activerecord_hoarder 0.0.1

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 (44) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +14 -0
  3. data/.rspec +2 -0
  4. data/.travis.yml +5 -0
  5. data/Gemfile +18 -0
  6. data/LICENSE.txt +21 -0
  7. data/README.md +62 -0
  8. data/Rakefile +6 -0
  9. data/activerecord_hoarder.gemspec +27 -0
  10. data/bin/console +29 -0
  11. data/bin/setup +8 -0
  12. data/config/activerecord_hoarder.yml.template +6 -0
  13. data/config/dbspec.yml.template +2 -0
  14. data/config/dbspec_rspec.yml.template +2 -0
  15. data/example/example.rb +3 -0
  16. data/example/fixture.rb +6 -0
  17. data/example/schema.rb +8 -0
  18. data/lib/activerecord_hoarder/aws_s3_storage.rb +64 -0
  19. data/lib/activerecord_hoarder/batch.rb +26 -0
  20. data/lib/activerecord_hoarder/batch_archiver.rb +16 -0
  21. data/lib/activerecord_hoarder/core.rb +13 -0
  22. data/lib/activerecord_hoarder/record_collector.rb +67 -0
  23. data/lib/activerecord_hoarder/record_query.rb +85 -0
  24. data/lib/activerecord_hoarder/restore.rb +16 -0
  25. data/lib/activerecord_hoarder/serializer.rb +9 -0
  26. data/lib/activerecord_hoarder/storage.rb +27 -0
  27. data/lib/activerecord_hoarder/storage_error.rb +4 -0
  28. data/lib/activerecord_hoarder/storage_key.rb +18 -0
  29. data/lib/activerecord_hoarder/storages.rb +20 -0
  30. data/lib/activerecord_hoarder/version.rb +3 -0
  31. data/lib/activerecord_hoarder.rb +21 -0
  32. data/spec/activerecord_hoarder/aws_s3_storage_spec.rb +26 -0
  33. data/spec/activerecord_hoarder/batch_archiver_spec.rb +10 -0
  34. data/spec/activerecord_hoarder/core_spec.rb +13 -0
  35. data/spec/activerecord_hoarder/serializer_spec.rb +7 -0
  36. data/spec/activerecord_hoarder/storage_spec.rb +29 -0
  37. data/spec/activerecord_hoarder_spec.rb +168 -0
  38. data/spec/factories/examples.rb +40 -0
  39. data/spec/spec_helper.rb +15 -0
  40. data/spec/support/0_rspec_configuration.rb +14 -0
  41. data/spec/support/1_active_record_configuration.rb +1 -0
  42. data/spec/support/2_database_content.rb +14 -0
  43. data/spec/support/3_test_storage.rb +7 -0
  44. metadata +162 -0
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 476f76a46fae44bba761080f33f0c5073733de0e
4
+ data.tar.gz: 5040b1ce780046408e8ab065d18452e9ff6803b1
5
+ SHA512:
6
+ metadata.gz: 195f314b03bf2f5f0e2f82da4a9c409b03ca4896d39e1bb055a8d3090d956b5ad929a69e0c1ab9015f6c5726233318062f364e2c392ccc0b58fcf662f7740370
7
+ data.tar.gz: ebd4a813bb3de31d7e61f962b4ff1b5098f71857dda2d016782c91227d22725de4c31dc45c99579de60b5e2f7f374cbde7fb2c6556f6fd6e5adf4bdc7abca75d
data/.gitignore ADDED
@@ -0,0 +1,14 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /Gemfile.lock
4
+ /_yardoc/
5
+ /coverage/
6
+ /doc/
7
+ /pkg/
8
+ /spec/reports/
9
+ /tmp/
10
+
11
+ # rspec failure tracking
12
+ .rspec_status
13
+ config/*.yml
14
+ *.sqlite3
data/.rspec ADDED
@@ -0,0 +1,2 @@
1
+ --format documentation
2
+ --color
data/.travis.yml ADDED
@@ -0,0 +1,5 @@
1
+ sudo: false
2
+ language: ruby
3
+ rvm:
4
+ - 2.4.1
5
+ before_install: gem install bundler -v 1.15.4
data/Gemfile ADDED
@@ -0,0 +1,18 @@
1
+ source "https://rubygems.org"
2
+
3
+ repo_name = "gem_batch_archiving"
4
+ git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
5
+
6
+ gem 'aws-sdk-s3', '~> 1'
7
+
8
+ group :test do
9
+ gem 'factory_girl_rails'
10
+ gem 'sqlite3'
11
+ gem 'timecop'
12
+ end
13
+
14
+ group :development do
15
+ gem 'sqlite3'
16
+ end
17
+
18
+ gemspec
data/LICENSE.txt ADDED
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2017 ACCESS MARKETING & COMMUNICATION LLC
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in
13
+ all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21
+ THE SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,62 @@
1
+ # Activerecord Hoarder
2
+
3
+ hoard records
4
+
5
+ ## 1 Use
6
+
7
+ ### 1.1 make model a hoarder
8
+ ```
9
+ class ExampleModel < ActiveRecord::Base
10
+ acts_as_hoarder
11
+ end
12
+ ```
13
+
14
+ ### 1.2 hoarding records
15
+ from console:
16
+ ```
17
+ ExampleModel.hoard
18
+ ```
19
+ will create S3 entries with keys: `<bucket_sub_dir>/<table_name = example_models>/<year>/<month>/<year>-<month>-<day>.json` and json formatted content
20
+
21
+ ### 1.3 restoring records
22
+ from console:
23
+ ```
24
+ ExampleModel.restore_date(Date.new(<Y>,<m>,<d>))
25
+ ```
26
+
27
+ ## 2 Development
28
+
29
+ ### 2.0 initial setup
30
+
31
+ Make a clone. Make a branch. Install dependencies.
32
+
33
+ ### 2.1 playing around
34
+
35
+ #### Configure database
36
+
37
+ Create config file from template (`cp config/dbspec.yml.template config/dbspec.yml`). Change database from `postgresql` to `sqlite3` and database name from `activerecord_hoarder` to `<as_desired>.sqlite3`.
38
+
39
+ #### Configure archive
40
+
41
+ Create config file from template (`cp config/activerecord_hoarder.yml.template config/activerecord_hoarder.yml`). Add your S3 credentials `access_key_id` and `secret_access_key` for target bucket `bucket`. Change `region` if necessary. If you want, change `acl` and add `bucket_sub_dir`.
42
+
43
+ #### Hop into sandbox
44
+ ```
45
+ bundler exec bin/console
46
+ ```
47
+
48
+ #### bin/example
49
+ Convenience functionality
50
+ - `require_relative "bin/example/schema"` for creating an example table `examples`
51
+ - `require_relative "bin/example/example"` for an example archivable model `Example`
52
+ - `require_relative "bin/example/fixture"` for a factory method `create_examples(count, start: 0, deleted: true)` for creating examples
53
+
54
+ ### 2.2 testing it
55
+
56
+ #### Configure test database
57
+ Create config file from template (`cp config/dbspec_rspec.yml.template config/dbspec_rspec.yml`). Modify settings if you want.
58
+
59
+ #### Run tests
60
+ ```
61
+ bundler exec rspec spec
62
+ ```
data/Rakefile ADDED
@@ -0,0 +1,6 @@
1
+ require "bundler/gem_tasks"
2
+ require "rspec/core/rake_task"
3
+
4
+ RSpec::Core::RakeTask.new(:spec)
5
+
6
+ task :default => :spec
@@ -0,0 +1,27 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path("../lib", __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require "activerecord_hoarder/version"
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = "activerecord_hoarder"
8
+ spec.version = ActiverecordHoarder::VERSION
9
+ spec.authors = ["Matthias Engh"]
10
+ spec.email = ["matthias@wescrimmage.com"]
11
+
12
+ spec.summary = %q{hoards records}
13
+ spec.description = %q{extend active records with simple archiving mechanics}
14
+ spec.homepage = "https://github.com/Scrimmage/gem_batch_archiving"
15
+ spec.license = "MIT"
16
+
17
+ spec.files = `git ls-files -z`.split("\x0")
18
+ spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
19
+ spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
20
+ spec.require_paths = ["lib"]
21
+
22
+ spec.add_dependency "activerecord", [">= 4.2", "< 6.0"]
23
+
24
+ spec.add_development_dependency "bundler", "~> 1.15"
25
+ spec.add_development_dependency "rake", "~> 10.0"
26
+ spec.add_development_dependency "rspec", "~> 3.0"
27
+ end
data/bin/console ADDED
@@ -0,0 +1,29 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "bundler/setup"
4
+
5
+ # require dependencies from gemspec
6
+ require "active_record"
7
+ require "aws-sdk-s3"
8
+ require "pp"
9
+ require "yaml"
10
+
11
+ dbspec_location = "config/dbspec.yml"
12
+
13
+ if File.exist?(dbspec_location)
14
+ dbspec = YAML.load_file(dbspec_location)
15
+ ActiveRecord::Base.establish_connection(dbspec)
16
+ ActiveRecord::Base.connection
17
+ else
18
+ raise "database configuration file #{dbspec_location} not found"
19
+ end
20
+
21
+ require "activerecord_hoarder"
22
+
23
+ storage_config_path = "config/activerecord_hoarder.yml"
24
+ raise "storage configuration file #{storage_config_path}` not found" if !File.exists?(storage_config_path)
25
+ storage_options = YAML.load_file(storage_config_path)
26
+ ::ActiverecordHoarder::Storage.configure(storage: :aws_s3, storage_options: storage_options)
27
+
28
+ require "irb"
29
+ IRB.start(__FILE__)
data/bin/setup ADDED
@@ -0,0 +1,8 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+ set -vx
5
+
6
+ bundle install
7
+
8
+ # Do any other automated setup that you need to do here
@@ -0,0 +1,6 @@
1
+ access_key_id:
2
+ acl: private
3
+ bucket:
4
+ bucket_sub_dir:
5
+ region: us-east-1
6
+ secret_access_key:
@@ -0,0 +1,2 @@
1
+ adapter: postgresql
2
+ database: activerecord_hoarder
@@ -0,0 +1,2 @@
1
+ adapter: sqlite3
2
+ database: activerecord_hoarder_rspec
@@ -0,0 +1,3 @@
1
+ class Example < ActiveRecord::Base
2
+ acts_as_hoarder
3
+ end
@@ -0,0 +1,6 @@
1
+ def create_examples(count, start: 0, deleted: true)
2
+ (1..count).each do |n|
3
+ Example.create(content: "example: #{n}", created_at: (n+start).hours.ago, deleted_at: Time.now)
4
+ end
5
+ nil
6
+ end
data/example/schema.rb ADDED
@@ -0,0 +1,8 @@
1
+ ActiveRecord::Schema.define do
2
+ create_table "examples", force: true do |t|
3
+ t.datetime "created_at"
4
+ t.datetime "updated_at"
5
+ t.datetime "deleted_at"
6
+ t.string "content"
7
+ end
8
+ end
@@ -0,0 +1,64 @@
1
+ module ActiverecordHoarder
2
+ class AwsS3
3
+ DEFAULT_ACL = "private"
4
+ OPTION_CONTENT_ACCESS = "acl"
5
+ OPTION_SUB_DIR = "bucket_sub_dir"
6
+ OPTION_BUCKET = "bucket"
7
+ OPTION_ACCESS_KEY_ID = "access_key_id"
8
+ OPTIONS_SECRET_ACCESS_KEY = "secret_access_key"
9
+ OPTION_REGION = "region"
10
+
11
+ attr_reader :storage_options
12
+
13
+ def initialize(table_name, storage_options)
14
+ @storage_options = storage_options
15
+
16
+ if storage_options[OPTION_SUB_DIR].blank?
17
+ @key_prefix = table_name
18
+ else
19
+ @key_prefix = File.join(storage_options[OPTION_SUB_DIR], table_name)
20
+ end
21
+ end
22
+
23
+ def fetch_data(key)
24
+ full_key = key_with_prefix(key)
25
+ begin
26
+ response = s3_client.get_object(bucket: s3_bucket, key: full_key)
27
+ rescue Aws::S3::Errors::NoSuchKey => e
28
+ raise ::ActiverecordHoarder::StorageError.new("fetch_data erred with '#{e.class}':'#{e.message}'' trying to access '#{full_key}'' in bucket: '#{s3_bucket}'")
29
+ end
30
+ response.body
31
+ end
32
+
33
+ def store_data(batch)
34
+ full_key = key_with_prefix(batch.key.to_s)
35
+
36
+ s3_client.put_object(bucket: s3_bucket, body: batch.content_string, key: full_key, acl: s3_acl)
37
+ true
38
+ end
39
+
40
+ private
41
+
42
+ def key_with_prefix(key)
43
+ File.join(@key_prefix, key.to_s)
44
+ end
45
+
46
+ def s3_acl
47
+ storage_options[OPTION_CONTENT_ACCESS] || DEFAULT_ACL
48
+ end
49
+
50
+ def s3_bucket
51
+ storage_options[OPTION_BUCKET]
52
+ end
53
+
54
+ def s3_client
55
+ @s3_client ||= begin
56
+ access_key_id = storage_options[OPTION_ACCESS_KEY_ID] or raise StorageError.new("access_key_id missing")
57
+ secret_access_key = storage_options[OPTIONS_SECRET_ACCESS_KEY] or raise StorageError.new("secret_access_key missing")
58
+ credentials = Aws::Credentials.new(access_key_id, secret_access_key)
59
+ region = storage_options[OPTION_REGION] or raise StorageError.new("region missing")
60
+ Aws::S3::Client.new(credentials: credentials, region: region)
61
+ end
62
+ end
63
+ end
64
+ end
@@ -0,0 +1,26 @@
1
+ module ::ActiverecordHoarder
2
+ class Batch
3
+ RECORD_DATE_FIELD = "created_at"
4
+
5
+ def self.from_records(record_data)
6
+ record_data.present? ? new(record_data) : nil
7
+ end
8
+
9
+ def initialize(record_data)
10
+ @record_data = record_data
11
+ @serializer = ::ActiverecordHoarder::Serializer
12
+ end
13
+
14
+ def date
15
+ @date ||= @record_data.first[RECORD_DATE_FIELD].to_date
16
+ end
17
+
18
+ def key
19
+ @key ||= ::ActiverecordHoarder::StorageKey.from_date(date, @serializer.extension)
20
+ end
21
+
22
+ def content_string
23
+ @serializer.create_archive(@record_data)
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,16 @@
1
+ class ::ActiverecordHoarder::BatchArchiver
2
+ def initialize(model_class, storage = nil)
3
+ @record_collector = ::ActiverecordHoarder::RecordCollector.new(model_class)
4
+ @archive_storage = storage || default_storage_for_records(model_class.table_name)
5
+ end
6
+
7
+ def archive_batch
8
+ @record_collector.in_batches(delete_on_success: true) do |batch|
9
+ @archive_storage.store_data(batch)
10
+ end
11
+ end
12
+
13
+ def default_storage_for_records(table_name)
14
+ ::ActiverecordHoarder::Storage.new(table_name)
15
+ end
16
+ end
@@ -0,0 +1,13 @@
1
+ module ActiverecordHoarder::Core
2
+ def self.included(base)
3
+ raise 'created_at accessor needed' if !base.column_names.include?("created_at")
4
+ raise 'deleted_at accessor needed' if !base.column_names.include?("deleted_at")
5
+ base.extend ClassMethods
6
+ end
7
+
8
+ module ClassMethods
9
+ def hoard
10
+ ::ActiverecordHoarder::BatchArchiver.new(self).archive_batch
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,67 @@
1
+ class ::ActiverecordHoarder::RecordCollector
2
+ attr_reader :relative_limit
3
+
4
+ def initialize(model_class)
5
+ @model_class = model_class
6
+ end
7
+
8
+ def in_batches(delete_on_success: false)
9
+ while collect_batch
10
+ success = yield @batch
11
+ return if !success
12
+ next if !delete_on_success
13
+ destroy_current_records!
14
+ end
15
+ end
16
+
17
+ private
18
+
19
+ def collect_batch
20
+ activate_limit if batch_data_cached? && !limit_toggled?
21
+ if limit_toggled?
22
+ @batch = ensuring_new_records do
23
+ retrieve_next_batch
24
+ end
25
+ else
26
+ @batch = retrieve_first_batch
27
+ end
28
+ batch_data_cached?
29
+ end
30
+
31
+ def activate_limit
32
+ @relative_limit = [@batch.date.end_of_week + 1, archive_timeframe_upper_limit].min
33
+ end
34
+
35
+ def archive_timeframe_upper_limit
36
+ Time.now.getutc.beginning_of_day
37
+ end
38
+
39
+ def batch_data_cached?
40
+ @batch.present?
41
+ end
42
+
43
+ def destroy_current_records!
44
+ @model_class.connection.execute(@batch_query.delete(@batch.date))
45
+ end
46
+
47
+ def ensuring_new_records
48
+ record_batch = yield
49
+ @batch.date == record_batch.try(:date) ? nil : record_batch
50
+ end
51
+
52
+ def limit_toggled?
53
+ @relative_limit.present?
54
+ end
55
+
56
+ def retrieve_first_batch
57
+ @batch_query = ::ActiverecordHoarder::BatchQuery.new(archive_timeframe_upper_limit, @model_class)
58
+ batch_data = @model_class.connection.exec_query(@batch_query.fetch)
59
+ ::ActiverecordHoarder::Batch.from_records(batch_data)
60
+ end
61
+
62
+ def retrieve_next_batch
63
+ @batch_query = ::ActiverecordHoarder::BatchQuery.new(relative_limit, @model_class)
64
+ batch_data = @model_class.connection.exec_query(@batch_query.fetch)
65
+ ::ActiverecordHoarder::Batch.from_records(batch_data)
66
+ end
67
+ end
@@ -0,0 +1,85 @@
1
+ module ActiverecordHoarder
2
+ class BatchQuery
3
+ SUBQUERY_DELETED_RECORDS = <<~SQL.strip_heredoc
4
+ SELECT
5
+ %{fields}
6
+ FROM
7
+ %{table_name}
8
+ WHERE
9
+ deleted_at IS NOT NULL
10
+ SQL
11
+
12
+ SUBQUERY_NON_DELETED_RECORDS = <<~SQL.strip_heredoc
13
+ SELECT
14
+ %{fields}
15
+ FROM
16
+ %{table_name}
17
+ WHERE
18
+ deleted_at IS NULL
19
+ SQL
20
+
21
+ QUERY_TEMPLATE_FOR_DATE_DELETION = <<~SQL.strip_heredoc
22
+ DELETE FROM %{table_name} WHERE date(created_at) = '%{date}';
23
+ SQL
24
+
25
+ QUERY_TEMPLATE_FOR_RECORD_WITH_LIMIT = <<~SQL.strip_heredoc
26
+ SELECT
27
+ %{fields}
28
+ FROM
29
+ %{table_name}
30
+ WHERE
31
+ date(created_at) = (
32
+ SELECT
33
+ min(dates_with_deleted.creation_date)
34
+ FROM
35
+ (
36
+ #{SUBQUERY_DELETED_RECORDS % {
37
+ fields: "date(created_at) as creation_date",
38
+ table_name: "%{table_name}"
39
+ }}
40
+ ) as dates_with_deleted
41
+ LEFT OUTER JOIN
42
+ (
43
+ #{SUBQUERY_NON_DELETED_RECORDS % {
44
+ fields: "date(created_at) as creation_date",
45
+ table_name: "%{table_name}"
46
+ }}
47
+ ) as dates_with_non_deleted
48
+ ON
49
+ dates_with_deleted.creation_date = dates_with_non_deleted.creation_date
50
+ WHERE
51
+ dates_with_non_deleted.creation_date IS NULL
52
+ AND
53
+ created_at < '%{limit}'
54
+ )
55
+ ;
56
+ SQL
57
+
58
+ def initialize(limit, model_class)
59
+ @limit = limit
60
+ @model_class = model_class
61
+ end
62
+
63
+ def delete(date)
64
+ QUERY_TEMPLATE_FOR_DATE_DELETION % {
65
+ fields: @model_class.column_names.join(", "),
66
+ date: date,
67
+ table_name: table_name
68
+ }
69
+ end
70
+
71
+ def fetch
72
+ QUERY_TEMPLATE_FOR_RECORD_WITH_LIMIT % {
73
+ fields: @model_class.column_names.join(", "),
74
+ limit: @limit,
75
+ table_name: table_name
76
+ }
77
+ end
78
+
79
+ private
80
+
81
+ def table_name
82
+ @model_class.table_name
83
+ end
84
+ end
85
+ end
@@ -0,0 +1,16 @@
1
+ module ActiverecordHoarder
2
+ module Restore
3
+ def self.included(base)
4
+ base.extend(ClassMethods)
5
+ end
6
+
7
+ module ClassMethods
8
+ def restore_archive_records(date)
9
+ storage = ::ActiverecordHoarder::Storage.new(self.table_name)
10
+ key = ::ActiverecordHoarder::StorageKey.from_date(date, :json)
11
+ dataIO = storage.fetch_data(key)
12
+ create(JSON.parse(dataIO.read))
13
+ end
14
+ end
15
+ end
16
+ end
@@ -0,0 +1,9 @@
1
+ class ::ActiverecordHoarder::Serializer
2
+ def self.create_archive(batch_data)
3
+ batch_data.to_json
4
+ end
5
+
6
+ def self.extension
7
+ :json
8
+ end
9
+ end
@@ -0,0 +1,27 @@
1
+ class ::ActiverecordHoarder::Storage
2
+ class_attribute :storage, :storage_options
3
+
4
+ def self.configure(storage:, storage_options:)
5
+ ::ActiverecordHoarder::Storages.is_valid_storage?(storage)
6
+
7
+ self.storage_options = storage_options
8
+ self.storage = storage
9
+ self
10
+ end
11
+
12
+ private
13
+
14
+ def self.new(table_name, storage_override: nil, storage_options_override: {})
15
+ self.check_configured
16
+ storage_class = ::ActiverecordHoarder::Storages.retrieve(storage_override || storage)
17
+ storage_class.new(table_name, storage_options.merge(storage_options_override))
18
+ end
19
+
20
+ def self.check_configured
21
+ raise ::ActiverecordHoarder::StorageError.new("storage needs to be configured") unless is_configured?
22
+ end
23
+
24
+ def self.is_configured?
25
+ storage.present? && storage_options.is_a?(Hash)
26
+ end
27
+ end
@@ -0,0 +1,4 @@
1
+ module ::ActiverecordHoarder
2
+ class StorageError < StandardError
3
+ end
4
+ end
@@ -0,0 +1,18 @@
1
+ module ActiverecordHoarder
2
+ class StorageKey
3
+ def self.from_date(date, file_extension = nil)
4
+ key_parts = [date.year.to_s, date.month.to_s, date.iso8601]
5
+ new(key_parts, file_extension)
6
+ end
7
+
8
+ def initialize(key_parts, file_extension)
9
+ @key_parts = key_parts
10
+ @file_extension = file_extension
11
+ end
12
+
13
+ def to_s
14
+ key_without_extension = File.join(@key_parts)
15
+ @file_extension.present? ? key_without_extension + '.' + @file_extension.to_s : key_without_extension
16
+ end
17
+ end
18
+ end
@@ -0,0 +1,20 @@
1
+ module ::ActiverecordHoarder
2
+ class Storages
3
+ STORAGE_DICT = {
4
+ aws_s3: ::ActiverecordHoarder::AwsS3
5
+ }
6
+
7
+ def self.check_storage(storage_key)
8
+ raise ::ActiverecordHoarder::StorageError.new("unknown storage (#{storage_key}), known keys are #{STORAGE_DICT.keys}") if !is_valid_storage?(storage_key)
9
+ end
10
+
11
+ def self.is_valid_storage?(storage_key)
12
+ STORAGE_DICT.keys.include?(storage_key)
13
+ end
14
+
15
+ def self.retrieve(storage_key)
16
+ check_storage(storage_key)
17
+ STORAGE_DICT[storage_key]
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,3 @@
1
+ module ActiverecordHoarder
2
+ VERSION = "0.0.1"
3
+ end
@@ -0,0 +1,21 @@
1
+ require 'activerecord_hoarder/aws_s3_storage'
2
+ require 'activerecord_hoarder/batch'
3
+ require 'activerecord_hoarder/batch_archiver'
4
+ require 'activerecord_hoarder/core'
5
+ require 'activerecord_hoarder/record_collector'
6
+ require 'activerecord_hoarder/record_query'
7
+ require 'activerecord_hoarder/restore'
8
+ require 'activerecord_hoarder/serializer'
9
+ require 'activerecord_hoarder/storage'
10
+ require 'activerecord_hoarder/storage_error'
11
+ require 'activerecord_hoarder/storage_key'
12
+ require 'activerecord_hoarder/storages'
13
+
14
+ module ActiverecordHoarder
15
+ def acts_as_hoarder
16
+ include ActiverecordHoarder::Core
17
+ include ActiverecordHoarder::Restore
18
+ end
19
+ end
20
+
21
+ ::ActiveRecord::Base.send :extend, ActiverecordHoarder
@@ -0,0 +1,26 @@
1
+ require 'spec_helper'
2
+
3
+ DATA_TEMPLATE = "data for key %{key}"
4
+
5
+ RSpec.describe ::ActiverecordHoarder::AwsS3 do
6
+ describe ".fetch_data" do
7
+ let(:date_data) { DATA_TEMPLATE % { key: full_key } }
8
+ let(:full_key) { File.join(table_name, key_string) }
9
+ let(:key) { double(key_string, to_s: key_string) }
10
+ let(:key_string) { "key" }
11
+ let(:storage) { ::ActiverecordHoarder::AwsS3.new(table_name, storage_options) }
12
+ let(:storage_options) { {} }
13
+ let(:table_name) { "records" }
14
+
15
+ before do
16
+ allow(storage).to receive(:s3_client).and_return(Aws::S3::Client.new(stub_responses: true))
17
+ allow_any_instance_of(Aws::S3::Client).to receive(:get_object) do |object, args|
18
+ double(body: DATA_TEMPLATE % { key: args[:key] })
19
+ end
20
+ end
21
+
22
+ it "returns the archive entry for given date" do
23
+ expect(storage.fetch_data(key)).to eq(date_data)
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,10 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe ::ActiverecordHoarder::BatchArchiver do
4
+ let(:model_class) { double("Record", table_name: "records") }
5
+
6
+ it "creates instance that can archive_batch" do
7
+ allow(::ActiverecordHoarder::Storage).to receive(:new).and_return(double)
8
+ expect(described_class.new(model_class)).to respond_to(:archive_batch)
9
+ end
10
+ end
@@ -0,0 +1,13 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe 'ActiverecordHoarder::Core' do
4
+ context 'included and instantiated' do
5
+ describe 'hoard' do
6
+ it "it works, no questions asked" do
7
+ expect(::ActiverecordHoarder::Storage).to receive(:new).and_return(double)
8
+ expect_any_instance_of(::ActiverecordHoarder::BatchArchiver).to receive(:archive_batch)
9
+ expect{ ExampleHoarder.hoard }.not_to raise_error
10
+ end
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,7 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe ::ActiverecordHoarder::Serializer do
4
+ it "has class method for serialization" do
5
+ expect(described_class).to respond_to(:create_archive)
6
+ end
7
+ end
@@ -0,0 +1,29 @@
1
+ require 'spec_helper'
2
+
3
+ RSpec.describe ::ActiverecordHoarder::Storage do
4
+ let(:stub_model) { double }
5
+
6
+ before do
7
+ allow(stub_model).to receive(:table_name)
8
+ end
9
+
10
+ describe "new" do
11
+ let(:storage) { ::ActiverecordHoarder::Storage.new(stub_model) }
12
+
13
+ context "not configured" do
14
+ it "fails and complains about configuration" do
15
+ expect{ ::ActiverecordHoarder::Storage.new(stub_model) }.to raise_error(::ActiverecordHoarder::StorageError)
16
+ end
17
+ end
18
+
19
+ context "aws_s3" do
20
+ before do
21
+ ::ActiverecordHoarder::Storage.configure(storage: :aws_s3, storage_options: {})
22
+ end
23
+
24
+ it "returns an aws storage" do
25
+ expect(storage.class).to be(::ActiverecordHoarder::AwsS3)
26
+ end
27
+ end
28
+ end
29
+ end
@@ -0,0 +1,168 @@
1
+ require "spec_helper"
2
+
3
+ RSpec.describe ActiverecordHoarder do
4
+
5
+ around(:all) do |example|
6
+ current_zone = Time.zone
7
+ Time.zone = "America/Chicago"
8
+ Timecop.freeze((Date.today.beginning_of_week - 3).to_time(:utc).end_of_day) do
9
+ example.run
10
+ end
11
+ Time.zone = current_zone
12
+ end
13
+
14
+ it "has a version number" do
15
+ expect(ActiverecordHoarder::VERSION).not_to be nil
16
+ end
17
+
18
+ it "extends ::ActiveRecord::Base with acts_as_hoarder" do
19
+ expect(::ActiveRecord::Base.methods).to include(:acts_as_hoarder)
20
+ end
21
+
22
+ describe "acts_as_hoarder" do
23
+ context "successfully included in ActiveRecord model" do
24
+ it "extends with public class method .hoard" do
25
+ expect(ExampleHoarder.methods).to include(:hoard)
26
+ end
27
+ end
28
+ end
29
+
30
+ describe "record archiving" do
31
+ let(:archive_data) {
32
+ @archivable_records.group_by { |item|
33
+ item.created_at.getutc.to_date
34
+ } .collect { |date, group|
35
+ JSON.pretty_generate(group.collect(&:serializable_hash))
36
+ }
37
+ }
38
+ let(:storage) { double }
39
+
40
+ before :each do
41
+ allow(::ActiverecordHoarder::Storage).to receive(:new).and_return(storage)
42
+ allow(storage).to receive(:store_data).and_return(true)
43
+ end
44
+
45
+ context "with records only in current week" do
46
+ before do
47
+ @archivable_records = create_list(
48
+ :examples_in_range,
49
+ 20,
50
+ deleted: true,
51
+ start_time: Time.now.getutc.beginning_of_week,
52
+ end_time: (Date.today - 1).to_time(:utc).end_of_day
53
+ )
54
+ @non_archivable_records = create_list(
55
+ :examples_on_date,
56
+ 4,
57
+ deleted: true,
58
+ records_date: Date.today
59
+ )
60
+ ExampleHoarder.hoard
61
+ end
62
+
63
+ it "ignores current day" do
64
+ expect(ExampleHoarder.unscoped.to_a).to include(*@non_archivable_records)
65
+ end
66
+
67
+ it "archives previous days" do
68
+ expect(ExampleHoarder.unscoped.to_a).not_to include(*@archivable_records)
69
+ end
70
+ end
71
+
72
+ context "with records in multiple weeks, non-deleted records mixed in and trailing" do
73
+ before do
74
+ @archivable_records = create_list(
75
+ :examples_in_range,
76
+ 20,
77
+ deleted: true,
78
+ end_time: (1.week.ago.getutc.beginning_of_week + 2.days).end_of_day,
79
+ start_time: 1.week.ago.getutc.beginning_of_week
80
+ ) + create_list(
81
+ :examples_in_range,
82
+ 20,
83
+ deleted: true,
84
+ end_time: 1.week.ago.getutc.end_of_week,
85
+ start_time: 1.week.ago.getutc.beginning_of_week + 4.days
86
+ )
87
+ @non_archivable_records = create_list(
88
+ :examples_on_date,
89
+ 2,
90
+ deleted: true,
91
+ records_date: (1.week.ago.getutc.beginning_of_week - 1.day).to_date
92
+ ) + create_list(
93
+ :examples_on_date,
94
+ 1,
95
+ deleted: false,
96
+ records_date: (1.week.ago.getutc.beginning_of_week - 1.day).to_date
97
+ ) + create_list(
98
+ :examples_on_date,
99
+ 4,
100
+ deleted: true,
101
+ records_date: (1.week.ago.getutc.beginning_of_week + 3.days).to_date,
102
+ ) + create_list(
103
+ :examples_on_date,
104
+ 2,
105
+ deleted: false,
106
+ records_date: (1.week.ago.getutc.beginning_of_week + 3.days).to_date
107
+ )
108
+ @out_of_range_records = create_list(
109
+ :examples_in_range,
110
+ 2,
111
+ deleted: true,
112
+ end_time: Time.now,
113
+ start_time: Time.now.getutc.beginning_of_week
114
+ ) + create_list(
115
+ :examples_in_range,
116
+ 2,
117
+ deleted: false,
118
+ end_time: Time.now,
119
+ start_time: Time.now.getutc.beginning_of_week
120
+ )
121
+ ExampleHoarder.hoard
122
+ end
123
+
124
+ it "skips records from days with active records" do
125
+ expect(ExampleHoarder.unscoped.to_a).to include(*@non_archivable_records)
126
+ end
127
+
128
+ it "archives one week of fully deleted records" do
129
+ expect(ExampleHoarder.unscoped.to_a).not_to include(*@archivable_records)
130
+ end
131
+
132
+ it "stops after one week" do
133
+ expect(ExampleHoarder.unscoped.to_a).to include(*@out_of_range_records)
134
+ end
135
+ end
136
+ end
137
+
138
+ describe "workflow" do
139
+ let(:batch1) { double }
140
+ let(:collector) { ::ActiverecordHoarder::RecordCollector.new(ExampleHoarder) }
141
+ let(:storage) { double }
142
+
143
+ before do
144
+ allow(::ActiverecordHoarder::Storage).to receive(:new).and_return(storage)
145
+ allow(::ActiverecordHoarder::RecordCollector).to receive(:new).and_return(collector)
146
+ allow(collector).to receive(:collect_batch).and_return(true, false)
147
+ allow(collector).to receive(:batch_data_cached?).and_return(true)
148
+ allow_any_instance_of(::ActiverecordHoarder::BatchArchiver).to receive(:compose_key).and_return("key")
149
+ allow(collector).to receive(:destroy_current_records!)
150
+ end
151
+
152
+ after do
153
+ ExampleHoarder.hoard
154
+ end
155
+
156
+ it "fully processes one record batch before moving on to the next" do
157
+ expect(collector).to receive(:collect_batch)
158
+ expect(storage).to receive(:store_data).and_return(true)
159
+ expect(collector).to receive(:destroy_current_records!)
160
+ expect(collector).to receive(:collect_batch)
161
+ end
162
+
163
+ it "does not delete a record that wasn't successfully archived" do
164
+ expect(storage).to receive(:store_data).and_return(false)
165
+ expect(collector).not_to receive(:destroy_current_records!)
166
+ end
167
+ end
168
+ end
@@ -0,0 +1,40 @@
1
+ def datetimes_in_range(n, step: 5, start:, stop:)
2
+ seconds_in_range = stop - start
3
+ seconds_ago = Time.now.getutc - stop
4
+ ((n*(step.hours+1.minute + 1.second)) % seconds_in_range + seconds_ago).seconds.ago
5
+ end
6
+
7
+ FactoryGirl.define do
8
+ factory :example_hoarder do
9
+ transient do
10
+ deleted false
11
+ end
12
+
13
+ after :build do |record, evaluator|
14
+ if evaluator.deleted
15
+ record.deleted_at = record.created_at
16
+ end
17
+ end
18
+ end
19
+
20
+ factory :examples_in_range, parent: :example_hoarder do
21
+ transient do
22
+ end_time Time.now
23
+ start_time 2.weeks.ago
24
+ step 5
25
+ end
26
+
27
+ sequence(:created_at, 0) { |n| datetimes_in_range(n, step: step, start: start_time, stop: end_time) }
28
+ end
29
+
30
+ factory :examples_on_date, parent: :example_hoarder do
31
+ transient do
32
+ records_date Date.today - 1
33
+ step 5
34
+ end
35
+
36
+ sequence(:created_at, 0) { |n|
37
+ created_at_value = datetimes_in_range(n, step: step, start: records_date.to_time(:utc), stop: records_date.to_time(:utc).end_of_day)
38
+ }
39
+ end
40
+ end
@@ -0,0 +1,15 @@
1
+ require "bundler/setup"
2
+ require "active_record"
3
+ require "aws-sdk-s3"
4
+
5
+ require "activerecord_hoarder"
6
+
7
+ require "factory_girl_rails"
8
+ require "pp"
9
+ require "timecop"
10
+
11
+ Dir.glob("spec/support/*.rb").each do |file| require File.expand_path(file) end
12
+
13
+ class ExampleHoarder < ActiveRecord::Base
14
+ acts_as_hoarder
15
+ end
@@ -0,0 +1,14 @@
1
+ RSpec.configure do |config|
2
+ # Enable flags like --only-failures and --next-failure
3
+ config.example_status_persistence_file_path = ".rspec_status"
4
+
5
+ # Disable RSpec exposing methods globally on `Module` and `main`
6
+ config.disable_monkey_patching!
7
+
8
+ config.expect_with :rspec do |c|
9
+ c.syntax = :expect
10
+ end
11
+
12
+ config.include FactoryGirl::Syntax::Methods
13
+ FactoryGirl.find_definitions
14
+ end
@@ -0,0 +1 @@
1
+ ActiveRecord::Base.establish_connection(YAML.load_file("config/dbspec_rspec.yml"))
@@ -0,0 +1,14 @@
1
+ ActiveRecord::Schema.define do
2
+ create_table "example_hoarders", force: true do |t|
3
+ t.datetime "created_at"
4
+ t.datetime "deleted_at"
5
+ t.datetime "updated_at"
6
+ t.string "content"
7
+ end
8
+ end
9
+
10
+ RSpec.configure do |config|
11
+ config.after(:each) do
12
+ ActiveRecord::Base.connection.execute("DELETE FROM example_hoarders;")
13
+ end
14
+ end
@@ -0,0 +1,7 @@
1
+
2
+ RSpec.configure do |config|
3
+ config.after(:each) do
4
+ ActiverecordHoarder.send(:remove_const, 'Storage')
5
+ load 'lib/activerecord_hoarder/storage.rb'
6
+ end
7
+ end
metadata ADDED
@@ -0,0 +1,162 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: activerecord_hoarder
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Matthias Engh
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2017-11-15 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: activerecord
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: '4.2'
20
+ - - "<"
21
+ - !ruby/object:Gem::Version
22
+ version: '6.0'
23
+ type: :runtime
24
+ prerelease: false
25
+ version_requirements: !ruby/object:Gem::Requirement
26
+ requirements:
27
+ - - ">="
28
+ - !ruby/object:Gem::Version
29
+ version: '4.2'
30
+ - - "<"
31
+ - !ruby/object:Gem::Version
32
+ version: '6.0'
33
+ - !ruby/object:Gem::Dependency
34
+ name: bundler
35
+ requirement: !ruby/object:Gem::Requirement
36
+ requirements:
37
+ - - "~>"
38
+ - !ruby/object:Gem::Version
39
+ version: '1.15'
40
+ type: :development
41
+ prerelease: false
42
+ version_requirements: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - "~>"
45
+ - !ruby/object:Gem::Version
46
+ version: '1.15'
47
+ - !ruby/object:Gem::Dependency
48
+ name: rake
49
+ requirement: !ruby/object:Gem::Requirement
50
+ requirements:
51
+ - - "~>"
52
+ - !ruby/object:Gem::Version
53
+ version: '10.0'
54
+ type: :development
55
+ prerelease: false
56
+ version_requirements: !ruby/object:Gem::Requirement
57
+ requirements:
58
+ - - "~>"
59
+ - !ruby/object:Gem::Version
60
+ version: '10.0'
61
+ - !ruby/object:Gem::Dependency
62
+ name: rspec
63
+ requirement: !ruby/object:Gem::Requirement
64
+ requirements:
65
+ - - "~>"
66
+ - !ruby/object:Gem::Version
67
+ version: '3.0'
68
+ type: :development
69
+ prerelease: false
70
+ version_requirements: !ruby/object:Gem::Requirement
71
+ requirements:
72
+ - - "~>"
73
+ - !ruby/object:Gem::Version
74
+ version: '3.0'
75
+ description: extend active records with simple archiving mechanics
76
+ email:
77
+ - matthias@wescrimmage.com
78
+ executables:
79
+ - console
80
+ - setup
81
+ extensions: []
82
+ extra_rdoc_files: []
83
+ files:
84
+ - ".gitignore"
85
+ - ".rspec"
86
+ - ".travis.yml"
87
+ - Gemfile
88
+ - LICENSE.txt
89
+ - README.md
90
+ - Rakefile
91
+ - activerecord_hoarder.gemspec
92
+ - bin/console
93
+ - bin/setup
94
+ - config/activerecord_hoarder.yml.template
95
+ - config/dbspec.yml.template
96
+ - config/dbspec_rspec.yml.template
97
+ - example/example.rb
98
+ - example/fixture.rb
99
+ - example/schema.rb
100
+ - lib/activerecord_hoarder.rb
101
+ - lib/activerecord_hoarder/aws_s3_storage.rb
102
+ - lib/activerecord_hoarder/batch.rb
103
+ - lib/activerecord_hoarder/batch_archiver.rb
104
+ - lib/activerecord_hoarder/core.rb
105
+ - lib/activerecord_hoarder/record_collector.rb
106
+ - lib/activerecord_hoarder/record_query.rb
107
+ - lib/activerecord_hoarder/restore.rb
108
+ - lib/activerecord_hoarder/serializer.rb
109
+ - lib/activerecord_hoarder/storage.rb
110
+ - lib/activerecord_hoarder/storage_error.rb
111
+ - lib/activerecord_hoarder/storage_key.rb
112
+ - lib/activerecord_hoarder/storages.rb
113
+ - lib/activerecord_hoarder/version.rb
114
+ - spec/activerecord_hoarder/aws_s3_storage_spec.rb
115
+ - spec/activerecord_hoarder/batch_archiver_spec.rb
116
+ - spec/activerecord_hoarder/core_spec.rb
117
+ - spec/activerecord_hoarder/serializer_spec.rb
118
+ - spec/activerecord_hoarder/storage_spec.rb
119
+ - spec/activerecord_hoarder_spec.rb
120
+ - spec/factories/examples.rb
121
+ - spec/spec_helper.rb
122
+ - spec/support/0_rspec_configuration.rb
123
+ - spec/support/1_active_record_configuration.rb
124
+ - spec/support/2_database_content.rb
125
+ - spec/support/3_test_storage.rb
126
+ homepage: https://github.com/Scrimmage/gem_batch_archiving
127
+ licenses:
128
+ - MIT
129
+ metadata: {}
130
+ post_install_message:
131
+ rdoc_options: []
132
+ require_paths:
133
+ - lib
134
+ required_ruby_version: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - ">="
137
+ - !ruby/object:Gem::Version
138
+ version: '0'
139
+ required_rubygems_version: !ruby/object:Gem::Requirement
140
+ requirements:
141
+ - - ">="
142
+ - !ruby/object:Gem::Version
143
+ version: '0'
144
+ requirements: []
145
+ rubyforge_project:
146
+ rubygems_version: 2.4.8
147
+ signing_key:
148
+ specification_version: 4
149
+ summary: hoards records
150
+ test_files:
151
+ - spec/activerecord_hoarder/aws_s3_storage_spec.rb
152
+ - spec/activerecord_hoarder/batch_archiver_spec.rb
153
+ - spec/activerecord_hoarder/core_spec.rb
154
+ - spec/activerecord_hoarder/serializer_spec.rb
155
+ - spec/activerecord_hoarder/storage_spec.rb
156
+ - spec/activerecord_hoarder_spec.rb
157
+ - spec/factories/examples.rb
158
+ - spec/spec_helper.rb
159
+ - spec/support/0_rspec_configuration.rb
160
+ - spec/support/1_active_record_configuration.rb
161
+ - spec/support/2_database_content.rb
162
+ - spec/support/3_test_storage.rb