Class: Solrizer::Indexer

Inherits:
Object
  • Object
show all
Defined in:
lib/solrizer/indexer.rb

Constant Summary collapse

@@unique_id =

Class variables

0

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(opts = {}) ⇒ Indexer

This method performs initialization tasks



25
26
27
28
29
30
31
32
33
34
35
36
 
# File 'lib/solrizer/indexer.rb', line 25

def initialize( opts={} )
  @@index_list = false unless defined?(@@index_list)
  @extractor = Extractor.new
  
  if opts[:index_full_text] == true || opts[:index_full_text] == "true"
    @index_full_text = true 
  else
    @index_full_text = false 
  end
  
  connect
end

Instance Attribute Details

#connection ⇒ Object

Member variables



20
21
22
 
# File 'lib/solrizer/indexer.rb', line 20

def connection
  @connection
end

#extractor ⇒ Object

Member variables



20
21
22
 
# File 'lib/solrizer/indexer.rb', line 20

def extractor
  @extractor
end

#index_full_text ⇒ Object

Member variables



20
21
22
 
# File 'lib/solrizer/indexer.rb', line 20

def index_full_text
  @index_full_text
end

Class Method Details

.solrize(input_hash, solr_doc = Solr::Document.new) ⇒ Object

Populates a solr doc with values from a hash.

Accepts two forms of hashes:

> “t2”], ‘company’=>“c1”, “person”=>[“p1”, “p2”]

or

> => {‘technology’=>[“t1”, “t2”], ‘company’=>“c1”, “person”=>[“p1”, “p2”] }

Note that values for individual fields can be a single string or an array of strings.



226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
 
# File 'lib/solrizer/indexer.rb', line 226

def self.solrize( input_hash, solr_doc=Solr::Document.new )    
  facets = input_hash.has_key?(:facets) ? input_hash[:facets] : input_hash
  facets.each_pair do |facet_name, value|
    case value.class.to_s
    when "String"
      solr_doc << Solr::Field.new( :"#{facet_name}_facet" => "#{value}" )
    when "Array"
      value.each { |v| solr_doc << Solr::Field.new( :"#{facet_name}_facet" => "#{v}" ) } 
    end
  end
  
  if input_hash.has_key?(:symbols) 
    input_hash[:symbols].each do |symbol_name, value|
      case value.class.to_s
      when "String"
        solr_doc << Solr::Field.new( :"#{symbol_name}_s" => "#{value}" )
     when "Array"
        value.each { |v| solr_doc << Solr::Field.new( :"#{symbol_name}_s" => "#{v}" ) } 
      end
    end
  end
  return solr_doc
end

.unique_id ⇒ Object 



13
14
15
 
# File 'lib/solrizer/indexer.rb', line 13

def self.unique_id
  @@unique_id
end

Instance Method Details

#class_exists?(class_name) ⇒ Boolean

Returns:

  • (Boolean) 


253
254
255
256
257
258
 
# File 'lib/solrizer/indexer.rb', line 253

def class_exists?(class_name)
  klass = Module.const_get(class_name)
  return klass.is_a?(Class)
rescue NameError
  return false
end

#deleteDocument(id) ⇒ Object

This method deletes a document from the Solr search index by id



215
216
217
 
# File 'lib/solrizer/indexer.rb', line 215

def deleteDocument( id )
  connection.delete( id )
end

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



94
95
96
97
 
# File 'lib/solrizer/indexer.rb', line 94

def extract_rels_ext( obj, ds_name, solr_doc=Solr::Document.new )
  rels_ext_ds = Repository.get_datastream( obj, ds_name )
  extractor.extract_rels_ext( rels_ext_ds.content, solr_doc )
end

#extract_xml_to_solr(obj, ds_name, solr_doc = Solr::Document.new) ⇒ Object

This method extracts the facet categories from the given Fedora object’s external tag datastream



86
87
88
89
 
# File 'lib/solrizer/indexer.rb', line 86

def extract_xml_to_solr( obj, ds_name, solr_doc=Solr::Document.new )
  xml_ds = Repository.get_datastream( obj, ds_name )
  extractor.xml_to_solr( xml_ds.content, solr_doc )
end

#generate_dates(solr_doc) ⇒ Object

This method generates the month and day facets from the date_t in solr_doc



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
 
# File 'lib/solrizer/indexer.rb', line 103

def generate_dates(solr_doc)
  
  # This will check for valid dates, but it seems most of the dates are currently invalid....
  #date_check =  /^(19|20)\d\d([- \/.])(0[1-9]|1[012])\2(0[1-9]|[12][0-9]|3[01])/

 #if there is not date_t, add on with easy-to-find value
 if solr_doc[:date_t].nil?
      solr_doc << Solr::Field.new( :date_t => "9999-99-99")
 end #if

  # unless date_check !~  solr_doc[:date_t]     
  date_obj = Date._parse(solr_doc[:date_t])
  
  if date_obj[:mon].nil? 
     solr_doc << Solr::Field.new(:month_facet => 99)
  elsif 0 < date_obj[:mon] && date_obj[:mon] < 13
    solr_doc << Solr::Field.new( :month_facet => date_obj[:mon].to_s.rjust(2, '0'))
  else
    solr_doc << Solr::Field.new( :month_facet => 99)
  end
    
  if  date_obj[:mday].nil?
    solr_doc << Solr::Field.new( :day_facet => 99)
  elsif 0 < date_obj[:mday] && date_obj[:mday] < 32   
    solr_doc << Solr::Field.new( :day_facet => date_obj[:mday].to_s.rjust(2, '0'))
  else
     solr_doc << Solr::Field.new( :day_facet => 99)
  end
  
  return solr_doc
#      end
      
end

#index(obj) ⇒ Object

This method adds a document to the Solr search index



179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
 
# File 'lib/solrizer/indexer.rb', line 179

def index( obj )
 # print "Indexing '#{obj.pid}'..."
  begin
    
    solr_doc = create_document( obj )
    connection.add( solr_doc )
 
   # puts connection.url
   #puts solr_doc
   #  puts "done"
 
  # rescue Exception => e
  #    p "unable to index #{obj.pid}.  Failed with #{e.inspect}"
  end
 
end

#printResults(query_str) ⇒ Object

This method prints out the results of the given query string by iterating through all the hits



206
207
208
209
210
 
# File 'lib/solrizer/indexer.rb', line 206

def printResults( query_str )
  query( query_str ) do |hit|
    puts hit.inspect
  end
end

#query(query_str) ⇒ Object

This method queries the Solr search index and returns a response



199
200
201
 
# File 'lib/solrizer/indexer.rb', line 199

def query( query_str )
  response = conn.query( query_str )
end