embulk-plugin-input-hbase 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (4) hide show
  1. checksums.yaml +7 -0
  2. data/README.md +42 -0
  3. data/lib/embulk/input_hbase.rb +55 -0
  4. metadata +87 -0
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 86fec11c1456942d02ab71d1af28eb9485ca9d0f
4
+ data.tar.gz: cdfb3faa20b8196951c482f73073655218d1df22
5
+ SHA512:
6
+ metadata.gz: 2d768b08a793abedcc55b4feea1c3d6e9a6a4f900c394612429277e2eff079d116c7622c08e625903210f3ac6408701b6094c7e30589b1fbf6f6e5d035312c0e
7
+ data.tar.gz: 4376a62c510a62d4fba1166759059692b153e4aa9c6bf13d1071f56f37b7dbdc2bf0a1f4563f3066a5ecf28a06ddecab3ef262457e6ac294d27671be81d863ac
data/README.md ADDED
@@ -0,0 +1,42 @@
1
+ # embulk-plugin-input-hbase
2
+
3
+ ## Example
4
+
5
+ HBase table:
6
+
7
+ ```ruby
8
+ hbase(main):029:0> scan 'example:test'
9
+ ROW COLUMN+CELL
10
+ r1 column=foo:dig, timestamp=1422458241976, value=\x00\x00\x00\x00\x00\x00\x00\x01
11
+ r2 column=foo:dig, timestamp=1422458257028, value=\x00\x00\x00\x00\x00\x00\x00\x02
12
+ r2 column=foo:str, timestamp=1422458830978, value=hello
13
+ r3 column=foo:str, timestamp=1422458270762, value=hey
14
+ 3 row(s) in 0.0860 seconds
15
+ ```
16
+
17
+ Embulk config:
18
+
19
+ ```yaml
20
+ in:
21
+ type: hbase
22
+ host: localhost
23
+ table: 'example:test'
24
+ columns:
25
+ - {name: 'foo:dig', type: long}
26
+ - {name: 'foo:str', type: string}
27
+ out:
28
+ type: stdout
29
+ ```
30
+
31
+ Embulk preview:
32
+
33
+ ```bash
34
+ $ java -jar embulk.jar preview example.yml
35
+ +--------------+----------------+
36
+ | foo:dig:long | foo:str:string |
37
+ +--------------+----------------+
38
+ | 1 | |
39
+ | 2 | hello |
40
+ | 0 | hey |
41
+ +--------------+----------------+
42
+ ```
@@ -0,0 +1,55 @@
1
+ require 'hbase-jruby'
2
+
3
+ module Embulk
4
+ class InputHBase < InputPlugin
5
+ Plugin.register_input('hbase', self)
6
+
7
+ def self.transaction(config, &control)
8
+ task = {
9
+ 'host' => config.param('host', :string, default: 'localhost'),
10
+ 'table' => config.param('table', :string)
11
+ }
12
+ threads = 1
13
+ columns = config.param('columns', :array).map.with_index { |column, i|
14
+ Column.new(i, column['name'], column['type'].to_sym)
15
+ }
16
+ commit_reports = yield(task, columns, threads)
17
+ return {}
18
+ end
19
+
20
+ def initialize(task, schema, index, page_builder)
21
+ super
22
+ end
23
+
24
+ def run
25
+ HBase.resolve_dependency! '0.98'
26
+ hbase = HBase.new('hbase.zookeeper.quorum' => @task['host'])
27
+ table = hbase.table(@task['table'])
28
+ table.each { |row|
29
+ @page_builder.add(@schema.map { |column|
30
+ value = row[column.name]
31
+ case column.type
32
+ when :long
33
+ if value
34
+ HBase::Util::from_bytes(:long, value)
35
+ else
36
+ 0
37
+ end
38
+ when :string
39
+ if value
40
+ HBase::Util::from_bytes(:string, value)
41
+ else
42
+ ''
43
+ end
44
+ else
45
+ value
46
+ end
47
+ })
48
+ }
49
+ @page_builder.finish
50
+ commit_report = {
51
+ }
52
+ return commit_report
53
+ end
54
+ end
55
+ end
metadata ADDED
@@ -0,0 +1,87 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-plugin-input-hbase
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Shun Takebayashi
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2015-01-28 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: hbase-jruby
15
+ version_requirements: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
20
+ requirement: !ruby/object:Gem::Requirement
21
+ requirements:
22
+ - - ">="
23
+ - !ruby/object:Gem::Version
24
+ version: '0'
25
+ prerelease: false
26
+ type: :runtime
27
+ - !ruby/object:Gem::Dependency
28
+ name: bundler
29
+ version_requirements: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '1.0'
34
+ requirement: !ruby/object:Gem::Requirement
35
+ requirements:
36
+ - - "~>"
37
+ - !ruby/object:Gem::Version
38
+ version: '1.0'
39
+ prerelease: false
40
+ type: :development
41
+ - !ruby/object:Gem::Dependency
42
+ name: rake
43
+ version_requirements: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: 0.9.2
48
+ requirement: !ruby/object:Gem::Requirement
49
+ requirements:
50
+ - - ">="
51
+ - !ruby/object:Gem::Version
52
+ version: 0.9.2
53
+ prerelease: false
54
+ type: :development
55
+ description: Embulk plugin for HBase input
56
+ email: shun@takebayashi.asia
57
+ executables: []
58
+ extensions: []
59
+ extra_rdoc_files: []
60
+ files:
61
+ - README.md
62
+ - lib/embulk/input_hbase.rb
63
+ homepage: https://github.com/takebayashi/embulk-plugin-input-hbase
64
+ licenses:
65
+ - Apache 2.0
66
+ metadata: {}
67
+ post_install_message:
68
+ rdoc_options: []
69
+ require_paths:
70
+ - lib
71
+ required_ruby_version: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ required_rubygems_version: !ruby/object:Gem::Requirement
77
+ requirements:
78
+ - - ">="
79
+ - !ruby/object:Gem::Version
80
+ version: '0'
81
+ requirements: []
82
+ rubyforge_project:
83
+ rubygems_version: 2.4.5
84
+ signing_key:
85
+ specification_version: 4
86
+ summary: Embulk plugin for HBase input
87
+ test_files: []