redshift-connector 7.0.2 → 7.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
- SHA1:
3
- metadata.gz: 4869945b94bf612693b98677cc3e4e9387f42533
4
- data.tar.gz: f920bd5ee6f860615cbfa4926b5a82f59642235c
2
+ SHA256:
3
+ metadata.gz: 6d05034adedce4cea33f24328428eb4823e89224eba62cd3548bf41e329cfe5d
4
+ data.tar.gz: 85b98e33059fcac9e50e505f9eea6cfc53665cf31b66a1de1fc676199150687d
5
5
  SHA512:
6
- metadata.gz: ca4ba82a836040efab25cd5c3484aab7fbc9881833bcb6dc1c8afb391d2b00348b577ac1a722e3d964e9f57a62a602bce38bf6e97917da9b095fa06fe622e477
7
- data.tar.gz: 505f1dd2b14ee460e46c274232d673bad58bd55b88a4558225a54c292177765b72f07514dfc0e59f5f7de4e8b78f373a0ea4c13dfcbc7404e03586e1c4431fa8
6
+ metadata.gz: 6ab6e0528d17951481902ed37679f110bed1718848a17cb962598524e5439e3784dc46b9293222fdf93e0c74ab820d58243e92fc3268172e91019140e99d92dc
7
+ data.tar.gz: 9800067fa5f06ea4268702519650b1155cdb71c212852402e7cf539f9e25a9408a2987f2e77b97ac6551dd8f5d7511e12fca10d9ebabfcaf07653f5f1feac464
data/.gitignore ADDED
@@ -0,0 +1,20 @@
1
+ # Packaging
2
+ *.gem
3
+ /spec/reports/
4
+ /spec/examples.txt
5
+
6
+ # Documents
7
+ /.yardoc/
8
+ /_yardoc/
9
+ /doc/
10
+ /rdoc/
11
+
12
+ # Bundler
13
+ /.bundle/
14
+ /vendor/bundle
15
+ /lib/bundler/man/
16
+ Gemfile.lock
17
+
18
+ # Gem Specific
19
+ test/database.yml
20
+ test/config.rb
data/Gemfile ADDED
@@ -0,0 +1,7 @@
1
+ source "https://rubygems.org"
2
+ gemspec
3
+
4
+ # We need explicit version specification (4 or 5) here,
5
+ # to resolve version dependencies correctly.
6
+ gem 'activerecord', '~> 5.0'
7
+ gem 'mysql2'
data/LICENSE ADDED
@@ -0,0 +1,21 @@
1
+ MIT License
2
+
3
+ Copyright (c) 2016,2017 Minero Aoki
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 all
13
+ 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 THE
21
+ SOFTWARE.
data/RELEASE.md ADDED
@@ -0,0 +1,76 @@
1
+ # Release Note
2
+
3
+ ## version 7.2.1
4
+
5
+ - no change.
6
+
7
+ ## version 7.2.0
8
+
9
+ - Removes aws-sdk dependency
10
+
11
+ ## version 7.0.2
12
+
13
+ - [fix] RedshiftConnector.foreach did not work
14
+
15
+ ## version 7.0.1
16
+
17
+ - [fix] RedshiftConnector.transport_delta_from_s3, .transport_all_from_s3 were wrongly dropped, restore them.
18
+
19
+ ## version 7.0.0
20
+
21
+ - [INCOMPATIBLE] Library hierarchy changed: redshift-connector/* -> redshift_connector/*. redshift-connector.rb still exists as an entry point for bundler.
22
+ - [new] Exporter becomes pluggable. You can implement your own exporter data source instead of ActiveRecord.
23
+
24
+ ## version 6.0.0
25
+
26
+ - version number change only.
27
+
28
+ ## version 5.6.0
29
+
30
+ - Unifies version 4.x (supports Rails 4) and 5.x (supports Rails 5).
31
+
32
+ ## version 4.5.0 / 5.5.0
33
+
34
+ - [new] Separates S3 access layer to another gem: redshift-connector-data_file
35
+
36
+ ## version 4.4.1 / 5.4.1
37
+
38
+ - [new] New option enable_sort for Connector.foreach, to enforce global sorting.
39
+
40
+ ## version 4.4.0 / 5.4.0
41
+
42
+ - [CHANGE] Drops export-only-once feature (and FORCE environment switch), it is not so useful.
43
+ Exporter now always exports data.
44
+
45
+ ## version 4.3.2 / 5.3.2
46
+
47
+ - [new] Allows reading from S3 signed URL (for separated export/import processes)
48
+
49
+ ## version 4.3.1 / 5.3.1
50
+
51
+ - First release for Rails 5 series.
52
+ - [fix] Add option for AWS multi-regions support
53
+
54
+ ## version 4.3.0
55
+
56
+ - [new] New method RedshiftConnector.foreach to read rows with UNLOAD
57
+
58
+ ## version 4.2.0
59
+
60
+ - [new] New methods RedshiftConnector.transport_delta_from_s3, .transport_all_from_s3 to read from S3
61
+
62
+ ## version 4.1.0
63
+
64
+ - [new] Introduces rebuild operator. New facade method Connector.transport_all.
65
+
66
+ ## version 4.0.2
67
+
68
+ - [fix] Correctly parses UNLOAD-generated CSV (dangerous characeters are escaped by backslash).
69
+
70
+ ## version 4.0.1
71
+
72
+ - [new] Allow configure the default logger by RedshiftConnector.logger=.
73
+
74
+ ## version 4.0.0
75
+
76
+ First release for Rails 4 series.
data/Rakefile ADDED
@@ -0,0 +1,3 @@
1
+ task :test do
2
+ load "#{__dir__}/test/all.rb"
3
+ end
@@ -1,3 +1,3 @@
1
1
  module RedshiftConnector
2
- VERSION = '7.0.2'
2
+ VERSION = '7.2.1'
3
3
  end
@@ -0,0 +1,26 @@
1
+ require_relative 'lib/redshift_connector/version'
2
+
3
+ Gem::Specification.new do |s|
4
+ s.platform = Gem::Platform::RUBY
5
+ s.name = 'redshift-connector'
6
+ s.version = RedshiftConnector::VERSION
7
+ s.summary = 'Redshift bulk data connector'
8
+ s.description = 'redshift-connector is a bulk data connector for Rails (ActiveRecord).'
9
+ s.license = 'MIT'
10
+
11
+ s.author = ['Minero Aoki']
12
+ s.email = 'aamine@loveruby.net'
13
+ s.homepage = 'https://github.com/bricolages/redshift-connector'
14
+
15
+ s.files = `git ls-files -z`.split("\x0").reject {|f| f.match(%r{^(test|spec|features)/}) }
16
+ s.require_path = 'lib'
17
+
18
+ s.required_ruby_version = '>= 2.1.0'
19
+ s.add_dependency 'redshift-connector-data_file', '>= 7.0.0'
20
+ s.add_dependency 'activerecord'
21
+ s.add_dependency 'activerecord-redshift'
22
+ s.add_dependency 'pg', '~> 0.18.0'
23
+ s.add_dependency 'activerecord-import'
24
+ s.add_development_dependency 'test-unit'
25
+ s.add_development_dependency 'rake'
26
+ end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: redshift-connector
3
3
  version: !ruby/object:Gem::Version
4
- version: 7.0.2
4
+ version: 7.2.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Minero Aoki
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2017-08-22 00:00:00.000000000 Z
11
+ date: 2018-07-25 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: redshift-connector-data_file
@@ -80,20 +80,6 @@ dependencies:
80
80
  - - ">="
81
81
  - !ruby/object:Gem::Version
82
82
  version: '0'
83
- - !ruby/object:Gem::Dependency
84
- name: aws-sdk
85
- requirement: !ruby/object:Gem::Requirement
86
- requirements:
87
- - - "~>"
88
- - !ruby/object:Gem::Version
89
- version: '2.0'
90
- type: :runtime
91
- prerelease: false
92
- version_requirements: !ruby/object:Gem::Requirement
93
- requirements:
94
- - - "~>"
95
- - !ruby/object:Gem::Version
96
- version: '2.0'
97
83
  - !ruby/object:Gem::Dependency
98
84
  name: test-unit
99
85
  requirement: !ruby/object:Gem::Requirement
@@ -108,20 +94,6 @@ dependencies:
108
94
  - - ">="
109
95
  - !ruby/object:Gem::Version
110
96
  version: '0'
111
- - !ruby/object:Gem::Dependency
112
- name: pry
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
97
  - !ruby/object:Gem::Dependency
126
98
  name: rake
127
99
  requirement: !ruby/object:Gem::Requirement
@@ -142,7 +114,12 @@ executables: []
142
114
  extensions: []
143
115
  extra_rdoc_files: []
144
116
  files:
117
+ - ".gitignore"
118
+ - Gemfile
119
+ - LICENSE
145
120
  - README.md
121
+ - RELEASE.md
122
+ - Rakefile
146
123
  - lib/redshift-connector.rb
147
124
  - lib/redshift_connector.rb
148
125
  - lib/redshift_connector/active_record_data_source.rb
@@ -161,18 +138,7 @@ files:
161
138
  - lib/redshift_connector/importer/upsert.rb
162
139
  - lib/redshift_connector/query.rb
163
140
  - lib/redshift_connector/version.rb
164
- - test/all.rb
165
- - test/config.rb
166
- - test/config.rb.example
167
- - test/database.yml
168
- - test/database.yml.example
169
- - test/foreach.rb
170
- - test/helper.rb
171
- - test/item_pvs.ct.mysql
172
- - test/item_pvs.ct.redshift
173
- - test/reader/test_redshift_csv.rb
174
- - test/test_connector.rb
175
- - test/test_s3_import.rb
141
+ - redshift-connector.gemspec
176
142
  homepage: https://github.com/bricolages/redshift-connector
177
143
  licenses:
178
144
  - MIT
@@ -193,7 +159,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
193
159
  version: '0'
194
160
  requirements: []
195
161
  rubyforge_project:
196
- rubygems_version: 2.6.8
162
+ rubygems_version: 2.7.6
197
163
  signing_key:
198
164
  specification_version: 4
199
165
  summary: Redshift bulk data connector
data/test/all.rb DELETED
@@ -1,3 +0,0 @@
1
- Dir.glob("#{__dir__}/**/test_*.rb").each do |path|
2
- load path
3
- end
data/test/config.rb DELETED
@@ -1,13 +0,0 @@
1
- $TEST_SCHEMA = 'aamine'
2
-
3
- module RedshiftConnector
4
- Exporter.default_data_source = RedshiftConnector::ActiveRecordDataSource.new(Redshift)
5
-
6
- S3Bucket.add(
7
- 'redshift-copy-buffer',
8
- bucket: 'redshift-copy-buffer',
9
- prefix: 'development',
10
- iam_role: 'arn:aws:iam::789035092620:role/RedshiftDevelopers',
11
- default: true
12
- )
13
- end
@@ -1,18 +0,0 @@
1
- module RedshiftConnector
2
- # For test only
3
- $TEST_SCHEMA = 'test'
4
-
5
- Exporter.default_data_source = Redshift
6
-
7
- S3Bucket.add(
8
- 'ENTRY_NAME',
9
- bucket: 'YOUR_BUCKET_NAME',
10
- prefix: 'development',
11
- # When using IAM role
12
- iam_role: 'arn:aws:iam::NNNNNNNNNNNN:role/RRRRRRRRR',
13
- # When using explicit access key
14
- #access_key_id: 'AAAAAAAAAA',
15
- #secret_access_key: 'SSSSSSSSSS',
16
- default: true
17
- )
18
- end
data/test/database.yml DELETED
@@ -1,15 +0,0 @@
1
- mysql:
2
- adapter: mysql2
3
- host: localhost
4
- username: minero-aoki
5
- database: test
6
- encoding: utf8
7
-
8
- redshift:
9
- adapter: redshift
10
- host: dwh.ckpd.co
11
- port: 5439
12
- database: production
13
- username: aamine
14
- password: "3edCVfr$"
15
- encoding: utf8
@@ -1,15 +0,0 @@
1
- mysql:
2
- adapter: mysql2
3
- host: localhost
4
- username: USER_NAME
5
- database: test
6
- encoding: utf8
7
-
8
- redshift:
9
- adapter: redshift
10
- host: HOST_NAME
11
- port: 5439
12
- database: DATABASE_NAME
13
- username: USER_NAME
14
- password: PASSWORD
15
- encoding: utf8
data/test/foreach.rb DELETED
@@ -1,5 +0,0 @@
1
- require_relative 'helper'
2
-
3
- RedshiftConnector.foreach(schema: 'tabemiru', table: 'items', query: 'select id from tabemiru.items where id < 50 order by 1', enable_sort: true) do |row|
4
- p row
5
- end
data/test/helper.rb DELETED
@@ -1,25 +0,0 @@
1
- require 'active_record'
2
- require 'yaml'
3
- require 'logger'
4
-
5
- YAML.load_file("#{__dir__}/database.yml").each do |name, ent|
6
- ActiveRecord::Base.configurations[name] = ent
7
- end
8
-
9
- class BaseConn < ActiveRecord::Base
10
- establish_connection :mysql
11
- self.abstract_class = true
12
- end
13
- class ItemPv < BaseConn
14
- connection
15
- end
16
- class Redshift < ActiveRecord::Base
17
- establish_connection :redshift
18
- end
19
-
20
- require 'redshift-connector'
21
- # This IS REQUIRED to ensure to load mysql2 driver, at least outside of Rails.
22
- ActiveRecord::Import.require_adapter 'mysql2'
23
- require_relative 'config'
24
-
25
- RedshiftConnector.logger = Logger.new($stderr)
@@ -1,11 +0,0 @@
1
- create table item_pvs
2
- ( id bigint(20) primary key
3
- , data_date date not null
4
- , item_id int(11) not null
5
- , pv bigint(20) not null default 0
6
- , uu bigint(20) not null default 0
7
- )
8
- ;
9
-
10
- create unique index item_pvs_idx on item_pvs (id, data_date, item_id) using btree
11
- ;
@@ -1,9 +0,0 @@
1
- create table item_pvs
2
- ( id bigint encode lzo
3
- , data_date date encode lzo
4
- , item_id integer encode lzo
5
- , pv bigint encode lzo
6
- , uu bigint encode lzo
7
- )
8
- sortkey (data_date, item_id)
9
- ;
@@ -1,30 +0,0 @@
1
- require 'test/unit'
2
- require 'redshift-connector/data_file'
3
-
4
- module RedshiftConnector
5
- module Reader
6
- class TestRedshiftCSV < Test::Unit::TestCase
7
- def parse_row(line)
8
- r = RedshiftCSV.new(nil)
9
- r.parse_row(line, 1)
10
- end
11
-
12
- def test_parse_row
13
- assert_equal ['xxx', 'yyyy', 'zzz'],
14
- parse_row(%Q("xxx","yyyy","zzz"\n))
15
-
16
- assert_equal ['xxx', 'yyyy', 'zzz'],
17
- parse_row(%Q( "xxx" , "yyyy","zzz"\t\n))
18
-
19
- assert_equal ['x,x', "y\r\ny", 'z"z', 'a\\a'],
20
- parse_row(%Q("x\\,x","y\\r\\ny","z\\"z","a\\\\a"\n))
21
-
22
- assert_equal ['981179', '2017-01-07', '6', 'show', '99', '3'],
23
- parse_row(%Q("981179","2017-01-07","6","show","99","3"\r\n))
24
-
25
- assert_equal ['981179', '2017-01-07', '6', '852', 'show', '{"page"=>"4"}', '1', '1'],
26
- parse_row(%Q("981179","2017-01-07","6","852","show","{\\"page\\"=>\\"4\\"}","1","1"\n))
27
- end
28
- end
29
- end
30
- end
@@ -1,148 +0,0 @@
1
- require_relative 'helper'
2
- require 'test/unit'
3
-
4
- class TestConnector < Test::Unit::TestCase
5
- def test_connector_upsert
6
- data_date = '2016-11-03'
7
- job = RedshiftConnector.transport_delta(
8
- schema: $TEST_SCHEMA,
9
- table: 'item_pvs',
10
-
11
- txn_id: data_date,
12
- condition: %Q(data_date = date '#{data_date}'),
13
-
14
- columns: %w[id data_date item_id pv uu],
15
- upsert_columns: %w[pv uu],
16
- filter: -> (id, data_date, item_id, pv, uu) {
17
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
18
- }
19
- )
20
- job.execute
21
- end
22
-
23
- def test_connector_delete_insert
24
- data_date = '2016-11-03'
25
- job = RedshiftConnector.transport_delta(
26
- schema: $TEST_SCHEMA,
27
- table: 'item_pvs',
28
-
29
- txn_id: data_date,
30
- condition: %Q(data_date = date '#{data_date}'),
31
- delete_cond: %Q(data_date = date '#{data_date}'),
32
-
33
- columns: %w[id data_date item_id pv uu],
34
- filter: -> (id, data_date, item_id, pv, uu) {
35
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
36
- }
37
- )
38
- job.execute
39
- end
40
-
41
- def test_dup_options
42
- data_date = '2016-11-03'
43
- assert_raise(ArgumentError) {
44
- RedshiftConnector.transport_delta(
45
- schema: $TEST_SCHEMA,
46
- table: 'item_pvs',
47
-
48
- txn_id: data_date,
49
- condition: %Q(data_date = date '#{data_date}'),
50
- delete_cond: %Q(data_date = date '#{data_date}'),
51
-
52
- # Conflicts with delete_cond option
53
- upsert_columns: %w[pv uu],
54
-
55
- columns: %w[id data_date item_id pv uu],
56
- filter: -> (id, data_date, item_id, pv, uu) {
57
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
58
- }
59
- )
60
- }
61
- end
62
-
63
- def test_no_required_option
64
- data_date = '2016-11-03'
65
- assert_raise(ArgumentError) {
66
- RedshiftConnector.transport_delta(
67
- schema: $TEST_SCHEMA,
68
- table: 'item_pvs',
69
-
70
- txn_id: data_date,
71
- condition: %Q(data_date = date '#{data_date}'),
72
-
73
- columns: %w[id data_date item_id pv uu],
74
- filter: -> (id, data_date, item_id, pv, uu) {
75
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
76
- }
77
- )
78
- }
79
- end
80
-
81
- def test_connector_rebuild_truncate
82
- data_date = '2016-11-03'
83
- job = RedshiftConnector.transport_all(
84
- strategy: 'truncate',
85
- schema: $TEST_SCHEMA,
86
- table: 'item_pvs',
87
- txn_id: data_date,
88
- columns: %w[id data_date item_id pv uu],
89
- filter: -> (id, data_date, item_id, pv, uu) {
90
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
91
- }
92
- )
93
- job.execute
94
- end
95
-
96
- def test_connector_rebuild_rename
97
- data_date = '2016-11-03'
98
- job = RedshiftConnector.transport_all(
99
- strategy: 'rename',
100
- schema: $TEST_SCHEMA,
101
- table: 'item_pvs',
102
- txn_id: data_date,
103
- columns: %w[id data_date item_id pv uu],
104
- filter: -> (id, data_date, item_id, pv, uu) {
105
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
106
- }
107
- )
108
- job.execute
109
- end
110
-
111
- def test_connector_src_dest_table
112
- data_date = '2016-11-03'
113
- job = RedshiftConnector.transport_delta(
114
- schema: $TEST_SCHEMA,
115
- src_table: 'item_pvs',
116
- dest_table: 'item_pvs',
117
-
118
- txn_id: data_date,
119
- condition: %Q(data_date = date '#{data_date}'),
120
-
121
- columns: %w[id data_date item_id pv uu],
122
- upsert_columns: %w[pv uu],
123
- filter: -> (id, data_date, item_id, pv, uu) {
124
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
125
- }
126
- )
127
- job.execute
128
- end
129
-
130
- def test_connector_missing_src_dest
131
- data_date = '2016-11-03'
132
- assert_raise(ArgumentError) {
133
- RedshiftConnector.transport_delta(
134
- schema: $TEST_SCHEMA,
135
- src_table: 'item_pvs',
136
-
137
- txn_id: data_date,
138
- condition: %Q(data_date = date '#{data_date}'),
139
-
140
- columns: %w[id data_date item_id pv uu],
141
- upsert_columns: %w[pv uu],
142
- filter: -> (id, data_date, item_id, pv, uu) {
143
- [id.to_i, data_date, item_id.to_i, pv.to_i, uu.to_i]
144
- }
145
- )
146
- }
147
- end
148
- end
@@ -1,32 +0,0 @@
1
- require_relative 'helper'
2
- require 'test/unit'
3
- require 'redshift-connector'
4
-
5
- class TestS3Import < Test::Unit::TestCase
6
- def test_import_delta_tsv
7
- data_date = '2016-11-03'
8
- job = RedshiftConnector.transport_delta_from_s3(
9
- prefix: "#{$TEST_SCHEMA}_export/item_pvs_tsv/#{data_date}/item_pvs.tsv.",
10
- format: :tsv,
11
-
12
- table: 'item_pvs',
13
- columns: %w[id data_date item_id pv uu],
14
- upsert_columns: %w[pv uu]
15
- )
16
- job.execute
17
- end
18
-
19
- def test_import_all
20
- data_date = '2016-11-03'
21
- job = RedshiftConnector.transport_all_from_s3(
22
- strategy: 'truncate',
23
-
24
- prefix: "#{$TEST_SCHEMA}_export/item_pvs_tsv/#{data_date}/item_pvs.tsv.",
25
- format: :tsv,
26
-
27
- table: 'item_pvs',
28
- columns: %w[id data_date item_id pv uu]
29
- )
30
- job.execute
31
- end
32
- end