rgabo-readability 0.1.3 → 0.1.4
Sign up to get free protection for your applications and to get access to all the features.
- data/VERSION +1 -1
- data/lib/readability/harmonizable.rb +12 -1
- data/readability.gems +0 -22
- data/rgabo-readability.gemspec +2 -2
- data/spec/readability/readable_spec.rb +19 -7
- data/spec/readability/urls.yaml +4 -3
- metadata +4 -4
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.1.
|
1
|
+
0.1.4
|
@@ -35,8 +35,19 @@ module Readability
|
|
35
35
|
end
|
36
36
|
|
37
37
|
def harmony_page
|
38
|
+
html = self.to_html
|
39
|
+
|
40
|
+
# unless encoding is already utf[-8], convert using iconv
|
41
|
+
unless meta_encoding =~ /utf/i
|
42
|
+
begin
|
43
|
+
require 'iconv'
|
44
|
+
html = Iconv.new("UTF8", "LATIN1//TRANSLIT//IGNORE").iconv(self.to_html)
|
45
|
+
rescue
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
38
49
|
# load document into a page
|
39
|
-
page = Harmony::Page.new(
|
50
|
+
page = Harmony::Page.new(html)
|
40
51
|
|
41
52
|
# yield the page and reparse if a block is given
|
42
53
|
if block_given?
|
data/readability.gems
CHANGED
@@ -1,30 +1,8 @@
|
|
1
1
|
# readability.gems generated gem export file. Note that any env variable settings will be missing. Append these after using a ';' field separator
|
2
2
|
|
3
|
-
# nokogiri
|
4
3
|
nokogiri -v1.4.1
|
5
|
-
|
6
|
-
# harmony (johnson & envjs)
|
7
|
-
stackdeck -v0.2.0
|
8
|
-
johnson -v2.0.0.pre3
|
9
|
-
envjs -v0.3.1
|
10
4
|
harmony -v0.5.5
|
11
|
-
|
12
|
-
# tomdoc
|
13
|
-
hoe -v2.6.0
|
14
|
-
ParseTree -v3.0.5
|
15
|
-
RubyInline -v3.7.0
|
16
|
-
ruby_parser -v2.0.4
|
17
|
-
sexp_processor -v3.0.4
|
18
|
-
colored -v1.2
|
19
5
|
tomdoc -v0.1.0
|
20
|
-
|
21
|
-
# jeweler
|
22
|
-
gemcutter -v0.5.0
|
23
|
-
git -v1.2.5
|
24
|
-
json_pure -v1.4.3
|
25
|
-
rubyforge -v2.0.4
|
26
6
|
jeweler -v1.4.0
|
27
|
-
|
28
|
-
# rspec
|
29
7
|
rspec -v1.3.0
|
30
8
|
syntax -v1.0.0
|
data/rgabo-readability.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{rgabo-readability}
|
8
|
-
s.version = "0.1.
|
8
|
+
s.version = "0.1.4"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Gabor Ratky"]
|
12
|
-
s.date = %q{2010-05-
|
12
|
+
s.date = %q{2010-05-19}
|
13
13
|
s.description = %q{Extends Nokogiri::HTML::Document to run Arc90's Readability script and produces easy to read HTML documents.}
|
14
14
|
s.email = %q{rgabo@rgabostyle.com}
|
15
15
|
s.extra_rdoc_files = [
|
@@ -72,16 +72,28 @@ describe Readability::Readable do
|
|
72
72
|
end
|
73
73
|
|
74
74
|
describe "Readability.js" do
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
75
|
+
class << self
|
76
|
+
def should_not_fail_on url
|
77
|
+
self.class_eval <<-EOF
|
78
|
+
it "should not fail on #{url}" do
|
79
|
+
@doc = Nokogiri::HTML(open("#{url}"))
|
80
|
+
|
81
|
+
# run readability in place
|
82
|
+
@doc.to_readable!
|
81
83
|
|
84
|
+
@doc.to_html.should include('Readability version 1.5.0')
|
85
|
+
end
|
86
|
+
EOF
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
YAML.load(File.open(File.join(File.dirname(__FILE__), 'urls.yaml'))).each do |url|
|
91
|
+
it "should not fail on #{url}" do
|
92
|
+
@doc = Nokogiri::HTML(open("#{url}"))
|
93
|
+
|
82
94
|
# run readability in place
|
83
95
|
@doc.to_readable!
|
84
|
-
|
96
|
+
|
85
97
|
@doc.to_html.should include('Readability version 1.5.0')
|
86
98
|
end
|
87
99
|
end
|
data/spec/readability/urls.yaml
CHANGED
@@ -1,8 +1,9 @@
|
|
1
1
|
# Array of URLs to test readability with
|
2
|
-
- 'http://techcrunch.com/2010/05/16/groupon-invades-europe-with-acquisition-of-citydeal'
|
3
2
|
- 'http://blogs.wsj.com/venturecapital/2010/05/14/despite-short-term-improvement-vc-10-year-index-goes-negative/?mod=rss_WSJBlog'
|
4
3
|
- 'http://www.engadget.com/2010/04/03/entelligence-the-ipad-as-a-productivity-tool/'
|
5
|
-
|
4
|
+
- 'http://www.huffingtonpost.com/2010/05/15/delete-facebook-account-q_n_576956.html'
|
6
5
|
- 'http://mashable.com/2010/05/16/in-defense-of-facebook/'
|
7
6
|
- 'http://feeds.venturebeat.com/~r/Venturebeat/~3/rYPVBROMiEI/'
|
8
|
-
- 'http://eu.techcrunch.com/2010/04/25/new-eu-rules-could-kill-off-european-vc-and-screw-startups-lets-stop-them/'
|
7
|
+
- 'http://eu.techcrunch.com/2010/04/25/new-eu-rules-could-kill-off-european-vc-and-screw-startups-lets-stop-them/'
|
8
|
+
- 'http://www.j-learning.org/promote_it/page/surveys/'
|
9
|
+
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rgabo-readability
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 19
|
5
5
|
prerelease: false
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 1
|
9
|
-
-
|
10
|
-
version: 0.1.
|
9
|
+
- 4
|
10
|
+
version: 0.1.4
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Gabor Ratky
|
@@ -15,7 +15,7 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2010-05-
|
18
|
+
date: 2010-05-19 00:00:00 +02:00
|
19
19
|
default_executable:
|
20
20
|
dependencies:
|
21
21
|
- !ruby/object:Gem::Dependency
|