wavedash 0.1.0
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/.rspec +2 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +13 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +100 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/lib/wavedash.rb +59 -0
- data/lib/wavedash/version.rb +3 -0
- data/wavedash.gemspec +24 -0
- metadata +99 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 5861f53c58547e735f4b8c2ecfd69e53e67487e9
|
4
|
+
data.tar.gz: c2ccc8f495977b929f221d34a9ad52e3200c53fa
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: f36db7862d0f9e6d393870d785f3f3ef9ff1ad2f090b17c04761d8301db206778aabcd854d79bf564f008b25d526a28f5e2a84fd60e6e91c673c1879e7cf1fa9
|
7
|
+
data.tar.gz: 521b9230335c8370539af0e311387029de89bb8d0e0ba1745bc049fec030a381a90a0ba7648cdcdea2f931263da090f0752107613edfb6addbb1536f64fff665
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
|
4
|
+
|
5
|
+
We are committed to making participation in this project a harassment-free experience for everyone, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, ethnicity, age, or religion.
|
6
|
+
|
7
|
+
Examples of unacceptable behavior by participants include the use of sexual language or imagery, derogatory comments or personal attacks, trolling, public or private harassment, insults, or other unprofessional conduct.
|
8
|
+
|
9
|
+
Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct. Project maintainers who do not follow the Code of Conduct may be removed from the project team.
|
10
|
+
|
11
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting one or more of the project maintainers.
|
12
|
+
|
13
|
+
This Code of Conduct is adapted from the [Contributor Covenant](http://contributor-covenant.org), version 1.0.0, available at [http://contributor-covenant.org/version/1/0/0/](http://contributor-covenant.org/version/1/0/0/)
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Takatoshi Ono
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
# Wavedash [![Build Status](https://travis-ci.org/takatoshiono/wavedash.svg?branch=master)](https://travis-ci.org/takatoshiono/wavedash)
|
2
|
+
|
3
|
+
Normalize unencodable characters that raise `Encoding::UndefinedConversionError` exception in `String#encode`.
|
4
|
+
|
5
|
+
### Support encoding
|
6
|
+
|
7
|
+
* eucjp-ms
|
8
|
+
* euc-jp
|
9
|
+
* cp932
|
10
|
+
* shift_jis
|
11
|
+
|
12
|
+
## Installation
|
13
|
+
|
14
|
+
Add this line to your application's Gemfile:
|
15
|
+
|
16
|
+
```ruby
|
17
|
+
gem 'wavedash'
|
18
|
+
```
|
19
|
+
|
20
|
+
And then execute:
|
21
|
+
|
22
|
+
$ bundle
|
23
|
+
|
24
|
+
Or install it yourself as:
|
25
|
+
|
26
|
+
$ gem install wavedash
|
27
|
+
|
28
|
+
## Usage
|
29
|
+
|
30
|
+
### destination_encoding
|
31
|
+
|
32
|
+
First af all, configure destination encoding that your application needs.
|
33
|
+
|
34
|
+
```ruby
|
35
|
+
require 'wavedash'
|
36
|
+
|
37
|
+
Wavedash.destination_encoding = 'eucjp-ms'
|
38
|
+
```
|
39
|
+
|
40
|
+
### #normalize
|
41
|
+
|
42
|
+
Normalize characters like "WAVE DASH (U+301C)"
|
43
|
+
|
44
|
+
```ruby
|
45
|
+
str = "こんにちは\u{301C}" # => "こんにちは〜"
|
46
|
+
str.encode('eucjp-ms') # => Encoding::UndefinedConversionError: U+301C from UTF-8 to eucJP-ms
|
47
|
+
|
48
|
+
normalized = Wavedash.normalize(str) # => "こんにちは~"
|
49
|
+
normalized.encode('eucjp-ms') # => "\x{A4B3}\x{A4F3}\x{A4CB}\x{A4C1}\x{A4CF}\x{A1C1}" ("こんにちは~")
|
50
|
+
```
|
51
|
+
|
52
|
+
### #invalid?
|
53
|
+
|
54
|
+
Detect unencodable characters
|
55
|
+
|
56
|
+
```ruby
|
57
|
+
str = "こんにちは\u{301C}" # => "こんにちは〜"
|
58
|
+
Wavedash.invalid?(str) # => true
|
59
|
+
```
|
60
|
+
|
61
|
+
### Thought of Wavedash
|
62
|
+
|
63
|
+
Character code conversion is required when interact between softwares that treet different character code. For example, it is a situation such as the following.
|
64
|
+
|
65
|
+
* A Web application written in UTF-8 using a database saved in EUC-JP
|
66
|
+
* Exchanging data files(csv,tsv,..) between different systems
|
67
|
+
|
68
|
+
In Ruby, You can convert a character code using `String#encode`, but some characters cannot. `Encoding::UndefinedConversionError` raises when a character is undefined in the destination encoding. But `String#encode` has options. You can specify `:undef => :replace` then replace the undefined characters with the replacement character.
|
69
|
+
|
70
|
+
`Wavedash` is similar to `String#encode` with `:undef => :replace`, but it does more aggressive character conversion.
|
71
|
+
|
72
|
+
Despite some characters have resembling shape, character code point is different each other. For example, when you convert characters to EUCJP-MS from UTF-8, can convert "~" (FULLWIDTH TILDE U+FF5E) but cannot convert "〜" (WAVE DASH U+301C). The opposite will occur when you convert to EUC-JP.
|
73
|
+
|
74
|
+
UNICODE | EUC-JP | EUCJP-MS |
|
75
|
+
--------|--------|---------
|
76
|
+
"〜" U+301C WAVE-DASH | 0xA1C1 | Encoding::UndefinedConversionError
|
77
|
+
"~" U+FF5E FULLWIDTH TILDE | Encoding::UndefinedConversionError | 0xA1C1
|
78
|
+
|
79
|
+
In Web applications, it depends on the client environment that the input character as "〜" is U+301C or U+FF5E. This cannot select by the application. What you can do with the application is only to determine the handling of the unencodable characters.
|
80
|
+
|
81
|
+
`Wavedash` offers the option that to convert unencodable characters to resembling characters.
|
82
|
+
|
83
|
+
## Development
|
84
|
+
|
85
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake rspec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
86
|
+
|
87
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
88
|
+
|
89
|
+
## Contributing
|
90
|
+
|
91
|
+
1. Fork it
|
92
|
+
2. Create your feature branch (git checkout -b my-new-feature)
|
93
|
+
3. Commit your changes (git commit -am 'Add some feature')
|
94
|
+
4. Push to the branch (git push origin my-new-feature)
|
95
|
+
5. Create new Pull Request
|
96
|
+
|
97
|
+
## License
|
98
|
+
|
99
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
100
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "wavedash"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/wavedash.rb
ADDED
@@ -0,0 +1,59 @@
|
|
1
|
+
require "wavedash/version"
|
2
|
+
|
3
|
+
module Wavedash
|
4
|
+
@@destination_encoding = nil
|
5
|
+
|
6
|
+
CHARACTER_CODE_MAPPING = {
|
7
|
+
'eucjp-ms' => {
|
8
|
+
"\u{301C}" => "\u{FF5E}", # 'WAVE DASH' => 'FULLWIDTH TILDE'
|
9
|
+
"\u{2212}" => "\u{FF0D}", # 'MINUS SIGN' => 'FULLWIDTH HYPHEN-MINUS'
|
10
|
+
"\u{2016}" => "\u{2225}", # 'DOUBLE VERTICAL LINE' => 'PARALLEL TO'
|
11
|
+
"\u{2014}" => "\u{2015}", # 'EM DASH' => 'HORIZONTAL BAR'
|
12
|
+
"\u{00A2}" => "\u{FFE0}", # 'CENT SIGN' => 'FULLWIDTH CENT SIGN'
|
13
|
+
"\u{00A3}" => "\u{FFE1}", # 'POUND SIGN' => 'FULLWIDTH POUND SIGN'
|
14
|
+
"\u{00AC}" => "\u{FFE2}", # 'NOT SIGN' => 'FULLWIDTH NOT SIGN'
|
15
|
+
},
|
16
|
+
'euc-jp' => {
|
17
|
+
"\u{FF5E}" => "\u{301C}", # 'FULLWIDTH TILDE' => 'WAVE DASH'
|
18
|
+
"\u{FF0D}" => "\u{2212}", # 'FULLWIDTH HYPHEN-MINUS' => 'MINUS SIGN'
|
19
|
+
"\u{2225}" => "\u{2016}", # 'PARALLEL TO' => 'DOUBLE VERTICAL LINE'
|
20
|
+
"\u{FFE0}" => "\u{00A2}", # 'FULLWIDTH CENT SIGN' => 'CENT SIGN'
|
21
|
+
"\u{FFE1}" => "\u{00A3}", # 'FULLWIDTH POUND SIGN' => 'POUND SIGN'
|
22
|
+
"\u{FFE2}" => "\u{00AC}", # 'FULLWIDTH NOT SIGN' => 'NOT SIGN'
|
23
|
+
},
|
24
|
+
'cp932' => {
|
25
|
+
"\u{301C}" => "\u{FF5E}", # 'WAVE DASH' => 'FULLWIDTH TILDE'
|
26
|
+
"\u{2212}" => "\u{FF0D}", # 'MINUS SIGN' => 'FULLWIDTH HYPHEN-MINUS'
|
27
|
+
"\u{2016}" => "\u{2225}", # 'DOUBLE VERTICAL LINE' => 'PARALLEL TO'
|
28
|
+
"\u{2014}" => "\u{2015}", # 'EM DASH' => 'HORIZONTAL BAR'
|
29
|
+
"\u{00A2}" => "\u{FFE0}", # 'CENT SIGN' => 'FULLWIDTH CENT SIGN'
|
30
|
+
"\u{00A3}" => "\u{FFE1}", # 'POUND SIGN' => 'FULLWIDTH POUND SIGN'
|
31
|
+
"\u{00AC}" => "\u{FFE2}", # 'NOT SIGN' => 'FULLWIDTH NOT SIGN'
|
32
|
+
},
|
33
|
+
'shift_jis' => {
|
34
|
+
"\u{FF5E}" => "\u{301C}", # 'FULLWIDTH TILDE' => 'WAVE DASH'
|
35
|
+
"\u{FF0D}" => "\u{2212}", # 'FULLWIDTH HYPHEN-MINUS' => 'MINUS SIGN'
|
36
|
+
"\u{2225}" => "\u{2016}", # 'PARALLEL TO' => 'DOUBLE VERTICAL LINE'
|
37
|
+
"\u{FFE0}" => "\u{00A2}", # 'FULLWIDTH CENT SIGN' => 'CENT SIGN'
|
38
|
+
"\u{FFE1}" => "\u{00A3}", # 'FULLWIDTH POUND SIGN' => 'POUND SIGN'
|
39
|
+
"\u{FFE2}" => "\u{00AC}", # 'FULLWIDTH NOT SIGN' => 'NOT SIGN'
|
40
|
+
},
|
41
|
+
}
|
42
|
+
|
43
|
+
def self.destination_encoding=(encoding)
|
44
|
+
@@destination_encoding = encoding
|
45
|
+
end
|
46
|
+
|
47
|
+
def self.normalize(str)
|
48
|
+
mapping = CHARACTER_CODE_MAPPING[@@destination_encoding]
|
49
|
+
return str unless mapping
|
50
|
+
str.tr(mapping.keys.join, mapping.values.join)
|
51
|
+
end
|
52
|
+
|
53
|
+
def self.invalid?(str)
|
54
|
+
return false unless str.is_a?(String)
|
55
|
+
mapping = CHARACTER_CODE_MAPPING[@@destination_encoding]
|
56
|
+
return false unless mapping
|
57
|
+
str.each_char.any? { |c| mapping[c] }
|
58
|
+
end
|
59
|
+
end
|
data/wavedash.gemspec
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
lib = File.expand_path('../lib', __FILE__)
|
2
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
3
|
+
require 'wavedash/version'
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "wavedash"
|
7
|
+
spec.version = Wavedash::VERSION
|
8
|
+
spec.authors = ["Takatoshi Ono"]
|
9
|
+
spec.email = ["takatoshi.ono@gmail.com"]
|
10
|
+
|
11
|
+
spec.summary = %q{Normalize unencodable characters}
|
12
|
+
spec.description = %q{Normalize unencodable characters}
|
13
|
+
spec.homepage = "https://github.com/takatoshiono/wavedash"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.10"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,99 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: wavedash
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Takatoshi Ono
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-07-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.10'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.10'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description: Normalize unencodable characters
|
56
|
+
email:
|
57
|
+
- takatoshi.ono@gmail.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- ".gitignore"
|
63
|
+
- ".rspec"
|
64
|
+
- ".travis.yml"
|
65
|
+
- CODE_OF_CONDUCT.md
|
66
|
+
- Gemfile
|
67
|
+
- LICENSE.txt
|
68
|
+
- README.md
|
69
|
+
- Rakefile
|
70
|
+
- bin/console
|
71
|
+
- bin/setup
|
72
|
+
- lib/wavedash.rb
|
73
|
+
- lib/wavedash/version.rb
|
74
|
+
- wavedash.gemspec
|
75
|
+
homepage: https://github.com/takatoshiono/wavedash
|
76
|
+
licenses:
|
77
|
+
- MIT
|
78
|
+
metadata: {}
|
79
|
+
post_install_message:
|
80
|
+
rdoc_options: []
|
81
|
+
require_paths:
|
82
|
+
- lib
|
83
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
84
|
+
requirements:
|
85
|
+
- - ">="
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0'
|
88
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
89
|
+
requirements:
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: '0'
|
93
|
+
requirements: []
|
94
|
+
rubyforge_project:
|
95
|
+
rubygems_version: 2.2.2
|
96
|
+
signing_key:
|
97
|
+
specification_version: 4
|
98
|
+
summary: Normalize unencodable characters
|
99
|
+
test_files: []
|