phonem_encoder 0.0.1
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.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +47 -0
- data/Rakefile +2 -0
- data/lib/phonem_encoder/CHANGELOG +3 -0
- data/lib/phonem_encoder/version.rb +3 -0
- data/lib/phonem_encoder.rb +74 -0
- data/phonem_encoder.gemspec +16 -0
- metadata +74 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Arndt Touby
|
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 +1,47 @@
|
|
1
|
+
# PHOMEN Encoder
|
2
|
+
|
3
|
+
Encode a string with the PHONEM algorithm. This gem can be used for finding strings by their phonetic sound - optimized for the german language.
|
4
|
+
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
Add this line to your application's Gemfile:
|
9
|
+
|
10
|
+
```ruby
|
11
|
+
gem 'phonem_encoder'
|
12
|
+
```
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install phonem_encoder
|
20
|
+
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
Call `phonetic_encode` on any string to get the phonetic code of the string.
|
25
|
+
|
26
|
+
```ruby
|
27
|
+
"Müller".phonetic_code
|
28
|
+
```
|
29
|
+
|
30
|
+
This will output "mylr"
|
31
|
+
|
32
|
+
|
33
|
+
## Development
|
34
|
+
|
35
|
+
Questions or problems? Please post them on the [issue tracker](https://github.com/arndttouby/phonem_encoder/issues).
|
36
|
+
|
37
|
+
|
38
|
+
## Contributing
|
39
|
+
|
40
|
+
1. Fork it
|
41
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
42
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
43
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
44
|
+
5. Create new Pull Request
|
45
|
+
|
46
|
+
|
47
|
+
This gem is craeted by Arndt Touby and is under the MIT License.
|
data/Rakefile
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
require "phonem_encoder/version"
|
2
|
+
|
3
|
+
module PhonemEncoder
|
4
|
+
class << self
|
5
|
+
def encode_string(string, length=2)
|
6
|
+
raise("length must be 1 or 2") if ![1,2].include?(length)
|
7
|
+
|
8
|
+
code = ''
|
9
|
+
string = string.downcase.gsub('ß','ss').gsub('ä', 'ae').gsub('ü', 'ue').scan(/./)
|
10
|
+
|
11
|
+
string.each_cons(length) do |chars|
|
12
|
+
if length == 2
|
13
|
+
case chars.join
|
14
|
+
when /^(sc|sz|cz|tz|ts)/ then
|
15
|
+
code << 'c'
|
16
|
+
when /^(ae)/ then
|
17
|
+
code << 'e'
|
18
|
+
when /^(pf)/ then
|
19
|
+
code << 'v'
|
20
|
+
when /^(ks)/ then
|
21
|
+
code << 'x'
|
22
|
+
when /^(qu)/ then
|
23
|
+
code << 'kw'
|
24
|
+
when /^(ow)/ then
|
25
|
+
code << 'ö'
|
26
|
+
when /^(ei|ey)/ then
|
27
|
+
code << 'ay'
|
28
|
+
when /^(eu)/ then
|
29
|
+
code << 'oy'
|
30
|
+
when /^(ou)/ then
|
31
|
+
code << 'u'
|
32
|
+
else
|
33
|
+
code << chars.join
|
34
|
+
end
|
35
|
+
else
|
36
|
+
case chars.join
|
37
|
+
when /^(z|k|g|q)/ then
|
38
|
+
code << 'c'
|
39
|
+
when /^(i|j)/ then
|
40
|
+
code << 'y'
|
41
|
+
when /^(f|w)/ then
|
42
|
+
code << 'v'
|
43
|
+
when /^(p)/ then
|
44
|
+
code << 'b'
|
45
|
+
when /^(t)/ then
|
46
|
+
code << 'd'
|
47
|
+
else
|
48
|
+
code << chars.join
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
code = encode_string(code, 1) if length == 2
|
54
|
+
|
55
|
+
reduce_multiples(code).scan(/[abcdlmnorsuvwxyö]/).join
|
56
|
+
end
|
57
|
+
|
58
|
+
def reduce_multiples(code)
|
59
|
+
unless code.gsub!(/(.)\1/, '\1').nil?
|
60
|
+
reduce_multiples(code)
|
61
|
+
end
|
62
|
+
|
63
|
+
code
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
def phonetic_code
|
68
|
+
PhonemEncoder.encode_string self.to_s
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
class String
|
73
|
+
include PhonemEncoder
|
74
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require File.expand_path('../lib/phonem_encoder/version', __FILE__)
|
2
|
+
|
3
|
+
Gem::Specification.new do |gem|
|
4
|
+
gem.authors = ["Arndt Touby"]
|
5
|
+
gem.email = ["arndt@touby.eu"]
|
6
|
+
gem.description = %q{This gem can be used for finding strings by their phonetic sound - optimized for the german language}
|
7
|
+
gem.summary = %q{Encode a string with the PHONEM algorithm}
|
8
|
+
gem.homepage = "http://github.com/arndttouby/phonem_encoder"
|
9
|
+
|
10
|
+
gem.files = `git ls-files`.split($\)
|
11
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
12
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
13
|
+
gem.name = "phonem_encoder"
|
14
|
+
gem.require_paths = ["lib"]
|
15
|
+
gem.version = PhonemEncoder::VERSION
|
16
|
+
end
|
metadata
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: phonem_encoder
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 29
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 1
|
10
|
+
version: 0.0.1
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Arndt Touby
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2012-09-12 00:00:00 Z
|
19
|
+
dependencies: []
|
20
|
+
|
21
|
+
description: This gem can be used for finding strings by their phonetic sound - optimized for the german language
|
22
|
+
email:
|
23
|
+
- arndt@touby.eu
|
24
|
+
executables: []
|
25
|
+
|
26
|
+
extensions: []
|
27
|
+
|
28
|
+
extra_rdoc_files: []
|
29
|
+
|
30
|
+
files:
|
31
|
+
- .gitignore
|
32
|
+
- Gemfile
|
33
|
+
- LICENSE
|
34
|
+
- README.md
|
35
|
+
- Rakefile
|
36
|
+
- lib/phonem_encoder.rb
|
37
|
+
- lib/phonem_encoder/CHANGELOG
|
38
|
+
- lib/phonem_encoder/version.rb
|
39
|
+
- phonem_encoder.gemspec
|
40
|
+
homepage: http://github.com/arndttouby/phonem_encoder
|
41
|
+
licenses: []
|
42
|
+
|
43
|
+
post_install_message:
|
44
|
+
rdoc_options: []
|
45
|
+
|
46
|
+
require_paths:
|
47
|
+
- lib
|
48
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ">="
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
hash: 3
|
54
|
+
segments:
|
55
|
+
- 0
|
56
|
+
version: "0"
|
57
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
|
+
none: false
|
59
|
+
requirements:
|
60
|
+
- - ">="
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
hash: 3
|
63
|
+
segments:
|
64
|
+
- 0
|
65
|
+
version: "0"
|
66
|
+
requirements: []
|
67
|
+
|
68
|
+
rubyforge_project:
|
69
|
+
rubygems_version: 1.8.22
|
70
|
+
signing_key:
|
71
|
+
specification_version: 3
|
72
|
+
summary: Encode a string with the PHONEM algorithm
|
73
|
+
test_files: []
|
74
|
+
|