fileinfo 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/Gemfile +2 -0
- data/LICENSE.txt +22 -0
- data/README.md +47 -0
- data/Rakefile +1 -0
- data/fileinfo.gemspec +24 -0
- data/lib/file_info.rb +43 -0
- data/lib/file_info/version.rb +3 -0
- data/lib/fileinfo.rb +1 -0
- data/spec/file_info_spec.rb +50 -0
- data/spec/fixtures/encoding_ascii.csv +2 -0
- data/spec/fixtures/encoding_isolatin.csv +2 -0
- data/spec/fixtures/encoding_isowindows.csv +2 -0
- data/spec/fixtures/encoding_utf8.csv +2 -0
- data/spec/spec_helper.rb +13 -0
- metadata +110 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: d118d43747ad299895b1f1d8cdf958617a98ebf6
|
4
|
+
data.tar.gz: 1bc3e0c4c74d6e308f7ca0aa8914407fade41039
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 8555f22f4c06c74e2e90aef4150b9637bd03030adc0ccc4e7e114f499ff801844574f59fd5d3cbe9eed8a83f7cc54a62ee1831aa1d6487f298c123054e47e779
|
7
|
+
data.tar.gz: 9a19e2014c9545ec433570177aa443b5312ad6c012128168603414913f1dd58be5392dca55b60d8b6a6e6badb2ce90a5678cec0b0531f86f6ca8d031106ab1f8
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Rafaël Blais Masson
|
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
@@ -0,0 +1,47 @@
|
|
1
|
+
# FileInfo
|
2
|
+
|
3
|
+
FileInfo extracts encoding from strings and files using the [wonderful Unix `file` command](http://en.wikipedia.org/wiki/File_\(command\)).
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'fileinfo'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
```sh
|
16
|
+
$ bundle
|
17
|
+
```
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
```sh
|
22
|
+
$ gem install fileinfo
|
23
|
+
```
|
24
|
+
|
25
|
+
## Usage
|
26
|
+
|
27
|
+
Use `FileInfo.parse` with a string:
|
28
|
+
|
29
|
+
```ruby
|
30
|
+
FileInfo.parse('foo bar baz').encoding # => #<Encoding:US-ASCII>
|
31
|
+
FileInfo.parse('föø bår bàz').encoding # => #<Encoding:UTF-8>
|
32
|
+
```
|
33
|
+
|
34
|
+
Use `FileInfo.load` with a filename:
|
35
|
+
|
36
|
+
```ruby
|
37
|
+
filename = '/Users/rafbm/Downloads/some_crap_coming_from_windows.csv'
|
38
|
+
FileInfo.load(filename).encoding # => #<Encoding:ISO-8859-1>
|
39
|
+
```
|
40
|
+
|
41
|
+
## Contributing
|
42
|
+
|
43
|
+
1. Fork it
|
44
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
45
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
46
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
47
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'bundler/gem_tasks'
|
data/fileinfo.gemspec
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'file_info/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'fileinfo'
|
8
|
+
spec.version = FileInfo::VERSION
|
9
|
+
spec.authors = ['Rafaël Blais Masson']
|
10
|
+
spec.email = ['rafael@heliom.ca']
|
11
|
+
spec.description = "FileInfo extracts encoding from strings and files using the wonderful Unix `file` command."
|
12
|
+
spec.summary = "FileInfo extracts encoding from strings and files using the wonderful Unix `file` command."
|
13
|
+
spec.homepage = 'http://github.com/rafBM/fileinfo'
|
14
|
+
spec.license = 'MIT'
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ['lib']
|
20
|
+
|
21
|
+
spec.add_development_dependency 'bundler', '~> 1.3'
|
22
|
+
spec.add_development_dependency 'rake'
|
23
|
+
spec.add_development_dependency 'rspec', '~> 2.14'
|
24
|
+
end
|
data/lib/file_info.rb
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
require 'file_info/version'
|
2
|
+
|
3
|
+
require 'shellwords'
|
4
|
+
require 'tempfile'
|
5
|
+
|
6
|
+
class FileInfo
|
7
|
+
STRING_REGEX = /: ([^:]+)$/
|
8
|
+
ENCODING_REGEX = /charset=(\S+)/
|
9
|
+
|
10
|
+
def initialize(output)
|
11
|
+
@output = output
|
12
|
+
end
|
13
|
+
|
14
|
+
def encoding
|
15
|
+
@encoding ||= ::Encoding.find(encoding_string)
|
16
|
+
end
|
17
|
+
|
18
|
+
def self.load(filename)
|
19
|
+
raise ArgumentError, "File '#{filename}' does not exist." if !File.exists? filename
|
20
|
+
new `file --mime #{Shellwords.escape(filename)}`
|
21
|
+
end
|
22
|
+
|
23
|
+
def self.parse(content)
|
24
|
+
file = Tempfile.new(rand.to_s)
|
25
|
+
file.write(content)
|
26
|
+
file.rewind
|
27
|
+
output = `file --mime #{file.path}`
|
28
|
+
file.close
|
29
|
+
file.unlink
|
30
|
+
|
31
|
+
new output
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
def string
|
37
|
+
@string ||= @output.match(STRING_REGEX)[1].strip
|
38
|
+
end
|
39
|
+
|
40
|
+
def encoding_string
|
41
|
+
@encoding_string ||= string.match(ENCODING_REGEX)[1]
|
42
|
+
end
|
43
|
+
end
|
data/lib/fileinfo.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'file_info'
|
@@ -0,0 +1,50 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe FileInfo do
|
4
|
+
let(:ascii_file) { fixture('encoding_ascii.csv') }
|
5
|
+
let(:isolatin_file) { fixture('encoding_isolatin.csv') }
|
6
|
+
let(:isowindows_file) { fixture('encoding_isowindows.csv') }
|
7
|
+
let(:utf8_file) { fixture('encoding_utf8.csv') }
|
8
|
+
|
9
|
+
describe '.load' do
|
10
|
+
it 'extracts encoding from filename' do
|
11
|
+
expect(FileInfo.load(ascii_file.path).encoding).to eq Encoding::US_ASCII
|
12
|
+
expect(FileInfo.load(isolatin_file.path).encoding).to eq Encoding::ISO_8859_1
|
13
|
+
expect(FileInfo.load(isowindows_file.path).encoding).to eq Encoding::ISO_8859_1
|
14
|
+
expect(FileInfo.load(utf8_file.path).encoding).to eq Encoding::UTF_8
|
15
|
+
end
|
16
|
+
|
17
|
+
it 'extracts encoding from filename with space' do
|
18
|
+
old_filename = fixture('encoding_utf8.csv').path
|
19
|
+
new_filename = old_filename.sub('_', ' ')
|
20
|
+
FileUtils.cp(old_filename, new_filename)
|
21
|
+
|
22
|
+
expect(FileInfo.load(new_filename).encoding).to eq Encoding::UTF_8
|
23
|
+
|
24
|
+
FileUtils.rm(new_filename)
|
25
|
+
end
|
26
|
+
|
27
|
+
it 'extracts encoding from filename with space and quote' do
|
28
|
+
old_filename = fixture('encoding_utf8.csv').path
|
29
|
+
new_filename = old_filename.sub('_', ' " ')
|
30
|
+
FileUtils.cp(old_filename, new_filename)
|
31
|
+
|
32
|
+
expect(FileInfo.load(new_filename).encoding).to eq Encoding::UTF_8
|
33
|
+
|
34
|
+
FileUtils.rm(new_filename)
|
35
|
+
end
|
36
|
+
|
37
|
+
it 'raises ArgumentError if file does not exist' do
|
38
|
+
expect { FileInfo.load('WRONG!!1') }.to raise_error ArgumentError
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
describe '.parse' do
|
43
|
+
it 'extracts encoding from string' do
|
44
|
+
expect(FileInfo.parse(ascii_file.read).encoding).to eq Encoding::US_ASCII
|
45
|
+
expect(FileInfo.parse(isolatin_file.read).encoding).to eq Encoding::ISO_8859_1
|
46
|
+
expect(FileInfo.parse(isowindows_file.read).encoding).to eq Encoding::ISO_8859_1
|
47
|
+
expect(FileInfo.parse(utf8_file.read).encoding).to eq Encoding::UTF_8
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,110 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: fileinfo
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Rafaël Blais Masson
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-09-08 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.14'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.14'
|
55
|
+
description: FileInfo extracts encoding from strings and files using the wonderful
|
56
|
+
Unix `file` command.
|
57
|
+
email:
|
58
|
+
- rafael@heliom.ca
|
59
|
+
executables: []
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- .gitignore
|
64
|
+
- .rspec
|
65
|
+
- Gemfile
|
66
|
+
- LICENSE.txt
|
67
|
+
- README.md
|
68
|
+
- Rakefile
|
69
|
+
- fileinfo.gemspec
|
70
|
+
- lib/file_info.rb
|
71
|
+
- lib/file_info/version.rb
|
72
|
+
- lib/fileinfo.rb
|
73
|
+
- spec/file_info_spec.rb
|
74
|
+
- spec/fixtures/encoding_ascii.csv
|
75
|
+
- spec/fixtures/encoding_isolatin.csv
|
76
|
+
- spec/fixtures/encoding_isowindows.csv
|
77
|
+
- spec/fixtures/encoding_utf8.csv
|
78
|
+
- spec/spec_helper.rb
|
79
|
+
homepage: http://github.com/rafBM/fileinfo
|
80
|
+
licenses:
|
81
|
+
- MIT
|
82
|
+
metadata: {}
|
83
|
+
post_install_message:
|
84
|
+
rdoc_options: []
|
85
|
+
require_paths:
|
86
|
+
- lib
|
87
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - '>='
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '0'
|
92
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
requirements: []
|
98
|
+
rubyforge_project:
|
99
|
+
rubygems_version: 2.0.3
|
100
|
+
signing_key:
|
101
|
+
specification_version: 4
|
102
|
+
summary: FileInfo extracts encoding from strings and files using the wonderful Unix
|
103
|
+
`file` command.
|
104
|
+
test_files:
|
105
|
+
- spec/file_info_spec.rb
|
106
|
+
- spec/fixtures/encoding_ascii.csv
|
107
|
+
- spec/fixtures/encoding_isolatin.csv
|
108
|
+
- spec/fixtures/encoding_isowindows.csv
|
109
|
+
- spec/fixtures/encoding_utf8.csv
|
110
|
+
- spec/spec_helper.rb
|