streamingly 0.0.5 → 0.0.8

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: 45d8a9c657e19d5c57d2ac76e894b1c5507fbbe2
4
- data.tar.gz: 7189cc2394882efacc17854af55ad164d15dc397
3
+ metadata.gz: f507114d8202daadc401f6de1d18054035a7c557
4
+ data.tar.gz: 4cab496f8fb9940b12aca0eab8735ef00344e124
5
5
  SHA512:
6
- metadata.gz: ea3e8af5b941d4b24686d25674bc36e6777f37995b422590466e6b6d7edaa73f744fc2f281e02466db54b05fa5a6cd163b6e0a0b16fb3ae8ea54b4387217130e
7
- data.tar.gz: caa7454fd12f4c5724e6488bbe93dfb567f270e840b4e5772be0382051a4f4016bd780c47190c043008aa4f4732ee10ef41e260086f87dc3c4e1897e67124db5
6
+ metadata.gz: 7a33cace50cfb7ebf35723738474b0026f415228366df9385b63abc645f0c046017c174aa633fd2bf1953f358ec4c31be6d3577741c7bb83c4286abeb0002d91
7
+ data.tar.gz: a3f0251f7359e1ada162f7cf5378ecdd458fae05eb3bff8dde27e1d9f26e0cc68210de99e01ce25313555cbec1c58050fcb4476bcb76a73a8013a7d50a31546a
@@ -11,7 +11,7 @@ module Streamingly
11
11
  end
12
12
 
13
13
  # TODO: remove .split from https://github.com/swipely/streamingly/blob/master/lib/streamingly/reducer.rb#L28
14
- def split(char="\t")
14
+ def split(char="\t", limit=1)
15
15
  [key, value]
16
16
  end
17
17
  end
@@ -25,7 +25,10 @@ module Streamingly
25
25
  end
26
26
 
27
27
  def reduce(line)
28
- key, value = line.split("\t")
28
+ # Streaming Hadoop only treats the first tab as the delimiter between
29
+ # the key and value. Additional tabs are grouped into the value:
30
+ # http://hadoop.apache.org/docs/r0.18.3/streaming.html#How+Does+Streaming+Work
31
+ key, value = line.split("\t", 2)
29
32
 
30
33
  if @prev_key != key
31
34
  results = flush
@@ -1,3 +1,3 @@
1
1
  module Streamingly
2
- VERSION = "0.0.5"
2
+ VERSION = "0.0.8"
3
3
  end
@@ -62,6 +62,29 @@ describe Streamingly::Reducer do
62
62
  end
63
63
  end
64
64
 
65
+ context "given a record with multiple tabs" do
66
+ let(:key) { 'key1' }
67
+ let(:value) { "asdf\tqwerty" }
68
+
69
+ let(:records) {
70
+ [
71
+ [key, value].join("\t"),
72
+ ]
73
+ }
74
+
75
+ let(:accumulator) { double(:accumulator, :flush => []) }
76
+
77
+ before do
78
+ accumulator_class.stub(:new).with(key) { accumulator }
79
+ end
80
+
81
+ it "treats only the first tab as the key/value delimiter and leaves the value untouched" do
82
+ accumulator.should_receive(:apply_value).with(value)
83
+
84
+ subject.reduce_over(records)
85
+ end
86
+ end
87
+
65
88
  context "when supplied with accumulator options" do
66
89
  let(:accumulator_options) { { foo: 'bar' } }
67
90
  subject { described_class.new(accumulator_class, accumulator_options) }
metadata CHANGED
@@ -1,55 +1,55 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: streamingly
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.5
4
+ version: 0.0.8
5
5
  platform: ruby
6
6
  authors:
7
7
  - Matt Gillooly
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2014-02-24 00:00:00.000000000 Z
11
+ date: 2014-07-08 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: bundler
15
15
  requirement: !ruby/object:Gem::Requirement
16
16
  requirements:
17
- - - ~>
17
+ - - "~>"
18
18
  - !ruby/object:Gem::Version
19
19
  version: '1.3'
20
20
  type: :development
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
- - - ~>
24
+ - - "~>"
25
25
  - !ruby/object:Gem::Version
26
26
  version: '1.3'
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: rake
29
29
  requirement: !ruby/object:Gem::Requirement
30
30
  requirements:
31
- - - '>='
31
+ - - ">="
32
32
  - !ruby/object:Gem::Version
33
33
  version: '0'
34
34
  type: :development
35
35
  prerelease: false
36
36
  version_requirements: !ruby/object:Gem::Requirement
37
37
  requirements:
38
- - - '>='
38
+ - - ">="
39
39
  - !ruby/object:Gem::Version
40
40
  version: '0'
41
41
  - !ruby/object:Gem::Dependency
42
42
  name: rspec
43
43
  requirement: !ruby/object:Gem::Requirement
44
44
  requirements:
45
- - - ~>
45
+ - - "~>"
46
46
  - !ruby/object:Gem::Version
47
47
  version: '2.11'
48
48
  type: :development
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
- - - ~>
52
+ - - "~>"
53
53
  - !ruby/object:Gem::Version
54
54
  version: '2.11'
55
55
  description: Helpful classes for writing streaming Hadoop jobs in Ruby
@@ -59,8 +59,8 @@ executables: []
59
59
  extensions: []
60
60
  extra_rdoc_files: []
61
61
  files:
62
- - .gitignore
63
- - .rspec
62
+ - ".gitignore"
63
+ - ".rspec"
64
64
  - Gemfile
65
65
  - LICENSE.txt
66
66
  - README.md
@@ -85,17 +85,17 @@ require_paths:
85
85
  - lib
86
86
  required_ruby_version: !ruby/object:Gem::Requirement
87
87
  requirements:
88
- - - '>='
88
+ - - ">="
89
89
  - !ruby/object:Gem::Version
90
90
  version: '0'
91
91
  required_rubygems_version: !ruby/object:Gem::Requirement
92
92
  requirements:
93
- - - '>='
93
+ - - ">="
94
94
  - !ruby/object:Gem::Version
95
95
  version: '0'
96
96
  requirements: []
97
97
  rubyforge_project:
98
- rubygems_version: 2.0.14
98
+ rubygems_version: 2.2.0
99
99
  signing_key:
100
100
  specification_version: 4
101
101
  summary: Helpful classes for writing streaming Hadoop jobs in Ruby