hpricot_scrub 0.1.0 → 0.2.0

data/CHANGELOG.txt

@@ -0,0 +1,9 @@
+2007-03-04 Michael <michael@underpantsgnome.com>
+	Release 0.2.0
+	Add String methods for scrub and scrub!
+	
+	Fixed a bug where nested elements were not being scrubbed when using a 
+	config hash
+
+2007-03-03 Michael <michael@underpantsgnome.com>
+	Release 0.1.0, Initial Gem version

data/README.txt

@@ -6,7 +6,4 @@ of tags and attributes you don't want in the final output.
 
 See examples/config.yml for a sample config file or 
 
-http://underpantsgnome.com/2007/01/20/hpricot-scrub/
-
-for more info.
-
+http://trac.underpantsgnome.com/hpricot_scrub

data/Rakefile

@@ -15,10 +15,9 @@ AUTHOR = "UnderpantsGnome"  # can also be an array of Authors
 EMAIL = "michael@underpantsgnome.com"
 DESCRIPTION = "Scrub HTML with Hpricot"
 GEM_NAME = "hpricot_scrub" # what ppl will type to install your gem
-RUBYFORGE_PROJECT = "hpricot_scrub" # The unix name for your project
+RUBYFORGE_PROJECT = "hpricot-scrub" # The unix name for your project
 HOMEPATH = "http://trac.underpantsgnome.com/hpricot_scrub/"
 
-
 NAME = "hpricot_scrub"
 REV = nil # UNCOMMENT IF REQUIRED: File.read(".svn/entries")[/committed-rev="(d+)"/, 1] rescue nil
 VERS = ENV['VERSION'] || (HpricotScrub::VERSION::STRING + (REV ? ".#{REV}" : ""))

data/lib/hpricot_scrub/version.rb

@@ -1,7 +1,7 @@
 module HpricotScrub #:nodoc:
   module VERSION #:nodoc:
     MAJOR = 0
-    MINOR = 1
+    MINOR = 2
     TINY  = 0
 
     STRING = [MAJOR, MINOR, TINY].join('.')

data/lib/hpricot_scrub.rb

@@ -1 +1 @@
-Dir[File.join(File.dirname(__FILE__), 'hpricot_scrub/**/*.rb')].sort.each { |lib| require lib }
+Dir[File.join(File.dirname(__FILE__), 'hpricot_scrub/**/*.rb')].sort.each { |lib| require lib }

data/test/hpricot_scrub_test.rb

@@ -4,15 +4,42 @@ require File.dirname(__FILE__) + '/scrubber_data.rb'
 class HpricotScrubTest < Test::Unit::TestCase
 
   def setup
+    @clean = Hpricot(MARKUP).scrub.inner_html
+    @config = YAML.load_file('examples/config.yml')
   end
-  
+
   def test_full_scrub
-    # using the divisor search throws warnings in test
     doc = Hpricot(MARKUP).scrub
-    assert doc.search('//a').size == 0 
-    assert doc.search('//p').size == 0 
-    assert doc.search('//img').size == 0 
-    assert doc.search('//br').size == 0 
-    assert doc.search('//script').size == 0 
+    # using the divisor search throws warnings in test
+    assert_tag_count(doc, 'a', 0)
+    assert_tag_count(doc, 'p', 0)
+    assert_tag_count(doc, 'img', 0)
+    assert_tag_count(doc, 'br', 0)
+    assert_tag_count(doc, 'div', 0)
+    assert_tag_count(doc, 'script', 0)
+  end
+
+  def test_partial_scrub
+    full = Hpricot(MARKUP)
+    doc = Hpricot(MARKUP).scrub(@config)
+    # using the divisor search throws warnings in test
+    assert_tag_count(doc, 'a', 0)
+    assert_tag_count(doc, 'p', full.search('//p').size)
+    assert_tag_count(doc, 'div', full.search('//div').size)
+    assert_tag_count(doc, 'img', full.search('//img').size)
+    assert_tag_count(doc, 'br', full.search('//br').size)
+    assert_tag_count(doc, 'script', 0)
+  end
+
+  def test_string_scrub
+    formatted = MARKUP
+    assert formatted.scrub == @clean
+    assert formatted == MARKUP
+  end
+  
+  def test_string_scrub!
+    formatted = MARKUP
+    assert formatted.scrub! == @clean
+    assert formatted == @clean
   end
 end

data/test/scrubber_data.rb

@@ -4,9 +4,11 @@ MARKUP = <<-EOS
 <p>Still more junk <u>here</u>... </p>
 <p><img title="nothing to see here" alt="nothing to see here" mce_src="http://example.com/imgtest.png" src="http://example.com/imgtest.png" align="middle" border="1" height="240" hspace="5" vspace="5" width="320">&nbsp;</p>
 <p>&nbsp;And a <a title="Just a link" target="_blank" mce_href="http://example.com/nothing.html" href="http://example.com/nothing.html">link</a> just because</p>
+<p><div>some stuff in here</div><img title="nothing to see here" alt="nothing to see here" mce_src="http://example.com/imgtest.png" src="http://example.com/imgtest.png" align="middle" border="1" height="240" hspace="5" vspace="5" width="320"></p>
 <a name="junk"></a>
-<script type="text/javascript">//nasty bits go here
+<p><script type="text/javascript">//nasty bits go here
 alert("gotcha");</script><img src="http://content.example.com/content/3587a2f6ee641074fec4e7534c01655326c218ec">how about an <a href="javascript:alert('gotcha')">inline script</a>
+</p>
 <span>some random unclosed span
 <style type="text/css">.foo {color:blue}</style>
 EOS

data/test/test_helper.rb

@@ -1,2 +1,8 @@
 require 'test/unit'
 require File.dirname(__FILE__) + '/../lib/hpricot_scrub'
+
+def assert_tag_count(doc, tag, expected)
+  found = doc.search("//#{tag}").size
+  assert found == expected,
+    "Expected to find #{expected} '#{tag}' tag(s), found #{found}"
+end

metadata

@@ -3,14 +3,14 @@ rubygems_version: 0.9.1
 specification_version: 1
 name: hpricot_scrub
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
+  version: 0.2.0
 date: 2007-03-04 00:00:00 -08:00
 summary: Scrub HTML with Hpricot
 require_paths: 
 - lib
 email: michael@underpantsgnome.com
 homepage: http://trac.underpantsgnome.com/hpricot_scrub/
-rubyforge_project: hpricot_scrub
+rubyforge_project: hpricot-scrub
 description: Scrub HTML with Hpricot
 autorequire: 
 default_executable: