sentino 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.document +5 -0
- data/Gemfile +15 -0
- data/Gemfile.lock +86 -0
- data/LICENSE.txt +20 -0
- data/README.rdoc +31 -0
- data/Rakefile +51 -0
- data/VERSION +1 -0
- data/lib/sentino/word.rb +36 -0
- data/lib/sentino.rb +5 -0
- data/test/helper.rb +34 -0
- data/test/test_sentino.rb +20 -0
- metadata +140 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 02701d80b54badf1f285fead072a79954eac92c6
|
4
|
+
data.tar.gz: 7fca4ebe8d6c983fc7b58b5b724bc3298b112e2a
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: fea7d2eada29dae5731cebb8cf072805f1850ffd231d788014b181a21fe7c07c57fca73db99af059ab18e84aa8501797fb29a938aa0d43f8fad1701340ee27cb
|
7
|
+
data.tar.gz: 432b18f8d105cac91eb29ae88f1a6d5651cf058fdb351531062e9501cf2e7169872ab377f01f27260de29ba9692e79de7c2194ad532bee11e3a3b5fda9d84321
|
data/.document
ADDED
data/Gemfile
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
source "https://rubygems.org"
|
2
|
+
# Add dependencies required to use your gem here.
|
3
|
+
# Example:
|
4
|
+
# gem "activesupport", ">= 2.3.5"
|
5
|
+
|
6
|
+
# Add dependencies to develop your gem here.
|
7
|
+
# Include everything needed to run rake, tests, features, etc.
|
8
|
+
group :development do
|
9
|
+
gem "shoulda", ">= 0"
|
10
|
+
gem "rdoc", "~> 3.12"
|
11
|
+
gem "bundler", "~> 1.0"
|
12
|
+
gem "jeweler", "~> 2.0.1"
|
13
|
+
gem "simplecov", ">= 0"
|
14
|
+
gem "test-unit"
|
15
|
+
end
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
GEM
|
2
|
+
remote: https://rubygems.org/
|
3
|
+
specs:
|
4
|
+
activesupport (4.2.6)
|
5
|
+
i18n (~> 0.7)
|
6
|
+
json (~> 1.7, >= 1.7.7)
|
7
|
+
minitest (~> 5.1)
|
8
|
+
thread_safe (~> 0.3, >= 0.3.4)
|
9
|
+
tzinfo (~> 1.1)
|
10
|
+
addressable (2.4.0)
|
11
|
+
builder (3.2.2)
|
12
|
+
descendants_tracker (0.0.4)
|
13
|
+
thread_safe (~> 0.3, >= 0.3.1)
|
14
|
+
docile (1.1.5)
|
15
|
+
faraday (0.9.2)
|
16
|
+
multipart-post (>= 1.2, < 3)
|
17
|
+
git (1.3.0)
|
18
|
+
github_api (0.13.1)
|
19
|
+
addressable (~> 2.4.0)
|
20
|
+
descendants_tracker (~> 0.0.4)
|
21
|
+
faraday (~> 0.8, < 0.10)
|
22
|
+
hashie (>= 3.4)
|
23
|
+
multi_json (>= 1.7.5, < 2.0)
|
24
|
+
oauth2
|
25
|
+
hashie (3.4.3)
|
26
|
+
highline (1.7.8)
|
27
|
+
i18n (0.7.0)
|
28
|
+
jeweler (2.0.1)
|
29
|
+
builder
|
30
|
+
bundler (>= 1.0)
|
31
|
+
git (>= 1.2.5)
|
32
|
+
github_api
|
33
|
+
highline (>= 1.6.15)
|
34
|
+
nokogiri (>= 1.5.10)
|
35
|
+
rake
|
36
|
+
rdoc
|
37
|
+
json (1.8.3)
|
38
|
+
jwt (1.5.1)
|
39
|
+
mini_portile2 (2.0.0)
|
40
|
+
minitest (5.8.4)
|
41
|
+
multi_json (1.11.2)
|
42
|
+
multi_xml (0.5.5)
|
43
|
+
multipart-post (2.0.0)
|
44
|
+
nokogiri (1.6.7.2)
|
45
|
+
mini_portile2 (~> 2.0.0.rc2)
|
46
|
+
oauth2 (1.1.0)
|
47
|
+
faraday (>= 0.8, < 0.10)
|
48
|
+
jwt (~> 1.0, < 1.5.2)
|
49
|
+
multi_json (~> 1.3)
|
50
|
+
multi_xml (~> 0.5)
|
51
|
+
rack (>= 1.2, < 3)
|
52
|
+
power_assert (0.2.7)
|
53
|
+
rack (1.6.4)
|
54
|
+
rake (11.1.2)
|
55
|
+
rdoc (3.12.2)
|
56
|
+
json (~> 1.4)
|
57
|
+
shoulda (3.5.0)
|
58
|
+
shoulda-context (~> 1.0, >= 1.0.1)
|
59
|
+
shoulda-matchers (>= 1.4.1, < 3.0)
|
60
|
+
shoulda-context (1.2.1)
|
61
|
+
shoulda-matchers (2.8.0)
|
62
|
+
activesupport (>= 3.0.0)
|
63
|
+
simplecov (0.11.2)
|
64
|
+
docile (~> 1.1.0)
|
65
|
+
json (~> 1.8)
|
66
|
+
simplecov-html (~> 0.10.0)
|
67
|
+
simplecov-html (0.10.0)
|
68
|
+
test-unit (3.1.8)
|
69
|
+
power_assert
|
70
|
+
thread_safe (0.3.5)
|
71
|
+
tzinfo (1.2.2)
|
72
|
+
thread_safe (~> 0.1)
|
73
|
+
|
74
|
+
PLATFORMS
|
75
|
+
ruby
|
76
|
+
|
77
|
+
DEPENDENCIES
|
78
|
+
bundler (~> 1.0)
|
79
|
+
jeweler (~> 2.0.1)
|
80
|
+
rdoc (~> 3.12)
|
81
|
+
shoulda
|
82
|
+
simplecov
|
83
|
+
test-unit
|
84
|
+
|
85
|
+
BUNDLED WITH
|
86
|
+
1.11.2
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2016 Ferhat Ziba
|
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 +1,31 @@
|
|
1
|
+
= sentino
|
2
|
+
|
3
|
+
An Sentence Compare Util. With Sentino you can match strings and get an value how much identical words are included.
|
4
|
+
|
5
|
+
Sentino is used by HanseHype to automap categories from differente XML Source
|
6
|
+
|
7
|
+
== How to use
|
8
|
+
|
9
|
+
sentino = Sentino::Word.new("This is an example sentence")
|
10
|
+
sentino.match("this is an other sentence") # => 0.8
|
11
|
+
|
12
|
+
== TODO
|
13
|
+
|
14
|
+
* Create differente compare Methods
|
15
|
+
* Make it configureable
|
16
|
+
|
17
|
+
== Contributing to sentino
|
18
|
+
|
19
|
+
* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
|
20
|
+
* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
|
21
|
+
* Fork the project.
|
22
|
+
* Start a feature/bugfix branch.
|
23
|
+
* Commit and push until you are happy with your contribution.
|
24
|
+
* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
|
25
|
+
* 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.
|
26
|
+
|
27
|
+
== Copyright
|
28
|
+
|
29
|
+
Copyright (c) 2016 Ferhat Ziba. See LICENSE.txt for
|
30
|
+
further details.
|
31
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'rubygems'
|
4
|
+
require 'bundler'
|
5
|
+
begin
|
6
|
+
Bundler.setup(:default, :development)
|
7
|
+
rescue Bundler::BundlerError => e
|
8
|
+
$stderr.puts e.message
|
9
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
10
|
+
exit e.status_code
|
11
|
+
end
|
12
|
+
require 'rake'
|
13
|
+
|
14
|
+
require 'jeweler'
|
15
|
+
Jeweler::Tasks.new do |gem|
|
16
|
+
# gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
|
17
|
+
gem.name = "sentino"
|
18
|
+
gem.homepage = "http://github.com/fero46/sentino"
|
19
|
+
gem.license = "MIT"
|
20
|
+
gem.summary = "Compare Strings by word"
|
21
|
+
gem.description = "Compare and give as result a matching result between 0 and 1"
|
22
|
+
gem.email = "fero.ziba@gmail.com"
|
23
|
+
gem.authors = ["Ferhat Ziba"]
|
24
|
+
# dependencies defined in Gemfile
|
25
|
+
end
|
26
|
+
Jeweler::RubygemsDotOrgTasks.new
|
27
|
+
|
28
|
+
require 'rake/testtask'
|
29
|
+
Rake::TestTask.new(:test) do |test|
|
30
|
+
test.libs << 'lib' << 'test'
|
31
|
+
test.pattern = 'test/**/test_*.rb'
|
32
|
+
test.verbose = true
|
33
|
+
end
|
34
|
+
|
35
|
+
desc "Code coverage detail"
|
36
|
+
task :simplecov do
|
37
|
+
ENV['COVERAGE'] = "true"
|
38
|
+
Rake::Task['test'].execute
|
39
|
+
end
|
40
|
+
|
41
|
+
task :default => :test
|
42
|
+
|
43
|
+
require 'rdoc/task'
|
44
|
+
Rake::RDocTask.new do |rdoc|
|
45
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
46
|
+
|
47
|
+
rdoc.rdoc_dir = 'rdoc'
|
48
|
+
rdoc.title = "sentino #{version}"
|
49
|
+
rdoc.rdoc_files.include('README*')
|
50
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
51
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
data/lib/sentino/word.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
module Sentino
|
2
|
+
class Word
|
3
|
+
|
4
|
+
def initialize(reference)
|
5
|
+
@reference = prepare_string(reference)
|
6
|
+
end
|
7
|
+
|
8
|
+
def match(string)
|
9
|
+
splitted_array = prepare_string(string)
|
10
|
+
check(splitted_array)
|
11
|
+
end
|
12
|
+
|
13
|
+
private
|
14
|
+
def prepare_string(string)
|
15
|
+
string.split(" ").map{|s| s.downcase}
|
16
|
+
end
|
17
|
+
|
18
|
+
def check(input_array)
|
19
|
+
hash = {}
|
20
|
+
for array in [@reference, input_array]
|
21
|
+
for element in array
|
22
|
+
if hash[element] == nil
|
23
|
+
hash[element]=0
|
24
|
+
end
|
25
|
+
hash[element]+=1
|
26
|
+
end
|
27
|
+
end
|
28
|
+
analyze = hash.map{|k,v| v}
|
29
|
+
total_length = analyze.map{|x| x == 0 ? 1 : x}.reduce(:+)
|
30
|
+
matching_length = analyze.map{|x| x == 1 ? 0 : x}.reduce(:+)
|
31
|
+
matching_length.to_f/total_length.to_f
|
32
|
+
end
|
33
|
+
|
34
|
+
|
35
|
+
end
|
36
|
+
end
|
data/lib/sentino.rb
ADDED
data/test/helper.rb
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
require 'simplecov'
|
2
|
+
|
3
|
+
module SimpleCov::Configuration
|
4
|
+
def clean_filters
|
5
|
+
@filters = []
|
6
|
+
end
|
7
|
+
end
|
8
|
+
|
9
|
+
SimpleCov.configure do
|
10
|
+
clean_filters
|
11
|
+
load_adapter 'test_frameworks'
|
12
|
+
end
|
13
|
+
|
14
|
+
ENV["COVERAGE"] && SimpleCov.start do
|
15
|
+
add_filter "/.rvm/"
|
16
|
+
end
|
17
|
+
require 'rubygems'
|
18
|
+
require 'bundler'
|
19
|
+
begin
|
20
|
+
Bundler.setup(:default, :development)
|
21
|
+
rescue Bundler::BundlerError => e
|
22
|
+
$stderr.puts e.message
|
23
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
24
|
+
exit e.status_code
|
25
|
+
end
|
26
|
+
require 'test/unit'
|
27
|
+
require 'shoulda'
|
28
|
+
|
29
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
30
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
31
|
+
require 'sentino'
|
32
|
+
|
33
|
+
class Test::Unit::TestCase
|
34
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestSentino < Test::Unit::TestCase
|
4
|
+
|
5
|
+
should "should give 1.0 for identical String" do
|
6
|
+
reference = "Der erste String Test"
|
7
|
+
target_1 = reference
|
8
|
+
sentino = Sentino::Word.new(reference)
|
9
|
+
assert_equal 1.0, sentino.match(target_1)
|
10
|
+
end
|
11
|
+
|
12
|
+
should "should give 75 % identical Words" do
|
13
|
+
reference = "Der erste String Test"
|
14
|
+
target_1 = reference.gsub("erste", "zweite")
|
15
|
+
sentino = Sentino::Word.new(reference)
|
16
|
+
assert_equal 0.75, sentino.match(target_1)
|
17
|
+
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
metadata
ADDED
@@ -0,0 +1,140 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: sentino
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ferhat Ziba
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-04-08 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: shoulda
|
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: rdoc
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3.12'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3.12'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: jeweler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 2.0.1
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 2.0.1
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: simplecov
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: test-unit
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description: Compare and give as result a matching result between 0 and 1
|
98
|
+
email: fero.ziba@gmail.com
|
99
|
+
executables: []
|
100
|
+
extensions: []
|
101
|
+
extra_rdoc_files:
|
102
|
+
- LICENSE.txt
|
103
|
+
- README.rdoc
|
104
|
+
files:
|
105
|
+
- ".document"
|
106
|
+
- Gemfile
|
107
|
+
- Gemfile.lock
|
108
|
+
- LICENSE.txt
|
109
|
+
- README.rdoc
|
110
|
+
- Rakefile
|
111
|
+
- VERSION
|
112
|
+
- lib/sentino.rb
|
113
|
+
- lib/sentino/word.rb
|
114
|
+
- test/helper.rb
|
115
|
+
- test/test_sentino.rb
|
116
|
+
homepage: http://github.com/fero46/sentino
|
117
|
+
licenses:
|
118
|
+
- MIT
|
119
|
+
metadata: {}
|
120
|
+
post_install_message:
|
121
|
+
rdoc_options: []
|
122
|
+
require_paths:
|
123
|
+
- lib
|
124
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
125
|
+
requirements:
|
126
|
+
- - ">="
|
127
|
+
- !ruby/object:Gem::Version
|
128
|
+
version: '0'
|
129
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
130
|
+
requirements:
|
131
|
+
- - ">="
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0'
|
134
|
+
requirements: []
|
135
|
+
rubyforge_project:
|
136
|
+
rubygems_version: 2.4.5.1
|
137
|
+
signing_key:
|
138
|
+
specification_version: 4
|
139
|
+
summary: Compare Strings by word
|
140
|
+
test_files: []
|