hanzi_to_pinyin 0.8.0 → 0.9.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +9 -7
- data/VERSION +1 -1
- data/lib/hanzi_to_pinyin.rb +10 -4
- metadata +3 -3
data/README.rdoc
CHANGED
|
@@ -6,7 +6,7 @@ translate chinese to pinyin, fetch first letter OR full pinyin
|
|
|
6
6
|
|
|
7
7
|
rails3
|
|
8
8
|
|
|
9
|
-
$ gem 'hanzi_to_pinyin', '0.
|
|
9
|
+
$ gem 'hanzi_to_pinyin', '0.9.0', require: 'hanzi_to_pinyin'
|
|
10
10
|
or latest develop version
|
|
11
11
|
$ gem 'hanzi_to_pinyin', git: 'git://github.com/wxianfeng/hanzi_to_pinyin.git'
|
|
12
12
|
or freeze ref version
|
|
@@ -22,19 +22,21 @@ or freeze ref version
|
|
|
22
22
|
$ HanziToPinyin.is_hanzi?("你") => true
|
|
23
23
|
$ HanziToPinyin.is_hanzi?("a") => false
|
|
24
24
|
|
|
25
|
-
# 多音字,分隔
|
|
25
|
+
# 多音字,分隔 字字之间;分隔,字母数字保留不变
|
|
26
26
|
$ HanziToPinyin.hanzi_2_py("我们") => "wo;men"
|
|
27
|
-
$ HanziToPinyin.hanzi_2_py("
|
|
27
|
+
$ HanziToPinyin.hanzi_2_py("yyf") => "yyf"
|
|
28
|
+
$ HanziToPinyin.hanzi_2_py("查理Smith") => "cha,zha;li;Smith"
|
|
28
29
|
$ HanziToPinyin.hanzi_2_py("测试1") => "ce;shi;1"
|
|
29
30
|
$ HanziToPinyin.hanzi_2_py("测_试") => "ce;_;shi"
|
|
30
|
-
$ HanziToPinyin.hanzi_2_py("测-试")
|
|
31
|
+
$ HanziToPinyin.hanzi_2_py("测-试") => "ce;-;shi"
|
|
32
|
+
$ HanziToPinyin.hanzi_2_py(2).should == "2"
|
|
31
33
|
|
|
32
34
|
$ HanziToPinyin.is_number?("1".ord) => true
|
|
33
35
|
$ HanziToPinyin.is_number?("a".ord) => false
|
|
34
36
|
|
|
35
|
-
$ HanziToPinyin.is_underline?("_".ord)
|
|
36
|
-
$ HanziToPinyin.is_underline?("豆豆")
|
|
37
|
-
$ HanziToPinyin.is_dash?("-".ord)
|
|
37
|
+
$ HanziToPinyin.is_underline?("_".ord) => true
|
|
38
|
+
$ HanziToPinyin.is_underline?("豆豆") => false
|
|
39
|
+
$ HanziToPinyin.is_dash?("-".ord) => true
|
|
38
40
|
|
|
39
41
|
== Test
|
|
40
42
|
$ rake spec
|
data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.
|
|
1
|
+
0.9.0
|
data/lib/hanzi_to_pinyin.rb
CHANGED
|
@@ -55,30 +55,36 @@ class HanziToPinyin
|
|
|
55
55
|
|
|
56
56
|
##
|
|
57
57
|
# 多音字,分隔 字字之间;分隔,字母丢弃
|
|
58
|
-
# 查理Smith => "cha,zha;li"
|
|
58
|
+
# 查理Smith => "cha,zha;li;Smith"
|
|
59
59
|
# 郭轶 => "guo;yi,die"
|
|
60
60
|
# 我们 => "wo;men"
|
|
61
61
|
# 宗志强 => "zong;zhi;qiang,jiang"
|
|
62
62
|
def self.hanzi_2_py(hanzi)
|
|
63
|
-
hanzi = hanzi.force_encoding("utf-8")
|
|
63
|
+
hanzi = hanzi.to_s.force_encoding("utf-8")
|
|
64
64
|
@str = ''
|
|
65
|
+
index = 0
|
|
65
66
|
hanzi.each_char do |hz|
|
|
66
67
|
if is_hanzi?(hz.ord)
|
|
67
68
|
values = @@py[hz]
|
|
68
69
|
append(values)
|
|
69
|
-
elsif is_letter?(hz.ord)
|
|
70
|
-
next
|
|
71
70
|
else
|
|
72
71
|
if @str.length == 0
|
|
73
72
|
@str << hz.chr
|
|
74
73
|
else
|
|
75
74
|
if @str[-1] == ";"
|
|
76
75
|
@str << hz.chr
|
|
76
|
+
elsif @str[-1] =~ /[a-z]/i
|
|
77
|
+
if is_hanzi?(hanzi[index-1].ord)
|
|
78
|
+
@str << ";#{hz.chr}"
|
|
79
|
+
else
|
|
80
|
+
@str << hz.chr
|
|
81
|
+
end
|
|
77
82
|
else
|
|
78
83
|
@str << ";#{hz.chr}"
|
|
79
84
|
end
|
|
80
85
|
end
|
|
81
86
|
end
|
|
87
|
+
index += 1
|
|
82
88
|
end
|
|
83
89
|
@str
|
|
84
90
|
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: 0.9.0
|
|
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: 2012-
|
|
12
|
+
date: 2012-12-26 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: json
|
|
@@ -90,7 +90,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
|
90
90
|
version: '0'
|
|
91
91
|
segments:
|
|
92
92
|
- 0
|
|
93
|
-
hash:
|
|
93
|
+
hash: -4254974955912349874
|
|
94
94
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
95
95
|
none: false
|
|
96
96
|
requirements:
|