trafficbroker-mandy 0.2.12 → 0.2.13
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/lib/job.rb +19 -2
- data/lib/mandy.rb +6 -4
- data/lib/mappers/base_mapper.rb +4 -2
- data/lib/reducers/base_reducer.rb +4 -2
- data/lib/serializers/json.rb +13 -0
- data/lib/support/formatting.rb +27 -0
- data/lib/task.rb +30 -7
- metadata +3 -1
data/lib/job.rb
CHANGED
@@ -26,6 +26,15 @@ module Mandy
|
|
26
26
|
def mixin(*modules)
|
27
27
|
modules.each {|m| @modules << m}
|
28
28
|
end
|
29
|
+
alias_method :serialize, :mixin
|
30
|
+
|
31
|
+
def input_format(format)
|
32
|
+
@input_format = format
|
33
|
+
end
|
34
|
+
|
35
|
+
def output_format(format)
|
36
|
+
@output_format = format
|
37
|
+
end
|
29
38
|
|
30
39
|
def set(key, value)
|
31
40
|
@settings[key.to_s] = value.to_s
|
@@ -61,15 +70,23 @@ module Mandy
|
|
61
70
|
end
|
62
71
|
|
63
72
|
def run_map(input=STDIN, output=STDOUT, &blk)
|
64
|
-
|
73
|
+
@mapper_class.send(:include, Mandy::IO::OutputFormatting) unless reducer_defined?
|
74
|
+
mapper = @mapper_class.new(input, output, @input_format, @output_format)
|
65
75
|
yield(mapper) if blk
|
66
76
|
mapper.execute
|
67
77
|
end
|
68
78
|
|
69
79
|
def run_reduce(input=STDIN, output=STDOUT, &blk)
|
70
|
-
reducer = @reducer_class.new(input, output)
|
80
|
+
reducer = @reducer_class.new(input, output, @input_format, @output_format)
|
71
81
|
yield(reducer) if blk
|
72
82
|
reducer.execute
|
73
83
|
end
|
84
|
+
|
85
|
+
private
|
86
|
+
|
87
|
+
def reducer_defined?
|
88
|
+
@reducer_class != Mandy::Reducers::PassThroughReducer
|
89
|
+
end
|
90
|
+
|
74
91
|
end
|
75
92
|
end
|
data/lib/mandy.rb
CHANGED
@@ -1,4 +1,9 @@
|
|
1
|
+
require "rubygems"
|
2
|
+
require "json"
|
3
|
+
require "uri"
|
4
|
+
|
1
5
|
%w(
|
6
|
+
support/formatting
|
2
7
|
task
|
3
8
|
dsl
|
4
9
|
job
|
@@ -14,16 +19,13 @@
|
|
14
19
|
reducers/max_reducer
|
15
20
|
reducers/min_reducer
|
16
21
|
reducers/transpose_reducer
|
22
|
+
serializers/json
|
17
23
|
stores/hbase
|
18
24
|
stores/in_memory
|
19
25
|
test_runner
|
20
26
|
ruby-hbase
|
21
27
|
).each {|file| require File.join(File.dirname(__FILE__), file) }
|
22
28
|
|
23
|
-
require "rubygems"
|
24
|
-
require "json"
|
25
|
-
require "uri"
|
26
|
-
|
27
29
|
module Mandy
|
28
30
|
class << self
|
29
31
|
def stores
|
data/lib/mappers/base_mapper.rb
CHANGED
@@ -1,6 +1,8 @@
|
|
1
1
|
module Mandy
|
2
2
|
module Mappers
|
3
3
|
class Base < Mandy::Task
|
4
|
+
include Mandy::IO::InputFormatting
|
5
|
+
|
4
6
|
def self.compile(&blk)
|
5
7
|
Class.new(Mandy::Mappers::Base) do
|
6
8
|
self.class_eval do
|
@@ -14,10 +16,10 @@ module Mandy
|
|
14
16
|
key, value = line.split(KEY_VALUE_SEPERATOR, 2)
|
15
17
|
key, value = nil, key if value.nil?
|
16
18
|
value.chomp!
|
17
|
-
mapper(key, value)
|
19
|
+
mapper(input_deserialize_key(key), input_deserialize_value(value))
|
18
20
|
end
|
19
21
|
end
|
20
|
-
|
22
|
+
|
21
23
|
private
|
22
24
|
|
23
25
|
def mapper(key,value)
|
@@ -1,6 +1,8 @@
|
|
1
1
|
module Mandy
|
2
2
|
module Reducers
|
3
3
|
class Base < Mandy::Task
|
4
|
+
include Mandy::IO::OutputFormatting
|
5
|
+
|
4
6
|
def self.compile(&blk)
|
5
7
|
Class.new(Mandy::Reducers::Base) do
|
6
8
|
self.class_eval do
|
@@ -21,11 +23,11 @@ module Mandy
|
|
21
23
|
end
|
22
24
|
values << value
|
23
25
|
end
|
24
|
-
reducer(last_key, values)
|
26
|
+
reducer(deserialize_key(last_key), values.map {|v| deserialize_value(v) })
|
25
27
|
end
|
26
28
|
|
27
29
|
private
|
28
|
-
|
30
|
+
|
29
31
|
def reducer(key,values)
|
30
32
|
#nil
|
31
33
|
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module Mandy
|
2
|
+
module IO
|
3
|
+
module InputFormatting
|
4
|
+
def input_deserialize_key(key)
|
5
|
+
return key if input_format && input_format == :plain
|
6
|
+
deserialize_key(key)
|
7
|
+
end
|
8
|
+
|
9
|
+
def input_deserialize_value(value)
|
10
|
+
return value if input_format && input_format == :plain
|
11
|
+
deserialize_value(value)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
module OutputFormatting
|
16
|
+
def output_serialize_key(key)
|
17
|
+
return key if output_format && output_format == :plain
|
18
|
+
serialize_key(key)
|
19
|
+
end
|
20
|
+
|
21
|
+
def output_serialize_value(value)
|
22
|
+
return value if output_format && output_format == :plain
|
23
|
+
serialize_value(value)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
data/lib/task.rb
CHANGED
@@ -3,18 +3,19 @@ module Mandy
|
|
3
3
|
JSON_PAYLOAD_KEY = "json"
|
4
4
|
KEY_VALUE_SEPERATOR = "\t" unless defined?(KEY_VALUE_SEPERATOR)
|
5
5
|
NUMERIC_PADDING = 16
|
6
|
-
|
7
|
-
|
6
|
+
|
7
|
+
attr_reader :input_format, :output_format
|
8
|
+
|
9
|
+
def initialize(input=STDIN, output=STDOUT, input_format = nil, output_format = nil)
|
8
10
|
@input, @output = input, output
|
11
|
+
@input_format, @output_format = input_format, output_format
|
9
12
|
end
|
10
13
|
|
11
14
|
def emit(key, value=nil)
|
12
15
|
key = 'nil' if key.nil?
|
13
|
-
|
14
|
-
|
15
|
-
@output.puts(value.nil? ? key.to_s : "#{serialize(key)}\t#{serialize(value)}")
|
16
|
+
@output.puts(value.nil? ? key.to_s : "#{output_serialize_key(key)}\t#{output_serialize_value(value)}")
|
16
17
|
end
|
17
|
-
|
18
|
+
|
18
19
|
def get(store, key)
|
19
20
|
Mandy.stores[store].get(key)
|
20
21
|
end
|
@@ -43,10 +44,32 @@ module Mandy
|
|
43
44
|
def json_provided?
|
44
45
|
!ENV[JSON_PAYLOAD_KEY].nil?
|
45
46
|
end
|
47
|
+
|
48
|
+
def deserialize_key(key)
|
49
|
+
key
|
50
|
+
end
|
51
|
+
|
52
|
+
def deserialize_value(value)
|
53
|
+
value
|
54
|
+
end
|
55
|
+
|
56
|
+
def serialize_key(key)
|
57
|
+
key = pad(key) if key.is_a?(Numeric) && key.to_s.length < NUMERIC_PADDING
|
58
|
+
key
|
59
|
+
end
|
46
60
|
|
47
|
-
def
|
61
|
+
def serialize_value(value)
|
48
62
|
value = ArraySerializer.new(value) if value.is_a?(Array)
|
49
63
|
value.to_s
|
50
64
|
end
|
65
|
+
|
66
|
+
def output_serialize_key(key)
|
67
|
+
serialize_key(key)
|
68
|
+
end
|
69
|
+
|
70
|
+
def output_serialize_value(value)
|
71
|
+
serialize_value(value)
|
72
|
+
end
|
73
|
+
|
51
74
|
end
|
52
75
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: trafficbroker-mandy
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.13
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andy Kent
|
@@ -40,6 +40,7 @@ files:
|
|
40
40
|
- Rakefile
|
41
41
|
- lib/mandy.rb
|
42
42
|
- lib/support/tuple.rb
|
43
|
+
- lib/support/formatting.rb
|
43
44
|
- lib/support/array_serializer.rb
|
44
45
|
- lib/task.rb
|
45
46
|
- lib/dsl.rb
|
@@ -54,6 +55,7 @@ files:
|
|
54
55
|
- lib/reducers/sum_reducer.rb
|
55
56
|
- lib/reducers/max_reducer.rb
|
56
57
|
- lib/reducers/min_reducer.rb
|
58
|
+
- lib/serializers/json.rb
|
57
59
|
- lib/stores/hbase.rb
|
58
60
|
- lib/stores/in_memory.rb
|
59
61
|
- lib/ruby-hbase.rb
|