active_record_data_loader 1.0.1 → 1.3.0

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.
Files changed (40) hide show
  1. checksums.yaml +4 -4
  2. data/.github/workflows/build.yml +51 -0
  3. data/.github/workflows/codeql-analysis.yml +70 -0
  4. data/.github/workflows/gem-push.yml +29 -0
  5. data/.rubocop.yml +46 -7
  6. data/CHANGELOG.md +37 -1
  7. data/CODE_OF_CONDUCT.md +2 -2
  8. data/Gemfile.lock +72 -72
  9. data/README.md +162 -9
  10. data/Rakefile +8 -2
  11. data/active_record_data_loader.gemspec +8 -6
  12. data/config/database.yml +9 -0
  13. data/docker-compose.yml +18 -0
  14. data/gemfiles/activerecord_6.gemfile +1 -1
  15. data/lib/active_record_data_loader/active_record/{belongs_to_configuration.rb → belongs_to_data_provider.rb} +8 -7
  16. data/lib/active_record_data_loader/active_record/{column_configuration.rb → column_data_provider.rb} +14 -5
  17. data/lib/active_record_data_loader/active_record/datetime_value_generator.rb +1 -1
  18. data/lib/active_record_data_loader/active_record/enum_value_generator.rb +28 -5
  19. data/lib/active_record_data_loader/active_record/integer_value_generator.rb +2 -2
  20. data/lib/active_record_data_loader/active_record/list.rb +35 -0
  21. data/lib/active_record_data_loader/active_record/model_data_generator.rb +74 -6
  22. data/lib/active_record_data_loader/active_record/{polymorphic_belongs_to_configuration.rb → polymorphic_belongs_to_data_provider.rb} +12 -7
  23. data/lib/active_record_data_loader/active_record/text_value_generator.rb +1 -1
  24. data/lib/active_record_data_loader/active_record/unique_index_tracker.rb +67 -0
  25. data/lib/active_record_data_loader/bulk_insert_strategy.rb +16 -8
  26. data/lib/active_record_data_loader/configuration.rb +28 -3
  27. data/lib/active_record_data_loader/connection_handler.rb +52 -0
  28. data/lib/active_record_data_loader/copy_strategy.rb +38 -24
  29. data/lib/active_record_data_loader/data_faker.rb +12 -4
  30. data/lib/active_record_data_loader/dsl/model.rb +19 -2
  31. data/lib/active_record_data_loader/errors.rb +5 -0
  32. data/lib/active_record_data_loader/file_output_adapter.rb +48 -0
  33. data/lib/active_record_data_loader/loader.rb +57 -67
  34. data/lib/active_record_data_loader/null_output_adapter.rb +15 -0
  35. data/lib/active_record_data_loader/table_loader.rb +59 -0
  36. data/lib/active_record_data_loader/version.rb +1 -1
  37. data/lib/active_record_data_loader.rb +12 -36
  38. metadata +52 -15
  39. data/.travis.yml +0 -23
  40. data/config/database.yml.travis +0 -7
@@ -1,92 +1,82 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- require "benchmark"
4
-
5
3
  module ActiveRecordDataLoader
6
4
  class Loader
7
- class << self
8
- def load_data(
9
- data_generator:,
10
- total_rows:,
11
- batch_size:,
12
- configuration:
13
- )
14
- new(
15
- logger: configuration.logger,
16
- statement_timeout: configuration.statement_timeout,
17
- strategy: strategy_class.new(data_generator)
18
- ).load_data(batch_size, total_rows)
19
- end
20
-
21
- private
22
-
23
- def strategy_class
24
- if ::ActiveRecord::Base.connection.raw_connection.respond_to?(:copy_data)
25
- ActiveRecordDataLoader::CopyStrategy
26
- else
27
- ActiveRecordDataLoader::BulkInsertStrategy
28
- end
29
- end
30
- end
31
-
32
- def initialize(logger:, statement_timeout:, strategy:)
33
- @logger = logger
34
- @strategy = strategy
35
- @statement_timeout = statement_timeout
5
+ def initialize(configuration, definition)
6
+ @configuration = configuration
7
+ @definition = definition
36
8
  end
37
9
 
38
- def load_data(batch_size, total_rows)
39
- batch_count = (total_rows / batch_size.to_f).ceil
10
+ def load_data
11
+ ActiveRecordDataLoader::ActiveRecord::PerRowValueCache.clear
40
12
 
41
- logger.info(
42
- "[ActiveRecordDataLoader] "\
43
- "Loading #{total_rows} row(s) into '#{strategy.table_name}' via #{strategy.name}. "\
44
- "#{batch_size} row(s) per batch, #{batch_count} batch(es)."
45
- )
46
- total_time = Benchmark.realtime do
47
- load_in_batches(batch_size, total_rows, batch_count)
13
+ file_adapter_class.with_output_options(file_adapter_options) do |file_adapter|
14
+ definition.models.map { |m| load_model(m, file_adapter) }
48
15
  end
49
- logger.info(
50
- "[ActiveRecordDataLoader] "\
51
- "Completed loading #{total_rows} row(s) into '#{strategy.table_name}' "\
52
- "in #{total_time} seconds."
53
- )
54
16
  end
55
17
 
56
18
  private
57
19
 
58
- attr_reader :strategy, :statement_timeout, :logger
20
+ attr_reader :definition, :configuration
59
21
 
60
- def load_in_batches(batch_size, total_rows, batch_count)
61
- with_connection do |connection|
62
- total_rows.times.each_slice(batch_size).with_index do |row_numbers, i|
63
- time = Benchmark.realtime { strategy.load_batch(row_numbers, connection) }
22
+ def load_model(model, file_adapter)
23
+ ActiveRecordDataLoader::TableLoader.load_data(
24
+ batch_size: model.batch_size,
25
+ total_rows: model.row_count,
26
+ connection_handler: connection_handler,
27
+ strategy: strategy_class.new(generator(model), file_adapter),
28
+ logger: configuration.logger
29
+ )
30
+ end
64
31
 
65
- logger.debug(
66
- "[ActiveRecordDataLoader] "\
67
- "Completed batch #{i + 1}/#{batch_count}, #{row_numbers.count} row(s) in #{time} seconds"
68
- )
69
- end
70
- end
32
+ def generator(model)
33
+ ActiveRecordDataLoader::ActiveRecord::ModelDataGenerator.new(
34
+ model: model.klass,
35
+ column_settings: model.columns,
36
+ polymorphic_settings: model.polymorphic_associations,
37
+ belongs_to_settings: model.belongs_to_associations,
38
+ connection_factory: configuration.connection_factory,
39
+ raise_on_duplicates: model.raise_on_duplicates_flag,
40
+ max_duplicate_retries: model.max_duplicate_retries,
41
+ logger: configuration.logger
42
+ )
71
43
  end
72
44
 
73
- def with_connection
74
- if ::ActiveRecord::Base.connection.adapter_name.downcase.to_sym == :postgresql
75
- original_timeout = retrieve_statement_timeout
76
- update_statement_timeout(statement_timeout)
77
- yield ::ActiveRecord::Base.connection
78
- update_statement_timeout(original_timeout)
45
+ def file_adapter_class
46
+ if configuration.output.present?
47
+ ActiveRecordDataLoader::FileOutputAdapter
79
48
  else
80
- yield ::ActiveRecord::Base.connection
49
+ ActiveRecordDataLoader::NullOutputAdapter
81
50
  end
82
51
  end
83
52
 
84
- def retrieve_statement_timeout
85
- ::ActiveRecord::Base.connection.execute("SHOW statement_timeout").first["statement_timeout"]
53
+ def file_adapter_options
54
+ timeout_commands =
55
+ if connection_handler.supports_timeout?
56
+ {
57
+ pre_command: connection_handler.timeout_set_command,
58
+ post_command: connection_handler.reset_timeout_command,
59
+ }
60
+ else
61
+ {}
62
+ end
63
+
64
+ timeout_commands.merge(filename: configuration.output)
86
65
  end
87
66
 
88
- def update_statement_timeout(timeout)
89
- ::ActiveRecord::Base.connection.execute("SET statement_timeout = \"#{timeout}\"")
67
+ def strategy_class
68
+ @strategy_class ||= if connection_handler.supports_copy?
69
+ ActiveRecordDataLoader::CopyStrategy
70
+ else
71
+ ActiveRecordDataLoader::BulkInsertStrategy
72
+ end
73
+ end
74
+
75
+ def connection_handler
76
+ @connection_handler ||= ActiveRecordDataLoader::ConnectionHandler.new(
77
+ connection_factory: configuration.connection_factory,
78
+ statement_timeout: configuration.statement_timeout
79
+ )
90
80
  end
91
81
  end
92
82
  end
@@ -0,0 +1,15 @@
1
+ # frozen_string_literal: true
2
+
3
+ module ActiveRecordDataLoader
4
+ class NullOutputAdapter
5
+ def self.with_output_options(_options)
6
+ yield new
7
+ end
8
+
9
+ def copy(table:, columns:, data:, row_numbers:); end
10
+
11
+ def insert(command); end
12
+
13
+ def write_command(command); end
14
+ end
15
+ end
@@ -0,0 +1,59 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "benchmark"
4
+
5
+ module ActiveRecordDataLoader
6
+ class TableLoader
7
+ def self.load_data(
8
+ total_rows:,
9
+ batch_size:,
10
+ logger:,
11
+ connection_handler:,
12
+ strategy:
13
+ )
14
+ new(logger: logger, connection_handler: connection_handler, strategy: strategy)
15
+ .load_data(batch_size, total_rows)
16
+ end
17
+
18
+ def initialize(logger:, connection_handler:, strategy:)
19
+ @logger = logger
20
+ @connection_handler = connection_handler
21
+ @strategy = strategy
22
+ end
23
+
24
+ def load_data(batch_size, total_rows)
25
+ batch_count = (total_rows / batch_size.to_f).ceil
26
+
27
+ logger.info(
28
+ "[ActiveRecordDataLoader] "\
29
+ "Loading #{total_rows} row(s) into '#{strategy.table_name}' via #{strategy.name}. "\
30
+ "#{batch_size} row(s) per batch, #{batch_count} batch(es)."
31
+ )
32
+ total_time = Benchmark.realtime do
33
+ load_in_batches(batch_size, total_rows, batch_count)
34
+ end
35
+ logger.info(
36
+ "[ActiveRecordDataLoader] "\
37
+ "Completed loading #{total_rows} row(s) into '#{strategy.table_name}' "\
38
+ "in #{total_time} seconds."
39
+ )
40
+ end
41
+
42
+ private
43
+
44
+ attr_reader :strategy, :connection_handler, :logger
45
+
46
+ def load_in_batches(batch_size, total_rows, batch_count)
47
+ connection_handler.with_connection do |connection|
48
+ total_rows.times.each_slice(batch_size).with_index do |row_numbers, i|
49
+ time = Benchmark.realtime { strategy.load_batch(row_numbers, connection) }
50
+
51
+ logger.debug(
52
+ "[ActiveRecordDataLoader] "\
53
+ "Completed batch #{i + 1}/#{batch_count}, #{row_numbers.count} row(s) in #{time} seconds"
54
+ )
55
+ end
56
+ end
57
+ end
58
+ end
59
+ end
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module ActiveRecordDataLoader
4
- VERSION = "1.0.1"
4
+ VERSION = "1.3.0"
5
5
  end
@@ -2,29 +2,36 @@
2
2
 
3
3
  require "active_record_data_loader/version"
4
4
  require "active_record"
5
+ require "active_record_data_loader/errors"
5
6
  require "active_record_data_loader/configuration"
7
+ require "active_record_data_loader/connection_handler"
6
8
  require "active_record_data_loader/data_faker"
9
+ require "active_record_data_loader/active_record/list"
7
10
  require "active_record_data_loader/active_record/per_row_value_cache"
8
11
  require "active_record_data_loader/active_record/integer_value_generator"
9
12
  require "active_record_data_loader/active_record/text_value_generator"
10
13
  require "active_record_data_loader/active_record/enum_value_generator"
11
14
  require "active_record_data_loader/active_record/datetime_value_generator"
12
- require "active_record_data_loader/active_record/column_configuration"
13
- require "active_record_data_loader/active_record/belongs_to_configuration"
14
- require "active_record_data_loader/active_record/polymorphic_belongs_to_configuration"
15
+ require "active_record_data_loader/active_record/column_data_provider"
16
+ require "active_record_data_loader/active_record/belongs_to_data_provider"
17
+ require "active_record_data_loader/active_record/polymorphic_belongs_to_data_provider"
18
+ require "active_record_data_loader/active_record/unique_index_tracker"
15
19
  require "active_record_data_loader/active_record/model_data_generator"
16
20
  require "active_record_data_loader/dsl/belongs_to_association"
17
21
  require "active_record_data_loader/dsl/polymorphic_association"
18
22
  require "active_record_data_loader/dsl/model"
19
23
  require "active_record_data_loader/dsl/definition"
24
+ require "active_record_data_loader/file_output_adapter"
25
+ require "active_record_data_loader/null_output_adapter"
20
26
  require "active_record_data_loader/copy_strategy"
21
27
  require "active_record_data_loader/bulk_insert_strategy"
28
+ require "active_record_data_loader/table_loader"
22
29
  require "active_record_data_loader/loader"
23
30
 
24
31
  module ActiveRecordDataLoader
25
32
  def self.define(config = ActiveRecordDataLoader.configuration, &block)
26
- LoaderProxy.new(
27
- configuration,
33
+ ActiveRecordDataLoader::Loader.new(
34
+ config,
28
35
  ActiveRecordDataLoader::Dsl::Definition.new(config).tap { |l| l.instance_eval(&block) }
29
36
  )
30
37
  end
@@ -36,35 +43,4 @@ module ActiveRecordDataLoader
36
43
  def self.configuration
37
44
  @configuration ||= ActiveRecordDataLoader::Configuration.new
38
45
  end
39
-
40
- class LoaderProxy
41
- def initialize(configuration, definition)
42
- @configuration = configuration
43
- @definition = definition
44
- end
45
-
46
- def load_data
47
- ActiveRecordDataLoader::ActiveRecord::PerRowValueCache.clear
48
-
49
- definition.models.map do |m|
50
- generator = ActiveRecordDataLoader::ActiveRecord::ModelDataGenerator.new(
51
- model: m.klass,
52
- column_settings: m.columns,
53
- polymorphic_settings: m.polymorphic_associations,
54
- belongs_to_settings: m.belongs_to_associations
55
- )
56
-
57
- ActiveRecordDataLoader::Loader.load_data(
58
- data_generator: generator,
59
- batch_size: m.batch_size,
60
- total_rows: m.row_count,
61
- configuration: configuration
62
- )
63
- end
64
- end
65
-
66
- private
67
-
68
- attr_reader :definition, :configuration
69
- end
70
46
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: active_record_data_loader
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.1
4
+ version: 1.3.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Alejandro Beiderman
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2019-06-17 00:00:00.000000000 Z
11
+ date: 2021-12-10 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: activerecord
@@ -16,14 +16,14 @@ dependencies:
16
16
  requirements:
17
17
  - - ">="
18
18
  - !ruby/object:Gem::Version
19
- version: '4.0'
19
+ version: '5.0'
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
24
  - - ">="
25
25
  - !ruby/object:Gem::Version
26
- version: '4.0'
26
+ version: '5.0'
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: appraisal
29
29
  requirement: !ruby/object:Gem::Requirement
@@ -53,7 +53,7 @@ dependencies:
53
53
  - !ruby/object:Gem::Version
54
54
  version: '1.16'
55
55
  - !ruby/object:Gem::Dependency
56
- name: coveralls
56
+ name: mysql2
57
57
  requirement: !ruby/object:Gem::Requirement
58
58
  requirements:
59
59
  - - ">="
@@ -100,14 +100,14 @@ dependencies:
100
100
  requirements:
101
101
  - - "~>"
102
102
  - !ruby/object:Gem::Version
103
- version: '12.0'
103
+ version: '13.0'
104
104
  type: :development
105
105
  prerelease: false
106
106
  version_requirements: !ruby/object:Gem::Requirement
107
107
  requirements:
108
108
  - - "~>"
109
109
  - !ruby/object:Gem::Version
110
- version: '12.0'
110
+ version: '13.0'
111
111
  - !ruby/object:Gem::Dependency
112
112
  name: rspec
113
113
  requirement: !ruby/object:Gem::Requirement
@@ -150,6 +150,34 @@ dependencies:
150
150
  - - ">="
151
151
  - !ruby/object:Gem::Version
152
152
  version: '0'
153
+ - !ruby/object:Gem::Dependency
154
+ name: simplecov
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: simplecov-lcov
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'
153
181
  - !ruby/object:Gem::Dependency
154
182
  name: sqlite3
155
183
  requirement: !ruby/object:Gem::Requirement
@@ -180,17 +208,19 @@ dependencies:
180
208
  version: '0'
181
209
  description: A utility to bulk load test data for performance testing.
182
210
  email:
183
- - abeiderman@gmail.com
211
+ - active_record_data_loader@ossprojects.dev
184
212
  executables:
185
213
  - console
186
214
  - setup
187
215
  extensions: []
188
216
  extra_rdoc_files: []
189
217
  files:
218
+ - ".github/workflows/build.yml"
219
+ - ".github/workflows/codeql-analysis.yml"
220
+ - ".github/workflows/gem-push.yml"
190
221
  - ".gitignore"
191
222
  - ".rspec"
192
223
  - ".rubocop.yml"
193
- - ".travis.yml"
194
224
  - Appraisals
195
225
  - CHANGELOG.md
196
226
  - CODE_OF_CONDUCT.md
@@ -203,7 +233,7 @@ files:
203
233
  - bin/console
204
234
  - bin/setup
205
235
  - config/database.yml
206
- - config/database.yml.travis
236
+ - docker-compose.yml
207
237
  - gemfiles/.bundle/config
208
238
  - gemfiles/activerecord_5.gemfile
209
239
  - gemfiles/activerecord_6.gemfile
@@ -211,24 +241,31 @@ files:
211
241
  - gemfiles/ffaker.gemfile
212
242
  - gemfiles/rails.gemfile
213
243
  - lib/active_record_data_loader.rb
214
- - lib/active_record_data_loader/active_record/belongs_to_configuration.rb
215
- - lib/active_record_data_loader/active_record/column_configuration.rb
244
+ - lib/active_record_data_loader/active_record/belongs_to_data_provider.rb
245
+ - lib/active_record_data_loader/active_record/column_data_provider.rb
216
246
  - lib/active_record_data_loader/active_record/datetime_value_generator.rb
217
247
  - lib/active_record_data_loader/active_record/enum_value_generator.rb
218
248
  - lib/active_record_data_loader/active_record/integer_value_generator.rb
249
+ - lib/active_record_data_loader/active_record/list.rb
219
250
  - lib/active_record_data_loader/active_record/model_data_generator.rb
220
251
  - lib/active_record_data_loader/active_record/per_row_value_cache.rb
221
- - lib/active_record_data_loader/active_record/polymorphic_belongs_to_configuration.rb
252
+ - lib/active_record_data_loader/active_record/polymorphic_belongs_to_data_provider.rb
222
253
  - lib/active_record_data_loader/active_record/text_value_generator.rb
254
+ - lib/active_record_data_loader/active_record/unique_index_tracker.rb
223
255
  - lib/active_record_data_loader/bulk_insert_strategy.rb
224
256
  - lib/active_record_data_loader/configuration.rb
257
+ - lib/active_record_data_loader/connection_handler.rb
225
258
  - lib/active_record_data_loader/copy_strategy.rb
226
259
  - lib/active_record_data_loader/data_faker.rb
227
260
  - lib/active_record_data_loader/dsl/belongs_to_association.rb
228
261
  - lib/active_record_data_loader/dsl/definition.rb
229
262
  - lib/active_record_data_loader/dsl/model.rb
230
263
  - lib/active_record_data_loader/dsl/polymorphic_association.rb
264
+ - lib/active_record_data_loader/errors.rb
265
+ - lib/active_record_data_loader/file_output_adapter.rb
231
266
  - lib/active_record_data_loader/loader.rb
267
+ - lib/active_record_data_loader/null_output_adapter.rb
268
+ - lib/active_record_data_loader/table_loader.rb
232
269
  - lib/active_record_data_loader/version.rb
233
270
  - log/.keep
234
271
  homepage:
@@ -244,14 +281,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
244
281
  requirements:
245
282
  - - ">="
246
283
  - !ruby/object:Gem::Version
247
- version: 2.3.0
284
+ version: 2.5.0
248
285
  required_rubygems_version: !ruby/object:Gem::Requirement
249
286
  requirements:
250
287
  - - ">="
251
288
  - !ruby/object:Gem::Version
252
289
  version: '0'
253
290
  requirements: []
254
- rubygems_version: 3.0.3
291
+ rubygems_version: 3.0.3.1
255
292
  signing_key:
256
293
  specification_version: 4
257
294
  summary: A utility to bulk load test data for performance testing.
data/.travis.yml DELETED
@@ -1,23 +0,0 @@
1
- sudo: false
2
- language: ruby
3
- env:
4
- - COVERALLS_PARALLEL=true
5
- rvm:
6
- - 2.3.8
7
- - 2.4.6
8
- - 2.5.5
9
- - 2.6.3
10
- gemfile:
11
- - gemfiles/activerecord_5.gemfile
12
- - gemfiles/rails.gemfile
13
- - gemfiles/faker.gemfile
14
- - gemfiles/ffaker.gemfile
15
- services:
16
- - postgresql
17
- notifications:
18
- webhooks: https://coveralls.io/webhook
19
- before_install: "gem update --system && gem install bundler"
20
- before_script:
21
- - psql -c 'create database test;' -U postgres
22
- - cp config/database.yml.travis config/database.yml
23
- script: "bundle exec rake"
@@ -1,7 +0,0 @@
1
- postgres:
2
- adapter: "postgresql"
3
- database: "test"
4
-
5
- sqlite3:
6
- adapter: "sqlite3"
7
- database: ":memory:"