active-fedora 2.2.0 → 2.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (48) hide show
  1. data/.gitignore +30 -0
  2. data/.gitmodules +3 -0
  3. data/.rvmrc +33 -0
  4. data/CONSOLE_GETTING_STARTED.textile +337 -0
  5. data/Gemfile +6 -1
  6. data/Gemfile.lock +39 -23
  7. data/NOKOGIRI_DATASTREAMS.textile +107 -0
  8. data/README.textile +41 -17
  9. data/Rakefile +5 -30
  10. data/active-fedora.gemspec +34 -496
  11. data/lib/active_fedora.rb +6 -1
  12. data/lib/active_fedora/base.rb +7 -5
  13. data/lib/active_fedora/datastream.rb +9 -8
  14. data/lib/active_fedora/metadata_datastream.rb +10 -3
  15. data/lib/active_fedora/model.rb +8 -4
  16. data/lib/active_fedora/nokogiri_datastream.rb +30 -24
  17. data/lib/active_fedora/qualified_dublin_core_datastream.rb +3 -2
  18. data/lib/active_fedora/rels_ext_datastream.rb +14 -5
  19. data/lib/active_fedora/samples.rb +3 -0
  20. data/lib/active_fedora/samples/hydra-mods_article_datastream.rb +517 -0
  21. data/lib/active_fedora/samples/hydra-rights_metadata_datastream.rb +206 -0
  22. data/lib/active_fedora/samples/marpa-dc_datastream.rb +97 -0
  23. data/lib/active_fedora/samples/special_thing.rb +45 -0
  24. data/lib/active_fedora/semantic_node.rb +16 -13
  25. data/lib/active_fedora/version.rb +3 -0
  26. data/lib/fedora/base.rb +5 -5
  27. data/lib/fedora/datastream.rb +1 -1
  28. data/lib/fedora/fedora_object.rb +1 -1
  29. data/lib/fedora/repository.rb +4 -0
  30. data/lib/tasks/active_fedora.rake +126 -0
  31. data/lib/tasks/active_fedora_dev.rake +127 -0
  32. data/solr/conf/schema.xml +278 -0
  33. data/solr/conf/solrconfig.xml +840 -0
  34. data/spec/integration/full_featured_model_spec.rb +2 -2
  35. data/spec/integration/mods_article_integration_spec.rb +2 -2
  36. data/spec/integration/nokogiri_datastream_spec.rb +2 -2
  37. data/spec/rcov.opts +2 -0
  38. data/spec/samples/models/hydrangea_article.rb +12 -0
  39. data/spec/spec_helper.rb +1 -1
  40. data/spec/unit/nokogiri_datastream_spec.rb +10 -7
  41. metadata +189 -886
  42. data/NG_XML_DATASTREAM.textile +0 -25
  43. data/USING_OM_DATASTREAMS.textile +0 -60
  44. data/VERSION +0 -1
  45. data/lib/hydra.rb +0 -2
  46. data/lib/hydra/sample_mods_datastream.rb +0 -63
  47. data/tasks/hoe.rake +0 -0
  48. data/tasks/rspec.rake +0 -29
@@ -153,7 +153,7 @@ class Fedora::FedoraObject < Fedora::BaseObject
153
153
  "fedora:info/#{pid}"
154
154
  end
155
155
 
156
- # @returns the url of the object in Fedora, without the repository userinfo
156
+ # @return [String] url of the datastream in Fedora, without the repository userinfo
157
157
  def url
158
158
  repo_url = Fedora::Repository.instance.fedora_url
159
159
  return "#{repo_url.scheme}://#{repo_url.host}:#{repo_url.port}#{repo_url.path}/objects/#{pid}"
@@ -98,6 +98,10 @@ module Fedora
98
98
  convert_xml(connection.get("#{fedora_url.path}/objects?#{params.to_fedora_query}#{includes}"))
99
99
  end
100
100
 
101
+ # Retrieve an object from fedora and load it as an instance of the given model/class
102
+ #
103
+ # @param pid of the Fedora object to retrieve and deserialize
104
+ # @param klazz the Model whose deserialize method the object's FOXML will be passed into
101
105
  def find_model(pid, klazz)
102
106
  obj = self.find_objects("pid=#{pid}").first
103
107
  if obj.nil?
@@ -0,0 +1,126 @@
1
+ # require File.expand_path(File.dirname(__FILE__) + '/hydra_jetty.rb')
2
+ require "active-fedora"
3
+ require "solrizer-fedora"
4
+ require "active_support" # This is just to load ActiveSupport::CoreExtensions::String::Inflections
5
+ namespace :af do
6
+
7
+
8
+ desc "Delete and re-import the fixture identified by pid"
9
+ task :refresh_fixture => [:delete,:import_fixture]
10
+
11
+ desc "Delete the object identified by pid. Example: rake fedora:delete pid=demo:12"
12
+ task :delete => :init do
13
+ # If a destination url has been provided, attampt to export from the fedora repository there.
14
+ if ENV["destination"]
15
+ Fedora::Repository.register(ENV["destination"])
16
+ end
17
+
18
+ if ENV["pid"].nil?
19
+ puts "You must specify a valid pid. Example: rake fedora:delete pid=demo:12"
20
+ else
21
+ pid = ENV["pid"]
22
+ puts "Deleting '#{pid}' from #{Fedora::Repository.instance.fedora_url}"
23
+ begin
24
+ ActiveFedora::Base.load_instance(pid).delete
25
+ rescue ActiveFedora::ObjectNotFoundError
26
+ puts "The object #{pid} has already been deleted (or was never created)."
27
+ rescue Errno::ECONNREFUSED => e
28
+ puts "Can't connect to Fedora! Are you sure jetty is running?"
29
+ rescue Fedora::ServerError => e
30
+ logger.error("Received a Fedora error while deleting #{pid}")
31
+ end
32
+ logger.info "Deleted '#{pid}' from #{Fedora::Repository.instance.fedora_url}"
33
+ end
34
+ end
35
+
36
+ desc "Delete a range of objects in a given namespace. ie 'rake fedora:purge_range[demo, 22, 50]' will delete demo:22 through demo:50"
37
+ task :purge_range => :init do |t, args|
38
+ # If Fedora Repository connection is not already initialized, initialize it using ActiveFedora defaults
39
+ # ActiveFedora.init unless Thread.current[:repo]
40
+
41
+ namespace = ENV["namespace"]
42
+ start_point = ENV["start"].to_i
43
+ stop_point = ENV["stop"].to_i
44
+ unless start_point < stop_point
45
+ raise StandardError "start point must be less that end point."
46
+ end
47
+ puts "Deleting #{stop_point - start_point} objects from #{namespace}:#{start_point.to_s} to #{namespace}:#{stop_point.to_s}"
48
+ i = start_point
49
+ while i <= stop_point do
50
+ pid = namespace + ":" + i.to_s
51
+ begin
52
+ ActiveFedora::Base.load_instance(pid).delete
53
+ rescue ActiveFedora::ObjectNotFoundError
54
+ # The object has already been deleted (or was never created). Do nothing.
55
+ end
56
+ puts "Deleted '#{pid}' from #{Fedora::Repository.instance.fedora_url}"
57
+ i += 1
58
+ end
59
+ end
60
+
61
+ desc "Export the object identified by pid into spec/fixtures. Example:rake fedora:harvest_fixture pid=druid:sb733gr4073 source=http://fedoraAdmin:fedoraAdmin@127.0.0.1:8080/fedora"
62
+ task :harvest_fixture => :init do
63
+
64
+ # If a source url has been provided, attampt to export from the fedora repository there.
65
+ if ENV["source"]
66
+ Fedora::Repository.register(ENV["source"])
67
+ end
68
+
69
+ if ENV["pid"].nil?
70
+ puts "You must specify a valid pid. Example: rake fedora:harvest_fixture pid=demo:12"
71
+ else
72
+ pid = ENV["pid"]
73
+ puts "Exporting '#{pid}' from #{Fedora::Repository.instance.fedora_url}"
74
+ foxml = Fedora::Repository.instance.export(pid)
75
+ filename = File.join("spec","fixtures","#{pid.gsub(":","_")}.foxml.xml")
76
+ file = File.new(filename,"w")
77
+ file.syswrite(foxml)
78
+ puts "The object has been saved as #{filename}"
79
+ end
80
+ end
81
+
82
+ desc "Import the fixture located at the provided path. Example: rake fedora:import_fixture fixture=spec/fixtures/demo_12.foxml.xml"
83
+ task :import_fixture => [:init, :environment] do
84
+
85
+ # If a destination url has been provided, attampt to export from the fedora repository there.
86
+ if ENV["destination"]
87
+ Fedora::Repository.register(ENV["destination"])
88
+ end
89
+
90
+ if !ENV["fixture"].nil?
91
+ filename = ENV["fixture"]
92
+ elsif !ENV["pid"].nil?
93
+ pid = ENV["pid"]
94
+ filename = File.join("spec","fixtures","#{pid.gsub(":","_")}.foxml.xml")
95
+ else
96
+ puts "You must specify a path to the fixture or provide its pid. Example: rake fedora:import_fixture fixture=spec/fixtures/demo_12.foxml.xml"
97
+ end
98
+
99
+ if !filename.nil?
100
+ puts "Importing '#{filename}' to #{Fedora::Repository.instance.fedora_url}"
101
+ file = File.new(filename, "r")
102
+ result = foxml = Fedora::Repository.instance.ingest(file.read)
103
+ if result
104
+ puts "The fixture has been ingested as #{result.body}"
105
+ if !pid.nil?
106
+ solrizer = Solrizer::Fedora::Solrizer.new
107
+ solrizer.solrize(pid)
108
+ end
109
+ else
110
+ puts "Failed to ingest the fixture."
111
+ end
112
+ end
113
+
114
+ end
115
+
116
+
117
+ desc "Init ActiveFedora configuration"
118
+ task :init do
119
+ if !ENV["environment"].nil?
120
+ RAILS_ENV = ENV["environment"]
121
+ end
122
+ # If Fedora Repository connection is not already initialized, initialize it using ActiveFedora defaults
123
+ ActiveFedora.init unless Thread.current[:repo]
124
+ end
125
+
126
+ end
@@ -0,0 +1,127 @@
1
+ begin
2
+ require 'spec'
3
+ rescue LoadError
4
+ require 'rubygems'
5
+ require 'spec'
6
+ end
7
+ begin
8
+ require 'spec/rake/spectask'
9
+ rescue LoadError
10
+ puts <<-EOS
11
+ To use rspec for testing you must install rspec gem:
12
+ gem install rspec
13
+ EOS
14
+ exit(0)
15
+ end
16
+
17
+ $: << 'lib'
18
+
19
+ desc "Run active-fedora rspec tests"
20
+ task :spec do
21
+ Rake::Task["active_fedora:rspec"].invoke
22
+ end
23
+
24
+ desc "Hudson build"
25
+ task :hudson do
26
+ require 'jettywrapper'
27
+ project_root = File.expand_path("#{File.dirname(__FILE__)}/../../")
28
+
29
+ if (ENV['RAILS_ENV'] == "test")
30
+ Rake::Task["active_fedora:doc"].invoke
31
+ Rake::Task["active_fedora:configure_jetty"].invoke
32
+ jetty_params = {
33
+ :quiet => false,
34
+ :jetty_home => File.join(project_root,'jetty'),
35
+ :jetty_port => 8983,
36
+ :solr_home => File.expand_path(File.join(project_root,'jetty','solr')),
37
+ :fedora_home => File.expand_path(File.join(project_root,'jetty','fedora','default')),
38
+ :startup_wait=>30
39
+ }
40
+ error = Jettywrapper.wrap(jetty_params) do
41
+ Rake::Task["active_fedora:load_fixtures"].invoke
42
+ Rake::Task["active_fedora:rspec"].invoke
43
+ end
44
+ raise "test failures: #{error}" if error
45
+ else
46
+ system("rake hudson RAILS_ENV=test")
47
+ fail unless $?.success?
48
+ end
49
+ end
50
+
51
+ namespace :active_fedora do
52
+ require 'lib/active-fedora'
53
+
54
+ # Use yard to build docs
55
+ begin
56
+ require 'yard'
57
+ require 'yard/rake/yardoc_task'
58
+ project_root = File.expand_path("#{File.dirname(__FILE__)}/../../")
59
+ doc_destination = File.join(project_root, 'doc')
60
+
61
+ YARD::Rake::YardocTask.new(:doc) do |yt|
62
+ yt.files = Dir.glob(File.join(project_root, 'lib', '**', '*.rb')) +
63
+ [ File.join(project_root, 'README.textile'),'-', File.join(project_root,'CONSOLE_GETTING_STARTED.textile'),'-', File.join(project_root,'NOKOGIRI_DATASTREAMS.textile') ]
64
+ yt.options = ['--output-dir', doc_destination, '--readme', 'README.textile']
65
+ end
66
+ rescue LoadError
67
+ desc "Generate YARD Documentation"
68
+ task :doc do
69
+ abort "Please install the YARD gem to generate rdoc."
70
+ end
71
+ end
72
+
73
+
74
+ Spec::Rake::SpecTask.new(:rspec) do |t|
75
+ t.spec_files = FileList['spec/**/*_spec.rb']
76
+ t.rcov = true
77
+ t.rcov_opts << ['--exclude', 'gems']
78
+ t.rcov_opts << ['--exclude', 'spec']
79
+ end
80
+
81
+ task :refresh_fixtures do
82
+ Rake::Task["active_fedora:clean_jetty"].invoke
83
+ Rake::Task["active_fedora:load_fixtures"].invoke
84
+ end
85
+
86
+ task :clean_jetty do
87
+ Dir.chdir("./jetty")
88
+ system("git clean -f -d")
89
+ system("git checkout .")
90
+ Dir.chdir("..")
91
+ end
92
+
93
+ task :load_fixtures => :environment do
94
+ require 'solrizer'
95
+ require 'solrizer-fedora'
96
+ require 'spec/samples/models/hydrangea_article'
97
+ ENV["FEDORA_HOME"]=File.expand_path(File.join(File.dirname(__FILE__),'..','..','jetty','fedora','default'))
98
+ retval = `$FEDORA_HOME/client/bin/fedora-ingest-demos.sh localhost 8983 fedoraAdmin fedoraAdmin http`
99
+ puts "loaded demo objects #{retval}"
100
+ ActiveFedora.init unless Thread.current[:repo]
101
+
102
+ ENV["pid"] = "hydrangea:fixture_mods_article1"
103
+ Rake::Task["af:refresh_fixture"].invoke
104
+ ENV["pid"] = nil
105
+ end
106
+
107
+ desc "Copies the default SOLR config for the bundled Testing Server"
108
+ task :configure_jetty do
109
+ Rake::Task["active_fedora:clean_jetty"].invoke
110
+ FileList['solr/conf/*'].each do |f|
111
+ cp("#{f}", 'jetty/solr/development-core/conf/', :verbose => true)
112
+ cp("#{f}", 'jetty/solr/test-core/conf/', :verbose => true)
113
+ end
114
+ end
115
+
116
+ end
117
+
118
+ # Provides an :environment task for use while working within a working copy of active-fedora
119
+ # You should never load this rake file into any other application
120
+ desc 'Set up ActiveFedora environment. !! Only for use while working within a working copy of active-fedora'
121
+ task :environment do
122
+ puts "Initializing ActiveFedora Rake environment. This should only be called when working within a workign copy of the active-fedora code."
123
+ require 'spec/samples/models/hydrangea_article'
124
+ require 'active_fedora/samples'
125
+ # $:.unshift(File.dirname(__FILE__) + '/../lib')
126
+ # Dir[File.join(File.dirname(__FILE__)+'/../lib/')+'**/*.rb'].each{|x| require x}
127
+ end
@@ -0,0 +1,278 @@
1
+ <?xml version="1.0" encoding="UTF-8" ?>
2
+ <!--
3
+ Licensed to the Apache Software Foundation (ASF) under one or more
4
+ contributor license agreements. See the NOTICE file distributed with
5
+ this work for additional information regarding copyright ownership.
6
+ The ASF licenses this file to You under the Apache License, Version 2.0
7
+ (the "License"); you may not use this file except in compliance with
8
+ the License. You may obtain a copy of the License at
9
+
10
+ http://www.apache.org/licenses/LICENSE-2.0
11
+
12
+ Unless required by applicable law or agreed to in writing, software
13
+ distributed under the License is distributed on an "AS IS" BASIS,
14
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ See the License for the specific language governing permissions and
16
+ limitations under the License.
17
+ -->
18
+
19
+ <!--
20
+ This is the Solr schema file. This file should be named "schema.xml" and
21
+ should be in the conf directory under the solr home
22
+ (i.e. ./solr/conf/schema.xml by default)
23
+ or located where the classloader for the Solr webapp can find it.
24
+
25
+ This example schema is the recommended starting point for users.
26
+ It should be kept correct and concise, usable out-of-the-box.
27
+
28
+ For more information, on how to customize this file, please see
29
+ http://wiki.apache.org/solr/SchemaXml
30
+ -->
31
+
32
+ <schema name="salt" version="1.1">
33
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
34
+ Applications should change this to reflect the nature of the search collection.
35
+ version="1.1" is Solr's version number for the schema syntax and semantics. It should
36
+ not normally be changed by applications.
37
+ 1.0: multiValued attribute did not exist, all fields are multiValued by nature
38
+ 1.1: multiValued attribute introduced, false by default -->
39
+
40
+ <types>
41
+ <!-- field type definitions. The "name" attribute is
42
+ just a label to be used by field definitions. The "class"
43
+ attribute and any other attributes determine the real
44
+ behavior of the fieldType.
45
+ Class names starting with "solr" refer to java classes in the
46
+ org.apache.solr.analysis package.
47
+ -->
48
+
49
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
50
+ - StrField and TextField support an optional compressThreshold which
51
+ limits compression (if enabled in the derived fields) to values which
52
+ exceed a certain size (in characters).
53
+ -->
54
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
55
+
56
+ <!-- boolean type: "true" or "false" -->
57
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
58
+
59
+ <!-- The optional sortMissingLast and sortMissingFirst attributes are
60
+ currently supported on types that are sorted internally as strings.
61
+ - If sortMissingLast="true", then a sort on this field will cause documents
62
+ without the field to come after documents with the field,
63
+ regardless of the requested sort order (asc or desc).
64
+ - If sortMissingFirst="true", then a sort on this field will cause documents
65
+ without the field to come before documents with the field,
66
+ regardless of the requested sort order.
67
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
68
+ then default lucene sorting will be used which places docs without the
69
+ field first in an ascending sort and last in a descending sort.
70
+ -->
71
+
72
+
73
+ <!-- numeric field types that store and index the text
74
+ value verbatim (and hence don't support range queries, since the
75
+ lexicographic ordering isn't equal to the numeric ordering) -->
76
+ <fieldType name="integer" class="solr.IntField" omitNorms="true"/>
77
+ <fieldType name="long" class="solr.LongField" omitNorms="true"/>
78
+ <fieldType name="float" class="solr.FloatField" omitNorms="true"/>
79
+ <fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
80
+
81
+
82
+ <!-- Numeric field types that manipulate the value into
83
+ a string value that isn't human-readable in its internal form,
84
+ but with a lexicographic ordering the same as the numeric ordering,
85
+ so that range queries work correctly. -->
86
+ <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
87
+ <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
88
+ <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
89
+ <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
90
+
91
+
92
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
93
+ is a more restricted form of the canonical representation of dateTime
94
+ http://www.w3.org/TR/xmlschema-2/#dateTime
95
+ The trailing "Z" designates UTC time and is mandatory.
96
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
97
+ All other components are mandatory.
98
+
99
+ Expressions can also be used to denote calculations that should be
100
+ performed relative to "NOW" to determine the value, ie...
101
+
102
+ NOW/HOUR
103
+ ... Round to the start of the current hour
104
+ NOW-1DAY
105
+ ... Exactly 1 day prior to now
106
+ NOW/DAY+6MONTHS+3DAYS
107
+ ... 6 months and 3 days in the future from the start of
108
+ the current day
109
+
110
+ Consult the DateField javadocs for more information.
111
+ -->
112
+ <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
113
+
114
+
115
+ <!-- The "RandomSortField" is not used to store or search any
116
+ data. You can declare fields of this type it in your schema
117
+ to generate psuedo-random orderings of your docs for sorting
118
+ purposes. The ordering is generated based on the field name
119
+ and the version of the index, As long as the index version
120
+ remains unchanged, and the same field name is reused,
121
+ the ordering of the docs will be consistent.
122
+ If you want differend psuedo-random orderings of documents,
123
+ for the same version of the index, use a dynamicField and
124
+ change the name
125
+ -->
126
+ <fieldType name="random" class="solr.RandomSortField" indexed="true" />
127
+
128
+ <!-- solr.TextField allows the specification of custom text analyzers
129
+ specified as a tokenizer and a list of token filters. Different
130
+ analyzers may be specified for indexing and querying.
131
+
132
+ The optional positionIncrementGap puts space between multiple fields of
133
+ this type on the same document, with the purpose of preventing false phrase
134
+ matching across fields.
135
+
136
+ For more info on customizing your analyzer chain, please see
137
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
138
+ -->
139
+
140
+ <!-- One can also specify an existing Analyzer class that has a
141
+ default constructor via the class attribute on the analyzer element
142
+ <fieldType name="text_greek" class="solr.TextField">
143
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
144
+ </fieldType>
145
+ -->
146
+
147
+ <!-- A text field that only splits on whitespace for exact matching of words -->
148
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
149
+ <analyzer>
150
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
151
+ </analyzer>
152
+ </fieldType>
153
+
154
+ <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
155
+ words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
156
+ so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
157
+ Synonyms and stopwords are customized by external files, and stemming is enabled.
158
+ Duplicate tokens at the same position (which may result from Stemmed Synonyms or
159
+ WordDelim parts) are removed.
160
+ -->
161
+ <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
162
+ <analyzer type="index">
163
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
164
+ <!-- in this example, we will only use synonyms at query time
165
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
166
+ -->
167
+ <!-- Case insensitive stop word removal.
168
+ enablePositionIncrements=true ensures that a 'gap' is left to
169
+ allow for accurate phrase queries.
170
+ -->
171
+ <filter class="solr.StopFilterFactory"
172
+ ignoreCase="true"
173
+ words="stopwords.txt"
174
+ enablePositionIncrements="true"
175
+ />
176
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
177
+ <filter class="solr.LowerCaseFilterFactory"/>
178
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
179
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
180
+ </analyzer>
181
+ <analyzer type="query">
182
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
183
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
184
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
185
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
186
+ <filter class="solr.LowerCaseFilterFactory"/>
187
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
188
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
189
+ </analyzer>
190
+ </fieldType>
191
+
192
+
193
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
194
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
195
+ <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
196
+ <analyzer>
197
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
198
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
199
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
200
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
201
+ <filter class="solr.LowerCaseFilterFactory"/>
202
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
203
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
204
+ </analyzer>
205
+ </fieldType>
206
+
207
+ <!-- This is an example of using the KeywordTokenizer along
208
+ With various TokenFilterFactories to produce a sortable field
209
+ that does not include some properties of the source text
210
+ -->
211
+ <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
212
+ <analyzer>
213
+ <!-- KeywordTokenizer does no actual tokenizing, so the entire
214
+ input string is preserved as a single token
215
+ -->
216
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
217
+ <!-- The LowerCase TokenFilter does what you expect, which can be
218
+ when you want your sorting to be case insensitive
219
+ -->
220
+ <filter class="solr.LowerCaseFilterFactory" />
221
+ <!-- The TrimFilter removes any leading or trailing whitespace -->
222
+ <filter class="solr.TrimFilterFactory" />
223
+ <!-- The PatternReplaceFilter gives you the flexibility to use
224
+ Java Regular expression to replace any sequence of characters
225
+ matching a pattern with an arbitrary replacement string,
226
+ which may include back refrences to portions of the orriginal
227
+ string matched by the pattern.
228
+
229
+ See the Java Regular Expression documentation for more
230
+ infomation on pattern and replacement string syntax.
231
+
232
+ http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
233
+ -->
234
+ <filter class="solr.PatternReplaceFilterFactory"
235
+ pattern="([^a-z])" replacement="" replace="all"
236
+ />
237
+ </analyzer>
238
+ </fieldType>
239
+
240
+ <!-- since fields of this type are by default not stored or indexed, any data added to
241
+ them will be ignored outright
242
+ -->
243
+ <fieldtype name="ignored" stored="false" indexed="false" class="solr.StrField" />
244
+
245
+ </types>
246
+
247
+ <fields>
248
+
249
+ <field name="id" type="string" indexed="true" stored="true" required="true" />
250
+ <field name="text" type="text" indexed="true" stored="true" multiValued="true"/>
251
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
252
+
253
+ <!-- format is used for facet, display, and choosing which partial to use for the show view, so it must be stored and indexed -->
254
+ <field name="format" type="string" indexed="true" stored="true"/>
255
+
256
+ <dynamicField name="*_i" type="sint" indexed="true" stored="true"/>
257
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" multiValued="true"/>
258
+ <dynamicField name="*_l" type="slong" indexed="true" stored="true"/>
259
+ <dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true"/>
260
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
261
+ <dynamicField name="*_f" type="sfloat" indexed="true" stored="true"/>
262
+ <dynamicField name="*_d" type="sdouble" indexed="true" stored="true"/>
263
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
264
+
265
+ <dynamicField name="random*" type="random" />
266
+
267
+ <dynamicField name="*_sort" type="string" indexed="true" stored="false" multiValued="true" />
268
+ <dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true" />
269
+ <dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
270
+
271
+ </fields>
272
+
273
+ <uniqueKey>id</uniqueKey>
274
+ <defaultSearchField>text</defaultSearchField>
275
+ <solrQueryParser defaultOperator="AND" />
276
+ <copyField source="*_facet" dest="text" />
277
+
278
+ </schema>