korean-string 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.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +33 -0
- data/Rakefile +53 -0
- data/VERSION +1 -0
- data/lib/korean-string.rb +112 -0
- data/test/helper.rb +9 -0
- data/test/test_korean-string.rb +38 -0
- metadata +77 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Ben Humphreys
|
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 +1,33 @@
|
|
1
|
+
= korean-string
|
2
|
+
|
3
|
+
Split Korean characters to individual compontents, join components together to create characters.
|
4
|
+
|
5
|
+
You could use it to make some weird conjugation rules. Go wild.
|
6
|
+
|
7
|
+
== Methods
|
8
|
+
|
9
|
+
=== String.split_ko
|
10
|
+
|
11
|
+
Return an array of arrays of Korean character components
|
12
|
+
|
13
|
+
require 'korean-string'
|
14
|
+
'읽어싶'.split_ko
|
15
|
+
=> [["ㅇ", "ㅣ", "ㄺ"], ["ㅇ", "ㅓ"], ["ㅅ", "ㅣ", "ㅍ"]]
|
16
|
+
|
17
|
+
=== Array.join_ko
|
18
|
+
|
19
|
+
Accepts an array of character pieces
|
20
|
+
|
21
|
+
require 'korean-string'
|
22
|
+
[["ㅇ", "ㅣ", "ㄺ"], ["ㅇ", "ㅓ"], ["ㅅ", "ㅣ", "ㅍ"]].join_ko
|
23
|
+
=> '읽어싶'
|
24
|
+
|
25
|
+
|
26
|
+
== Todo
|
27
|
+
|
28
|
+
Come up with other useful methods?
|
29
|
+
|
30
|
+
|
31
|
+
== Copyright
|
32
|
+
|
33
|
+
Copyright (c) 2010 Ben Humphreys. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "korean-string"
|
8
|
+
gem.summary = %Q{Korean string join and split}
|
9
|
+
gem.description = %Q{Split Korean characters to individual compontents, join components together to create characters}
|
10
|
+
gem.email = "benhumphreys@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/bhumphreys/korean-string"
|
12
|
+
gem.authors = ["Ben Humphreys"]
|
13
|
+
#gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
|
14
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
15
|
+
end
|
16
|
+
Jeweler::GemcutterTasks.new
|
17
|
+
rescue LoadError
|
18
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
19
|
+
end
|
20
|
+
|
21
|
+
require 'rake/testtask'
|
22
|
+
Rake::TestTask.new(:test) do |test|
|
23
|
+
test.libs << 'lib' << 'test'
|
24
|
+
test.pattern = 'test/**/test_*.rb'
|
25
|
+
test.verbose = true
|
26
|
+
end
|
27
|
+
|
28
|
+
begin
|
29
|
+
require 'rcov/rcovtask'
|
30
|
+
Rcov::RcovTask.new do |test|
|
31
|
+
test.libs << 'test'
|
32
|
+
test.pattern = 'test/**/test_*.rb'
|
33
|
+
test.verbose = true
|
34
|
+
end
|
35
|
+
rescue LoadError
|
36
|
+
task :rcov do
|
37
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
task :test => :check_dependencies
|
42
|
+
|
43
|
+
task :default => :test
|
44
|
+
|
45
|
+
require 'rake/rdoctask'
|
46
|
+
Rake::RDocTask.new do |rdoc|
|
47
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
48
|
+
|
49
|
+
rdoc.rdoc_dir = 'rdoc'
|
50
|
+
rdoc.title = "korean-string #{version}"
|
51
|
+
rdoc.rdoc_files.include('README*')
|
52
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
53
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
@@ -0,0 +1,112 @@
|
|
1
|
+
# Originally transliterate-hacked from Perl from
|
2
|
+
# http://blog.naver.com/PostView.nhn?blogId=mokomoji&logNo=130013133481
|
3
|
+
#
|
4
|
+
# For the theory of why this works, check out the W3C spec on Korean encoding
|
5
|
+
# http://www.w3c.or.kr/i18n/hangul-i18n/ko-code.html
|
6
|
+
# (Thanks to @ntrolls for this)
|
7
|
+
|
8
|
+
$KCODE = 'UTF8'
|
9
|
+
|
10
|
+
# ㄱ ㄲ ㄴ ㄷ ㄸ ㄹ ㅁ ㅂ
|
11
|
+
CHOSUNG = [0x3131, 0x3132, 0x3134, 0x3137, 0x3138, 0x3139, 0x3141, 0x3142,
|
12
|
+
# ㅃ ㅅ ㅆ ㅇ ㅈ ㅉ ㅊ ㅋ
|
13
|
+
0x3143, 0x3145, 0x3146, 0x3147, 0x3148, 0x3149, 0x314a, 0x314b,
|
14
|
+
# ㅌ ㅍ ㅎ
|
15
|
+
0x314c, 0x314d, 0x314e]
|
16
|
+
|
17
|
+
# ㅏ ㅐ ㅑ ㅒ ㅓ ㅔ ㅕ ㅖ
|
18
|
+
JWUNGSUNG = [0x314f, 0x3150, 0x3151, 0x3152, 0x3153, 0x3154, 0x3155, 0x3156,
|
19
|
+
# ㅗ ㅘ ㅙ ㅚ ㅛ ㅜ ㅝ ㅞ
|
20
|
+
0x3157, 0x3158, 0x3159, 0x315a, 0x315b, 0x315c, 0x315d, 0x315e,
|
21
|
+
# ㅟ ㅠ ㅡ ㅢ ㅣ
|
22
|
+
0x315f, 0x3160, 0x3161, 0x3162, 0x3163]
|
23
|
+
|
24
|
+
# ㄱ ㄲ ㄳ ㄴ ㄵ ㄶ ㄷ ㄹ
|
25
|
+
JONGSUNG = [ 0, 0x3131, 0x3132, 0x3133, 0x3134, 0x3135, 0x3136, 0x3137,
|
26
|
+
# ㄺ ㄻ ㄼ ㄽ ㄾ ㄿ ㅀ ㅁ
|
27
|
+
0x3139, 0x313a, 0x313b, 0x313c, 0x313d, 0x313e, 0x313f, 0x3140,
|
28
|
+
# ㅂ ㅄ ㅅ ㅆ ㅇ ㅈ ㅊ ㅋ
|
29
|
+
0x3141, 0x3142, 0x3144, 0x3145, 0x3146, 0x3147, 0x3148, 0x314a,
|
30
|
+
# ㅌ ㅍ ㅎ ?whoops
|
31
|
+
0x314b, 0x314c, 0x314d, 0x314e ]
|
32
|
+
|
33
|
+
|
34
|
+
# Not wrapping this in a module... not sure if that's a terrible idea
|
35
|
+
|
36
|
+
class String
|
37
|
+
def split_ko
|
38
|
+
|
39
|
+
raw_chars = self.unpack("U*")
|
40
|
+
|
41
|
+
final_result = Array.new
|
42
|
+
|
43
|
+
raw_chars.each do |char|
|
44
|
+
result = Array.new
|
45
|
+
if (char >= 0xAC00 && char <= 0xD7A3)
|
46
|
+
# Move it down in the range
|
47
|
+
c = char - 0xAC00;
|
48
|
+
|
49
|
+
# Here be dragons
|
50
|
+
a = c.to_f / (21 * 28)
|
51
|
+
c = c % (21 * 28)
|
52
|
+
b = c.to_f / 28
|
53
|
+
c = c % 28
|
54
|
+
|
55
|
+
a = a.to_i
|
56
|
+
b = b.to_i
|
57
|
+
c = c.to_i
|
58
|
+
|
59
|
+
result.push( CHOSUNG[a], JWUNGSUNG[b] )
|
60
|
+
|
61
|
+
if c != 0
|
62
|
+
result.push( JONGSUNG[c] )
|
63
|
+
end
|
64
|
+
else
|
65
|
+
result.push(char)
|
66
|
+
end
|
67
|
+
|
68
|
+
final_result.push(result.pack("U*").split(''))
|
69
|
+
end
|
70
|
+
|
71
|
+
return final_result
|
72
|
+
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
|
77
|
+
class Array
|
78
|
+
# We've got our sploded array of korean bits
|
79
|
+
# need to put them back into Real Words
|
80
|
+
def join_ko
|
81
|
+
# http://www.w3c.or.kr/i18n/hangul-i18n/ko-code.html
|
82
|
+
# Leading, middle, following (optional)
|
83
|
+
a = self[0].unpack("U*").first
|
84
|
+
b = self[1].unpack("U*").first
|
85
|
+
c = self[2].unpack("U*").first if self[2]
|
86
|
+
|
87
|
+
offset_a = CHOSUNG.index(a)
|
88
|
+
if offset_a.nil?
|
89
|
+
raise
|
90
|
+
end
|
91
|
+
offset_b = JWUNGSUNG.index(b)
|
92
|
+
if offset_b.nil?
|
93
|
+
raise
|
94
|
+
end
|
95
|
+
|
96
|
+
offset_c = 0
|
97
|
+
if c
|
98
|
+
offset_c = JONGSUNG.index(c)
|
99
|
+
if offset_c.nil?
|
100
|
+
raise
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
raw = 0xAC00 +
|
105
|
+
offset_a * (21 * 28) +
|
106
|
+
offset_b * 28 +
|
107
|
+
offset_c
|
108
|
+
|
109
|
+
[ raw ].pack("U*")
|
110
|
+
end
|
111
|
+
end
|
112
|
+
|
data/test/helper.rb
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestKoreanString < Test::Unit::TestCase
|
4
|
+
|
5
|
+
def test_split
|
6
|
+
assert_equal(
|
7
|
+
[["ㅇ", "ㅏ", "ㄴ"],
|
8
|
+
["ㄴ", "ㅕ", "ㅇ"],
|
9
|
+
["ㅎ", "ㅏ"],
|
10
|
+
["ㅅ", "ㅔ"],
|
11
|
+
["ㅇ", "ㅛ"]],
|
12
|
+
'안녕하세요'.split_ko
|
13
|
+
)
|
14
|
+
|
15
|
+
assert_equal(
|
16
|
+
[["ㅇ", "ㅣ", "ㄺ"], ["ㅇ", "ㅓ"], ["ㅅ", "ㅣ", "ㅍ"]],
|
17
|
+
'읽어싶'.split_ko
|
18
|
+
)
|
19
|
+
|
20
|
+
assert_equal(
|
21
|
+
[["ㄱ", "ㅙ", "ㄴ"], ["ㅊ", "ㅏ", "ㄶ"], ["ㅇ", "ㅏ"]],
|
22
|
+
'괜찮아'.split_ko
|
23
|
+
)
|
24
|
+
end
|
25
|
+
|
26
|
+
def test_join
|
27
|
+
assert_equal(
|
28
|
+
"아",
|
29
|
+
%w(ㅇ ㅏ).join_ko
|
30
|
+
)
|
31
|
+
|
32
|
+
assert_equal(
|
33
|
+
"일",
|
34
|
+
%w(ㅇ ㅣ ㄹ).join_ko
|
35
|
+
)
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
metadata
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: korean-string
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Ben Humphreys
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-11-03 00:00:00 +09:00
|
19
|
+
default_executable:
|
20
|
+
dependencies: []
|
21
|
+
|
22
|
+
description: Split Korean characters to individual compontents, join components together to create characters
|
23
|
+
email: benhumphreys@gmail.com
|
24
|
+
executables: []
|
25
|
+
|
26
|
+
extensions: []
|
27
|
+
|
28
|
+
extra_rdoc_files:
|
29
|
+
- LICENSE
|
30
|
+
- README.rdoc
|
31
|
+
files:
|
32
|
+
- .document
|
33
|
+
- .gitignore
|
34
|
+
- LICENSE
|
35
|
+
- README.rdoc
|
36
|
+
- Rakefile
|
37
|
+
- VERSION
|
38
|
+
- lib/korean-string.rb
|
39
|
+
- test/helper.rb
|
40
|
+
- test/test_korean-string.rb
|
41
|
+
has_rdoc: true
|
42
|
+
homepage: http://github.com/bhumphreys/korean-string
|
43
|
+
licenses: []
|
44
|
+
|
45
|
+
post_install_message:
|
46
|
+
rdoc_options:
|
47
|
+
- --charset=UTF-8
|
48
|
+
require_paths:
|
49
|
+
- lib
|
50
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
51
|
+
none: false
|
52
|
+
requirements:
|
53
|
+
- - ">="
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
hash: 3
|
56
|
+
segments:
|
57
|
+
- 0
|
58
|
+
version: "0"
|
59
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
60
|
+
none: false
|
61
|
+
requirements:
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
hash: 3
|
65
|
+
segments:
|
66
|
+
- 0
|
67
|
+
version: "0"
|
68
|
+
requirements: []
|
69
|
+
|
70
|
+
rubyforge_project:
|
71
|
+
rubygems_version: 1.3.7
|
72
|
+
signing_key:
|
73
|
+
specification_version: 3
|
74
|
+
summary: Korean string join and split
|
75
|
+
test_files:
|
76
|
+
- test/helper.rb
|
77
|
+
- test/test_korean-string.rb
|