unaccent 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/.github/workflows/build.yml +36 -0
- data/.gitignore +9 -0
- data/.ruby-version +1 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +74 -0
- data/Rakefile +8 -0
- data/bin/benchmark +81 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/unaccent/accentmap.rb +17668 -0
- data/lib/unaccent/string.rb +23 -0
- data/lib/unaccent/version.rb +3 -0
- data/lib/unaccent.rb +78 -0
- data/unaccent.gemspec +24 -0
- metadata +86 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 22fd05234b8a82c9fb4528e7490bc96d35d6004891106e64b89a41c3019fb05d
|
4
|
+
data.tar.gz: c8878cdf36d7647264676d22b6068398a9c5a4c67dc48a65a7e2033a9d65e97c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 8fddd65833fc29aaaee6dd35088181403803714bd54d0dccfaa499dad55928c2263db27561cdefa0a565d0bb587a64d969f2523a3a87994caa9935b530a1461b
|
7
|
+
data.tar.gz: 33b518cba22b0919320a1b4ac65bd4406b2dac1b2cbe17b63448a59ea132967a2014120dc5ca461e74de9fa4cf782ceb9422fe548a56538c204ec723c6549457
|
@@ -0,0 +1,36 @@
|
|
1
|
+
---
|
2
|
+
name: Build
|
3
|
+
|
4
|
+
on:
|
5
|
+
push:
|
6
|
+
branches: [master]
|
7
|
+
paths-ignore:
|
8
|
+
- 'README.md'
|
9
|
+
- 'LICENSE.txt'
|
10
|
+
- 'bin/**'
|
11
|
+
pull_request:
|
12
|
+
branches: [master]
|
13
|
+
|
14
|
+
permissions:
|
15
|
+
contents: read
|
16
|
+
|
17
|
+
jobs:
|
18
|
+
build:
|
19
|
+
strategy:
|
20
|
+
matrix:
|
21
|
+
os: [ubuntu-latest]
|
22
|
+
ruby: ['2.7']
|
23
|
+
runs-on: ${{ matrix.os }}
|
24
|
+
|
25
|
+
steps:
|
26
|
+
- uses: actions/checkout@v3
|
27
|
+
|
28
|
+
- name: Set up Ruby
|
29
|
+
uses: ruby/setup-ruby@v1
|
30
|
+
with:
|
31
|
+
ruby-version: ${{ matrix.ruby }}
|
32
|
+
bundler-cache: true
|
33
|
+
|
34
|
+
- name: Run tests
|
35
|
+
run: |
|
36
|
+
bundle exec rake test
|
data/.gitignore
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
3.1.2
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2022 Jonian Guveli
|
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 +1,74 @@
|
|
1
|
+
# Unaccent
|
2
|
+
|
3
|
+
Ruby gem to replace a string's accent characters with ASCII characters. Based on [SixArm Ruby Unaccent](https://github.com/SixArm/sixarm_ruby_unaccent).
|
4
|
+
|
5
|
+
[![Gem Version](https://badge.fury.io/rb/unaccent.svg)](https://badge.fury.io/rb/unaccent)
|
6
|
+
[![Build](https://github.com/hardpixel/unaccent/actions/workflows/build.yml/badge.svg)](https://github.com/hardpixel/unaccent/actions/workflows/build.yml)
|
7
|
+
[![Maintainability](https://api.codeclimate.com/v1/badges/9070ea120ceeddbcc1d2/maintainability)](https://codeclimate.com/github/hardpixel/unaccent/maintainability)
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
Add this line to your application's Gemfile:
|
12
|
+
|
13
|
+
```ruby
|
14
|
+
gem 'unaccent'
|
15
|
+
```
|
16
|
+
|
17
|
+
And then execute:
|
18
|
+
|
19
|
+
$ bundle install
|
20
|
+
|
21
|
+
Or install it yourself as:
|
22
|
+
|
23
|
+
$ gem install unaccent
|
24
|
+
|
25
|
+
## Usage
|
26
|
+
|
27
|
+
```ruby
|
28
|
+
require 'unaccent'
|
29
|
+
|
30
|
+
Unaccent.unaccent('déjà vu') # deja vu
|
31
|
+
Unaccent.unaccent('νέα') # νεα
|
32
|
+
|
33
|
+
require 'unaccent/string'
|
34
|
+
|
35
|
+
'déjà vu'.unaccent # deja vu
|
36
|
+
'νέα'.unaccent # νεα
|
37
|
+
```
|
38
|
+
|
39
|
+
## Benchmark
|
40
|
+
|
41
|
+
```
|
42
|
+
IPS Comparison:
|
43
|
+
gsub: 33804.1 i/s
|
44
|
+
each_char: 16639.9 i/s - 2.03x (± 0.00) slower
|
45
|
+
each_char (sixarm): 13708.2 i/s - 2.47x (± 0.00) slower
|
46
|
+
scan: 10390.0 i/s - 3.25x (± 0.00) slower
|
47
|
+
scan (sixarm): 8765.8 i/s - 3.86x (± 0.00) slower
|
48
|
+
split_map: 7800.9 i/s - 4.33x (± 0.00) slower
|
49
|
+
split_map (sixarm): 6780.7 i/s - 4.99x (± 0.00) slower
|
50
|
+
|
51
|
+
|
52
|
+
Memory Comparison:
|
53
|
+
gsub: 5947 allocated
|
54
|
+
each_char: 10704 allocated - 1.80x more
|
55
|
+
scan: 15368 allocated - 2.58x more
|
56
|
+
split_map: 20582 allocated - 3.46x more
|
57
|
+
split_map (sixarm): 23185 allocated - 3.90x more
|
58
|
+
each_char (sixarm): 24979 allocated - 4.20x more
|
59
|
+
scan (sixarm): 29979 allocated - 5.04x more
|
60
|
+
```
|
61
|
+
|
62
|
+
## Development
|
63
|
+
|
64
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
65
|
+
|
66
|
+
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).
|
67
|
+
|
68
|
+
## Contributing
|
69
|
+
|
70
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/hardpixel/unaccent.
|
71
|
+
|
72
|
+
## License
|
73
|
+
|
74
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/benchmark
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'bundler/inline'
|
4
|
+
require 'tempfile'
|
5
|
+
|
6
|
+
gemfile true, quiet: true do
|
7
|
+
source 'https://rubygems.org'
|
8
|
+
gemspec
|
9
|
+
|
10
|
+
gem 'benchmark-ips'
|
11
|
+
gem 'benchmark-memory'
|
12
|
+
gem 'sixarm_ruby_unaccent'
|
13
|
+
end
|
14
|
+
|
15
|
+
STRINGS = [
|
16
|
+
'String without accents in english',
|
17
|
+
'Streng med aksenter på norsk',
|
18
|
+
'Řetězec s akcenty v češtině',
|
19
|
+
'Chaîne avec accents en français',
|
20
|
+
'Cuerda con acentos en español',
|
21
|
+
'Corda amb accents en català',
|
22
|
+
'Stīga ar akcentiem latviešu valodā',
|
23
|
+
'Türkçe aksanlı dize',
|
24
|
+
'Varg me theks në shqip',
|
25
|
+
'Κείμενο με τόνους στα ελληνικά'
|
26
|
+
]
|
27
|
+
|
28
|
+
reports = lambda do |x|
|
29
|
+
x.report('gsub') do
|
30
|
+
STRINGS.each do |str|
|
31
|
+
Unaccent.via_gsub(str)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
x.report('scan') do
|
36
|
+
STRINGS.each do |str|
|
37
|
+
Unaccent.via_scan(str)
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
x.report('each_char') do
|
42
|
+
STRINGS.each do |str|
|
43
|
+
Unaccent.via_each_char(str)
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
x.report('split_map') do
|
48
|
+
STRINGS.each do |str|
|
49
|
+
Unaccent.via_split_map(str)
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
|
54
|
+
x.report('scan (sixarm)') do
|
55
|
+
STRINGS.each do |str|
|
56
|
+
str.unaccent_via_scan
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
x.report('each_char (sixarm)') do
|
61
|
+
STRINGS.each do |str|
|
62
|
+
str.unaccent_via_each_char
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
x.report('split_map (sixarm)') do
|
67
|
+
STRINGS.each do |str|
|
68
|
+
str.unaccent_via_split_map
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
Benchmark.ips do |x|
|
74
|
+
reports.call(x)
|
75
|
+
x.compare!
|
76
|
+
end
|
77
|
+
|
78
|
+
Benchmark.memory do |x|
|
79
|
+
reports.call(x)
|
80
|
+
x.compare!
|
81
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'bundler/setup'
|
4
|
+
require 'unaccent'
|
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(__FILE__)
|