ruby-pinyin 0.2.0 → 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README.markdown +7 -2
- data/lib/ruby-pinyin.rb +18 -0
- data/lib/ruby-pinyin/Punctuations.dat +9 -0
- data/lib/ruby-pinyin/version.rb +1 -1
- metadata +3 -2
data/README.markdown
CHANGED
@@ -6,8 +6,13 @@
|
|
6
6
|
* 能够显示数字或者UNICODE音调(eg: 'cao1', 'cāo')
|
7
7
|
* 丰富的API
|
8
8
|
* 支持中英文标点混合字符串
|
9
|
+
* 中文标点转为英文标点
|
9
10
|
* 支持自定义读音
|
10
11
|
|
12
|
+
## Installation
|
13
|
+
|
14
|
+
gem install ruby-pinyin
|
15
|
+
|
11
16
|
## Examples
|
12
17
|
|
13
18
|
# encoding: utf-8
|
@@ -33,8 +38,8 @@
|
|
33
38
|
PinYin.abbr('感谢party感谢guo jia')
|
34
39
|
|
35
40
|
# return 'gan xie party, gan xie guo jia!'
|
36
|
-
# PinYin.sentence
|
37
|
-
PinYin.sentence('感谢party
|
41
|
+
# PinYin.sentence保留标点符号, 同时用对应英文标点代替中文标点
|
42
|
+
PinYin.sentence('感谢party, 感谢guo家!')
|
38
43
|
|
39
44
|
# override readings with your own data file
|
40
45
|
PinYin.override_files = [File.expand_path('../my.dat', __FILE__)]
|
data/lib/ruby-pinyin.rb
CHANGED
@@ -23,6 +23,16 @@ module PinYin
|
|
23
23
|
@codes
|
24
24
|
end
|
25
25
|
|
26
|
+
def punctuations
|
27
|
+
return @punctuations if @punctuations
|
28
|
+
|
29
|
+
@punctuations = {}
|
30
|
+
src = File.expand_path('../ruby-pinyin/Punctuations.dat', __FILE__)
|
31
|
+
load_punctuations_from(src)
|
32
|
+
|
33
|
+
@punctuations
|
34
|
+
end
|
35
|
+
|
26
36
|
def of_string(str, tone=nil, include_punctuations=false)
|
27
37
|
res = []
|
28
38
|
return res unless str && !str.empty?
|
@@ -38,6 +48,7 @@ module PinYin
|
|
38
48
|
if val =~ /^[_0-9a-zA-Z\s]*$/ # 复原,去除特殊字符,如全角符号等。
|
39
49
|
(res.last && res.last.english? ? res.last : res) << Value.new(val, true) # 如果上一个字符也是非中文则与之合并
|
40
50
|
elsif include_punctuations
|
51
|
+
val = [punctuations[code]].pack('H*') if punctuations.has_key?(code)
|
41
52
|
(res.last ? res.last : res) << Value.new(val, false)
|
42
53
|
end
|
43
54
|
end
|
@@ -74,6 +85,13 @@ module PinYin
|
|
74
85
|
end
|
75
86
|
end
|
76
87
|
|
88
|
+
def load_punctuations_from(file)
|
89
|
+
File.readlines(file).map do |line|
|
90
|
+
from, to = line.split(/\s+/)
|
91
|
+
@punctuations[from] = to
|
92
|
+
end
|
93
|
+
end
|
94
|
+
|
77
95
|
def format(readings, tone)
|
78
96
|
case tone
|
79
97
|
when :unicode
|
data/lib/ruby-pinyin/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ruby-pinyin
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.1
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-05-
|
12
|
+
date: 2013-05-18 00:00:00.000000000 Z
|
13
13
|
dependencies: []
|
14
14
|
description: Pinyin is a romanization system (phonemic notation) of Chinese characters,
|
15
15
|
this gem helps you to convert Chinese characters into pinyin form.
|
@@ -23,6 +23,7 @@ files:
|
|
23
23
|
- lib/ruby-pinyin/version.rb
|
24
24
|
- lib/ruby-pinyin/value.rb
|
25
25
|
- lib/ruby-pinyin/Mandarin.dat
|
26
|
+
- lib/ruby-pinyin/Punctuations.dat
|
26
27
|
- MIT-LICENSE
|
27
28
|
- README.markdown
|
28
29
|
homepage: https://github.com/janx/ruby-pinyin
|