guess_html_encoding 0.0.7 → 0.0.8
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.
- data/Gemfile.lock +1 -1
- data/lib/guess_html_encoding.rb +5 -2
- data/lib/guess_html_encoding/version.rb +1 -1
- data/spec/guess_html_encoding_spec.rb +12 -0
- metadata +2 -2
data/Gemfile.lock
CHANGED
data/lib/guess_html_encoding.rb
CHANGED
|
@@ -19,9 +19,12 @@ module GuessHtmlEncoding
|
|
|
19
19
|
end
|
|
20
20
|
|
|
21
21
|
if out.nil? || out.empty? || !encoding_loaded?(out)
|
|
22
|
-
if html =~ /<meta[^>]*HTTP-EQUIV=["']Content-Type["'][^>]*content=["']([^'"]*)["']/i && $1 =~ /charset=([\w\d-]+);?/i
|
|
23
|
-
out = $1
|
|
22
|
+
if html =~ /<meta[^>]*HTTP-EQUIV=["']?Content-Type["']?[^>]*content=["']([^'"]*)["']/i && $1 =~ /charset=([\w\d-]+);?/i
|
|
23
|
+
out = $1
|
|
24
|
+
elsif html =~ /<meta\s+charset=["']([\w\d-]+)?/i
|
|
25
|
+
out = $1
|
|
24
26
|
end
|
|
27
|
+
out.upcase! unless out.nil?
|
|
25
28
|
end
|
|
26
29
|
|
|
27
30
|
# Translate encodings with other names.
|
|
@@ -146,5 +146,17 @@ describe "GuessHtmlEncoding" do
|
|
|
146
146
|
it 'returns false for irregular or unloaded encoding' do
|
|
147
147
|
GuessHtmlEncoding.encoding_loaded?('_WHY').should be_false
|
|
148
148
|
end
|
|
149
|
+
|
|
150
|
+
it "accepts a simple meta tag" do
|
|
151
|
+
# Like http://www.taobao.com
|
|
152
|
+
guess = GuessHtmlEncoding.guess('<html><head><meta charset="gbk" /></head><body><div>hi!</div></body></html>')
|
|
153
|
+
guess.should == "GBK"
|
|
154
|
+
end
|
|
155
|
+
|
|
156
|
+
it "works as well when there is no double quotation marks with http-equiv in meta-tags" do
|
|
157
|
+
# Like http://www.frozentux.net/iptables-tutorial/cn/iptables-tutorial-cn-1.1.19.html
|
|
158
|
+
guess = GuessHtmlEncoding.guess('<html><head><META http-equiv=Content-Type content="text/html; charset=utf-8"></head><body><div>hi!</div></body></html>')
|
|
159
|
+
guess.should == "UTF-8"
|
|
160
|
+
end
|
|
149
161
|
end
|
|
150
162
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: guess_html_encoding
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.8
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2013-01-
|
|
12
|
+
date: 2013-01-08 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: rspec
|