unibits 1.0.0
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.
- 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 +7 -0
- data/MIT-LICENSE.txt +20 -0
- data/README.md +108 -0
- data/Rakefile +38 -0
- data/bin/unibits +58 -0
- data/lib/unibits.rb +174 -0
- data/lib/unibits/kernel_method.rb +9 -0
- data/lib/unibits/version.rb +3 -0
- data/screenshots/ascii.png +0 -0
- data/screenshots/binary.png +0 -0
- data/screenshots/utf-16be.png +0 -0
- data/screenshots/utf-16le.png +0 -0
- data/screenshots/utf-32be.png +0 -0
- data/screenshots/utf-32le.png +0 -0
- data/screenshots/utf-8.png +0 -0
- data/spec/unibits_spec.rb +70 -0
- data/unibits.gemspec +25 -0
- metadata +112 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 0405b9099735bcf25bc05f82e91d9c5629071ee1
|
4
|
+
data.tar.gz: 85d9bde5ddc1e90ac70cf288e7753ddc8511fc87
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a8d944dfcf50869cf1a64a7237e8145ee8b8fcb57a801db9a475684ac0e7bd4865be2b2d372f943ddeebb6d86f632a3eb9655d147cc6e3b79bc6e0c6dc09fa66
|
7
|
+
data.tar.gz: be6685c1bfc9b9ecf073e9899be4ded5d590ccdd90b527dfdfdfeb1ac654016cac4116033905183f988e249cabedcc767cc8fa3a4d04b3681650ad7852035330
|
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 +1,108 @@
|
|
1
|
+
# unibits [![[version]](https://badge.fury.io/rb/unibits.svg)](http://badge.fury.io/rb/unibits) [![[travis]](https://travis-ci.org/janlelis/unibits.svg)](https://travis-ci.org/janlelis/unibits)
|
2
|
+
|
3
|
+
Ruby library and CLI command that visualizes various Unicode and ASCII encodings in the terminal.
|
4
|
+
|
5
|
+
Helps you debugging and learning about Unicode encodings.
|
6
|
+
|
7
|
+
Supported encodings: **UTF-8**, **UTF-16LE**, **UTF-16BE**, **UTF-32LE**, **UTF-32BE**, **BINARY**, **ASCII**
|
8
|
+
|
9
|
+
## Setup
|
10
|
+
|
11
|
+
```
|
12
|
+
$ gem install unibits
|
13
|
+
```
|
14
|
+
|
15
|
+
## Usage
|
16
|
+
### From CLI
|
17
|
+
|
18
|
+
```
|
19
|
+
$ unibits "🌫 Idiosyncrätic ℜսᖯʏ"
|
20
|
+
```
|
21
|
+
|
22
|
+
### From Ruby
|
23
|
+
|
24
|
+
```ruby
|
25
|
+
require 'unibits/kernel_method'
|
26
|
+
unibits "🌫 Idiosyncrätic ℜսᖯʏ"
|
27
|
+
```
|
28
|
+
|
29
|
+
### Options
|
30
|
+
|
31
|
+
`unibits` takes three optional options:
|
32
|
+
|
33
|
+
- *encoding (e)*: The encoding of the given string (uses your default encoding if none given)
|
34
|
+
- *convert (c)*: An encoding the string should be converted to before visualizing it
|
35
|
+
- *stats*: Whether to show a short stats header (default: `true`), you can deactivate on the CLI with `--no-stats`
|
36
|
+
|
37
|
+
**Please note**: This uses Ruby's built-in encoding support. Currently, only strings with valid encodings are supported.
|
38
|
+
|
39
|
+
## Output for Different Encodings
|
40
|
+
### UTF-8
|
41
|
+
|
42
|
+
CLI: `$ unibits -e utf-8 -c utf-8 "🌫 Idiosyncrätic ℜսᖯʏ"`
|
43
|
+
|
44
|
+
Ruby: `unibits "🌫 Idiosyncrätic ℜսᖯʏ", encoding: 'utf-8', convert: 'utf-8'`
|
45
|
+
|
46
|
+

|
47
|
+
|
48
|
+
### UTF-16LE
|
49
|
+
|
50
|
+
CLI: `$ unibits -e utf-8 -c utf-8 "🌫 Idiosyncrätic ℜսᖯʏ"`
|
51
|
+
|
52
|
+
Ruby: `unibits "🌫 Idiosyncrätic ℜսᖯʏ", encoding: 'utf-8', convert: 'utf-8'`
|
53
|
+
|
54
|
+

|
55
|
+
|
56
|
+
### UTF-16BE
|
57
|
+
|
58
|
+
CLI: `$ unibits -e utf-8 -c utf-8 "🌫 Idiosyncrätic ℜսᖯʏ"`
|
59
|
+
|
60
|
+
Ruby: `unibits "🌫 Idiosyncrätic ℜսᖯʏ", encoding: 'utf-8', convert: 'utf-8'`
|
61
|
+
|
62
|
+

|
63
|
+
|
64
|
+
### UTF-32LE
|
65
|
+
|
66
|
+
CLI: `$ unibits -e utf-8 -c utf-8 "🌫 Idiosyncrätic ℜսᖯʏ"`
|
67
|
+
|
68
|
+
Ruby: `unibits "🌫 Idiosyncrätic ℜսᖯʏ", encoding: 'utf-8', convert: 'utf-8'`
|
69
|
+
|
70
|
+

|
71
|
+
|
72
|
+
### UTF-32BE
|
73
|
+
|
74
|
+
CLI: `$ unibits -e utf-8 -c utf-8 "🌫 Idiosyncrätic ℜսᖯʏ"`
|
75
|
+
|
76
|
+
Ruby: `unibits "🌫 Idiosyncrätic ℜսᖯʏ", encoding: 'utf-8', convert: 'utf-8'`
|
77
|
+
|
78
|
+

|
79
|
+
|
80
|
+
### BINARY
|
81
|
+
|
82
|
+
CLI: `$ unibits -e binary "🌫 Idiosyncrätic ℜսᖯʏ"`
|
83
|
+
|
84
|
+
Ruby: `unibits "🌫 Idiosyncrätic ℜսᖯʏ", encoding: 'binary'`
|
85
|
+
|
86
|
+

|
87
|
+
|
88
|
+
### ASCII
|
89
|
+
|
90
|
+
CLI: `$ unibits -e utf-8 -c ascii "ascii"`
|
91
|
+
|
92
|
+
Ruby: `unibits "ASCII String", encoding: 'utf-8', convert: 'ascii'`
|
93
|
+
|
94
|
+

|
95
|
+
|
96
|
+
## Notes
|
97
|
+
|
98
|
+
Also see
|
99
|
+
|
100
|
+
- [UTF-8 (Wikipedia)](https://en.wikipedia.org/wiki/UTF-8#Description)
|
101
|
+
- [UTF-16 (Wikipedia)](https://en.wikipedia.org/wiki/UTF-16#Description)
|
102
|
+
- [UTF-32 (Wikipedia)](https://en.wikipedia.org/wiki/UTF-32)
|
103
|
+
- [Ruby's Encoding class](https://ruby-doc.org/core/Encoding.html)
|
104
|
+
- [Unicode Micro Libraries for Ruby](https://github.com/janlelis/unicode-x)
|
105
|
+
|
106
|
+
Lots of thanks to @damienklinnert for the motivation and inspiration required to build this! 🎆
|
107
|
+
|
108
|
+
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 $file; done"
|
36
|
+
end
|
37
|
+
task default: :spec
|
38
|
+
|
data/bin/unibits
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "rationalist"
|
4
|
+
require "unibits"
|
5
|
+
|
6
|
+
argv = Rationalist.parse(
|
7
|
+
ARGV,
|
8
|
+
string: '_',
|
9
|
+
alias: {
|
10
|
+
e: 'encoding',
|
11
|
+
c: 'convert',
|
12
|
+
v: 'version',
|
13
|
+
},
|
14
|
+
boolean: [
|
15
|
+
'help',
|
16
|
+
'version',
|
17
|
+
'stats'
|
18
|
+
],
|
19
|
+
default: {
|
20
|
+
stats: true
|
21
|
+
},
|
22
|
+
)
|
23
|
+
|
24
|
+
if argv[:version]
|
25
|
+
puts Unibits::VERSION
|
26
|
+
exit(0)
|
27
|
+
end
|
28
|
+
|
29
|
+
if argv[:help]
|
30
|
+
puts <<-HELP
|
31
|
+
|
32
|
+
#{Paint["USAGE", :underline]}
|
33
|
+
|
34
|
+
#{Paint["unibits", :bold]} [--encoding <encoding>] [--convert <encoding>] [--no-stats] data
|
35
|
+
|
36
|
+
Supported encodings: #{Unibits::SUPPORTED_ENCODINGS.join(', ')}
|
37
|
+
Explanation of stats: bytes / codepoints / glyphs / expected terminal width
|
38
|
+
|
39
|
+
More info and examples at: https://github.com/janlelis/unibits
|
40
|
+
|
41
|
+
HELP
|
42
|
+
exit(0)
|
43
|
+
end
|
44
|
+
|
45
|
+
if argv[:_] && argv[:_][0]
|
46
|
+
data = argv[:_][0]
|
47
|
+
elsif !$stdin.tty?
|
48
|
+
data = $stdin.read
|
49
|
+
else
|
50
|
+
data = nil
|
51
|
+
end
|
52
|
+
|
53
|
+
begin
|
54
|
+
Unibits.of(data, encoding: argv[:encoding], convert: argv[:convert], stats: argv[:stats])
|
55
|
+
rescue ArgumentError
|
56
|
+
$stderr.puts Paint[$!.message, :red]
|
57
|
+
exit(1)
|
58
|
+
end
|
data/lib/unibits.rb
ADDED
@@ -0,0 +1,174 @@
|
|
1
|
+
require_relative "unibits/version"
|
2
|
+
|
3
|
+
require "io/console"
|
4
|
+
require "paint"
|
5
|
+
require "unicode/display_width"
|
6
|
+
|
7
|
+
module Unibits
|
8
|
+
SUPPORTED_ENCODINGS = [
|
9
|
+
'UTF-8',
|
10
|
+
'UTF-16LE',
|
11
|
+
'UTF-16BE',
|
12
|
+
'UTF-32LE',
|
13
|
+
'UTF-32BE',
|
14
|
+
'ASCII-8BIT',
|
15
|
+
'US-ASCII',
|
16
|
+
].freeze
|
17
|
+
|
18
|
+
def self.of(string, encoding: nil, convert: nil, stats: true)
|
19
|
+
if !string || string.empty?
|
20
|
+
raise ArgumentError, "no data given to unibits"
|
21
|
+
end
|
22
|
+
|
23
|
+
string = string.dup.force_encoding(encoding) if encoding
|
24
|
+
string = string.encode(convert) if convert
|
25
|
+
|
26
|
+
case string.encoding.name
|
27
|
+
when *SUPPORTED_ENCODINGS
|
28
|
+
unless string.valid_encoding?
|
29
|
+
raise ArgumentError, "the data given is not valid #{string.encoding.name}"
|
30
|
+
end
|
31
|
+
|
32
|
+
puts stats(string) if stats
|
33
|
+
puts visualize(string)
|
34
|
+
when 'UTF-16', 'UTF-32'
|
35
|
+
raise ArgumentError, "unibits only supports #{string.encoding.name} with specified endianess, please use #{string.encoding.name}LE or #{string.encoding.name}BE"
|
36
|
+
else
|
37
|
+
raise ArgumentError, "unibits does not support strings of encoding #{string.encoding}"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
def self.stats(string)
|
42
|
+
"\n " \
|
43
|
+
"#{Paint[string.encoding.name, :bold]} (" \
|
44
|
+
"#{string.bytesize}/" \
|
45
|
+
"#{string.size}/" \
|
46
|
+
"#{string.scan(Regexp.compile('\X'.encode(string.encoding))).size}/" \
|
47
|
+
"#{Unicode::DisplayWidth.of(string)})"
|
48
|
+
end
|
49
|
+
|
50
|
+
def self.visualize(string)
|
51
|
+
cols = determine_terminal_cols
|
52
|
+
|
53
|
+
cp_buffer = [" "]
|
54
|
+
enc_buffer = [" "]
|
55
|
+
hex_buffer = [" "]
|
56
|
+
bin_buffer = [" "]
|
57
|
+
separator = [" "]
|
58
|
+
|
59
|
+
puts
|
60
|
+
string.each_char{ |char|
|
61
|
+
current_color = random_color
|
62
|
+
|
63
|
+
char.each_byte.with_index{ |byte, index|
|
64
|
+
if Paint.unpaint(hex_buffer[-1]).bytesize > cols - 12
|
65
|
+
cp_buffer << " "
|
66
|
+
enc_buffer << " "
|
67
|
+
hex_buffer << " "
|
68
|
+
bin_buffer << " "
|
69
|
+
separator << " "
|
70
|
+
end
|
71
|
+
|
72
|
+
if index == 0
|
73
|
+
cp_buffer[-1] << Paint[
|
74
|
+
("U+%04X" % char.ord).ljust(10), current_color, :bold
|
75
|
+
]
|
76
|
+
|
77
|
+
symbolified_char = symbolify(char)
|
78
|
+
padding = 10 - Unicode::DisplayWidth.of(symbolified_char)
|
79
|
+
|
80
|
+
enc_buffer[-1] << Paint[
|
81
|
+
symbolified_char, current_color
|
82
|
+
]
|
83
|
+
enc_buffer[-1] << " " * padding if padding > 0
|
84
|
+
else
|
85
|
+
cp_buffer[-1] << " " * 10
|
86
|
+
enc_buffer[-1] << " " * 10
|
87
|
+
end
|
88
|
+
|
89
|
+
hex_buffer[-1] << Paint[
|
90
|
+
("%02X" % byte).ljust(10, " "), current_color
|
91
|
+
]
|
92
|
+
|
93
|
+
bin_byte_complete = byte.to_s(2).rjust(8, "0")
|
94
|
+
|
95
|
+
case string.encoding.name
|
96
|
+
when 'US-ASCII'
|
97
|
+
bin_byte_1 = bin_byte_complete[0...1]
|
98
|
+
bin_byte_2 = bin_byte_complete[1...8]
|
99
|
+
when 'ASCII-8BIT'
|
100
|
+
bin_byte_1 = ""
|
101
|
+
bin_byte_2 = bin_byte_complete
|
102
|
+
when 'UTF-8'
|
103
|
+
if index == 0
|
104
|
+
if bin_byte_complete =~ /^(0|1{2,4}0)([01]+)$/
|
105
|
+
bin_byte_1 = $1
|
106
|
+
bin_byte_2 = $2
|
107
|
+
else
|
108
|
+
bin_byte_1 = ""
|
109
|
+
bin_byte_2 = bin_byte_complete
|
110
|
+
end
|
111
|
+
else
|
112
|
+
bin_byte_1 = bin_byte_complete[0...2]
|
113
|
+
bin_byte_2 = bin_byte_complete[2...8]
|
114
|
+
end
|
115
|
+
when 'UTF-16LE'
|
116
|
+
if char.ord <= 0xFFFF || index == 0 || index == 2
|
117
|
+
bin_byte_1 = ""
|
118
|
+
bin_byte_2 = bin_byte_complete
|
119
|
+
else
|
120
|
+
bin_byte_complete =~ /^(11011[01])([01]+)$/
|
121
|
+
bin_byte_1 = $1
|
122
|
+
bin_byte_2 = $2
|
123
|
+
end
|
124
|
+
when 'UTF-16BE'
|
125
|
+
if char.ord <= 0xFFFF || index == 1 || index == 3
|
126
|
+
bin_byte_1 = ""
|
127
|
+
bin_byte_2 = bin_byte_complete
|
128
|
+
else
|
129
|
+
bin_byte_complete =~ /^(11011[01])([01]+)$/
|
130
|
+
bin_byte_1 = $1
|
131
|
+
bin_byte_2 = $2
|
132
|
+
end
|
133
|
+
when 'UTF-32LE', 'UTF-32BE'
|
134
|
+
bin_byte_1 = ""
|
135
|
+
bin_byte_2 = bin_byte_complete
|
136
|
+
end
|
137
|
+
bin_buffer[-1] << Paint[
|
138
|
+
bin_byte_1, current_color
|
139
|
+
] unless !bin_byte_1 || bin_byte_1.empty?
|
140
|
+
bin_buffer[-1] << Paint[
|
141
|
+
bin_byte_2, current_color, :underline
|
142
|
+
] unless !bin_byte_2 || bin_byte_2.empty?
|
143
|
+
bin_buffer[-1] << " "
|
144
|
+
}
|
145
|
+
}
|
146
|
+
|
147
|
+
if string.encoding.name[0, 3] == "UTF"
|
148
|
+
enc_buffer.zip(cp_buffer, hex_buffer, bin_buffer, separator).flatten.join("\n")
|
149
|
+
else
|
150
|
+
enc_buffer.zip(hex_buffer, bin_buffer, separator).flatten.join("\n")
|
151
|
+
end
|
152
|
+
end
|
153
|
+
|
154
|
+
def self.random_color
|
155
|
+
"%.2x%.2x%.2x" %[rand(90) + 60, rand(90) + 60, rand(90) + 60]
|
156
|
+
end
|
157
|
+
|
158
|
+
def self.symbolify(char)
|
159
|
+
return char.inspect unless char.encoding.name[0, 3] == "UTF"
|
160
|
+
char
|
161
|
+
.tr("\x00-\x1F".encode(char.encoding), "\u{2400}-\u{241F}".encode(char.encoding))
|
162
|
+
.gsub(
|
163
|
+
Regexp.compile('[\p{Space}]'.encode(char.encoding)),
|
164
|
+
']\0['.encode(char.encoding)
|
165
|
+
)
|
166
|
+
.encode('UTF-8')
|
167
|
+
end
|
168
|
+
|
169
|
+
def self.determine_terminal_cols
|
170
|
+
STDIN.winsize[1] || 80
|
171
|
+
rescue Errno::ENOTTY
|
172
|
+
return 80
|
173
|
+
end
|
174
|
+
end
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
@@ -0,0 +1,70 @@
|
|
1
|
+
require_relative "../lib/unibits/kernel_method"
|
2
|
+
require "minitest/autorun"
|
3
|
+
|
4
|
+
describe Unibits do
|
5
|
+
it "will not work for unsupported encodings" do
|
6
|
+
proc{
|
7
|
+
Unibits.of("string".encode("UTF-32"))
|
8
|
+
}.must_raise ArgumentError
|
9
|
+
end
|
10
|
+
|
11
|
+
describe 'Encodings' do
|
12
|
+
let(:string){ "🌫 Idiosyncrätic ℜսᖯʏ" }
|
13
|
+
|
14
|
+
it "works with UTF-8" do
|
15
|
+
result = Paint.unpaint(Unibits.visualize(string))
|
16
|
+
result.must_match "ℜ"
|
17
|
+
result.must_match "U+211C"
|
18
|
+
result.must_match /E2.*84.*9C/m
|
19
|
+
result.must_match /11100010.*10000100.*10011100/m
|
20
|
+
end
|
21
|
+
|
22
|
+
it "works with UTF-16LE" do
|
23
|
+
result = Paint.unpaint(Unibits.visualize(string.encode('UTF-16LE')))
|
24
|
+
result.must_match "ℜ"
|
25
|
+
result.must_match "U+211C"
|
26
|
+
result.must_match /1C.*21/m
|
27
|
+
result.must_match /00011100.*00100001/m
|
28
|
+
end
|
29
|
+
|
30
|
+
it "works with UTF-16BE" do
|
31
|
+
result = Paint.unpaint(Unibits.visualize(string.encode('UTF-16BE')))
|
32
|
+
result.must_match "ℜ"
|
33
|
+
result.must_match "U+211C"
|
34
|
+
result.must_match /21.*1C/m
|
35
|
+
result.must_match /00100001.*00011100/m
|
36
|
+
end
|
37
|
+
|
38
|
+
it "works with UTF-32LE" do
|
39
|
+
result = Paint.unpaint(Unibits.visualize(string.encode('UTF-32LE')))
|
40
|
+
result.must_match "ℜ"
|
41
|
+
result.must_match "U+211C"
|
42
|
+
result.must_match /1C.*21.*00.*00/m
|
43
|
+
result.must_match /00011100.*00100001.*00000000.*00000000/m
|
44
|
+
end
|
45
|
+
|
46
|
+
it "works with UTF-32BE" do
|
47
|
+
result = Paint.unpaint(Unibits.visualize(string.encode('UTF-32BE')))
|
48
|
+
result.must_match "ℜ"
|
49
|
+
result.must_match "U+211C"
|
50
|
+
result.must_match /00.*00.*21.*1C/m
|
51
|
+
result.must_match /00000000.*00000000.*00100001.*00011100/m
|
52
|
+
end
|
53
|
+
|
54
|
+
it "works with BINARY" do
|
55
|
+
result = Paint.unpaint(Unibits.visualize(string.dup.force_encoding('BINARY')))
|
56
|
+
# testing for the UTF-8 encoded "ℜ"
|
57
|
+
result.must_match "\\xE2"
|
58
|
+
result.must_match "\\x84"
|
59
|
+
result.must_match "\\x9C"
|
60
|
+
result.must_match /11100010.*10000100.*10011100/m
|
61
|
+
end
|
62
|
+
|
63
|
+
it "works with ASCII" do
|
64
|
+
result = Paint.unpaint(Unibits.visualize("ASCII string".force_encoding('ASCII')))
|
65
|
+
result.must_match "C"
|
66
|
+
result.must_match "43"
|
67
|
+
result.must_match "01000011"
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
data/unibits.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
|
3
|
+
require File.dirname(__FILE__) + "/lib/unibits/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |gem|
|
6
|
+
gem.name = "unibits"
|
7
|
+
gem.version = Unibits::VERSION
|
8
|
+
gem.summary = "Visualizes Unicode encodings."
|
9
|
+
gem.description = "Visualizes Unicode encodings in the terminal. Supports UTF-8, UTF-16LE, UTF-16BE, UTF-32LE, UTF-32BE, US-ASCII, and ASCII-8BIT. Comes as CLI command and as Ruby Kernel method."
|
10
|
+
gem.authors = ["Jan Lelis"]
|
11
|
+
gem.email = ["mail@janlelis.de"]
|
12
|
+
gem.homepage = "https://github.com/janlelis/unibits"
|
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.add_dependency 'paint', '~> 2.0'
|
21
|
+
gem.add_dependency 'unicode-display_width', '~> 1.1'
|
22
|
+
gem.add_dependency 'rationalist', '~> 2.0'
|
23
|
+
|
24
|
+
gem.required_ruby_version = "~> 2.0"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,112 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: unibits
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jan Lelis
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-03-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: paint
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '2.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '2.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: unicode-display_width
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.1'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.1'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rationalist
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.0'
|
55
|
+
description: Visualizes Unicode encodings in the terminal. Supports UTF-8, UTF-16LE,
|
56
|
+
UTF-16BE, UTF-32LE, UTF-32BE, US-ASCII, and ASCII-8BIT. Comes as CLI command and
|
57
|
+
as Ruby Kernel method.
|
58
|
+
email:
|
59
|
+
- mail@janlelis.de
|
60
|
+
executables:
|
61
|
+
- unibits
|
62
|
+
extensions: []
|
63
|
+
extra_rdoc_files: []
|
64
|
+
files:
|
65
|
+
- ".gitignore"
|
66
|
+
- ".travis.yml"
|
67
|
+
- CHANGELOG.md
|
68
|
+
- CODE_OF_CONDUCT.md
|
69
|
+
- Gemfile
|
70
|
+
- Gemfile.lock
|
71
|
+
- MIT-LICENSE.txt
|
72
|
+
- README.md
|
73
|
+
- Rakefile
|
74
|
+
- bin/unibits
|
75
|
+
- lib/unibits.rb
|
76
|
+
- lib/unibits/kernel_method.rb
|
77
|
+
- lib/unibits/version.rb
|
78
|
+
- screenshots/ascii.png
|
79
|
+
- screenshots/binary.png
|
80
|
+
- screenshots/utf-16be.png
|
81
|
+
- screenshots/utf-16le.png
|
82
|
+
- screenshots/utf-32be.png
|
83
|
+
- screenshots/utf-32le.png
|
84
|
+
- screenshots/utf-8.png
|
85
|
+
- spec/unibits_spec.rb
|
86
|
+
- unibits.gemspec
|
87
|
+
homepage: https://github.com/janlelis/unibits
|
88
|
+
licenses:
|
89
|
+
- MIT
|
90
|
+
metadata: {}
|
91
|
+
post_install_message:
|
92
|
+
rdoc_options: []
|
93
|
+
require_paths:
|
94
|
+
- lib
|
95
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
96
|
+
requirements:
|
97
|
+
- - "~>"
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: '2.0'
|
100
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
101
|
+
requirements:
|
102
|
+
- - ">="
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: '0'
|
105
|
+
requirements: []
|
106
|
+
rubyforge_project:
|
107
|
+
rubygems_version: 2.6.8
|
108
|
+
signing_key:
|
109
|
+
specification_version: 4
|
110
|
+
summary: Visualizes Unicode encodings.
|
111
|
+
test_files:
|
112
|
+
- spec/unibits_spec.rb
|