Class: Shelver::Extractor

Inherits:
Object
  • Object
show all
Defined in:
lib/shelver/extractor.rb

Instance Method Summary collapse

Instance Method Details

#extract_rels_ext(text, solr_doc = Solr::Document.new) ⇒ Object

Extracts content-model and hydra-type from RELS-EXT datastream



25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
 
# File 'lib/shelver/extractor.rb', line 25

def extract_rels_ext( text, solr_doc=Solr::Document.new )
  # TODO: only read in this file once
  
  if defined?(RAILS_ROOT)
    config_path = File.join(RAILS_ROOT, "config")
  else
    config_path = File.join(File.dirname(__FILE__), "..", "..", "config")
  end    
  map = YAML.load(File.open(File.join(config_path, "hydra_types.yml")))
  
  doc = Nokogiri::XML(text)
  doc.xpath( '//foo:hasModel', 'foo' => 'info:fedora/fedora-system:def/model#' ).each do |element|
    cmodel = element.attributes['resource'].to_s
    solr_doc << Solr::Field.new( :cmodel_t => cmodel )
    
    if map.has_key?(cmodel)
      solr_doc << Solr::Field.new( :hydra_type_t => map[cmodel] )
    end
  end

  return solr_doc
end

#extract_tag(doc, type) ⇒ Object 



15
16
17
18
19
 
# File 'lib/shelver/extractor.rb', line 15

def extract_tag(doc, type)
  tags = doc.elements["/fields/#{type}"]
  return {} unless tags
  {type => tags.text.split(/,/).map {|t| t.strip}}
end

#extract_tags(text) ⇒ Object 



10
11
12
13
 
# File 'lib/shelver/extractor.rb', line 10

def extract_tags(text)
  doc = REXML::Document.new( text )
  extract_tag(doc, 'archivist_tags').merge(extract_tag(doc, 'donor_tags'))
end

#html_content_to_solr(ds, solr_doc = Solr::Document.new) ⇒ Object

This method strips html tags out and returns content to be indexed in solr



63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
 
# File 'lib/shelver/extractor.rb', line 63

def html_content_to_solr( ds, solr_doc=Solr::Document.new )
  
  text = CGI.unescapeHTML(ds.content)
  doc = Nokogiri::HTML(text)
  
  # html to story_display
  stories = doc.xpath('//story')
      
  stories.each do |story|
    solr_doc << Solr::Field.new(:story_display => story.children.to_xml)
  end
  
  #strip out text and put in story_t
  text_nodes = doc.xpath("//text()")
  text = String.new
  
   text_nodes.each do |text_node|
     text << text_node.content
   end
  
   solr_doc << Solr::Field.new(:story_t => text)
   
   return solr_doc
end

#xml_to_solr(text, solr_doc = Solr::Document.new) ⇒ Object

This method extracts solr fields from simple xml



51
52
53
54
55
56
57
58
 
# File 'lib/shelver/extractor.rb', line 51

def xml_to_solr( text, solr_doc=Solr::Document.new )
  doc = REXML::Document.new( text )
  doc.root.elements.each do |element|
    solr_doc << Solr::Field.new( :"#{element.name}_t" => "#{element.text}" )
  end

  return solr_doc
end