beetle_etl 0.0.1 → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +1 -1
- data/beetle_etl.gemspec +1 -2
- data/lib/beetle_etl/import.rb +5 -5
- data/lib/beetle_etl/steps/assign_ids.rb +4 -2
- data/lib/beetle_etl/steps/load.rb +14 -3
- data/lib/beetle_etl/steps/table_diff.rb +3 -3
- data/lib/beetle_etl/task_runner/dependency_resolver.rb +1 -1
- data/lib/beetle_etl/task_runner/task_runner.rb +45 -38
- data/lib/beetle_etl/version.rb +1 -1
- data/spec/steps/load_spec.rb +17 -1
- data/spec/steps/step_spec.rb +0 -1
- metadata +23 -37
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b08e51fe6819079c6b8317636030d5d678b102cc
|
4
|
+
data.tar.gz: 6afa19db3171f105fa275f99c82c07306aa9c568
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a915efc65e4450aa4ba7cec71a75b89082d6b65be4cd2e6db88ee8e540f9bc0d1db96afd18c787ac504309460447bfdbb20ab462e012ac503e8fe8cdecb65880
|
7
|
+
data.tar.gz: afc74720f9875d7a447030bb14fbc4da90c1004b5c725fb55b0630bbc073d3d15560e6c5e2b7002951e1989eb4b63b956508411811c146986820aee2679a6462
|
data/.travis.yml
CHANGED
@@ -5,7 +5,7 @@ rvm:
|
|
5
5
|
addons:
|
6
6
|
postgresql: "9.3"
|
7
7
|
code_climate:
|
8
|
-
repo_token:
|
8
|
+
repo_token: fcd6d8c28da900609a2cf903716d858621b8ce68152edbcebe6908a9a3f5d3d5
|
9
9
|
|
10
10
|
before_script:
|
11
11
|
- psql -c 'create database travis_ci_test;' -U postgres
|
data/beetle_etl.gemspec
CHANGED
@@ -19,11 +19,10 @@ Gem::Specification.new do |spec|
|
|
19
19
|
spec.require_paths = ['lib']
|
20
20
|
|
21
21
|
spec.add_runtime_dependency 'sequel', '>= 4.13.0'
|
22
|
-
spec.add_runtime_dependency 'celluloid', '>= 0.15.2'
|
23
22
|
|
24
23
|
spec.add_development_dependency 'bundler', '~> 1.6'
|
25
24
|
spec.add_development_dependency 'rake'
|
26
|
-
spec.add_development_dependency 'rspec', '~> 3.
|
25
|
+
spec.add_development_dependency 'rspec', '~> 3.1.0'
|
27
26
|
spec.add_development_dependency 'pg'
|
28
27
|
spec.add_development_dependency 'codeclimate-test-reporter'
|
29
28
|
spec.add_development_dependency 'activesupport'
|
data/lib/beetle_etl/import.rb
CHANGED
@@ -4,28 +4,28 @@ module BeetleETL
|
|
4
4
|
extend self
|
5
5
|
|
6
6
|
def run
|
7
|
-
TaskRunner.
|
7
|
+
TaskRunner.new(data_steps).run
|
8
8
|
BeetleETL.database.transaction do
|
9
|
-
load_steps.
|
9
|
+
TaskRunner.new(load_steps).run
|
10
10
|
end
|
11
11
|
end
|
12
12
|
|
13
13
|
private
|
14
14
|
|
15
15
|
def data_steps
|
16
|
-
transformations.
|
16
|
+
transformations.flat_map do |t|
|
17
17
|
[
|
18
18
|
Transform.new(t.table_name, t.dependencies, t.query),
|
19
19
|
MapRelations.new(t.table_name, t.relations),
|
20
20
|
TableDiff.new(t.table_name),
|
21
21
|
AssignIds.new(t.table_name),
|
22
22
|
]
|
23
|
-
end
|
23
|
+
end
|
24
24
|
end
|
25
25
|
|
26
26
|
def load_steps
|
27
27
|
transformations.map do |t|
|
28
|
-
Load.new(t.table_name)
|
28
|
+
Load.new(t.table_name, t.relations)
|
29
29
|
end
|
30
30
|
end
|
31
31
|
|
@@ -7,10 +7,21 @@ module BeetleETL
|
|
7
7
|
transition
|
8
8
|
]
|
9
9
|
|
10
|
+
attr_reader :relations
|
11
|
+
|
12
|
+
def initialize(table_name, relations)
|
13
|
+
super(table_name)
|
14
|
+
@relations = relations
|
15
|
+
end
|
16
|
+
|
10
17
|
def run
|
11
|
-
%w(create update delete undelete).
|
12
|
-
public_send(:"load_#{transition}")
|
13
|
-
end
|
18
|
+
%w(create update delete undelete).map do |transition|
|
19
|
+
Thread.new { public_send(:"load_#{transition}") }
|
20
|
+
end.each(&:join)
|
21
|
+
end
|
22
|
+
|
23
|
+
def dependencies
|
24
|
+
relations.values.map { |d| Load.step_name(d) }.to_set
|
14
25
|
end
|
15
26
|
|
16
27
|
def load_create
|
@@ -12,9 +12,9 @@ module BeetleETL
|
|
12
12
|
end
|
13
13
|
|
14
14
|
def run
|
15
|
-
%w(create keep update delete undelete).
|
16
|
-
public_send(:"transition_#{transition}")
|
17
|
-
end
|
15
|
+
%w(create keep update delete undelete).map do |transition|
|
16
|
+
Thread.new { public_send(:"transition_#{transition}") }
|
17
|
+
end.each(&:join)
|
18
18
|
end
|
19
19
|
|
20
20
|
def transition_create
|
@@ -1,63 +1,70 @@
|
|
1
|
-
require 'celluloid/autostart'
|
2
|
-
|
3
1
|
module BeetleETL
|
4
2
|
class TaskRunner
|
5
3
|
|
6
|
-
|
4
|
+
def initialize(tasks)
|
5
|
+
@dependency_resolver = DependencyResolver.new(tasks)
|
6
|
+
@tasks = tasks
|
7
7
|
|
8
|
-
|
9
|
-
@runnables = runnables
|
8
|
+
@queue = Queue.new
|
10
9
|
@completed = Set.new
|
11
10
|
@running = Set.new
|
12
|
-
@dependency_resolver = DependencyResolver.new(runnables)
|
13
|
-
|
14
|
-
run_next
|
15
11
|
end
|
16
12
|
|
17
|
-
def
|
18
|
-
|
19
|
-
@completed << runnable_name
|
20
|
-
|
21
|
-
run_next
|
22
|
-
end
|
13
|
+
def run
|
14
|
+
results = {}
|
23
15
|
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
resolvables.each do |runnable|
|
29
|
-
unless @running.include?(runnable.name)
|
30
|
-
Task.new(Actor.current, runnable).async.run_task
|
31
|
-
@running << runnable.name
|
32
|
-
end
|
16
|
+
until all_tasks_complete?
|
17
|
+
runnables.each do |task|
|
18
|
+
run_task_async(task)
|
19
|
+
mark_task_running(task.name)
|
33
20
|
end
|
21
|
+
|
22
|
+
task_name, task_data = @queue.pop
|
23
|
+
results[task_name] = task_data
|
24
|
+
mark_task_completed(task_name)
|
34
25
|
end
|
26
|
+
|
27
|
+
results
|
35
28
|
end
|
36
29
|
|
37
30
|
private
|
38
31
|
|
39
|
-
|
40
|
-
|
32
|
+
attr_reader :running, :completed
|
33
|
+
|
34
|
+
def run_task_async(task)
|
35
|
+
Thread.new do
|
36
|
+
started_at = now
|
37
|
+
result = task.run
|
38
|
+
finished_at = now
|
39
|
+
|
40
|
+
@queue.push [task.name, {
|
41
|
+
started_at: started_at,
|
42
|
+
finished_at: finished_at,
|
43
|
+
result: result,
|
44
|
+
}]
|
45
|
+
end
|
41
46
|
end
|
42
47
|
|
43
|
-
def
|
44
|
-
|
48
|
+
def mark_task_running(task_name)
|
49
|
+
running.add(task_name)
|
45
50
|
end
|
46
51
|
|
47
|
-
|
52
|
+
def mark_task_completed(task_name)
|
53
|
+
runnables.delete(task_name)
|
54
|
+
completed.add(task_name)
|
55
|
+
end
|
48
56
|
|
49
|
-
|
57
|
+
def runnables
|
58
|
+
resolvables = @dependency_resolver.resolvables(completed)
|
59
|
+
resolvables.reject { |r| running.include? r.name }
|
60
|
+
end
|
50
61
|
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
end
|
62
|
+
def all_tasks_complete?
|
63
|
+
@tasks.map(&:name).to_set == completed.to_set
|
64
|
+
end
|
55
65
|
|
56
|
-
|
57
|
-
|
58
|
-
@runner.async.completed(@task.name)
|
59
|
-
terminate
|
60
|
-
end
|
66
|
+
def now
|
67
|
+
Time.now
|
61
68
|
end
|
62
69
|
|
63
70
|
end
|
data/lib/beetle_etl/version.rb
CHANGED
data/spec/steps/load_spec.rb
CHANGED
@@ -13,7 +13,7 @@ module BeetleETL
|
|
13
13
|
let(:now) { Time.now.beginning_of_day }
|
14
14
|
let(:yesterday) { 1.day.ago.beginning_of_day }
|
15
15
|
|
16
|
-
subject { Load.new(:example_table) }
|
16
|
+
subject { Load.new(:example_table, []) }
|
17
17
|
|
18
18
|
before do
|
19
19
|
BeetleETL.configure do |config|
|
@@ -52,6 +52,22 @@ module BeetleETL
|
|
52
52
|
end
|
53
53
|
end
|
54
54
|
|
55
|
+
describe '#depenencies' do
|
56
|
+
it 'depends on Transform of the same table and AssignIds of its dependees' do
|
57
|
+
relations = {
|
58
|
+
dependee_a_id: :dependee_a,
|
59
|
+
dependee_b_id: :dependee_b,
|
60
|
+
}
|
61
|
+
|
62
|
+
expect(Load.new(:depender, relations).dependencies).to eql(
|
63
|
+
[
|
64
|
+
'dependee_a: Load',
|
65
|
+
'dependee_b: Load',
|
66
|
+
].to_set
|
67
|
+
)
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
55
71
|
describe '#run' do
|
56
72
|
it 'runs all load steps' do
|
57
73
|
%w(create update delete undelete).each do |transition|
|
data/spec/steps/step_spec.rb
CHANGED
metadata
CHANGED
@@ -1,125 +1,111 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: beetle_etl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Luciano Maiwald
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-
|
11
|
+
date: 2014-12-31 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: sequel
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- -
|
17
|
+
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: 4.13.0
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- -
|
24
|
+
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: 4.13.0
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: celluloid
|
29
|
-
requirement: !ruby/object:Gem::Requirement
|
30
|
-
requirements:
|
31
|
-
- - '>='
|
32
|
-
- !ruby/object:Gem::Version
|
33
|
-
version: 0.15.2
|
34
|
-
type: :runtime
|
35
|
-
prerelease: false
|
36
|
-
version_requirements: !ruby/object:Gem::Requirement
|
37
|
-
requirements:
|
38
|
-
- - '>='
|
39
|
-
- !ruby/object:Gem::Version
|
40
|
-
version: 0.15.2
|
41
27
|
- !ruby/object:Gem::Dependency
|
42
28
|
name: bundler
|
43
29
|
requirement: !ruby/object:Gem::Requirement
|
44
30
|
requirements:
|
45
|
-
- - ~>
|
31
|
+
- - "~>"
|
46
32
|
- !ruby/object:Gem::Version
|
47
33
|
version: '1.6'
|
48
34
|
type: :development
|
49
35
|
prerelease: false
|
50
36
|
version_requirements: !ruby/object:Gem::Requirement
|
51
37
|
requirements:
|
52
|
-
- - ~>
|
38
|
+
- - "~>"
|
53
39
|
- !ruby/object:Gem::Version
|
54
40
|
version: '1.6'
|
55
41
|
- !ruby/object:Gem::Dependency
|
56
42
|
name: rake
|
57
43
|
requirement: !ruby/object:Gem::Requirement
|
58
44
|
requirements:
|
59
|
-
- -
|
45
|
+
- - ">="
|
60
46
|
- !ruby/object:Gem::Version
|
61
47
|
version: '0'
|
62
48
|
type: :development
|
63
49
|
prerelease: false
|
64
50
|
version_requirements: !ruby/object:Gem::Requirement
|
65
51
|
requirements:
|
66
|
-
- -
|
52
|
+
- - ">="
|
67
53
|
- !ruby/object:Gem::Version
|
68
54
|
version: '0'
|
69
55
|
- !ruby/object:Gem::Dependency
|
70
56
|
name: rspec
|
71
57
|
requirement: !ruby/object:Gem::Requirement
|
72
58
|
requirements:
|
73
|
-
- - ~>
|
59
|
+
- - "~>"
|
74
60
|
- !ruby/object:Gem::Version
|
75
|
-
version: 3.
|
61
|
+
version: 3.1.0
|
76
62
|
type: :development
|
77
63
|
prerelease: false
|
78
64
|
version_requirements: !ruby/object:Gem::Requirement
|
79
65
|
requirements:
|
80
|
-
- - ~>
|
66
|
+
- - "~>"
|
81
67
|
- !ruby/object:Gem::Version
|
82
|
-
version: 3.
|
68
|
+
version: 3.1.0
|
83
69
|
- !ruby/object:Gem::Dependency
|
84
70
|
name: pg
|
85
71
|
requirement: !ruby/object:Gem::Requirement
|
86
72
|
requirements:
|
87
|
-
- -
|
73
|
+
- - ">="
|
88
74
|
- !ruby/object:Gem::Version
|
89
75
|
version: '0'
|
90
76
|
type: :development
|
91
77
|
prerelease: false
|
92
78
|
version_requirements: !ruby/object:Gem::Requirement
|
93
79
|
requirements:
|
94
|
-
- -
|
80
|
+
- - ">="
|
95
81
|
- !ruby/object:Gem::Version
|
96
82
|
version: '0'
|
97
83
|
- !ruby/object:Gem::Dependency
|
98
84
|
name: codeclimate-test-reporter
|
99
85
|
requirement: !ruby/object:Gem::Requirement
|
100
86
|
requirements:
|
101
|
-
- -
|
87
|
+
- - ">="
|
102
88
|
- !ruby/object:Gem::Version
|
103
89
|
version: '0'
|
104
90
|
type: :development
|
105
91
|
prerelease: false
|
106
92
|
version_requirements: !ruby/object:Gem::Requirement
|
107
93
|
requirements:
|
108
|
-
- -
|
94
|
+
- - ">="
|
109
95
|
- !ruby/object:Gem::Version
|
110
96
|
version: '0'
|
111
97
|
- !ruby/object:Gem::Dependency
|
112
98
|
name: activesupport
|
113
99
|
requirement: !ruby/object:Gem::Requirement
|
114
100
|
requirements:
|
115
|
-
- -
|
101
|
+
- - ">="
|
116
102
|
- !ruby/object:Gem::Version
|
117
103
|
version: '0'
|
118
104
|
type: :development
|
119
105
|
prerelease: false
|
120
106
|
version_requirements: !ruby/object:Gem::Requirement
|
121
107
|
requirements:
|
122
|
-
- -
|
108
|
+
- - ">="
|
123
109
|
- !ruby/object:Gem::Version
|
124
110
|
version: '0'
|
125
111
|
description: Taking care of synchronizing external data with referential data in your
|
@@ -130,8 +116,8 @@ executables: []
|
|
130
116
|
extensions: []
|
131
117
|
extra_rdoc_files: []
|
132
118
|
files:
|
133
|
-
- .gitignore
|
134
|
-
- .travis.yml
|
119
|
+
- ".gitignore"
|
120
|
+
- ".travis.yml"
|
135
121
|
- Gemfile
|
136
122
|
- LICENSE.txt
|
137
123
|
- README.md
|
@@ -183,17 +169,17 @@ require_paths:
|
|
183
169
|
- lib
|
184
170
|
required_ruby_version: !ruby/object:Gem::Requirement
|
185
171
|
requirements:
|
186
|
-
- -
|
172
|
+
- - ">="
|
187
173
|
- !ruby/object:Gem::Version
|
188
174
|
version: '0'
|
189
175
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
190
176
|
requirements:
|
191
|
-
- -
|
177
|
+
- - ">="
|
192
178
|
- !ruby/object:Gem::Version
|
193
179
|
version: '0'
|
194
180
|
requirements: []
|
195
181
|
rubyforge_project:
|
196
|
-
rubygems_version: 2.
|
182
|
+
rubygems_version: 2.4.5
|
197
183
|
signing_key:
|
198
184
|
specification_version: 4
|
199
185
|
summary: BeetleETL helps you with your recurring ETL imports.
|