unicode-tools 1.0.1
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.
- checksums.yaml +7 -0
- data/.gitignore +15 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +22 -0
- data/README.md +4 -0
- data/Rakefile +10 -0
- data/lib/unicode-tools.rb +20 -0
- data/lib/unicode-tools/bidi.rb +20 -0
- data/lib/unicode-tools/string_ext/base.rb +20 -0
- data/lib/unicode-tools/string_ext/squish.rb +27 -0
- data/lib/unicode-tools/string_ext/trim.rb +40 -0
- data/lib/unicode-tools/whitespace.rb +44 -0
- data/test/test_unicode_tools.rb +23 -0
- data/unicode-tools.gemspec +21 -0
- metadata +86 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4e05d62c46b9719b21c9948d09839218ae0b987c
|
4
|
+
data.tar.gz: efd5a84c44ed55899af1fbaaf7977abfdf439c24
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 8ee83292371cf5d714ab80f3617842d105d5a167d92848fd686dde2f91e7753bbcfef0d355aa0f2f7eeafd1a23f32c93ea62a95ae649c4fedd0ce0535e765762
|
7
|
+
data.tar.gz: 6be9d74ba8b3decd9cd131c4cdd504d925ade86071b48b891ef1e51d799276d63c593fac0b48d67b4fb590a1b00e8ca4b9005a16ec38b71e425c32d4b0ffd877
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 Yaroslav Konoplov
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
data/Rakefile
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
# Override ActiveSupport's String#squish
|
5
|
+
begin
|
6
|
+
require 'active_support/core_ext/string'
|
7
|
+
rescue LoadError
|
8
|
+
end
|
9
|
+
|
10
|
+
require 'unicode-tools/whitespace'
|
11
|
+
require 'unicode-tools/string_ext/base'
|
12
|
+
require 'unicode-tools/string_ext/trim'
|
13
|
+
require 'unicode-tools/string_ext/squish'
|
14
|
+
require 'unicode-tools/bidi'
|
15
|
+
|
16
|
+
class String
|
17
|
+
include UnicodeTools::StringExt::Base
|
18
|
+
include UnicodeTools::StringExt::Trim
|
19
|
+
include UnicodeTools::StringExt::Squish
|
20
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
module UnicodeTools
|
5
|
+
BIDI_OVERRIDE_CHARS_REGEX = /\u00E2\u0080[\u008E\u008F\u00AA-\u00AE]/.freeze
|
6
|
+
|
7
|
+
class << self
|
8
|
+
def has_bidi_override?(string)
|
9
|
+
!!(string =~ BIDI_OVERRIDE_CHARS_REGEX)
|
10
|
+
end
|
11
|
+
|
12
|
+
def strip_bidi_override_chars(string)
|
13
|
+
string.gsub(BIDI_OVERRIDE_CHARS_REGEX, '')
|
14
|
+
end
|
15
|
+
|
16
|
+
def strip_bidi_override_chars!(string)
|
17
|
+
string.gsub!(BIDI_OVERRIDE_CHARS_REGEX, '')
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
module UnicodeTools
|
5
|
+
module StringExt
|
6
|
+
module Base
|
7
|
+
def has_whitespace?
|
8
|
+
!!(self =~ WHITESPACE_REGEX)
|
9
|
+
end
|
10
|
+
|
11
|
+
def replace_whitespace(replacement = nil, &block)
|
12
|
+
gsub(WHITESPACE_REGEX, replacement, &block)
|
13
|
+
end
|
14
|
+
|
15
|
+
def replace_whitespace!(replacement = nil, &block)
|
16
|
+
gsub!(WHITESPACE_REGEX, replacement, &block)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
module UnicodeTools
|
5
|
+
module StringExt
|
6
|
+
module Squish
|
7
|
+
|
8
|
+
# Removes leading, trailing whitespace and
|
9
|
+
# collapses remaining whitespace into one group each.
|
10
|
+
#
|
11
|
+
# string = " Hello\f\n\r\t\v\u00A0\u1680\u180e\u2000
|
12
|
+
# \u2001\u2002\u2003\u2004\u2005\u2006
|
13
|
+
# \u2007\u2008\u2009\u200a\u2028\u2029
|
14
|
+
# \u2028\u2029\u202f\u205f\u3000 World! "
|
15
|
+
# string.squish => "Hello World!"
|
16
|
+
def squish
|
17
|
+
dup.squish!
|
18
|
+
end
|
19
|
+
|
20
|
+
def squish!
|
21
|
+
gsub!(SURROUNDING_WHITESPACE_REGEX, '')
|
22
|
+
gsub!(WHITESPACE_REGEX, ' ')
|
23
|
+
self
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
module UnicodeTools
|
5
|
+
module StringExt
|
6
|
+
module Trim
|
7
|
+
|
8
|
+
# Removes leading and trailing whitespace.
|
9
|
+
#
|
10
|
+
# string = "\f\n\r\t\v\u00A0\u1680\u180e\u2000
|
11
|
+
# \u2001\u2002\u2003\u2004\u2005\u2006
|
12
|
+
# \u2007\u2008\u2009\u200a\u2028\u2029
|
13
|
+
# \u2028\u2029\u202f\u205f\u3000"
|
14
|
+
# string.trim => ""
|
15
|
+
def trim
|
16
|
+
gsub(SURROUNDING_WHITESPACE_REGEX, '')
|
17
|
+
end
|
18
|
+
|
19
|
+
def trim!
|
20
|
+
gsub!(SURROUNDING_WHITESPACE_REGEX, '')
|
21
|
+
end
|
22
|
+
|
23
|
+
def ltrim
|
24
|
+
gsub(LEADING_WHITESPACE_REGEX, '')
|
25
|
+
end
|
26
|
+
|
27
|
+
def ltrim!
|
28
|
+
gsub!(LEADING_WHITESPACE_REGEX, '')
|
29
|
+
end
|
30
|
+
|
31
|
+
def rtrim
|
32
|
+
gsub(TRAILING_WHITESPACE_REGEX, '')
|
33
|
+
end
|
34
|
+
|
35
|
+
def rtrim!
|
36
|
+
gsub!(TRAILING_WHITESPACE_REGEX, '')
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
module UnicodeTools
|
5
|
+
# http://unicode.org/charts/uca/
|
6
|
+
WHITESPACE_CHARS = %w( \u0009-\u000D \u0085 \u2028 \u2029
|
7
|
+
\u0020 \u3000 \u1680 \u2000-\u200A
|
8
|
+
\u205F \u00A0 \u202F \u180E ).freeze
|
9
|
+
|
10
|
+
WHITESPACE_REGEX = /[#{WHITESPACE_CHARS.join('')}]+/.freeze
|
11
|
+
LEADING_WHITESPACE_REGEX = /\A#{WHITESPACE_REGEX.source}+/.freeze
|
12
|
+
TRAILING_WHITESPACE_REGEX = /#{WHITESPACE_REGEX.source}+\z/.freeze
|
13
|
+
SURROUNDING_WHITESPACE_REGEX = /(\A#{WHITESPACE_REGEX.source})|(#{WHITESPACE_REGEX.source}\z)/.freeze
|
14
|
+
|
15
|
+
class << self
|
16
|
+
def has_whitespace?(string)
|
17
|
+
string.has_whitespace?
|
18
|
+
end
|
19
|
+
|
20
|
+
def trim(string)
|
21
|
+
string.trim
|
22
|
+
end
|
23
|
+
|
24
|
+
def trim!(string)
|
25
|
+
string.trim!
|
26
|
+
end
|
27
|
+
|
28
|
+
def squish(string)
|
29
|
+
string.squish
|
30
|
+
end
|
31
|
+
|
32
|
+
def squish!(string)
|
33
|
+
string.squish!
|
34
|
+
end
|
35
|
+
|
36
|
+
def replace_whitespace(string, replacement = nil, &block)
|
37
|
+
string.replace_whitespace(replacement, &block)
|
38
|
+
end
|
39
|
+
|
40
|
+
def replace_whitespace!(string, replacement = nil, &block)
|
41
|
+
string.replace_whitespace!(replacement, &block)
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require 'unicode-tools'
|
5
|
+
require 'test/unit'
|
6
|
+
|
7
|
+
class UnicodeToolsTest < Test::Unit::TestCase
|
8
|
+
def test_trim
|
9
|
+
s = ["\f\n\r\t\v\u00A0\u1680\u180e\u2000\u2001",
|
10
|
+
"\u2002\u2003\u2004\u2005\u2006\u2007\u2008",
|
11
|
+
"\u2009\u200a\u2028\u2029\u2028\u2029\u202f\u205f\u3000"].join('')
|
12
|
+
assert_equal(s.trim, '')
|
13
|
+
assert_equal(UnicodeTools.trim(s), '')
|
14
|
+
end
|
15
|
+
|
16
|
+
def test_squish
|
17
|
+
s = ["Hello\f\n\r\t\v\u00A0\u1680\u180e\u2000\u2001",
|
18
|
+
"\u2002\u2003\u2004\u2005\u2006\u2007\u2008",
|
19
|
+
"\u2009\u200a\u2028\u2029\u2028\u2029\u202f\u205f\u3000 world!"].join('')
|
20
|
+
assert_equal(s.squish, 'Hello world!')
|
21
|
+
assert_equal(UnicodeTools.squish(s), 'Hello world!')
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
Gem::Specification.new do |s|
|
5
|
+
s.name = 'unicode-tools'
|
6
|
+
s.version = '1.0.1'
|
7
|
+
s.authors = ['Yaroslav Konoplov']
|
8
|
+
s.email = ['eahome00@gmail.com']
|
9
|
+
s.summary = 'Unicode Tools'
|
10
|
+
s.description = 'Unicode Tools'
|
11
|
+
s.homepage = 'http://github.com/yivo/unicode-tools'
|
12
|
+
s.license = 'MIT'
|
13
|
+
|
14
|
+
s.executables = `git ls-files -z -- bin/*`.split("\x0").map{ |f| File.basename(f) }
|
15
|
+
s.files = `git ls-files -z`.split("\x0")
|
16
|
+
s.test_files = `git ls-files -z -- {test,spec,features}/*`.split("\x0")
|
17
|
+
s.require_paths = ['lib']
|
18
|
+
|
19
|
+
s.add_development_dependency 'rake', '~> 10.0'
|
20
|
+
s.add_development_dependency 'test-unit', '~> 3.1.8'
|
21
|
+
end
|
metadata
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: unicode-tools
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Yaroslav Konoplov
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-10-20 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rake
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '10.0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '10.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: test-unit
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 3.1.8
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 3.1.8
|
41
|
+
description: Unicode Tools
|
42
|
+
email:
|
43
|
+
- eahome00@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- ".gitignore"
|
49
|
+
- Gemfile
|
50
|
+
- LICENSE.txt
|
51
|
+
- README.md
|
52
|
+
- Rakefile
|
53
|
+
- lib/unicode-tools.rb
|
54
|
+
- lib/unicode-tools/bidi.rb
|
55
|
+
- lib/unicode-tools/string_ext/base.rb
|
56
|
+
- lib/unicode-tools/string_ext/squish.rb
|
57
|
+
- lib/unicode-tools/string_ext/trim.rb
|
58
|
+
- lib/unicode-tools/whitespace.rb
|
59
|
+
- test/test_unicode_tools.rb
|
60
|
+
- unicode-tools.gemspec
|
61
|
+
homepage: http://github.com/yivo/unicode-tools
|
62
|
+
licenses:
|
63
|
+
- MIT
|
64
|
+
metadata: {}
|
65
|
+
post_install_message:
|
66
|
+
rdoc_options: []
|
67
|
+
require_paths:
|
68
|
+
- lib
|
69
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
70
|
+
requirements:
|
71
|
+
- - ">="
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
version: '0'
|
74
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
75
|
+
requirements:
|
76
|
+
- - ">="
|
77
|
+
- !ruby/object:Gem::Version
|
78
|
+
version: '0'
|
79
|
+
requirements: []
|
80
|
+
rubyforge_project:
|
81
|
+
rubygems_version: 2.5.1
|
82
|
+
signing_key:
|
83
|
+
specification_version: 4
|
84
|
+
summary: Unicode Tools
|
85
|
+
test_files:
|
86
|
+
- test/test_unicode_tools.rb
|