solrizer 0.1.0.pre2
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +19 -0
- data/LICENSE +20 -0
- data/README.rdoc +17 -0
- data/Rakefile +46 -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.rb +101 -0
- data/lib/solrizer/configuration.rb +8 -0
- data/lib/solrizer/extractor.rb +89 -0
- data/lib/solrizer/indexer.rb +261 -0
- data/lib/solrizer/main.rb +17 -0
- data/lib/solrizer/replicator.rb +143 -0
- data/lib/solrizer/repository.rb +54 -0
- data/lib/tasks/solrizer.rake +33 -0
- data/solrizer.gemspec +80 -0
- data/spec/fixtures/druid-bv448hq0314-descMetadata.xml +11 -0
- data/spec/fixtures/druid-bv448hq0314-extProperties.xml +52 -0
- data/spec/fixtures/druid-cm234kq4672-extProperties.xml +5 -0
- data/spec/fixtures/druid-cm234kq4672-stories.xml +17 -0
- data/spec/fixtures/druid-hc513kw4806-descMetadata.xml +11 -0
- data/spec/fixtures/rels_ext_cmodel.xml +8 -0
- data/spec/integration/indexer_spec.rb +18 -0
- data/spec/rcov.opts +2 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +16 -0
- data/spec/units/extractor_spec.rb +50 -0
- data/spec/units/indexer_spec.rb +127 -0
- data/spec/units/shelver_spec.rb +42 -0
- metadata +126 -0
data/.gitignore
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.rdoc
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
= foo
|
2
|
+
|
3
|
+
Description goes here.
|
4
|
+
|
5
|
+
== Note on Patches/Pull Requests
|
6
|
+
|
7
|
+
* Fork the project.
|
8
|
+
* Make your feature addition or bug fix.
|
9
|
+
* Add tests for it. This is important so I don't break it in a
|
10
|
+
future version unintentionally.
|
11
|
+
* Commit, do not mess with rakefile, version, or history.
|
12
|
+
(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)
|
13
|
+
* Send me a pull request. Bonus points for topic branches.
|
14
|
+
|
15
|
+
== Copyright
|
16
|
+
|
17
|
+
Copyright (c) 2010 Matt Zumwalt. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "solrizer"
|
8
|
+
gem.summary = %Q{A utility for building solr indexes, usually from Fedora repository content.}
|
9
|
+
gem.description = %Q{Use solrizer to populate solr indexes from Fedora repository content or from other sources. You can run solrizer from within your apps, using the provided rake tasks, or as a JMS listener}
|
10
|
+
gem.email = "matt.zumwalt@yourmediashelf.com"
|
11
|
+
gem.homepage = "http://github.com/projecthydra/solrizer"
|
12
|
+
gem.authors = ["Matt Zumwalt"]
|
13
|
+
gem.add_dependency "active-fedora", "> 1.1.3"
|
14
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
15
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
16
|
+
end
|
17
|
+
Jeweler::GemcutterTasks.new
|
18
|
+
rescue LoadError
|
19
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
20
|
+
end
|
21
|
+
|
22
|
+
require 'spec/rake/spectask'
|
23
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
24
|
+
spec.libs << 'lib' << 'spec'
|
25
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
26
|
+
end
|
27
|
+
|
28
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
29
|
+
spec.libs << 'lib' << 'spec'
|
30
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
31
|
+
spec.rcov = true
|
32
|
+
end
|
33
|
+
|
34
|
+
task :spec => :check_dependencies
|
35
|
+
|
36
|
+
task :default => :spec
|
37
|
+
|
38
|
+
require 'rake/rdoctask'
|
39
|
+
Rake::RDocTask.new do |rdoc|
|
40
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
41
|
+
|
42
|
+
rdoc.rdoc_dir = 'rdoc'
|
43
|
+
rdoc.title = "solrizer #{version}"
|
44
|
+
rdoc.rdoc_files.include('README*')
|
45
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
46
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0.pre2
|
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
data/lib/solrizer.rb
ADDED
@@ -0,0 +1,101 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'solrizer/indexer.rb'
|
3
|
+
# require 'fastercsv'
|
4
|
+
require "ruby-debug"
|
5
|
+
|
6
|
+
|
7
|
+
|
8
|
+
module Solrizer
|
9
|
+
class Solrizer
|
10
|
+
|
11
|
+
attr_accessor :indexer, :index_full_text
|
12
|
+
|
13
|
+
#
|
14
|
+
# This method initializes the indexer
|
15
|
+
# If passed an argument of :index_full_text=>true, it will perform full-text indexing instead of indexing fields only.
|
16
|
+
#
|
17
|
+
def initialize( opts={} )
|
18
|
+
@@index_list = false unless defined?(@@index_list)
|
19
|
+
if opts[:index_full_text] == true || opts[:index_full_text] == "true"
|
20
|
+
@index_full_text = true
|
21
|
+
else
|
22
|
+
@index_full_text = false
|
23
|
+
end
|
24
|
+
@indexer = Indexer.new( :index_full_text=>@index_full_text )
|
25
|
+
end
|
26
|
+
|
27
|
+
#
|
28
|
+
# This method solrizes the given Fedora object's full-text and facets into the search index
|
29
|
+
#
|
30
|
+
def solrize( obj )
|
31
|
+
# retrieve the Fedora object based on the given unique id
|
32
|
+
|
33
|
+
begin
|
34
|
+
|
35
|
+
start = Time.now
|
36
|
+
print "Retrieving object #{obj} ..."
|
37
|
+
obj = obj.kind_of?(ActiveFedora::Base) ? obj : Repository.get_object( obj )
|
38
|
+
|
39
|
+
obj_done = Time.now
|
40
|
+
obj_done_elapse = obj_done - start
|
41
|
+
puts " completed. Duration: #{obj_done_elapse}"
|
42
|
+
|
43
|
+
print "\t Indexing object #{obj.pid} ... "
|
44
|
+
# add the keywords and facets to the search index
|
45
|
+
index_start = Time.now
|
46
|
+
indexer.index( obj )
|
47
|
+
|
48
|
+
index_done = Time.now
|
49
|
+
index_elapsed = index_done - index_start
|
50
|
+
|
51
|
+
puts "completed. Duration: #{index_elapsed} ."
|
52
|
+
|
53
|
+
|
54
|
+
rescue Exception => e
|
55
|
+
p "unable to index #{obj}. Failed with #{e.inspect}"
|
56
|
+
|
57
|
+
|
58
|
+
end #begin
|
59
|
+
|
60
|
+
end
|
61
|
+
|
62
|
+
#
|
63
|
+
# This method retrieves a comprehensive list of all the unique identifiers in Fedora and
|
64
|
+
# solrizes each object's full-text and facets into the search index
|
65
|
+
#
|
66
|
+
def solrize_objects
|
67
|
+
# retrieve a list of all the pids in the fedora repository
|
68
|
+
num_docs = 1000000 # modify this number to guarantee that all the objects are retrieved from the repository
|
69
|
+
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
|
70
|
+
|
71
|
+
if @@index_list == false
|
72
|
+
|
73
|
+
pids = Repository.get_pids( num_docs )
|
74
|
+
puts "Shelving #{pids.length} Fedora objects"
|
75
|
+
pids.each do |pid|
|
76
|
+
unless pid[0].empty? || pid[0].nil?
|
77
|
+
solrize( pid )
|
78
|
+
end
|
79
|
+
end #pids.each
|
80
|
+
|
81
|
+
else
|
82
|
+
|
83
|
+
if File.exists?(@@index_list)
|
84
|
+
arr_of_pids = FasterCSV.read(@@index_list, :headers=>false)
|
85
|
+
|
86
|
+
puts "Indexing from list at #{@@index_list}"
|
87
|
+
puts "Shelving #{arr_of_pids.length} Fedora objects"
|
88
|
+
|
89
|
+
arr_of_pids.each do |row|
|
90
|
+
pid = row[0]
|
91
|
+
solrize( pid )
|
92
|
+
end #FASTERCSV
|
93
|
+
else
|
94
|
+
puts "#{@@index_list} does not exists!"
|
95
|
+
end #if File.exists
|
96
|
+
|
97
|
+
end #if Index_LISTS
|
98
|
+
end #solrize_objects
|
99
|
+
|
100
|
+
end #class
|
101
|
+
end #module
|
@@ -0,0 +1,8 @@
|
|
1
|
+
|
2
|
+
# FEDORA_URL = 'http://fedoraAdmin:fedoraAdmin@salt-dev.stanford.edu/fedora'
|
3
|
+
# FEDORA_SOLR_URL = 'http://salt-dev.stanford.edu:8080/solr'
|
4
|
+
# SHELVER_SOLR_URL = 'http://sulwebappdev1.stanford.edu:8100/salt_solr'
|
5
|
+
FEDORA_URL = 'http://fedoraAdmin:fedoraAdmin@localhost:8080/fedora'
|
6
|
+
FEDORA_SOLR_URL = 'http://localhost:8080/solr'
|
7
|
+
SHELVER_SOLR_URL = 'http://localhost:8080/bl_solr'
|
8
|
+
|
@@ -0,0 +1,89 @@
|
|
1
|
+
require 'solr'
|
2
|
+
require 'rexml/document'
|
3
|
+
require "nokogiri"
|
4
|
+
require 'yaml'
|
5
|
+
|
6
|
+
module Solrizer
|
7
|
+
class Extractor
|
8
|
+
|
9
|
+
|
10
|
+
def extract_tags(text)
|
11
|
+
doc = REXML::Document.new( text )
|
12
|
+
extract_tag(doc, 'archivist_tags').merge(extract_tag(doc, 'donor_tags'))
|
13
|
+
end
|
14
|
+
|
15
|
+
def extract_tag(doc, type)
|
16
|
+
tags = doc.elements["/fields/#{type}"]
|
17
|
+
return {} unless tags
|
18
|
+
{type => tags.text.split(/,/).map {|t| t.strip}}
|
19
|
+
end
|
20
|
+
|
21
|
+
|
22
|
+
#
|
23
|
+
# Extracts content-model and hydra-type from RELS-EXT datastream
|
24
|
+
#
|
25
|
+
def extract_rels_ext( text, solr_doc=Solr::Document.new )
|
26
|
+
# TODO: only read in this file once
|
27
|
+
|
28
|
+
if defined?(RAILS_ROOT)
|
29
|
+
config_path = File.join(RAILS_ROOT, "config")
|
30
|
+
else
|
31
|
+
config_path = File.join(File.dirname(__FILE__), "..", "..", "config")
|
32
|
+
end
|
33
|
+
map = YAML.load(File.open(File.join(config_path, "hydra_types.yml")))
|
34
|
+
|
35
|
+
doc = Nokogiri::XML(text)
|
36
|
+
doc.xpath( '//foo:hasModel', 'foo' => 'info:fedora/fedora-system:def/model#' ).each do |element|
|
37
|
+
cmodel = element.attributes['resource'].to_s
|
38
|
+
solr_doc << Solr::Field.new( :cmodel_t => cmodel )
|
39
|
+
|
40
|
+
if map.has_key?(cmodel)
|
41
|
+
solr_doc << Solr::Field.new( :hydra_type_t => map[cmodel] )
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
return solr_doc
|
46
|
+
end
|
47
|
+
|
48
|
+
#
|
49
|
+
# This method extracts solr fields from simple xml
|
50
|
+
#
|
51
|
+
def xml_to_solr( text, solr_doc=Solr::Document.new )
|
52
|
+
doc = REXML::Document.new( text )
|
53
|
+
doc.root.elements.each do |element|
|
54
|
+
solr_doc << Solr::Field.new( :"#{element.name}_t" => "#{element.text}" )
|
55
|
+
end
|
56
|
+
|
57
|
+
return solr_doc
|
58
|
+
end
|
59
|
+
|
60
|
+
#
|
61
|
+
# This method strips html tags out and returns content to be indexed in solr
|
62
|
+
#
|
63
|
+
def html_content_to_solr( ds, solr_doc=Solr::Document.new )
|
64
|
+
|
65
|
+
text = CGI.unescapeHTML(ds.content)
|
66
|
+
doc = Nokogiri::HTML(text)
|
67
|
+
|
68
|
+
# html to story_display
|
69
|
+
stories = doc.xpath('//story')
|
70
|
+
|
71
|
+
stories.each do |story|
|
72
|
+
solr_doc << Solr::Field.new(:story_display => story.children.to_xml)
|
73
|
+
end
|
74
|
+
|
75
|
+
#strip out text and put in story_t
|
76
|
+
text_nodes = doc.xpath("//text()")
|
77
|
+
text = String.new
|
78
|
+
|
79
|
+
text_nodes.each do |text_node|
|
80
|
+
text << text_node.content
|
81
|
+
end
|
82
|
+
|
83
|
+
solr_doc << Solr::Field.new(:story_t => text)
|
84
|
+
|
85
|
+
return solr_doc
|
86
|
+
end
|
87
|
+
|
88
|
+
end
|
89
|
+
end
|
@@ -0,0 +1,261 @@
|
|
1
|
+
require 'solr'
|
2
|
+
require 'solrizer/extractor'
|
3
|
+
require 'solrizer/repository'
|
4
|
+
|
5
|
+
|
6
|
+
module Solrizer
|
7
|
+
class Indexer
|
8
|
+
#
|
9
|
+
# Class variables
|
10
|
+
#
|
11
|
+
@@unique_id = 0
|
12
|
+
|
13
|
+
def self.unique_id
|
14
|
+
@@unique_id
|
15
|
+
end
|
16
|
+
|
17
|
+
#
|
18
|
+
# Member variables
|
19
|
+
#
|
20
|
+
attr_accessor :connection, :extractor, :index_full_text
|
21
|
+
|
22
|
+
#
|
23
|
+
# This method performs initialization tasks
|
24
|
+
#
|
25
|
+
def initialize( opts={} )
|
26
|
+
@@index_list = false unless defined?(@@index_list)
|
27
|
+
@extractor = Extractor.new
|
28
|
+
|
29
|
+
if opts[:index_full_text] == true || opts[:index_full_text] == "true"
|
30
|
+
@index_full_text = true
|
31
|
+
else
|
32
|
+
@index_full_text = false
|
33
|
+
end
|
34
|
+
|
35
|
+
connect
|
36
|
+
end
|
37
|
+
|
38
|
+
#
|
39
|
+
# This method connects to the Solr instance
|
40
|
+
#
|
41
|
+
def connect
|
42
|
+
|
43
|
+
if ActiveFedora.fedora_config.empty?
|
44
|
+
ActiveFedora.init
|
45
|
+
end
|
46
|
+
|
47
|
+
if defined?(Blacklight)
|
48
|
+
solr_config = Blacklight.solr_config
|
49
|
+
else
|
50
|
+
|
51
|
+
if defined?(RAILS_ROOT)
|
52
|
+
config_path = File.join(RAILS_ROOT, "config")
|
53
|
+
yaml = YAML.load(File.open(File.join(config_path, "solr.yml")))
|
54
|
+
solr_config = yaml[RAILS_ENV]
|
55
|
+
puts solr_config.inspect
|
56
|
+
else
|
57
|
+
config_path = File.join(File.dirname(__FILE__), "..", "..", "config")
|
58
|
+
yaml = YAML.load(File.open(File.join(config_path, "solr.yml")))
|
59
|
+
|
60
|
+
|
61
|
+
if ENV["environment"].nil?
|
62
|
+
environment = "development"
|
63
|
+
else
|
64
|
+
environment = ENV["environment"]
|
65
|
+
end
|
66
|
+
|
67
|
+
solr_config = yaml[environment]
|
68
|
+
puts solr_config.inspect
|
69
|
+
end
|
70
|
+
|
71
|
+
end
|
72
|
+
|
73
|
+
if index_full_text == true
|
74
|
+
url = solr_config['fulltext']['url']
|
75
|
+
elsif solr_config.has_key?("default")
|
76
|
+
url = solr_config['default']['url']
|
77
|
+
else
|
78
|
+
url = solr_config['url']
|
79
|
+
end
|
80
|
+
@connection = Solr::Connection.new(url, :autocommit => :on )
|
81
|
+
end
|
82
|
+
|
83
|
+
#
|
84
|
+
# This method extracts the facet categories from the given Fedora object's external tag datastream
|
85
|
+
#
|
86
|
+
def extract_xml_to_solr( obj, ds_name, solr_doc=Solr::Document.new )
|
87
|
+
xml_ds = Repository.get_datastream( obj, ds_name )
|
88
|
+
extractor.xml_to_solr( xml_ds.content, solr_doc )
|
89
|
+
end
|
90
|
+
|
91
|
+
#
|
92
|
+
#
|
93
|
+
#
|
94
|
+
def extract_rels_ext( obj, ds_name, solr_doc=Solr::Document.new )
|
95
|
+
rels_ext_ds = Repository.get_datastream( obj, ds_name )
|
96
|
+
extractor.extract_rels_ext( rels_ext_ds.content, solr_doc )
|
97
|
+
end
|
98
|
+
|
99
|
+
#
|
100
|
+
# This method generates the month and day facets from the date_t in solr_doc
|
101
|
+
#
|
102
|
+
|
103
|
+
def generate_dates(solr_doc)
|
104
|
+
|
105
|
+
# This will check for valid dates, but it seems most of the dates are currently invalid....
|
106
|
+
#date_check = /^(19|20)\d\d([- \/.])(0[1-9]|1[012])\2(0[1-9]|[12][0-9]|3[01])/
|
107
|
+
|
108
|
+
#if there is not date_t, add on with easy-to-find value
|
109
|
+
if solr_doc[:date_t].nil?
|
110
|
+
solr_doc << Solr::Field.new( :date_t => "9999-99-99")
|
111
|
+
end #if
|
112
|
+
|
113
|
+
# unless date_check !~ solr_doc[:date_t]
|
114
|
+
date_obj = Date._parse(solr_doc[:date_t])
|
115
|
+
|
116
|
+
if date_obj[:mon].nil?
|
117
|
+
solr_doc << Solr::Field.new(:month_facet => 99)
|
118
|
+
elsif 0 < date_obj[:mon] && date_obj[:mon] < 13
|
119
|
+
solr_doc << Solr::Field.new( :month_facet => date_obj[:mon].to_s.rjust(2, '0'))
|
120
|
+
else
|
121
|
+
solr_doc << Solr::Field.new( :month_facet => 99)
|
122
|
+
end
|
123
|
+
|
124
|
+
if date_obj[:mday].nil?
|
125
|
+
solr_doc << Solr::Field.new( :day_facet => 99)
|
126
|
+
elsif 0 < date_obj[:mday] && date_obj[:mday] < 32
|
127
|
+
solr_doc << Solr::Field.new( :day_facet => date_obj[:mday].to_s.rjust(2, '0'))
|
128
|
+
else
|
129
|
+
solr_doc << Solr::Field.new( :day_facet => 99)
|
130
|
+
end
|
131
|
+
|
132
|
+
return solr_doc
|
133
|
+
# end
|
134
|
+
|
135
|
+
end
|
136
|
+
|
137
|
+
|
138
|
+
#
|
139
|
+
# This method creates a Solr-formatted XML document
|
140
|
+
#
|
141
|
+
def create_document( obj )
|
142
|
+
|
143
|
+
solr_doc = Solr::Document.new
|
144
|
+
|
145
|
+
model_klazz_array = ActiveFedora::ContentModel.known_models_for( obj )
|
146
|
+
model_klazz_array.delete(ActiveFedora::Base)
|
147
|
+
|
148
|
+
# If the object was passed in as an ActiveFedora::Base, call to_solr in order to get the base field entries from ActiveFedora::Base
|
149
|
+
# 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
|
150
|
+
if obj.class == ActiveFedora::Base
|
151
|
+
solr_doc = obj.to_solr(solr_doc)
|
152
|
+
puts " added base fields from #{obj.class.to_s}"
|
153
|
+
else
|
154
|
+
solr_doc = obj.to_solr(solr_doc)
|
155
|
+
model_klazz_array.delete(obj.class)
|
156
|
+
puts " added base fields from #{obj.class.to_s} and model fields from #{obj.class.to_s}"
|
157
|
+
end
|
158
|
+
|
159
|
+
# Load the object as an instance of each of its other models and get the corresponding solr fields
|
160
|
+
# Include :model_only=>true in the options in order to avoid adding the metadata from ActiveFedora::Base every time.
|
161
|
+
model_klazz_array.each do |klazz|
|
162
|
+
instance = klazz.load_instance(obj.pid)
|
163
|
+
solr_doc = instance.to_solr(solr_doc, :model_only=>true)
|
164
|
+
puts " added solr fields from #{klazz.to_s}"
|
165
|
+
end
|
166
|
+
|
167
|
+
solr_doc << Solr::Field.new( :id_t => "#{obj.pid}" )
|
168
|
+
solr_doc << Solr::Field.new( :id => "#{obj.pid}" ) unless solr_doc[:id]
|
169
|
+
|
170
|
+
# increment the unique id to ensure that all documents in the search index are unique
|
171
|
+
@@unique_id += 1
|
172
|
+
|
173
|
+
return solr_doc
|
174
|
+
end
|
175
|
+
|
176
|
+
#
|
177
|
+
# This method adds a document to the Solr search index
|
178
|
+
#
|
179
|
+
def index( obj )
|
180
|
+
# print "Indexing '#{obj.pid}'..."
|
181
|
+
begin
|
182
|
+
|
183
|
+
solr_doc = create_document( obj )
|
184
|
+
connection.add( solr_doc )
|
185
|
+
|
186
|
+
# puts connection.url
|
187
|
+
#puts solr_doc
|
188
|
+
# puts "done"
|
189
|
+
|
190
|
+
# rescue Exception => e
|
191
|
+
# p "unable to index #{obj.pid}. Failed with #{e.inspect}"
|
192
|
+
end
|
193
|
+
|
194
|
+
end
|
195
|
+
|
196
|
+
#
|
197
|
+
# This method queries the Solr search index and returns a response
|
198
|
+
#
|
199
|
+
def query( query_str )
|
200
|
+
response = conn.query( query_str )
|
201
|
+
end
|
202
|
+
|
203
|
+
#
|
204
|
+
# This method prints out the results of the given query string by iterating through all the hits
|
205
|
+
#
|
206
|
+
def printResults( query_str )
|
207
|
+
query( query_str ) do |hit|
|
208
|
+
puts hit.inspect
|
209
|
+
end
|
210
|
+
end
|
211
|
+
|
212
|
+
#
|
213
|
+
# This method deletes a document from the Solr search index by id
|
214
|
+
#
|
215
|
+
def deleteDocument( id )
|
216
|
+
connection.delete( id )
|
217
|
+
end
|
218
|
+
|
219
|
+
# Populates a solr doc with values from a hash.
|
220
|
+
# Accepts two forms of hashes:
|
221
|
+
# => {'technology'=>["t1", "t2"], 'company'=>"c1", "person"=>["p1", "p2"]}
|
222
|
+
# or
|
223
|
+
# => {:facets => {'technology'=>["t1", "t2"], 'company'=>"c1", "person"=>["p1", "p2"]} }
|
224
|
+
#
|
225
|
+
# Note that values for individual fields can be a single string or an array of strings.
|
226
|
+
def self.solrize( input_hash, solr_doc=Solr::Document.new )
|
227
|
+
facets = input_hash.has_key?(:facets) ? input_hash[:facets] : input_hash
|
228
|
+
facets.each_pair do |facet_name, value|
|
229
|
+
case value.class.to_s
|
230
|
+
when "String"
|
231
|
+
solr_doc << Solr::Field.new( :"#{facet_name}_facet" => "#{value}" )
|
232
|
+
when "Array"
|
233
|
+
value.each { |v| solr_doc << Solr::Field.new( :"#{facet_name}_facet" => "#{v}" ) }
|
234
|
+
end
|
235
|
+
end
|
236
|
+
|
237
|
+
if input_hash.has_key?(:symbols)
|
238
|
+
input_hash[:symbols].each do |symbol_name, value|
|
239
|
+
case value.class.to_s
|
240
|
+
when "String"
|
241
|
+
solr_doc << Solr::Field.new( :"#{symbol_name}_s" => "#{value}" )
|
242
|
+
when "Array"
|
243
|
+
value.each { |v| solr_doc << Solr::Field.new( :"#{symbol_name}_s" => "#{v}" ) }
|
244
|
+
end
|
245
|
+
end
|
246
|
+
end
|
247
|
+
return solr_doc
|
248
|
+
end
|
249
|
+
|
250
|
+
|
251
|
+
private :connect, :create_document
|
252
|
+
|
253
|
+
def class_exists?(class_name)
|
254
|
+
klass = Module.const_get(class_name)
|
255
|
+
return klass.is_a?(Class)
|
256
|
+
rescue NameError
|
257
|
+
return false
|
258
|
+
end
|
259
|
+
|
260
|
+
end
|
261
|
+
end
|