hpricot_scrub 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.txt +0 -0
- data/Manifest.txt +11 -0
- data/README.txt +12 -0
- data/Rakefile +54 -0
- data/examples/config.yml +47 -0
- data/lib/hpricot_scrub/version.rb +9 -0
- data/lib/hpricot_scrub.rb +1 -0
- data/setup.rb +1585 -0
- data/test/hpricot_scrub_test.rb +18 -0
- data/test/scrubber_data.rb +12 -0
- data/test/test_helper.rb +2 -0
- metadata +64 -0
data/CHANGELOG.txt
ADDED
File without changes
|
data/Manifest.txt
ADDED
data/README.txt
ADDED
@@ -0,0 +1,12 @@
|
|
1
|
+
README for hpricot_scrub
|
2
|
+
========================
|
3
|
+
|
4
|
+
HpricotScrub is a wrapper around Hpricot that allows you to easily scrub HTML
|
5
|
+
of tags and attributes you don't want in the final output.
|
6
|
+
|
7
|
+
See examples/config.yml for a sample config file or
|
8
|
+
|
9
|
+
http://underpantsgnome.com/2007/01/20/hpricot-scrub/
|
10
|
+
|
11
|
+
for more info.
|
12
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
require 'rake/clean'
|
4
|
+
require 'rake/testtask'
|
5
|
+
require 'rake/packagetask'
|
6
|
+
require 'rake/gempackagetask'
|
7
|
+
require 'rake/rdoctask'
|
8
|
+
require 'rake/contrib/rubyforgepublisher'
|
9
|
+
require 'fileutils'
|
10
|
+
require 'hoe'
|
11
|
+
include FileUtils
|
12
|
+
require File.join(File.dirname(__FILE__), 'lib', 'hpricot_scrub', 'version')
|
13
|
+
|
14
|
+
AUTHOR = "UnderpantsGnome" # can also be an array of Authors
|
15
|
+
EMAIL = "michael@underpantsgnome.com"
|
16
|
+
DESCRIPTION = "Scrub HTML with Hpricot"
|
17
|
+
GEM_NAME = "hpricot_scrub" # what ppl will type to install your gem
|
18
|
+
RUBYFORGE_PROJECT = "hpricot_scrub" # The unix name for your project
|
19
|
+
HOMEPATH = "http://trac.underpantsgnome.com/hpricot_scrub/"
|
20
|
+
|
21
|
+
|
22
|
+
NAME = "hpricot_scrub"
|
23
|
+
REV = nil # UNCOMMENT IF REQUIRED: File.read(".svn/entries")[/committed-rev="(d+)"/, 1] rescue nil
|
24
|
+
VERS = ENV['VERSION'] || (HpricotScrub::VERSION::STRING + (REV ? ".#{REV}" : ""))
|
25
|
+
CLEAN.include ['**/.*.sw?', '*.gem', '.config']
|
26
|
+
RDOC_OPTS = ['--quiet', '--title', "hpricot_scrub documentation",
|
27
|
+
"--opname", "index.html",
|
28
|
+
"--line-numbers",
|
29
|
+
"--main", "README",
|
30
|
+
"--inline-source"]
|
31
|
+
|
32
|
+
class Hoe
|
33
|
+
def extra_deps
|
34
|
+
@extra_deps.reject { |x| Array(x).first == 'hoe' }
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
# Generate all the Rake tasks
|
39
|
+
# Run 'rake -T' to see list of generated tasks (from gem root directory)
|
40
|
+
hoe = Hoe.new(GEM_NAME, VERS) do |p|
|
41
|
+
p.author = AUTHOR
|
42
|
+
p.description = DESCRIPTION
|
43
|
+
p.email = EMAIL
|
44
|
+
p.summary = DESCRIPTION
|
45
|
+
p.url = HOMEPATH
|
46
|
+
p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
|
47
|
+
p.test_globs = ["test/**/*_test.rb"]
|
48
|
+
p.clean_globs = CLEAN #An array of file patterns to delete on clean.
|
49
|
+
|
50
|
+
# == Optional
|
51
|
+
#p.changes - A description of the release's latest changes.
|
52
|
+
p.extra_deps = ['hpricot', '>= 0.5']
|
53
|
+
#p.spec_extras - A hash of extra values to set in the gemspec.
|
54
|
+
end
|
data/examples/config.yml
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
|
2
|
+
---
|
3
|
+
:allow_tags: # let these tags stay, but will strip attributes
|
4
|
+
- 'b'
|
5
|
+
- 'blockquote'
|
6
|
+
- 'br'
|
7
|
+
- 'div'
|
8
|
+
- 'h1'
|
9
|
+
- 'h2'
|
10
|
+
- 'h3'
|
11
|
+
- 'h4'
|
12
|
+
- 'h5'
|
13
|
+
- 'h6'
|
14
|
+
- 'hr'
|
15
|
+
- 'i'
|
16
|
+
- 'em'
|
17
|
+
- 'img'
|
18
|
+
- 'li'
|
19
|
+
- 'ol'
|
20
|
+
- 'p'
|
21
|
+
- 'pre'
|
22
|
+
- 'small'
|
23
|
+
- 'span'
|
24
|
+
- 'span'
|
25
|
+
- 'strike'
|
26
|
+
- 'strong'
|
27
|
+
- 'sub'
|
28
|
+
- 'sup'
|
29
|
+
- 'table'
|
30
|
+
- 'tbody'
|
31
|
+
- 'td'
|
32
|
+
- 'tfoot'
|
33
|
+
- 'thead'
|
34
|
+
- 'tr'
|
35
|
+
- 'u'
|
36
|
+
- 'ul'
|
37
|
+
|
38
|
+
:remove_tags: # completely removes everything between open and close tag
|
39
|
+
- 'form'
|
40
|
+
- 'script'
|
41
|
+
|
42
|
+
:allow_attributes: # let these attributes stay, strip all others
|
43
|
+
- 'src'
|
44
|
+
- 'font'
|
45
|
+
- 'alt'
|
46
|
+
- 'style'
|
47
|
+
- 'align'
|
@@ -0,0 +1 @@
|
|
1
|
+
Dir[File.join(File.dirname(__FILE__), 'hpricot_scrub/**/*.rb')].sort.each { |lib| require lib }
|