carrot2 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +73 -0
- data/Rakefile +2 -0
- data/carrot2.gemspec +20 -0
- data/lib/carrot2.rb +37 -0
- data/lib/carrot2/version.rb +3 -0
- metadata +91 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Andrew Kane
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
# Carrot2
|
2
|
+
|
3
|
+
Ruby client for Carrot2 - the **awesome** open-source document clustering server
|
4
|
+
|
5
|
+
## Usage
|
6
|
+
|
7
|
+
Download and run the Carrot2 server. [Great instructions here](http://project.carrot2.org/download-dcs.html)
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
require "carrot2"
|
11
|
+
|
12
|
+
documents = [
|
13
|
+
"Sign up for an exclusive coupon.",
|
14
|
+
"Exclusive members get a free coupon.",
|
15
|
+
"Coupons are going fast.",
|
16
|
+
"This is completely unrelated to the other documents."
|
17
|
+
]
|
18
|
+
|
19
|
+
carrot2 = Carrot2.new
|
20
|
+
carrot2.cluster(documents)
|
21
|
+
```
|
22
|
+
|
23
|
+
returns
|
24
|
+
|
25
|
+
```ruby
|
26
|
+
{
|
27
|
+
"processing-time-total"=>1,
|
28
|
+
"clusters"=> [
|
29
|
+
{
|
30
|
+
"id"=>0,
|
31
|
+
"size"=>3,
|
32
|
+
"phrases"=>["Coupon"],
|
33
|
+
"score"=>0.06462323710740674,
|
34
|
+
"documents"=>[0, 1, 2],
|
35
|
+
"attributes"=>{"score"=>0.06462323710740674}
|
36
|
+
},
|
37
|
+
{
|
38
|
+
"id"=>1,
|
39
|
+
"size"=>2,
|
40
|
+
"phrases"=>["Exclusive"],
|
41
|
+
"score"=>0.05873148311034013,
|
42
|
+
"documents"=>[0, 1],
|
43
|
+
"attributes"=>{"score"=>0.05873148311034013}
|
44
|
+
},
|
45
|
+
{
|
46
|
+
"id"=>2,
|
47
|
+
"size"=>1,
|
48
|
+
"phrases"=>["Other Topics"],
|
49
|
+
"score"=>0.0,
|
50
|
+
"documents"=>[3],
|
51
|
+
"attributes"=>{"other-topics"=>true, "score"=>0.0}
|
52
|
+
}
|
53
|
+
],
|
54
|
+
"processing-time-algorithm"=>1,
|
55
|
+
"query"=>nil
|
56
|
+
}
|
57
|
+
```
|
58
|
+
|
59
|
+
Documents are numbered in the order provided, starting with 0.
|
60
|
+
|
61
|
+
To specify the Carrot2 endpoint, use
|
62
|
+
|
63
|
+
```ruby
|
64
|
+
carrot2 = Carrot2.new("http://localhost:8080/dcs/rest") # default
|
65
|
+
```
|
66
|
+
|
67
|
+
## Contributing
|
68
|
+
|
69
|
+
1. Fork it
|
70
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
71
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
72
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
73
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/carrot2.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/carrot2/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Andrew Kane"]
|
6
|
+
gem.email = ["acekane1@gmail.com"]
|
7
|
+
gem.description = %q{Ruby client for Carrot2}
|
8
|
+
gem.summary = %q{Ruby client for Carrot2}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "carrot2"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = Carrot2::VERSION
|
17
|
+
|
18
|
+
gem.add_dependency "builder"
|
19
|
+
gem.add_dependency "rest-client"
|
20
|
+
end
|
data/lib/carrot2.rb
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
require "carrot2/version"
|
2
|
+
require "builder"
|
3
|
+
require "rest-client"
|
4
|
+
require "json"
|
5
|
+
|
6
|
+
class Carrot2
|
7
|
+
|
8
|
+
def initialize(endpoint = "http://localhost:8080/dcs/rest")
|
9
|
+
@endpoint = endpoint
|
10
|
+
end
|
11
|
+
|
12
|
+
def cluster(documents)
|
13
|
+
xml = Builder::XmlMarkup.new
|
14
|
+
xml.instruct! :xml, :version=>"1.0", :encoding=>"UTF-8"
|
15
|
+
xml.searchresult do |s|
|
16
|
+
documents.each do |document|
|
17
|
+
s.document do |d|
|
18
|
+
d.title document
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
params = {
|
24
|
+
"dcs.output.format" => "JSON",
|
25
|
+
"dcs.clusters.only" => true,
|
26
|
+
"dcs.c2stream" => xml.target!,
|
27
|
+
:multipart => true
|
28
|
+
}
|
29
|
+
response = RestClient.post @endpoint, params
|
30
|
+
if response.code == 200
|
31
|
+
JSON.parse(response.body)
|
32
|
+
else
|
33
|
+
raise "Bad response code from Carrot2 server: #{response.code}"
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
end
|
metadata
ADDED
@@ -0,0 +1,91 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: carrot2
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Andrew Kane
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-06-21 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: builder
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rest-client
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
description: Ruby client for Carrot2
|
47
|
+
email:
|
48
|
+
- acekane1@gmail.com
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- .gitignore
|
54
|
+
- Gemfile
|
55
|
+
- LICENSE
|
56
|
+
- README.md
|
57
|
+
- Rakefile
|
58
|
+
- carrot2.gemspec
|
59
|
+
- lib/carrot2.rb
|
60
|
+
- lib/carrot2/version.rb
|
61
|
+
homepage: ''
|
62
|
+
licenses: []
|
63
|
+
post_install_message:
|
64
|
+
rdoc_options: []
|
65
|
+
require_paths:
|
66
|
+
- lib
|
67
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
68
|
+
none: false
|
69
|
+
requirements:
|
70
|
+
- - ! '>='
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
version: '0'
|
73
|
+
segments:
|
74
|
+
- 0
|
75
|
+
hash: 389504047466366044
|
76
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
77
|
+
none: false
|
78
|
+
requirements:
|
79
|
+
- - ! '>='
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '0'
|
82
|
+
segments:
|
83
|
+
- 0
|
84
|
+
hash: 389504047466366044
|
85
|
+
requirements: []
|
86
|
+
rubyforge_project:
|
87
|
+
rubygems_version: 1.8.23
|
88
|
+
signing_key:
|
89
|
+
specification_version: 3
|
90
|
+
summary: Ruby client for Carrot2
|
91
|
+
test_files: []
|