hanzi_to_pinyin 0.7.0 → 0.8.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +5 -5
- data/VERSION +1 -1
- data/lib/hanzi_to_pinyin.rb +39 -35
- metadata +26 -13
data/README.rdoc
CHANGED
@@ -1,16 +1,16 @@
|
|
1
1
|
= hanzi_to_pinyin
|
2
2
|
|
3
|
-
translate chinese to pinyin
|
3
|
+
translate chinese to pinyin, fetch first letter OR full pinyin
|
4
4
|
|
5
5
|
== Install
|
6
6
|
|
7
7
|
rails3
|
8
8
|
|
9
|
-
$ gem 'hanzi_to_pinyin'
|
9
|
+
$ gem 'hanzi_to_pinyin', '0.8.0', require: 'hanzi_to_pinyin'
|
10
10
|
or latest develop version
|
11
|
-
$ gem 'hanzi_to_pinyin'
|
11
|
+
$ gem 'hanzi_to_pinyin', git: 'git://github.com/wxianfeng/hanzi_to_pinyin.git'
|
12
12
|
or freeze ref version
|
13
|
-
$ gem 'hanzi_to_pinyin'
|
13
|
+
$ gem 'hanzi_to_pinyin', git: 'git://github.com/wxianfeng/hanzi_to_pinyin.git', ref: 5fa43b0
|
14
14
|
|
15
15
|
== Usage
|
16
16
|
|
@@ -22,7 +22,7 @@ or freeze ref version
|
|
22
22
|
$ HanziToPinyin.is_hanzi?("你") => true
|
23
23
|
$ HanziToPinyin.is_hanzi?("a") => false
|
24
24
|
|
25
|
-
#
|
25
|
+
# 多音字,分隔 字字之间;分隔,字母丢弃
|
26
26
|
$ HanziToPinyin.hanzi_2_py("我们") => "wo;men"
|
27
27
|
$ HanziToPinyin.hanzi_2_py("查理Smith") => "cha,zha;li"
|
28
28
|
$ HanziToPinyin.hanzi_2_py("测试1") => "ce;shi;1"
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.
|
1
|
+
0.8.0
|
data/lib/hanzi_to_pinyin.rb
CHANGED
@@ -11,6 +11,12 @@ class HanziToPinyin
|
|
11
11
|
# Unicode中汉字的结束点
|
12
12
|
@@hanzi_unicode_end = 40869
|
13
13
|
|
14
|
+
# 字母(10进制)
|
15
|
+
@@letter_upcase_start = 65
|
16
|
+
@@letter_upcase_end = 90
|
17
|
+
@@letter_downcase_start = 97
|
18
|
+
@@letter_downcase_end = 122
|
19
|
+
|
14
20
|
# 数字(10进制)
|
15
21
|
@@number_unicode_start = 48
|
16
22
|
@@number_unicode_end = 57
|
@@ -48,55 +54,49 @@ class HanziToPinyin
|
|
48
54
|
end
|
49
55
|
|
50
56
|
##
|
51
|
-
#
|
52
|
-
#
|
53
|
-
#
|
54
|
-
#
|
55
|
-
#
|
57
|
+
# 多音字,分隔 字字之间;分隔,字母丢弃
|
58
|
+
# 查理Smith => "cha,zha;li"
|
59
|
+
# 郭轶 => "guo;yi,die"
|
60
|
+
# 我们 => "wo;men"
|
61
|
+
# 宗志强 => "zong;zhi;qiang,jiang"
|
56
62
|
def self.hanzi_2_py(hanzi)
|
57
63
|
hanzi = hanzi.force_encoding("utf-8")
|
58
|
-
str = ''
|
64
|
+
@str = ''
|
59
65
|
hanzi.each_char do |hz|
|
60
|
-
if
|
61
|
-
if str.length == 0
|
62
|
-
str << hz.chr
|
63
|
-
else
|
64
|
-
if str[-1] == ";"
|
65
|
-
str << hz.chr
|
66
|
-
else
|
67
|
-
str << ";#{hz.chr}"
|
68
|
-
end
|
69
|
-
end
|
70
|
-
elsif is_hanzi?(hz.ord)
|
66
|
+
if is_hanzi?(hz.ord)
|
71
67
|
values = @@py[hz]
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
else
|
79
|
-
str << ";#{values.join(',')}"
|
80
|
-
end
|
81
|
-
end
|
68
|
+
append(values)
|
69
|
+
elsif is_letter?(hz.ord)
|
70
|
+
next
|
71
|
+
else
|
72
|
+
if @str.length == 0
|
73
|
+
@str << hz.chr
|
82
74
|
else
|
83
|
-
if str
|
84
|
-
str <<
|
75
|
+
if @str[-1] == ";"
|
76
|
+
@str << hz.chr
|
85
77
|
else
|
86
|
-
|
87
|
-
str << "#{values.join}"
|
88
|
-
else
|
89
|
-
str << ";#{values.join}"
|
90
|
-
end
|
78
|
+
@str << ";#{hz.chr}"
|
91
79
|
end
|
92
80
|
end
|
93
81
|
end
|
94
82
|
end
|
95
|
-
str
|
83
|
+
@str
|
96
84
|
end
|
97
85
|
class << self
|
98
86
|
alias_method :hanzi_to_py , :hanzi_2_py
|
99
87
|
end
|
88
|
+
|
89
|
+
def self.append(values)
|
90
|
+
if @str.length == 0
|
91
|
+
@str << "#{values.join(',')}"
|
92
|
+
else
|
93
|
+
if @str[-1] == ";"
|
94
|
+
@str << "#{values.join(',')}"
|
95
|
+
else
|
96
|
+
@str << ";#{values.join(',')}"
|
97
|
+
end
|
98
|
+
end
|
99
|
+
end
|
100
100
|
|
101
101
|
def self.is_hanzi?(hanzi_codepoint)
|
102
102
|
hanzi_codepoint >= @@hanzi_unicode_start && hanzi_codepoint <= @@hanzi_unicode_end
|
@@ -113,5 +113,9 @@ class HanziToPinyin
|
|
113
113
|
def self.is_dash?(codepoint)
|
114
114
|
codepoint == @@dash
|
115
115
|
end
|
116
|
+
|
117
|
+
def self.is_letter?(codepoint)
|
118
|
+
codepoint >= @@letter_upcase_start && codepoint <= @@letter_upcase_end or codepoint >= @@letter_downcase_start && codepoint <= @@letter_downcase_end
|
119
|
+
end
|
116
120
|
|
117
121
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: hanzi_to_pinyin
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.8.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,12 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
13
|
-
default_executable:
|
12
|
+
date: 2012-05-14 00:00:00.000000000 Z
|
14
13
|
dependencies:
|
15
14
|
- !ruby/object:Gem::Dependency
|
16
15
|
name: json
|
17
|
-
requirement:
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
18
17
|
none: false
|
19
18
|
requirements:
|
20
19
|
- - ! '>='
|
@@ -22,10 +21,15 @@ dependencies:
|
|
22
21
|
version: '0'
|
23
22
|
type: :runtime
|
24
23
|
prerelease: false
|
25
|
-
version_requirements:
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
26
30
|
- !ruby/object:Gem::Dependency
|
27
31
|
name: yamler
|
28
|
-
requirement:
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
29
33
|
none: false
|
30
34
|
requirements:
|
31
35
|
- - ! '>='
|
@@ -33,10 +37,15 @@ dependencies:
|
|
33
37
|
version: '0'
|
34
38
|
type: :runtime
|
35
39
|
prerelease: false
|
36
|
-
version_requirements:
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
37
46
|
- !ruby/object:Gem::Dependency
|
38
47
|
name: rspec
|
39
|
-
requirement:
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
40
49
|
none: false
|
41
50
|
requirements:
|
42
51
|
- - ! '>='
|
@@ -44,7 +53,12 @@ dependencies:
|
|
44
53
|
version: '0'
|
45
54
|
type: :development
|
46
55
|
prerelease: false
|
47
|
-
version_requirements:
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
48
62
|
description: chinese hanzi to pinyin , fetch first letter OR full pinyin, written
|
49
63
|
in Ruby.
|
50
64
|
email:
|
@@ -57,10 +71,9 @@ files:
|
|
57
71
|
- VERSION
|
58
72
|
- LICENSE.txt
|
59
73
|
- Rakefile
|
74
|
+
- lib/hanzi_to_pinyin.rb
|
60
75
|
- lib/data/unicode_to_pinyin.yml
|
61
76
|
- lib/data/hz2py.json
|
62
|
-
- lib/hanzi_to_pinyin.rb
|
63
|
-
has_rdoc: true
|
64
77
|
homepage: http://github.com/wxianfeng/hanzi_to_pinyin
|
65
78
|
licenses: []
|
66
79
|
post_install_message: ! " hanzi_to_pinyin is a tool for chinese hanzi to pinyin ,fetch
|
@@ -77,7 +90,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
77
90
|
version: '0'
|
78
91
|
segments:
|
79
92
|
- 0
|
80
|
-
hash:
|
93
|
+
hash: 292557973814545694
|
81
94
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
82
95
|
none: false
|
83
96
|
requirements:
|
@@ -86,7 +99,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
86
99
|
version: 1.3.6
|
87
100
|
requirements: []
|
88
101
|
rubyforge_project:
|
89
|
-
rubygems_version: 1.
|
102
|
+
rubygems_version: 1.8.24
|
90
103
|
signing_key:
|
91
104
|
specification_version: 3
|
92
105
|
summary: chinese hanzi to pinyin , fetch first letter OR full pinyin
|