dam_lev 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/.rvmrc +1 -0
- data/Gemfile +2 -0
- data/LICENSE +20 -0
- data/README.md +33 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/lib/dam_lev.rb +37 -0
- data/spec/DamLev_spec.rb +29 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +9 -0
- metadata +104 -0
data/.document
ADDED
data/.gitignore
ADDED
data/.rvmrc
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
rvm --create use 1.9.2@DamLev
|
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Allen Madsen
|
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.md
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# DamLev
|
2
|
+
|
3
|
+
DamLev implements the [Damerau–Levenshtein distance algorithm][1]. It is an algorithm that measures the distance between two strings taking into account deletions, insertions, substitutions, and transpositions. It's written in pure ruby.
|
4
|
+
|
5
|
+
[1]: http://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance
|
6
|
+
|
7
|
+
## Get it!
|
8
|
+
|
9
|
+
gem install dam_lev
|
10
|
+
|
11
|
+
## Use it!
|
12
|
+
|
13
|
+
require 'dam_lev'
|
14
|
+
|
15
|
+
DamLev.distance("DamLev", "DamLev") # => 0
|
16
|
+
DamLev.distance("DamLev", "Damev") # => 1 # deletion
|
17
|
+
DamLev.distance("DamLev", "DamLiev") # => 1 # insertion
|
18
|
+
DamLev.distance("DamLev", "Dam7ev") # => 1 # substitution
|
19
|
+
DamLev.distance("DamLev", "DameLv") # => 2 # transposition
|
20
|
+
|
21
|
+
## Note on Patches/Pull Requests
|
22
|
+
|
23
|
+
* Fork the project.
|
24
|
+
* Make your feature addition or bug fix.
|
25
|
+
* Add tests for it. This is important so I don't break it in a
|
26
|
+
future version unintentionally.
|
27
|
+
* Commit, do not mess with rakefile, version, or history.
|
28
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
29
|
+
* Send me a pull request. Bonus points for topic branches.
|
30
|
+
|
31
|
+
## Copyright
|
32
|
+
|
33
|
+
Copyright (c) 2010 Allen Madsen. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'rubygems'
|
4
|
+
require 'rake'
|
5
|
+
|
6
|
+
begin
|
7
|
+
require 'jeweler'
|
8
|
+
Jeweler::Tasks.new do |gem|
|
9
|
+
gem.name = "dam_lev"
|
10
|
+
gem.summary = %Q{Measure the distance between two strings.}
|
11
|
+
gem.description = %Q{Measures the distance between two strings using the Damerau–Levenshtein distance algorithm. For more, see http://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance }
|
12
|
+
gem.email = "blatyo@gmail.com"
|
13
|
+
gem.homepage = "http://github.com/blatyo/DamLev"
|
14
|
+
gem.authors = ["Allen Madsen"]
|
15
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
16
|
+
gem.add_development_dependency "yard", ">= 0"
|
17
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
18
|
+
end
|
19
|
+
Jeweler::GemcutterTasks.new
|
20
|
+
rescue LoadError
|
21
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
22
|
+
end
|
23
|
+
|
24
|
+
require 'spec/rake/spectask'
|
25
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
26
|
+
spec.libs << 'lib' << 'spec'
|
27
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
28
|
+
end
|
29
|
+
|
30
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
31
|
+
spec.libs << 'lib' << 'spec'
|
32
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
33
|
+
spec.rcov = true
|
34
|
+
end
|
35
|
+
|
36
|
+
task :spec => :check_dependencies
|
37
|
+
task :default => :spec
|
38
|
+
|
39
|
+
begin
|
40
|
+
require 'yard'
|
41
|
+
YARD::Rake::YardocTask.new
|
42
|
+
rescue LoadError
|
43
|
+
task :yardoc do
|
44
|
+
abort "YARD is not available. In order to run yardoc, you must: sudo gem install yard"
|
45
|
+
end
|
46
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
1.0.0
|
data/lib/dam_lev.rb
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
class DamLev
|
2
|
+
def self.distance(str1, str2)
|
3
|
+
return str1.length if str2.empty?
|
4
|
+
return str2.length if str1.empty?
|
5
|
+
|
6
|
+
distance_matrix = build_matrix(str1, str2)
|
7
|
+
|
8
|
+
(1..str1.length).each do |i|
|
9
|
+
(1..str2.length).each do |j|
|
10
|
+
sub_cost = str1[i-1] == str2[j-1] ? 0 : 1
|
11
|
+
|
12
|
+
distance_matrix[i][j] = [distance_matrix[i-1][j] + 1, # deletion
|
13
|
+
distance_matrix[i][j-1] + 1, # insertion
|
14
|
+
distance_matrix[i-1][j-1] + sub_cost].min # substitution
|
15
|
+
|
16
|
+
if i > 1 && j > 1 && str1[i-1] == str2[j-2] && str1[i-2] == str2[j-1]
|
17
|
+
distance_matrix[i+1][j+1] = [distance_matrix[i][j],
|
18
|
+
distance_matrix[i-2][j-2] + sub_cost].min # transposition
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
distance_matrix.last.last
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def self.build_matrix(str1, str2)
|
29
|
+
distance_matrix = [(0..str2.length).to_a]
|
30
|
+
|
31
|
+
(1..str1.length).each do |i|
|
32
|
+
distance_matrix[i] = [i]
|
33
|
+
end
|
34
|
+
|
35
|
+
distance_matrix
|
36
|
+
end
|
37
|
+
end
|
data/spec/DamLev_spec.rb
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
|
3
|
+
describe DamLev do
|
4
|
+
describe ".distance" do
|
5
|
+
it "should calculate a distance of zero between the same string" do
|
6
|
+
DamLev.distance("DamLev", "DamLev").should == 0
|
7
|
+
end
|
8
|
+
|
9
|
+
it "should calculate a distance of one when a character has been deleted between two strings" do
|
10
|
+
DamLev.distance("DamLev", "Damev").should == 1
|
11
|
+
end
|
12
|
+
|
13
|
+
it "should calculate a distance of one when a character has been inserted between two strings" do
|
14
|
+
DamLev.distance("DamLev", "DamLiev").should == 1
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should calculate a distance of one when a character has been substituted between two strings" do
|
18
|
+
DamLev.distance("DamLev", "Dam7ev").should == 1
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should calculate a distance of two when two characters have been swapped between two strings" do
|
22
|
+
DamLev.distance("DamLev", "DameLv").should == 2
|
23
|
+
end
|
24
|
+
|
25
|
+
it "should calculate a distance equal to the longest string if the other is empty" do
|
26
|
+
DamLev.distance("DamLev", "").should == "DamLev".length
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,104 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: dam_lev
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 1
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
version: 1.0.0
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Allen Madsen
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-07-04 00:00:00 -04:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: rspec
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - ">="
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
segments:
|
29
|
+
- 1
|
30
|
+
- 2
|
31
|
+
- 9
|
32
|
+
version: 1.2.9
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: yard
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
segments:
|
44
|
+
- 0
|
45
|
+
version: "0"
|
46
|
+
type: :development
|
47
|
+
version_requirements: *id002
|
48
|
+
description: "Measures the distance between two strings using the Damerau\xE2\x80\x93Levenshtein distance algorithm. For more, see http://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance "
|
49
|
+
email: blatyo@gmail.com
|
50
|
+
executables: []
|
51
|
+
|
52
|
+
extensions: []
|
53
|
+
|
54
|
+
extra_rdoc_files:
|
55
|
+
- LICENSE
|
56
|
+
- README.md
|
57
|
+
files:
|
58
|
+
- .document
|
59
|
+
- .gitignore
|
60
|
+
- .rvmrc
|
61
|
+
- Gemfile
|
62
|
+
- LICENSE
|
63
|
+
- README.md
|
64
|
+
- Rakefile
|
65
|
+
- VERSION
|
66
|
+
- lib/dam_lev.rb
|
67
|
+
- spec/DamLev_spec.rb
|
68
|
+
- spec/spec.opts
|
69
|
+
- spec/spec_helper.rb
|
70
|
+
has_rdoc: true
|
71
|
+
homepage: http://github.com/blatyo/DamLev
|
72
|
+
licenses: []
|
73
|
+
|
74
|
+
post_install_message:
|
75
|
+
rdoc_options:
|
76
|
+
- --charset=UTF-8
|
77
|
+
require_paths:
|
78
|
+
- lib
|
79
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
80
|
+
none: false
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
segments:
|
85
|
+
- 0
|
86
|
+
version: "0"
|
87
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
88
|
+
none: false
|
89
|
+
requirements:
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
segments:
|
93
|
+
- 0
|
94
|
+
version: "0"
|
95
|
+
requirements: []
|
96
|
+
|
97
|
+
rubyforge_project:
|
98
|
+
rubygems_version: 1.3.7
|
99
|
+
signing_key:
|
100
|
+
specification_version: 3
|
101
|
+
summary: Measure the distance between two strings.
|
102
|
+
test_files:
|
103
|
+
- spec/DamLev_spec.rb
|
104
|
+
- spec/spec_helper.rb
|