mongo_mapper_parallel 1.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/lib/mongo_mapper_parallel.rb +105 -0
- metadata +95 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
ZjgxNGEzYTAwMmQxOWJjMzY1YTM4YjZjYzRmZjBkYzQ3MWUxMThlMw==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
Njk4YjEyYjNmY2I5YjExODAyNzA5ZTNiNzRhNWJlYWUwNzA0N2NkYQ==
|
7
|
+
SHA512:
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
ODBjOTBhYjIzMTUyNTZjMTkyYTQ0N2IyMDA2YmI5YTVlNWQxMDZhN2VmZTVh
|
10
|
+
Y2VhOWFjZDk3NTM5NmQzYmU1MTRmYTlmYWJiY2NiMzYxNmRlZTRlYTljN2Q5
|
11
|
+
MjdjNjk2YmY1NjY0ZTViMTI3N2Y4ZmQ2NWZjMjVjYjgxYzczZjc=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
NDg0NmY2OWJjYzk1ZjVjNzQ1NTljMzQwYjViMjRiZWMzZTJkMmJmZThjZWYy
|
14
|
+
ZWM4ZDAzYmQ1OTE4ZmQzZGRjMjA5ZGM0NjZkNTU2MTNlOWI3YjllY2EzNGI3
|
15
|
+
MzNhYTc1YTcwN2Y5NGE0YWU3ZmI2OTVhYjgyZWI1MzMzZDk1ZDg=
|
@@ -0,0 +1,105 @@
|
|
1
|
+
# @title Mongo Mapper Parallel
|
2
|
+
# @author Jonathan Raiman
|
3
|
+
require 'parallel' # for parallel processing
|
4
|
+
require 'colorize' # for colored output
|
5
|
+
require 'mongo_mapper' # for access to collections.
|
6
|
+
|
7
|
+
class MongoMapperParallel
|
8
|
+
# runs distributed computation over a Mongo collection
|
9
|
+
|
10
|
+
attr_reader :split_keys
|
11
|
+
attr_accessor :command_class
|
12
|
+
attr_accessor :javascript
|
13
|
+
attr_accessor :args
|
14
|
+
|
15
|
+
class Key
|
16
|
+
# A chunk that will be parallelized
|
17
|
+
attr_accessor :future_key
|
18
|
+
attr_accessor :key
|
19
|
+
attr_accessor :completed
|
20
|
+
attr_reader :compiler
|
21
|
+
|
22
|
+
# A chunk that will be parallelized
|
23
|
+
#
|
24
|
+
# @param key [String] the lower bound of the range of resources to retrieve
|
25
|
+
# @param future_key [String] the upper bound for the range of resources to retrieve
|
26
|
+
# @param compiler [MongoMapperParallel] the Parallel execution object that holds the keys, javascript, and arguments.
|
27
|
+
#
|
28
|
+
def initialize(opts={})
|
29
|
+
@key = opts[:key]
|
30
|
+
@compiler = opts[:compiler]
|
31
|
+
@future_key = opts[:future_key]
|
32
|
+
@completed = false
|
33
|
+
end
|
34
|
+
|
35
|
+
# The javascript function to run on the resources
|
36
|
+
#
|
37
|
+
# @return [String] The function to run.
|
38
|
+
def javascript; @compiler.javascript; end
|
39
|
+
|
40
|
+
# The arguments to pass to the Javascript function to run on the resources
|
41
|
+
#
|
42
|
+
# @return [Array, Hash] The arguments to pass to the javascript function
|
43
|
+
#
|
44
|
+
def args; @compiler.args; end
|
45
|
+
|
46
|
+
# The Ruby Class representing the collection containing the resources
|
47
|
+
#
|
48
|
+
# @return [Class]
|
49
|
+
def command_class; @compiler.command_class; end
|
50
|
+
|
51
|
+
# Sends the Javascript function, the range, and the arguments to the MongoDB instance for computation via the `db.runCommand` command.
|
52
|
+
#
|
53
|
+
def compile
|
54
|
+
search_opts = {:name => {:$gte => @key}}
|
55
|
+
if @future_key then search_opts[:name][:$lte] = @future_key end
|
56
|
+
command_class.database.command({
|
57
|
+
:"$eval" => javascript,
|
58
|
+
:args => [@key, @future_key, args],
|
59
|
+
:nolock => true
|
60
|
+
})
|
61
|
+
@completed = true
|
62
|
+
puts "Completed chunk".green
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
# Obtains the splitVectors keys to find chunks to parallelize via the `splitVector` command.
|
67
|
+
#
|
68
|
+
# @return list [Array<MongoMapperParallel::Key>] the list of the keys that will be used for parallel operation
|
69
|
+
#
|
70
|
+
def get_split_keys
|
71
|
+
@split_keys, splits = [], @command_class.database.command({splitVector: "#{@command_class.database.name}.#{@command_class.collection.name}", keyPattern: {@split.to_sym => 1}, maxChunkSizeBytes: 32*1024*1024 })["splitKeys"]
|
72
|
+
splits.each_with_index do |split_key,k|
|
73
|
+
@split_keys << MongoMapperParallel::Key.new(:compiler => self, :key => split_key[@split.to_s], :future_key => (splits[k+1] ? splits[k+1][@split.to_s] : nil))
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
# Instantiates the parallel operation object with the right class, javascript function, and field
|
78
|
+
#
|
79
|
+
# @param class [Class] the Mongo collection's Ruby Class to execute operations on.
|
80
|
+
# @param javascript [String] the Javascript function in String format
|
81
|
+
# @param args [Array, Hash] the arguments to pass to the Javascript function
|
82
|
+
# @param split [String, Symbol] the field to split the computation on -- typically an indexed unique property of the resources in the collection.
|
83
|
+
# @return list [Array<MongoMapperParallel::Key>] the list of the keys that will be used for parallel operation.
|
84
|
+
#
|
85
|
+
def initialize(opts={})
|
86
|
+
@command_class = opts[:class]
|
87
|
+
@javascript = opts[:javascript]
|
88
|
+
@args = opts[:args]
|
89
|
+
@split = opts[:split] # name, title, etc...
|
90
|
+
get_split_keys()
|
91
|
+
self
|
92
|
+
end
|
93
|
+
|
94
|
+
# Starts the parallel processing using {https://github.com/grosser/parallel Parallel}.
|
95
|
+
#
|
96
|
+
def run
|
97
|
+
total = @split_keys.length
|
98
|
+
Parallel.each_with_index(@split_keys) do |section,k|
|
99
|
+
if !section.completed then section.compile end
|
100
|
+
# ProgressBar.displayPosition(k,total)
|
101
|
+
end
|
102
|
+
puts "Success".green
|
103
|
+
end
|
104
|
+
|
105
|
+
end
|
metadata
ADDED
@@ -0,0 +1,95 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: mongo_mapper_parallel
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jonathan Raiman
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-11-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: mongo_mapper
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ! '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ! '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: colorize
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ! '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ! '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: parallel
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ! '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ! '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description: Mongo Mapper Parallel can perform MapReduce-like operations on an entire
|
56
|
+
collection in parallel. This is a non-blocking operation, so the scripts can invoke
|
57
|
+
database methods (db.collection.update, db.collection.insert, etc...) at blazing
|
58
|
+
speed.
|
59
|
+
email: jraiman@mit.edu
|
60
|
+
executables: []
|
61
|
+
extensions: []
|
62
|
+
extra_rdoc_files: []
|
63
|
+
files:
|
64
|
+
- lib/mongo_mapper_parallel.rb
|
65
|
+
homepage: http://github.org/JonathanRaiman/mongo_mapper_parallel
|
66
|
+
licenses:
|
67
|
+
- MIT
|
68
|
+
metadata: {}
|
69
|
+
post_install_message:
|
70
|
+
rdoc_options: []
|
71
|
+
require_paths:
|
72
|
+
- lib
|
73
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ! '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
requirements:
|
84
|
+
- MongoDB, 2.4+
|
85
|
+
- mongo_mapper
|
86
|
+
- colorize
|
87
|
+
- Parallel
|
88
|
+
rubyforge_project:
|
89
|
+
rubygems_version: 2.1.10
|
90
|
+
signing_key:
|
91
|
+
specification_version: 4
|
92
|
+
summary: Extremely fast non-blocking parallel javascripts on entire MongoDB collection
|
93
|
+
with MongoMapper adapter.
|
94
|
+
test_files: []
|
95
|
+
has_rdoc: yard
|