samvera-nesting_indexer 0.3.0

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.
@@ -0,0 +1,127 @@
1
+ require 'samvera/nesting_indexer/exceptions'
2
+ require 'forwardable'
3
+ require 'set'
4
+
5
+ module Samvera
6
+ # Establishing namespace
7
+ module NestingIndexer
8
+ # Responsible for reindexing the PID and its descendants
9
+ # @note There is cycle detection via the TIME_TO_LIVE counter
10
+ # @api private
11
+ class RelationshipReindexer
12
+ # @api private
13
+ #
14
+ # A convenience method that coordinate the relationship reindexing of the given id.
15
+ #
16
+ # @see #initialize
17
+ # @return Samvera::NestingIndexer::RelationshipReindexer
18
+ def self.call(**kwargs)
19
+ new(**kwargs).call
20
+ end
21
+
22
+ # @param id [String]
23
+ # @param maximum_nesting_depth [Integer] Samvera::NestingIndexer::TIME_TO_LIVE to detect cycles in the graph
24
+ # @param adapter [Samvera::NestingIndexer::Adapters::AbstractAdapter] Conforms to the Samvera::NestingIndexer::Adapters::AbstractAdapter interface
25
+ # @param queue [#shift, #push] queue
26
+ def initialize(id:, maximum_nesting_depth:, adapter:, queue: [])
27
+ @id = id.to_s
28
+ @maximum_nesting_depth = maximum_nesting_depth.to_i
29
+ @adapter = adapter
30
+ @queue = queue
31
+ end
32
+ attr_reader :id, :maximum_nesting_depth, :queue, :adapter
33
+
34
+ # Perform a bread-first tree traversal of the initial document and its descendants.
35
+ def call
36
+ enqueue(initial_index_document, maximum_nesting_depth)
37
+ processing_document = dequeue
38
+ while processing_document
39
+ process_a_document(processing_document)
40
+ adapter.each_child_document_of(document: processing_document) { |child| enqueue(child, processing_document.maximum_nesting_depth - 1) }
41
+ processing_document = dequeue
42
+ end
43
+ self
44
+ end
45
+
46
+ private
47
+
48
+ attr_writer :document
49
+
50
+ def initial_index_document
51
+ adapter.find_index_document_by(id: id)
52
+ end
53
+
54
+ extend Forwardable
55
+ def_delegator :queue, :shift, :dequeue
56
+
57
+ require 'delegate'
58
+ # A small object to help track time to live concerns
59
+ class ProcessingDocument < SimpleDelegator
60
+ def initialize(document, maximum_nesting_depth)
61
+ @maximum_nesting_depth = maximum_nesting_depth
62
+ super(document)
63
+ end
64
+ attr_reader :maximum_nesting_depth
65
+ end
66
+ private_constant :ProcessingDocument
67
+ def enqueue(document, maximum_nesting_depth)
68
+ queue.push(ProcessingDocument.new(document, maximum_nesting_depth))
69
+ end
70
+
71
+ def process_a_document(index_document)
72
+ raise Exceptions::CycleDetectionError, id if index_document.maximum_nesting_depth <= 0
73
+ preservation_document = adapter.find_preservation_document_by(id: index_document.id)
74
+ parent_ids_and_path_and_ancestors = parent_ids_and_path_and_ancestors_for(preservation_document)
75
+ adapter.write_document_attributes_to_index_layer(parent_ids_and_path_and_ancestors)
76
+ end
77
+
78
+ def parent_ids_and_path_and_ancestors_for(preservation_document)
79
+ ParentAndPathAndAncestorsBuilder.new(preservation_document, adapter).to_hash
80
+ end
81
+
82
+ # A small object that helps encapsulate the logic of building the hash of information regarding
83
+ # the initialization of an Samvera::NestingIndexer::Documents::IndexDocument
84
+ #
85
+ # @see Samvera::NestingIndexer::Documents::IndexDocument for details on pathnames, ancestors, and parent_ids.
86
+ class ParentAndPathAndAncestorsBuilder
87
+ def initialize(preservation_document, adapter)
88
+ @preservation_document = preservation_document
89
+ @parent_ids = Set.new
90
+ @pathnames = Set.new
91
+ @ancestors = Set.new
92
+ @adapter = adapter
93
+ compile!
94
+ end
95
+
96
+ def to_hash
97
+ { id: @preservation_document.id, parent_ids: @parent_ids.to_a, pathnames: @pathnames.to_a, ancestors: @ancestors.to_a }
98
+ end
99
+
100
+ private
101
+
102
+ attr_reader :adapter
103
+
104
+ def compile!
105
+ @preservation_document.parent_ids.each do |parent_id|
106
+ parent_index_document = adapter.find_index_document_by(id: parent_id)
107
+ compile_one!(parent_index_document)
108
+ end
109
+ # Ensuring that an "orphan" has a path to get to it
110
+ @pathnames << @preservation_document.id if @parent_ids.empty?
111
+ end
112
+
113
+ def compile_one!(parent_index_document)
114
+ @parent_ids << parent_index_document.id
115
+ parent_index_document.pathnames.each do |pathname|
116
+ @pathnames << File.join(pathname, @preservation_document.id)
117
+ slugs = pathname.split("/")
118
+ slugs.each_index { |i| @ancestors << slugs[0..i].join('/') }
119
+ end
120
+ @ancestors += parent_index_document.ancestors
121
+ end
122
+ end
123
+ private_constant :ParentAndPathAndAncestorsBuilder
124
+ end
125
+ private_constant :RelationshipReindexer
126
+ end
127
+ end
@@ -0,0 +1,65 @@
1
+ module Samvera
2
+ # Establishing namespace
3
+ module NestingIndexer
4
+ # Responsible for reindexing the entire repository
5
+ # @api private
6
+ # @note There is cycle detection logic for walking the graph prior to attempting relationship re-indexing
7
+ class RepositoryReindexer
8
+ # @api private
9
+ #
10
+ # A convenience method to reindex all documents.
11
+ #
12
+ # @note This could crush your system as it will loop through ALL the documents
13
+ #
14
+ # @see #initialize
15
+ # @return Samvera::NestingIndexer::RepositoryReindexer
16
+ def self.call(*args)
17
+ new(*args).call
18
+ end
19
+
20
+ # @param id_reindexer [#call] Samvera::NestingIndexer.method(:reindex_relationships) Responsible for reindexing a single object
21
+ # @param maximum_nesting_depth [Integer] detect cycles in the graph
22
+ # @param adapter [Samvera::NestingIndexer::Adapters::AbstractAdapter] Conforms to the Samvera::NestingIndexer::Adapters::AbstractAdapter interface
23
+ def initialize(maximum_nesting_depth:, id_reindexer:, adapter:)
24
+ @max_maximum_nesting_depth = maximum_nesting_depth.to_i
25
+ @id_reindexer = id_reindexer
26
+ @adapter = adapter
27
+ @processed_ids = []
28
+ end
29
+
30
+ # @todo Would it make sense to leverage an each_preservation_id instead?
31
+ def call
32
+ @adapter.each_preservation_document { |document| recursive_reindex(document, max_maximum_nesting_depth) }
33
+ end
34
+
35
+ private
36
+
37
+ attr_reader :max_maximum_nesting_depth, :processed_ids, :id_reindexer
38
+
39
+ # When we find a document, reindex it if it doesn't have a parent. If it has a parent, reindex the parent first.
40
+ #
41
+ # Given that we are attempting to reindex the parents before we reindex a document, we can't rely on
42
+ # the reindex maximum_nesting_depth but instead must have a separate time to live.
43
+ #
44
+ # The reindexing process assumes that an object's parents have been indexed; Thus we need to
45
+ # walk up the parent graph to reindex the parents before we start on the child.
46
+ def recursive_reindex(document, maximum_nesting_depth = max_maximum_nesting_depth)
47
+ return true if processed_ids.include?(document.id)
48
+ raise Exceptions::CycleDetectionError, document.id if maximum_nesting_depth <= 0
49
+ document.parent_ids.each do |parent_id|
50
+ parent_document = @adapter.find_preservation_document_by(id: parent_id)
51
+ recursive_reindex(parent_document, maximum_nesting_depth - 1)
52
+ end
53
+ reindex_a_id(document.id)
54
+ end
55
+
56
+ def reindex_a_id(id)
57
+ id_reindexer.call(id: id)
58
+ processed_ids << id
59
+ rescue StandardError => e
60
+ raise Exceptions::ReindexingError.new(id, e)
61
+ end
62
+ end
63
+ private_constant :RepositoryReindexer
64
+ end
65
+ end
@@ -0,0 +1,5 @@
1
+ module Samvera
2
+ module NestingIndexer
3
+ VERSION = "0.3.0".freeze
4
+ end
5
+ end
@@ -0,0 +1,39 @@
1
+ lib = File.expand_path('../lib', __FILE__)
2
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
3
+ require 'samvera/nesting_indexer/version'
4
+
5
+ Gem::Specification.new do |spec|
6
+ spec.name = "samvera-nesting_indexer"
7
+ spec.version = Samvera::NestingIndexer::VERSION
8
+ spec.authors = ["Jeremy Friesen"]
9
+ spec.email = ["jeremy.n.friesen@gmail.com"]
10
+
11
+ spec.summary = %q{Samvera nested collections indexing}
12
+ spec.description = %q{Samvera nested collections indexing}
13
+ spec.homepage = "https://github.com/samvera-labs/samvera-nesting_indexer"
14
+ spec.license = "Apache-2.0"
15
+
16
+ spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
17
+ spec.bindir = "bin"
18
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
19
+ spec.require_paths = ["lib"]
20
+ spec.required_ruby_version = '~>2.0'
21
+
22
+ spec.add_development_dependency "bundler", "~> 1.12"
23
+ spec.add_development_dependency "rake", "~> 10.0"
24
+ spec.add_development_dependency "rspec", "~> 3.0"
25
+ spec.add_development_dependency "rspec-its"
26
+ spec.add_development_dependency "guard-rspec"
27
+ spec.add_development_dependency "guard-rubocop"
28
+ spec.add_development_dependency "terminal-notifier-guard"
29
+ spec.add_development_dependency "terminal-notifier"
30
+ spec.add_development_dependency "rubocop"
31
+ spec.add_development_dependency "simplecov"
32
+ spec.add_development_dependency "codeclimate-test-reporter"
33
+ spec.add_development_dependency "json"
34
+ spec.add_development_dependency "byebug"
35
+ spec.add_development_dependency "railties"
36
+ # As a secondary dependency, listen is preventing bundling
37
+ spec.add_development_dependency "listen", '~> 3.0.8'
38
+ spec.add_dependency "dry-equalizer"
39
+ end
metadata ADDED
@@ -0,0 +1,294 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: samvera-nesting_indexer
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.3.0
5
+ platform: ruby
6
+ authors:
7
+ - Jeremy Friesen
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2017-08-24 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: bundler
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '1.12'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.12'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rake
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '10.0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '10.0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rspec
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '3.0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '3.0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: rspec-its
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: guard-rspec
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: guard-rubocop
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: terminal-notifier-guard
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ - !ruby/object:Gem::Dependency
112
+ name: terminal-notifier
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - ">="
116
+ - !ruby/object:Gem::Version
117
+ version: '0'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - ">="
123
+ - !ruby/object:Gem::Version
124
+ version: '0'
125
+ - !ruby/object:Gem::Dependency
126
+ name: rubocop
127
+ requirement: !ruby/object:Gem::Requirement
128
+ requirements:
129
+ - - ">="
130
+ - !ruby/object:Gem::Version
131
+ version: '0'
132
+ type: :development
133
+ prerelease: false
134
+ version_requirements: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - ">="
137
+ - !ruby/object:Gem::Version
138
+ version: '0'
139
+ - !ruby/object:Gem::Dependency
140
+ name: simplecov
141
+ requirement: !ruby/object:Gem::Requirement
142
+ requirements:
143
+ - - ">="
144
+ - !ruby/object:Gem::Version
145
+ version: '0'
146
+ type: :development
147
+ prerelease: false
148
+ version_requirements: !ruby/object:Gem::Requirement
149
+ requirements:
150
+ - - ">="
151
+ - !ruby/object:Gem::Version
152
+ version: '0'
153
+ - !ruby/object:Gem::Dependency
154
+ name: codeclimate-test-reporter
155
+ requirement: !ruby/object:Gem::Requirement
156
+ requirements:
157
+ - - ">="
158
+ - !ruby/object:Gem::Version
159
+ version: '0'
160
+ type: :development
161
+ prerelease: false
162
+ version_requirements: !ruby/object:Gem::Requirement
163
+ requirements:
164
+ - - ">="
165
+ - !ruby/object:Gem::Version
166
+ version: '0'
167
+ - !ruby/object:Gem::Dependency
168
+ name: json
169
+ requirement: !ruby/object:Gem::Requirement
170
+ requirements:
171
+ - - ">="
172
+ - !ruby/object:Gem::Version
173
+ version: '0'
174
+ type: :development
175
+ prerelease: false
176
+ version_requirements: !ruby/object:Gem::Requirement
177
+ requirements:
178
+ - - ">="
179
+ - !ruby/object:Gem::Version
180
+ version: '0'
181
+ - !ruby/object:Gem::Dependency
182
+ name: byebug
183
+ requirement: !ruby/object:Gem::Requirement
184
+ requirements:
185
+ - - ">="
186
+ - !ruby/object:Gem::Version
187
+ version: '0'
188
+ type: :development
189
+ prerelease: false
190
+ version_requirements: !ruby/object:Gem::Requirement
191
+ requirements:
192
+ - - ">="
193
+ - !ruby/object:Gem::Version
194
+ version: '0'
195
+ - !ruby/object:Gem::Dependency
196
+ name: railties
197
+ requirement: !ruby/object:Gem::Requirement
198
+ requirements:
199
+ - - ">="
200
+ - !ruby/object:Gem::Version
201
+ version: '0'
202
+ type: :development
203
+ prerelease: false
204
+ version_requirements: !ruby/object:Gem::Requirement
205
+ requirements:
206
+ - - ">="
207
+ - !ruby/object:Gem::Version
208
+ version: '0'
209
+ - !ruby/object:Gem::Dependency
210
+ name: listen
211
+ requirement: !ruby/object:Gem::Requirement
212
+ requirements:
213
+ - - "~>"
214
+ - !ruby/object:Gem::Version
215
+ version: 3.0.8
216
+ type: :development
217
+ prerelease: false
218
+ version_requirements: !ruby/object:Gem::Requirement
219
+ requirements:
220
+ - - "~>"
221
+ - !ruby/object:Gem::Version
222
+ version: 3.0.8
223
+ - !ruby/object:Gem::Dependency
224
+ name: dry-equalizer
225
+ requirement: !ruby/object:Gem::Requirement
226
+ requirements:
227
+ - - ">="
228
+ - !ruby/object:Gem::Version
229
+ version: '0'
230
+ type: :runtime
231
+ prerelease: false
232
+ version_requirements: !ruby/object:Gem::Requirement
233
+ requirements:
234
+ - - ">="
235
+ - !ruby/object:Gem::Version
236
+ version: '0'
237
+ description: Samvera nested collections indexing
238
+ email:
239
+ - jeremy.n.friesen@gmail.com
240
+ executables: []
241
+ extensions: []
242
+ extra_rdoc_files: []
243
+ files:
244
+ - ".gitignore"
245
+ - ".rspec"
246
+ - ".rubocop.yml"
247
+ - ".rubocop_todo.yml"
248
+ - ".ruby-version"
249
+ - ".travis.yml"
250
+ - Gemfile
251
+ - Guardfile
252
+ - LICENSE
253
+ - README.md
254
+ - Rakefile
255
+ - bin/console
256
+ - bin/setup
257
+ - lib/samvera/nesting_indexer.rb
258
+ - lib/samvera/nesting_indexer/adapters.rb
259
+ - lib/samvera/nesting_indexer/adapters/abstract_adapter.rb
260
+ - lib/samvera/nesting_indexer/adapters/in_memory_adapter.rb
261
+ - lib/samvera/nesting_indexer/adapters/interface_behavior_spec.rb
262
+ - lib/samvera/nesting_indexer/configuration.rb
263
+ - lib/samvera/nesting_indexer/documents.rb
264
+ - lib/samvera/nesting_indexer/exceptions.rb
265
+ - lib/samvera/nesting_indexer/railtie.rb
266
+ - lib/samvera/nesting_indexer/relationship_reindexer.rb
267
+ - lib/samvera/nesting_indexer/repository_reindexer.rb
268
+ - lib/samvera/nesting_indexer/version.rb
269
+ - samvera-nesting_indexer.gemspec
270
+ homepage: https://github.com/samvera-labs/samvera-nesting_indexer
271
+ licenses:
272
+ - Apache-2.0
273
+ metadata: {}
274
+ post_install_message:
275
+ rdoc_options: []
276
+ require_paths:
277
+ - lib
278
+ required_ruby_version: !ruby/object:Gem::Requirement
279
+ requirements:
280
+ - - "~>"
281
+ - !ruby/object:Gem::Version
282
+ version: '2.0'
283
+ required_rubygems_version: !ruby/object:Gem::Requirement
284
+ requirements:
285
+ - - ">="
286
+ - !ruby/object:Gem::Version
287
+ version: '0'
288
+ requirements: []
289
+ rubyforge_project:
290
+ rubygems_version: 2.6.11
291
+ signing_key:
292
+ specification_version: 4
293
+ summary: Samvera nested collections indexing
294
+ test_files: []