hpricot_scrub 0.1.0

data/Manifest.txt

@@ -0,0 +1,11 @@
+Rakefile
+README.txt
+CHANGELOG.txt
+Manifest.txt
+setup.rb
+lib/hpricot_scrub/version.rb
+lib/hpricot_scrub.rb
+test/test_helper.rb
+test/scrubber_data.rb
+test/hpricot_scrub_test.rb
+examples/config.yml

data/README.txt

@@ -0,0 +1,12 @@
+README for hpricot_scrub
+========================
+
+HpricotScrub is a wrapper around Hpricot that allows you to easily scrub HTML
+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.
+

data/Rakefile

@@ -0,0 +1,54 @@
+require 'rubygems'
+require 'rake'
+require 'rake/clean'
+require 'rake/testtask'
+require 'rake/packagetask'
+require 'rake/gempackagetask'
+require 'rake/rdoctask'
+require 'rake/contrib/rubyforgepublisher'
+require 'fileutils'
+require 'hoe'
+include FileUtils
+require File.join(File.dirname(__FILE__), 'lib', 'hpricot_scrub', 'version')
+
+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
+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}" : ""))
+                          CLEAN.include ['**/.*.sw?', '*.gem', '.config']
+RDOC_OPTS = ['--quiet', '--title', "hpricot_scrub documentation",
+    "--opname", "index.html",
+    "--line-numbers", 
+    "--main", "README",
+    "--inline-source"]
+
+class Hoe
+  def extra_deps 
+    @extra_deps.reject { |x| Array(x).first == 'hoe' } 
+  end 
+end
+
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+hoe = Hoe.new(GEM_NAME, VERS) do |p|
+  p.author = AUTHOR 
+  p.description = DESCRIPTION
+  p.email = EMAIL
+  p.summary = DESCRIPTION
+  p.url = HOMEPATH
+  p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
+  p.test_globs = ["test/**/*_test.rb"]
+  p.clean_globs = CLEAN  #An array of file patterns to delete on clean.
+  
+  # == Optional
+  #p.changes        - A description of the release's latest changes.
+  p.extra_deps = ['hpricot', '>= 0.5']
+  #p.spec_extras    - A hash of extra values to set in the gemspec.
+end

data/examples/config.yml

@@ -0,0 +1,47 @@
+
+---
+    :allow_tags: # let these tags stay, but will strip attributes
+        - 'b'
+        - 'blockquote'
+        - 'br'
+        - 'div'
+        - 'h1'
+        - 'h2'
+        - 'h3'
+        - 'h4'
+        - 'h5'
+        - 'h6'
+        - 'hr'
+        - 'i'
+        - 'em'
+        - 'img'
+        - 'li'
+        - 'ol'
+        - 'p'
+        - 'pre'
+        - 'small'
+        - 'span'
+        - 'span'
+        - 'strike'
+        - 'strong'
+        - 'sub'
+        - 'sup'
+        - 'table'
+        - 'tbody'
+        - 'td'
+        - 'tfoot'
+        - 'thead'
+        - 'tr'
+        - 'u'
+        - 'ul'
+
+    :remove_tags: # completely removes everything between open and close tag
+        - 'form'
+        - 'script'
+        
+    :allow_attributes: # let these attributes stay, strip all others
+        - 'src'
+        - 'font'
+        - 'alt'
+        - 'style'
+        - 'align'

data/lib/hpricot_scrub/version.rb

@@ -0,0 +1,9 @@
+module HpricotScrub #:nodoc:
+  module VERSION #:nodoc:
+    MAJOR = 0
+    MINOR = 1
+    TINY  = 0
+
+    STRING = [MAJOR, MINOR, TINY].join('.')
+  end
+end

data/lib/hpricot_scrub.rb

@@ -0,0 +1 @@
+Dir[File.join(File.dirname(__FILE__), 'hpricot_scrub/**/*.rb')].sort.each { |lib| require lib }