solrizer 2.0.0.rc1 → 2.0.0.rc2
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +1 -1
- data/lib/solrizer/version.rb +1 -1
- data/lib/solrizer/xml/terminology_based_solrizer.rb +1 -1
- data/solrizer.gemspec +1 -0
- data/spec/fixtures/mods_article.rb +4 -4
- data/spec/units/xml_terminology_based_solrizer_spec.rb +19 -1
- metadata +180 -166
data/Rakefile
CHANGED
data/lib/solrizer/version.rb
CHANGED
@@ -56,7 +56,7 @@ module Solrizer::XML::TerminologyBasedSolrizer
|
|
56
56
|
# @param [Hash] (optional) solr_doc (values hash) to populate
|
57
57
|
# @return [Hash] the solr doc
|
58
58
|
def self.solrize_node(node, doc, term_pointer, term, solr_doc = Hash.new, field_mapper = nil, opts = {})
|
59
|
-
return solr_doc unless term.index_as
|
59
|
+
return solr_doc unless term.index_as && !term.index_as.empty?
|
60
60
|
field_mapper ||= self.default_field_mapper
|
61
61
|
terminology = doc.class.terminology
|
62
62
|
|
data/solrizer.gemspec
CHANGED
@@ -20,6 +20,7 @@ Gem::Specification.new do |s|
|
|
20
20
|
s.add_dependency "daemons"
|
21
21
|
s.add_development_dependency 'rspec', '~>2.0'
|
22
22
|
s.add_development_dependency 'rake'
|
23
|
+
s.add_development_dependency 'rdoc'
|
23
24
|
s.add_development_dependency 'mocha'
|
24
25
|
s.add_development_dependency 'yard'
|
25
26
|
s.add_development_dependency 'RedCloth'
|
@@ -18,7 +18,7 @@ module Samples
|
|
18
18
|
t.language{
|
19
19
|
t.lang_code(:index_as=>[:facetable], :path=>"languageTerm", :attributes=>{:type=>"code"})
|
20
20
|
}
|
21
|
-
t.abstract(:index_as=>[])
|
21
|
+
t.abstract(:index_as=>[:searchable])
|
22
22
|
t.subject {
|
23
23
|
t.topic(:index_as=>[:facetable])
|
24
24
|
}
|
@@ -35,7 +35,7 @@ module Samples
|
|
35
35
|
t.role(:ref=>[:role])
|
36
36
|
t.description(:index_as=>[:facetable])
|
37
37
|
t.date(:path=>"namePart", :attributes=>{:type=>"date"})
|
38
|
-
t.last_name(:path=>"namePart", :attributes=>{:type=>"family"}, :index_as=>[])
|
38
|
+
t.last_name(:path=>"namePart", :attributes=>{:type=>"family"}, :index_as=>[:searchable])
|
39
39
|
t.first_name(:path=>"namePart", :attributes=>{:type=>"given"}, :label=>"first name")
|
40
40
|
t.terms_of_address(:path=>"namePart", :attributes=>{:type=>"termsOfAddress"})
|
41
41
|
t.computing_id
|
@@ -47,7 +47,7 @@ module Samples
|
|
47
47
|
t.organization(:ref=>:name, :attributes=>{:type=>"corporate"}, :index_as=>[:facetable])
|
48
48
|
t.conference(:ref=>:name, :attributes=>{:type=>"conference"}, :index_as=>[:facetable])
|
49
49
|
t.role {
|
50
|
-
t.text(:path=>"roleTerm",:attributes=>{:type=>"text"}, :index_as=>[])
|
50
|
+
t.text(:path=>"roleTerm",:attributes=>{:type=>"text"}, :index_as=>[:searchable])
|
51
51
|
t.code(:path=>"roleTerm",:attributes=>{:type=>"code"})
|
52
52
|
}
|
53
53
|
t.journal(:path=>'relatedItem', :attributes=>{:type=>"host"}) {
|
@@ -68,7 +68,7 @@ module Samples
|
|
68
68
|
}
|
69
69
|
t.start_page(:proxy=>[:pages, :start])
|
70
70
|
t.end_page(:proxy=>[:pages, :end])
|
71
|
-
t.publication_date(:path=>"date", :index_as=>[])
|
71
|
+
t.publication_date(:path=>"date", :index_as=>[:searchable])
|
72
72
|
}
|
73
73
|
}
|
74
74
|
t.note
|
@@ -55,7 +55,6 @@ describe Solrizer::XML::TerminologyBasedSolrizer do
|
|
55
55
|
solr_doc["topic_tag_t"].sort.should == ["CONTROLLED TERM", "TOPIC 1", "TOPIC 2"]
|
56
56
|
|
57
57
|
# These are a holdover from an old verison of OM
|
58
|
-
puts "DOC: #{solr_doc.length}"
|
59
58
|
solr_doc['journal_0_issue_0_publication_date_t'].should == ["FEB. 2007"]
|
60
59
|
|
61
60
|
|
@@ -85,6 +84,25 @@ describe Solrizer::XML::TerminologyBasedSolrizer do
|
|
85
84
|
{suffix => actual_names}.should == {suffix => expected_names}
|
86
85
|
end
|
87
86
|
end
|
87
|
+
|
88
|
+
it "shouldn't index terms where index_as is an empty array" do
|
89
|
+
fake_solr_doc = {}
|
90
|
+
term = Samples::ModsArticle.terminology.retrieve_term(:name)
|
91
|
+
term.children[:namePart].index_as = []# [:displayable, :facetable]
|
92
|
+
|
93
|
+
@mods_article.solrize_term(term, fake_solr_doc)
|
94
|
+
fake_solr_doc["name_0_namePart_t"].should be_nil
|
95
|
+
end
|
96
|
+
|
97
|
+
it "shouldn't index terms where index_as is searchable" do
|
98
|
+
fake_solr_doc = {}
|
99
|
+
term = Samples::ModsArticle.terminology.retrieve_term(:name)
|
100
|
+
term.children[:namePart].index_as = [:searchable]
|
101
|
+
|
102
|
+
@mods_article.solrize_term(term, fake_solr_doc)
|
103
|
+
|
104
|
+
fake_solr_doc["name_0_namePart_t"].sort.should == ["DR.", "FAMILY NAME", "GIVEN NAMES"]
|
105
|
+
end
|
88
106
|
|
89
107
|
end
|
90
108
|
|
metadata
CHANGED
@@ -1,195 +1,219 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: solrizer
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 2.0.0.rc2
|
5
5
|
prerelease: 6
|
6
|
-
segments:
|
7
|
-
- 2
|
8
|
-
- 0
|
9
|
-
- 0
|
10
|
-
- rc
|
11
|
-
- 1
|
12
|
-
version: 2.0.0.rc1
|
13
6
|
platform: ruby
|
14
|
-
authors:
|
7
|
+
authors:
|
15
8
|
- Matt Zumwalt
|
16
9
|
autorequire:
|
17
10
|
bindir: bin
|
18
11
|
cert_chain: []
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
dependencies:
|
23
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2012-10-25 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
24
15
|
name: nokogiri
|
25
|
-
|
26
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
27
17
|
none: false
|
28
|
-
requirements:
|
29
|
-
- -
|
30
|
-
- !ruby/object:Gem::Version
|
31
|
-
|
32
|
-
segments:
|
33
|
-
- 0
|
34
|
-
version: "0"
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
35
22
|
type: :runtime
|
36
|
-
version_requirements: *id001
|
37
|
-
- !ruby/object:Gem::Dependency
|
38
|
-
name: om
|
39
23
|
prerelease: false
|
40
|
-
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
25
|
none: false
|
42
|
-
requirements:
|
43
|
-
- -
|
44
|
-
- !ruby/object:Gem::Version
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: om
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
50
37
|
version: 1.5.0
|
51
38
|
type: :runtime
|
52
|
-
version_requirements: *id002
|
53
|
-
- !ruby/object:Gem::Dependency
|
54
|
-
name: xml-simple
|
55
39
|
prerelease: false
|
56
|
-
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
41
|
none: false
|
58
|
-
requirements:
|
59
|
-
- -
|
60
|
-
- !ruby/object:Gem::Version
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 1.5.0
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: xml-simple
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
65
54
|
type: :runtime
|
66
|
-
version_requirements: *id003
|
67
|
-
- !ruby/object:Gem::Dependency
|
68
|
-
name: mediashelf-loggable
|
69
55
|
prerelease: false
|
70
|
-
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: mediashelf-loggable
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
71
65
|
none: false
|
72
|
-
requirements:
|
66
|
+
requirements:
|
73
67
|
- - ~>
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
hash: 1
|
76
|
-
segments:
|
77
|
-
- 0
|
78
|
-
- 4
|
79
|
-
- 7
|
68
|
+
- !ruby/object:Gem::Version
|
80
69
|
version: 0.4.7
|
81
70
|
type: :runtime
|
82
|
-
version_requirements: *id004
|
83
|
-
- !ruby/object:Gem::Dependency
|
84
|
-
name: stomp
|
85
71
|
prerelease: false
|
86
|
-
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ~>
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: 0.4.7
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: stomp
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
87
81
|
none: false
|
88
|
-
requirements:
|
89
|
-
- -
|
90
|
-
- !ruby/object:Gem::Version
|
91
|
-
|
92
|
-
segments:
|
93
|
-
- 0
|
94
|
-
version: "0"
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
95
86
|
type: :runtime
|
96
|
-
version_requirements: *id005
|
97
|
-
- !ruby/object:Gem::Dependency
|
98
|
-
name: daemons
|
99
87
|
prerelease: false
|
100
|
-
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
101
89
|
none: false
|
102
|
-
requirements:
|
103
|
-
- -
|
104
|
-
- !ruby/object:Gem::Version
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
90
|
+
requirements:
|
91
|
+
- - ! '>='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: daemons
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ! '>='
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
109
102
|
type: :runtime
|
110
|
-
version_requirements: *id006
|
111
|
-
- !ruby/object:Gem::Dependency
|
112
|
-
name: rspec
|
113
103
|
prerelease: false
|
114
|
-
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
115
105
|
none: false
|
116
|
-
requirements:
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
- !ruby/object:Gem::Dependency
|
111
|
+
name: rspec
|
112
|
+
requirement: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
117
115
|
- - ~>
|
118
|
-
- !ruby/object:Gem::Version
|
119
|
-
|
120
|
-
segments:
|
121
|
-
- 2
|
122
|
-
- 0
|
123
|
-
version: "2.0"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '2.0'
|
124
118
|
type: :development
|
125
|
-
|
126
|
-
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
none: false
|
122
|
+
requirements:
|
123
|
+
- - ~>
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '2.0'
|
126
|
+
- !ruby/object:Gem::Dependency
|
127
127
|
name: rake
|
128
|
+
requirement: !ruby/object:Gem::Requirement
|
129
|
+
none: false
|
130
|
+
requirements:
|
131
|
+
- - ! '>='
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0'
|
134
|
+
type: :development
|
128
135
|
prerelease: false
|
129
|
-
|
136
|
+
version_requirements: !ruby/object:Gem::Requirement
|
137
|
+
none: false
|
138
|
+
requirements:
|
139
|
+
- - ! '>='
|
140
|
+
- !ruby/object:Gem::Version
|
141
|
+
version: '0'
|
142
|
+
- !ruby/object:Gem::Dependency
|
143
|
+
name: rdoc
|
144
|
+
requirement: !ruby/object:Gem::Requirement
|
130
145
|
none: false
|
131
|
-
requirements:
|
132
|
-
- -
|
133
|
-
- !ruby/object:Gem::Version
|
134
|
-
|
135
|
-
segments:
|
136
|
-
- 0
|
137
|
-
version: "0"
|
146
|
+
requirements:
|
147
|
+
- - ! '>='
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '0'
|
138
150
|
type: :development
|
139
|
-
version_requirements: *id008
|
140
|
-
- !ruby/object:Gem::Dependency
|
141
|
-
name: mocha
|
142
151
|
prerelease: false
|
143
|
-
|
152
|
+
version_requirements: !ruby/object:Gem::Requirement
|
144
153
|
none: false
|
145
|
-
requirements:
|
146
|
-
- -
|
147
|
-
- !ruby/object:Gem::Version
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
154
|
+
requirements:
|
155
|
+
- - ! '>='
|
156
|
+
- !ruby/object:Gem::Version
|
157
|
+
version: '0'
|
158
|
+
- !ruby/object:Gem::Dependency
|
159
|
+
name: mocha
|
160
|
+
requirement: !ruby/object:Gem::Requirement
|
161
|
+
none: false
|
162
|
+
requirements:
|
163
|
+
- - ! '>='
|
164
|
+
- !ruby/object:Gem::Version
|
165
|
+
version: '0'
|
152
166
|
type: :development
|
153
|
-
version_requirements: *id009
|
154
|
-
- !ruby/object:Gem::Dependency
|
155
|
-
name: yard
|
156
167
|
prerelease: false
|
157
|
-
|
168
|
+
version_requirements: !ruby/object:Gem::Requirement
|
158
169
|
none: false
|
159
|
-
requirements:
|
160
|
-
- -
|
161
|
-
- !ruby/object:Gem::Version
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
170
|
+
requirements:
|
171
|
+
- - ! '>='
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '0'
|
174
|
+
- !ruby/object:Gem::Dependency
|
175
|
+
name: yard
|
176
|
+
requirement: !ruby/object:Gem::Requirement
|
177
|
+
none: false
|
178
|
+
requirements:
|
179
|
+
- - ! '>='
|
180
|
+
- !ruby/object:Gem::Version
|
181
|
+
version: '0'
|
166
182
|
type: :development
|
167
|
-
version_requirements: *id010
|
168
|
-
- !ruby/object:Gem::Dependency
|
169
|
-
name: RedCloth
|
170
183
|
prerelease: false
|
171
|
-
|
184
|
+
version_requirements: !ruby/object:Gem::Requirement
|
172
185
|
none: false
|
173
|
-
requirements:
|
174
|
-
- -
|
175
|
-
- !ruby/object:Gem::Version
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
186
|
+
requirements:
|
187
|
+
- - ! '>='
|
188
|
+
- !ruby/object:Gem::Version
|
189
|
+
version: '0'
|
190
|
+
- !ruby/object:Gem::Dependency
|
191
|
+
name: RedCloth
|
192
|
+
requirement: !ruby/object:Gem::Requirement
|
193
|
+
none: false
|
194
|
+
requirements:
|
195
|
+
- - ! '>='
|
196
|
+
- !ruby/object:Gem::Version
|
197
|
+
version: '0'
|
180
198
|
type: :development
|
181
|
-
|
182
|
-
|
199
|
+
prerelease: false
|
200
|
+
version_requirements: !ruby/object:Gem::Requirement
|
201
|
+
none: false
|
202
|
+
requirements:
|
203
|
+
- - ! '>='
|
204
|
+
- !ruby/object:Gem::Version
|
205
|
+
version: '0'
|
206
|
+
description: Use solrizer to populate solr indexes. You can run solrizer from within
|
207
|
+
your app, using the provided rake tasks, or as a JMS listener
|
183
208
|
email: hydra-tech@googlegroups.com
|
184
|
-
executables:
|
209
|
+
executables:
|
185
210
|
- solrizer
|
186
211
|
- solrizerd
|
187
212
|
extensions: []
|
188
|
-
|
189
|
-
extra_rdoc_files:
|
213
|
+
extra_rdoc_files:
|
190
214
|
- LICENSE
|
191
215
|
- README.textile
|
192
|
-
files:
|
216
|
+
files:
|
193
217
|
- .gitignore
|
194
218
|
- Gemfile
|
195
219
|
- History.txt
|
@@ -232,43 +256,32 @@ files:
|
|
232
256
|
- spec/units/field_name_mapper_spec.rb
|
233
257
|
- spec/units/xml_extractor_spec.rb
|
234
258
|
- spec/units/xml_terminology_based_solrizer_spec.rb
|
235
|
-
has_rdoc: true
|
236
259
|
homepage: http://github.com/projecthydra/solrizer
|
237
260
|
licenses: []
|
238
|
-
|
239
261
|
post_install_message:
|
240
262
|
rdoc_options: []
|
241
|
-
|
242
|
-
require_paths:
|
263
|
+
require_paths:
|
243
264
|
- lib
|
244
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
265
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
245
266
|
none: false
|
246
|
-
requirements:
|
247
|
-
- -
|
248
|
-
- !ruby/object:Gem::Version
|
249
|
-
|
250
|
-
|
251
|
-
- 0
|
252
|
-
version: "0"
|
253
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
267
|
+
requirements:
|
268
|
+
- - ! '>='
|
269
|
+
- !ruby/object:Gem::Version
|
270
|
+
version: '0'
|
271
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
254
272
|
none: false
|
255
|
-
requirements:
|
256
|
-
- -
|
257
|
-
- !ruby/object:Gem::Version
|
258
|
-
hash: 25
|
259
|
-
segments:
|
260
|
-
- 1
|
261
|
-
- 3
|
262
|
-
- 1
|
273
|
+
requirements:
|
274
|
+
- - ! '>'
|
275
|
+
- !ruby/object:Gem::Version
|
263
276
|
version: 1.3.1
|
264
277
|
requirements: []
|
265
|
-
|
266
278
|
rubyforge_project:
|
267
|
-
rubygems_version: 1.
|
279
|
+
rubygems_version: 1.8.24
|
268
280
|
signing_key:
|
269
281
|
specification_version: 3
|
270
|
-
summary: A utility for building solr indexes, usually from Fedora repository content
|
271
|
-
|
282
|
+
summary: A utility for building solr indexes, usually from Fedora repository content
|
283
|
+
with solrizer-fedora extension gem.
|
284
|
+
test_files:
|
272
285
|
- spec/fixtures/druid-bv448hq0314-descMetadata.xml
|
273
286
|
- spec/fixtures/druid-bv448hq0314-extProperties.xml
|
274
287
|
- spec/fixtures/druid-cm234kq4672-extProperties.xml
|
@@ -283,3 +296,4 @@ test_files:
|
|
283
296
|
- spec/units/field_name_mapper_spec.rb
|
284
297
|
- spec/units/xml_extractor_spec.rb
|
285
298
|
- spec/units/xml_terminology_based_solrizer_spec.rb
|
299
|
+
has_rdoc:
|