auto-correct 0.3.1 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +11 -13
- data/lib/auto-correct.rb +0 -3
- data/lib/auto-correct/format.rb +17 -27
- data/lib/auto-correct/version.rb +1 -1
- metadata +6 -7
- data/lib/auto-correct/string.rb +0 -13
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: dc4ebaa39c033494ca5d6e7b704a7563755f62ea2a120000f012908780a70375
|
4
|
+
data.tar.gz: 33a17e83502ced4f06c0a11b222038d036e46c235ddf6b4bda68131dcaf58e84
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f88c421b4f2c5cf7fc16063778d57d4f6e3b4aa7eef8fe51075cec0df20fc539d760de99c37ddfc2557069836cbffb310087a2accbce27494d15edfe1748a742
|
7
|
+
data.tar.gz: 2e4bef9e663b45553e1a930a3d16c30283f8ed091f34bc26416d1658c7e45e36b4643cb15686e906adbc771e18c2d1befd07e8268742f8bd71409f47d24571b5
|
data/README.md
CHANGED
@@ -4,15 +4,13 @@ Automatically add whitespace between CJK (Chinese, Japanese, Korean) and half-wi
|
|
4
4
|
|
5
5
|
中文、日语、韩语 + 英文混排自动纠正补充空格,此方式已在 Ruby China 使用多年,支持 HTML 处理。
|
6
6
|
|
7
|
-
[![Gem Version](https://badge.fury.io/rb/auto-correct.svg)](https://rubygems.org/gems/auto-correct) [![
|
8
|
-
Status](https://api.travis-ci.org/huacnlee/auto-correct.svg?branch=master&.svg)](http://travis-ci.org/huacnlee/auto-correct)
|
9
|
-
|
7
|
+
[![Gem Version](https://badge.fury.io/rb/auto-correct.svg)](https://rubygems.org/gems/auto-correct) [![build](https://github.com/huacnlee/auto-correct/workflows/build/badge.svg)](https://github.com/huacnlee/auto-correct/actions?query=workflow%3Abuild)
|
10
8
|
|
11
9
|
## Other implements
|
12
10
|
|
13
11
|
- Ruby - [auto-correct](https://github.com/huacnlee/auto-correct).
|
14
12
|
- Go - [go-auto-correct](https://github.com/huacnlee/go-auto-correct).
|
15
|
-
- Rust - [
|
13
|
+
- Rust - [autocorrect](https://github.com/huacnlee/autocorrect).
|
16
14
|
|
17
15
|
## Features
|
18
16
|
|
@@ -36,7 +34,7 @@ AutoCorrect.format("于3月10日开始")
|
|
36
34
|
# => "于 3 月 10 日开始"
|
37
35
|
|
38
36
|
AutoCorrect.format("包装日期为2013年3月10日")
|
39
|
-
# => "包装日期为2013年3月10日"
|
37
|
+
# => "包装日期为 2013 年 3 月 10 日"
|
40
38
|
|
41
39
|
AutoCorrect.format("生产环境中使用Ruby")
|
42
40
|
# => "生产环境中使用 Ruby"
|
@@ -73,24 +71,24 @@ Calculating -------------------------------------
|
|
73
71
|
```
|
74
72
|
|
75
73
|
| Total chars | Duration |
|
76
|
-
|
|
77
|
-
| 50
|
78
|
-
| 100
|
79
|
-
| 400
|
74
|
+
| ----------- | -------- |
|
75
|
+
| 50 | 0.33 ms |
|
76
|
+
| 100 | 0.60 ms |
|
77
|
+
| 400 | 2 ms |
|
80
78
|
|
81
79
|
### FormatHTML
|
82
80
|
|
83
81
|
| Total chars | Duration |
|
84
|
-
|
|
85
|
-
| 2K
|
82
|
+
| ----------- | -------- |
|
83
|
+
| 2K | 7 ms |
|
86
84
|
|
87
85
|
## Use cases
|
88
86
|
|
89
|
-
|
87
|
+
- [Ruby China](https://ruby-china.org) - 目前整站都做了自动转换处理。
|
90
88
|
|
91
89
|
## Links
|
92
90
|
|
93
|
-
|
91
|
+
- [Chinese Copywriting Guidelines](https://github.com/sparanoid/chinese-copywriting-guidelines)
|
94
92
|
|
95
93
|
## License
|
96
94
|
|
data/lib/auto-correct.rb
CHANGED
@@ -2,10 +2,7 @@ require "auto-correct/strategery"
|
|
2
2
|
require "auto-correct/base"
|
3
3
|
require "auto-correct/format"
|
4
4
|
require "auto-correct/html"
|
5
|
-
require "auto-correct/string"
|
6
5
|
require "auto-correct/version"
|
7
6
|
|
8
7
|
class AutoCorrect
|
9
8
|
end
|
10
|
-
|
11
|
-
String.send :include, AutoCorrect::String
|
data/lib/auto-correct/format.rb
CHANGED
@@ -4,47 +4,37 @@ class AutoCorrect
|
|
4
4
|
|
5
5
|
# rubocop:disable Style/StringLiterals
|
6
6
|
# EnglishLetter
|
7
|
-
rule
|
7
|
+
rule CJK.to_s, '[a-zA-Z0-9]', space: true, reverse: true
|
8
8
|
|
9
9
|
# SpecialSymbol
|
10
|
-
rule
|
11
|
-
rule
|
12
|
-
rule '[
|
10
|
+
rule CJK.to_s, '[\|+*]', space: true, reverse: true
|
11
|
+
rule CJK.to_s, '[@]', space: true, reverse: false
|
12
|
+
rule CJK.to_s, '[\[\(‘“]', space: true
|
13
|
+
rule '[’”\]\)!%]', CJK.to_s, space: true
|
13
14
|
rule '[”\]\)!]', '[a-zA-Z0-9]+', space: true
|
14
15
|
|
15
|
-
# FullwidthPunctuation
|
16
|
-
rule %r
|
17
|
-
rule '[
|
16
|
+
# FullwidthPunctuation remove space case, Fullwidth can safe to remove spaces
|
17
|
+
rule %r{[\w#{CJK}]}o, '[,。!?:;)」》】”’]', reverse: true
|
18
|
+
rule '[‘“【「《(]', %r{[\w#{CJK}]}o, reverse: true
|
18
19
|
|
19
20
|
class << self
|
20
|
-
|
21
|
-
DASH_HAN_RE = /([#{CJK})】」》”’])([\-]+)([#{CJK}(【「《“‘])/
|
21
|
+
DASH_HAN_RE = /([#{CJK})】」》”’])(-+)([#{CJK}(【「《“‘])/
|
22
22
|
LEFT_QUOTE_RE = /#{SPACE}([(【「《])/
|
23
23
|
RIGHT_QUOTE_RE = /([)】」》])#{SPACE}/
|
24
24
|
|
25
25
|
def format(str)
|
26
|
-
|
27
|
-
|
28
|
-
out = s.format(out)
|
26
|
+
strategies.each do |s|
|
27
|
+
str = s.format(str)
|
29
28
|
end
|
30
|
-
|
31
|
-
out = space_dash_with_hans(out)
|
32
|
-
out
|
29
|
+
space_dash_with_hans(str)
|
33
30
|
end
|
34
31
|
|
35
32
|
private
|
36
33
|
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
def space_dash_with_hans(str)
|
44
|
-
str = str.gsub(DASH_HAN_RE, '\1 \2 \3')
|
45
|
-
str = str.gsub(LEFT_QUOTE_RE, '\1')
|
46
|
-
str = str.gsub(RIGHT_QUOTE_RE, '\1')
|
47
|
-
str
|
48
|
-
end
|
34
|
+
def space_dash_with_hans(str)
|
35
|
+
str = str.gsub(DASH_HAN_RE, '\1 \2 \3')
|
36
|
+
str = str.gsub(LEFT_QUOTE_RE, '\1')
|
37
|
+
str.gsub(RIGHT_QUOTE_RE, '\1')
|
38
|
+
end
|
49
39
|
end
|
50
40
|
end
|
data/lib/auto-correct/version.rb
CHANGED
metadata
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: auto-correct
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 1.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Luikore
|
8
8
|
- Jason Lee
|
9
|
-
autorequire:
|
9
|
+
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date:
|
12
|
+
date: 2021-07-27 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: nokogiri
|
@@ -40,12 +40,11 @@ files:
|
|
40
40
|
- lib/auto-correct/format.rb
|
41
41
|
- lib/auto-correct/html.rb
|
42
42
|
- lib/auto-correct/strategery.rb
|
43
|
-
- lib/auto-correct/string.rb
|
44
43
|
- lib/auto-correct/version.rb
|
45
44
|
homepage: https://github.com/huacnlee/auto-correct
|
46
45
|
licenses: []
|
47
46
|
metadata: {}
|
48
|
-
post_install_message:
|
47
|
+
post_install_message:
|
49
48
|
rdoc_options: []
|
50
49
|
require_paths:
|
51
50
|
- lib
|
@@ -60,8 +59,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
60
59
|
- !ruby/object:Gem::Version
|
61
60
|
version: '0'
|
62
61
|
requirements: []
|
63
|
-
rubygems_version: 3.
|
64
|
-
signing_key:
|
62
|
+
rubygems_version: 3.2.3
|
63
|
+
signing_key:
|
65
64
|
specification_version: 4
|
66
65
|
summary: Automatically add whitespace between Chinese and and half-width characters
|
67
66
|
(alphabetical letters, numerical digits and symbols).
|
data/lib/auto-correct/string.rb
DELETED
@@ -1,13 +0,0 @@
|
|
1
|
-
class AutoCorrect
|
2
|
-
module String
|
3
|
-
def auto_space!
|
4
|
-
ActiveSupport::Deprecation.warn("String.auto_space! is deprecated and will be removed in auto-corrrect 1.0, please use AutoCorrect.format instead.")
|
5
|
-
self.sub!(self, AutoCorrect.format(self))
|
6
|
-
end
|
7
|
-
|
8
|
-
def auto_correct!
|
9
|
-
ActiveSupport::Deprecation.warn("String.auto_correct! is deprecated and will be removed in auto-corrrect 1.0, please use AutoCorrect.format instead.")
|
10
|
-
self.sub!(self, AutoCorrect.format(self))
|
11
|
-
end
|
12
|
-
end
|
13
|
-
end
|