solrizer-fedora 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +22 -0
- data/Gemfile +10 -0
- data/Gemfile.lock +44 -0
- data/History.textile +3 -0
- data/LICENSE +20 -0
- data/README.textile +34 -0
- data/Rakefile +57 -0
- data/VERSION +1 -0
- data/config/fedora.yml +16 -0
- data/config/hydra_types.yml +4 -0
- data/config/solr.yml +7 -0
- data/lib/solrizer-fedora.rb +1 -0
- data/lib/solrizer/fedora.rb +7 -0
- data/lib/solrizer/fedora/extractor.rb +34 -0
- data/lib/solrizer/fedora/indexer.rb +213 -0
- data/lib/solrizer/fedora/repository.rb +44 -0
- data/lib/solrizer/fedora/solrizer.rb +118 -0
- data/lib/tasks/solrizer-fedora.rake +35 -0
- data/solrizer-fedora.gemspec +72 -0
- data/spec/fixtures/rels_ext_cmodel.xml +8 -0
- data/spec/integration/fedora_indexer_spec.rb +18 -0
- data/spec/rcov.opts +2 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +18 -0
- data/spec/units/fedora_extractor_spec.rb +31 -0
- data/spec/units/fedora_indexer_spec.rb +78 -0
- data/spec/units/fedora_solrizer_spec.rb +42 -0
- metadata +99 -0
data/.document
ADDED
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
GEM
|
2
|
+
remote: http://rubygems.org/
|
3
|
+
specs:
|
4
|
+
active-fedora (1.2.4)
|
5
|
+
mime-types (>= 1.16)
|
6
|
+
multipart-post
|
7
|
+
nokogiri
|
8
|
+
om (>= 1.0)
|
9
|
+
solr-ruby (>= 0.0.6)
|
10
|
+
xml-simple (>= 1.0.12)
|
11
|
+
columnize (0.3.1)
|
12
|
+
facets (2.9.0)
|
13
|
+
linecache (0.43)
|
14
|
+
mime-types (1.16)
|
15
|
+
mocha (0.9.9)
|
16
|
+
rake
|
17
|
+
multipart-post (1.0.1)
|
18
|
+
nokogiri (1.4.3.1)
|
19
|
+
om (1.0.0)
|
20
|
+
facets
|
21
|
+
nokogiri (>= 1.4.2)
|
22
|
+
rake (0.8.7)
|
23
|
+
rspec (1.3.1)
|
24
|
+
ruby-debug (0.10.3)
|
25
|
+
columnize (>= 0.1)
|
26
|
+
ruby-debug-base (~> 0.10.3.0)
|
27
|
+
ruby-debug-base (0.10.3)
|
28
|
+
linecache (>= 0.3)
|
29
|
+
solr-ruby (0.0.8)
|
30
|
+
solrizer (0.3.0)
|
31
|
+
active-fedora (>= 1.1.5)
|
32
|
+
om (>= 1.0.0)
|
33
|
+
xml-simple (1.0.12)
|
34
|
+
|
35
|
+
PLATFORMS
|
36
|
+
ruby
|
37
|
+
|
38
|
+
DEPENDENCIES
|
39
|
+
active-fedora (= 1.2.4)
|
40
|
+
mocha
|
41
|
+
rspec (< 2.0.0)
|
42
|
+
ruby-debug
|
43
|
+
ruby-debug-base
|
44
|
+
solrizer (>= 0.2.0)
|
data/History.textile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Matt Zumwalt
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.textile
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
h1. solrizer-fedora
|
2
|
+
|
3
|
+
An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.
|
4
|
+
|
5
|
+
h2. Usage
|
6
|
+
|
7
|
+
<pre>gem install solrizer-fedora</pre>
|
8
|
+
|
9
|
+
You must tell the app where to find fedora and solr. Put that information into config/fedora.yml and config/solr.yml
|
10
|
+
|
11
|
+
Then...
|
12
|
+
|
13
|
+
<pre>
|
14
|
+
irb
|
15
|
+
require "rubygems"
|
16
|
+
require "solrizer-fedora"
|
17
|
+
solrizer = Solrizer::Fedora::Solrizer.new
|
18
|
+
solrizer.solrize("demo:5")
|
19
|
+
</pre>
|
20
|
+
|
21
|
+
|
22
|
+
h2. Note on Patches/Pull Requests
|
23
|
+
|
24
|
+
* Fork the project.
|
25
|
+
* Make your feature addition or bug fix.
|
26
|
+
* Add tests for it. This is important so I don't break it in a
|
27
|
+
future version unintentionally.
|
28
|
+
* Commit, do not mess with rakefile, version, or history.
|
29
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
30
|
+
* Send me a pull request. Bonus points for topic branches.
|
31
|
+
|
32
|
+
h2. Copyright
|
33
|
+
|
34
|
+
Copyright (c) 2010 Matt Zumwalt and MediaShelf. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "solrizer-fedora"
|
8
|
+
gem.summary = %Q{An extension to solrizer that deals with Fedora objects & Repositories}
|
9
|
+
gem.description = %Q{An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.}
|
10
|
+
gem.email = "matt.zumwalt@yourmediashelf.com"
|
11
|
+
gem.homepage = "http://github.com/projecthydra/solrizer-fedora"
|
12
|
+
gem.authors = ["Matt Zumwalt"]
|
13
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
14
|
+
end
|
15
|
+
Jeweler::GemcutterTasks.new
|
16
|
+
rescue LoadError
|
17
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
18
|
+
end
|
19
|
+
|
20
|
+
require 'spec/rake/spectask'
|
21
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
22
|
+
spec.libs << 'lib' << 'spec'
|
23
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
24
|
+
end
|
25
|
+
|
26
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
27
|
+
spec.libs << 'lib' << 'spec'
|
28
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
29
|
+
spec.rcov = true
|
30
|
+
end
|
31
|
+
|
32
|
+
task :spec => :check_dependencies
|
33
|
+
|
34
|
+
task :default => :spec
|
35
|
+
|
36
|
+
require 'rake/rdoctask'
|
37
|
+
Rake::RDocTask.new do |rdoc|
|
38
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
39
|
+
|
40
|
+
rdoc.rdoc_dir = 'rdoc'
|
41
|
+
rdoc.title = "solrizer #{version}"
|
42
|
+
rdoc.rdoc_files.include('README*')
|
43
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
44
|
+
end
|
45
|
+
|
46
|
+
begin
|
47
|
+
require 'rcov/rcovtask'
|
48
|
+
Rcov::RcovTask.new do |test|
|
49
|
+
test.libs << 'test'
|
50
|
+
test.pattern = 'test/**/test_*.rb'
|
51
|
+
test.verbose = true
|
52
|
+
end
|
53
|
+
rescue LoadError
|
54
|
+
task :rcov do
|
55
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
56
|
+
end
|
57
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
data/config/fedora.yml
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
development:
|
2
|
+
fedora:
|
3
|
+
url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora
|
4
|
+
solr:
|
5
|
+
url: http://127.0.0.1:8983/solr/development
|
6
|
+
test:
|
7
|
+
fedora:
|
8
|
+
url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8983/fedora
|
9
|
+
solr:
|
10
|
+
url: http://127.0.0.1:8983/solr/test
|
11
|
+
production:
|
12
|
+
fedora:
|
13
|
+
url: http://fedoraAdmin:fedoraAdmin@127.0.0.1:8080/fedora
|
14
|
+
solr:
|
15
|
+
url: http://127.0.0.1:8080/solr
|
16
|
+
|
data/config/solr.yml
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "solrizer/fedora"
|
@@ -0,0 +1,34 @@
|
|
1
|
+
require 'solr'
|
2
|
+
require 'rexml/document'
|
3
|
+
require "nokogiri"
|
4
|
+
require 'yaml'
|
5
|
+
|
6
|
+
module Solrizer::Fedora::Extractor
|
7
|
+
|
8
|
+
#
|
9
|
+
# Extracts content-model and hydra-type from RELS-EXT datastream
|
10
|
+
#
|
11
|
+
def extract_rels_ext( text, solr_doc=Solr::Document.new )
|
12
|
+
# TODO: only read in this file once
|
13
|
+
|
14
|
+
if defined?(RAILS_ROOT)
|
15
|
+
config_path = File.join(RAILS_ROOT, "config")
|
16
|
+
else
|
17
|
+
config_path = File.join(File.dirname(__FILE__), "..", "..", "..", "config")
|
18
|
+
end
|
19
|
+
map = YAML.load(File.open(File.join(config_path, "hydra_types.yml")))
|
20
|
+
|
21
|
+
doc = Nokogiri::XML(text)
|
22
|
+
doc.xpath( '//foo:hasModel', 'foo' => 'info:fedora/fedora-system:def/model#' ).each do |element|
|
23
|
+
cmodel = element.attributes['resource'].to_s
|
24
|
+
solr_doc << Solr::Field.new( :cmodel_t => cmodel )
|
25
|
+
|
26
|
+
if map.has_key?(cmodel)
|
27
|
+
solr_doc << Solr::Field.new( :hydra_type_t => map[cmodel] )
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
return solr_doc
|
32
|
+
end
|
33
|
+
|
34
|
+
end
|
@@ -0,0 +1,213 @@
|
|
1
|
+
require 'solr'
|
2
|
+
require 'solrizer/extractor'
|
3
|
+
require 'solrizer/fedora/repository'
|
4
|
+
|
5
|
+
module Solrizer::Fedora
|
6
|
+
class Indexer
|
7
|
+
#
|
8
|
+
# Class variables
|
9
|
+
#
|
10
|
+
@@unique_id = 0
|
11
|
+
|
12
|
+
def self.unique_id
|
13
|
+
@@unique_id
|
14
|
+
end
|
15
|
+
|
16
|
+
#
|
17
|
+
# Member variables
|
18
|
+
#
|
19
|
+
attr_accessor :connection, :extractor, :index_full_text
|
20
|
+
|
21
|
+
#
|
22
|
+
# This method performs initialization tasks
|
23
|
+
#
|
24
|
+
def initialize( opts={} )
|
25
|
+
@@index_list = false unless defined?(@@index_list)
|
26
|
+
@extractor = ::Solrizer::Extractor.new
|
27
|
+
|
28
|
+
if opts[:index_full_text] == true || opts[:index_full_text] == "true"
|
29
|
+
@index_full_text = true
|
30
|
+
else
|
31
|
+
@index_full_text = false
|
32
|
+
end
|
33
|
+
|
34
|
+
connect
|
35
|
+
end
|
36
|
+
|
37
|
+
#
|
38
|
+
# This method connects to the Solr instance
|
39
|
+
#
|
40
|
+
def connect
|
41
|
+
|
42
|
+
if ActiveFedora.fedora_config.empty?
|
43
|
+
ActiveFedora.init
|
44
|
+
end
|
45
|
+
|
46
|
+
if defined?(Blacklight)
|
47
|
+
solr_config = Blacklight.solr_config
|
48
|
+
else
|
49
|
+
|
50
|
+
if defined?(RAILS_ROOT)
|
51
|
+
config_path = File.join(RAILS_ROOT, "config")
|
52
|
+
yaml = YAML.load(File.open(File.join(config_path, "solr.yml")))
|
53
|
+
solr_config = yaml[RAILS_ENV]
|
54
|
+
puts solr_config.inspect
|
55
|
+
else
|
56
|
+
config_path = File.join(File.dirname(__FILE__), "..", "..", "..", "config")
|
57
|
+
yaml = YAML.load(File.open(File.join(config_path, "solr.yml")))
|
58
|
+
|
59
|
+
|
60
|
+
if ENV["environment"].nil?
|
61
|
+
environment = "development"
|
62
|
+
else
|
63
|
+
environment = ENV["environment"]
|
64
|
+
end
|
65
|
+
|
66
|
+
solr_config = yaml[environment]
|
67
|
+
puts solr_config.inspect
|
68
|
+
end
|
69
|
+
|
70
|
+
end
|
71
|
+
|
72
|
+
if index_full_text == true
|
73
|
+
url = solr_config['fulltext']['url']
|
74
|
+
elsif solr_config.has_key?("default")
|
75
|
+
url = solr_config['default']['url']
|
76
|
+
else
|
77
|
+
url = solr_config['url']
|
78
|
+
end
|
79
|
+
@connection = Solr::Connection.new(url, :autocommit => :on )
|
80
|
+
end
|
81
|
+
|
82
|
+
#
|
83
|
+
# This method extracts the facet categories from the given Fedora object's external tag datastream
|
84
|
+
#
|
85
|
+
def extract_xml_to_solr( obj, ds_name, solr_doc=Solr::Document.new )
|
86
|
+
xml_ds = Repository.get_datastream( obj, ds_name )
|
87
|
+
extractor.xml_to_solr( xml_ds.content, solr_doc )
|
88
|
+
end
|
89
|
+
|
90
|
+
#
|
91
|
+
#
|
92
|
+
#
|
93
|
+
def extract_rels_ext( obj, ds_name, solr_doc=Solr::Document.new )
|
94
|
+
rels_ext_ds = Repository.get_datastream( obj, ds_name )
|
95
|
+
extractor.extract_rels_ext( rels_ext_ds.content, solr_doc )
|
96
|
+
end
|
97
|
+
|
98
|
+
#
|
99
|
+
# This method generates the month and day facets from the date_t in solr_doc
|
100
|
+
#
|
101
|
+
|
102
|
+
def generate_dates(solr_doc)
|
103
|
+
|
104
|
+
# This will check for valid dates, but it seems most of the dates are currently invalid....
|
105
|
+
#date_check = /^(19|20)\d\d([- \/.])(0[1-9]|1[012])\2(0[1-9]|[12][0-9]|3[01])/
|
106
|
+
|
107
|
+
#if there is not date_t, add on with easy-to-find value
|
108
|
+
if solr_doc[:date_t].nil?
|
109
|
+
solr_doc << Solr::Field.new( :date_t => "9999-99-99")
|
110
|
+
end #if
|
111
|
+
|
112
|
+
# unless date_check !~ solr_doc[:date_t]
|
113
|
+
date_obj = Date._parse(solr_doc[:date_t])
|
114
|
+
|
115
|
+
if date_obj[:mon].nil?
|
116
|
+
solr_doc << Solr::Field.new(:month_facet => 99)
|
117
|
+
elsif 0 < date_obj[:mon] && date_obj[:mon] < 13
|
118
|
+
solr_doc << Solr::Field.new( :month_facet => date_obj[:mon].to_s.rjust(2, '0'))
|
119
|
+
else
|
120
|
+
solr_doc << Solr::Field.new( :month_facet => 99)
|
121
|
+
end
|
122
|
+
|
123
|
+
if date_obj[:mday].nil?
|
124
|
+
solr_doc << Solr::Field.new( :day_facet => 99)
|
125
|
+
elsif 0 < date_obj[:mday] && date_obj[:mday] < 32
|
126
|
+
solr_doc << Solr::Field.new( :day_facet => date_obj[:mday].to_s.rjust(2, '0'))
|
127
|
+
else
|
128
|
+
solr_doc << Solr::Field.new( :day_facet => 99)
|
129
|
+
end
|
130
|
+
|
131
|
+
return solr_doc
|
132
|
+
# end
|
133
|
+
|
134
|
+
end
|
135
|
+
|
136
|
+
|
137
|
+
#
|
138
|
+
# This method creates a Solr-formatted XML document
|
139
|
+
#
|
140
|
+
def create_document( obj )
|
141
|
+
|
142
|
+
solr_doc = Solr::Document.new
|
143
|
+
|
144
|
+
model_klazz_array = ActiveFedora::ContentModel.known_models_for( obj )
|
145
|
+
model_klazz_array.delete(ActiveFedora::Base)
|
146
|
+
|
147
|
+
# If the object was passed in as an ActiveFedora::Base, call to_solr in order to get the base field entries from ActiveFedora::Base
|
148
|
+
# Otherwise, the object was passed in as a model instance other than ActiveFedora::Base,so call its to_solr method & allow it to insert the fields from ActiveFedora::Base
|
149
|
+
if obj.class == ActiveFedora::Base
|
150
|
+
solr_doc = obj.to_solr(solr_doc)
|
151
|
+
puts " added base fields from #{obj.class.to_s}"
|
152
|
+
else
|
153
|
+
solr_doc = obj.to_solr(solr_doc)
|
154
|
+
model_klazz_array.delete(obj.class)
|
155
|
+
puts " added base fields from #{obj.class.to_s} and model fields from #{obj.class.to_s}"
|
156
|
+
end
|
157
|
+
|
158
|
+
# Load the object as an instance of each of its other models and get the corresponding solr fields
|
159
|
+
# Include :model_only=>true in the options in order to avoid adding the metadata from ActiveFedora::Base every time.
|
160
|
+
model_klazz_array.each do |klazz|
|
161
|
+
instance = klazz.load_instance(obj.pid)
|
162
|
+
solr_doc = instance.to_solr(solr_doc, :model_only=>true)
|
163
|
+
puts " added solr fields from #{klazz.to_s}"
|
164
|
+
end
|
165
|
+
|
166
|
+
solr_doc << Solr::Field.new( :id_t => "#{obj.pid}" )
|
167
|
+
solr_doc << Solr::Field.new( :id => "#{obj.pid}" ) unless solr_doc[:id]
|
168
|
+
|
169
|
+
# increment the unique id to ensure that all documents in the search index are unique
|
170
|
+
@@unique_id += 1
|
171
|
+
|
172
|
+
return solr_doc
|
173
|
+
end
|
174
|
+
|
175
|
+
#
|
176
|
+
# This method adds a document to the Solr search index
|
177
|
+
#
|
178
|
+
def index( obj )
|
179
|
+
# print "Indexing '#{obj.pid}'..."
|
180
|
+
begin
|
181
|
+
|
182
|
+
solr_doc = create_document( obj )
|
183
|
+
connection.add( solr_doc )
|
184
|
+
|
185
|
+
# puts connection.url
|
186
|
+
#puts solr_doc
|
187
|
+
# puts "done"
|
188
|
+
|
189
|
+
# rescue Exception => e
|
190
|
+
# p "unable to index #{obj.pid}. Failed with #{e.inspect}"
|
191
|
+
end
|
192
|
+
|
193
|
+
end
|
194
|
+
|
195
|
+
#
|
196
|
+
# This method queries the Solr search index and returns a response
|
197
|
+
#
|
198
|
+
def query( query_str )
|
199
|
+
response = conn.query( query_str )
|
200
|
+
end
|
201
|
+
|
202
|
+
|
203
|
+
private :connect, :create_document
|
204
|
+
|
205
|
+
def class_exists?(class_name)
|
206
|
+
klass = Module.const_get(class_name)
|
207
|
+
return klass.is_a?(Class)
|
208
|
+
rescue NameError
|
209
|
+
return false
|
210
|
+
end
|
211
|
+
|
212
|
+
end
|
213
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require 'active-fedora'
|
2
|
+
|
3
|
+
module Solrizer::Fedora
|
4
|
+
class Repository
|
5
|
+
|
6
|
+
#
|
7
|
+
# This method retrieves a comprehensive list of unique ids in the fedora repository
|
8
|
+
#
|
9
|
+
def self.get_pids( num_docs )
|
10
|
+
solr_results = ActiveFedora::SolrService.instance.conn.query( "active_fedora_model_field:Document", { :rows => num_docs } )
|
11
|
+
id_array = []
|
12
|
+
solr_results.hits.each do |hit|
|
13
|
+
id_array << hit[SOLR_DOCUMENT_ID]
|
14
|
+
end
|
15
|
+
return id_array
|
16
|
+
end
|
17
|
+
|
18
|
+
#
|
19
|
+
# This method retrieves the object associated with the given unique id
|
20
|
+
#
|
21
|
+
def self.get_object( pid )
|
22
|
+
object = ActiveFedora::Base.load_instance( pid )
|
23
|
+
end
|
24
|
+
|
25
|
+
#
|
26
|
+
# This method retrieves a comprehensive list of datastreams for the given object
|
27
|
+
#
|
28
|
+
def self.get_datastreams( obj )
|
29
|
+
ds_keys = obj.datastreams.keys
|
30
|
+
end
|
31
|
+
|
32
|
+
#
|
33
|
+
# This method retrieves the datastream for the given object with the given datastream name
|
34
|
+
#
|
35
|
+
def self.get_datastream( obj, ds_name )
|
36
|
+
begin
|
37
|
+
obj.datastreams[ ds_name ]
|
38
|
+
rescue
|
39
|
+
return nil
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,118 @@
|
|
1
|
+
require 'solrizer/field_mapper.rb'
|
2
|
+
require 'solrizer/field_name_mapper'
|
3
|
+
|
4
|
+
require 'solrizer/fedora/indexer'
|
5
|
+
require 'solrizer/xml'
|
6
|
+
require 'solrizer/html'
|
7
|
+
|
8
|
+
# Let people explicitly require xml support if they want it ...
|
9
|
+
# require 'solrizer/xml.rb'
|
10
|
+
|
11
|
+
# require 'fastercsv'
|
12
|
+
require "ruby-debug"
|
13
|
+
|
14
|
+
|
15
|
+
module Solrizer::Fedora
|
16
|
+
class Solrizer
|
17
|
+
|
18
|
+
attr_accessor :indexer, :index_full_text
|
19
|
+
|
20
|
+
#
|
21
|
+
# This method initializes the indexer
|
22
|
+
# If passed an argument of :index_full_text=>true, it will perform full-text indexing instead of indexing fields only.
|
23
|
+
#
|
24
|
+
def initialize( opts={} )
|
25
|
+
@@index_list = false unless defined?(@@index_list)
|
26
|
+
if opts[:index_full_text] == true || opts[:index_full_text] == "true"
|
27
|
+
@index_full_text = true
|
28
|
+
else
|
29
|
+
@index_full_text = false
|
30
|
+
end
|
31
|
+
@indexer = Indexer.new( :index_full_text=>@index_full_text )
|
32
|
+
end
|
33
|
+
|
34
|
+
#
|
35
|
+
# This method solrizes the given Fedora object's full-text and facets into the search index
|
36
|
+
#
|
37
|
+
def solrize( obj )
|
38
|
+
# retrieve the Fedora object based on the given unique id
|
39
|
+
|
40
|
+
begin
|
41
|
+
|
42
|
+
start = Time.now
|
43
|
+
print "Retrieving object #{obj} ..."
|
44
|
+
|
45
|
+
case obj
|
46
|
+
when ActiveFedora::Base
|
47
|
+
# do nothing
|
48
|
+
when Fedora::FedoraObject
|
49
|
+
obj = Repository.get_object( obj.pid )
|
50
|
+
when String
|
51
|
+
obj = Repository.get_object( obj )
|
52
|
+
else
|
53
|
+
raise "you must pass either a ActiveFedora::Base, Fedora::RepositoryObject, or a String. You submitted a #{obj.class}"
|
54
|
+
end
|
55
|
+
|
56
|
+
# obj = obj.kind_of?(ActiveFedora::Base) ? obj : Repository.get_object( obj )
|
57
|
+
|
58
|
+
obj_done = Time.now
|
59
|
+
obj_done_elapse = obj_done - start
|
60
|
+
puts " completed. Duration: #{obj_done_elapse}"
|
61
|
+
|
62
|
+
print "\t Indexing object #{obj.pid} ... "
|
63
|
+
# add the keywords and facets to the search index
|
64
|
+
index_start = Time.now
|
65
|
+
indexer.index( obj )
|
66
|
+
|
67
|
+
index_done = Time.now
|
68
|
+
index_elapsed = index_done - index_start
|
69
|
+
|
70
|
+
puts "completed. Duration: #{index_elapsed} ."
|
71
|
+
|
72
|
+
|
73
|
+
rescue Exception => e
|
74
|
+
p "unable to index #{obj}. Failed with #{e.inspect}"
|
75
|
+
|
76
|
+
|
77
|
+
end #begin
|
78
|
+
|
79
|
+
end
|
80
|
+
|
81
|
+
#
|
82
|
+
# This method retrieves a comprehensive list of all the unique identifiers in Fedora and
|
83
|
+
# solrizes each object's full-text and facets into the search index
|
84
|
+
def solrize_objects
|
85
|
+
# retrieve a list of all the pids in the fedora repository
|
86
|
+
num_docs = 1000000 # modify this number to guarantee that all the objects are retrieved from the repository
|
87
|
+
puts "WARNING: You have turned off indexing of Full Text content. Be sure to re-run indexer with @@index_full_text set to true in main.rb" if index_full_text == false
|
88
|
+
|
89
|
+
if @@index_list == false
|
90
|
+
|
91
|
+
objects = ::Fedora::Repository.instance.find_objects(:limit=>num_docs)
|
92
|
+
|
93
|
+
puts "Shelving #{objects.length} Fedora objects"
|
94
|
+
objects.each do |object|
|
95
|
+
solrize( object )
|
96
|
+
end
|
97
|
+
|
98
|
+
else
|
99
|
+
|
100
|
+
if File.exists?(@@index_list)
|
101
|
+
arr_of_pids = FasterCSV.read(@@index_list, :headers=>false)
|
102
|
+
|
103
|
+
puts "Indexing from list at #{@@index_list}"
|
104
|
+
puts "Shelving #{arr_of_pids.length} Fedora objects"
|
105
|
+
|
106
|
+
arr_of_pids.each do |row|
|
107
|
+
pid = row[0]
|
108
|
+
solrize( pid )
|
109
|
+
end #FASTERCSV
|
110
|
+
else
|
111
|
+
puts "#{@@index_list} does not exists!"
|
112
|
+
end #if File.exists
|
113
|
+
|
114
|
+
end #if Index_LISTS
|
115
|
+
end #solrize_objects
|
116
|
+
|
117
|
+
end #class
|
118
|
+
end #module
|
@@ -0,0 +1,35 @@
|
|
1
|
+
namespace :solrizer do
|
2
|
+
|
3
|
+
namespace :fedora
|
4
|
+
desc 'Index a fedora object of the given pid.'
|
5
|
+
task :solrize => :environment do
|
6
|
+
index_full_text = ENV['FULL_TEXT'] == 'true'
|
7
|
+
if ENV['PID']
|
8
|
+
puts "indexing #{ENV['PID'].inspect}"
|
9
|
+
solrizer = Solrizer::Fedora::Solrizer.new :index_full_text=> index_full_text
|
10
|
+
solrizer.solrize(ENV['PID'])
|
11
|
+
puts "Finished shelving #{ENV['PID']}"
|
12
|
+
else
|
13
|
+
puts "You must provide a pid using the format 'solrizer::solrize_object PID=sample:pid'."
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
desc 'Index all objects in the repository.'
|
18
|
+
task :solrize_objects => :environment do
|
19
|
+
index_full_text = ENV['FULL_TEXT'] == 'true'
|
20
|
+
if ENV['INDEX_LIST']
|
21
|
+
@@index_list = ENV['INDEX_LIST']
|
22
|
+
end
|
23
|
+
|
24
|
+
puts "Re-indexing Fedora Repository."
|
25
|
+
puts "Fedora URL: #{ActiveFedora.fedora_config[:url]}"
|
26
|
+
puts "Fedora Solr URL: #{ActiveFedora.solr_config[:url]}"
|
27
|
+
puts "Blacklight Solr Config: #{Blacklight.solr_config.inspect}"
|
28
|
+
puts "Doing full text index." if index_full_text
|
29
|
+
solrizer = Solrizer::Fedora::Solrizer.new :index_full_text=> index_full_text
|
30
|
+
solrizer.solrize_objects
|
31
|
+
puts "Solrizer task complete."
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
@@ -0,0 +1,72 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{solrizer-fedora}
|
8
|
+
s.version = "0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Matt Zumwalt"]
|
12
|
+
s.date = %q{2010-10-26}
|
13
|
+
s.description = %q{An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.}
|
14
|
+
s.email = %q{matt.zumwalt@yourmediashelf.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.textile"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"Gemfile",
|
23
|
+
"Gemfile.lock",
|
24
|
+
"History.textile",
|
25
|
+
"LICENSE",
|
26
|
+
"README.textile",
|
27
|
+
"Rakefile",
|
28
|
+
"VERSION",
|
29
|
+
"config/fedora.yml",
|
30
|
+
"config/hydra_types.yml",
|
31
|
+
"config/solr.yml",
|
32
|
+
"lib/solrizer-fedora.rb",
|
33
|
+
"lib/solrizer/fedora.rb",
|
34
|
+
"lib/solrizer/fedora/extractor.rb",
|
35
|
+
"lib/solrizer/fedora/indexer.rb",
|
36
|
+
"lib/solrizer/fedora/repository.rb",
|
37
|
+
"lib/solrizer/fedora/solrizer.rb",
|
38
|
+
"lib/tasks/solrizer-fedora.rake",
|
39
|
+
"solrizer-fedora.gemspec",
|
40
|
+
"spec/fixtures/rels_ext_cmodel.xml",
|
41
|
+
"spec/integration/fedora_indexer_spec.rb",
|
42
|
+
"spec/rcov.opts",
|
43
|
+
"spec/spec.opts",
|
44
|
+
"spec/spec_helper.rb",
|
45
|
+
"spec/units/fedora_extractor_spec.rb",
|
46
|
+
"spec/units/fedora_indexer_spec.rb",
|
47
|
+
"spec/units/fedora_solrizer_spec.rb"
|
48
|
+
]
|
49
|
+
s.homepage = %q{http://github.com/projecthydra/solrizer-fedora}
|
50
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
51
|
+
s.require_paths = ["lib"]
|
52
|
+
s.rubygems_version = %q{1.3.7}
|
53
|
+
s.summary = %q{An extension to solrizer that deals with Fedora objects & Repositories}
|
54
|
+
s.test_files = [
|
55
|
+
"spec/integration/fedora_indexer_spec.rb",
|
56
|
+
"spec/spec_helper.rb",
|
57
|
+
"spec/units/fedora_extractor_spec.rb",
|
58
|
+
"spec/units/fedora_indexer_spec.rb",
|
59
|
+
"spec/units/fedora_solrizer_spec.rb"
|
60
|
+
]
|
61
|
+
|
62
|
+
if s.respond_to? :specification_version then
|
63
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
64
|
+
s.specification_version = 3
|
65
|
+
|
66
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
67
|
+
else
|
68
|
+
end
|
69
|
+
else
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
@@ -0,0 +1,8 @@
|
|
1
|
+
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
|
2
|
+
<rdf:Description rdf:about="info:fedora/demo:multipurpose-objects-model_and_sdef">
|
3
|
+
<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/fedora-system:ContentModel-3.0"/>
|
4
|
+
<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/afmodel:SaltDocument"/>
|
5
|
+
<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/afmodel:JP2Document"/>
|
6
|
+
<hasModel xmlns="info:fedora/fedora-system:def/model#" rdf:resource="info:fedora/afmodel:DCDocument"/>
|
7
|
+
</rdf:Description>
|
8
|
+
</rdf:RDF>
|
@@ -0,0 +1,18 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
|
2
|
+
require 'solrizer'
|
3
|
+
|
4
|
+
describe Solrizer::Fedora::Indexer do
|
5
|
+
|
6
|
+
before(:each) do
|
7
|
+
@indexer = Solrizer::Fedora::Indexer.new
|
8
|
+
end
|
9
|
+
|
10
|
+
describe "index" do
|
11
|
+
it "should update solr with the metadata from the given object" do
|
12
|
+
pending "Got to decide if/how to handle fixtures in this gem. Probably should just mock out Fedora & Solr entirely."
|
13
|
+
obj = Solrizer::Repository.get_object( "druid:sb733gr4073" )
|
14
|
+
@indexer.index( obj )
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
data/spec/rcov.opts
ADDED
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
2
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
3
|
+
require 'solrizer/fedora'
|
4
|
+
require 'spec'
|
5
|
+
require 'spec/autorun'
|
6
|
+
|
7
|
+
require 'solrizer'
|
8
|
+
|
9
|
+
Spec::Runner.configure do |config|
|
10
|
+
|
11
|
+
config.mock_with :mocha
|
12
|
+
|
13
|
+
|
14
|
+
def fixture(file)
|
15
|
+
File.new(File.join(File.dirname(__FILE__), 'fixtures', file))
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
|
2
|
+
require 'solrizer'
|
3
|
+
|
4
|
+
describe Solrizer::Fedora::Extractor do
|
5
|
+
|
6
|
+
before(:all) do
|
7
|
+
@extractor = Solrizer::Extractor.new
|
8
|
+
end
|
9
|
+
|
10
|
+
describe "extract_rels_ext" do
|
11
|
+
it "should extract the content model of the RELS-EXT datastream of a Fedora object and set hydra_type using hydra_types mapping" do
|
12
|
+
rels_ext = fixture("rels_ext_cmodel.xml")
|
13
|
+
result = @extractor.extract_rels_ext( rels_ext )
|
14
|
+
result[:cmodel_t].should == "info:fedora/fedora-system:ContentModel-3.0"
|
15
|
+
result[:hydra_type_t].should == "salt_document"
|
16
|
+
|
17
|
+
# ... and a hacky way of making sure that it added a field for each of the dc:medium values
|
18
|
+
result.inspect.include?('@value="info:fedora/afmodel:SaltDocument"').should be_true
|
19
|
+
result.inspect.include?('@value="jp2_document"').should be_true
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
describe "extract_hydra_types" do
|
24
|
+
it "should extract the hydra_type of a Fedora object" do
|
25
|
+
rels_ext = fixture("rels_ext_cmodel.xml")
|
26
|
+
result = @extractor.extract_rels_ext( rels_ext )
|
27
|
+
result[:hydra_type_t].should == "salt_document"
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
@@ -0,0 +1,78 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
|
2
|
+
require 'solrizer'
|
3
|
+
require "solrizer/fedora"
|
4
|
+
|
5
|
+
describe Solrizer::Fedora::Indexer do
|
6
|
+
|
7
|
+
before(:each) do
|
8
|
+
Solrizer::Fedora::Indexer.any_instance.stubs(:connect).returns("foo")
|
9
|
+
|
10
|
+
@extractor = mock("Extractor")
|
11
|
+
@extractor.stubs(:html_content_to_solr).returns(@solr_doc)
|
12
|
+
# @solr_doc = mock('solr_doc')
|
13
|
+
# @solr_doc.stubs(:<<)
|
14
|
+
# @solr_doc.stubs(:[])
|
15
|
+
|
16
|
+
@solr_doc = Solr::Document.new
|
17
|
+
|
18
|
+
Solrizer::Extractor.expects(:new).returns(@extractor)
|
19
|
+
@indexer = Solrizer::Fedora::Indexer.new
|
20
|
+
|
21
|
+
end
|
22
|
+
|
23
|
+
describe "#generate_dates" do
|
24
|
+
it "should still give 9999-99-99 date if the solr document does not have a date_t field" do
|
25
|
+
|
26
|
+
solr_result = @indexer.generate_dates(@solr_doc)
|
27
|
+
solr_result.should be_kind_of Solr::Document
|
28
|
+
solr_result[:date_t].should == "9999-99-99"
|
29
|
+
solr_result[:month_facet].should == "99"
|
30
|
+
solr_result[:day_facet].should == '99'
|
31
|
+
|
32
|
+
end
|
33
|
+
|
34
|
+
it "should still give 9999-99-99 date if the solr_doc[:date_t] is not valid date in YYYY-MM-DD format " do
|
35
|
+
|
36
|
+
@solr_doc << Solr::Field.new(:date_t => "Unknown")
|
37
|
+
solr_result = @indexer.generate_dates(@solr_doc)
|
38
|
+
solr_result.should be_kind_of Solr::Document
|
39
|
+
solr_result[:date_t].should == "Unknown"
|
40
|
+
solr_result[:month_facet].should == "99"
|
41
|
+
solr_result[:day_facet].should == '99'
|
42
|
+
|
43
|
+
end
|
44
|
+
|
45
|
+
it "should give month and dates even if the :date_t is not a valid date but is in YYYY-MM-DD format " do
|
46
|
+
|
47
|
+
@solr_doc << Solr::Field.new(:date_t => "0000-13-11")
|
48
|
+
solr_result = @indexer.generate_dates(@solr_doc)
|
49
|
+
solr_result.should be_kind_of Solr::Document
|
50
|
+
solr_result[:date_t].should == "0000-13-11"
|
51
|
+
solr_result[:month_facet].should == "99"
|
52
|
+
solr_result[:day_facet].should == '11'
|
53
|
+
end
|
54
|
+
|
55
|
+
it "should give month and day when in a valid date format" do
|
56
|
+
@solr_doc << Solr::Field.new(:date_t => "1978-04-11")
|
57
|
+
solr_result = @indexer.generate_dates(@solr_doc)
|
58
|
+
solr_result.should be_kind_of Solr::Document
|
59
|
+
solr_result[:date_t].should == "1978-04-11"
|
60
|
+
solr_result[:month_facet].should == "04"
|
61
|
+
solr_result[:day_facet].should == '11'
|
62
|
+
|
63
|
+
end
|
64
|
+
|
65
|
+
it "should still give two digit strings even if the month/day is single digit" do
|
66
|
+
|
67
|
+
@solr_doc << Solr::Field.new(:date_t => "1978-4-1")
|
68
|
+
solr_result = @indexer.generate_dates(@solr_doc)
|
69
|
+
solr_result.should be_kind_of Solr::Document
|
70
|
+
solr_result[:date_t].should == "1978-4-1"
|
71
|
+
solr_result[:month_facet].should == "04"
|
72
|
+
solr_result[:day_facet].should == '01'
|
73
|
+
|
74
|
+
end
|
75
|
+
|
76
|
+
end
|
77
|
+
|
78
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
|
2
|
+
|
3
|
+
describe Solrizer::Fedora::Solrizer do
|
4
|
+
|
5
|
+
before(:each) do
|
6
|
+
@solrizer = Solrizer::Fedora::Solrizer.new
|
7
|
+
end
|
8
|
+
|
9
|
+
describe "solrize" do
|
10
|
+
it "should trigger the indexer for the provided object" do
|
11
|
+
sample_obj = ActiveFedora::Base.new
|
12
|
+
@solrizer.indexer.expects(:index).with( sample_obj )
|
13
|
+
@solrizer.solrize( sample_obj )
|
14
|
+
end
|
15
|
+
it "should work with Fedora::FedoraObject objects" do
|
16
|
+
mock_object = Fedora::FedoraObject.new(:pid=>"my:pid", :label=>"my label")
|
17
|
+
ActiveFedora::Base.expects(:load_instance).with( mock_object.pid ).returns(mock_object)
|
18
|
+
@solrizer.indexer.expects(:index).with( mock_object )
|
19
|
+
@solrizer.solrize( mock_object )
|
20
|
+
end
|
21
|
+
it "should load the object if only a pid is provided" do
|
22
|
+
mock_object = mock("my object")
|
23
|
+
mock_object.stubs(:pid)
|
24
|
+
mock_object.stubs(:label)
|
25
|
+
mock_object.stubs(:datastreams).returns({'descMetadata'=>"foo","location"=>"bar"})
|
26
|
+
|
27
|
+
ActiveFedora::Base.expects(:load_instance).with( "_PID_" ).returns(mock_object)
|
28
|
+
@solrizer.indexer.expects(:index).with(mock_object)
|
29
|
+
@solrizer.solrize("_PID_")
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
33
|
+
|
34
|
+
describe "solrize_objects" do
|
35
|
+
it "should call solrize for each object returned by Fedora::Repository.find_objects" do
|
36
|
+
objects = [["pid1"], ["pid2"], ["pid3"]]
|
37
|
+
Fedora::Repository.any_instance.expects(:find_objects).returns(objects)
|
38
|
+
objects.each {|object| @solrizer.expects(:solrize).with( object ) }
|
39
|
+
@solrizer.solrize_objects
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
metadata
ADDED
@@ -0,0 +1,99 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: solrizer-fedora
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Matt Zumwalt
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-10-26 00:00:00 -05:00
|
19
|
+
default_executable:
|
20
|
+
dependencies: []
|
21
|
+
|
22
|
+
description: An extension to projecthydra/solrizer that provides utilities for loading objects from Fedora Repositories and creating solr documents from them.
|
23
|
+
email: matt.zumwalt@yourmediashelf.com
|
24
|
+
executables: []
|
25
|
+
|
26
|
+
extensions: []
|
27
|
+
|
28
|
+
extra_rdoc_files:
|
29
|
+
- LICENSE
|
30
|
+
- README.textile
|
31
|
+
files:
|
32
|
+
- .document
|
33
|
+
- .gitignore
|
34
|
+
- Gemfile
|
35
|
+
- Gemfile.lock
|
36
|
+
- History.textile
|
37
|
+
- LICENSE
|
38
|
+
- README.textile
|
39
|
+
- Rakefile
|
40
|
+
- VERSION
|
41
|
+
- config/fedora.yml
|
42
|
+
- config/hydra_types.yml
|
43
|
+
- config/solr.yml
|
44
|
+
- lib/solrizer-fedora.rb
|
45
|
+
- lib/solrizer/fedora.rb
|
46
|
+
- lib/solrizer/fedora/extractor.rb
|
47
|
+
- lib/solrizer/fedora/indexer.rb
|
48
|
+
- lib/solrizer/fedora/repository.rb
|
49
|
+
- lib/solrizer/fedora/solrizer.rb
|
50
|
+
- lib/tasks/solrizer-fedora.rake
|
51
|
+
- solrizer-fedora.gemspec
|
52
|
+
- spec/fixtures/rels_ext_cmodel.xml
|
53
|
+
- spec/integration/fedora_indexer_spec.rb
|
54
|
+
- spec/rcov.opts
|
55
|
+
- spec/spec.opts
|
56
|
+
- spec/spec_helper.rb
|
57
|
+
- spec/units/fedora_extractor_spec.rb
|
58
|
+
- spec/units/fedora_indexer_spec.rb
|
59
|
+
- spec/units/fedora_solrizer_spec.rb
|
60
|
+
has_rdoc: true
|
61
|
+
homepage: http://github.com/projecthydra/solrizer-fedora
|
62
|
+
licenses: []
|
63
|
+
|
64
|
+
post_install_message:
|
65
|
+
rdoc_options:
|
66
|
+
- --charset=UTF-8
|
67
|
+
require_paths:
|
68
|
+
- lib
|
69
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
70
|
+
none: false
|
71
|
+
requirements:
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
hash: 3
|
75
|
+
segments:
|
76
|
+
- 0
|
77
|
+
version: "0"
|
78
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
79
|
+
none: false
|
80
|
+
requirements:
|
81
|
+
- - ">="
|
82
|
+
- !ruby/object:Gem::Version
|
83
|
+
hash: 3
|
84
|
+
segments:
|
85
|
+
- 0
|
86
|
+
version: "0"
|
87
|
+
requirements: []
|
88
|
+
|
89
|
+
rubyforge_project:
|
90
|
+
rubygems_version: 1.3.7
|
91
|
+
signing_key:
|
92
|
+
specification_version: 3
|
93
|
+
summary: An extension to solrizer that deals with Fedora objects & Repositories
|
94
|
+
test_files:
|
95
|
+
- spec/integration/fedora_indexer_spec.rb
|
96
|
+
- spec/spec_helper.rb
|
97
|
+
- spec/units/fedora_extractor_spec.rb
|
98
|
+
- spec/units/fedora_indexer_spec.rb
|
99
|
+
- spec/units/fedora_solrizer_spec.rb
|