filter_word 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +5 -0
- data/.rspec +1 -0
- data/.travis.yml +4 -0
- data/CHANGELOG +7 -0
- data/MIT-LICENSE +20 -0
- data/README.markdown +73 -0
- data/Rakefile +7 -0
- data/benchmark/benchmark.rb +39 -0
- data/benchmark/text_test_100.txt +4 -0
- data/benchmark/text_test_1000.txt +25 -0
- data/benchmark/text_test_10000.txt +219 -0
- data/bin/harmonious_rseg +11 -0
- data/filter_word.gemspec +22 -0
- data/lib/filter_word.rb +34 -0
- data/lib/filter_word/app.rb +18 -0
- data/lib/filter_word/engines/dict.rb +51 -0
- data/lib/filter_word/engines/engine.rb +21 -0
- data/lib/filter_word/engines/english.rb +29 -0
- data/lib/filter_word/filters/conjunction.rb +13 -0
- data/lib/filter_word/filters/fullwidth.rb +21 -0
- data/lib/filter_word/filters/symbol.rb +18 -0
- data/lib/filter_word/model_additions.rb +20 -0
- data/lib/filter_word/railtie.rb +15 -0
- data/lib/filter_word/rseg.rb +150 -0
- data/lib/filter_word/version.rb +3 -0
- data/lib/generators/filter_word/setup/setup_generator.rb +15 -0
- data/lib/generators/filter_word/setup/templates/chinese_dictionary.txt +1511 -0
- data/lib/generators/filter_word/setup/templates/english_dictionary.txt +66 -0
- data/lib/tasks/generate_dictionary.rake +67 -0
- data/spec/filter_word_spec.rb +56 -0
- data/spec/model_additions_spec.rb +42 -0
- data/spec/spec_helper.rb +21 -0
- metadata +107 -0
@@ -0,0 +1,66 @@
|
|
1
|
+
6-4tianwang
|
2
|
+
89-64cdjp
|
3
|
+
ADMIN
|
4
|
+
Administrator
|
5
|
+
asshole
|
6
|
+
BLOWJOB
|
7
|
+
chinaliberal
|
8
|
+
chinamz
|
9
|
+
chinesenewsnet
|
10
|
+
Clockgemstone
|
11
|
+
creaders
|
12
|
+
Crestbone
|
13
|
+
dajiyuan
|
14
|
+
dfdz
|
15
|
+
DICK
|
16
|
+
falun
|
17
|
+
falundafa
|
18
|
+
Feelmistone
|
19
|
+
freechina
|
20
|
+
freenet
|
21
|
+
fuck
|
22
|
+
gcd
|
23
|
+
Gruepin
|
24
|
+
Guichuideng
|
25
|
+
HACKING
|
26
|
+
hongzhi
|
27
|
+
hrichina
|
28
|
+
HUANET
|
29
|
+
hypermart.net
|
30
|
+
incest
|
31
|
+
jiangdongriji
|
32
|
+
jiaochuang
|
33
|
+
jiaochun
|
34
|
+
KEFU
|
35
|
+
KISSMYASS
|
36
|
+
lihongzhi
|
37
|
+
minghui
|
38
|
+
minghuinews
|
39
|
+
nacb
|
40
|
+
Neckromancer
|
41
|
+
NMIS
|
42
|
+
PAPER64
|
43
|
+
penis
|
44
|
+
qiangjian
|
45
|
+
renminbao
|
46
|
+
renmingbao
|
47
|
+
SHIT
|
48
|
+
SUCKPENIS
|
49
|
+
taip
|
50
|
+
tibetalk
|
51
|
+
triangle
|
52
|
+
triangleboy
|
53
|
+
Tringel
|
54
|
+
UltraSurf
|
55
|
+
ustibet
|
56
|
+
voachinese
|
57
|
+
wangce
|
58
|
+
WEBZEN
|
59
|
+
wstaiji
|
60
|
+
xinsheng
|
61
|
+
YUMING
|
62
|
+
zangdu
|
63
|
+
ZHENGJIAN
|
64
|
+
ZHENGJIANWANG
|
65
|
+
ZHENSHANREN
|
66
|
+
zhuanfalun
|
@@ -0,0 +1,67 @@
|
|
1
|
+
require 'yaml'
|
2
|
+
|
3
|
+
namespace :filter_word do
|
4
|
+
desc "generate harmonious dictionary for use"
|
5
|
+
task :generate => :environment do
|
6
|
+
|
7
|
+
puts "Processing chinese words..."
|
8
|
+
tree = {}
|
9
|
+
model = ENV['model']
|
10
|
+
|
11
|
+
chinese_dictionary = model.nil? ? 'chinese_dictionary.txt' : "#{model}_chinese_dictionary.txt"
|
12
|
+
english_dictionary = model.nil? ? 'english_dictionary.txt' : "#{model}_english_dictionary.txt"
|
13
|
+
chinese_dictionary_path = File.join(Rails.root, 'config','filter_word', chinese_dictionary)
|
14
|
+
english_dictionary_path = File.join(Rails.root, 'config','filter_word', english_dictionary)
|
15
|
+
|
16
|
+
process(chinese_dictionary_path, tree)
|
17
|
+
File.open(hash_path(model), "wb") {|io| Marshal.dump(tree, io)}
|
18
|
+
puts 'chinese_dictionary hash Done'
|
19
|
+
|
20
|
+
puts 'Processing english words...'
|
21
|
+
english_dictionary_list = []
|
22
|
+
process_english_words(english_dictionary_path, english_dictionary_list)
|
23
|
+
File.open(yaml_path(model), "wb") {|io| YAML::dump(english_dictionary_list, io)}
|
24
|
+
puts 'english_dictionary yaml Done'
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def process_english_words(path,list)
|
29
|
+
File.open(path, 'r') do |file|
|
30
|
+
file.each_line{|line| list << line.gsub!("\n",'') }
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
def process(path, tree)
|
35
|
+
File.open(path, 'r') do |file|
|
36
|
+
file.each_line do |line|
|
37
|
+
node = nil
|
38
|
+
line.chars.each do |c|
|
39
|
+
next if c == "\n" || c == "\r"
|
40
|
+
if node
|
41
|
+
node[c] ||= {}
|
42
|
+
node = node[c]
|
43
|
+
else
|
44
|
+
tree[c] ||= Hash.new
|
45
|
+
node = tree[c]
|
46
|
+
end
|
47
|
+
end
|
48
|
+
node[:end] = true
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def hash_path(model = nil)
|
54
|
+
if model
|
55
|
+
File.join(Rails.root, 'config','filter_word',"#{model}_harmonious.hash")
|
56
|
+
else
|
57
|
+
File.join(Rails.root, 'config','filter_word','harmonious.hash')
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def yaml_path(model = nil)
|
62
|
+
if model
|
63
|
+
File.join(Rails.root, 'config','filter_word',"#{model}_harmonious_english.yml")
|
64
|
+
else
|
65
|
+
File.join(Rails.root, 'config','filter_word','harmonious_english.yml')
|
66
|
+
end
|
67
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'spec_helper'
|
4
|
+
|
5
|
+
describe FilterWord do
|
6
|
+
|
7
|
+
describe 'local' do
|
8
|
+
describe 'segment' do
|
9
|
+
it 'should return harmonious word for sentence' do
|
10
|
+
FilterWord.harmonious_words('戴秉国在中国').should == ['戴秉国']
|
11
|
+
end
|
12
|
+
|
13
|
+
it 'should return harmonious word for sentence under have model param' do
|
14
|
+
FilterWord.harmonious_words('戴秉国在中国', 'user').should == ['戴秉国']
|
15
|
+
end
|
16
|
+
|
17
|
+
it 'should return english,url and chinese words' do
|
18
|
+
FilterWord.harmonious_words('戴秉国 in china,watch cctv.com.let fuck it','user').should == ['戴秉国','fuck']
|
19
|
+
end
|
20
|
+
|
21
|
+
it 'should return english words under have model param' do
|
22
|
+
FilterWord.harmonious_words('Gruepin','user').should == ['Gruepin']
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
|
27
|
+
it 'should find harmonious chinese words' do
|
28
|
+
FilterWord.clean?('李源潮在中国').should == false
|
29
|
+
end
|
30
|
+
|
31
|
+
it 'should find harmonious chinese words under have model param' do
|
32
|
+
FilterWord.clean?('李源潮在中国', 'user').should == false
|
33
|
+
end
|
34
|
+
|
35
|
+
it 'should pass good words' do
|
36
|
+
FilterWord.clean?('过去').should == true
|
37
|
+
end
|
38
|
+
|
39
|
+
it 'should pass good words under have model param' do
|
40
|
+
FilterWord.clean?('过去', 'user').should == true
|
41
|
+
end
|
42
|
+
|
43
|
+
it 'should clean sentence by replace harmonious words by *' do
|
44
|
+
FilterWord.clean('戴秉国在中国').should == '***在中国'
|
45
|
+
end
|
46
|
+
|
47
|
+
it 'should clean sentence by replace harmonious words by * under model param' do
|
48
|
+
FilterWord.clean('戴秉国在中国', 'user').should == '***在中国'
|
49
|
+
end
|
50
|
+
|
51
|
+
it 'should replace harmonious with *' do
|
52
|
+
FilterWord.clean_word_basic('大米').should == '**'
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require 'spec_helper'
|
3
|
+
|
4
|
+
ActiveRecord::Base.establish_connection(:adapter => "sqlite3", :database => ":memory:")
|
5
|
+
|
6
|
+
ActiveRecord::Schema.define(:version => 1) do
|
7
|
+
create_table :posts do |t|
|
8
|
+
t.string :title
|
9
|
+
t.text :body
|
10
|
+
t.text :note
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
class Post < ActiveRecord::Base
|
15
|
+
extend FilterWord::ModelAdditions
|
16
|
+
validate_harmonious_of [:title,:body], model: :post
|
17
|
+
end
|
18
|
+
|
19
|
+
describe FilterWord::ModelAdditions do
|
20
|
+
let(:post) { @post = Post.create title:'戴秉国在中国',body:'戴秉国在中国',note:'戴秉国在中国' }
|
21
|
+
|
22
|
+
describe 'use local' do
|
23
|
+
it 'should validate for harmonious' do
|
24
|
+
post.errors[:title].should == ['不能含有敏感词']
|
25
|
+
end
|
26
|
+
|
27
|
+
it 'should have error on title' do
|
28
|
+
post.errors[:body].should == ['不能含有敏感词']
|
29
|
+
end
|
30
|
+
|
31
|
+
it 'should allow empty input value' do
|
32
|
+
p = Post.create body:'戴秉国在中国',note:'戴秉国在中国'
|
33
|
+
post.errors[:body].should == ['不能含有敏感词']
|
34
|
+
end
|
35
|
+
|
36
|
+
it 'should filter! any harmonious words' do
|
37
|
+
FilterWord.clean(post.body).should == '***在中国'
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
42
|
+
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
|
3
|
+
require 'rails'
|
4
|
+
require 'active_model'
|
5
|
+
require 'active_record'
|
6
|
+
require 'filter_word'
|
7
|
+
|
8
|
+
RSpec.configure do |config|
|
9
|
+
config.color_enabled = true
|
10
|
+
config.formatter = 'documentation'
|
11
|
+
end
|
12
|
+
|
13
|
+
module Rails
|
14
|
+
def self.root
|
15
|
+
File.join File.dirname(__FILE__),'../'
|
16
|
+
end
|
17
|
+
|
18
|
+
def self.env
|
19
|
+
'test'
|
20
|
+
end
|
21
|
+
end
|
metadata
ADDED
@@ -0,0 +1,107 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: filter_word
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- xiaobo
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-09-08 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rake
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
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: rspec
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: "和谐检测用于检查输入是否包含中文或英文敏感词."
|
42
|
+
email:
|
43
|
+
- peterwillcn@gmail.com
|
44
|
+
executables:
|
45
|
+
- harmonious_rseg
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- ".gitignore"
|
50
|
+
- ".rspec"
|
51
|
+
- ".travis.yml"
|
52
|
+
- CHANGELOG
|
53
|
+
- MIT-LICENSE
|
54
|
+
- README.markdown
|
55
|
+
- Rakefile
|
56
|
+
- benchmark/benchmark.rb
|
57
|
+
- benchmark/text_test_100.txt
|
58
|
+
- benchmark/text_test_1000.txt
|
59
|
+
- benchmark/text_test_10000.txt
|
60
|
+
- bin/harmonious_rseg
|
61
|
+
- filter_word.gemspec
|
62
|
+
- lib/filter_word.rb
|
63
|
+
- lib/filter_word/app.rb
|
64
|
+
- lib/filter_word/engines/dict.rb
|
65
|
+
- lib/filter_word/engines/engine.rb
|
66
|
+
- lib/filter_word/engines/english.rb
|
67
|
+
- lib/filter_word/filters/conjunction.rb
|
68
|
+
- lib/filter_word/filters/fullwidth.rb
|
69
|
+
- lib/filter_word/filters/symbol.rb
|
70
|
+
- lib/filter_word/model_additions.rb
|
71
|
+
- lib/filter_word/railtie.rb
|
72
|
+
- lib/filter_word/rseg.rb
|
73
|
+
- lib/filter_word/version.rb
|
74
|
+
- lib/generators/filter_word/setup/setup_generator.rb
|
75
|
+
- lib/generators/filter_word/setup/templates/chinese_dictionary.txt
|
76
|
+
- lib/generators/filter_word/setup/templates/english_dictionary.txt
|
77
|
+
- lib/tasks/generate_dictionary.rake
|
78
|
+
- spec/filter_word_spec.rb
|
79
|
+
- spec/model_additions_spec.rb
|
80
|
+
- spec/spec_helper.rb
|
81
|
+
homepage: https://github.com/tian-xiaobo/filter_word
|
82
|
+
licenses: []
|
83
|
+
metadata: {}
|
84
|
+
post_install_message:
|
85
|
+
rdoc_options: []
|
86
|
+
require_paths:
|
87
|
+
- lib
|
88
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
89
|
+
requirements:
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: '0'
|
93
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
requirements: []
|
99
|
+
rubyforge_project:
|
100
|
+
rubygems_version: 2.4.5.1
|
101
|
+
signing_key:
|
102
|
+
specification_version: 4
|
103
|
+
summary: filter any words that need to be harmonized
|
104
|
+
test_files:
|
105
|
+
- spec/filter_word_spec.rb
|
106
|
+
- spec/model_additions_spec.rb
|
107
|
+
- spec/spec_helper.rb
|