characteristics 0.1.0
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.
- checksums.yaml +7 -0
- data/.gitignore +2 -0
- data/.travis.yml +22 -0
- data/CHANGELOG.md +6 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +5 -0
- data/MIT-LICENSE.txt +20 -0
- data/README.md +73 -0
- data/Rakefile +38 -0
- data/characteristics.gemspec +22 -0
- data/lib/characteristics/ascii.rb +42 -0
- data/lib/characteristics/binary.rb +43 -0
- data/lib/characteristics/byte.rb +103 -0
- data/lib/characteristics/unicode.rb +103 -0
- data/lib/characteristics/version.rb +4 -0
- data/lib/characteristics.rb +65 -0
- data/spec/characteristics_spec.rb +181 -0
- metadata +82 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: be2da5691ab55cf6657a961f4ad7f4fc880a8b65
|
4
|
+
data.tar.gz: 71d2b668a4e2383aac937505ebaf8ec5450d3969
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: da6dad0bb4c897c7145064894c483625f8fb68162cf0e3e8b812a8dfc3cddb5c4aec49f04a7a8452ff7166ba5c74ebdd0600f084e6333e010b11345335bb1ac0
|
7
|
+
data.tar.gz: 02b16977833dbaa784516e08b9bb65581dad9c8bf2e32207b5f95f3d6b65a83f2fd3557c5abe05e0a878730906a5a193342eba248706a28c00cf37d7741e0901
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
sudo: false
|
2
|
+
language: ruby
|
3
|
+
|
4
|
+
rvm:
|
5
|
+
- ruby-head
|
6
|
+
- 2.4.0
|
7
|
+
- 2.3.3
|
8
|
+
- 2.2
|
9
|
+
- 2.1
|
10
|
+
- 2.0
|
11
|
+
- jruby-head
|
12
|
+
- jruby-9.1.7.0
|
13
|
+
|
14
|
+
cache:
|
15
|
+
- bundler
|
16
|
+
|
17
|
+
matrix:
|
18
|
+
allow_failures:
|
19
|
+
- rvm: jruby-head
|
20
|
+
- rvm: ruby-head
|
21
|
+
- rvm: 2.0
|
22
|
+
# fast_finish: true
|
data/CHANGELOG.md
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at opensource@janlelis.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/MIT-LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2017 Jan Lelis, mail@janlelis.de
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
# Characteristics [![[version]](https://badge.fury.io/rb/characteristics.svg)](http://badge.fury.io/rb/characteristics) [![[travis]](https://travis-ci.org/janlelis/characteristics.svg)](https://travis-ci.org/janlelis/characteristics)
|
2
|
+
|
3
|
+
A Ruby library which provides some basic information about how characters behave in different encodings:
|
4
|
+
|
5
|
+
- Is a character valid according to its encoding?
|
6
|
+
- Is a character assigned?
|
7
|
+
- Is a character a special control character?
|
8
|
+
- Could a character be invisible (blank)?
|
9
|
+
|
10
|
+
The [unibits](https://github.com/janlelis/unibits) gem makes use of this data to visualize it accordingliy.
|
11
|
+
|
12
|
+
## Setup
|
13
|
+
|
14
|
+
Add to your `Gemfile`:
|
15
|
+
|
16
|
+
```ruby
|
17
|
+
gem 'characteristics'
|
18
|
+
```
|
19
|
+
|
20
|
+
## Usage
|
21
|
+
|
22
|
+
```ruby
|
23
|
+
char_info = Characteristics.new(character)
|
24
|
+
char_info.valid? # => true / false
|
25
|
+
char_info.unicode? # => true / false
|
26
|
+
char_info.assigned? # => true / false
|
27
|
+
char_info.control? # => true / false
|
28
|
+
char_info.blank? # => true / false
|
29
|
+
```
|
30
|
+
|
31
|
+
## Types of Encodings
|
32
|
+
|
33
|
+
This library knows of four different kinds of encodings:
|
34
|
+
|
35
|
+
- **:unicode** Unicode familiy of multibyte encodings (*UTF-\**)
|
36
|
+
- **:ascii** 7-Bit ASCII (*US-ASCII*)
|
37
|
+
- **:binary** Arbitrary string (*ASCII-8BIT*)
|
38
|
+
- **:byte ** Known byte encoding (*ISO-8859-\**, *Windows-\**)
|
39
|
+
|
40
|
+
Other encodings are not supported, yet.
|
41
|
+
|
42
|
+
## Predicates
|
43
|
+
|
44
|
+
### `valid?`
|
45
|
+
|
46
|
+
Validness is determined by Ruby's String#valid_encoding?
|
47
|
+
|
48
|
+
### `unicode?`
|
49
|
+
|
50
|
+
`true` for Unicode encodings (`UTF-*`)
|
51
|
+
|
52
|
+
### `control?`
|
53
|
+
|
54
|
+
Control characters are codepoints in the is C0, delete or C1 control character range.
|
55
|
+
|
56
|
+
### `assigned?`
|
57
|
+
|
58
|
+
- All valid ASCII and BINARY characters are considered assigned
|
59
|
+
- For other byte based encodings, a character is considered assigned if it is not on the exception list included in this library. C0 control characters (and `\x7F`) are always considered assigned. C1 control characters are treated as assigned, if the encoding generally does not assign characters in the C1 region.
|
60
|
+
- For Unicode, the general category is considered
|
61
|
+
|
62
|
+
### `blank?`
|
63
|
+
|
64
|
+
The library includes a list of characters that might not be rendered visually. This list does not include unassigned codepoints, control characters (except for `\t`, `\n`, `\v`, `\f`, `\r`), or special formatting characters (right-to-left marker, variation selectors, etc).
|
65
|
+
|
66
|
+
## Todo
|
67
|
+
|
68
|
+
- Support all non-dummy encodings that Ruby supports
|
69
|
+
- Complete test matrix
|
70
|
+
|
71
|
+
## MIT License
|
72
|
+
|
73
|
+
Copyright (C) 2017 Jan Lelis <http://janlelis.com>. Released under the MIT license.
|
data/Rakefile
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
# # #
|
2
|
+
# Get gemspec info
|
3
|
+
|
4
|
+
gemspec_file = Dir['*.gemspec'].first
|
5
|
+
gemspec = eval File.read(gemspec_file), binding, gemspec_file
|
6
|
+
info = "#{gemspec.name} | #{gemspec.version} | " \
|
7
|
+
"#{gemspec.runtime_dependencies.size} dependencies | " \
|
8
|
+
"#{gemspec.files.size} files"
|
9
|
+
|
10
|
+
# # #
|
11
|
+
# Gem build and install task
|
12
|
+
|
13
|
+
desc info
|
14
|
+
task :gem do
|
15
|
+
puts info + "\n\n"
|
16
|
+
print " "; sh "gem build #{gemspec_file}"
|
17
|
+
FileUtils.mkdir_p 'pkg'
|
18
|
+
FileUtils.mv "#{gemspec.name}-#{gemspec.version}.gem", 'pkg'
|
19
|
+
puts; sh %{gem install --no-document pkg/#{gemspec.name}-#{gemspec.version}.gem}
|
20
|
+
end
|
21
|
+
|
22
|
+
# # #
|
23
|
+
# Start an IRB session with the gem loaded
|
24
|
+
|
25
|
+
desc "#{gemspec.name} | IRB"
|
26
|
+
task :irb do
|
27
|
+
sh "irb -I ./lib -r #{gemspec.name.gsub '-','/'}"
|
28
|
+
end
|
29
|
+
|
30
|
+
# # #
|
31
|
+
# Run specs
|
32
|
+
|
33
|
+
desc "#{gemspec.name} | Spec"
|
34
|
+
task :spec do
|
35
|
+
sh "for file in spec/*_spec.rb; do ruby $file; done"
|
36
|
+
end
|
37
|
+
task default: :spec
|
38
|
+
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
|
3
|
+
require File.dirname(__FILE__) + "/lib/characteristics/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |gem|
|
6
|
+
gem.name = "characteristics"
|
7
|
+
gem.version = Characteristics::VERSION
|
8
|
+
gem.summary = "Basic character properties."
|
9
|
+
gem.description = "A Ruby library which provides some basic information about how characters behave in different encodings."
|
10
|
+
gem.authors = ["Jan Lelis"]
|
11
|
+
gem.email = ["mail@janlelis.de"]
|
12
|
+
gem.homepage = "https://github.com/janlelis/characteristics"
|
13
|
+
gem.license = "MIT"
|
14
|
+
|
15
|
+
gem.files = Dir["{**/}{.*,*}"].select{ |path| File.file?(path) && path !~ /^pkg/ }
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
|
20
|
+
gem.required_ruby_version = "~> 2.0"
|
21
|
+
gem.add_dependency 'unicode-categories', '~> 1.1', '>= 1.1.2'
|
22
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
class AsciiCharacteristics < Characteristics
|
2
|
+
BLANKS = [
|
3
|
+
0x9,
|
4
|
+
0x20,
|
5
|
+
].freeze
|
6
|
+
|
7
|
+
SEPARATORS = [
|
8
|
+
0xA,
|
9
|
+
0xB,
|
10
|
+
0xC,
|
11
|
+
0xD,
|
12
|
+
].freeze
|
13
|
+
|
14
|
+
def initialize(char)
|
15
|
+
super
|
16
|
+
@ord = char.ord if @is_valid
|
17
|
+
end
|
18
|
+
|
19
|
+
def assigned?
|
20
|
+
true
|
21
|
+
end
|
22
|
+
|
23
|
+
def control?
|
24
|
+
c0? || delete?
|
25
|
+
end
|
26
|
+
|
27
|
+
def c0?
|
28
|
+
@is_valid && @ord < 0x20
|
29
|
+
end
|
30
|
+
|
31
|
+
def delete?
|
32
|
+
@is_valid && @ord == 0x7F
|
33
|
+
end
|
34
|
+
|
35
|
+
def c1?
|
36
|
+
false
|
37
|
+
end
|
38
|
+
|
39
|
+
def blank?
|
40
|
+
@is_valid && ( BLANKS.include?(@ord) || SEPARATORS.include?(@ord) )
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
class BinaryCharacteristics < Characteristics
|
2
|
+
BLANKS = [
|
3
|
+
0x9,
|
4
|
+
0x20,
|
5
|
+
].freeze
|
6
|
+
|
7
|
+
SEPARATORS = [
|
8
|
+
0xA,
|
9
|
+
0xB,
|
10
|
+
0xC,
|
11
|
+
0xD,
|
12
|
+
].freeze
|
13
|
+
|
14
|
+
def initialize(char)
|
15
|
+
@ord = char.ord
|
16
|
+
@encoding = char.encoding
|
17
|
+
@encoding_name = @encoding.name
|
18
|
+
end
|
19
|
+
|
20
|
+
def valid?
|
21
|
+
true
|
22
|
+
end
|
23
|
+
|
24
|
+
def assigned?
|
25
|
+
true
|
26
|
+
end
|
27
|
+
|
28
|
+
def control?
|
29
|
+
c0? || delete?
|
30
|
+
end
|
31
|
+
|
32
|
+
def c0?
|
33
|
+
@ord < 0x20
|
34
|
+
end
|
35
|
+
|
36
|
+
def delete?
|
37
|
+
@ord == 0x7F
|
38
|
+
end
|
39
|
+
|
40
|
+
def blank?
|
41
|
+
BLANKS.include?(@ord) || SEPARATORS.include?(@ord)
|
42
|
+
end
|
43
|
+
end
|
@@ -0,0 +1,103 @@
|
|
1
|
+
class ByteCharacteristics < Characteristics
|
2
|
+
HAS_C1 = /^(ISO-8859-)/
|
3
|
+
|
4
|
+
UNASSIGNED = {
|
5
|
+
0x81 => /^Windows-(1250|1252|1253|1254|1255|1257|1258)/,
|
6
|
+
0x83 => /^Windows-(1250|1257)/,
|
7
|
+
0x88 => /^Windows-(1250|1253|1257)/,
|
8
|
+
0x8A => /^Windows-(1253|1255|1257|1258)/,
|
9
|
+
0x8C => /^Windows-(1253|1255|1257)/,
|
10
|
+
0x8D => /^Windows-(1252|1253|1254|1255|1258)/,
|
11
|
+
0x8E => /^Windows-(1253|1254|1255|1258)/,
|
12
|
+
0x8F => /^Windows-(1252|1253|1254|1255|1258)/,
|
13
|
+
|
14
|
+
0x90 => /^Windows-(1250|1252|1253|1254|1255|1257|1258)/,
|
15
|
+
0x98 => /^Windows-(1250|1251|1253|1257)/,
|
16
|
+
0x9A => /^Windows-(1253|1255|1257|1258)/,
|
17
|
+
0x9B => /^Windows-(1252)/,
|
18
|
+
0x9C => /^Windows-(1253|1255|1257)/,
|
19
|
+
0x9D => /^Windows-(1253|1254|1255|1258)/,
|
20
|
+
0x9E => /^Windows-(1253|1254|1255|1258)/,
|
21
|
+
0x9F => /^Windows-(1253|1255|1257)/,
|
22
|
+
|
23
|
+
0xA1 => /^Windows-(1257)/,
|
24
|
+
0xA5 => /^Windows-(1257)/,
|
25
|
+
0xAA => /^Windows-(1253)/,
|
26
|
+
|
27
|
+
0xD2 => /^Windows-(1253)/,
|
28
|
+
0xD9 => /^Windows-(1255)/,
|
29
|
+
0xDA => /^Windows-(1255)/,
|
30
|
+
0xDB => /^Windows-(1255)/,
|
31
|
+
0xDC => /^Windows-(1255)/,
|
32
|
+
0xDD => /^Windows-(1255)/,
|
33
|
+
0xDE => /^Windows-(1255)/,
|
34
|
+
0xDF => /^Windows-(1255)/,
|
35
|
+
|
36
|
+
0xFB => /^Windows-(1255)/,
|
37
|
+
0xFC => /^Windows-(1255)/,
|
38
|
+
0xFF => /^Windows-(1253|1255)/,
|
39
|
+
}.freeze
|
40
|
+
|
41
|
+
BLANKS = [
|
42
|
+
0x9,
|
43
|
+
0x20,
|
44
|
+
].freeze
|
45
|
+
|
46
|
+
SEPARATORS = [
|
47
|
+
0xA,
|
48
|
+
0xB,
|
49
|
+
0xC,
|
50
|
+
0xD,
|
51
|
+
].freeze
|
52
|
+
|
53
|
+
EXTRA_BLANKS = {
|
54
|
+
0xA0 => /^(ISO-8859-|Windows-)/,
|
55
|
+
0x9D => /^Windows-(1256)/,
|
56
|
+
0x9F => /^Windows-(1256)/,
|
57
|
+
}.freeze
|
58
|
+
|
59
|
+
def initialize(char)
|
60
|
+
super
|
61
|
+
@ord = char.ord
|
62
|
+
end
|
63
|
+
|
64
|
+
def encoding_has_c0?
|
65
|
+
# !!(HAS_C0 =~ @encoding_name)
|
66
|
+
true
|
67
|
+
end
|
68
|
+
|
69
|
+
def encoding_has_delete?
|
70
|
+
# !!(HAS_C0 =~ @encoding_name)
|
71
|
+
true
|
72
|
+
end
|
73
|
+
|
74
|
+
def encoding_has_c1?
|
75
|
+
!!(HAS_C1 =~ @encoding_name)
|
76
|
+
end
|
77
|
+
|
78
|
+
def assigned?
|
79
|
+
control? || UNASSIGNED[@ord] !~ @encoding_name
|
80
|
+
end
|
81
|
+
|
82
|
+
def control?
|
83
|
+
c0? || c1? || delete?
|
84
|
+
end
|
85
|
+
|
86
|
+
def c0?
|
87
|
+
@ord < 0x20 && encoding_has_c0?
|
88
|
+
end
|
89
|
+
|
90
|
+
def c1?
|
91
|
+
@ord >= 0x80 && @ord < 0xA0 && encoding_has_c1?
|
92
|
+
end
|
93
|
+
|
94
|
+
def delete?
|
95
|
+
@ord == 0x7F && encoding_has_delete?
|
96
|
+
end
|
97
|
+
|
98
|
+
def blank?
|
99
|
+
BLANKS.include?(@ord) ||
|
100
|
+
SEPARATORS.include?(@ord) ||
|
101
|
+
EXTRA_BLANKS[@ord] =~ @encoding_name
|
102
|
+
end
|
103
|
+
end
|
@@ -0,0 +1,103 @@
|
|
1
|
+
require "unicode/categories"
|
2
|
+
|
3
|
+
class UnicodeCharacteristics < Characteristics
|
4
|
+
BLANKS = [
|
5
|
+
0x0009,
|
6
|
+
0x0020,
|
7
|
+
0x00AD,
|
8
|
+
0x115F,
|
9
|
+
0x1160,
|
10
|
+
0x1680,
|
11
|
+
0x180E,
|
12
|
+
0x2000,
|
13
|
+
0x2001,
|
14
|
+
0x2002,
|
15
|
+
0x2003,
|
16
|
+
0x2004,
|
17
|
+
0x2005,
|
18
|
+
0x2006,
|
19
|
+
0x2007,
|
20
|
+
0x2008,
|
21
|
+
0x2009,
|
22
|
+
0x200A,
|
23
|
+
0x200B,
|
24
|
+
0x200C,
|
25
|
+
0x200D,
|
26
|
+
0x202F,
|
27
|
+
0x205F,
|
28
|
+
0x2060,
|
29
|
+
0x2061,
|
30
|
+
0x2062,
|
31
|
+
0x2063,
|
32
|
+
0x2064,
|
33
|
+
0x206A,
|
34
|
+
0x206B,
|
35
|
+
0x206C,
|
36
|
+
0x206D,
|
37
|
+
0x206E,
|
38
|
+
0x206F,
|
39
|
+
0x3000,
|
40
|
+
0x3164,
|
41
|
+
0x2800,
|
42
|
+
0xFEFF,
|
43
|
+
0x1BCA0,
|
44
|
+
0x1BCA1,
|
45
|
+
0x1BCA2,
|
46
|
+
0x1BCA3,
|
47
|
+
0x1D159,
|
48
|
+
0x1D173,
|
49
|
+
0x1D174,
|
50
|
+
0x1D175,
|
51
|
+
0x1D176,
|
52
|
+
0x1D177,
|
53
|
+
0x1D178,
|
54
|
+
0x1D179,
|
55
|
+
0x1D17A,
|
56
|
+
].freeze
|
57
|
+
|
58
|
+
SEPARATORS = [
|
59
|
+
0x000A,
|
60
|
+
0x000B,
|
61
|
+
0x000C,
|
62
|
+
0x000D,
|
63
|
+
0x2028,
|
64
|
+
0x2029,
|
65
|
+
].freeze
|
66
|
+
|
67
|
+
def initialize(char)
|
68
|
+
super
|
69
|
+
|
70
|
+
if @is_valid
|
71
|
+
@category = Unicode::Categories.category(char)
|
72
|
+
@ord = char.ord
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
def unicode?
|
77
|
+
true
|
78
|
+
end
|
79
|
+
|
80
|
+
def assigned?
|
81
|
+
@is_valid && @category != "Cn"
|
82
|
+
end
|
83
|
+
|
84
|
+
def control?
|
85
|
+
@is_valid && @category == "Cc"
|
86
|
+
end
|
87
|
+
|
88
|
+
def c0?
|
89
|
+
@is_valid && @ord < 0x20
|
90
|
+
end
|
91
|
+
|
92
|
+
def delete?
|
93
|
+
@is_valid && @ord == 0x7F
|
94
|
+
end
|
95
|
+
|
96
|
+
def c1?
|
97
|
+
@is_valid && @ord >= 0x80 && @ord < 0xA0
|
98
|
+
end
|
99
|
+
|
100
|
+
def blank?
|
101
|
+
@is_valid && ( BLANKS.include?(@ord) || SEPARATORS.include?(@ord) )
|
102
|
+
end
|
103
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
require_relative "characteristics/version"
|
2
|
+
|
3
|
+
require_relative "characteristics/ascii"
|
4
|
+
require_relative "characteristics/binary"
|
5
|
+
require_relative "characteristics/byte"
|
6
|
+
require_relative "characteristics/unicode"
|
7
|
+
|
8
|
+
class Characteristics
|
9
|
+
def self.type_from_encoding_name(encoding_name)
|
10
|
+
case encoding_name
|
11
|
+
when "US-ASCII"
|
12
|
+
:ascii
|
13
|
+
when "ASCII-8BIT"
|
14
|
+
:binary
|
15
|
+
when /^UTF-/
|
16
|
+
:unicode
|
17
|
+
when /^ISO-8859-/, /^Windows/
|
18
|
+
:byte
|
19
|
+
else
|
20
|
+
raise ArgumentError, "encoding <#{encoding_name}> not supported"
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def self.create_for_type(char, type)
|
25
|
+
case type
|
26
|
+
when :unicode
|
27
|
+
UnicodeCharacteristics.new(char)
|
28
|
+
when :byte
|
29
|
+
ByteCharacteristics.new(char)
|
30
|
+
when :ascii
|
31
|
+
AsciiCharacteristics.new(char)
|
32
|
+
else
|
33
|
+
BinaryCharacteristics.new(char)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
def self.create(char)
|
38
|
+
create_for_type(char, type_from_encoding_name(char.encoding.name))
|
39
|
+
end
|
40
|
+
|
41
|
+
attr_reader :encoding
|
42
|
+
|
43
|
+
def initialize(char)
|
44
|
+
@is_valid = char.valid_encoding?
|
45
|
+
@encoding = char.encoding
|
46
|
+
@encoding_name = @encoding.name
|
47
|
+
end
|
48
|
+
|
49
|
+
def valid?
|
50
|
+
@is_valid
|
51
|
+
end
|
52
|
+
|
53
|
+
def unicode?
|
54
|
+
false
|
55
|
+
end
|
56
|
+
|
57
|
+
def assigned?
|
58
|
+
end
|
59
|
+
|
60
|
+
def control?
|
61
|
+
end
|
62
|
+
|
63
|
+
def blank?
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,181 @@
|
|
1
|
+
require_relative "../lib/characteristics"
|
2
|
+
require "minitest/autorun"
|
3
|
+
|
4
|
+
describe Characteristics do
|
5
|
+
def valid?(char)
|
6
|
+
Characteristics.create(char.force_encoding(encoding)).valid?
|
7
|
+
end
|
8
|
+
|
9
|
+
def assigned?(char)
|
10
|
+
Characteristics.create(char.force_encoding(encoding)).assigned?
|
11
|
+
end
|
12
|
+
|
13
|
+
def control?(char)
|
14
|
+
Characteristics.create(char.force_encoding(encoding)).control?
|
15
|
+
end
|
16
|
+
|
17
|
+
def blank?(char)
|
18
|
+
Characteristics.create(char.force_encoding(encoding)).blank?
|
19
|
+
end
|
20
|
+
|
21
|
+
describe UnicodeCharacteristics do
|
22
|
+
describe "UTF-*" do
|
23
|
+
let(:encoding) { "UTF-8" }
|
24
|
+
|
25
|
+
it "is valid or not" do
|
26
|
+
assert valid? "\x21"
|
27
|
+
refute valid? "\x80"
|
28
|
+
end
|
29
|
+
|
30
|
+
it "is assigned or not" do
|
31
|
+
assert assigned? "\x21"
|
32
|
+
refute assigned? "\uFFEF"
|
33
|
+
end
|
34
|
+
|
35
|
+
it "is control or not" do
|
36
|
+
assert control? "\x1E"
|
37
|
+
assert control? "\x7F"
|
38
|
+
assert control? "\u0080"
|
39
|
+
refute control? "\x67"
|
40
|
+
end
|
41
|
+
|
42
|
+
it "is blank or not" do
|
43
|
+
assert blank? "\x20"
|
44
|
+
refute blank? "\x21"
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
describe BinaryCharacteristics do
|
50
|
+
describe "ASCII-8BIT" do
|
51
|
+
let(:encoding) { "ASCII-8BIT" }
|
52
|
+
|
53
|
+
it "is always valid" do
|
54
|
+
assert valid? "\x80"
|
55
|
+
end
|
56
|
+
|
57
|
+
it "is always assigned" do
|
58
|
+
assert assigned? "\x7F"
|
59
|
+
end
|
60
|
+
|
61
|
+
it "is control or not" do
|
62
|
+
assert control? "\x1E"
|
63
|
+
assert control? "\x7F"
|
64
|
+
refute control? "\x67"
|
65
|
+
end
|
66
|
+
|
67
|
+
it "is blank or not" do
|
68
|
+
assert blank? "\x20"
|
69
|
+
refute blank? "\x21"
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
describe AsciiCharacteristics do
|
75
|
+
describe "US-ASCII" do
|
76
|
+
let(:encoding) { "US-ASCII" }
|
77
|
+
|
78
|
+
it "is valid or not" do
|
79
|
+
assert valid? "\x21"
|
80
|
+
refute valid? "\x80"
|
81
|
+
end
|
82
|
+
|
83
|
+
it "is always assigned" do
|
84
|
+
assert assigned? "\x21"
|
85
|
+
end
|
86
|
+
|
87
|
+
it "is control or not" do
|
88
|
+
assert control? "\x1E"
|
89
|
+
assert control? "\x7F"
|
90
|
+
refute control? "\x67"
|
91
|
+
end
|
92
|
+
|
93
|
+
it "is blank or not" do
|
94
|
+
assert blank? "\x20"
|
95
|
+
refute blank? "\x21"
|
96
|
+
end
|
97
|
+
end
|
98
|
+
end
|
99
|
+
|
100
|
+
describe ByteCharacteristics do
|
101
|
+
describe "ISO-8859-*" do
|
102
|
+
describe "ISO-8859-1" do
|
103
|
+
let(:encoding) { "ISO-8859-1" }
|
104
|
+
|
105
|
+
it "is always valid" do
|
106
|
+
assert valid? "\x80"
|
107
|
+
end
|
108
|
+
|
109
|
+
it "is always assigned" do
|
110
|
+
assert assigned? "\x21"
|
111
|
+
assert assigned? "\x80"
|
112
|
+
end
|
113
|
+
|
114
|
+
it "is control or not" do
|
115
|
+
assert control? "\x1E"
|
116
|
+
assert control? "\x7F"
|
117
|
+
assert control? "\x80"
|
118
|
+
refute control? "\x67"
|
119
|
+
end
|
120
|
+
|
121
|
+
it "is blank or not" do
|
122
|
+
assert blank? "\x20"
|
123
|
+
refute blank? "\x21"
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
# TODO
|
128
|
+
|
129
|
+
# describe "ISO-8859-2" do
|
130
|
+
# describe "ISO-8859-3" do
|
131
|
+
# describe "ISO-8859-4" do
|
132
|
+
# describe "ISO-8859-5" do
|
133
|
+
# describe "ISO-8859-6" do
|
134
|
+
# describe "ISO-8859-7" do
|
135
|
+
# describe "ISO-8859-8" do
|
136
|
+
# describe "ISO-8859-9" do
|
137
|
+
# describe "ISO-8859-10" do
|
138
|
+
# describe "ISO-8859-11" do
|
139
|
+
# describe "ISO-8859-13" do
|
140
|
+
# describe "ISO-8859-14" do
|
141
|
+
# describe "ISO-8859-15" do
|
142
|
+
# describe "ISO-8859-16" do
|
143
|
+
end
|
144
|
+
|
145
|
+
describe "Windows-*" do
|
146
|
+
describe "Windows-1252" do
|
147
|
+
let(:encoding) { "Windows-1252" }
|
148
|
+
|
149
|
+
it "is always valid" do
|
150
|
+
assert valid? "\x80"
|
151
|
+
end
|
152
|
+
|
153
|
+
it "is assigned or not" do
|
154
|
+
assert assigned? "\x21"
|
155
|
+
refute assigned? "\x81"
|
156
|
+
end
|
157
|
+
|
158
|
+
it "is control or not" do
|
159
|
+
assert control? "\x1E"
|
160
|
+
refute control? "\x67"
|
161
|
+
end
|
162
|
+
|
163
|
+
it "is blank or not" do
|
164
|
+
assert blank? "\x20"
|
165
|
+
refute blank? "\x21"
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
# TODO
|
170
|
+
|
171
|
+
# describe "Windows-1250" do
|
172
|
+
# describe "Windows-1251" do
|
173
|
+
# describe "Windows-1253" do
|
174
|
+
# describe "Windows-1254" do
|
175
|
+
# describe "Windows-1255" do
|
176
|
+
# describe "Windows-1256" do
|
177
|
+
# describe "Windows-1257" do
|
178
|
+
# describe "Windows-1258" do
|
179
|
+
end
|
180
|
+
end
|
181
|
+
end
|
metadata
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: characteristics
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jan Lelis
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-03-12 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: unicode-categories
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.1'
|
20
|
+
- - ">="
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: 1.1.2
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - "~>"
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.1'
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 1.1.2
|
33
|
+
description: A Ruby library which provides some basic information about how characters
|
34
|
+
behave in different encodings.
|
35
|
+
email:
|
36
|
+
- mail@janlelis.de
|
37
|
+
executables: []
|
38
|
+
extensions: []
|
39
|
+
extra_rdoc_files: []
|
40
|
+
files:
|
41
|
+
- ".gitignore"
|
42
|
+
- ".travis.yml"
|
43
|
+
- CHANGELOG.md
|
44
|
+
- CODE_OF_CONDUCT.md
|
45
|
+
- Gemfile
|
46
|
+
- MIT-LICENSE.txt
|
47
|
+
- README.md
|
48
|
+
- Rakefile
|
49
|
+
- characteristics.gemspec
|
50
|
+
- lib/characteristics.rb
|
51
|
+
- lib/characteristics/ascii.rb
|
52
|
+
- lib/characteristics/binary.rb
|
53
|
+
- lib/characteristics/byte.rb
|
54
|
+
- lib/characteristics/unicode.rb
|
55
|
+
- lib/characteristics/version.rb
|
56
|
+
- spec/characteristics_spec.rb
|
57
|
+
homepage: https://github.com/janlelis/characteristics
|
58
|
+
licenses:
|
59
|
+
- MIT
|
60
|
+
metadata: {}
|
61
|
+
post_install_message:
|
62
|
+
rdoc_options: []
|
63
|
+
require_paths:
|
64
|
+
- lib
|
65
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - "~>"
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '2.0'
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
requirements: []
|
76
|
+
rubyforge_project:
|
77
|
+
rubygems_version: 2.6.8
|
78
|
+
signing_key:
|
79
|
+
specification_version: 4
|
80
|
+
summary: Basic character properties.
|
81
|
+
test_files:
|
82
|
+
- spec/characteristics_spec.rb
|