cchardet 0.2.0 → 0.2.1
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 +4 -4
- data/CHANGELOG.md +5 -0
- data/README.md +60 -11
- data/cchardet.gemspec +3 -3
- data/lib/cchardet/version.rb +1 -1
- metadata +12 -11
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 15c796c93834634e0aa4c71da57950fc7a42d43a3a28766d43fd7cf7103936a5
|
4
|
+
data.tar.gz: 581baba4d7dc98eb5720933125fdcb47c24272456fbe5cfb3a8b609c42916d0b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3e40197160218e7893d5250cd2c6504d8cbd128d4ff8ade21c0621d80a3faa6498070285dbfa4247363c63a7b66252fcc5c0b06bba86cf669af9937337444f4f
|
7
|
+
data.tar.gz: c66c7db53e896f9b609477fed8f67038c9a9143442e563bd79b3ac1ab8fa1cefff709b1c2fd988f098ae853ad246c755402529d9833ee7f8ada8abd2f27f909b
|
data/CHANGELOG.md
CHANGED
data/README.md
CHANGED
@@ -1,35 +1,84 @@
|
|
1
|
-
#
|
1
|
+
# cchardet
|
2
2
|
|
3
|
-
|
3
|
+
Ruby bindings for freedesktop.org's uchardet (<https://gitlab.freedesktop.org/uchardet/uchardet>).
|
4
4
|
|
5
|
-
|
5
|
+
By default, this gem depends on the system uchardet. Alternatively, it can build
|
6
|
+
the unreleased `wip/Jehan/improved-API` branch of uchardet as a native extension.
|
7
|
+
Note that uchardet's license terms may differ from those of this gem.
|
6
8
|
|
7
9
|
## Installation
|
8
10
|
|
11
|
+
### System uchardet
|
12
|
+
|
9
13
|
Add this line to your application's Gemfile:
|
10
14
|
|
11
15
|
```ruby
|
12
|
-
gem
|
16
|
+
gem "cchardet"
|
13
17
|
```
|
14
18
|
|
15
19
|
And then execute:
|
16
20
|
|
17
|
-
|
21
|
+
```
|
22
|
+
bundle install
|
23
|
+
```
|
18
24
|
|
19
25
|
Or install it yourself as:
|
20
26
|
|
21
|
-
|
27
|
+
```
|
28
|
+
gem install cchardet
|
29
|
+
```
|
30
|
+
|
31
|
+
### Unreleased branch as native extension
|
32
|
+
|
33
|
+
When using bundler:
|
34
|
+
|
35
|
+
```
|
36
|
+
bundle config set --global build.cchardet --with-unreleased-uchardet
|
37
|
+
bundle install
|
38
|
+
```
|
39
|
+
|
40
|
+
When using gem directly:
|
41
|
+
|
42
|
+
```
|
43
|
+
gem install cchardet -- --with-unreleased-uchardet
|
44
|
+
```
|
22
45
|
|
23
46
|
## Usage
|
24
47
|
|
25
|
-
|
48
|
+
```ruby
|
49
|
+
require "cchardet"
|
50
|
+
|
51
|
+
# ...
|
52
|
+
|
53
|
+
CChardet.detect(unknown_bytes)
|
54
|
+
# released uchardet:
|
55
|
+
# { encoding: "UTF-8" }
|
56
|
+
# unreleased native extension:
|
57
|
+
# { encoding: "UTF-8", confidence: 1.0, language: nil }
|
58
|
+
```
|
26
59
|
|
27
|
-
|
60
|
+
The only public interface is `CChardet.detect`, which takes a sequence of bytes.
|
28
61
|
|
29
|
-
|
62
|
+
When using a released version of uchardet, it will return a hash with a single
|
63
|
+
element, `encoding`, indicating the detected encoding of the byte stream. Future
|
64
|
+
versions of uchardet are likely to provide additional fields (see <https://gitlab.freedesktop.org/uchardet/uchardet/-/issues/5#note_474963>).
|
30
65
|
|
31
|
-
|
66
|
+
When using the unreleased native extension, it will return an array of hashes
|
67
|
+
having three elements:
|
68
|
+
|
69
|
+
- `encoding` – Detected encoding of the byte stream
|
70
|
+
- `confidence` – Confidence of the encoding value
|
71
|
+
- `language` – Detected language, if known
|
72
|
+
|
73
|
+
The hashes are ordered by descending confidence.
|
32
74
|
|
33
75
|
## Contributing
|
34
76
|
|
35
|
-
Bug reports and pull requests are welcome on GitHub at https://github.com/
|
77
|
+
Bug reports and pull requests are welcome on GitHub at <https://github.com/elebow/cchardet>.
|
78
|
+
|
79
|
+
## License
|
80
|
+
|
81
|
+
MIT License.
|
82
|
+
|
83
|
+
Note that uchardet, which may be compiled as a native extension, is covered by its
|
84
|
+
own license.
|
data/cchardet.gemspec
CHANGED
@@ -9,12 +9,12 @@ Gem::Specification.new do |spec|
|
|
9
9
|
spec.email = ["elebow@users.noreply.github.com"]
|
10
10
|
|
11
11
|
spec.summary = "Ruby bindings for freedesktop.org's libuchardet, for encoding detection."
|
12
|
-
spec.homepage = "https://github.com/elebow/cchardet"
|
13
|
-
spec.license = "
|
12
|
+
spec.homepage = "https://github.com/elebow/cchardet-ruby"
|
13
|
+
spec.license = "MIT"
|
14
14
|
spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
15
15
|
|
16
16
|
spec.metadata["homepage_uri"] = spec.homepage
|
17
|
-
spec.metadata["source_code_uri"] = "https://github.com/elebow/cchardet"
|
17
|
+
spec.metadata["source_code_uri"] = "https://github.com/elebow/cchardet-ruby"
|
18
18
|
spec.metadata["changelog_uri"] = "https://github.com/elebow/cchardet/blob/trunk/CHANGELOG.md"
|
19
19
|
|
20
20
|
# Specify which files should be added to the gem when it is released.
|
data/lib/cchardet/version.rb
CHANGED
metadata
CHANGED
@@ -1,16 +1,16 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: cchardet
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Eddie Lebow
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2021-03-
|
11
|
+
date: 2021-03-08 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
|
-
description:
|
13
|
+
description:
|
14
14
|
email:
|
15
15
|
- elebow@users.noreply.github.com
|
16
16
|
executables: []
|
@@ -333,14 +333,14 @@ files:
|
|
333
333
|
- lib/cchardet.rb
|
334
334
|
- lib/cchardet/lib_finder.rb
|
335
335
|
- lib/cchardet/version.rb
|
336
|
-
homepage: https://github.com/elebow/cchardet
|
336
|
+
homepage: https://github.com/elebow/cchardet-ruby
|
337
337
|
licenses:
|
338
|
-
-
|
338
|
+
- MIT
|
339
339
|
metadata:
|
340
|
-
homepage_uri: https://github.com/elebow/cchardet
|
341
|
-
source_code_uri: https://github.com/elebow/cchardet
|
340
|
+
homepage_uri: https://github.com/elebow/cchardet-ruby
|
341
|
+
source_code_uri: https://github.com/elebow/cchardet-ruby
|
342
342
|
changelog_uri: https://github.com/elebow/cchardet/blob/trunk/CHANGELOG.md
|
343
|
-
post_install_message:
|
343
|
+
post_install_message:
|
344
344
|
rdoc_options: []
|
345
345
|
require_paths:
|
346
346
|
- lib
|
@@ -355,8 +355,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
355
355
|
- !ruby/object:Gem::Version
|
356
356
|
version: '0'
|
357
357
|
requirements: []
|
358
|
-
|
359
|
-
|
358
|
+
rubyforge_project:
|
359
|
+
rubygems_version: 2.7.6.2
|
360
|
+
signing_key:
|
360
361
|
specification_version: 4
|
361
362
|
summary: Ruby bindings for freedesktop.org's libuchardet, for encoding detection.
|
362
363
|
test_files: []
|