plagiarism2 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +11 -0
- data/.rspec +2 -0
- data/.travis.yml +4 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +54 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/plagiarism.rb +19 -0
- data/lib/plagiarism/config.rb +9 -0
- data/lib/plagiarism/strategries/bing.rb +23 -0
- data/lib/plagiarism/strategries/duck.rb +25 -0
- data/lib/plagiarism/strategries/engine.rb +41 -0
- data/lib/plagiarism/strategries/google.rb +24 -0
- data/lib/plagiarism/strategries/yahoo.rb +25 -0
- data/lib/plagiarism/strategy.rb +22 -0
- data/lib/plagiarism/version.rb +3 -0
- data/plagiarism.gemspec +29 -0
- metadata +147 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 253b52f49b6d8943468f5f58aabe4d98eb0d19b1
|
4
|
+
data.tar.gz: 6ed790050a1d5efe1715ad596e5f67047a2d82bc
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: c7a9fcf7eb0cfdb33c1521be06a8fed18880c7e24fa4661a151fdc69a1700c45af00693657bbf83759cfc0015bba8369e8df6f525e616de299fe317ca6f30d2f
|
7
|
+
data.tar.gz: 9560ccc5cb705f9c6a07601f69d14fa6863f56962a62a0261fe87ea663d7a45136ec89be1d6aefd4d5bda770c0df2c41feb9b54dec050e9c69876feee9579bc1
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 MQuy
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
# Plagiarism
|
2
|
+
|
3
|
+
Search for plagiarism and check the duplication of your content from Bing, Google, Yahoo and DuckDuckGo.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
```ruby
|
8
|
+
gem 'plagiarism2', require: 'plagiarism'
|
9
|
+
```
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install plagiarism2
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Add in your config
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
Plagiarism.configure do |config|
|
25
|
+
config.strategies = [xxx] # => [:google, :bing, :duck, :yahoo]
|
26
|
+
config.whitelists = ['www.ring.md']
|
27
|
+
end
|
28
|
+
```
|
29
|
+
|
30
|
+
In case of using bing engine, you have to set access key
|
31
|
+
|
32
|
+
```ruby
|
33
|
+
config.bing_key = xxx
|
34
|
+
```
|
35
|
+
|
36
|
+
After that you can check the unique of content
|
37
|
+
|
38
|
+
```ruby
|
39
|
+
text = 'Latte user story paradigm affordances experiential innovate venture capital physical computing. Ship it agile actionable insight iterate thought leader pitch deck experiential iterate. Venture capital food-truck quantitative vs. qualitative SpaceTeam convergence agile.'
|
40
|
+
Plagiarism.unique? text
|
41
|
+
```
|
42
|
+
|
43
|
+
`Plagiarism.unique?` is true when all strategies is true
|
44
|
+
|
45
|
+
## Contributing
|
46
|
+
|
47
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/MQuy/plagiarism. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
48
|
+
|
49
|
+
> Disclaim: Yahoo and DuckDuckGo don't support api, therefore I have to crawl data, if you find any solution to fix, please help me.
|
50
|
+
|
51
|
+
## License
|
52
|
+
|
53
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
54
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "plagiarism"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/plagiarism.rb
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
require 'typhoeus'
|
2
|
+
require 'pragmatic_segmenter'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
require 'plagiarism/version'
|
6
|
+
require 'plagiarism/config'
|
7
|
+
require 'plagiarism/strategy'
|
8
|
+
|
9
|
+
module Plagiarism
|
10
|
+
extend self
|
11
|
+
|
12
|
+
def configure
|
13
|
+
yield Config
|
14
|
+
end
|
15
|
+
|
16
|
+
def unique?(content, params = {})
|
17
|
+
Strategy.unique?(content, params)
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module Plagiarism
|
2
|
+
module Strategies
|
3
|
+
class Bing < Engine
|
4
|
+
URL = 'https://api.datamarket.azure.com/Bing/SearchWeb/v1/Web'
|
5
|
+
|
6
|
+
class << self
|
7
|
+
|
8
|
+
def fetch(content, params)
|
9
|
+
Typhoeus.get(URL, params: params.merge('$format' => :json, 'Query' => "'#{content}'"), userpwd: ":#{Config.bing_key}")
|
10
|
+
end
|
11
|
+
|
12
|
+
def exists?(response)
|
13
|
+
JSON.parse(response)['d']['results'].all? do |r|
|
14
|
+
uri = URI.parse(r['Url'])
|
15
|
+
uri.host =~ whitelists_regex
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module Plagiarism
|
2
|
+
module Strategies
|
3
|
+
class Duck < Engine
|
4
|
+
URL = 'https://duckduckgo.com/html'
|
5
|
+
|
6
|
+
class << self
|
7
|
+
|
8
|
+
def fetch(content, params)
|
9
|
+
Typhoeus.get(URL, params: params.merge(q: content))
|
10
|
+
end
|
11
|
+
|
12
|
+
def exists?(response)
|
13
|
+
doc = Nokogiri::HTML response
|
14
|
+
doc.css('.results_links_deep').all? do |row|
|
15
|
+
href = row.at_css('.result__a').attributes['href'].value rescue ''
|
16
|
+
uri = URI.parse href
|
17
|
+
uri.host =~ whitelists_regex
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
module Plagiarism
|
2
|
+
module Strategies
|
3
|
+
class Engine
|
4
|
+
THRESHOLD = 0.8
|
5
|
+
|
6
|
+
attr_accessor :content, :params
|
7
|
+
|
8
|
+
class << self
|
9
|
+
def fetch(content, params)
|
10
|
+
raise
|
11
|
+
end
|
12
|
+
|
13
|
+
def valid_segments(ps, params)
|
14
|
+
ps.segment.count do |sentence|
|
15
|
+
typhoeus = fetch("\"#{sentence}\"", params)
|
16
|
+
exists?(typhoeus.response_body)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def exists?(response)
|
21
|
+
raise
|
22
|
+
end
|
23
|
+
|
24
|
+
def whitelists_regex
|
25
|
+
whitelists = Config.whitelists.map { |w| Regexp.new w }
|
26
|
+
Regexp.union whitelists
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def initialize(c, p)
|
31
|
+
@content, @params = c, p
|
32
|
+
end
|
33
|
+
|
34
|
+
def unique?
|
35
|
+
ps = PragmaticSegmenter::Segmenter.new(text: content)
|
36
|
+
valid_segments = self.class.valid_segments(ps, params)
|
37
|
+
valid_segments / ps.segment.size >= THRESHOLD
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
module Plagiarism
|
2
|
+
module Strategies
|
3
|
+
class Google < Engine
|
4
|
+
URL = 'https://ajax.googleapis.com/ajax/services/search/web'
|
5
|
+
VERSION = '1.0'
|
6
|
+
|
7
|
+
class << self
|
8
|
+
|
9
|
+
def fetch(content, params)
|
10
|
+
Typhoeus.get URL, params: params.merge(v: VERSION, q: content, rsz: :large)
|
11
|
+
end
|
12
|
+
|
13
|
+
def exists?(response)
|
14
|
+
JSON.parse(response)['responseData']['results'].all? do |r|
|
15
|
+
uri = URI.parse(r['unescapedUrl'])
|
16
|
+
uri.host =~ whitelists_regex
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
21
|
+
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module Plagiarism
|
2
|
+
module Strategies
|
3
|
+
class Yahoo < Engine
|
4
|
+
URL = 'https://search.yahoo.com/search'
|
5
|
+
|
6
|
+
class << self
|
7
|
+
|
8
|
+
def fetch(content, params)
|
9
|
+
Typhoeus.get(URL, params: params.merge(p: content))
|
10
|
+
end
|
11
|
+
|
12
|
+
def exists?(response)
|
13
|
+
doc = Nokogiri::HTML response
|
14
|
+
doc.css('.searchCenterMiddle li').all? do |row|
|
15
|
+
href = row.at_css('.compTitle div').content.strip rescue ''
|
16
|
+
uri = URI.parse(href =~ /^http/ ? href : 'https://' + href)
|
17
|
+
uri.host =~ whitelists_regex
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require 'plagiarism/strategries/engine'
|
2
|
+
require 'plagiarism/strategries/google'
|
3
|
+
require 'plagiarism/strategries/bing'
|
4
|
+
require 'plagiarism/strategries/duck'
|
5
|
+
require 'plagiarism/strategries/yahoo'
|
6
|
+
|
7
|
+
module Plagiarism
|
8
|
+
module Strategy
|
9
|
+
extend self
|
10
|
+
|
11
|
+
def get(name = :google)
|
12
|
+
Strategies.const_get(name.to_s.classify)
|
13
|
+
end
|
14
|
+
|
15
|
+
def unique?(content, params)
|
16
|
+
Config.strategies.all? do |strategy|
|
17
|
+
klass = get(strategy)
|
18
|
+
klass.new(content, params).unique?
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
data/plagiarism.gemspec
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'plagiarism/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "plagiarism2"
|
8
|
+
spec.version = Plagiarism::VERSION
|
9
|
+
spec.authors = ["MQuy"]
|
10
|
+
spec.email = ["sugiacupit@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Check the unique content on internet.}
|
13
|
+
spec.description = %q{Check the unique content on internet from bing, google, yahoo and duckduckgo.}
|
14
|
+
spec.homepage = "https://github.com/MQuy/plagiarism"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
23
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
24
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
25
|
+
|
26
|
+
spec.add_dependency 'typhoeus', '~> 1.0'
|
27
|
+
spec.add_dependency 'pragmatic_segmenter', '~> 0.3'
|
28
|
+
spec.add_dependency 'nokogiri', '~> 1.6'
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,147 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: plagiarism2
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- MQuy
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-04-01 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.11'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.11'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: typhoeus
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: pragmatic_segmenter
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0.3'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0.3'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: nokogiri
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.6'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.6'
|
97
|
+
description: Check the unique content on internet from bing, google, yahoo and duckduckgo.
|
98
|
+
email:
|
99
|
+
- sugiacupit@gmail.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".gitignore"
|
105
|
+
- ".rspec"
|
106
|
+
- ".travis.yml"
|
107
|
+
- Gemfile
|
108
|
+
- LICENSE.txt
|
109
|
+
- README.md
|
110
|
+
- Rakefile
|
111
|
+
- bin/console
|
112
|
+
- bin/setup
|
113
|
+
- lib/plagiarism.rb
|
114
|
+
- lib/plagiarism/config.rb
|
115
|
+
- lib/plagiarism/strategries/bing.rb
|
116
|
+
- lib/plagiarism/strategries/duck.rb
|
117
|
+
- lib/plagiarism/strategries/engine.rb
|
118
|
+
- lib/plagiarism/strategries/google.rb
|
119
|
+
- lib/plagiarism/strategries/yahoo.rb
|
120
|
+
- lib/plagiarism/strategy.rb
|
121
|
+
- lib/plagiarism/version.rb
|
122
|
+
- plagiarism.gemspec
|
123
|
+
homepage: https://github.com/MQuy/plagiarism
|
124
|
+
licenses:
|
125
|
+
- MIT
|
126
|
+
metadata: {}
|
127
|
+
post_install_message:
|
128
|
+
rdoc_options: []
|
129
|
+
require_paths:
|
130
|
+
- lib
|
131
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ">="
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '0'
|
136
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
137
|
+
requirements:
|
138
|
+
- - ">="
|
139
|
+
- !ruby/object:Gem::Version
|
140
|
+
version: '0'
|
141
|
+
requirements: []
|
142
|
+
rubyforge_project:
|
143
|
+
rubygems_version: 2.5.1
|
144
|
+
signing_key:
|
145
|
+
specification_version: 4
|
146
|
+
summary: Check the unique content on internet.
|
147
|
+
test_files: []
|