html_massage 0.5.0 → 0.5.1
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/bin/html_massage +2 -1
- data/html_massage.gemspec +1 -0
- data/lib/html_massage/cli.rb +2 -1
- data/lib/html_massage/version.rb +1 -1
- data/lib/html_massage.rb +7 -1
- metadata +16 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: f43fabc2e9508236d4db368d421dc9530cd2e32d
|
|
4
|
+
data.tar.gz: b58b4a919ee6153b20c2818d7f473040d5893fe0
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 68ee791a114fa0864eef87730ef09b3e367d1894632e39abdd8885f67a646c27179a453a3141378f246b353ce8619bf001405b7e34a5d84adf920e476871c23d
|
|
7
|
+
data.tar.gz: 9a7cc0f89b9a58a8f89c04dda1488f97aa77ea14f7ab29d9afefdc0f738add22315867a9e4e20821e9b9b48d930f6084998dc1e21440219a6ef9a8c789c87fea
|
data/bin/html_massage
CHANGED
data/html_massage.gemspec
CHANGED
|
@@ -23,6 +23,7 @@ Gem::Specification.new do |gem|
|
|
|
23
23
|
gem.add_dependency "thor"
|
|
24
24
|
gem.add_dependency "rest-client", "~> 1.7"
|
|
25
25
|
gem.add_dependency "reverse_markdown", "~> 0.5"
|
|
26
|
+
gem.add_dependency "charlock_holmes", "~> 0.7"
|
|
26
27
|
|
|
27
28
|
gem.add_development_dependency "rspec", "~> 2.5"
|
|
28
29
|
end
|
data/lib/html_massage/cli.rb
CHANGED
data/lib/html_massage/version.rb
CHANGED
data/lib/html_massage.rb
CHANGED
|
@@ -2,7 +2,8 @@ require "cgi"
|
|
|
2
2
|
require "nokogiri"
|
|
3
3
|
require "sanitize"
|
|
4
4
|
require "reverse_markdown"
|
|
5
|
-
require "
|
|
5
|
+
require "charlock_holmes"
|
|
6
|
+
require File.expand_path File.join(File.dirname(__FILE__), "html_massage", "version")
|
|
6
7
|
|
|
7
8
|
module HtmlMassager
|
|
8
9
|
|
|
@@ -180,6 +181,11 @@ module HtmlMassager
|
|
|
180
181
|
|
|
181
182
|
def initialize( html )
|
|
182
183
|
@html = html.dup
|
|
184
|
+
detection = CharlockHolmes::EncodingDetector.detect( html ) rescue nil
|
|
185
|
+
if detection
|
|
186
|
+
utf8_html = CharlockHolmes::Converter.convert html, detection[:encoding], "UTF-8"
|
|
187
|
+
@html = utf8_html
|
|
188
|
+
end
|
|
183
189
|
end
|
|
184
190
|
|
|
185
191
|
def massage!( options={} )
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: html_massage
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.5.
|
|
4
|
+
version: 0.5.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Harlan T Wood
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2014-
|
|
11
|
+
date: 2014-09-01 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: nokogiri
|
|
@@ -80,6 +80,20 @@ dependencies:
|
|
|
80
80
|
- - "~>"
|
|
81
81
|
- !ruby/object:Gem::Version
|
|
82
82
|
version: '0.5'
|
|
83
|
+
- !ruby/object:Gem::Dependency
|
|
84
|
+
name: charlock_holmes
|
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
|
86
|
+
requirements:
|
|
87
|
+
- - "~>"
|
|
88
|
+
- !ruby/object:Gem::Version
|
|
89
|
+
version: '0.7'
|
|
90
|
+
type: :runtime
|
|
91
|
+
prerelease: false
|
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
93
|
+
requirements:
|
|
94
|
+
- - "~>"
|
|
95
|
+
- !ruby/object:Gem::Version
|
|
96
|
+
version: '0.7'
|
|
83
97
|
- !ruby/object:Gem::Dependency
|
|
84
98
|
name: rspec
|
|
85
99
|
requirement: !ruby/object:Gem::Requirement
|