hadoop-jruby-connector 0.0.6 → 0.0.7
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.
- data/VERSION +1 -1
- data/lib/hjc/hadoop_streaming.rb +1 -8
- data/spec/hjc/hadoop_streaming_spec.rb +2 -10
- metadata +3 -3
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.0.
|
1
|
+
0.0.7
|
data/lib/hjc/hadoop_streaming.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
module Hjc
|
2
2
|
class HadoopStreaming
|
3
|
-
attr_accessor :input_path, :output_path, :mapper_path, :reducer_path, :jobconf
|
3
|
+
attr_accessor :input_path, :output_path, :mapper_path, :reducer_path, :jobconf
|
4
4
|
attr_accessor :local, :debug
|
5
5
|
|
6
6
|
def initialize
|
@@ -30,13 +30,11 @@ module Hjc
|
|
30
30
|
end
|
31
31
|
|
32
32
|
def mapper=(mapper)
|
33
|
-
mapper = with_shebang(mapper, @language)
|
34
33
|
@files['mapper'] = file = Util.to_temp_file('mapper', mapper, :mod => 0700)
|
35
34
|
@mapper_path = File.basename(file.path)
|
36
35
|
end
|
37
36
|
|
38
37
|
def reducer=(reducer)
|
39
|
-
reducer = with_shebang(reducer, @language)
|
40
38
|
@files['reducer'] = file = Util.to_temp_file('reducer', reducer, :mod => 0700)
|
41
39
|
@reducer_path = File.basename(file.path)
|
42
40
|
end
|
@@ -62,10 +60,5 @@ module Hjc
|
|
62
60
|
puts "args: #{concated_args.join(' ')}" if @debug
|
63
61
|
concated_args
|
64
62
|
end
|
65
|
-
|
66
|
-
private
|
67
|
-
def with_shebang(body, language)
|
68
|
-
"#!/usr/bin/env #{language}\n#{body}"
|
69
|
-
end
|
70
63
|
end
|
71
64
|
end
|
@@ -34,16 +34,6 @@ module Hjc
|
|
34
34
|
job.args.join(" ").should match(/reducer/)
|
35
35
|
end
|
36
36
|
|
37
|
-
it 'adds shebang if language exists' do
|
38
|
-
job = HadoopStreaming.new
|
39
|
-
job.language = 'ruby'
|
40
|
-
job.mapper = 'mapper'
|
41
|
-
job.reducer = 'reducer'
|
42
|
-
|
43
|
-
File.read(File.join(TMP_DIR, job.mapper_path)).should match(%Q:#!/usr/bin/env ruby:)
|
44
|
-
File.read(File.join(TMP_DIR, job.reducer_path)).should match(%Q:#!/usr/bin/env ruby:)
|
45
|
-
end
|
46
|
-
|
47
37
|
it 'can run Hadoop streaming job with path' do
|
48
38
|
pending 'path does not work'
|
49
39
|
job = HadoopStreaming.new
|
@@ -101,6 +91,7 @@ module Hjc
|
|
101
91
|
end
|
102
92
|
|
103
93
|
MAPPER = <<-'EOF'
|
94
|
+
#!/usr/bin/env ruby
|
104
95
|
ARGF.each do |line|
|
105
96
|
line.chomp!
|
106
97
|
line.split.each do |word|
|
@@ -110,6 +101,7 @@ end
|
|
110
101
|
EOF
|
111
102
|
|
112
103
|
REDUCER = <<-'EOF'
|
104
|
+
#!/usr/bin/env ruby
|
113
105
|
count = Hash.new {|h,k| h[k] = 0}
|
114
106
|
ARGF.each do |line|
|
115
107
|
line.chomp!
|
metadata
CHANGED
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
5
5
|
segments:
|
6
6
|
- 0
|
7
7
|
- 0
|
8
|
-
-
|
9
|
-
version: 0.0.
|
8
|
+
- 7
|
9
|
+
version: 0.0.7
|
10
10
|
platform: ruby
|
11
11
|
authors:
|
12
12
|
- Koichi Fujikawa
|
@@ -14,7 +14,7 @@ autorequire:
|
|
14
14
|
bindir: bin
|
15
15
|
cert_chain: []
|
16
16
|
|
17
|
-
date: 2011-
|
17
|
+
date: 2011-06-06 00:00:00 +09:00
|
18
18
|
default_executable:
|
19
19
|
dependencies: []
|
20
20
|
|