fileinfo 0.2.0 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +31 -6
- data/fileinfo.gemspec +3 -2
- data/lib/file_info.rb +36 -18
- data/lib/file_info/version.rb +1 -1
- data/spec/file_info_spec.rb +89 -8
- data/spec/fixtures/bytes +1 -0
- data/spec/fixtures/mockup.psd +0 -0
- metadata +36 -18
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1fd22a80c28289631c040bde751eee82a7b51369
|
4
|
+
data.tar.gz: 38320adc6dc77ad1e6e38e6d4d1b4c49052da480
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 24f820540d61e3e613b3c511eb3d5e8cebc7663de1c8828d6b4456a7215835ec7c18e1574411315e8961c0a7b1de2c63f7eddf1654b675a45139a0cf0ac8b59c
|
7
|
+
data.tar.gz: 2823c8c4c042db5d8b8aecbfffd38b3c552c7c2b20f1300bbddd4aacf5b08ff8139127339fd20d19043d795e1152dc6c3a88f32195aa86ec8f9d2eaf2f466e54
|
data/README.md
CHANGED
@@ -6,7 +6,7 @@
|
|
6
6
|
[![Coverage Status](https://coveralls.io/repos/rafBM/fileinfo/badge.png?branch=master)](https://coveralls.io/r/rafBM/fileinfo?branch=master)
|
7
7
|
[![Dependency Status](https://gemnasium.com/rafBM/fileinfo.png)](https://gemnasium.com/rafBM/fileinfo)
|
8
8
|
|
9
|
-
FileInfo detects
|
9
|
+
FileInfo detects file encodings and MIME types using the [wonderful Unix `file` command](http://en.wikipedia.org/wiki/File_\(command\)).
|
10
10
|
|
11
11
|
## Installation
|
12
12
|
|
@@ -30,18 +30,43 @@ $ gem install fileinfo
|
|
30
30
|
|
31
31
|
## Usage
|
32
32
|
|
33
|
-
|
33
|
+
### Detect encoding
|
34
|
+
|
35
|
+
Use `FileInfo.parse` with a string or `FileInfo.load` with a filename.
|
34
36
|
|
35
37
|
```ruby
|
36
38
|
FileInfo.parse('foo bar baz').encoding # => #<Encoding:US-ASCII>
|
37
39
|
FileInfo.parse('föø bår bàz').encoding # => #<Encoding:UTF-8>
|
40
|
+
|
41
|
+
filename = '/Users/rafbm/Downloads/some_crap_coming_from_windows.csv'
|
42
|
+
FileInfo.load(filename).encoding # => #<Encoding:ISO-8859-1>
|
38
43
|
```
|
39
44
|
|
40
|
-
|
45
|
+
### Detect MIME type
|
46
|
+
|
47
|
+
A bunch of methods are available depending on your needs.
|
41
48
|
|
42
49
|
```ruby
|
43
|
-
|
44
|
-
|
50
|
+
info = FileInfo.load('picture.jpg')
|
51
|
+
info.type # => "image/jpeg"
|
52
|
+
info.media_type # => "image"
|
53
|
+
info.sub_type # => "jpeg"
|
54
|
+
```
|
55
|
+
|
56
|
+
The `#mime_type` method can also return a `MIME::Type` instance.
|
57
|
+
|
58
|
+
```ruby
|
59
|
+
info = FileInfo.parse('Hello world')
|
60
|
+
info.mime_type # => #<MIME::Type:0x007f81a1a36090 @content_type="text/plain" ...>
|
61
|
+
```
|
62
|
+
|
63
|
+
**NOTE:** You must install the `mime-types` gem yourself as it is not a dependency of `fileinfo`.
|
64
|
+
|
65
|
+
Finally, `#content_type` can be used to get the full string returned by `file --mime --brief`.
|
66
|
+
|
67
|
+
```ruby
|
68
|
+
info = FileInfo.parse('Hëllø wõrld')
|
69
|
+
info.content_type # => "text/plain; charset=utf-8"
|
45
70
|
```
|
46
71
|
|
47
72
|
## Contributing
|
@@ -54,4 +79,4 @@ FileInfo.load(filename).encoding # => #<Encoding:ISO-8859-1>
|
|
54
79
|
|
55
80
|
---
|
56
81
|
|
57
|
-
©
|
82
|
+
© 2014 [Rafaël Blais Masson](http://rafbm.com). FileInfo is released under the MIT license.
|
data/fileinfo.gemspec
CHANGED
@@ -8,8 +8,8 @@ Gem::Specification.new do |spec|
|
|
8
8
|
spec.version = FileInfo::VERSION
|
9
9
|
spec.authors = ['Rafaël Blais Masson']
|
10
10
|
spec.email = ['rafael@heliom.ca']
|
11
|
-
spec.description = "FileInfo detects
|
12
|
-
spec.summary = "FileInfo detects
|
11
|
+
spec.description = "FileInfo detects file encodings and MIME types using the wonderful Unix `file` command."
|
12
|
+
spec.summary = "FileInfo detects file encodings and MIME types using the wonderful Unix `file` command."
|
13
13
|
spec.homepage = 'http://github.com/rafBM/fileinfo'
|
14
14
|
spec.license = 'MIT'
|
15
15
|
|
@@ -21,4 +21,5 @@ Gem::Specification.new do |spec|
|
|
21
21
|
spec.add_development_dependency 'bundler', '~> 1.3'
|
22
22
|
spec.add_development_dependency 'rake'
|
23
23
|
spec.add_development_dependency 'rspec', '~> 2.14'
|
24
|
+
spec.add_development_dependency 'mime-types'
|
24
25
|
end
|
data/lib/file_info.rb
CHANGED
@@ -6,42 +6,60 @@ require 'tempfile'
|
|
6
6
|
class FileInfo
|
7
7
|
class UnknownEncodingError < StandardError; end
|
8
8
|
|
9
|
-
|
10
|
-
|
9
|
+
MIME_TYPE_REGEX = /^[^;]+/
|
10
|
+
CHARSET_REGEX = /charset=(\S+)/
|
11
|
+
|
12
|
+
MIME_TYPE_ERROR_MESSAGE = 'You must install the "mime-types" gem to use FileInfo#mime_type'
|
13
|
+
|
14
|
+
attr_reader :content_type
|
11
15
|
|
12
16
|
def initialize(output)
|
13
|
-
@
|
17
|
+
@content_type = output.strip
|
18
|
+
end
|
19
|
+
|
20
|
+
def type
|
21
|
+
@type ||= content_type.match(MIME_TYPE_REGEX)[0]
|
22
|
+
end
|
23
|
+
|
24
|
+
def media_type
|
25
|
+
@media_type ||= type.split('/')[0]
|
26
|
+
end
|
27
|
+
|
28
|
+
def sub_type
|
29
|
+
@sub_type ||= type.split('/')[1]
|
30
|
+
end
|
31
|
+
|
32
|
+
def mime_type
|
33
|
+
@mime_type ||= begin
|
34
|
+
require 'mime/types' unless defined? MIME::Types
|
35
|
+
MIME::Types[type][0]
|
36
|
+
rescue LoadError
|
37
|
+
raise LoadError, MIME_TYPE_ERROR_MESSAGE
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
def charset
|
42
|
+
@charset ||= content_type.match(CHARSET_REGEX)[1]
|
14
43
|
end
|
15
44
|
|
16
45
|
def encoding
|
17
|
-
@encoding ||= ::Encoding.find(
|
46
|
+
@encoding ||= ::Encoding.find(charset)
|
18
47
|
rescue ArgumentError => e
|
19
48
|
raise UnknownEncodingError, e.message
|
20
49
|
end
|
21
50
|
|
22
51
|
def self.load(filename)
|
23
52
|
raise ArgumentError, "File '#{filename}' does not exist." if !File.exists? filename
|
24
|
-
new `file --mime #{Shellwords.escape(filename)}`
|
53
|
+
new `file --mime --brief #{Shellwords.escape(filename)}`
|
25
54
|
end
|
26
55
|
|
27
56
|
def self.parse(content)
|
28
57
|
file = Tempfile.new(rand.to_s)
|
29
58
|
file.write(content)
|
30
59
|
file.rewind
|
31
|
-
|
60
|
+
new `file --mime --brief #{file.path}`
|
61
|
+
ensure
|
32
62
|
file.close
|
33
63
|
file.unlink
|
34
|
-
|
35
|
-
new output
|
36
|
-
end
|
37
|
-
|
38
|
-
private
|
39
|
-
|
40
|
-
def string
|
41
|
-
@string ||= @output.match(STRING_REGEX)[1].strip
|
42
|
-
end
|
43
|
-
|
44
|
-
def encoding_string
|
45
|
-
@encoding_string ||= string.match(ENCODING_REGEX)[1]
|
46
64
|
end
|
47
65
|
end
|
data/lib/file_info/version.rb
CHANGED
data/spec/file_info_spec.rb
CHANGED
@@ -7,15 +7,33 @@ describe FileInfo do
|
|
7
7
|
let(:macroman_file) { fixture('encoding_macroman.csv') }
|
8
8
|
let(:utf8_file) { fixture('encoding_utf8.csv') }
|
9
9
|
|
10
|
-
|
11
|
-
|
10
|
+
let(:photoshop_file) { fixture('mockup.psd') }
|
11
|
+
let(:binary_file) { fixture('bytes') }
|
12
|
+
|
13
|
+
describe '#charset' do
|
14
|
+
it 'returns encoding string' do
|
15
|
+
expect(FileInfo.load(ascii_file.path).charset).to eq 'us-ascii'
|
16
|
+
expect(FileInfo.load(isolatin_file.path).charset).to eq 'iso-8859-1'
|
17
|
+
expect(FileInfo.load(isowindows_file.path).charset).to eq 'iso-8859-1'
|
18
|
+
expect(FileInfo.load(utf8_file.path).charset).to eq 'utf-8'
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
describe '#encoding' do
|
23
|
+
it 'returns Encoding instance' do
|
12
24
|
expect(FileInfo.load(ascii_file.path).encoding).to eq Encoding::US_ASCII
|
13
25
|
expect(FileInfo.load(isolatin_file.path).encoding).to eq Encoding::ISO_8859_1
|
14
26
|
expect(FileInfo.load(isowindows_file.path).encoding).to eq Encoding::ISO_8859_1
|
15
27
|
expect(FileInfo.load(utf8_file.path).encoding).to eq Encoding::UTF_8
|
16
28
|
end
|
17
29
|
|
18
|
-
it '
|
30
|
+
it 'raises UnknownEncodingError' do
|
31
|
+
expect { FileInfo.load(macroman_file.path).encoding }.to raise_error(FileInfo::UnknownEncodingError)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
describe '.load' do
|
36
|
+
it 'accepts filename with space' do
|
19
37
|
old_filename = fixture('encoding_utf8.csv').path
|
20
38
|
new_filename = old_filename.sub('_', ' ')
|
21
39
|
FileUtils.cp(old_filename, new_filename)
|
@@ -25,7 +43,7 @@ describe FileInfo do
|
|
25
43
|
FileUtils.rm(new_filename)
|
26
44
|
end
|
27
45
|
|
28
|
-
it '
|
46
|
+
it 'accepts filename with space and quote' do
|
29
47
|
old_filename = fixture('encoding_utf8.csv').path
|
30
48
|
new_filename = old_filename.sub('_', ' " ')
|
31
49
|
FileUtils.cp(old_filename, new_filename)
|
@@ -41,7 +59,7 @@ describe FileInfo do
|
|
41
59
|
end
|
42
60
|
|
43
61
|
describe '.parse' do
|
44
|
-
it '
|
62
|
+
it 'accepts a string' do
|
45
63
|
expect(FileInfo.parse(ascii_file.read).encoding).to eq Encoding::US_ASCII
|
46
64
|
expect(FileInfo.parse(isolatin_file.read).encoding).to eq Encoding::ISO_8859_1
|
47
65
|
expect(FileInfo.parse(isowindows_file.read).encoding).to eq Encoding::ISO_8859_1
|
@@ -49,9 +67,72 @@ describe FileInfo do
|
|
49
67
|
end
|
50
68
|
end
|
51
69
|
|
52
|
-
|
53
|
-
|
54
|
-
|
70
|
+
let(:txt) { FileInfo.parse(FileInfo.parse('Hello, world!')) }
|
71
|
+
let(:csv) { FileInfo.load(utf8_file.path) }
|
72
|
+
let(:psd) { FileInfo.load(photoshop_file.path) }
|
73
|
+
let(:empty) { FileInfo.parse('') }
|
74
|
+
let(:bytes) { FileInfo.load(binary_file.path) }
|
75
|
+
|
76
|
+
describe '#content_type' do
|
77
|
+
it 'returns full Content-Type string' do
|
78
|
+
expect(txt.content_type).to eq 'text/plain; charset=us-ascii'
|
79
|
+
expect(csv.content_type).to eq 'text/plain; charset=utf-8'
|
80
|
+
expect(psd.content_type).to eq 'image/vnd.adobe.photoshop; charset=binary'
|
81
|
+
expect(empty.content_type).to eq 'application/x-empty; charset=binary'
|
82
|
+
expect(bytes.content_type).to eq 'application/octet-stream; charset=binary'
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
describe '#type' do
|
87
|
+
it 'returns MIME type string' do
|
88
|
+
expect(txt.type).to eq 'text/plain'
|
89
|
+
expect(csv.type).to eq 'text/plain'
|
90
|
+
expect(psd.type).to eq 'image/vnd.adobe.photoshop'
|
91
|
+
expect(empty.type).to eq 'application/x-empty'
|
92
|
+
expect(bytes.type).to eq 'application/octet-stream'
|
93
|
+
end
|
94
|
+
end
|
95
|
+
|
96
|
+
describe '#media_type' do
|
97
|
+
it 'returns MIME media type string' do
|
98
|
+
expect(txt.media_type).to eq 'text'
|
99
|
+
expect(csv.media_type).to eq 'text'
|
100
|
+
expect(psd.media_type).to eq 'image'
|
101
|
+
expect(empty.media_type).to eq 'application'
|
102
|
+
expect(bytes.media_type).to eq 'application'
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
describe '#sub_type' do
|
107
|
+
it 'returns MIME sub type string' do
|
108
|
+
expect(txt.sub_type).to eq 'plain'
|
109
|
+
expect(csv.sub_type).to eq 'plain'
|
110
|
+
expect(psd.sub_type).to eq 'vnd.adobe.photoshop'
|
111
|
+
expect(empty.sub_type).to eq 'x-empty'
|
112
|
+
expect(bytes.sub_type).to eq 'octet-stream'
|
113
|
+
end
|
114
|
+
end
|
115
|
+
|
116
|
+
describe '#mime_type' do
|
117
|
+
it 'returns a MIME::Type instance' do
|
118
|
+
[txt, csv, psd, bytes].each do |fileinfo|
|
119
|
+
expect(fileinfo.mime_type).to be_a MIME::Type
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
it 'returns nil for empty file' do
|
124
|
+
expect(empty.mime_type).to eq nil
|
125
|
+
end
|
126
|
+
|
127
|
+
context 'when "mime-types" gem isn’t available' do
|
128
|
+
before do
|
129
|
+
MIME.send(:remove_const, :Types)
|
130
|
+
allow_any_instance_of(FileInfo).to receive(:require).with('mime/types').and_raise(LoadError)
|
131
|
+
end
|
132
|
+
|
133
|
+
it 'raises LoadError with custom message' do
|
134
|
+
expect { txt.mime_type }.to raise_error(LoadError, FileInfo::MIME_TYPE_ERROR_MESSAGE)
|
135
|
+
end
|
55
136
|
end
|
56
137
|
end
|
57
138
|
end
|
data/spec/fixtures/bytes
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
�Ɋ���z��S��Q_
|
Binary file
|
metadata
CHANGED
@@ -1,68 +1,82 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: fileinfo
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Rafaël Blais Masson
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2014-04-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - ~>
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '1.3'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - ~>
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '1.3'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: rake
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: '0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- -
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: rspec
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - ~>
|
45
|
+
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
47
|
version: '2.14'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - ~>
|
52
|
+
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '2.14'
|
55
|
-
|
56
|
-
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: mime-types
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: FileInfo detects file encodings and MIME types using the wonderful Unix
|
70
|
+
`file` command.
|
57
71
|
email:
|
58
72
|
- rafael@heliom.ca
|
59
73
|
executables: []
|
60
74
|
extensions: []
|
61
75
|
extra_rdoc_files: []
|
62
76
|
files:
|
63
|
-
- .gitignore
|
64
|
-
- .rspec
|
65
|
-
- .travis.yml
|
77
|
+
- ".gitignore"
|
78
|
+
- ".rspec"
|
79
|
+
- ".travis.yml"
|
66
80
|
- Gemfile
|
67
81
|
- LICENSE.txt
|
68
82
|
- README.md
|
@@ -72,11 +86,13 @@ files:
|
|
72
86
|
- lib/file_info/version.rb
|
73
87
|
- lib/fileinfo.rb
|
74
88
|
- spec/file_info_spec.rb
|
89
|
+
- spec/fixtures/bytes
|
75
90
|
- spec/fixtures/encoding_ascii.csv
|
76
91
|
- spec/fixtures/encoding_isolatin.csv
|
77
92
|
- spec/fixtures/encoding_isowindows.csv
|
78
93
|
- spec/fixtures/encoding_macroman.csv
|
79
94
|
- spec/fixtures/encoding_utf8.csv
|
95
|
+
- spec/fixtures/mockup.psd
|
80
96
|
- spec/spec_helper.rb
|
81
97
|
homepage: http://github.com/rafBM/fileinfo
|
82
98
|
licenses:
|
@@ -88,26 +104,28 @@ require_paths:
|
|
88
104
|
- lib
|
89
105
|
required_ruby_version: !ruby/object:Gem::Requirement
|
90
106
|
requirements:
|
91
|
-
- -
|
107
|
+
- - ">="
|
92
108
|
- !ruby/object:Gem::Version
|
93
109
|
version: '0'
|
94
110
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
95
111
|
requirements:
|
96
|
-
- -
|
112
|
+
- - ">="
|
97
113
|
- !ruby/object:Gem::Version
|
98
114
|
version: '0'
|
99
115
|
requirements: []
|
100
116
|
rubyforge_project:
|
101
|
-
rubygems_version: 2.
|
117
|
+
rubygems_version: 2.2.2
|
102
118
|
signing_key:
|
103
119
|
specification_version: 4
|
104
|
-
summary: FileInfo detects
|
105
|
-
|
120
|
+
summary: FileInfo detects file encodings and MIME types using the wonderful Unix `file`
|
121
|
+
command.
|
106
122
|
test_files:
|
107
123
|
- spec/file_info_spec.rb
|
124
|
+
- spec/fixtures/bytes
|
108
125
|
- spec/fixtures/encoding_ascii.csv
|
109
126
|
- spec/fixtures/encoding_isolatin.csv
|
110
127
|
- spec/fixtures/encoding_isowindows.csv
|
111
128
|
- spec/fixtures/encoding_macroman.csv
|
112
129
|
- spec/fixtures/encoding_utf8.csv
|
130
|
+
- spec/fixtures/mockup.psd
|
113
131
|
- spec/spec_helper.rb
|