rugroupy 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE.txt +20 -0
- data/README.rdoc +42 -0
- data/lib/rugroupy/entity.rb +86 -0
- data/lib/rugroupy/group.rb +101 -0
- data/lib/rugroupy.rb +2 -0
- metadata +193 -0
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2011 Ryan Wynn
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
= rugroupy
|
2
|
+
|
3
|
+
rugroupy is a ruby library which interacts with mongodb allowing one to tag entities and perform queries
|
4
|
+
to determine similarity between entities. rugroupy finds similarities by performing a series of map-reduce
|
5
|
+
operations using mongo. By using mongo's auto sharding capabilities rugroupy's grouping operation can
|
6
|
+
be distributed between multiple servers.
|
7
|
+
|
8
|
+
== features
|
9
|
+
* find entities most similiar to a given entity
|
10
|
+
* find the most similiar entities over the entire entity set
|
11
|
+
* use javascript to include only certain tags in the grouping operation
|
12
|
+
* use javascript to assign custom scoring to certain tags
|
13
|
+
* use javascript to create dynamic tags
|
14
|
+
|
15
|
+
== Examples
|
16
|
+
|
17
|
+
See http://github.com/rwynn/rugroupy/tree/master/test
|
18
|
+
|
19
|
+
== Requirements
|
20
|
+
|
21
|
+
* Mongo http://www.mongodb.org/downloads
|
22
|
+
* Mongo Ruby Driver http://www.mongodb.org/display/DOCS/Ruby+Language+Center#RubyLanguageCenter-RubyDriver
|
23
|
+
|
24
|
+
== Install
|
25
|
+
|
26
|
+
* sudo gem install rugroupy
|
27
|
+
|
28
|
+
== Contributing to rugroupy
|
29
|
+
|
30
|
+
* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
|
31
|
+
* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
|
32
|
+
* Fork the project
|
33
|
+
* Start a feature/bugfix branch
|
34
|
+
* Commit and push until you are happy with your contribution
|
35
|
+
* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
|
36
|
+
* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
|
37
|
+
|
38
|
+
== Copyright
|
39
|
+
|
40
|
+
Copyright (c) 2011 Ryan Wynn. See LICENSE.txt for
|
41
|
+
further details.
|
42
|
+
|
@@ -0,0 +1,86 @@
|
|
1
|
+
require 'mongo'
|
2
|
+
require 'bson'
|
3
|
+
|
4
|
+
module Groupy
|
5
|
+
|
6
|
+
class Entity
|
7
|
+
def initialize(database, name, entity_id, create=true)
|
8
|
+
@database, @name, @entity_id = database, name, entity_id
|
9
|
+
@database.create_collection(@name) if not @database.collection_names.member?(@name)
|
10
|
+
|
11
|
+
@database["#{@name}_count"].ensure_index([['_id.e', Mongo::DESCENDING],
|
12
|
+
['_id.tag', Mongo::DESCENDING],
|
13
|
+
['value.count', Mongo::DESCENDING]], :background => false)
|
14
|
+
|
15
|
+
if create
|
16
|
+
begin
|
17
|
+
doc = Hash["_id"=>@entity_id, "tags"=>Hash.new]
|
18
|
+
@database[@name].insert(doc, :safe=>true)
|
19
|
+
rescue Mongo::MongoDBError => e
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def get
|
25
|
+
@database[@name].find_one({ "_id" => @entity_id })
|
26
|
+
end
|
27
|
+
|
28
|
+
def delete
|
29
|
+
@database[@name].remove({"_id" => @entity_id}, :safe => true)
|
30
|
+
nil
|
31
|
+
end
|
32
|
+
|
33
|
+
def clear_tags
|
34
|
+
spec = {"_id" => @entity_id }
|
35
|
+
doc = {"$set" => { "tags" => Hash.new } }
|
36
|
+
@database[@name].update(spec, doc, :safe=>true)
|
37
|
+
nil
|
38
|
+
end
|
39
|
+
|
40
|
+
def has_tag(tag, value)
|
41
|
+
e = self.get()
|
42
|
+
e['tags'].member?(tag) and e['tags'][tag].member?(value)
|
43
|
+
end
|
44
|
+
|
45
|
+
def tag(tag, value)
|
46
|
+
self.apply_tag(tag, value)
|
47
|
+
nil
|
48
|
+
end
|
49
|
+
|
50
|
+
def untag(tag, value)
|
51
|
+
self.apply_tag(tag, value, add=false)
|
52
|
+
nil
|
53
|
+
end
|
54
|
+
|
55
|
+
def apply_tag(tag, value, add=true)
|
56
|
+
op = add ? "$addToSet" : "$pull"
|
57
|
+
doc = Hash.new
|
58
|
+
field = "tags.#{tag}"
|
59
|
+
if value.is_a?(String)
|
60
|
+
doc[op] = { field => value }
|
61
|
+
else
|
62
|
+
op = "$pullAll" unless add
|
63
|
+
doc[op] = add ? {field => {"$each" => value}} : {field => value}
|
64
|
+
end
|
65
|
+
spec = Hash["_id" => @entity_id]
|
66
|
+
@database[@name].update(spec, doc, :safe=>true)
|
67
|
+
nil
|
68
|
+
end
|
69
|
+
|
70
|
+
def similiar(tag=nil, skip=nil, limit=nil, reverse=false)
|
71
|
+
q = BSON::OrderedHash.new
|
72
|
+
q["_id.e"] = @entity_id
|
73
|
+
q["_id.tag"] = tag ? tag : {"$exists" => false}
|
74
|
+
cursor = @database["#{@name}_count"].find(q, :fields => {"_id.e" => 1})
|
75
|
+
cursor.skip(skip) if skip
|
76
|
+
cursor.limit(limit) if limit
|
77
|
+
cursor.sort("value.count", reverse ? Mongo::ASCENDING : Mongo::DESCENDING)
|
78
|
+
cursor.collect do |r|
|
79
|
+
pair = r["_id"]["e"]
|
80
|
+
pair[0] == @entity_id ? pair[1] : pair[0]
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
@@ -0,0 +1,101 @@
|
|
1
|
+
require 'mongo'
|
2
|
+
require 'bson'
|
3
|
+
|
4
|
+
module Groupy
|
5
|
+
|
6
|
+
class EntityGrouper
|
7
|
+
|
8
|
+
@@defaultScoreFunction = "function(tag) { return 1; }"
|
9
|
+
@@defaultIncludeFunction = "function(tag) { return true; }"
|
10
|
+
@@dynamicTagFunction = "function(doc) {}"
|
11
|
+
|
12
|
+
def initialize(database, entity)
|
13
|
+
@database, @entity = database, entity
|
14
|
+
@database["#{@entity}_count"].ensure_index([['_id.tag', Mongo::DESCENDING],
|
15
|
+
['value.count', Mongo::DESCENDING]], :background => false)
|
16
|
+
end
|
17
|
+
|
18
|
+
def similiar(tag=nil, skip=nil, limit=nil, reverse=false)
|
19
|
+
q = BSON::OrderedHash.new
|
20
|
+
q["_id.tag"] = tag ? tag : {"$exists" => false}
|
21
|
+
cursor = @database["#{@entity}_count"].find(q, :fields => {"_id.e" => 1})
|
22
|
+
cursor.skip(skip) if skip
|
23
|
+
cursor.limit(limit) if limit
|
24
|
+
cursor.sort("value.count", reverse ? Mongo::ASCENDING : Mongo::DESCENDING)
|
25
|
+
cursor.collect { |r| r["_id"]["e"] }
|
26
|
+
end
|
27
|
+
|
28
|
+
def group(options={})
|
29
|
+
self.invert_entities(options[:includeFunction] || @@defaultIncludeFunction,
|
30
|
+
options[:dynamicTagFunction] || @@dynamicTagFunction)
|
31
|
+
self.count_entities(options[:scoreFunction] || @@defaultScoreFunction)
|
32
|
+
end
|
33
|
+
|
34
|
+
def count_entities(scoreFunction)
|
35
|
+
map = BSON::Code.new(<<eos)
|
36
|
+
function() {
|
37
|
+
score = #{scoreFunction};
|
38
|
+
tag = this._id.tag;
|
39
|
+
tagScore = score(tag);
|
40
|
+
entities = this.value.entities.slice(0).sort();
|
41
|
+
for (x in entities) {
|
42
|
+
for (y in entities) {
|
43
|
+
if (x < y) {
|
44
|
+
emit({tag:tag, e:[entities[x], entities[y]]}, {count:tagScore});
|
45
|
+
emit({e:[entities[x], entities[y]]}, {count:tagScore});
|
46
|
+
}
|
47
|
+
}
|
48
|
+
}
|
49
|
+
}
|
50
|
+
eos
|
51
|
+
|
52
|
+
reduce = BSON::Code.new(<<eos)
|
53
|
+
function(key, values) {
|
54
|
+
result = {count:0};
|
55
|
+
values.forEach(function(value) {
|
56
|
+
result.count += value.count;
|
57
|
+
});
|
58
|
+
return result;
|
59
|
+
}
|
60
|
+
eos
|
61
|
+
|
62
|
+
@database["#{@entity}_invert"].map_reduce(map, reduce, :out => "#{@entity}_count")
|
63
|
+
nil
|
64
|
+
end
|
65
|
+
|
66
|
+
def invert_entities(includeFunction, dynamicTagFunction)
|
67
|
+
map = BSON::Code.new(<<eos)
|
68
|
+
function() {
|
69
|
+
include = #{includeFunction};
|
70
|
+
dynamicTagFunction = #{dynamicTagFunction};
|
71
|
+
entity_id = this._id;
|
72
|
+
if (this.tags) {
|
73
|
+
for (tag in this.tags) {
|
74
|
+
if (!include(tag)) continue;
|
75
|
+
this.tags[tag].forEach(function(z) {
|
76
|
+
emit({tag:tag, value:z}, {entities: [entity_id]});
|
77
|
+
});
|
78
|
+
}
|
79
|
+
dynamicTagFunction(this);
|
80
|
+
}
|
81
|
+
}
|
82
|
+
eos
|
83
|
+
|
84
|
+
reduce = BSON::Code.new(<<eos)
|
85
|
+
function(key, values) {
|
86
|
+
result = {entities:[]};
|
87
|
+
values.forEach(function(value) {
|
88
|
+
value['entities'].forEach(function(entity_id) {
|
89
|
+
result['entities'].push( entity_id );
|
90
|
+
});
|
91
|
+
});
|
92
|
+
return result;
|
93
|
+
}
|
94
|
+
eos
|
95
|
+
|
96
|
+
@database[@entity].map_reduce(map, reduce, :out => "#{@entity}_invert")
|
97
|
+
nil
|
98
|
+
end
|
99
|
+
|
100
|
+
end
|
101
|
+
end
|
data/lib/rugroupy.rb
ADDED
metadata
ADDED
@@ -0,0 +1,193 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rugroupy
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Ryan Wynn
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2011-08-17 00:00:00 Z
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
22
|
+
none: false
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
hash: 3
|
27
|
+
segments:
|
28
|
+
- 0
|
29
|
+
version: "0"
|
30
|
+
version_requirements: *id001
|
31
|
+
name: shoulda
|
32
|
+
prerelease: false
|
33
|
+
type: :development
|
34
|
+
- !ruby/object:Gem::Dependency
|
35
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
36
|
+
none: false
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
hash: 23
|
41
|
+
segments:
|
42
|
+
- 1
|
43
|
+
- 0
|
44
|
+
- 0
|
45
|
+
version: 1.0.0
|
46
|
+
version_requirements: *id002
|
47
|
+
name: bundler
|
48
|
+
prerelease: false
|
49
|
+
type: :development
|
50
|
+
- !ruby/object:Gem::Dependency
|
51
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ~>
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
hash: 7
|
57
|
+
segments:
|
58
|
+
- 1
|
59
|
+
- 6
|
60
|
+
- 4
|
61
|
+
version: 1.6.4
|
62
|
+
version_requirements: *id003
|
63
|
+
name: jeweler
|
64
|
+
prerelease: false
|
65
|
+
type: :development
|
66
|
+
- !ruby/object:Gem::Dependency
|
67
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
68
|
+
none: false
|
69
|
+
requirements:
|
70
|
+
- - ">="
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
hash: 3
|
73
|
+
segments:
|
74
|
+
- 0
|
75
|
+
version: "0"
|
76
|
+
version_requirements: *id004
|
77
|
+
name: rcov
|
78
|
+
prerelease: false
|
79
|
+
type: :development
|
80
|
+
- !ruby/object:Gem::Dependency
|
81
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
82
|
+
none: false
|
83
|
+
requirements:
|
84
|
+
- - ">="
|
85
|
+
- !ruby/object:Gem::Version
|
86
|
+
hash: 25
|
87
|
+
segments:
|
88
|
+
- 1
|
89
|
+
- 3
|
90
|
+
- 1
|
91
|
+
version: 1.3.1
|
92
|
+
version_requirements: *id005
|
93
|
+
name: mongo
|
94
|
+
prerelease: false
|
95
|
+
type: :development
|
96
|
+
- !ruby/object:Gem::Dependency
|
97
|
+
requirement: &id006 !ruby/object:Gem::Requirement
|
98
|
+
none: false
|
99
|
+
requirements:
|
100
|
+
- - ">="
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
hash: 25
|
103
|
+
segments:
|
104
|
+
- 1
|
105
|
+
- 3
|
106
|
+
- 1
|
107
|
+
version: 1.3.1
|
108
|
+
version_requirements: *id006
|
109
|
+
name: bson
|
110
|
+
prerelease: false
|
111
|
+
type: :development
|
112
|
+
- !ruby/object:Gem::Dependency
|
113
|
+
requirement: &id007 !ruby/object:Gem::Requirement
|
114
|
+
none: false
|
115
|
+
requirements:
|
116
|
+
- - ">="
|
117
|
+
- !ruby/object:Gem::Version
|
118
|
+
hash: 25
|
119
|
+
segments:
|
120
|
+
- 1
|
121
|
+
- 3
|
122
|
+
- 1
|
123
|
+
version: 1.3.1
|
124
|
+
version_requirements: *id007
|
125
|
+
name: bson_ext
|
126
|
+
prerelease: false
|
127
|
+
type: :development
|
128
|
+
- !ruby/object:Gem::Dependency
|
129
|
+
requirement: &id008 !ruby/object:Gem::Requirement
|
130
|
+
none: false
|
131
|
+
requirements:
|
132
|
+
- - ">="
|
133
|
+
- !ruby/object:Gem::Version
|
134
|
+
hash: 25
|
135
|
+
segments:
|
136
|
+
- 1
|
137
|
+
- 2
|
138
|
+
- 3
|
139
|
+
version: 1.2.3
|
140
|
+
version_requirements: *id008
|
141
|
+
name: SystemTimer
|
142
|
+
prerelease: false
|
143
|
+
type: :development
|
144
|
+
description: a library which uses the map-reduce capabilities of mongodb to group entities based on tags.
|
145
|
+
email: ryan.m.wynn@gmail.com
|
146
|
+
executables: []
|
147
|
+
|
148
|
+
extensions: []
|
149
|
+
|
150
|
+
extra_rdoc_files:
|
151
|
+
- LICENSE.txt
|
152
|
+
- README.rdoc
|
153
|
+
files:
|
154
|
+
- lib/rugroupy.rb
|
155
|
+
- lib/rugroupy/entity.rb
|
156
|
+
- lib/rugroupy/group.rb
|
157
|
+
- LICENSE.txt
|
158
|
+
- README.rdoc
|
159
|
+
homepage: http://github.com/rwynn/rugroupy
|
160
|
+
licenses:
|
161
|
+
- MIT
|
162
|
+
post_install_message:
|
163
|
+
rdoc_options: []
|
164
|
+
|
165
|
+
require_paths:
|
166
|
+
- lib
|
167
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
168
|
+
none: false
|
169
|
+
requirements:
|
170
|
+
- - ">="
|
171
|
+
- !ruby/object:Gem::Version
|
172
|
+
hash: 3
|
173
|
+
segments:
|
174
|
+
- 0
|
175
|
+
version: "0"
|
176
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
177
|
+
none: false
|
178
|
+
requirements:
|
179
|
+
- - ">="
|
180
|
+
- !ruby/object:Gem::Version
|
181
|
+
hash: 3
|
182
|
+
segments:
|
183
|
+
- 0
|
184
|
+
version: "0"
|
185
|
+
requirements: []
|
186
|
+
|
187
|
+
rubyforge_project:
|
188
|
+
rubygems_version: 1.8.6
|
189
|
+
signing_key:
|
190
|
+
specification_version: 3
|
191
|
+
summary: find things that are similiar to things
|
192
|
+
test_files: []
|
193
|
+
|