unicode_alphanumeric 0.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/unicode_alphanumeric.rb +51 -0
- metadata +94 -0
@@ -0,0 +1,51 @@
|
|
1
|
+
require 'unicode'
|
2
|
+
|
3
|
+
module UnicodeAlphanumeric
|
4
|
+
def self.filter(str, options = {})
|
5
|
+
replace(str, '', options)
|
6
|
+
end
|
7
|
+
|
8
|
+
def self.replace(str, replacement, options = {})
|
9
|
+
str.gsub(ascii_regex(options)) do |char|
|
10
|
+
alphanumeric?(char, options) ? char : replacement
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.scan(str, options = {})
|
15
|
+
non_alphanumeric = []
|
16
|
+
str.scan(ascii_regex(options)) do |char|
|
17
|
+
non_alphanumeric << char if !alphanumeric?(char, options)
|
18
|
+
end
|
19
|
+
non_alphanumeric
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.map(str, options = {})
|
23
|
+
str.gsub(ascii_regex(options)) do |char|
|
24
|
+
alphanumeric?(char, options) ? char : yield(char)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
private
|
29
|
+
|
30
|
+
def self.alphanumeric?(char, options)
|
31
|
+
# If there's any intersection between the string's categories and the alphanumeric
|
32
|
+
# categories, then the character is alphanumeric.
|
33
|
+
!(alphanumeric_categories(options) & Unicode.categories(char)).empty?
|
34
|
+
end
|
35
|
+
|
36
|
+
def self.alphanumeric_categories(options)
|
37
|
+
categories = [:Lowercase_Letter, :Uppercase_Letter, :Decimal_Number]
|
38
|
+
if options[:spaces] and options[:spaces] != :ascii
|
39
|
+
categories << :Space_Separator
|
40
|
+
end
|
41
|
+
categories
|
42
|
+
end
|
43
|
+
|
44
|
+
def self.ascii_regex(options)
|
45
|
+
if options[:spaces]
|
46
|
+
/[^a-zA-Z0-9 ]/
|
47
|
+
else
|
48
|
+
/[^a-zA-Z0-9]/
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
metadata
ADDED
@@ -0,0 +1,94 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: unicode_alphanumeric
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jarrett Colby
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2014-03-03 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: unicode
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 0.4.4
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 0.4.4
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: minitest
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: turn
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
description: Removes, replaces, transforms, or detects non-alphanumeric Unicode characters
|
63
|
+
in a string
|
64
|
+
email: jarrett@madebyhq.com
|
65
|
+
executables: []
|
66
|
+
extensions: []
|
67
|
+
extra_rdoc_files: []
|
68
|
+
files:
|
69
|
+
- lib/unicode_alphanumeric.rb
|
70
|
+
homepage: http://madebyhq.com/
|
71
|
+
licenses: []
|
72
|
+
post_install_message:
|
73
|
+
rdoc_options: []
|
74
|
+
require_paths:
|
75
|
+
- lib
|
76
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
77
|
+
none: false
|
78
|
+
requirements:
|
79
|
+
- - ! '>='
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '0'
|
82
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
83
|
+
none: false
|
84
|
+
requirements:
|
85
|
+
- - ! '>='
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0'
|
88
|
+
requirements: []
|
89
|
+
rubyforge_project:
|
90
|
+
rubygems_version: 1.8.25
|
91
|
+
signing_key:
|
92
|
+
specification_version: 3
|
93
|
+
summary: Filters non-alphanumeric Unicode characters
|
94
|
+
test_files: []
|