redshifter 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +4 -0
- data/.rspec +3 -0
- data/.travis.yml +4 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +147 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/lib/redshifter.rb +15 -0
- data/lib/redshifter/config.rb +41 -0
- data/lib/redshifter/extract_and_replace_redshift_table.rb +33 -0
- data/lib/redshifter/extract_and_update_redshift_table.rb +33 -0
- data/lib/redshifter/job/update_redshift_table_job.rb +15 -0
- data/lib/redshifter/table.rb +109 -0
- data/lib/redshifter/tasks.rb +25 -0
- data/lib/redshifter/util/create_or_replace_table.rb +65 -0
- data/lib/redshifter/util/extract_and_transform_updates.rb +81 -0
- data/lib/redshifter/util/redshift.rb +18 -0
- data/lib/redshifter/util/s3.rb +92 -0
- data/lib/redshifter/util/s3_manifest_writer.rb +36 -0
- data/lib/redshifter/util/table_config_validator.rb +65 -0
- data/lib/redshifter/util/update_table.rb +88 -0
- data/lib/redshifter/version.rb +3 -0
- data/redshifter.gemspec +30 -0
- metadata +180 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 8760ba2ad72e5e668d9f3c4eb6b70d04d86b15e9
|
4
|
+
data.tar.gz: 8eb1c3fa50e558f9cfac14ae1d4c606754d0bdf7
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: d1e972e73eea10034797bf4713185a845e9f8f1c61227b1db480c355aeda7a232aa8c2caa50a2cdb3e95243ec94ece2a5acc35383cbb016f35bb6f63ba150099
|
7
|
+
data.tar.gz: 6ed7ad01c948ee874b558e0f13a1009249feb95b7365330557e3d5a6bd754426c47092fa3ff53788f5b92af4c53a2cdea0792ba82586428d3f46b4a97d33a685
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Apartment List, Inc
|
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 +1,147 @@
|
|
1
|
+
# Redshifter
|
2
|
+
|
3
|
+
Provides a resque job and rake tasks to facilitate ETL (Extract Transform Load) processing of Postgres tables for export to a Redshift cluster.
|
4
|
+
|
5
|
+
Specifically provides:
|
6
|
+
1) Create/Replace job to replace all model data in Redshift
|
7
|
+
2) Update job updates all records created or updated since the last update ran
|
8
|
+
|
9
|
+
Limitations:
|
10
|
+
* deleted records are NOT synced to Redshift by the update job
|
11
|
+
|
12
|
+
Feature Roadmap:
|
13
|
+
* store last runtime locally instead of using potentially costly redshift query
|
14
|
+
|
15
|
+
## Versions
|
16
|
+
0.2.4 - New config format; update and replace rake tasks available
|
17
|
+
0.3.0 - Public version
|
18
|
+
|
19
|
+
## Installation
|
20
|
+
|
21
|
+
Add this line to your application's Gemfile:
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
gem 'redshifter'
|
25
|
+
```
|
26
|
+
|
27
|
+
And then execute:
|
28
|
+
|
29
|
+
$ bundle
|
30
|
+
|
31
|
+
Or install it yourself as:
|
32
|
+
|
33
|
+
$ gem install redshifter
|
34
|
+
|
35
|
+
## Usage
|
36
|
+
|
37
|
+
### Setup Redshifter in a Rails initializer
|
38
|
+
```ruby
|
39
|
+
# config/initializers/redshifter.rb
|
40
|
+
Redshifter.setup do |config|
|
41
|
+
# path in your app available for writing temp files
|
42
|
+
config.temp_directory_path = File.expand_path('../../tmp', __FILE__)
|
43
|
+
# path to redshifter table config
|
44
|
+
config.table_config_path = File.expand_path('../redshfiter.rb', __FILE__)
|
45
|
+
# redshift user should have access to create tables in the specified schema
|
46
|
+
config.redshift_username = 'your_app_user'
|
47
|
+
config.redshift_password = 'p@ssw0rd'
|
48
|
+
config.redshift_host = 'app.host.without.protocol.com'
|
49
|
+
config.redshift_port = 5439
|
50
|
+
config.redshift_database = 'database_name'
|
51
|
+
config.redshift_schema = 'a_schema'
|
52
|
+
# AWS user should be allowed full access to the specified bucket
|
53
|
+
config.aws_access_key_id = '<AWS user access key ID>'
|
54
|
+
config.aws_secret_access_key = '<AWS user secret access key>'
|
55
|
+
config.s3_bucket = 'a_redshifter_bucket'
|
56
|
+
# Heroku user must be a member of the app and have privileges to
|
57
|
+
# start new dynos
|
58
|
+
config.heroku_api_key = '<Heroku user api key>'
|
59
|
+
config.heroku_app_name = 'name of the app on heroku'
|
60
|
+
end
|
61
|
+
```
|
62
|
+
|
63
|
+
### Require Redshifter tasks in your Rakefile
|
64
|
+
```ruby
|
65
|
+
# Rakefile
|
66
|
+
# ...
|
67
|
+
require 'redshifter/tasks'
|
68
|
+
# ...
|
69
|
+
```
|
70
|
+
|
71
|
+
### Create a config file describing the tables, columns and transforms for export to redshift
|
72
|
+
```ruby
|
73
|
+
# config/redshifter.rb
|
74
|
+
Redshifter.config.tables = {
|
75
|
+
'books_with_export_at' => {
|
76
|
+
# [required] Source *table* name, not the Rails model name
|
77
|
+
source_table_name: 'books',
|
78
|
+
# [required] Prefixing your redshift table with its source is recommended
|
79
|
+
redshift_table_name: 'app_name_books',
|
80
|
+
# [required] Columns with Redshift datatypes to create; may differ from source DB
|
81
|
+
redshift_columns: {
|
82
|
+
'id' => 'INTEGER',
|
83
|
+
'title' => 'VARCHAR(128)',
|
84
|
+
'published_at' => 'TIMESTAMP',
|
85
|
+
'updated_at' => 'TIMESTAMP',
|
86
|
+
'exported_at' => 'TIMESTAMP'
|
87
|
+
},
|
88
|
+
# [optional] SQL statements to transform or populate redshift columns from
|
89
|
+
# source DB. By default, redshift columns will be populated from source
|
90
|
+
# column with the same name. Column key must exist in redshift_columns.
|
91
|
+
# If a matching source column does not exist you MUST specify it here.
|
92
|
+
source_column_transforms: {
|
93
|
+
'title' => "lower(title)",
|
94
|
+
'published_at' => 'first_edition_published_at',
|
95
|
+
'exported_at' => 'now()'
|
96
|
+
},
|
97
|
+
# [required] valid values: KEY, EVEN, ALL
|
98
|
+
redshift_distribution_style: 'KEY',
|
99
|
+
# [required, if redshift_distribution_style: 'KEY'] distribution key column
|
100
|
+
# name MUST be present in redshift_columns.keys
|
101
|
+
redshift_distribution_key: 'id',
|
102
|
+
# [optional] valid values: COMPOUND, INTERLEAVED; If omitted the Redshift
|
103
|
+
# table DDL statement will not specify the sort style and Redshift will
|
104
|
+
# implicitly default to COMPOUND style.
|
105
|
+
redshift_sort_style: 'INTERLEAVED',
|
106
|
+
# [required] Column names MUST be present in redshift_columns.keys; Max
|
107
|
+
# length of 8 when using INTERLEAVED sort style, and 400 when using
|
108
|
+
# COMPOUND sort style.
|
109
|
+
redshift_sort_keys: ['published_at'],
|
110
|
+
# [optional] Used for query planning in Redshift
|
111
|
+
redshift_primary_key: 'id'
|
112
|
+
}
|
113
|
+
}
|
114
|
+
|
115
|
+
```
|
116
|
+
|
117
|
+
### Run redshifter:replace rake task for each table you want to export
|
118
|
+
```
|
119
|
+
$ rake redshifter:replace[books_with_export_at]
|
120
|
+
```
|
121
|
+
|
122
|
+
### Schedule a Redshifter::Job::UpdateRedshiftTableJob resque job per each table you want to export updates for
|
123
|
+
|
124
|
+
Then schedule this meta job to run in `resque_schedule.yml` to run once at 10:00pm
|
125
|
+
```YAML
|
126
|
+
# config/resque_schedule.yml
|
127
|
+
|
128
|
+
etl_books_to_redshift:
|
129
|
+
cron: "0 22 * * *"
|
130
|
+
class: 'Redshifter::Job::UpdateRedshiftTableJob'
|
131
|
+
args: 'books_with_export_at'
|
132
|
+
description: 'Export the books table to Redshift'
|
133
|
+
```
|
134
|
+
|
135
|
+
## Development
|
136
|
+
|
137
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.
|
138
|
+
|
139
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
140
|
+
|
141
|
+
## Contributing
|
142
|
+
|
143
|
+
1. Fork it ( https://github.com/[my-github-username]/redshifter/fork )
|
144
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
145
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
146
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
147
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "redshifter"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/redshifter.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'redshifter/version'
|
2
|
+
require 'redshifter/config'
|
3
|
+
require 'redshifter/table'
|
4
|
+
|
5
|
+
require 'redshifter/util/table_config_validator'
|
6
|
+
require 'redshifter/util/redshift'
|
7
|
+
require 'redshifter/util/s3'
|
8
|
+
require 'redshifter/util/extract_and_transform_updates'
|
9
|
+
require 'redshifter/util/s3_manifest_writer'
|
10
|
+
require 'redshifter/util/create_or_replace_table'
|
11
|
+
require 'redshifter/util/update_table'
|
12
|
+
|
13
|
+
require 'redshifter/extract_and_replace_redshift_table'
|
14
|
+
require 'redshifter/extract_and_update_redshift_table'
|
15
|
+
require 'redshifter/job/update_redshift_table_job'
|
@@ -0,0 +1,41 @@
|
|
1
|
+
module Redshifter
|
2
|
+
class << self
|
3
|
+
def setup
|
4
|
+
yield config if block_given?
|
5
|
+
load_export_table_definitions
|
6
|
+
config_dynosaur
|
7
|
+
end
|
8
|
+
|
9
|
+
def config
|
10
|
+
@config ||= Struct.new(:tables,
|
11
|
+
:redshift_username,
|
12
|
+
:redshift_password,
|
13
|
+
:redshift_host,
|
14
|
+
:redshift_port,
|
15
|
+
:redshift_database,
|
16
|
+
:redshift_schema,
|
17
|
+
:aws_access_key_id,
|
18
|
+
:aws_secret_access_key,
|
19
|
+
:s3_bucket,
|
20
|
+
:heroku_api_key,
|
21
|
+
:heroku_app_name,
|
22
|
+
:temp_directory_path,
|
23
|
+
:table_config_path).new
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def load_export_table_definitions
|
29
|
+
load config.table_config_path
|
30
|
+
end
|
31
|
+
|
32
|
+
def config_dynosaur
|
33
|
+
require 'dynosaur'
|
34
|
+
|
35
|
+
Dynosaur::Client::HerokuClient.configure do |config|
|
36
|
+
config.api_key = Redshifter.config.heroku_api_key
|
37
|
+
config.app_name = Redshifter.config.heroku_app_name
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
module Redshifter
|
2
|
+
class ExtractAndReplaceRedshiftTable
|
3
|
+
def initialize(table, s3_util = Util::S3.new)
|
4
|
+
@table = table
|
5
|
+
@s3_util = s3_util
|
6
|
+
end
|
7
|
+
|
8
|
+
def run
|
9
|
+
extracted_s3_urls = Util::ExtractAndTransformUpdates
|
10
|
+
.new(table: table,
|
11
|
+
since: Table::EPOCH_TIMESTAMP,
|
12
|
+
s3_util: s3_util
|
13
|
+
).run
|
14
|
+
|
15
|
+
if extracted_s3_urls.any?
|
16
|
+
manifest_url = Util::S3ManifestWriter
|
17
|
+
.new(file_name: "#{SecureRandom.uuid}.manifest",
|
18
|
+
file_urls: extracted_s3_urls,
|
19
|
+
s3_util: s3_util
|
20
|
+
).run
|
21
|
+
|
22
|
+
Util::CreateOrReplaceTable
|
23
|
+
.new(table: table,
|
24
|
+
manifest_url: manifest_url
|
25
|
+
).run
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
private
|
30
|
+
|
31
|
+
attr_reader :table, :s3_util
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
module Redshifter
|
2
|
+
class ExtractAndUpdateRedshiftTable
|
3
|
+
def initialize(table, s3_util = Util::S3.new)
|
4
|
+
@table = table
|
5
|
+
@s3_util = s3_util
|
6
|
+
end
|
7
|
+
|
8
|
+
def run
|
9
|
+
extracted_s3_urls = Util::ExtractAndTransformUpdates
|
10
|
+
.new(table: table,
|
11
|
+
since: table.redshift_last_update,
|
12
|
+
s3_util: s3_util
|
13
|
+
).run
|
14
|
+
|
15
|
+
if extracted_s3_urls.any?
|
16
|
+
manifest_url = Util::S3ManifestWriter
|
17
|
+
.new(file_name: "#{SecureRandom.uuid}.manifest",
|
18
|
+
file_urls: extracted_s3_urls,
|
19
|
+
s3_util: s3_util
|
20
|
+
).run
|
21
|
+
|
22
|
+
Util::UpdateTable
|
23
|
+
.new(table: table,
|
24
|
+
manifest_url: manifest_url
|
25
|
+
).run
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
private
|
30
|
+
|
31
|
+
attr_reader :table, :s3_util
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'dynosaur'
|
2
|
+
|
3
|
+
module Redshifter
|
4
|
+
module Job
|
5
|
+
class UpdateRedshiftTableJob
|
6
|
+
@queue = :low
|
7
|
+
|
8
|
+
def self.perform(table_config_key)
|
9
|
+
dyno = Dynosaur::Process::Heroku
|
10
|
+
.new(task: 'redshifter:update', args: [table_config_key])
|
11
|
+
dyno.start
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
@@ -0,0 +1,109 @@
|
|
1
|
+
module Redshifter
|
2
|
+
class Table
|
3
|
+
EPOCH_TIMESTAMP = '1970-01-01 00:00:00'
|
4
|
+
|
5
|
+
def initialize(config)
|
6
|
+
Util::TableConfigValidator.new(config).validate!
|
7
|
+
|
8
|
+
@source_table_name = config[:source_table_name]
|
9
|
+
@redshift_table_name = config[:redshift_table_name]
|
10
|
+
@redshift_columns = config[:redshift_columns]
|
11
|
+
@source_column_transforms = config[:source_column_transforms] || {}
|
12
|
+
@redshift_distribution_style = config[:redshift_distribution_style]
|
13
|
+
@redshift_distribution_key = config[:redshift_distribution_key]
|
14
|
+
@redshift_sort_keys = config[:redshift_sort_keys]
|
15
|
+
@redshift_sort_style = config[:redshift_sort_style]
|
16
|
+
@redshift_primary_key = config[:redshift_primary_key]
|
17
|
+
end
|
18
|
+
|
19
|
+
attr_reader :source_table_name, :redshift_table_name
|
20
|
+
|
21
|
+
def redshift_column_names
|
22
|
+
redshift_columns.keys
|
23
|
+
end
|
24
|
+
|
25
|
+
def source_column_statements
|
26
|
+
redshift_columns.keys.map do |v|
|
27
|
+
return v unless source_column_transforms
|
28
|
+
source_column_transforms[v] || v
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
def redshift_schema
|
33
|
+
Redshifter.config.redshift_schema
|
34
|
+
end
|
35
|
+
|
36
|
+
def redshift_table_ddl(table_name = redshift_table_name)
|
37
|
+
<<-QUERY.squish
|
38
|
+
CREATE TABLE
|
39
|
+
#{redshift_schema}.#{table_name}(
|
40
|
+
#{redshift_columns.map { |k, v| "#{k} #{v}" }.join(', ')}#{primary_key_statement}
|
41
|
+
)
|
42
|
+
#{dist_statement}
|
43
|
+
#{sortkey_statement};
|
44
|
+
QUERY
|
45
|
+
end
|
46
|
+
|
47
|
+
# returns unix epoch timestamp literal if table does not exist or table
|
48
|
+
# exist with zero rows. Otherwise returns timestamp literal of most
|
49
|
+
# recently updated row in the analytics table
|
50
|
+
def redshift_last_update
|
51
|
+
conn = Util::Redshift.connect
|
52
|
+
|
53
|
+
table_presence_query = <<-QUERY.squish
|
54
|
+
SELECT EXISTS(
|
55
|
+
SELECT 1
|
56
|
+
FROM information_schema.tables
|
57
|
+
WHERE table_schema = '#{redshift_schema}'
|
58
|
+
AND table_name = '#{redshift_table_name}')
|
59
|
+
QUERY
|
60
|
+
|
61
|
+
# Redshift does not allow pg catalog table and user table to be accessed
|
62
|
+
# in the same query
|
63
|
+
# http://docs.aws.amazon.com/redshift/latest/dg/c_sql-functions-leader-node.html
|
64
|
+
table_present = conn.exec(table_presence_query).getvalue(0, 0)
|
65
|
+
|
66
|
+
if table_present == 't'
|
67
|
+
conn.exec(
|
68
|
+
<<-QUERY.squish
|
69
|
+
SELECT COALESCE(MAX(updated_at), TIMESTAMP '#{EPOCH_TIMESTAMP}')
|
70
|
+
FROM #{redshift_schema}.#{redshift_table_name}
|
71
|
+
QUERY
|
72
|
+
).getvalue(0, 0)
|
73
|
+
else
|
74
|
+
EPOCH_TIMESTAMP
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
private
|
79
|
+
|
80
|
+
attr_reader :redshift_columns,
|
81
|
+
:source_column_transforms,
|
82
|
+
:redshift_distribution_key,
|
83
|
+
:redshift_sort_keys,
|
84
|
+
:redshift_distribution_style,
|
85
|
+
:redshift_sort_style,
|
86
|
+
:redshift_primary_key
|
87
|
+
|
88
|
+
def dist_statement
|
89
|
+
output = "DISTSTYLE #{redshift_distribution_style}"
|
90
|
+
if redshift_distribution_style == 'KEY'
|
91
|
+
output << " DISTKEY(#{redshift_distribution_key})"
|
92
|
+
end
|
93
|
+
|
94
|
+
output
|
95
|
+
end
|
96
|
+
|
97
|
+
def sortkey_statement
|
98
|
+
output = ''
|
99
|
+
output << "#{redshift_sort_style} " if redshift_sort_style
|
100
|
+
output << "SORTKEY(#{redshift_sort_keys.join(', ')})"
|
101
|
+
|
102
|
+
output
|
103
|
+
end
|
104
|
+
|
105
|
+
def primary_key_statement
|
106
|
+
redshift_primary_key ? ", PRIMARY KEY(#{redshift_primary_key})" : ''
|
107
|
+
end
|
108
|
+
end
|
109
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module Redshifter
|
2
|
+
class Tasks
|
3
|
+
include Rake::DSL if defined? Rake::DSL
|
4
|
+
|
5
|
+
def install_tasks
|
6
|
+
namespace :redshifter do
|
7
|
+
desc 'Create or replace an extracted table in Redshift'
|
8
|
+
task :replace, [:table_config_key] => :environment do |_task, args|
|
9
|
+
table_config = Redshifter.config.tables[args[:table_config_key]]
|
10
|
+
table = Redshifter::Table.new(table_config)
|
11
|
+
Redshifter::ExtractAndReplaceRedshiftTable.new(table).run
|
12
|
+
end
|
13
|
+
|
14
|
+
desc 'Update an extracted table in Redshift'
|
15
|
+
task :update, [:table_config_key] => :environment do |_task, args|
|
16
|
+
table_config = Redshifter.config.tables[args[:table_config_key]]
|
17
|
+
table = Redshifter::Table.new(table_config)
|
18
|
+
Redshifter::ExtractAndUpdateRedshiftTable.new(table).run
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
Redshifter::Tasks.new.install_tasks
|
@@ -0,0 +1,65 @@
|
|
1
|
+
module Redshifter
|
2
|
+
module Util
|
3
|
+
class CreateOrReplaceTable
|
4
|
+
def initialize(table:, manifest_url:)
|
5
|
+
@table = table
|
6
|
+
@manifest_url = manifest_url
|
7
|
+
end
|
8
|
+
|
9
|
+
def run(conn = Redshift.connect)
|
10
|
+
conn.transaction do |within_transaction|
|
11
|
+
[
|
12
|
+
drop_and_create_table_sql,
|
13
|
+
grant_readonly_permissions_sql
|
14
|
+
].each do |query|
|
15
|
+
within_transaction.exec(query)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
private
|
21
|
+
|
22
|
+
attr_reader :table, :manifest_url
|
23
|
+
|
24
|
+
# creates or replaces an existing table from an s3 manifest of gzipped pipe
|
25
|
+
# delimitted files.
|
26
|
+
#
|
27
|
+
# COPY is the most efficient way to load data into redshift. When COPY is
|
28
|
+
# run on a new table with zero rows it automatically runs statistics
|
29
|
+
# (ANALYZE) and sorts and distributes data (VACUUM). Using the manifest
|
30
|
+
# allows COPY command to run in parallel.
|
31
|
+
#
|
32
|
+
#SQL Notes:
|
33
|
+
# CSV QUOTE AS '"' -- only way to define quote character for multiline
|
34
|
+
# -- column data (even though file is not comma separated)
|
35
|
+
# DELIMITER '|' -- this is the default separator, just being explicit
|
36
|
+
# TIMEFORMAT 'YYYY-MM-DD HH:MI:SS' -- being explicit insead of auto detect
|
37
|
+
def drop_and_create_table_sql
|
38
|
+
<<-QUERY.squish
|
39
|
+
DROP TABLE IF EXISTS #{table.redshift_schema}.#{table.redshift_table_name};
|
40
|
+
|
41
|
+
#{table.redshift_table_ddl}
|
42
|
+
|
43
|
+
COPY #{table.redshift_schema}.#{table.redshift_table_name}
|
44
|
+
(#{table.redshift_column_names.join(', ')})
|
45
|
+
FROM '#{manifest_url}'
|
46
|
+
CREDENTIALS 'aws_access_key_id=#{Redshifter.config.aws_access_key_id};aws_secret_access_key=#{Redshifter.config.aws_secret_access_key}'
|
47
|
+
CSV QUOTE AS '"'
|
48
|
+
DELIMITER '|'
|
49
|
+
GZIP
|
50
|
+
TIMEFORMAT 'YYYY-MM-DD HH:MI:SS'
|
51
|
+
NULL AS '#{ExtractAndTransformUpdates::NULL_CHARACTER}'
|
52
|
+
MANIFEST;
|
53
|
+
QUERY
|
54
|
+
end
|
55
|
+
|
56
|
+
def grant_readonly_permissions_sql
|
57
|
+
<<-QUERY.squish
|
58
|
+
GRANT SELECT, REFERENCES
|
59
|
+
ON TABLE #{table.redshift_schema}.#{table.redshift_table_name}
|
60
|
+
TO GROUP readonly;
|
61
|
+
QUERY
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,81 @@
|
|
1
|
+
require 'csv'
|
2
|
+
|
3
|
+
module Redshifter
|
4
|
+
module Util
|
5
|
+
class ExtractAndTransformUpdates
|
6
|
+
# Character used to represent a NULL value in the CSV. We cannot use an
|
7
|
+
# empty string to represent NULL, because then any tables with empty string
|
8
|
+
# values would have those converted to NULL in the Redshift tables. This
|
9
|
+
# needs to be a character we do not expect to appear as a value in any of
|
10
|
+
# the tables that are in the ETL process.
|
11
|
+
NULL_CHARACTER = '∅'
|
12
|
+
|
13
|
+
def initialize(table:, since:, s3_util:)
|
14
|
+
@table = table
|
15
|
+
@since = since
|
16
|
+
@s3_util = s3_util
|
17
|
+
end
|
18
|
+
|
19
|
+
# Writes pipe delimited 'CSV' files to S3 of updated records.
|
20
|
+
# Returns a list of internal s3 URLs created
|
21
|
+
def run(batch_size: 1000)
|
22
|
+
uploaded_s3_urls = []
|
23
|
+
run_name = SecureRandom.uuid
|
24
|
+
|
25
|
+
transform_in_batches(table.source_column_statements,
|
26
|
+
batch_size: batch_size) do |rows, batch|
|
27
|
+
csv_rows = rows.map(&method(:csv_row))
|
28
|
+
|
29
|
+
uploaded_s3_urls << s3_util.upload_file(
|
30
|
+
file_name: "#{table.redshift_table_name}_updates_#{run_name}_#{batch}.txt",
|
31
|
+
body: csv_rows.join,
|
32
|
+
gzip: true)
|
33
|
+
end
|
34
|
+
|
35
|
+
uploaded_s3_urls
|
36
|
+
end
|
37
|
+
|
38
|
+
private
|
39
|
+
|
40
|
+
attr_reader :table, :since, :s3_util
|
41
|
+
|
42
|
+
def csv_row(row)
|
43
|
+
row.map! { |value| value.nil? ? NULL_CHARACTER : value }
|
44
|
+
CSV.generate_line(row, col_sep: '|')
|
45
|
+
end
|
46
|
+
|
47
|
+
def transform_in_batches(*column_transforms, batch_size: 1000)
|
48
|
+
# guarantee id is present in the first column for batch functionality
|
49
|
+
select_column_transforms = column_transforms.dup.unshift('id as id_for_batching')
|
50
|
+
batch_start_id = 1
|
51
|
+
batch_count = 0
|
52
|
+
|
53
|
+
loop do
|
54
|
+
rows = ActiveRecord::Base.connection_pool.with_connection do |conn|
|
55
|
+
conn.exec_query(select_batch_sql(columns: select_column_transforms,
|
56
|
+
batch_size: batch_size,
|
57
|
+
start_id: batch_start_id)
|
58
|
+
)
|
59
|
+
end.rows
|
60
|
+
|
61
|
+
break if rows.empty?
|
62
|
+
|
63
|
+
# get the id from the first column position where it was injected
|
64
|
+
last_id = rows.last[0].to_i
|
65
|
+
# remove the injected id from the first column
|
66
|
+
rows.map! { |row| row[1..-1] }
|
67
|
+
|
68
|
+
yield rows, batch_count
|
69
|
+
|
70
|
+
break if rows.size < batch_size
|
71
|
+
batch_start_id = last_id + 1
|
72
|
+
batch_count += 1
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
def select_batch_sql(columns:, batch_size:, start_id:)
|
77
|
+
"select #{columns.join(', ')} from #{table.source_table_name} where updated_at >= '#{since}' AND id >= #{start_id} ORDER BY id ASC limit #{batch_size}"
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
module Redshifter
|
2
|
+
module Util
|
3
|
+
module Redshift
|
4
|
+
def self.connect
|
5
|
+
PG.connect(
|
6
|
+
{
|
7
|
+
host: Redshifter.config.redshift_host,
|
8
|
+
port: Redshifter.config.redshift_port,
|
9
|
+
dbname: Redshifter.config.redshift_database,
|
10
|
+
user: Redshifter.config.redshift_username,
|
11
|
+
password: Redshifter.config.redshift_password,
|
12
|
+
sslmode: 'require'
|
13
|
+
}
|
14
|
+
)
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
@@ -0,0 +1,92 @@
|
|
1
|
+
require 'fog'
|
2
|
+
require 'tmpdir'
|
3
|
+
|
4
|
+
module Redshifter
|
5
|
+
module Util
|
6
|
+
class S3
|
7
|
+
def upload_file(file_name:, body:, gzip: false)
|
8
|
+
s3_url = ''
|
9
|
+
|
10
|
+
Dir.mktmpdir('redshifter', ensure_app_tmp_directory) do |temp_dir|
|
11
|
+
temp_file = write_temp_file(File.join(temp_dir, file_name), body, gzip)
|
12
|
+
File.open(temp_file) do |file|
|
13
|
+
s3_file = bucket.files.create(file_options(file, gzip))
|
14
|
+
s3_url = internal_file_url(s3_file.key)
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
s3_url
|
19
|
+
end
|
20
|
+
|
21
|
+
private
|
22
|
+
|
23
|
+
def internal_file_url(file_name)
|
24
|
+
"s3://#{bucket_name}/#{file_name}"
|
25
|
+
end
|
26
|
+
|
27
|
+
def conn
|
28
|
+
@conn ||= Fog::Storage.new(
|
29
|
+
provider: 'AWS',
|
30
|
+
aws_access_key_id: Redshifter.config.aws_access_key_id,
|
31
|
+
aws_secret_access_key: Redshifter.config.aws_secret_access_key
|
32
|
+
)
|
33
|
+
end
|
34
|
+
|
35
|
+
def bucket
|
36
|
+
@bucket ||= conn.directories.get(bucket_name)
|
37
|
+
end
|
38
|
+
|
39
|
+
def bucket_name
|
40
|
+
Redshifter.config.s3_bucket
|
41
|
+
end
|
42
|
+
|
43
|
+
def file_options(file, gzip)
|
44
|
+
s3_file_options = {
|
45
|
+
key: File.basename(file),
|
46
|
+
body: file,
|
47
|
+
public: false
|
48
|
+
}
|
49
|
+
|
50
|
+
s3_file_options.merge!(
|
51
|
+
content_encoding: 'ASCII-8BIT',
|
52
|
+
compression_mime_type: 'application/x-gzip'
|
53
|
+
) if gzip
|
54
|
+
|
55
|
+
s3_file_options
|
56
|
+
end
|
57
|
+
|
58
|
+
def ensure_app_tmp_directory
|
59
|
+
tmp_path = Redshifter.config.temp_directory_path
|
60
|
+
Dir.mkdir(tmp_path) unless File.directory?(tmp_path)
|
61
|
+
tmp_path
|
62
|
+
end
|
63
|
+
|
64
|
+
def write_temp_file(file_path, body, gzip)
|
65
|
+
if gzip
|
66
|
+
write_temp_gzipped_file(file_path, body)
|
67
|
+
else
|
68
|
+
write_temp_uncompressed_file(file_path, body)
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
def write_temp_uncompressed_file(file_path, body)
|
73
|
+
File.open(file_path, 'w') do |file|
|
74
|
+
file << body
|
75
|
+
file
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
def write_temp_gzipped_file(file_path, body)
|
80
|
+
gz_file_path = file_path + '.gz'
|
81
|
+
File.open(gz_file_path, 'w', encoding: 'ASCII-8BIT') do |compressed_file|
|
82
|
+
compressed_file.sync = true
|
83
|
+
gzip = Zlib::GzipWriter.new(compressed_file)
|
84
|
+
gzip.write(body)
|
85
|
+
gzip.close # Important: Without this call, gzip headers won't be written
|
86
|
+
compressed_file
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
module Redshifter
|
2
|
+
module Util
|
3
|
+
class S3ManifestWriter
|
4
|
+
def initialize(file_name:, file_urls:, s3_util:)
|
5
|
+
@file_name = file_name
|
6
|
+
@file_urls = file_urls
|
7
|
+
@s3_util = s3_util
|
8
|
+
end
|
9
|
+
|
10
|
+
# Uploads a s3 manifest file that requires all files be processed with
|
11
|
+
# mandatory: true attribute per file.
|
12
|
+
# Returns internal s3 URL for the manifest
|
13
|
+
def run
|
14
|
+
s3_util.upload_file(
|
15
|
+
file_name: file_name,
|
16
|
+
body: JSON.generate(manifest),
|
17
|
+
gzip: false
|
18
|
+
)
|
19
|
+
end
|
20
|
+
|
21
|
+
private
|
22
|
+
|
23
|
+
attr_reader :file_name, :file_urls, :s3_util
|
24
|
+
|
25
|
+
def manifest
|
26
|
+
{ entries: manifest_files }
|
27
|
+
end
|
28
|
+
|
29
|
+
def manifest_files
|
30
|
+
file_urls.map do |child_url|
|
31
|
+
{ url: child_url, mandatory: true }
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
module Redshifter
|
2
|
+
module Util
|
3
|
+
class TableConfigValidator
|
4
|
+
REQUIRED_KEYS = [:source_table_name,
|
5
|
+
:redshift_table_name,
|
6
|
+
:redshift_columns,
|
7
|
+
:redshift_distribution_style,
|
8
|
+
:redshift_sort_keys]
|
9
|
+
|
10
|
+
# hash format: { required_key: { when_this_key_and_value: 'present'} }
|
11
|
+
CONDITIONALLY_REQUIRED_KEYS = {
|
12
|
+
redshift_distribution_key: { redshift_distribution_style: 'KEY' }
|
13
|
+
}
|
14
|
+
|
15
|
+
# Use a nil value when the key is optional, but has allowable values
|
16
|
+
# when it is present. e.g. {optional_key: ['valid1', 'valid2', nil]}
|
17
|
+
ALLOWABLE_VALUES = {
|
18
|
+
redshift_distribution_style: ['KEY', 'ALL', 'EVEN'],
|
19
|
+
redshift_sort_style: ['COMPOUND', 'INTERLEAVED', nil]
|
20
|
+
}
|
21
|
+
|
22
|
+
def initialize(config)
|
23
|
+
@config = config
|
24
|
+
end
|
25
|
+
|
26
|
+
def validate!
|
27
|
+
raise 'invalid table config' unless valid?
|
28
|
+
end
|
29
|
+
|
30
|
+
def valid?
|
31
|
+
all_required_keys_present? &&
|
32
|
+
all_conditionally_required_keys_present? &&
|
33
|
+
all_validated_values_allowed?
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
attr_reader :config
|
39
|
+
|
40
|
+
def all_required_keys_present?
|
41
|
+
((REQUIRED_KEYS & config.keys) == REQUIRED_KEYS)
|
42
|
+
end
|
43
|
+
|
44
|
+
def all_conditionally_required_keys_present?
|
45
|
+
conditional_keys_presence = []
|
46
|
+
CONDITIONALLY_REQUIRED_KEYS.each do |required_k, condition_kv|
|
47
|
+
if (config.select { |k, v| k == condition_kv.keys.first } == condition_kv)
|
48
|
+
conditional_keys_presence << config.include?(required_k)
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
conditional_keys_presence.all?
|
53
|
+
end
|
54
|
+
|
55
|
+
def all_validated_values_allowed?
|
56
|
+
allowed_values_presence = []
|
57
|
+
ALLOWABLE_VALUES.each do |k, v|
|
58
|
+
allowed_values_presence << v.include?(config[k])
|
59
|
+
end
|
60
|
+
|
61
|
+
allowed_values_presence.all?
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,88 @@
|
|
1
|
+
module Redshifter
|
2
|
+
module Util
|
3
|
+
class UpdateTable
|
4
|
+
def initialize(table:, manifest_url:)
|
5
|
+
@table = table
|
6
|
+
@manifest_url = manifest_url
|
7
|
+
end
|
8
|
+
|
9
|
+
def run(conn = Redshift.connect)
|
10
|
+
conn.transaction do |within_transaction|
|
11
|
+
[
|
12
|
+
create_and_load_temp_table_sql,
|
13
|
+
upsert_changes_sql,
|
14
|
+
cleanup_temp_table_sql,
|
15
|
+
analyze_updated_table_sql
|
16
|
+
].each do |query|
|
17
|
+
within_transaction.exec(query)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
attr_reader :table, :manifest_url
|
25
|
+
|
26
|
+
def analytics_temp_table
|
27
|
+
"#{table.redshift_table_name}_temp"
|
28
|
+
end
|
29
|
+
|
30
|
+
#creates a temp table from original table DDL because it's the
|
31
|
+
# most efficient way to get a table the most closely mimics the destination.
|
32
|
+
# http://docs.aws.amazon.com/redshift/latest/dg/performing-a-deep-copy.html
|
33
|
+
#
|
34
|
+
# Imports rows from an s3 manifest of gzipped pipe delimitted files.
|
35
|
+
# Using the manifest allows COPY command to run in parallel.
|
36
|
+
#
|
37
|
+
#SQL Notes:
|
38
|
+
# CSV QUOTE AS '"' -- only way to define quote character for multiline
|
39
|
+
# -- column data (even though file is not comma separated)
|
40
|
+
# DELIMITER '|' -- this is the default separator, just being explicit
|
41
|
+
# TIMEFORMAT 'YYYY-MM-DD HH:MI:SS' -- being explicit insead of auto detect
|
42
|
+
# compupdate off -- save time by not compressing columns; it's temporary
|
43
|
+
# statupdate off -- save time by not running statistics; it's temporary
|
44
|
+
def create_and_load_temp_table_sql
|
45
|
+
<<-QUERY.squish
|
46
|
+
#{table.redshift_table_ddl(analytics_temp_table)}
|
47
|
+
|
48
|
+
COPY #{table.redshift_schema}.#{analytics_temp_table}
|
49
|
+
(#{table.redshift_column_names.join(', ')})
|
50
|
+
FROM '#{manifest_url}'
|
51
|
+
CREDENTIALS 'aws_access_key_id=#{Redshifter.config.aws_access_key_id};aws_secret_access_key=#{Redshifter.config.aws_secret_access_key}'
|
52
|
+
CSV QUOTE AS '"'
|
53
|
+
DELIMITER '|'
|
54
|
+
GZIP
|
55
|
+
TIMEFORMAT 'YYYY-MM-DD HH:MI:SS'
|
56
|
+
NULL AS '#{ExtractAndTransformUpdates::NULL_CHARACTER}'
|
57
|
+
MANIFEST
|
58
|
+
compupdate off
|
59
|
+
statupdate off;
|
60
|
+
QUERY
|
61
|
+
end
|
62
|
+
|
63
|
+
# Replaces existing rows with updated row in a single transaction using AWS
|
64
|
+
# recommended method
|
65
|
+
# http://docs.aws.amazon.com/redshift/latest/dg/merge-replacing-existing-rows.html
|
66
|
+
def upsert_changes_sql
|
67
|
+
<<-QUERY.squish
|
68
|
+
DELETE FROM #{table.redshift_schema}.#{table.redshift_table_name}
|
69
|
+
USING #{table.redshift_schema}.#{analytics_temp_table}
|
70
|
+
WHERE #{table.redshift_schema}.#{table.redshift_table_name}.id
|
71
|
+
= #{table.redshift_schema}.#{analytics_temp_table}.id;
|
72
|
+
|
73
|
+
INSERT INTO #{table.redshift_schema}.#{table.redshift_table_name}
|
74
|
+
SELECT * FROM #{table.redshift_schema}.#{analytics_temp_table};
|
75
|
+
QUERY
|
76
|
+
end
|
77
|
+
|
78
|
+
def cleanup_temp_table_sql
|
79
|
+
"drop table #{table.redshift_schema}.#{analytics_temp_table};"
|
80
|
+
end
|
81
|
+
|
82
|
+
# analyze recomputes table statistics for efficient querying after change
|
83
|
+
def analyze_updated_table_sql
|
84
|
+
"analyze #{table.redshift_schema}.#{table.redshift_table_name};"
|
85
|
+
end
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
data/redshifter.gemspec
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'redshifter/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'redshifter'
|
8
|
+
spec.version = Redshifter::VERSION
|
9
|
+
spec.authors = ['Justin Richard']
|
10
|
+
spec.email = ['justin@apartmentlist.com']
|
11
|
+
|
12
|
+
spec.summary = %q{ETL processing jobs to exporting Rails model tables to Redshift}
|
13
|
+
spec.homepage = 'https://github.com/apartmentlist/redshifter'
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
16
|
+
spec.require_paths = ['lib']
|
17
|
+
|
18
|
+
spec.add_runtime_dependency 'dynosaur', '~> 0'
|
19
|
+
spec.add_runtime_dependency 'fog', '~> 1.36.0'
|
20
|
+
# mime-types now an explicit dependency of fog-core >=1.35.0
|
21
|
+
# fog 1.36.0 has a loose dependency on fog-core "~> 1.32" that causes this
|
22
|
+
# dependency change to bubble up to redshifter
|
23
|
+
spec.add_runtime_dependency 'mime-types'
|
24
|
+
spec.add_runtime_dependency 'pg', '~> 0.18'
|
25
|
+
|
26
|
+
spec.add_development_dependency 'bundler'
|
27
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
28
|
+
spec.add_development_dependency 'pry-byebug', '~> 3'
|
29
|
+
spec.add_development_dependency 'rspec', '~> 3.3'
|
30
|
+
end
|
metadata
ADDED
@@ -0,0 +1,180 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: redshifter
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Justin Richard
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-12-04 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: dynosaur
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: fog
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.36.0
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.36.0
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: mime-types
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pg
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0.18'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0.18'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: bundler
|
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: rake
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '10.0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '10.0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: pry-byebug
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '3'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '3'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rspec
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '3.3'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '3.3'
|
125
|
+
description:
|
126
|
+
email:
|
127
|
+
- justin@apartmentlist.com
|
128
|
+
executables: []
|
129
|
+
extensions: []
|
130
|
+
extra_rdoc_files: []
|
131
|
+
files:
|
132
|
+
- ".gitignore"
|
133
|
+
- ".rspec"
|
134
|
+
- ".travis.yml"
|
135
|
+
- Gemfile
|
136
|
+
- LICENSE.txt
|
137
|
+
- README.md
|
138
|
+
- Rakefile
|
139
|
+
- bin/console
|
140
|
+
- bin/setup
|
141
|
+
- lib/redshifter.rb
|
142
|
+
- lib/redshifter/config.rb
|
143
|
+
- lib/redshifter/extract_and_replace_redshift_table.rb
|
144
|
+
- lib/redshifter/extract_and_update_redshift_table.rb
|
145
|
+
- lib/redshifter/job/update_redshift_table_job.rb
|
146
|
+
- lib/redshifter/table.rb
|
147
|
+
- lib/redshifter/tasks.rb
|
148
|
+
- lib/redshifter/util/create_or_replace_table.rb
|
149
|
+
- lib/redshifter/util/extract_and_transform_updates.rb
|
150
|
+
- lib/redshifter/util/redshift.rb
|
151
|
+
- lib/redshifter/util/s3.rb
|
152
|
+
- lib/redshifter/util/s3_manifest_writer.rb
|
153
|
+
- lib/redshifter/util/table_config_validator.rb
|
154
|
+
- lib/redshifter/util/update_table.rb
|
155
|
+
- lib/redshifter/version.rb
|
156
|
+
- redshifter.gemspec
|
157
|
+
homepage: https://github.com/apartmentlist/redshifter
|
158
|
+
licenses: []
|
159
|
+
metadata: {}
|
160
|
+
post_install_message:
|
161
|
+
rdoc_options: []
|
162
|
+
require_paths:
|
163
|
+
- lib
|
164
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
165
|
+
requirements:
|
166
|
+
- - ">="
|
167
|
+
- !ruby/object:Gem::Version
|
168
|
+
version: '0'
|
169
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - ">="
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '0'
|
174
|
+
requirements: []
|
175
|
+
rubyforge_project:
|
176
|
+
rubygems_version: 2.4.5
|
177
|
+
signing_key:
|
178
|
+
specification_version: 4
|
179
|
+
summary: ETL processing jobs to exporting Rails model tables to Redshift
|
180
|
+
test_files: []
|