hydra-head 4.0.0 → 4.0.1

data/lib/marc_mapper.rb

@@ -1,131 +0,0 @@
-require 'rubygems'
-require 'marc' # ruby gem for working with MARC data in Ruby
-require 'block_mapper' # the generic mapper class
-require 'marc_record_ext.rb' # our custom methods
-require 'base64' # so we can base64 encode the marc21 record
-
-class MARCMapper
-  
-  # pass in a path to a marc file
-  # a block can be used for logging etc..
-  # 
-  # mapper.from_marc_file('/path/to/data.mrc') do |mapped_doc|
-  #   # do something here... logging etc..
-  # end
-  #
-  # this returns an array of documents (hashes)
-  #
-  def self.from_marc_file(marc_file, &blk)
-    
-    @mapper = BlockMapper.new
-    
-    # add custom methods to each marc record
-    @mapper.before_each_source_item do |rec,index|
-      rec.extend MARCRecordExt
-    end
-    
-    # remove ; / . , : and spaces from the end
-    cleanup_regexp = /( |;|\/|\.|,|:)+$/
-    # after_each_mapped_value gets executed for each mapped item
-    # ... after it has been mapped
-    @mapper.after_each_mapped_value do |field,v|
-      #puts "cleaning up #{field} value(s) before adding to solr..."
-      if v.is_a?(String)
-        v.gsub(cleanup_regexp, '') # clean this string and return
-      elsif v.is_a?(Array)
-        v.map{|vv|vv.gsub(cleanup_regexp, '')} # clean each value and return a new array
-      else
-        v # just return whatever it is
-      end
-    end
-    
-    @mapper.map :id do |rec,index|
-      rec['001'].value.gsub(" ","").gsub("/","")
-    end
-    
-    # titles (text)
-    @mapper.map :title_t do |rec,index|
-      rec.values_for '245', 'a'
-    end
-    
-    @mapper.map :sub_title_t do |rec,index|
-      rec.values_for '245', 'b'
-    end
-    
-    @mapper.map :alt_titles_t do |rec,index|
-      rec.extract '240:b 700:t 710:t 711:t 440:a 490:a 505:a 830:a'
-    end
-    
-    @mapper.map :title_added_entry_t do |rec,index|
-      rec.values_for '700', 't'
-    end
-    
-    # title sort
-    @mapper.map :title_sort do |rec,index|
-      rec.extract '245:a'
-    end
-
-    @mapper.map :author_t do |rec,index|
-      rec.extract '100:a 110:a 111:a 130:a 700:a 710:a 711:a'
-    end
-    
-    @mapper.map :published_t do |rec,index|
-      rec.extract '260:a'
-    end
-    
-    @mapper.map :isbn_t do |rec,index|
-      rec.isbn # in MARCRecordExt module
-    end
-    
-    @mapper.map :material_type_t do |rec,index|
-      rec.values_for '300', 'a'
-    end
-
-    # subject (text)
-    @mapper.map :subject_t do |rec,index|
-      rec.extract '600:a 610:a 611:a 630:a 650:a 651:a 655:a 690:a'
-    end
-    
-    # subject (facets)
-    @mapper.map :subject_era_facet do |rec,index|
-      rec.extract '650:d 650:y 651:y 655:y'
-    end
-    
-    @mapper.map :geographic_subject_facet do |rec,index|
-      rec.extract '650:c 650:z 651:a 651:x 651:z 655:z'
-    end
-
-    @mapper.map :language_facet do |rec,index|
-      rec.languages # in MARCRecordExt module
-    end
-    
-    # format fields
-    @mapper.map :format_facet do |rec,index|
-      rec.format # in MARCRecordExt module
-    end
-    
-    # downcased, format, spaces converted to _
-    # This can be used for the partial view mapping
-    @mapper.map :format_code_t do |rec,index|
-      rec.format.to_s.downcase.gsub(/ _/, ' ').gsub(/ /, '_')
-    end
-    
-    # grab some vernacular for demonstration purposes (e.g. "did you mean")
-    @mapper.map :vern_t do |rec,index|
-      rec.extract '880:a 880:b 880:c 880:e 880:f 880:p 880:t'
-    end
-    
-    # _display is stored, but not indexed
-    # don't store a string, store marc21 so we can read it back out
-    # into a MARC::Record object 
-    @mapper.map :marc_display do |rec,index|
-      rec.to_xml
-    end
-    
-    reader = MARC::Reader.new(marc_file)
-    
-    @mapper.run(reader, &blk)
-    
-  end
-  
-end

data/lib/marc_record_ext.rb

@@ -1,97 +0,0 @@
-
-# MARC::Record helpers
-
-# This module gets mixed into each MARC::Record instance
-
-require 'field_maps'
-
-module MARCRecordExt
-  
-  # input is a string in the format of: field:subfield
-  # multiple fields can be given, use a single space to separate
-  # example: record.extract '245:a 245:b'
-  def extract(input, regexp=nil)
-    hash = {}
-    input.split(' ').each do |item|
-      k,v = item.split(':')
-      next unless k
-      hash[k]||=[]
-      hash[k] << v if v
-    end
-    hash.map do |field,subfields|
-      values_for(field, subfields, regexp)
-    end.flatten
-  end
-  
-  # This methods returns a single dimensional array of values for subfields (it also removes blank values)
-  # if subs is specified, only the matching subfields are returned
-  # if subs is nil, the all subfields are returned
-  # the value_regx can be used to match the value of the subfield
-  #
-  # =example: values_for '045', [:a]
-  #
-  # =parameters
-  # field_name - '045' etc.
-  # subs - [:a, :b] etc.
-  # value_regx - a Regexp
-  def values_for(field_name, subs=nil, value_regx=nil)
-    subs ||= []
-    subs = [subs] unless subs.is_a?(Array)
-    self.fields.collect do |field|
-      if field.tag==field_name and ! field.value.to_s.empty?
-        field.subfields.collect do |subfield|
-          next if ! subs.empty? and ! subs.include?(subfield.code)
-          v = value_regx ? subfield.value.match(value_regx) : subfield.value
-          v.empty? ? nil : v
-        end
-      end
-    end.flatten.uniq.reject{|v|v.to_s.empty?}
-  end
-  
-  # http://woss.name/2005/09/09/isbn-validation-part-2
-  def valid_isbn?(isbn, c_map = '0123456789X')
-    sum = 0
-    return unless isbn
-    match = isbn[0..-2].to_s.scan(/\d/)
-    match.each_with_index do |c,i|
-      sum += c.to_i * (i+1)
-    end
-    isbn[-1] == c_map[sum % c_map.length]
-  end
-  
-  # extracts valid isbns
-  def isbn
-    values = self.extract('020:a')
-    # go through each value
-    values.select do |v| # "select" collects values only if the last line of this block is true
-      # split on a space, grab the first
-      isbn = v.to_s.split(' ').first
-      # is it valid?
-      valid_isbn?(isbn)
-    end
-  end
-  
-  # returns the mapped language value
-  def languages
-    values = [self['008'].value[35..37]]
-    values += self.extract('041:a 041:d')
-    values.uniq!
-    mapped = values.map{|code| FieldMaps::LANGUAGE[code] }
-    mapped.reject{|v| v.to_s.empty? }
-  end
-  
-  # http://www.itsmarc.com/crs/Bib0021.htm#Leader_06_Definition
-  def format
-    char_6 = self.leader[6...7]
-    char_7 = self.leader[7...8]
-    if char_6 == 'a' and %W(a c d m).include? char_7
-      code = 'a'
-    elsif %W(b s).include? char_7
-      code = 'serials'
-    else
-      code = char_6
-    end
-    FieldMaps::FORMAT[code] || 'Unknown'
-  end
-  
-end

data/test_support/spec/models/audio_asset_spec.rb

@@ -1,23 +0,0 @@
-require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
-require "active_fedora"
-
-describe AudioAsset do
-  
-  before(:each) do
-#    Fedora::Repository.stubs(:instance).returns(stub_everything())
-    @asset = AudioAsset.new
-    @asset.stubs(:create_date).returns("2008-07-02T05:09:42.015Z")
-    @asset.stubs(:modified_date).returns("2008-09-29T21:21:52.892Z")
-  end
-  
-  it "Should be a kind of ActiveFedora::Base kind of FileAsset, and instance of AudioAsset" do
-    @asset.should be_kind_of(ActiveFedora::Base)
-    @asset.should be_kind_of(FileAsset)
-    @asset.should be_instance_of(AudioAsset)
-  end
-  
-  it "should have a conforms_to relationship pointing to FileAsset" do
-    @asset.ids_for_outbound(:has_model).should include("afmodel:FileAsset")
-  end
-  
-end

data/test_support/spec/models/image_asset_spec.rb

@@ -1,23 +0,0 @@
-require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
-require "active_fedora"
-
-describe ImageAsset do
-  
-  before(:each) do
-#    Fedora::Repository.stubs(:instance).returns(stub_everything())
-    @asset = ImageAsset.new
-    @asset.stubs(:create_date).returns("2008-07-02T05:09:42.015Z")
-    @asset.stubs(:modified_date).returns("2008-09-29T21:21:52.892Z")
-  end
-  
-  it "Should be a kind of ActiveFedora::Base kind of FileAsset, and instance of ImageAsset" do
-    @asset.should be_kind_of(ActiveFedora::Base)
-    @asset.should be_kind_of(FileAsset)
-    @asset.should be_instance_of(ImageAsset)
-  end
-  
-  it "should have a conforms_to relationship pointing to FileAsset" do
-    @asset.ids_for_outbound(:has_model).should include("afmodel:FileAsset")
-  end
-  
-end

data/test_support/spec/models/video_asset_spec.rb

@@ -1,23 +0,0 @@
-require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
-require "active_fedora"
-
-describe VideoAsset do
-  
-  before(:each) do
-#    Fedora::Repository.stubs(:instance).returns(stub_everything())
-    @asset = VideoAsset.new
-    @asset.stubs(:create_date).returns("2008-07-02T05:09:42.015Z")
-    @asset.stubs(:modified_date).returns("2008-09-29T21:21:52.892Z")
-  end
-  
-  it "Should be a kind of ActiveFedora::Base kind of FileAsset, and instance of VideoAsset" do
-    @asset.should be_kind_of(ActiveFedora::Base)
-    @asset.should be_kind_of(FileAsset)
-    @asset.should be_instance_of(VideoAsset)
-  end
-  
-  it "should have a conforms_to relationship pointing to FileAsset" do
-    @asset.ids_for_outbound(:has_model).should include("afmodel:FileAsset")
-  end
-  
-end