kraps 0.8.0 → 0.10.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop.yml +9 -0
- data/CHANGELOG.md +34 -0
- data/Gemfile +4 -3
- data/README.md +29 -6
- data/lib/kraps/actions.rb +2 -1
- data/lib/kraps/job.rb +18 -0
- data/lib/kraps/runner.rb +16 -1
- data/lib/kraps/version.rb +1 -1
- data/lib/kraps/worker.rb +52 -1
- metadata +2 -45
- data/Gemfile.lock +0 -108
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6ac0098a3c2f8acf49552f5b72621619345f9b59c83edd58368d7a999605f817
|
4
|
+
data.tar.gz: 3d522dd1149b57c9dce596ea4b38aa67ba5f2bc18a96bbc2840e80096e9eb192
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e859a2ecd0e635a067bde3cf3d51f76dc64702d91975342c590a43370d5a8a49da5c2272b6806550420537c74b3c7129ee0c76f58ff42ef0b154d7e8d0904417
|
7
|
+
data.tar.gz: 8e93aa69360b48b46f96a94cc2dd49d841b72fc858688c93071d46b99b86d50bf3b0758dd7f071cb50fd6ddc13cf532ed00d1ed1e4eee277d064568a11931f22
|
data/.rubocop.yml
CHANGED
@@ -16,6 +16,12 @@ Lint/UnreachableLoop:
|
|
16
16
|
Metrics/BlockLength:
|
17
17
|
Enabled: false
|
18
18
|
|
19
|
+
Style/HashEachMethods:
|
20
|
+
Enabled: false
|
21
|
+
|
22
|
+
Style/ZeroLengthPredicate:
|
23
|
+
Enabled: false
|
24
|
+
|
19
25
|
Gemspec/RequiredRubyVersion:
|
20
26
|
Enabled: false
|
21
27
|
|
@@ -48,6 +54,9 @@ Style/StringLiteralsInInterpolation:
|
|
48
54
|
Enabled: true
|
49
55
|
EnforcedStyle: double_quotes
|
50
56
|
|
57
|
+
Style/RedundantSelfAssignment:
|
58
|
+
Enabled: false
|
59
|
+
|
51
60
|
Layout/LineLength:
|
52
61
|
Max: 250
|
53
62
|
|
data/CHANGELOG.md
CHANGED
@@ -1,5 +1,39 @@
|
|
1
1
|
# CHANGELOG
|
2
2
|
|
3
|
+
## v0.10.0
|
4
|
+
|
5
|
+
* `append` operation added
|
6
|
+
|
7
|
+
## v0.9.0
|
8
|
+
|
9
|
+
* Argments are no longer passed to the `call` method, but to the
|
10
|
+
initializer instead
|
11
|
+
|
12
|
+
Before:
|
13
|
+
|
14
|
+
```ruby
|
15
|
+
class MyJob
|
16
|
+
def call(arg1, arg2)
|
17
|
+
# ...
|
18
|
+
end
|
19
|
+
end
|
20
|
+
```
|
21
|
+
|
22
|
+
After:
|
23
|
+
|
24
|
+
```ruby
|
25
|
+
class MyJob
|
26
|
+
def initializer(arg1, arg2)
|
27
|
+
@arg1 = arg1
|
28
|
+
@arg2 = arg2
|
29
|
+
end
|
30
|
+
|
31
|
+
def call
|
32
|
+
# ...
|
33
|
+
end
|
34
|
+
end
|
35
|
+
```
|
36
|
+
|
3
37
|
## v0.8.0
|
4
38
|
|
5
39
|
* Use number of partitions of previous step for `jobs` option by default
|
data/Gemfile
CHANGED
data/README.md
CHANGED
@@ -38,16 +38,21 @@ Kraps.configure(
|
|
38
38
|
|
39
39
|
Afterwards, create a job class, which tells Kraps what your job should do.
|
40
40
|
Therefore, you create some class with a `call` method, and optionally some
|
41
|
-
arguments. Let's create a simple job, which reads
|
42
|
-
how often search queries have been searched:
|
41
|
+
arguments passed to its initializer. Let's create a simple job, which reads
|
42
|
+
search log files to analyze how often search queries have been searched:
|
43
43
|
|
44
44
|
```ruby
|
45
45
|
class SearchLogCounter
|
46
|
-
def
|
46
|
+
def initialize(start_date:, end_date:)
|
47
|
+
@start_date = start_date
|
48
|
+
@end_date = end_date
|
49
|
+
end
|
50
|
+
|
51
|
+
def call
|
47
52
|
job = Kraps::Job.new(worker: MyKrapsWorker)
|
48
53
|
|
49
54
|
job = job.parallelize(partitions: 128) do |collector|
|
50
|
-
(Date.parse(start_date)..Date.parse(end_date)).each do |date|
|
55
|
+
(Date.parse(@start_date)..Date.parse(@end_date)).each do |date|
|
51
56
|
collector.call(date.to_s)
|
52
57
|
end
|
53
58
|
end
|
@@ -214,6 +219,10 @@ job.parallelize(partitions: 128, partitioner: partitioner, worker: MyKrapsWorker
|
|
214
219
|
end
|
215
220
|
```
|
216
221
|
|
222
|
+
Please note, that `parallelize` itself is not parallelized but rather
|
223
|
+
parallelizes the data you feed into Kraps within `parallelize` by splitting it
|
224
|
+
into the number of `partitions` specified.
|
225
|
+
|
217
226
|
The block must use the collector to feed Kraps with individual items. The
|
218
227
|
items are used as keys and the values are set to `nil`.
|
219
228
|
|
@@ -267,6 +276,15 @@ The `key` itself is also passed to the block for the case that you need to
|
|
267
276
|
customize the reduce calculation according to the value of the key. However,
|
268
277
|
most of the time, this is not neccessary and the key can simply be ignored.
|
269
278
|
|
279
|
+
* `append`: Appends the results of 2 jobs, such that all key-value pairs
|
280
|
+
of both jobs will be in the result. `append` does not accept any block.
|
281
|
+
|
282
|
+
```ruby
|
283
|
+
job.append(other_job, worker: MyKrapsWorker, jobs: 8)
|
284
|
+
```
|
285
|
+
Please note that the partitioners and the number of partitions must match for
|
286
|
+
the jobs to be appended.
|
287
|
+
|
270
288
|
* `combine`: Combines the results of 2 jobs by combining every key available
|
271
289
|
in the current job result with the corresponding key from the passed job
|
272
290
|
result. When the passed job result does not have the corresponding key,
|
@@ -345,11 +363,16 @@ of searches made:
|
|
345
363
|
|
346
364
|
```ruby
|
347
365
|
class SearchLogCounter
|
348
|
-
def
|
366
|
+
def initialize(start_date:, end_date:)
|
367
|
+
@start_date = start_date
|
368
|
+
@end_date = end_date
|
369
|
+
end
|
370
|
+
|
371
|
+
def call
|
349
372
|
count_job = Kraps::Job.new(worker: SomeBackgroundWorker)
|
350
373
|
|
351
374
|
count_job = count_job.parallelize(partitions: 128) do |collector|
|
352
|
-
(Date.parse(start_date)..Date.parse(end_date)).each do |date|
|
375
|
+
(Date.parse(@start_date)..Date.parse(@end_date)).each do |date|
|
353
376
|
collector.call(date.to_s)
|
354
377
|
end
|
355
378
|
end
|
data/lib/kraps/actions.rb
CHANGED
data/lib/kraps/job.rb
CHANGED
@@ -103,6 +103,24 @@ module Kraps
|
|
103
103
|
end
|
104
104
|
end
|
105
105
|
|
106
|
+
def append(other_job, jobs: nil, worker: @worker, before: nil, &block)
|
107
|
+
fresh.tap do |job|
|
108
|
+
job.instance_eval do
|
109
|
+
@steps << Step.new(
|
110
|
+
action: Actions::APPEND,
|
111
|
+
jobs: [jobs, @partitions].compact.min,
|
112
|
+
partitions: @partitions,
|
113
|
+
partitioner: @partitioner,
|
114
|
+
worker: worker,
|
115
|
+
before: before,
|
116
|
+
block: block,
|
117
|
+
dependency: other_job,
|
118
|
+
options: { append_step_index: other_job.steps.size - 1 }
|
119
|
+
)
|
120
|
+
end
|
121
|
+
end
|
122
|
+
end
|
123
|
+
|
106
124
|
def each_partition(jobs: nil, worker: @worker, before: nil, &block)
|
107
125
|
fresh.tap do |job|
|
108
126
|
job.instance_eval do
|
data/lib/kraps/runner.rb
CHANGED
@@ -5,7 +5,7 @@ module Kraps
|
|
5
5
|
end
|
6
6
|
|
7
7
|
def call(*args, **kwargs)
|
8
|
-
JobResolver.new.call(@klass.new
|
8
|
+
JobResolver.new.call(@klass.new(*args, **kwargs).call).tap do |jobs|
|
9
9
|
jobs.each_with_index do |job, job_index|
|
10
10
|
job.steps.each_with_index.inject(nil) do |frame, (_, step_index)|
|
11
11
|
StepRunner.new(
|
@@ -91,6 +91,21 @@ module Kraps
|
|
91
91
|
Frame.new(token: token, partitions: @step.partitions)
|
92
92
|
end
|
93
93
|
|
94
|
+
def perform_append
|
95
|
+
append_job = @step.dependency
|
96
|
+
append_step = append_job.steps[@step.options[:append_step_index]]
|
97
|
+
|
98
|
+
raise(IncompatibleFrame, "Incompatible number of partitions") if append_step.partitions != @step.partitions
|
99
|
+
|
100
|
+
enum = (0...@frame.partitions).map do |partition|
|
101
|
+
{ partition: partition, append_frame: append_step.frame.to_h }
|
102
|
+
end
|
103
|
+
|
104
|
+
token = push_and_wait(job_count: @step.jobs, enum: enum)
|
105
|
+
|
106
|
+
Frame.new(token: token, partitions: @step.partitions)
|
107
|
+
end
|
108
|
+
|
94
109
|
def perform_each_partition
|
95
110
|
enum = (0...@frame.partitions).map { |partition| { partition: partition } }
|
96
111
|
push_and_wait(job_count: @step.jobs, enum: enum)
|
data/lib/kraps/version.rb
CHANGED
data/lib/kraps/worker.rb
CHANGED
@@ -86,6 +86,57 @@ module Kraps
|
|
86
86
|
temp_paths&.delete
|
87
87
|
end
|
88
88
|
|
89
|
+
def perform_append(payload)
|
90
|
+
temp_paths1 = download_all(token: @args["frame"]["token"], partition: payload["partition"])
|
91
|
+
temp_paths2 = download_all(token: payload["append_frame"]["token"], partition: payload["partition"])
|
92
|
+
|
93
|
+
implementation = Object.new
|
94
|
+
implementation.define_singleton_method(:map) do |key, value, &block|
|
95
|
+
block.call(key, value)
|
96
|
+
end
|
97
|
+
|
98
|
+
subsequent_step = next_step
|
99
|
+
|
100
|
+
if subsequent_step&.action == Actions::REDUCE
|
101
|
+
implementation.define_singleton_method(:reduce) do |key, value1, value2|
|
102
|
+
subsequent_step.block.call(key, value1, value2)
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
mapper = MapReduce::Mapper.new(implementation, partitioner: partitioner, memory_limit: @memory_limit)
|
107
|
+
|
108
|
+
temp_paths1.each do |temp_path|
|
109
|
+
File.open(temp_path.path) do |stream|
|
110
|
+
stream.each_line do |line|
|
111
|
+
key, value = JSON.parse(line)
|
112
|
+
|
113
|
+
mapper.map(key, value)
|
114
|
+
end
|
115
|
+
end
|
116
|
+
end
|
117
|
+
|
118
|
+
temp_paths2.each do |temp_path|
|
119
|
+
File.open(temp_path.path) do |stream|
|
120
|
+
stream.each_line do |line|
|
121
|
+
key, value = JSON.parse(line)
|
122
|
+
|
123
|
+
mapper.map(key, value)
|
124
|
+
end
|
125
|
+
end
|
126
|
+
end
|
127
|
+
|
128
|
+
mapper.shuffle(chunk_limit: @chunk_limit) do |partitions|
|
129
|
+
Parallelizer.each(partitions.to_a, @concurrency) do |partition, path|
|
130
|
+
File.open(path) do |stream|
|
131
|
+
Kraps.driver.store(Kraps.driver.with_prefix("#{@args["token"]}/#{partition}/chunk.#{payload["partition"]}.json"), stream)
|
132
|
+
end
|
133
|
+
end
|
134
|
+
end
|
135
|
+
ensure
|
136
|
+
temp_paths1&.delete
|
137
|
+
temp_paths2&.delete
|
138
|
+
end
|
139
|
+
|
89
140
|
def perform_map_partitions(payload)
|
90
141
|
temp_paths = download_all(token: @args["frame"]["token"], partition: payload["partition"])
|
91
142
|
|
@@ -274,7 +325,7 @@ module Kraps
|
|
274
325
|
end
|
275
326
|
|
276
327
|
def jobs
|
277
|
-
@jobs ||= JobResolver.new.call(@args["klass"].constantize.new
|
328
|
+
@jobs ||= JobResolver.new.call(@args["klass"].constantize.new(*@args["args"], **@args["kwargs"].transform_keys(&:to_sym)).call)
|
278
329
|
end
|
279
330
|
|
280
331
|
def job
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: kraps
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.10.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Benjamin Vetter
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2024-04-09 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: attachie
|
@@ -66,48 +66,6 @@ dependencies:
|
|
66
66
|
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '0'
|
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: rspec
|
85
|
-
requirement: !ruby/object:Gem::Requirement
|
86
|
-
requirements:
|
87
|
-
- - ">="
|
88
|
-
- !ruby/object:Gem::Version
|
89
|
-
version: '0'
|
90
|
-
type: :development
|
91
|
-
prerelease: false
|
92
|
-
version_requirements: !ruby/object:Gem::Requirement
|
93
|
-
requirements:
|
94
|
-
- - ">="
|
95
|
-
- !ruby/object:Gem::Version
|
96
|
-
version: '0'
|
97
|
-
- !ruby/object:Gem::Dependency
|
98
|
-
name: rubocop
|
99
|
-
requirement: !ruby/object:Gem::Requirement
|
100
|
-
requirements:
|
101
|
-
- - ">="
|
102
|
-
- !ruby/object:Gem::Version
|
103
|
-
version: '0'
|
104
|
-
type: :development
|
105
|
-
prerelease: false
|
106
|
-
version_requirements: !ruby/object:Gem::Requirement
|
107
|
-
requirements:
|
108
|
-
- - ">="
|
109
|
-
- !ruby/object:Gem::Version
|
110
|
-
version: '0'
|
111
69
|
description: Kraps allows to process and perform calculations on very large datasets
|
112
70
|
in parallel
|
113
71
|
email:
|
@@ -121,7 +79,6 @@ files:
|
|
121
79
|
- CHANGELOG.md
|
122
80
|
- CODE_OF_CONDUCT.md
|
123
81
|
- Gemfile
|
124
|
-
- Gemfile.lock
|
125
82
|
- LICENSE.txt
|
126
83
|
- README.md
|
127
84
|
- Rakefile
|
data/Gemfile.lock
DELETED
@@ -1,108 +0,0 @@
|
|
1
|
-
PATH
|
2
|
-
remote: .
|
3
|
-
specs:
|
4
|
-
kraps (0.7.0)
|
5
|
-
attachie
|
6
|
-
map-reduce-ruby (>= 3.0.0)
|
7
|
-
redis
|
8
|
-
ruby-progressbar
|
9
|
-
|
10
|
-
GEM
|
11
|
-
remote: https://rubygems.org/
|
12
|
-
specs:
|
13
|
-
activesupport (7.0.4)
|
14
|
-
concurrent-ruby (~> 1.0, >= 1.0.2)
|
15
|
-
i18n (>= 1.6, < 2)
|
16
|
-
minitest (>= 5.1)
|
17
|
-
tzinfo (~> 2.0)
|
18
|
-
ast (2.4.2)
|
19
|
-
attachie (1.2.0)
|
20
|
-
activesupport
|
21
|
-
aws-sdk-s3
|
22
|
-
connection_pool
|
23
|
-
mime-types
|
24
|
-
aws-eventstream (1.2.0)
|
25
|
-
aws-partitions (1.657.0)
|
26
|
-
aws-sdk-core (3.166.0)
|
27
|
-
aws-eventstream (~> 1, >= 1.0.2)
|
28
|
-
aws-partitions (~> 1, >= 1.651.0)
|
29
|
-
aws-sigv4 (~> 1.5)
|
30
|
-
jmespath (~> 1, >= 1.6.1)
|
31
|
-
aws-sdk-kms (1.59.0)
|
32
|
-
aws-sdk-core (~> 3, >= 3.165.0)
|
33
|
-
aws-sigv4 (~> 1.1)
|
34
|
-
aws-sdk-s3 (1.117.1)
|
35
|
-
aws-sdk-core (~> 3, >= 3.165.0)
|
36
|
-
aws-sdk-kms (~> 1)
|
37
|
-
aws-sigv4 (~> 1.4)
|
38
|
-
aws-sigv4 (1.5.2)
|
39
|
-
aws-eventstream (~> 1, >= 1.0.2)
|
40
|
-
concurrent-ruby (1.1.10)
|
41
|
-
connection_pool (2.3.0)
|
42
|
-
diff-lcs (1.5.0)
|
43
|
-
i18n (1.12.0)
|
44
|
-
concurrent-ruby (~> 1.0)
|
45
|
-
jmespath (1.6.1)
|
46
|
-
json (2.6.2)
|
47
|
-
lazy_priority_queue (0.1.1)
|
48
|
-
map-reduce-ruby (3.0.0)
|
49
|
-
json
|
50
|
-
lazy_priority_queue
|
51
|
-
mime-types (3.4.1)
|
52
|
-
mime-types-data (~> 3.2015)
|
53
|
-
mime-types-data (3.2022.0105)
|
54
|
-
minitest (5.16.3)
|
55
|
-
parallel (1.22.1)
|
56
|
-
parser (3.1.2.1)
|
57
|
-
ast (~> 2.4.1)
|
58
|
-
rainbow (3.1.1)
|
59
|
-
rake (13.0.6)
|
60
|
-
redis (5.0.5)
|
61
|
-
redis-client (>= 0.9.0)
|
62
|
-
redis-client (0.11.2)
|
63
|
-
connection_pool
|
64
|
-
regexp_parser (2.6.0)
|
65
|
-
rexml (3.2.5)
|
66
|
-
rspec (3.12.0)
|
67
|
-
rspec-core (~> 3.12.0)
|
68
|
-
rspec-expectations (~> 3.12.0)
|
69
|
-
rspec-mocks (~> 3.12.0)
|
70
|
-
rspec-core (3.12.0)
|
71
|
-
rspec-support (~> 3.12.0)
|
72
|
-
rspec-expectations (3.12.0)
|
73
|
-
diff-lcs (>= 1.2.0, < 2.0)
|
74
|
-
rspec-support (~> 3.12.0)
|
75
|
-
rspec-mocks (3.12.0)
|
76
|
-
diff-lcs (>= 1.2.0, < 2.0)
|
77
|
-
rspec-support (~> 3.12.0)
|
78
|
-
rspec-support (3.12.0)
|
79
|
-
rubocop (1.38.0)
|
80
|
-
json (~> 2.3)
|
81
|
-
parallel (~> 1.10)
|
82
|
-
parser (>= 3.1.2.1)
|
83
|
-
rainbow (>= 2.2.2, < 4.0)
|
84
|
-
regexp_parser (>= 1.8, < 3.0)
|
85
|
-
rexml (>= 3.2.5, < 4.0)
|
86
|
-
rubocop-ast (>= 1.23.0, < 2.0)
|
87
|
-
ruby-progressbar (~> 1.7)
|
88
|
-
unicode-display_width (>= 1.4.0, < 3.0)
|
89
|
-
rubocop-ast (1.23.0)
|
90
|
-
parser (>= 3.1.1.0)
|
91
|
-
ruby-progressbar (1.11.0)
|
92
|
-
tzinfo (2.0.5)
|
93
|
-
concurrent-ruby (~> 1.0)
|
94
|
-
unicode-display_width (2.3.0)
|
95
|
-
|
96
|
-
PLATFORMS
|
97
|
-
ruby
|
98
|
-
x86_64-linux
|
99
|
-
|
100
|
-
DEPENDENCIES
|
101
|
-
bundler
|
102
|
-
kraps!
|
103
|
-
rake (~> 13.0)
|
104
|
-
rspec (~> 3.0)
|
105
|
-
rubocop
|
106
|
-
|
107
|
-
BUNDLED WITH
|
108
|
-
2.3.24
|