humboldt 1.0.2-java → 1.0.3-java

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 37a2d3fc7a3bc35d2da684d3359c9299da39b155
4
- data.tar.gz: abbfab2107a18d0f4fa5e5d6ef9934d2d2d81028
3
+ metadata.gz: ad7d9161131ab93f3ee98a2a22a730bf6af82d9a
4
+ data.tar.gz: ee3f4f283aa281be60b55ecc9b6c169743d87998
5
5
  SHA512:
6
- metadata.gz: 759cd4c0de2cd31a22019b6358fcb36dd26636d40dcc6766b78cd21d68a2f8894382cd7dcc177d996a7fea6506fb2a88d39ebe5b79036c542519cbd5ed82c3e9
7
- data.tar.gz: af8dea70e46df9fa5a8526ebe9d2b7db44c189b61e89c29bbd895d1190a42dbfa1ad92e024be7f9f2eb6dd93a81f2a1f7f9a44a5e50d5293270efae18c94f718
6
+ metadata.gz: 19ccf74a3524748dcea4b24b026f7870a4785d8e6ff18cc661cde2136ab3c955f8f2bd37fb5f4b85b292bbe1961d8464b07f679fc0c3ed263eba8cb5b3fd218b
7
+ data.tar.gz: 93bc3287a0859e02d380d66fb920fc3c48fd02697411c49468da63b86a5b94a381104408667a5cf18915928a3d7ee359e4a836ab9846c5520b30c9292a19b93c
@@ -5,31 +5,6 @@ module Humboldt
5
5
  class Binary
6
6
  HADOOP = ::Hadoop::Io::BytesWritable
7
7
  RUBY = ::String
8
-
9
- attr_reader :hadoop
10
-
11
- def hadoop=(value)
12
- unless value.is_a?(HADOOP)
13
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
14
- end
15
- @hadoop = value
16
- end
17
-
18
- def initialize
19
- @hadoop = HADOOP.new
20
- end
21
-
22
- def ruby
23
- String.from_java_bytes(@hadoop.bytes).byteslice(0, @hadoop.length)
24
- end
25
-
26
- def ruby=(value)
27
- unless value.is_a?(RUBY)
28
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
29
- end
30
-
31
- @hadoop.set(value.to_java_bytes, 0, value.bytesize)
32
- end
33
8
  end
34
9
 
35
10
  begin
@@ -40,13 +15,11 @@ module Humboldt
40
15
  unless value.is_a?(Hash) || value.is_a?(Array)
41
16
  raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected Hash or Array"
42
17
  end
43
- packed = MessagePack.pack(value)
44
- @hadoop.set(packed.to_java_bytes, 0, packed.bytesize)
18
+ super(MessagePack.pack(value))
45
19
  end
46
20
 
47
21
  def ruby
48
- packed = String.from_java_bytes(@hadoop.bytes).byteslice(0, @hadoop.length)
49
- MessagePack.unpack(packed, encoding: Encoding::UTF_8)
22
+ MessagePack.unpack(super(), encoding: Encoding::UTF_8)
50
23
  end
51
24
  end
52
25
  rescue LoadError
@@ -55,35 +28,6 @@ module Humboldt
55
28
  class Text
56
29
  HADOOP = ::Hadoop::Io::Text
57
30
  RUBY = ::String
58
-
59
- attr_reader :hadoop
60
-
61
- def hadoop=(value)
62
- unless value.is_a?(HADOOP)
63
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
64
- end
65
- @hadoop = value
66
- end
67
-
68
- def initialize
69
- @hadoop = HADOOP.new
70
- end
71
-
72
- def ruby
73
- String.from_java_bytes(@hadoop.bytes).byteslice(0, @hadoop.length).force_encoding(Encoding::UTF_8)
74
- end
75
-
76
- def ruby=(value)
77
- unless value.is_a?(RUBY)
78
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
79
- end
80
-
81
- if value.encoding == Encoding::UTF_8
82
- @hadoop.set(value.to_java_bytes, 0, value.bytesize)
83
- else
84
- @hadoop.set(value)
85
- end
86
- end
87
31
  end
88
32
 
89
33
  begin
@@ -94,11 +38,11 @@ module Humboldt
94
38
  unless value.is_a?(Hash) || value.is_a?(Array)
95
39
  raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected Hash or Array"
96
40
  end
97
- @hadoop.set(JSON.generate(value))
41
+ super(JSON.generate(value))
98
42
  end
99
43
 
100
44
  def ruby
101
- JSON.parse(hadoop.to_s)
45
+ JSON.parse(super())
102
46
  end
103
47
  end
104
48
  end
@@ -106,56 +50,11 @@ module Humboldt
106
50
  class Long
107
51
  HADOOP = ::Hadoop::Io::LongWritable
108
52
  RUBY = ::Integer
109
-
110
- attr_reader :hadoop
111
-
112
- def hadoop=(value)
113
- unless value.is_a?(HADOOP)
114
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
115
- end
116
- @hadoop = value
117
- end
118
-
119
- def initialize
120
- @hadoop = HADOOP.new
121
- end
122
-
123
- def ruby
124
- @hadoop.get
125
- end
126
-
127
- def ruby=(value)
128
- unless value.is_a?(Integer)
129
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
130
- end
131
-
132
- @hadoop.set value
133
- end
134
53
  end
135
54
 
136
55
  class None
137
56
  HADOOP = ::Hadoop::Io::NullWritable
138
57
  RUBY = ::NilClass
139
-
140
- def hadoop
141
- HADOOP.get
142
- end
143
-
144
- def hadoop=(value)
145
- unless value.is_a?(HADOOP)
146
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{HADOOP}"
147
- end
148
- end
149
-
150
- def ruby
151
- nil
152
- end
153
-
154
- def ruby=(value)
155
- unless value.nil?
156
- raise ArgumentError, "Hadoop type mismatch, was #{value.class}, expected #{RUBY}"
157
- end
158
- end
159
58
  end
160
59
 
161
60
  TYPE_CONVERTER_CLASS_CACHE = Hash.new { |h,k| h[k] = const_get(k.to_s.capitalize) }
@@ -1,5 +1,5 @@
1
1
  # encoding: utf-8
2
2
 
3
3
  module Humboldt
4
- VERSION = '1.0.2'.freeze
4
+ VERSION = '1.0.3'.freeze
5
5
  end
data/lib/humboldt.jar CHANGED
Binary file
data/lib/humboldt.rb CHANGED
@@ -4,6 +4,9 @@ require 'fileutils'
4
4
  require 'rubydoop'
5
5
  require 'hadoop'
6
6
 
7
+ $CLASSPATH << File.expand_path('../humboldt.jar', __FILE__)
8
+ Java::Humboldt::HumboldtLibrary.new.load(JRuby.runtime, false)
9
+
7
10
  require 'humboldt/java_lib'
8
11
 
9
12
  require 'ext/hadoop'
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: humboldt
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.2
4
+ version: 1.0.3
5
5
  platform: java
6
6
  authors:
7
7
  - The Burt Platform Team
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2015-04-02 00:00:00.000000000 Z
11
+ date: 2015-05-20 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  requirement: !ruby/object:Gem::Requirement
@@ -66,25 +66,25 @@ executables:
66
66
  extensions: []
67
67
  extra_rdoc_files: []
68
68
  files:
69
- - lib/humboldt.rb
69
+ - bin/humboldt
70
+ - config/emr-bootstrap/remove_old_jruby.sh
71
+ - config/hadoop-local.xml
70
72
  - lib/ext/hadoop.rb
71
73
  - lib/ext/rubydoop.rb
74
+ - lib/humboldt.jar
75
+ - lib/humboldt.rb
72
76
  - lib/humboldt/cli.rb
73
77
  - lib/humboldt/emr_flow.rb
74
78
  - lib/humboldt/hadoop_status_filter.rb
75
79
  - lib/humboldt/java_lib.rb
76
80
  - lib/humboldt/mapper.rb
81
+ - lib/humboldt/patterns/sum_reducer.rb
77
82
  - lib/humboldt/prefix_grouping.rb
78
83
  - lib/humboldt/processor.rb
79
84
  - lib/humboldt/reducer.rb
80
85
  - lib/humboldt/rspec.rb
81
86
  - lib/humboldt/type_converters.rb
82
87
  - lib/humboldt/version.rb
83
- - lib/humboldt/patterns/sum_reducer.rb
84
- - lib/humboldt.jar
85
- - bin/humboldt
86
- - config/hadoop-local.xml
87
- - config/emr-bootstrap/remove_old_jruby.sh
88
88
  homepage: http://github.com/burtcorp/humboldt
89
89
  licenses:
90
90
  - BSD-3-Clause
@@ -105,7 +105,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
105
105
  version: '0'
106
106
  requirements: []
107
107
  rubyforge_project:
108
- rubygems_version: 2.1.9
108
+ rubygems_version: 2.4.5
109
109
  signing_key:
110
110
  specification_version: 4
111
111
  summary: Tools and libraries for simplifying running Rubydoop jobs locally and on AWS Elastic MapReduce