thbar-diacritics_fu 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +5 -0
- data/Manifest.txt +6 -0
- data/README +34 -0
- data/diacritics_fu.gemspec +21 -0
- data/lib/diacritics_fu.rb +11 -0
- data/spec/diacritics_fu_spec.rb +26 -0
- metadata +68 -0
data/History.txt
ADDED
data/Manifest.txt
ADDED
data/README
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
Quick start
|
2
|
+
===========
|
3
|
+
|
4
|
+
DiacriticsFu::escape("éphémère")
|
5
|
+
=> "ephemere"
|
6
|
+
|
7
|
+
DiacriticsFu::escape("räksmörgås")
|
8
|
+
=> "raksmorgas"
|
9
|
+
|
10
|
+
What?
|
11
|
+
=====
|
12
|
+
|
13
|
+
A small library to remove accents from a string. Relies on ActiveSupport::Multibyte::Handlers::UTF8Handler (Rails).
|
14
|
+
|
15
|
+
Created because I needed a simple way to remove most diacritics from French sentences, while generating slugs (url) for a CMS (either Mephisto or ComatoseCMS).
|
16
|
+
|
17
|
+
Nb: this approach is not the fastest way to achieve this. It's good enough for me though.
|
18
|
+
|
19
|
+
The library is not packaged (either like a gem, or a plugin, that is). Just drop diacritics_fu.rb in your /lib folder.
|
20
|
+
|
21
|
+
Author
|
22
|
+
======
|
23
|
+
|
24
|
+
Thibaut Barrère (http://blog.logeek.fr)
|
25
|
+
|
26
|
+
TODO
|
27
|
+
====
|
28
|
+
|
29
|
+
This Git commit http://github.com/rails/rails/commit/22f75d539dca7b6f33cbf86e4e9d1944bb22731f indicates that the gem won't be able to work in future versions of rails => fix this.
|
30
|
+
|
31
|
+
License
|
32
|
+
=======
|
33
|
+
|
34
|
+
MIT
|
@@ -0,0 +1,21 @@
|
|
1
|
+
Gem::Specification.new do |s|
|
2
|
+
s.name = "diacritics_fu"
|
3
|
+
s.version = "1.0.0"
|
4
|
+
s.date = "2008-10-21"
|
5
|
+
s.summary = "Tiny Ruby library to remove accents and other diacritics from a string (relies on ActiveSupport)."
|
6
|
+
s.email = "thibaut.barrere@gmail.com"
|
7
|
+
s.homepage = "http://github.com/thbar/diacritics_fu"
|
8
|
+
s.description = "A small library to remove accents from a string."
|
9
|
+
s.has_rdoc = true
|
10
|
+
s.authors = ["Thibaut Barrère"]
|
11
|
+
s.files = ["History.txt",
|
12
|
+
"README",
|
13
|
+
"Manifest.txt",
|
14
|
+
"diacritics_fu.gemspec",
|
15
|
+
"lib/diacritics_fu.rb"]
|
16
|
+
s.test_files = ["spec/diacritics_fu_spec.rb"]
|
17
|
+
|
18
|
+
s.rdoc_options = ["--main", "README"]
|
19
|
+
s.extra_rdoc_files = ["History.txt", "Manifest.txt", "README"]
|
20
|
+
s.add_dependency("activesupport", ["> 0.0.0"])
|
21
|
+
end
|
@@ -0,0 +1,11 @@
|
|
1
|
+
# A tiny class to remove accents (éèê) and other diacritics (ç) from a string.
|
2
|
+
#
|
3
|
+
# Author:: Thibaut Barrère (mailto:thibaut.barrere@gmail.com)
|
4
|
+
# Copyright:: Copyright (c) 2008 LoGeek EURL
|
5
|
+
# License:: Distributes under the same terms as Ruby
|
6
|
+
module DiacriticsFu
|
7
|
+
# Remove all accents and other diacritics from the passed string (ie: éphémère will return ephemere)
|
8
|
+
def self.escape(str)
|
9
|
+
ActiveSupport::Multibyte::Handlers::UTF8Handler.normalize(str,:d).split(//u).reject { |e| e.length > 1 }.join
|
10
|
+
end
|
11
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../spec_helper'
|
2
|
+
require 'diacritics_fu'
|
3
|
+
|
4
|
+
describe "DiacriticsFu.escape" do
|
5
|
+
|
6
|
+
it "should remove the accents with grace" do
|
7
|
+
DiacriticsFu::escape("éphémère").should eql("ephemere")
|
8
|
+
DiacriticsFu::escape("éêèïîù").should eql("eeeiiu")
|
9
|
+
end
|
10
|
+
|
11
|
+
it "should work" do
|
12
|
+
DiacriticsFu::escape("räksmörgås").should eql("raksmorgas")
|
13
|
+
end
|
14
|
+
|
15
|
+
KNOWN_DIACRITICS = { "a" => "àäâ", "e" => "éèêë", "i" => "îï", "o" => "ôö", "u" => "üû", "c" => "ç",
|
16
|
+
"I" => "ÏÎ", "E" => "ÊË", "n" => "ñ", "O" => "ÔÖ", "Y" => "Ÿ", "y" => "ÿ", "N" => "Ñ" }
|
17
|
+
|
18
|
+
KNOWN_DIACRITICS.each do |expected_replacement,originals|
|
19
|
+
it "should transform any of '#{originals}' into '#{expected_replacement}'" do
|
20
|
+
originals.split(//).each do |original|
|
21
|
+
DiacriticsFu.escape(original).should eql(expected_replacement)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
metadata
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: thbar-diacritics_fu
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- "Thibaut Barr\xC3\xA8re"
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-10-21 00:00:00 -07:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: activesupport
|
17
|
+
version_requirement:
|
18
|
+
version_requirements: !ruby/object:Gem::Requirement
|
19
|
+
requirements:
|
20
|
+
- - ">"
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 0.0.0
|
23
|
+
version:
|
24
|
+
description: A small library to remove accents from a string.
|
25
|
+
email: thibaut.barrere@gmail.com
|
26
|
+
executables: []
|
27
|
+
|
28
|
+
extensions: []
|
29
|
+
|
30
|
+
extra_rdoc_files:
|
31
|
+
- History.txt
|
32
|
+
- Manifest.txt
|
33
|
+
- README
|
34
|
+
files:
|
35
|
+
- History.txt
|
36
|
+
- README
|
37
|
+
- Manifest.txt
|
38
|
+
- diacritics_fu.gemspec
|
39
|
+
- lib/diacritics_fu.rb
|
40
|
+
has_rdoc: true
|
41
|
+
homepage: http://github.com/thbar/diacritics_fu
|
42
|
+
post_install_message:
|
43
|
+
rdoc_options:
|
44
|
+
- --main
|
45
|
+
- README
|
46
|
+
require_paths:
|
47
|
+
- lib
|
48
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
49
|
+
requirements:
|
50
|
+
- - ">="
|
51
|
+
- !ruby/object:Gem::Version
|
52
|
+
version: "0"
|
53
|
+
version:
|
54
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
55
|
+
requirements:
|
56
|
+
- - ">="
|
57
|
+
- !ruby/object:Gem::Version
|
58
|
+
version: "0"
|
59
|
+
version:
|
60
|
+
requirements: []
|
61
|
+
|
62
|
+
rubyforge_project:
|
63
|
+
rubygems_version: 1.2.0
|
64
|
+
signing_key:
|
65
|
+
specification_version: 2
|
66
|
+
summary: Tiny Ruby library to remove accents and other diacritics from a string (relies on ActiveSupport).
|
67
|
+
test_files:
|
68
|
+
- spec/diacritics_fu_spec.rb
|