ruby_pinyin 1.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +22 -0
- data/README.md +35 -0
- data/Rakefile +2 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/ruby_pinyin.rb +41 -0
- data/lib/ruby_pinyin/backend.rb +6 -0
- data/lib/ruby_pinyin/backend/mmseg.rb +110 -0
- data/lib/ruby_pinyin/backend/simple.rb +72 -0
- data/lib/ruby_pinyin/data/Mandarin.dat +41208 -0
- data/lib/ruby_pinyin/data/Punctuations.dat +14 -0
- data/lib/ruby_pinyin/data/words.dat +175180 -0
- data/lib/ruby_pinyin/data/words.dic +175180 -0
- data/lib/ruby_pinyin/punctuation.rb +46 -0
- data/lib/ruby_pinyin/util.rb +29 -0
- data/lib/ruby_pinyin/value.rb +16 -0
- data/lib/ruby_pinyin/version.rb +3 -0
- data/ruby_pinyin.gemspec +27 -0
- metadata +107 -0
@@ -0,0 +1,46 @@
|
|
1
|
+
module PinYin
|
2
|
+
module Punctuation
|
3
|
+
|
4
|
+
class <<self
|
5
|
+
|
6
|
+
def regexp
|
7
|
+
return @regexp if @regexp
|
8
|
+
|
9
|
+
escaped_punctuations = punctuations.values.map {|v| "\\#{[v].pack('H*')}"}.join
|
10
|
+
@regexp = Regexp.new "([#{escaped_punctuations}]+)$"
|
11
|
+
@regexp
|
12
|
+
end
|
13
|
+
|
14
|
+
def chinese_regexp
|
15
|
+
@chinese_regexp ||= /([\u3000-\u303F\uFF00-\uFFEF]+)/
|
16
|
+
end
|
17
|
+
|
18
|
+
def [](code)
|
19
|
+
punctuations[code]
|
20
|
+
end
|
21
|
+
|
22
|
+
def include?(code)
|
23
|
+
punctuations.has_key?(code)
|
24
|
+
end
|
25
|
+
|
26
|
+
def punctuations
|
27
|
+
return @punctuations if @punctuations
|
28
|
+
|
29
|
+
@punctuations = {}
|
30
|
+
src = File.expand_path('../data/Punctuations.dat', __FILE__)
|
31
|
+
load_from src
|
32
|
+
|
33
|
+
@punctuations
|
34
|
+
end
|
35
|
+
|
36
|
+
def load_from(file)
|
37
|
+
File.readlines(file).map do |line|
|
38
|
+
from, to = line.split(/\s+/)
|
39
|
+
@punctuations[from] = to
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
46
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
module PinYin
|
4
|
+
module Util
|
5
|
+
extend self
|
6
|
+
|
7
|
+
ASCIIMapping = {
|
8
|
+
'üē' => ['ue', 1], 'üé' => ['ue', 2], 'üě' => ['ue', 3], 'üè' => ['ue', 4],
|
9
|
+
'ā' => ['a', 1], 'ē' => ['e', 1], 'ī' => ['i', 1], 'ō' => ['o', 1], 'ū' => ['u', 1], 'ǖ' => ['v', 1],
|
10
|
+
'á' => ['a', 2], 'é' => ['e', 2], 'í' => ['i', 2], 'ó' => ['o', 2], 'ú' => ['u', 2], 'ǘ' => ['v', 2],
|
11
|
+
'ǎ' => ['a', 3], 'ě' => ['e', 3], 'ǐ' => ['i', 3], 'ǒ' => ['o', 3], 'ǔ' => ['u', 3], 'ǚ' => ['v', 3],
|
12
|
+
'à' => ['a', 4], 'è' => ['e', 4], 'ì' => ['i', 4], 'ò' => ['o', 4], 'ù' => ['u', 4], 'ǜ' => ['v', 4]
|
13
|
+
}
|
14
|
+
|
15
|
+
def to_ascii(reading, with_tone=true)
|
16
|
+
ASCIIMapping.each do |char, (ascii, tone)|
|
17
|
+
if reading.include? char
|
18
|
+
if with_tone
|
19
|
+
return reading.sub(char, ascii).concat(tone.to_s)
|
20
|
+
else
|
21
|
+
return reading.sub(char, ascii)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
reading
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
module PinYin
|
2
|
+
class Value < String
|
3
|
+
attr_accessor :english
|
4
|
+
alias :english? :english
|
5
|
+
|
6
|
+
def initialize(str, english=true)
|
7
|
+
super(str)
|
8
|
+
self.english = english
|
9
|
+
end
|
10
|
+
|
11
|
+
def split(*args)
|
12
|
+
result = super
|
13
|
+
result.map {|str| self.class.new(str, english)}
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
data/ruby_pinyin.gemspec
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "ruby_pinyin/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "ruby_pinyin"
|
8
|
+
spec.version = PinYin::VERSION
|
9
|
+
spec.authors = ["Charles Zhang"]
|
10
|
+
spec.email = ["gis05zc@163.com"]
|
11
|
+
|
12
|
+
spec.summary = "Convert Chinese characters into pinyin."
|
13
|
+
spec.description = "Pinyin is a romanization system (phonemic notation) of Chinese characters, this gem helps you to convert Chinese characters into pinyin form."
|
14
|
+
spec.homepage = "https://github.com/chinazhangchao/ruby-pinyin"
|
15
|
+
spec.license = 'MIT'
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
18
|
+
f.match(%r{^(test|spec|features)/})
|
19
|
+
end
|
20
|
+
spec.bindir = "exe"
|
21
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
22
|
+
spec.require_paths = ["lib"]
|
23
|
+
|
24
|
+
spec.add_runtime_dependency('rmmseg-cpp-new', ['~> 0.3.1'])
|
25
|
+
spec.add_development_dependency "bundler", "~> 1.16"
|
26
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,107 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ruby_pinyin
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Charles Zhang
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-11-11 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rmmseg-cpp-new
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.3.1
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.3.1
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.16'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.16'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
description: Pinyin is a romanization system (phonemic notation) of Chinese characters,
|
56
|
+
this gem helps you to convert Chinese characters into pinyin form.
|
57
|
+
email:
|
58
|
+
- gis05zc@163.com
|
59
|
+
executables: []
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- ".gitignore"
|
64
|
+
- Gemfile
|
65
|
+
- Gemfile.lock
|
66
|
+
- README.md
|
67
|
+
- Rakefile
|
68
|
+
- bin/console
|
69
|
+
- bin/setup
|
70
|
+
- lib/ruby_pinyin.rb
|
71
|
+
- lib/ruby_pinyin/backend.rb
|
72
|
+
- lib/ruby_pinyin/backend/mmseg.rb
|
73
|
+
- lib/ruby_pinyin/backend/simple.rb
|
74
|
+
- lib/ruby_pinyin/data/Mandarin.dat
|
75
|
+
- lib/ruby_pinyin/data/Punctuations.dat
|
76
|
+
- lib/ruby_pinyin/data/words.dat
|
77
|
+
- lib/ruby_pinyin/data/words.dic
|
78
|
+
- lib/ruby_pinyin/punctuation.rb
|
79
|
+
- lib/ruby_pinyin/util.rb
|
80
|
+
- lib/ruby_pinyin/value.rb
|
81
|
+
- lib/ruby_pinyin/version.rb
|
82
|
+
- ruby_pinyin.gemspec
|
83
|
+
homepage: https://github.com/chinazhangchao/ruby-pinyin
|
84
|
+
licenses:
|
85
|
+
- MIT
|
86
|
+
metadata: {}
|
87
|
+
post_install_message:
|
88
|
+
rdoc_options: []
|
89
|
+
require_paths:
|
90
|
+
- lib
|
91
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
92
|
+
requirements:
|
93
|
+
- - ">="
|
94
|
+
- !ruby/object:Gem::Version
|
95
|
+
version: '0'
|
96
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
97
|
+
requirements:
|
98
|
+
- - ">="
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: '0'
|
101
|
+
requirements: []
|
102
|
+
rubyforge_project:
|
103
|
+
rubygems_version: 2.6.13
|
104
|
+
signing_key:
|
105
|
+
specification_version: 4
|
106
|
+
summary: Convert Chinese characters into pinyin.
|
107
|
+
test_files: []
|