data_keeper 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.travis.yml +6 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +111 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/data_keeper.gemspec +31 -0
- data/lib/data_keeper.rb +61 -0
- data/lib/data_keeper/database_config.rb +31 -0
- data/lib/data_keeper/database_helper.rb +24 -0
- data/lib/data_keeper/definition.rb +62 -0
- data/lib/data_keeper/dumper.rb +143 -0
- data/lib/data_keeper/error.rb +3 -0
- data/lib/data_keeper/loader.rb +161 -0
- data/lib/data_keeper/local_storage.rb +46 -0
- data/lib/data_keeper/railtie.rb +10 -0
- data/lib/data_keeper/tasks/data_keeper.rake +38 -0
- data/lib/data_keeper/version.rb +3 -0
- data/todo.md +14 -0
- metadata +121 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 9c4e8095729b6927bc11ae296fc30571577d1dfd5f5d910b1092f924981efa69
|
4
|
+
data.tar.gz: bb646294c8847fd637b765fd6a2f16af605dabe656b663d2cb0e6f54ff396f79
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: cd3696d94b9ef70bf108e8c77ee880e1b97e68989955c6c7975b4f9cea9196b95417a17e6b5bf6e3a9baf2047cd0a1db524e2bc8dd660d2576f10385f38a038d
|
7
|
+
data.tar.gz: 1ecab9088e179625113bb3a490a83c60a16405924f527caa059ed1dc05c68527049f12cc985aa1280f6e094597903f5bf280420a21c98a1670eb527b4e766c52
|
data/.gitignore
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) 2020 Roger Campos
|
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 +1,111 @@
|
|
1
|
+
# DataKeeper
|
2
|
+
|
3
|
+
In a rails app using postgresql, DataKeeper is a tool to create dumps of your database in production to be used later on for local development.
|
4
|
+
|
5
|
+
It automates the process of creating and storing them on the server, and applying them locally afterwards.
|
6
|
+
|
7
|
+
It supports full dumps, as well as partial dumps per specific tables or even specific rows (you provide a sql select).
|
8
|
+
On partial dumps, note you'll need to manage possible issues around foreign keys and maybe other constraints.
|
9
|
+
|
10
|
+
## Installation
|
11
|
+
|
12
|
+
Add this line to your application's Gemfile:
|
13
|
+
|
14
|
+
```ruby
|
15
|
+
gem 'data_keeper'
|
16
|
+
```
|
17
|
+
|
18
|
+
And then execute:
|
19
|
+
|
20
|
+
$ bundle install
|
21
|
+
|
22
|
+
Or install it yourself as:
|
23
|
+
|
24
|
+
$ gem install data_keeper
|
25
|
+
|
26
|
+
## Usage
|
27
|
+
|
28
|
+
Configure the storage to use to save the generated dumps.
|
29
|
+
|
30
|
+
You can use a local storage, a simple option which stores the dumps in the same server running the code,
|
31
|
+
in a path of your choosing (consider that it must be writable by the user running this code in production).
|
32
|
+
You also configure how to reach that server from your local machine (currently only scp is supported), in
|
33
|
+
order to download these dumps later. Ex:
|
34
|
+
|
35
|
+
```ruby
|
36
|
+
DataKeeper.storage = DataKeeper::LocalStorage.new(
|
37
|
+
local_store_dir: "/users/fredy/backups/...",
|
38
|
+
remote_access: {
|
39
|
+
type: "scp",
|
40
|
+
host: "141.12.241.22",
|
41
|
+
port: "8622",
|
42
|
+
user: "fredy"
|
43
|
+
}
|
44
|
+
)
|
45
|
+
```
|
46
|
+
|
47
|
+
Other storages, like S3, could be implemented, but currently this gem only ships with local storage.
|
48
|
+
If you want to do your own, you can assign as an storage whatever object that responds to:
|
49
|
+
|
50
|
+
- `#save(file, filename, dump_name)`, where file is a File object and filename a string. This method should save the given
|
51
|
+
dump file.
|
52
|
+
|
53
|
+
- `#retrieve(dump_name) { |file| (...) }`, which should retrieve the latest stored dump with the given dump_name.
|
54
|
+
It should yield the given block passing the File object pointing to the retrieved dump file in the local filesystem,
|
55
|
+
which is expected to be cleaned up on block termination.
|
56
|
+
|
57
|
+
|
58
|
+
Then, declare some dumps to work with:
|
59
|
+
|
60
|
+
```ruby
|
61
|
+
# Dump the whole database
|
62
|
+
DataKeeper.define_dump(:whole_database, :full)
|
63
|
+
|
64
|
+
# Dump only selected tables, and a custom SQL
|
65
|
+
DataKeeper.define_dump(:config) do |d|
|
66
|
+
# Specific tables, all rows
|
67
|
+
d.table "products"
|
68
|
+
d.table "traits"
|
69
|
+
|
70
|
+
# Only some rows in the "vouchers" table. MAKE SURE your sql returns only columns from the target table!
|
71
|
+
d.sql(:vouchers, :used_vouchers) { Voucher.joins(cart: :order).where(orders: {status: "sent"}).to_sql }
|
72
|
+
|
73
|
+
# Possible additional code to run after applying the dump locally
|
74
|
+
d.on_after_load do
|
75
|
+
User.create! email: "test@gmail.com", password: "password"
|
76
|
+
end
|
77
|
+
end
|
78
|
+
```
|
79
|
+
|
80
|
+
Now, in production, you'll have run `DataKeeper.create_dump!("config")`, passing in the same of the dump
|
81
|
+
you defined before. Running this will create the dump file, from the server you run this code from,
|
82
|
+
and store it in the configured storage.
|
83
|
+
|
84
|
+
If you want to have always an up-to-date dump, you'll need to call this periodically, for example once per day.
|
85
|
+
|
86
|
+
Finally, to apply the dump locally, you can use the rake task:
|
87
|
+
|
88
|
+
`bin/rake data_keeper:pull[config]`
|
89
|
+
|
90
|
+
This will download the latest version available of the "config" dump, and apply it locally, destroying anything
|
91
|
+
in your current database. It will give you an error if you try to run this in a production environment.
|
92
|
+
|
93
|
+
Note when using raw sql, your statement is expected to return all columns for the configured table, in the default
|
94
|
+
order (`select *`). This uses pg's COPY from/to for the full table internally.
|
95
|
+
|
96
|
+
## Development
|
97
|
+
|
98
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
99
|
+
|
100
|
+
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`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
101
|
+
|
102
|
+
## Contributing
|
103
|
+
|
104
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/data_keeper.
|
105
|
+
|
106
|
+
|
107
|
+
## License
|
108
|
+
|
109
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
110
|
+
|
111
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "data_keeper"
|
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(__FILE__)
|
data/bin/setup
ADDED
data/data_keeper.gemspec
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
require_relative 'lib/data_keeper/version'
|
2
|
+
|
3
|
+
Gem::Specification.new do |spec|
|
4
|
+
spec.name = "data_keeper"
|
5
|
+
spec.version = DataKeeper::VERSION
|
6
|
+
spec.authors = ["Roger Campos"]
|
7
|
+
spec.email = ["roger@rogercampos.com"]
|
8
|
+
|
9
|
+
spec.summary = %q{Easy management of database dumps for dev env}
|
10
|
+
spec.description = %q{Easy management of database dumps for dev env}
|
11
|
+
spec.homepage = "https://github.com/rogercampos/data_keeper"
|
12
|
+
spec.license = "MIT"
|
13
|
+
spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
14
|
+
|
15
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
16
|
+
|
17
|
+
# Specify which files should be added to the gem when it is released.
|
18
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
19
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
20
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
21
|
+
end
|
22
|
+
spec.bindir = "exe"
|
23
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
24
|
+
spec.require_paths = ["lib"]
|
25
|
+
|
26
|
+
spec.add_dependency "activerecord", ">= 5.2.0"
|
27
|
+
spec.add_dependency "terrapin", ">= 0.5.0"
|
28
|
+
spec.add_dependency "sshkit", ">= 1.20.0"
|
29
|
+
spec.add_dependency "rails", ">= 5.0.0"
|
30
|
+
|
31
|
+
end
|
data/lib/data_keeper.rb
ADDED
@@ -0,0 +1,61 @@
|
|
1
|
+
require "data_keeper/version"
|
2
|
+
require "terrapin"
|
3
|
+
require "zlib"
|
4
|
+
require "rubygems/package"
|
5
|
+
|
6
|
+
require 'data_keeper/error'
|
7
|
+
require 'data_keeper/definition'
|
8
|
+
require 'data_keeper/dumper'
|
9
|
+
require 'data_keeper/loader'
|
10
|
+
require 'data_keeper/local_storage'
|
11
|
+
require 'data_keeper/database_helper'
|
12
|
+
require 'data_keeper/railtie' if defined?(Rails) && defined?(Rails::Railtie)
|
13
|
+
|
14
|
+
module DataKeeper
|
15
|
+
DumpDoesNotExist = Class.new(Error)
|
16
|
+
NoStorageDefined = Class.new(Error)
|
17
|
+
|
18
|
+
@dumps = {}
|
19
|
+
@storage = nil
|
20
|
+
|
21
|
+
def self.define_dump(name, type = :partial, &block)
|
22
|
+
@dumps[name.to_sym] = DefinitionBuilder.build(type, block)
|
23
|
+
end
|
24
|
+
|
25
|
+
def self.create_dump!(name)
|
26
|
+
raise DumpDoesNotExist unless dump?(name)
|
27
|
+
raise NoStorageDefined if @storage.nil?
|
28
|
+
|
29
|
+
Dumper.new(name, @dumps[name.to_sym]).run! do |file, filename|
|
30
|
+
@storage.save(file, filename, name)
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
def self.fetch_and_load_dump!(name)
|
35
|
+
raise DumpDoesNotExist unless dump?(name)
|
36
|
+
raise NoStorageDefined if @storage.nil?
|
37
|
+
|
38
|
+
@storage.retrieve(name) do |file|
|
39
|
+
Loader.new(@dumps[name.to_sym], file).load!
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
def self.load_dump!(name, path)
|
44
|
+
raise DumpDoesNotExist unless File.file?(path)
|
45
|
+
raise NoStorageDefined if @storage.nil?
|
46
|
+
|
47
|
+
Loader.new(@dumps[name.to_sym], File.open(path)).load!
|
48
|
+
end
|
49
|
+
|
50
|
+
def self.dump?(name)
|
51
|
+
@dumps.key?(name.to_sym)
|
52
|
+
end
|
53
|
+
|
54
|
+
def self.storage=(value)
|
55
|
+
@storage = value
|
56
|
+
end
|
57
|
+
|
58
|
+
def self.clear_dumps!
|
59
|
+
@dumps = {}
|
60
|
+
end
|
61
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
module DataKeeper
|
2
|
+
module DatabaseConfig
|
3
|
+
def database_connection_config
|
4
|
+
Rails.configuration.database_configuration[Rails.env]
|
5
|
+
end
|
6
|
+
|
7
|
+
def psql_env
|
8
|
+
env = { 'PGUSER' => database_connection_config['username'] }
|
9
|
+
env['PGPASSWORD'] = database_connection_config['password'] if database_connection_config['password']
|
10
|
+
env
|
11
|
+
end
|
12
|
+
|
13
|
+
def host
|
14
|
+
database_connection_config['host'] || '127.0.0.1'
|
15
|
+
end
|
16
|
+
|
17
|
+
def database
|
18
|
+
database_connection_config['database']
|
19
|
+
end
|
20
|
+
|
21
|
+
def port
|
22
|
+
database_connection_config['port']
|
23
|
+
end
|
24
|
+
|
25
|
+
def connection_args
|
26
|
+
connection_opts = '--host=:host'
|
27
|
+
connection_opts += ' --port=:port' if database_connection_config['port']
|
28
|
+
connection_opts
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module DataKeeper
|
2
|
+
class DatabaseHelper
|
3
|
+
include DatabaseConfig
|
4
|
+
|
5
|
+
def kill
|
6
|
+
cmd = Terrapin::CommandLine.new(
|
7
|
+
'psql',
|
8
|
+
"-c :command #{connection_args} --dbname #{database} &> /dev/null || true",
|
9
|
+
environment: psql_env
|
10
|
+
)
|
11
|
+
|
12
|
+
cmd.run(
|
13
|
+
database: database,
|
14
|
+
host: host,
|
15
|
+
port: port,
|
16
|
+
command: "SELECT pid, pg_terminate_backend(pid) as terminated FROM pg_stat_activity WHERE pid <> pg_backend_pid();"
|
17
|
+
)
|
18
|
+
end
|
19
|
+
|
20
|
+
def self.kill
|
21
|
+
new.kill
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
module DataKeeper
|
2
|
+
InvalidDumpType = Class.new(Error)
|
3
|
+
InvalidDumpDefinition = Class.new(Error)
|
4
|
+
|
5
|
+
class Definition
|
6
|
+
attr_reader :type, :on_after_load_block
|
7
|
+
|
8
|
+
def initialize(type, tables, sqls, on_after_load_block)
|
9
|
+
@type = type
|
10
|
+
@tables = tables
|
11
|
+
@sqls = sqls
|
12
|
+
@on_after_load_block = on_after_load_block
|
13
|
+
end
|
14
|
+
|
15
|
+
def full_tables
|
16
|
+
@tables
|
17
|
+
end
|
18
|
+
|
19
|
+
def sqls
|
20
|
+
@sqls
|
21
|
+
end
|
22
|
+
|
23
|
+
def full_tables_to_export
|
24
|
+
full_tables + ['schema_migrations']
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
class DefinitionBuilder
|
29
|
+
attr_reader :tables, :raw_sqls, :on_after_load_block
|
30
|
+
|
31
|
+
def initialize(definition_block)
|
32
|
+
@tables = []
|
33
|
+
@raw_sqls = {}
|
34
|
+
instance_eval(&definition_block) if definition_block
|
35
|
+
end
|
36
|
+
|
37
|
+
def self.build(type, block)
|
38
|
+
@type = type
|
39
|
+
raise InvalidDumpType, "Invalid type! use :partial or :full" unless [:partial, :full].include?(type)
|
40
|
+
|
41
|
+
builder = new(block)
|
42
|
+
|
43
|
+
Definition.new(type, builder.tables, builder.raw_sqls, builder.on_after_load_block)
|
44
|
+
end
|
45
|
+
|
46
|
+
def table(name)
|
47
|
+
raise InvalidDumpDefinition if @type == :full
|
48
|
+
raise(InvalidDumpDefinition, "table already defined") if @tables.include?(name)
|
49
|
+
@tables << name
|
50
|
+
end
|
51
|
+
|
52
|
+
def sql(table, name, &block)
|
53
|
+
raise InvalidDumpDefinition if @type == :full
|
54
|
+
raise(InvalidDumpDefinition, "sql already defined") if @raw_sqls.key?(name)
|
55
|
+
@raw_sqls[name] = [table, block]
|
56
|
+
end
|
57
|
+
|
58
|
+
def on_after_load(&block)
|
59
|
+
@on_after_load_block = block
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
@@ -0,0 +1,143 @@
|
|
1
|
+
require 'data_keeper/database_config'
|
2
|
+
require 'tempfile'
|
3
|
+
|
4
|
+
module DataKeeper
|
5
|
+
class Dumper
|
6
|
+
include DatabaseConfig
|
7
|
+
|
8
|
+
def initialize(name, definition)
|
9
|
+
@dump_name = name
|
10
|
+
@definition = definition
|
11
|
+
end
|
12
|
+
|
13
|
+
def run!(&block)
|
14
|
+
if @definition.type == :full
|
15
|
+
dump_full_database(&block)
|
16
|
+
else
|
17
|
+
dump_partial_database(&block)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
private
|
22
|
+
|
23
|
+
def dump_full_database
|
24
|
+
Tempfile.create do |file|
|
25
|
+
cmd = Terrapin::CommandLine.new(
|
26
|
+
'pg_dump',
|
27
|
+
"#{connection_args} -x -Fc :database > :output_path",
|
28
|
+
environment: psql_env
|
29
|
+
)
|
30
|
+
|
31
|
+
cmd.run(
|
32
|
+
database: database,
|
33
|
+
host: host,
|
34
|
+
port: port,
|
35
|
+
output_path: file.path
|
36
|
+
)
|
37
|
+
|
38
|
+
yield file, "#{filename}.dump"
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
def dump_partial_database
|
43
|
+
Tempfile.create do |file|
|
44
|
+
file.binmode
|
45
|
+
|
46
|
+
Zlib::GzipWriter.wrap(file) do |gzip|
|
47
|
+
Gem::Package::TarWriter.new(gzip) do |tar|
|
48
|
+
dump_schema(tar)
|
49
|
+
dump_partial_tables(tar)
|
50
|
+
dump_sqls(tar)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
yield file, "#{filename}.tar.gz"
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def dump_sqls(tar)
|
59
|
+
@definition.sqls.each do |name, (_table, sql)|
|
60
|
+
Tempfile.create do |table_file|
|
61
|
+
cmd = Terrapin::CommandLine.new(
|
62
|
+
'psql',
|
63
|
+
"#{connection_args} -d :database -c :command > #{table_file.path}",
|
64
|
+
environment: psql_env
|
65
|
+
)
|
66
|
+
|
67
|
+
cmd.run(
|
68
|
+
database: database,
|
69
|
+
host: host,
|
70
|
+
port: port,
|
71
|
+
command: "COPY (#{sql.call}) to STDOUT DELIMITER ',' CSV HEADER"
|
72
|
+
)
|
73
|
+
|
74
|
+
tar.add_file_simple("#{name}.csv", 0644, File.size(table_file.path)) do |io|
|
75
|
+
table_file.reopen(table_file)
|
76
|
+
|
77
|
+
while !table_file.eof?
|
78
|
+
io.write(table_file.read(2048))
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
def dump_partial_tables(tar)
|
86
|
+
Tempfile.create do |tables_dump_file|
|
87
|
+
tables_dump_file.binmode
|
88
|
+
table_args = @definition.full_tables_to_export.map { |table| "-t #{table}" }.join(' ')
|
89
|
+
cmd = Terrapin::CommandLine.new(
|
90
|
+
'pg_dump',
|
91
|
+
"#{connection_args} -x -Fc :database #{table_args} > :output_path",
|
92
|
+
environment: psql_env
|
93
|
+
)
|
94
|
+
|
95
|
+
cmd.run(
|
96
|
+
database: database,
|
97
|
+
host: host,
|
98
|
+
port: port,
|
99
|
+
output_path: tables_dump_file.path
|
100
|
+
)
|
101
|
+
|
102
|
+
tar.add_file_simple("tables.dump", 0644, File.size(tables_dump_file.path)) do |io|
|
103
|
+
tables_dump_file.reopen(tables_dump_file)
|
104
|
+
|
105
|
+
while !tables_dump_file.eof?
|
106
|
+
io.write(tables_dump_file.read(2048))
|
107
|
+
end
|
108
|
+
end
|
109
|
+
end
|
110
|
+
end
|
111
|
+
|
112
|
+
def dump_schema(tar)
|
113
|
+
Tempfile.create do |schema_dump_file|
|
114
|
+
schema_dump_file.binmode
|
115
|
+
|
116
|
+
cmd = Terrapin::CommandLine.new(
|
117
|
+
'pg_dump',
|
118
|
+
"#{connection_args} -x --schema-only -Fc :database > :output_path",
|
119
|
+
environment: psql_env
|
120
|
+
)
|
121
|
+
|
122
|
+
cmd.run(
|
123
|
+
database: database,
|
124
|
+
host: host,
|
125
|
+
port: port,
|
126
|
+
output_path: schema_dump_file.path
|
127
|
+
)
|
128
|
+
|
129
|
+
tar.add_file_simple("schema.dump", 0644, File.size(schema_dump_file.path)) do |io|
|
130
|
+
schema_dump_file.reopen(schema_dump_file)
|
131
|
+
|
132
|
+
while !schema_dump_file.eof?
|
133
|
+
io.write(schema_dump_file.read(2048))
|
134
|
+
end
|
135
|
+
end
|
136
|
+
end
|
137
|
+
end
|
138
|
+
|
139
|
+
def filename
|
140
|
+
"#{@dump_name}-#{Time.now.strftime("%Y%m%d-%H%M")}"
|
141
|
+
end
|
142
|
+
end
|
143
|
+
end
|
@@ -0,0 +1,161 @@
|
|
1
|
+
require 'data_keeper/database_config'
|
2
|
+
|
3
|
+
module DataKeeper
|
4
|
+
class Loader
|
5
|
+
include DatabaseConfig
|
6
|
+
|
7
|
+
def initialize(dump, file)
|
8
|
+
@dump = dump
|
9
|
+
@file = file
|
10
|
+
end
|
11
|
+
|
12
|
+
def load!
|
13
|
+
if @dump.type == :full
|
14
|
+
load_full_database!
|
15
|
+
else
|
16
|
+
load_partial_database!
|
17
|
+
end
|
18
|
+
|
19
|
+
if @dump.on_after_load_block
|
20
|
+
@dump.on_after_load_block.call
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
private
|
25
|
+
|
26
|
+
def load_full_database!
|
27
|
+
pg_restore = Terrapin::CommandLine.new(
|
28
|
+
'pg_restore',
|
29
|
+
"#{connection_args} -j 4 --no-owner --dbname #{database} #{@file.path} 2>/dev/null",
|
30
|
+
environment: psql_env
|
31
|
+
)
|
32
|
+
|
33
|
+
pg_restore.run(
|
34
|
+
database: database,
|
35
|
+
host: host,
|
36
|
+
port: port
|
37
|
+
)
|
38
|
+
|
39
|
+
cmd = Terrapin::CommandLine.new(
|
40
|
+
'psql',
|
41
|
+
"#{connection_args} -d :database -c :sql",
|
42
|
+
environment: psql_env
|
43
|
+
)
|
44
|
+
|
45
|
+
cmd.run(
|
46
|
+
database: database,
|
47
|
+
host: host,
|
48
|
+
port: port,
|
49
|
+
sql: "UPDATE ar_internal_metadata SET value = 'development'"
|
50
|
+
)
|
51
|
+
end
|
52
|
+
|
53
|
+
def load_partial_database!
|
54
|
+
inflate(@file.path) do |schema_path, tables_path, sql_files|
|
55
|
+
pg_restore = Terrapin::CommandLine.new(
|
56
|
+
'pg_restore',
|
57
|
+
"#{connection_args} -j 4 --no-owner --dbname #{database} #{schema_path} 2>/dev/null",
|
58
|
+
environment: psql_env
|
59
|
+
)
|
60
|
+
|
61
|
+
pg_restore.run(
|
62
|
+
database: database,
|
63
|
+
host: host,
|
64
|
+
port: port
|
65
|
+
)
|
66
|
+
|
67
|
+
pg_restore = Terrapin::CommandLine.new(
|
68
|
+
'pg_restore',
|
69
|
+
"#{connection_args} -c -j 4 --no-owner --dbname #{database} #{tables_path} 2>/dev/null",
|
70
|
+
environment: psql_env
|
71
|
+
)
|
72
|
+
|
73
|
+
pg_restore.run(
|
74
|
+
database: database,
|
75
|
+
host: host,
|
76
|
+
port: port
|
77
|
+
)
|
78
|
+
|
79
|
+
sql_files.each do |table, csv_path|
|
80
|
+
cmd = Terrapin::CommandLine.new(
|
81
|
+
'psql',
|
82
|
+
"#{connection_args} -d :database -c :command < :csv_path",
|
83
|
+
environment: psql_env
|
84
|
+
)
|
85
|
+
|
86
|
+
cmd.run(
|
87
|
+
database: database,
|
88
|
+
host: host,
|
89
|
+
port: port,
|
90
|
+
csv_path: csv_path,
|
91
|
+
command: "COPY #{table} FROM stdin DELIMITER ',' CSV HEADER"
|
92
|
+
)
|
93
|
+
end
|
94
|
+
|
95
|
+
Rake::Task['db:environment:set'].invoke
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
class InflatedFiles
|
100
|
+
attr_reader :errors
|
101
|
+
|
102
|
+
def initialize(dump, paths)
|
103
|
+
@dump = dump
|
104
|
+
@paths = paths
|
105
|
+
@errors = []
|
106
|
+
end
|
107
|
+
|
108
|
+
def valid?
|
109
|
+
@errors = []
|
110
|
+
|
111
|
+
validate("Schema file is missing") { !!schema_path } &&
|
112
|
+
validate("Tables file is missing") { !!tables_path } &&
|
113
|
+
validate("Not all sql custom dumps are present") do
|
114
|
+
sql_dumps.size == @dump.sqls.keys.size
|
115
|
+
end
|
116
|
+
end
|
117
|
+
|
118
|
+
def schema_path
|
119
|
+
@schema_path ||= @paths.find { |x| File.basename(x) == "schema.dump" }
|
120
|
+
end
|
121
|
+
|
122
|
+
def tables_path
|
123
|
+
@tables_path ||= @paths.find { |x| File.basename(x) == "tables.dump" }
|
124
|
+
end
|
125
|
+
|
126
|
+
def sql_dumps
|
127
|
+
@sql_dumps ||= @dump.sqls.map do |name, (table, _proc)|
|
128
|
+
path = @paths.find { |x| File.basename(x) == "#{name}.csv" }
|
129
|
+
next unless path
|
130
|
+
|
131
|
+
[table, path]
|
132
|
+
end.compact
|
133
|
+
end
|
134
|
+
|
135
|
+
private
|
136
|
+
|
137
|
+
def validate(error_message)
|
138
|
+
result = yield
|
139
|
+
@errors << error_message unless result
|
140
|
+
result
|
141
|
+
end
|
142
|
+
end
|
143
|
+
|
144
|
+
def inflate(path)
|
145
|
+
Dir.mktmpdir do |dir|
|
146
|
+
File.open(path, "rb") do |f|
|
147
|
+
Gem::Package.new("").extract_tar_gz(f, dir)
|
148
|
+
|
149
|
+
inflated_files = InflatedFiles.new(@dump, Dir.glob(File.join(dir, "*")))
|
150
|
+
raise inflated_files.errors.join(", ") unless inflated_files.valid?
|
151
|
+
|
152
|
+
yield(
|
153
|
+
inflated_files.schema_path,
|
154
|
+
inflated_files.tables_path,
|
155
|
+
inflated_files.sql_dumps
|
156
|
+
)
|
157
|
+
end
|
158
|
+
end
|
159
|
+
end
|
160
|
+
end
|
161
|
+
end
|
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'sshkit'
|
2
|
+
require 'tempfile'
|
3
|
+
require 'fileutils'
|
4
|
+
|
5
|
+
module DataKeeper
|
6
|
+
class LocalStorage
|
7
|
+
include SSHKit::DSL
|
8
|
+
|
9
|
+
def initialize(data)
|
10
|
+
@local_store_dir = data[:local_store_dir]
|
11
|
+
@remote_access = data[:remote_access]
|
12
|
+
end
|
13
|
+
|
14
|
+
def save(file, filename, dump_name)
|
15
|
+
path = dump_path(dump_name, filename)
|
16
|
+
FileUtils.mkdir_p(File.dirname(path))
|
17
|
+
|
18
|
+
FileUtils.cp(file.path, path)
|
19
|
+
end
|
20
|
+
|
21
|
+
def retrieve(dump_name)
|
22
|
+
tempfile = Tempfile.new
|
23
|
+
local_store_dir = @local_store_dir
|
24
|
+
|
25
|
+
on complete_host do
|
26
|
+
last_dump = capture :ls, "-1t #{File.join(local_store_dir, dump_name.to_s)} | head -n 1"
|
27
|
+
|
28
|
+
download! File.join(local_store_dir, dump_name.to_s, last_dump), tempfile.path
|
29
|
+
end
|
30
|
+
|
31
|
+
yield(tempfile)
|
32
|
+
ensure
|
33
|
+
tempfile.delete
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
def complete_host
|
39
|
+
"#{@remote_access[:user]}@#{@remote_access[:host]}:#{@remote_access[:port]}"
|
40
|
+
end
|
41
|
+
|
42
|
+
def dump_path(dump_name, filename)
|
43
|
+
File.join(@local_store_dir, dump_name.to_s, filename)
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
namespace :data_keeper do
|
2
|
+
task :kill do
|
3
|
+
raise "Cannot be run in production!" if Rails.env.production?
|
4
|
+
|
5
|
+
DataKeeper::DatabaseHelper.kill
|
6
|
+
end
|
7
|
+
|
8
|
+
desc "Fetches and loads the given dump in your local database. WARN: Will remove all your current data."
|
9
|
+
task :pull, [:name] => [:kill, "db:drop", "db:create"] do |_t, args|
|
10
|
+
raise "NOT IN PRODUCTION" if Rails.env.production?
|
11
|
+
|
12
|
+
name = args[:name]
|
13
|
+
|
14
|
+
if name.blank? || !DataKeeper.dump?(name)
|
15
|
+
raise "Please use this rake task giving a name of a configured dump. Ex: bin/rake data_keeper:pull[full]"
|
16
|
+
end
|
17
|
+
|
18
|
+
DataKeeper.fetch_and_load_dump!(name)
|
19
|
+
end
|
20
|
+
|
21
|
+
desc "Loads the given dump (found on the given local path) and applies it to your local database. WARN: Will remove all your current data."
|
22
|
+
task :load, [:name, :path] => [:kill, "db:drop", "db:create"] do |_t, args|
|
23
|
+
raise "NOT IN PRODUCTION" if Rails.env.production?
|
24
|
+
|
25
|
+
name = args[:name]
|
26
|
+
path = args[:path]
|
27
|
+
|
28
|
+
if name.blank? || !DataKeeper.dump?(name)
|
29
|
+
raise "Please use this rake task giving a name of a configured dump."
|
30
|
+
end
|
31
|
+
|
32
|
+
unless File.file?(path)
|
33
|
+
raise "The given file '#{path}' does not exist."
|
34
|
+
end
|
35
|
+
|
36
|
+
DataKeeper.load_dump!(name, path)
|
37
|
+
end
|
38
|
+
end
|
data/todo.md
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
- decouple from rails / ar
|
2
|
+
|
3
|
+
- implement partial loads. What about the structure? load from schema.rb first (db:schema:load or db:structure:apply),
|
4
|
+
then load db.
|
5
|
+
|
6
|
+
- add anonymizing feature of certain columns
|
7
|
+
|
8
|
+
- skip download if present in cache. Clear cache.
|
9
|
+
|
10
|
+
- add s3 storage
|
11
|
+
|
12
|
+
- add option to apply dump but creating tables with "create table unlogged", can be useful for performance in tests
|
13
|
+
or even locally
|
14
|
+
|
metadata
ADDED
@@ -0,0 +1,121 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: data_keeper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Roger Campos
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2020-12-09 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: 5.2.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 5.2.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: terrapin
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 0.5.0
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.5.0
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: sshkit
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: 1.20.0
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 1.20.0
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rails
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 5.0.0
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 5.0.0
|
69
|
+
description: Easy management of database dumps for dev env
|
70
|
+
email:
|
71
|
+
- roger@rogercampos.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- ".travis.yml"
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- bin/console
|
83
|
+
- bin/setup
|
84
|
+
- data_keeper.gemspec
|
85
|
+
- lib/data_keeper.rb
|
86
|
+
- lib/data_keeper/database_config.rb
|
87
|
+
- lib/data_keeper/database_helper.rb
|
88
|
+
- lib/data_keeper/definition.rb
|
89
|
+
- lib/data_keeper/dumper.rb
|
90
|
+
- lib/data_keeper/error.rb
|
91
|
+
- lib/data_keeper/loader.rb
|
92
|
+
- lib/data_keeper/local_storage.rb
|
93
|
+
- lib/data_keeper/railtie.rb
|
94
|
+
- lib/data_keeper/tasks/data_keeper.rake
|
95
|
+
- lib/data_keeper/version.rb
|
96
|
+
- todo.md
|
97
|
+
homepage: https://github.com/rogercampos/data_keeper
|
98
|
+
licenses:
|
99
|
+
- MIT
|
100
|
+
metadata:
|
101
|
+
homepage_uri: https://github.com/rogercampos/data_keeper
|
102
|
+
post_install_message:
|
103
|
+
rdoc_options: []
|
104
|
+
require_paths:
|
105
|
+
- lib
|
106
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 2.3.0
|
111
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
112
|
+
requirements:
|
113
|
+
- - ">="
|
114
|
+
- !ruby/object:Gem::Version
|
115
|
+
version: '0'
|
116
|
+
requirements: []
|
117
|
+
rubygems_version: 3.0.3
|
118
|
+
signing_key:
|
119
|
+
specification_version: 4
|
120
|
+
summary: Easy management of database dumps for dev env
|
121
|
+
test_files: []
|