hanzi_to_pinyin 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +20 -0
- data/Gemfile +5 -0
- data/LICENSE.txt +20 -0
- data/README.rdoc +24 -0
- data/Rakefile +13 -0
- data/VERSION +1 -0
- data/hanzi_to_pinyin.gemspec +36 -0
- data/lib/data/unicode_to_pinyin.yml +25478 -0
- data/lib/hanzi_to_pinyin.rb +32 -0
- data/spec/spec_helper.rb +13 -0
- metadata +68 -0
@@ -0,0 +1,32 @@
|
|
1
|
+
class HanziToPinyin
|
2
|
+
|
3
|
+
# Unicode中汉字开始点
|
4
|
+
@@hanzi_unicode_start=19968
|
5
|
+
# Unicode中汉字的结束点
|
6
|
+
@@hanzi_unicode_end=40869
|
7
|
+
# 汉字 unicode 编码(16进制)
|
8
|
+
@@unicode = YAML.load(IO.read File.expand_path("../data/unicode_to_pinyin.yml",__FILE__))
|
9
|
+
|
10
|
+
def self.hanzi_2_pinyin(hanzi)
|
11
|
+
hanzi = hanzi.force_encoding("utf-8")
|
12
|
+
u_str = ''
|
13
|
+
hanzi.each_codepoint { |c|
|
14
|
+
if is_hanzi?(c)
|
15
|
+
unicode = c.to_s(16).upcase
|
16
|
+
u_str << @@unicode[unicode]
|
17
|
+
else
|
18
|
+
if c == 45 # -
|
19
|
+
u_str << "_"
|
20
|
+
else
|
21
|
+
u_str << c.chr.downcase
|
22
|
+
end
|
23
|
+
end
|
24
|
+
}
|
25
|
+
u_str
|
26
|
+
end
|
27
|
+
|
28
|
+
def self.is_hanzi?(hanzi_codepoint)
|
29
|
+
hanzi_codepoint>=@@hanzi_unicode_start&&hanzi_codepoint<=@@hanzi_unicode_end
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
|
11
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
12
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
13
|
+
require 'hanzi_to_pinyin'
|
metadata
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: hanzi_to_pinyin
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.2.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- wxianfeng
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-10-26 00:00:00.000000000Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rspec
|
16
|
+
requirement: &70237983291580 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70237983291580
|
25
|
+
description: chinese hanzi to pinyin , just fetch first letter, written in Ruby.
|
26
|
+
email:
|
27
|
+
- wang.fl1429@gmail.com
|
28
|
+
executables: []
|
29
|
+
extensions: []
|
30
|
+
extra_rdoc_files: []
|
31
|
+
files:
|
32
|
+
- .gitignore
|
33
|
+
- Gemfile
|
34
|
+
- LICENSE.txt
|
35
|
+
- README.rdoc
|
36
|
+
- Rakefile
|
37
|
+
- VERSION
|
38
|
+
- hanzi_to_pinyin.gemspec
|
39
|
+
- lib/data/unicode_to_pinyin.yml
|
40
|
+
- lib/hanzi_to_pinyin.rb
|
41
|
+
- spec/spec_helper.rb
|
42
|
+
homepage: http://github.com/wxianfeng/hanzi_to_pinyin
|
43
|
+
licenses: []
|
44
|
+
post_install_message: ! " hanzi_to_pinyin is a tool for chinese hanzi to pinyin ,just
|
45
|
+
fetch first letter , writen in Ruby.\n \n http://github.com/wxianfeng/hanzi_to_pinyin\n\n
|
46
|
+
\ Enjoy!\n\n wxianfeng (wang.fl1429@gmail.com)\n\n"
|
47
|
+
rdoc_options: []
|
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
|
+
version: '0'
|
56
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 1.3.6
|
62
|
+
requirements: []
|
63
|
+
rubyforge_project:
|
64
|
+
rubygems_version: 1.8.10
|
65
|
+
signing_key:
|
66
|
+
specification_version: 3
|
67
|
+
summary: chinese hanzi to pinyin , just fetch first letter.
|
68
|
+
test_files: []
|