ruby-fedora 0.1.2 → 0.9.0

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/COPYING.LESSER.txt +165 -0
  2. data/COPYING.txt +674 -0
  3. data/Manifest.txt +19 -20
  4. data/README.txt +6 -1
  5. data/Rakefile +4 -0
  6. data/config/hoe.rb +2 -2
  7. data/config/requirements.rb +9 -2
  8. data/lib/active_fedora.rb +41 -0
  9. data/lib/active_fedora/base.rb +278 -8
  10. data/lib/active_fedora/content_model.rb +22 -0
  11. data/lib/active_fedora/datastream.rb +95 -0
  12. data/lib/active_fedora/fedora_object.rb +84 -0
  13. data/lib/active_fedora/metadata_datastream.rb +97 -0
  14. data/lib/active_fedora/model.rb +94 -0
  15. data/lib/active_fedora/property.rb +15 -0
  16. data/lib/active_fedora/qualified_dublin_core_datastream.rb +72 -0
  17. data/lib/active_fedora/relationship.rb +43 -0
  18. data/lib/active_fedora/rels_ext_datastream.rb +43 -0
  19. data/lib/active_fedora/semantic_node.rb +221 -0
  20. data/lib/active_fedora/solr_service.rb +20 -0
  21. data/lib/fedora/base.rb +2 -1
  22. data/lib/fedora/connection.rb +104 -134
  23. data/lib/fedora/datastream.rb +10 -1
  24. data/lib/fedora/fedora_object.rb +28 -24
  25. data/lib/fedora/generic_search.rb +71 -0
  26. data/lib/fedora/repository.rb +47 -3
  27. data/lib/ruby-fedora.rb +9 -8
  28. data/lib/util/class_level_inheritable_attributes.rb +23 -0
  29. data/solr/config/schema.xml +229 -0
  30. metadata +37 -24
  31. data/lib/active-fedora.rb +0 -1
  32. data/lib/ambition/adapters/active_fedora.rb +0 -10
  33. data/lib/ambition/adapters/active_fedora/base.rb +0 -14
  34. data/lib/ambition/adapters/active_fedora/query.rb +0 -48
  35. data/lib/ambition/adapters/active_fedora/select.rb +0 -104
  36. data/lib/ambition/adapters/active_fedora/slice.rb +0 -19
  37. data/lib/ambition/adapters/active_fedora/sort.rb +0 -43
  38. data/script/destroy +0 -14
  39. data/script/generate +0 -14
  40. data/script/txt2html +0 -74
  41. data/tasks/deployment.rake +0 -34
  42. data/tasks/environment.rake +0 -7
  43. data/tasks/website.rake +0 -17
  44. data/website/index.html +0 -93
  45. data/website/index.txt +0 -39
  46. data/website/javascripts/rounded_corners_lite.inc.js +0 -285
  47. data/website/stylesheets/screen.css +0 -138
  48. data/website/template.rhtml +0 -48
@@ -12,11 +12,20 @@ class Fedora::Datastream < Fedora::BaseObject
12
12
  end
13
13
 
14
14
  def dsid
15
- attributes[:dsID]
15
+ if attributes.has_key?(:dsid)
16
+ attributes[:dsid]
17
+ else
18
+ attributes[:dsID]
19
+ end
16
20
  end
17
21
 
18
22
  # See http://www.fedora.info/definitions/identifiers/
19
23
  def uri
20
24
  "fedora:info/#{pid}/datastreams/#{dsid}"
21
25
  end
26
+
27
+ # @returns the url of the datastream in Fedora, without the repository userinfo
28
+ def url
29
+ return "#{Fedora::Repository.instance.base_url}/objects/#{pid}/datastreams/#{dsid}"
30
+ end
22
31
  end
@@ -33,19 +33,25 @@ class Fedora::FedoraObject < Fedora::BaseObject
33
33
  # TODO: Mix In DC attribute finders/accessors
34
34
  # TODO: Make sure that fedora_object_type and contentModel are juggled properly.
35
35
  def retrieve_attr_from_fedora
36
- self.attributes.merge!(objectProfile)
36
+ self.attributes.merge!(profile)
37
+ object_rexml = REXML::Document.new(object_xml)
37
38
  self.attributes.merge!({
38
- :state => objectXML.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#state']"].attributes["value"]
39
+ :state => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#state']"].attributes["value"],
40
+ :create_date => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#createdDate']"].attributes["value"],
41
+ :modified_date => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#lastModifiedDate']"].attributes["value"],
42
+ :label => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#label']"].attributes["value"]
39
43
  })
40
44
 
41
45
  end
42
46
 
43
47
  def create_date
44
- objectProfile[:create_date]
48
+ profile[:create_date]
49
+ #self.attributes[:cDate]
45
50
  end
46
51
 
47
52
  def modified_date
48
- objectProfile[:modified_date]
53
+ profile[:create_date]
54
+ #self.attributes[:mDate]
49
55
  end
50
56
 
51
57
 
@@ -77,14 +83,6 @@ class Fedora::FedoraObject < Fedora::BaseObject
77
83
  self.attributes[:label] = new_label
78
84
  end
79
85
 
80
- def content_model
81
- self.attributes[:contentModel]
82
- end
83
-
84
- def content_model=(new_content_model)
85
- self.attributes[:contentModel] = new_content_model
86
- end
87
-
88
86
  # Get the object and read its @ownerId from the profile
89
87
  def owner_id
90
88
  self.attributes[:ownerID]
@@ -96,24 +94,30 @@ class Fedora::FedoraObject < Fedora::BaseObject
96
94
 
97
95
  def profile
98
96
  # Use xmlsimple to slurp the attributes
99
- objectProfile = XmlSimple.xml_in(@fedora.call_resource(:retrieve, :objects_profile, {:pid => @pid}))
100
- # TODO: Find out if xmlsimple automatically expands camelCased element names...
101
- profile_as_array = {
102
- :owner_id => objectProfile[objOwnerId],
103
- :content_model => objectProfile[objContentModel],
104
- :label => objectProfile[objLabel],
105
- :date_created => objectProfile[objCreateDate],
106
- :date_modified => objectProfile[objLastModDate]
107
- }
97
+ retrieved_profile = XmlSimple.xml_in(Fedora::Repository.instance.fetch_custom(self.pid, :profile))
98
+ profile_hash = Hash[:owner_id => retrieved_profile["objOwnerId"],
99
+ :label => retrieved_profile["objLabel"],
100
+ :create_date => retrieved_profile["objCreateDate"],
101
+ :modified_date => retrieved_profile["objLastModDate"]
102
+ ]
108
103
  end
109
104
 
110
- def objectXML
111
- # Use REXML to slurp the attributes (can't use xmlsimple because the XML is too complex. Need XPath-like queries.
112
- @objectXML ||= REXML::Document.new(@fedora.call_resource(:retrieve, :objects_objectXml, {:pid => @pid}))
105
+ def object_xml
106
+ Fedora::Repository.instance.fetch_custom(pid, :objectXML)
107
+ end
108
+
109
+ def self.object_xml(pid=pid)
110
+ Fedora::Repository.instance.fetch_custom(pid, :objectXML)
113
111
  end
114
112
 
115
113
  # See http://www.fedora.info/definitions/identifiers
116
114
  def uri
117
115
  "fedora:info/#{pid}"
118
116
  end
117
+
118
+ # @returns the url of the object in Fedora, without the repository userinfo
119
+ def url
120
+ repo_url = Fedora::Repository.instance.fedora_url
121
+ return "#{repo_url.scheme}://#{repo_url.host}:#{repo_url.port}#{repo_url.path}/objects/#{pid}"
122
+ end
119
123
  end
@@ -0,0 +1,71 @@
1
+ #
2
+ # @Creator Matt Zumwalt, MediaShelf LLC
3
+ # @Copyright Matt Zumwalt, 2007. All Rights Reserved.
4
+ #
5
+
6
+ module Fedora
7
+ class GenericSearch
8
+
9
+ def initialize(uri, service_name)
10
+ @uri = "#{uri}/#{service_name}"
11
+ @client = HTTPClient.new(@uri)
12
+ @extheader = {'User-Agent'=>"RubyFedora"}
13
+ end
14
+
15
+ def call_resource
16
+
17
+ end
18
+
19
+ # TODO: Handle ruby-tyle params, camel-casing them before passing to call_resource...
20
+ def update_index(params)
21
+ query = {:action=>action,:value=>value,:repositoryName=>repository_name,:indexName=>indexname,:restXslt=>"copyXML"}.merge(params)
22
+ query.merge {:operation> "updateIndex"}
23
+
24
+ @client.get(@uri, query, @extheader)
25
+ return "update_index Not Implemented."
26
+ end
27
+
28
+
29
+ def browse_index(params)
30
+ # Sample: /fedoragsearch/rest?operation=browseIndex&startTerm=&fieldName=PID&termPageSize=20&indexName=FedoraIndex&restXslt=copyXml&resultPageXslt=browseIndexToResultPage
31
+ query = {:startTerm=>URLEncoder.encode(start_term, "UTF-8"),:fieldName=>"",:indexName=>"",:termPageSize=>"", :restXslt=>"copyXml", :resultPageXslt=>""}.merge(params)
32
+ query.merge {:operation> "browseIndex"}
33
+ @client.get(@uri, query, @extheader)
34
+ return "browse_index Not Implemented."
35
+ end
36
+
37
+ def gfind_objects(params)
38
+ # Sample: /fedoragsearch/rest?operation=gfindObjects&query=test&hitPageSize=10&restXslt=copyXml
39
+ # fieldMaxLength limits the number of characters returned from the value of each object field.
40
+ # Snippets will highlight matched words within the search results. To keep the xml as simple as possible, set snippetsMax to 0.
41
+ query = {:query=>URLEncoder.encode(query, "UTF-8"),:value=>value,:indexName=>indexname,:hitPageStart=>"",:hitPageSize=>"",:snippetsMax=>"0",:fieldMaxLength=>"",:restXslt=>"copyXML",:resultPageXslt=>""}.merge(params)
42
+ query.merge {:operation> "gfindObjects"}
43
+ @client.get(@uri, query, @extheader)
44
+ return "gfind_objects Not Implemented."
45
+ end
46
+
47
+ def get_index_info(params)
48
+ # Sample: /fedoragsearch/rest?operation=getIndexInfo&restXslt=copyXml
49
+ query = {:indexName=>"",:restXslt=>"copyXml", :resultPageXslt=>""}.merge(params)
50
+ query.merge {:operation> "getIndexInfo"}
51
+ @client.get(@uri, query, @extheader)
52
+ return "get_index_info Not Implemented."
53
+ end
54
+
55
+ def get_repository_info(params)
56
+ # Sample: /fedoragsearch/rest?operation=getRepositoryInfo&restXslt=copyXml
57
+ query = {:repositoryName=>"",:restXslt=>"copyXml", :resultPageXslt=>""}.merge(params)
58
+ query.merge {:operation> "getRepositoryInfo"}
59
+ @client.get(@uri, query, @extheader)
60
+ return "get_repository_info Not Implemented."
61
+ end
62
+
63
+ def configure(params)
64
+ query = {:configName=>""}.merge(params)
65
+ query.merge {:operation> "configure"}
66
+ @client.get(@uri, query, @extheader)
67
+ return "configure Not Implemented."
68
+ end
69
+
70
+ end
71
+ end
@@ -15,6 +15,30 @@ module Fedora
15
15
  ]
16
16
 
17
17
  class Repository
18
+
19
+ attr_accessor :repository_name, :base_url, :fedora_version, :pid_namespace, :pid_delimiter
20
+
21
+ def self.flush
22
+ Thread.current[:repo]=nil
23
+ end
24
+ def self.register(url, surrogate=nil)
25
+ Thread.current[:repo]= Fedora::Repository.new(url, surrogate)
26
+ begin
27
+ repo = Thread.current[:repo]
28
+ attributes = repo.describe_repository
29
+ repo.repository_name = attributes["repositoryName"].first
30
+ repo.base_url = attributes["repositoryBaseURL"].first
31
+ repo.fedora_version = attributes["repositoryVersion"].first
32
+ repo.pid_namespace = attributes["repositoryPID"].first["PID-namespaceIdentifier"].first
33
+ repo.pid_delimiter = attributes["repositoryPID"].first["PID-delimiter"].first
34
+ rescue
35
+ end
36
+ Thread.current[:repo]
37
+ end
38
+ def self.instance
39
+ raise "did you register a repo?" unless Thread.current[:repo]
40
+ Thread.current[:repo]
41
+ end
18
42
  class StringResponse < String
19
43
  attr_reader :content_type
20
44
 
@@ -26,8 +50,9 @@ module Fedora
26
50
 
27
51
  attr_accessor :fedora_url
28
52
 
29
- def initialize(fedora_url = "http://localhost:8080/fedora")
53
+ def initialize(fedora_url, surrogate=nil)
30
54
  @fedora_url = fedora_url.is_a?(URI) ? fedora_url : URI.parse(fedora_url)
55
+ @surrogate = surrogate
31
56
  @connection = nil
32
57
  end
33
58
 
@@ -37,6 +62,8 @@ module Fedora
37
62
  StringResponse.new(response.body, response.content_type)
38
63
  end
39
64
 
65
+
66
+
40
67
  # Find fedora objects with http://www.fedora.info/wiki/index.php/API-A-Lite_findObjects
41
68
  #
42
69
  # == Parameters
@@ -69,6 +96,11 @@ module Fedora
69
96
 
70
97
  convert_xml(connection.get("#{fedora_url.path}/objects?#{params.to_query}#{includes}"))
71
98
  end
99
+ def find_model(pid, klazz)
100
+ obj = self.find_objects("pid=#{pid}").first
101
+ doc = REXML::Document.new(obj.object_xml, :ignore_whitespace_nodes=>:all)
102
+ klazz.deserialize(doc)
103
+ end
72
104
 
73
105
  # Create the given object if it's new (not obtained from a find method). Otherwise update the object.
74
106
  #
@@ -78,6 +110,12 @@ module Fedora
78
110
  def save(object)
79
111
  object.new_object? ? create(object) : update(object)
80
112
  end
113
+
114
+ def nextid
115
+ d = REXML::Document.new(connection.post(fedora_url.path+"/management/getNextPID?xml=true").body)
116
+ d.elements['//pid'].text
117
+ end
118
+
81
119
 
82
120
  def create(object)
83
121
  case object
@@ -139,7 +177,7 @@ module Fedora
139
177
  def delete(object)
140
178
  raise ArgumentError, "Object must not be nil" if object.nil?
141
179
  response = connection.delete("#{url_for(object)}")
142
- response.code == '200'
180
+ response.code == '200' or response.code == '204' # Temporary hack around error in Fedora 3.0 Final's REST API
143
181
  end
144
182
 
145
183
  # Fetch the given object using custom method. This is used to fetch other aspects of a fedora object,
@@ -162,6 +200,11 @@ module Fedora
162
200
  connection.raw_get("#{url_for(object)}#{path}?#{extra_params.to_query}").body
163
201
  end
164
202
 
203
+ def describe_repository
204
+ result_body = connection.raw_get("#{fedora_url.path}/describe?xml=true").body
205
+ XmlSimple.xml_in(result_body)
206
+ end
207
+
165
208
  private
166
209
  def convert_xml(response)
167
210
  results = FedoraObjects.new
@@ -175,6 +218,7 @@ module Fedora
175
218
  when Hash
176
219
  results << FedoraObject.new(objectFields.symbolize_keys!)
177
220
  end
221
+ results.each {|result| result.new_object = false}
178
222
  results
179
223
  end
180
224
 
@@ -189,7 +233,7 @@ module Fedora
189
233
  # or not (defaults to +false+).
190
234
  def connection(refresh = false)
191
235
  if refresh || @connection.nil?
192
- @connection = RubyFedora::Connection.new(@fedora_url, Fedora::XmlFormat)
236
+ @connection = Fedora::Connection.new(@fedora_url, Fedora::XmlFormat, @surrogate)
193
237
  end
194
238
  @connection
195
239
  end
data/lib/ruby-fedora.rb CHANGED
@@ -1,17 +1,18 @@
1
1
  $LOAD_PATH.unshift File.dirname(__FILE__) unless
2
- $LOAD_PATH.include?(File.dirname(__FILE__)) ||
3
- $LOAD_PATH.include?(File.expand_path(File.dirname(__FILE__)))
2
+ $LOAD_PATH.include?(File.dirname(__FILE__)) || $LOAD_PATH.include?(File.expand_path(File.dirname(__FILE__)))
4
3
 
5
- module RubyFedora #:nodoc:
4
+ module Fedora #:nodoc:
6
5
  module VERSION #:nodoc:
7
- MAJOR = 0
8
- MINOR = 1
9
- TINY = 2
6
+ unless defined? MAJOR
7
+ MAJOR = 0
8
+ MINOR = 9
9
+ TINY = 0
10
10
 
11
- STRING = [MAJOR, MINOR, TINY].join('.')
11
+ STRING = [MAJOR, MINOR, TINY].join('.')
12
+ end
12
13
  end
13
14
  end
14
15
 
15
16
  module Fedora; end
16
17
 
17
- require 'fedora/repository'
18
+ require 'fedora/repository'
@@ -0,0 +1,23 @@
1
+ module MediaShelfClassLevelInheritableAttributes
2
+ def self.included(base)
3
+ base.extend(MSClassMethods)
4
+ end
5
+ module MSClassMethods
6
+ def ms_inheritable_attributes(*args)
7
+ @ms_inheritable_attributes ||=[:ms_inheritable_attributes]
8
+ @ms_inheritable_attributes+=args
9
+ args.each do |arg|
10
+ class_eval %(
11
+ class <<self;attr_accessor :#{arg} end
12
+ )
13
+ end
14
+ @ms_inheritable_attributes
15
+ end
16
+ def inherited(subclass)
17
+ @ms_inheritable_attributes.each do |attrib|
18
+ instance_var = "@#{attrib}"
19
+ subclass.instance_variable_set(instance_var, instance_variable_get(instance_var))
20
+ end
21
+ end
22
+ end
23
+ end
@@ -0,0 +1,229 @@
1
+ <?xml version="1.0" ?>
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
+ <!-- This is the Solr schema file. This file should be named "schema.xml" and
20
+ should be in the conf directory under the solr home
21
+ (i.e. ./solr/conf/schema.xml by default)
22
+ or located where the classloader for the Solr webapp can find it.
23
+
24
+ For more information, on how to customize this file, please see
25
+ http://wiki.apache.org/solr/SchemaXml
26
+ -->
27
+
28
+ <schema name="active_fedora" version="0.1">
29
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
30
+ Applications should change this to reflect the nature of the search collection.
31
+ version="1.1" is Solr's version number for the schema syntax and semantics. It should
32
+ not normally be changed by applications.
33
+ 1.0: multiValued attribute did not exist, all fields are multiValued by nature
34
+ 1.1: multiValued attribute introduced, false by default -->
35
+
36
+ <types>
37
+ <!-- field type definitions. The "name" attribute is
38
+ just a label to be used by field definitions. The "class"
39
+ attribute and any other attributes determine the real
40
+ behavior of the fieldtype.
41
+ Class names starting with "solr" refer to java classes in the
42
+ org.apache.solr.analysis package.
43
+ -->
44
+
45
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
46
+ - StrField and TextField support an optional compressThreshold which
47
+ limits compression (if enabled in the derived fields) to values which
48
+ exceed a certain size (in characters).
49
+ -->
50
+ <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
51
+
52
+ <!-- boolean type: "true" or "false" -->
53
+ <fieldtype name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
54
+
55
+ <!-- The optional sortMissingLast and sortMissingFirst attributes are
56
+ currently supported on types that are sorted internally as strings.
57
+ - If sortMissingLast="true", then a sort on this field will cause documents
58
+ without the field to come after documents with the field,
59
+ regardless of the requested sort order (asc or desc).
60
+ - If sortMissingFirst="true", then a sort on this field will cause documents
61
+ without the field to come before documents with the field,
62
+ regardless of the requested sort order.
63
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
64
+ then default lucene sorting will be used which places docs without the
65
+ field first in an ascending sort and last in a descending sort.
66
+ -->
67
+
68
+
69
+ <!-- numeric field types that store and index the text
70
+ value verbatim (and hence don't support range queries, since the
71
+ lexicographic ordering isn't equal to the numeric ordering) -->
72
+ <fieldtype name="integer" class="solr.IntField" omitNorms="true"/>
73
+ <fieldtype name="long" class="solr.LongField" omitNorms="true"/>
74
+ <fieldtype name="float" class="solr.FloatField" omitNorms="true"/>
75
+ <fieldtype name="double" class="solr.DoubleField" omitNorms="true"/>
76
+
77
+
78
+ <!-- Numeric field types that manipulate the value into
79
+ a string value that isn't human-readable in its internal form,
80
+ but with a lexicographic ordering the same as the numeric ordering,
81
+ so that range queries work correctly. -->
82
+ <fieldtype name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
83
+ <fieldtype name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
84
+ <fieldtype name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
85
+ <fieldtype name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
86
+
87
+
88
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
89
+ is a more restricted form of the canonical representation of dateTime
90
+ http://www.w3.org/TR/xmlschema-2/#dateTime
91
+ The trailing "Z" designates UTC time and is mandatory.
92
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
93
+ All other components are mandatory.
94
+
95
+ Expressions can also be used to denote calculations that should be
96
+ performed relative to "NOW" to determine the value, ie...
97
+
98
+ NOW/HOUR
99
+ ... Round to the start of the current hour
100
+ NOW-1DAY
101
+ ... Exactly 1 day prior to now
102
+ NOW/DAY+6MONTHS+3DAYS
103
+ ... 6 months and 3 days in the future from the start of
104
+ the current day
105
+
106
+ Consult the DateField javadocs for more information.
107
+ -->
108
+ <fieldtype name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
109
+
110
+ <!-- solr.TextField allows the specification of custom text analyzers
111
+ specified as a tokenizer and a list of token filters. Different
112
+ analyzers may be specified for indexing and querying.
113
+
114
+ The optional positionIncrementGap puts space between multiple fields of
115
+ this type on the same document, with the purpose of preventing false phrase
116
+ matching across fields.
117
+
118
+ For more info on customizing your analyzer chain, please see
119
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
120
+ -->
121
+
122
+ <!-- One can also specify an existing Analyzer class that has a
123
+ default constructor via the class attribute on the analyzer element
124
+ <fieldtype name="text_greek" class="solr.TextField">
125
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
126
+ </fieldType>
127
+ -->
128
+
129
+ <!-- A text field that only splits on whitespace for exact matching of words -->
130
+ <fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
131
+ <analyzer>
132
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
133
+ </analyzer>
134
+ </fieldtype>
135
+
136
+ <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
137
+ <analyzer>
138
+ <tokenizer class="solr.StandardTokenizerFactory"/>
139
+ <filter class="solr.StandardFilterFactory"/>
140
+ <filter class="solr.LowerCaseFilterFactory"/>
141
+ </analyzer>
142
+ </fieldtype>
143
+
144
+ <fieldtype name="text_zh" class="solr.TextField">
145
+ <analyzer class="org.apache.lucene.analysis.cn.ChineseAnalyzer"/>
146
+ </fieldtype>
147
+
148
+
149
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
150
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
151
+ <fieldtype name="textTight" class="solr.TextField" positionIncrementGap="100" >
152
+ <analyzer>
153
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
154
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
155
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
156
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
157
+ <filter class="solr.LowerCaseFilterFactory"/>
158
+ <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
159
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
160
+ </analyzer>
161
+ </fieldtype>
162
+
163
+ </types>
164
+
165
+
166
+ <fields>
167
+ <!-- Valid attributes for fields:
168
+ name: mandatory - the name for the field
169
+ type: mandatory - the name of a previously defined type from the <types> section
170
+ indexed: true if this field should be indexed (searchable or sortable)
171
+ stored: true if this field should be retrievable
172
+ compressed: [false] if this field should be stored using gzip compression
173
+ (this will only apply if the field type is compressable; among
174
+ the standard field types, only TextField and StrField are)
175
+ multiValued: true if this field may contain multiple values per document
176
+ omitNorms: (expert) set to true to omit the norms associated with
177
+ this field (this disables length normalization and index-time
178
+ boosting for the field, and saves some memory). Only full-text
179
+ fields or fields that need an index-time boost need norms.
180
+ -->
181
+
182
+ <field name="id" type="string" indexed="true" stored="true"/>
183
+
184
+ <!-- catchall field, containing all other searchable text fields (implemented
185
+ via copyField further on in this schema -->
186
+ <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
187
+ <!-- catchall field, containing all other searchable text fields (implemented
188
+ via copyField further on in this schema -->
189
+ <field name="date" type="date" indexed="true" stored="false" multiValued="true"/>
190
+
191
+ <!-- Dynamic field definitions. If a field name is not found, dynamicFields
192
+ will be used if the name matches any of the patterns.
193
+ RESTRICTION: the glob-like pattern in the name attribute must have
194
+ a "*" only at the start or the end.
195
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
196
+ Longer patterns will be matched first. if equal size patterns
197
+ both match, the first appearing in the schema will be used. -->
198
+ <dynamicField name="*_date" type="date" indexed="true" stored="true" multiValued="true"/>
199
+ <dynamicField name="*_name" type="date" indexed="true" stored="true" multiValued="true"/>
200
+ <dynamicField name="*_field" type="text" indexed="true" stored="true" multiValued="true"/>
201
+
202
+ <dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true"/>
203
+ <dynamicField name="*_zh_text" type="text_zh" indexed="true" stored="true" multiValued="true"/>
204
+ <dynamicField name="*_text" type="text" indexed="true" stored="true" multiValued="true"/>
205
+ <dynamicField name="*_display" type="text" indexed="false" stored="true" multiValued="true"/>
206
+ </fields>
207
+
208
+ <!-- field to use to determine and enforce document uniqueness. -->
209
+ <uniqueKey>id</uniqueKey>
210
+
211
+ <!-- field for the QueryParser to use when an explicit fieldname is absent -->
212
+ <defaultSearchField>text</defaultSearchField>
213
+
214
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
215
+ <solrQueryParser defaultOperator="AND"/>
216
+
217
+ <!-- copyField commands copy one field to another at the time a document
218
+ is added to the index. It's used either to index the same field differently,
219
+ or to add multiple fields to the same field for easier/faster searching. -->
220
+ <copyField source="*_date" dest="date"/>
221
+ <copyField source="*_text" dest="text"/>
222
+ <copyField source="*_facet" dest="text"/>
223
+
224
+ <!-- Similarity is the scoring routine for each document vs. a query.
225
+ A custom similarity may be specified here, but the default is fine
226
+ for most applications. -->
227
+ <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
228
+
229
+ </schema>