embulk-input-presto 0.1.1 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.ruby-version +1 -1
- data/Rakefile +9 -1
- data/embulk-input-presto.gemspec +3 -2
- data/lib/embulk/input/presto.rb +80 -46
- data/test/helper.rb +11 -0
- data/test/test_transaction.rb +65 -0
- metadata +26 -8
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1a57f6dc5a7064378aba3325b8765ffc3e3f1cdd
|
4
|
+
data.tar.gz: f272abf3aad3768b0603366e404685cf33d4e61d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 13ce34fd728876372f389ac13cf422d23b8facba8c3069b60f946f4762cc37e003e2493ec5c1129ca10fdab20a8ed0ed860028a9109e02a5afd6bb62e9e30ccc
|
7
|
+
data.tar.gz: 1898c4f776b9570ecf9813372cfd80ff2c62c339f0872e633d85a722e8a844d911b1bb0716489cf243cde6b25aa6fc2452a8c628d3877cc6b13399a8924b279a
|
data/.ruby-version
CHANGED
@@ -1 +1 @@
|
|
1
|
-
jruby-9.0.
|
1
|
+
jruby-9.0.5.0
|
data/Rakefile
CHANGED
@@ -1,3 +1,11 @@
|
|
1
1
|
require "bundler/gem_tasks"
|
2
|
+
require 'rake/testtask'
|
2
3
|
|
3
|
-
|
4
|
+
desc 'Run test_unit based test'
|
5
|
+
Rake::TestTask.new(:test) do |t|
|
6
|
+
t.libs << "test"
|
7
|
+
t.test_files = Dir["test/**/test_*.rb"].sort
|
8
|
+
t.verbose = true
|
9
|
+
t.warning = false
|
10
|
+
end
|
11
|
+
task :default => :test
|
data/embulk-input-presto.gemspec
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
|
2
2
|
Gem::Specification.new do |spec|
|
3
3
|
spec.name = "embulk-input-presto"
|
4
|
-
spec.version = "0.1.
|
4
|
+
spec.version = "0.1.2"
|
5
5
|
spec.authors = ["toyama0919"]
|
6
6
|
spec.summary = "Facebook Presto input plugin for Embulk"
|
7
7
|
spec.description = "Facebook Presto input plugin for Embulk."
|
@@ -14,7 +14,8 @@ Gem::Specification.new do |spec|
|
|
14
14
|
spec.require_paths = ["lib"]
|
15
15
|
|
16
16
|
spec.add_dependency "presto-client"
|
17
|
-
spec.add_development_dependency 'embulk', ['
|
17
|
+
spec.add_development_dependency 'embulk', ['>= 0.8.9']
|
18
18
|
spec.add_development_dependency 'bundler', ['~> 1.0']
|
19
19
|
spec.add_development_dependency 'rake', ['>= 10.0']
|
20
|
+
spec.add_development_dependency 'test-unit'
|
20
21
|
end
|
data/lib/embulk/input/presto.rb
CHANGED
@@ -1,59 +1,93 @@
|
|
1
1
|
module Embulk
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
Plugin.register_input("presto", self)
|
6
|
-
|
7
|
-
def self.transaction(config, &control)
|
8
|
-
task = {
|
9
|
-
"host" => config.param("host", :string, default: "localhost"),
|
10
|
-
"port" => config.param("port", :integer, default: 8080),
|
11
|
-
"schema" => config.param("schema", :string, default: "default"),
|
12
|
-
"catalog" => config.param("catalog", :string, default: "native"),
|
13
|
-
"query" => config.param("query", :string),
|
14
|
-
"user" => config.param("user", :string, default: "embulk"),
|
15
|
-
"columns" => config.param("columns", :array, default: [])
|
16
|
-
}
|
17
|
-
|
18
|
-
columns = task['columns'].each_with_index.map do |c, i|
|
19
|
-
Column.new(i, c["name"], c["type"].to_sym)
|
20
|
-
end
|
2
|
+
module Input
|
3
|
+
class Presto < InputPlugin
|
4
|
+
require 'presto-client'
|
21
5
|
|
22
|
-
|
23
|
-
end
|
6
|
+
Plugin.register_input("presto", self)
|
24
7
|
|
25
|
-
|
26
|
-
|
8
|
+
def self.transaction(config, &control)
|
9
|
+
task = {
|
10
|
+
"host" => config.param("host", :string, default: "localhost"),
|
11
|
+
"port" => config.param("port", :integer, default: 8080),
|
12
|
+
"schema" => config.param("schema", :string, default: "default"),
|
13
|
+
"catalog" => config.param("catalog", :string, default: "native"),
|
14
|
+
"query" => config.param("query", :string),
|
15
|
+
"user" => config.param("user", :string, default: "embulk"),
|
16
|
+
"columns" => config.param("columns", :array)
|
17
|
+
}
|
27
18
|
|
28
|
-
|
29
|
-
|
30
|
-
|
19
|
+
columns = task['columns'].each_with_index.map do |c, i|
|
20
|
+
Column.new(i, c["name"], c["type"].to_sym)
|
21
|
+
end
|
31
22
|
|
32
|
-
|
33
|
-
|
34
|
-
server: "#{task['host']}:#{task['port']}",
|
35
|
-
catalog: task['catalog'],
|
36
|
-
user: task['user'],
|
37
|
-
schema: task['schema']
|
38
|
-
)
|
39
|
-
@query = task["query"]
|
23
|
+
resume(task, columns, 1, &control)
|
24
|
+
end
|
40
25
|
|
41
|
-
|
42
|
-
|
26
|
+
def self.resume(task, columns, count, &control)
|
27
|
+
task_reports = yield(task, columns, count)
|
43
28
|
|
44
|
-
|
45
|
-
|
46
|
-
@client.query(@query) do |q|
|
47
|
-
q.each_row {|row|
|
48
|
-
page_builder.add(row)
|
49
|
-
}
|
50
|
-
size = q.rows.size
|
29
|
+
next_config_diff = {}
|
30
|
+
return next_config_diff
|
51
31
|
end
|
52
32
|
|
53
|
-
|
33
|
+
def init
|
34
|
+
@client = ::Presto::Client.new(
|
35
|
+
server: "#{task['host']}:#{task['port']}",
|
36
|
+
catalog: task['catalog'],
|
37
|
+
user: task['user'],
|
38
|
+
schema: task['schema']
|
39
|
+
)
|
40
|
+
@query = task["query"]
|
54
41
|
|
55
|
-
|
56
|
-
|
42
|
+
Embulk.logger.info "SQL: #{@query}"
|
43
|
+
end
|
44
|
+
|
45
|
+
def run
|
46
|
+
size = 0
|
47
|
+
@client.query(@query) do |q|
|
48
|
+
q.each_row {|row|
|
49
|
+
converted_values = row.map.with_index { |value,i| convert_value(value, schema[i]) }
|
50
|
+
page_builder.add(converted_values)
|
51
|
+
}
|
52
|
+
size = q.rows.size
|
53
|
+
end
|
54
|
+
|
55
|
+
page_builder.finish
|
56
|
+
|
57
|
+
task_report = { size: size }
|
58
|
+
return task_report
|
59
|
+
end
|
60
|
+
|
61
|
+
def convert_value(value, field)
|
62
|
+
return nil if value.nil?
|
63
|
+
case field["type"]
|
64
|
+
when :string
|
65
|
+
value
|
66
|
+
when :long
|
67
|
+
value.to_i
|
68
|
+
when :double
|
69
|
+
value.to_f
|
70
|
+
when :boolean
|
71
|
+
if value.is_a?(TrueClass) || value.is_a?(FalseClass)
|
72
|
+
value
|
73
|
+
else
|
74
|
+
downcased_val = value.downcase
|
75
|
+
case downcased_val
|
76
|
+
when 'true' then true
|
77
|
+
when 'false' then false
|
78
|
+
when '1' then true
|
79
|
+
when '0' then false
|
80
|
+
else nil
|
81
|
+
end
|
82
|
+
end
|
83
|
+
when :timestamp
|
84
|
+
Time.parse(value)
|
85
|
+
when :json
|
86
|
+
value
|
87
|
+
else
|
88
|
+
raise "Unsupported type #{field['type']}"
|
89
|
+
end
|
90
|
+
end
|
57
91
|
end
|
58
92
|
end
|
59
93
|
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'test/unit'
|
4
|
+
|
5
|
+
# require 'embulk/java/bootstrap'
|
6
|
+
require 'embulk'
|
7
|
+
Embulk.setup
|
8
|
+
Embulk.logger = Embulk::Logger.new('/dev/null')
|
9
|
+
|
10
|
+
APP_ROOT = File.expand_path('../', __dir__)
|
11
|
+
TEST_ROOT = File.expand_path(File.dirname(__FILE__))
|
@@ -0,0 +1,65 @@
|
|
1
|
+
require_relative './helper'
|
2
|
+
require 'embulk/input/presto'
|
3
|
+
require 'yaml'
|
4
|
+
|
5
|
+
Presto = Embulk::Input::Presto
|
6
|
+
|
7
|
+
module Embulk
|
8
|
+
class Input::Presto
|
9
|
+
class TestTransaction < Test::Unit::TestCase
|
10
|
+
def control
|
11
|
+
Proc.new {|task| task_reports = [] }
|
12
|
+
end
|
13
|
+
|
14
|
+
sub_test_case "transaction" do
|
15
|
+
def test_normal
|
16
|
+
yaml = YAML.load(%(
|
17
|
+
host: presto01
|
18
|
+
catalog: store
|
19
|
+
schema: public
|
20
|
+
query: |
|
21
|
+
SELECT
|
22
|
+
trim(upper(url_decode(keyword))) AS keyword,
|
23
|
+
count(*) as count
|
24
|
+
FROM search
|
25
|
+
CROSS JOIN UNNEST(split(keywords, ',')) AS t (keyword)
|
26
|
+
WHERE log_date >= (CURRENT_DATE - INTERVAL '90' DAY)
|
27
|
+
AND length(keywords) != 256
|
28
|
+
group by keyword
|
29
|
+
having count(*) >= 10
|
30
|
+
order by count(*) desc
|
31
|
+
columns:
|
32
|
+
- {name: keyword, type: string}
|
33
|
+
- {name: count, type: long}
|
34
|
+
)
|
35
|
+
)
|
36
|
+
config = DataSource.new(yaml)
|
37
|
+
Presto.transaction(config, &control)
|
38
|
+
end
|
39
|
+
|
40
|
+
def test_minimum
|
41
|
+
yaml = YAML.load(%(
|
42
|
+
query: |
|
43
|
+
SELECT
|
44
|
+
trim(upper(url_decode(keyword))) AS keyword,
|
45
|
+
count(*) as count
|
46
|
+
FROM search
|
47
|
+
CROSS JOIN UNNEST(split(keywords, ',')) AS t (keyword)
|
48
|
+
WHERE log_date >= (CURRENT_DATE - INTERVAL '90' DAY)
|
49
|
+
AND length(keywords) != 256
|
50
|
+
group by keyword
|
51
|
+
having count(*) >= 10
|
52
|
+
order by count(*) desc
|
53
|
+
columns:
|
54
|
+
- {name: keyword, type: string}
|
55
|
+
- {name: count, type: long}
|
56
|
+
|
57
|
+
)
|
58
|
+
)
|
59
|
+
config = DataSource.new(yaml)
|
60
|
+
Presto.transaction(config, &control)
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: embulk-input-presto
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- toyama0919
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2016-06-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
requirement: !ruby/object:Gem::Requirement
|
@@ -27,17 +27,17 @@ dependencies:
|
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
requirement: !ruby/object:Gem::Requirement
|
29
29
|
requirements:
|
30
|
-
- - "
|
30
|
+
- - ">="
|
31
31
|
- !ruby/object:Gem::Version
|
32
|
-
version: 0.
|
32
|
+
version: 0.8.9
|
33
33
|
name: embulk
|
34
34
|
prerelease: false
|
35
35
|
type: :development
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - "
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: 0.
|
40
|
+
version: 0.8.9
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
requirement: !ruby/object:Gem::Requirement
|
43
43
|
requirements:
|
@@ -66,6 +66,20 @@ dependencies:
|
|
66
66
|
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '10.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
requirement: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
name: test-unit
|
76
|
+
prerelease: false
|
77
|
+
type: :development
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
69
83
|
description: Facebook Presto input plugin for Embulk.
|
70
84
|
email:
|
71
85
|
- toyama0919@gmail.com
|
@@ -81,6 +95,8 @@ files:
|
|
81
95
|
- Rakefile
|
82
96
|
- embulk-input-presto.gemspec
|
83
97
|
- lib/embulk/input/presto.rb
|
98
|
+
- test/helper.rb
|
99
|
+
- test/test_transaction.rb
|
84
100
|
homepage: https://github.com/toyama0919/embulk-input-presto
|
85
101
|
licenses:
|
86
102
|
- MIT
|
@@ -101,8 +117,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
101
117
|
version: '0'
|
102
118
|
requirements: []
|
103
119
|
rubyforge_project:
|
104
|
-
rubygems_version: 2.4.
|
120
|
+
rubygems_version: 2.4.8
|
105
121
|
signing_key:
|
106
122
|
specification_version: 4
|
107
123
|
summary: Facebook Presto input plugin for Embulk
|
108
|
-
test_files:
|
124
|
+
test_files:
|
125
|
+
- test/helper.rb
|
126
|
+
- test/test_transaction.rb
|