒ Array<String>
Returns values for author_meeting_display.
83 84 85 |
# File 'lib/stanford-mods/searchworks.rb', line 83 def @mods_ng_xml.plain_name.select {|n| n.type_at == 'conference'}.map { |n| n.display_value_w_date } end |
#sw_person_authors ⇒ Array<String>
Returns values for author_person_facet, author_person_display.
66 67 68 |
# File 'lib/stanford-mods/searchworks.rb', line 66 def personal_names_w_dates end |
#sw_short_title ⇒ String
Returns value for title_245a_search field.
122 123 124 |
# File 'lib/stanford-mods/searchworks.rb', line 122 def sw_short_title short_titles ? short_titles.first : nil end |
#sw_sort_author ⇒ String
Returns a sortable version of the main_author:
main_author + sorting title
which is the mods approximation of the value created for a marc record
91 92 93 94 95 |
# File 'lib/stanford-mods/searchworks.rb', line 91 def # substitute java Character.MAX_CODE_POINT for nil main_author so missing main authors sort last val = '' + ( ? : "\u{FFFF} ") + ( sort_title ? sort_title : '') val.gsub(/[[:punct:]]*/, '').strip end |
#sw_sort_title ⇒ String
Returns a sortable version of the main title
183 184 185 186 187 188 189 190 191 192 193 194 195 |
# File 'lib/stanford-mods/searchworks.rb', line 183 def sw_sort_title # get nonSort piece outer_nodes = @mods_ng_xml.title_info outer_node = outer_nodes ? outer_nodes.first : nil if outer_node nonSort = outer_node.nonSort.text.strip.empty? ? nil : outer_node.nonSort.text.strip end val = '' + ( sw_full_title ? sw_full_title : '') val.sub!(Regexp.new("^" + nonSort), '') if nonSort val.gsub!(/[[:punct:]]*/, '').strip val.squeeze(" ").strip end |
#sw_subject_names(sep = ', ') ⇒ Array<String>
Values are the contents of:
subject/name/namePart
"Values from namePart subelements should be concatenated in the order they appear (e.g. "Shakespeare, William, 1564-1616")"
242 243 244 245 246 247 248 249 |
# File 'lib/stanford-mods/searchworks.rb', line 242 def sw_subject_names(sep = ', ') result = [] @mods_ng_xml.subject.name_el.select { |n_el| n_el.namePart }.each { |name_el_w_np| parts = name_el_w_np.namePart.map { |npn| npn.text unless npn.text.empty? }.compact result << parts.join(sep).strip unless parts.empty? } result end |
#sw_subject_titles(sep = ' ') ⇒ Array<String>
Values are the contents of:
subject/titleInfo/(subelements)
255 256 257 258 259 260 261 262 |
# File 'lib/stanford-mods/searchworks.rb', line 255 def sw_subject_titles(sep = ' ') result = [] @mods_ng_xml.subject.titleInfo.each { |ti_el| parts = ti_el.element_children.map { |el| el.text unless el.text.empty? }.compact result << parts.join(sep).strip unless parts.empty? } result end |
#sw_title_display ⇒ String
like sw_full_title without trailing ,/;:. spec from solrmarc-sw sw_index.properties
title_display = custom, removeTrailingPunct(245abdefghijklmnopqrstuvwxyz, [\\\\,/;:], ([A-Za-z]{4}|[0-9]{3}|\\)|\\,))
166 167 168 169 170 171 172 173 |
# File 'lib/stanford-mods/searchworks.rb', line 166 def sw_title_display result = sw_full_title ? sw_full_title : nil if result result.sub!(/[\.,;:\/\\]+$/, '') result.strip! end result end |
#topic_facet ⇒ Array<String>
Values are the contents of:
subject/topic
subject/name
subject/title
subject/occupation
with trailing comma, semicolon, and backslash (and any preceding spaces) removed
283 284 285 286 287 288 289 290 291 292 293 |
# File 'lib/stanford-mods/searchworks.rb', line 283 def topic_facet vals = subject_topics ? Array.new(subject_topics) : [] vals.concat(subject_names) if subject_names vals.concat(subject_titles) if subject_titles vals.concat(subject_occupations) if subject_occupations vals.map! { |val| v = val.sub(/[\\,;]$/, '') v.strip } vals.empty? ? nil : vals end |
#topic_search ⇒ Array<String>
Values are the contents of:
mods/genre
mods/subject/topic
268 269 270 271 272 273 274 |
# File 'lib/stanford-mods/searchworks.rb', line 268 def topic_search @topic_search ||= begin vals = self.term_values(:genre) || [] vals.concat(subject_topics) if subject_topics vals.empty? ? nil : vals end end |