premailer 1.7.3 → 1.7.8

data/lib/premailer/executor.rb

@@ -44,6 +44,10 @@ opts = OptionParser.new do |opts|
     options[:remove_classes] = v
   end
 
+  opts.on("-j", "--remove-scripts", "Remove <script> elements") do |v|
+    options[:remove_classes] = v
+  end
+
   opts.on("-l", "--line-length N", Integer, "Line length for plaintext (default: #{options[:line_length].to_s})") do |v|
     options[:line_length] = v
   end

data/lib/premailer/html_to_plain_text.rb

@@ -13,21 +13,37 @@ module HtmlToPlainText
     # decode HTML entities
     he = HTMLEntities.new
     txt = he.decode(txt)
-    
-    # replace image by their alt attribute
-    txt.gsub!(/<img.+?alt=\"([^\"]*)\"[^>]*\/>/i, '\1')
 
-    # replace image by their alt attribute
-    txt.gsub!(/<img.+?alt=\"([^\"]*)\"[^>]*\/>/i, '\1')
-    txt.gsub!(/<img.+?alt='([^\']*)\'[^>]*\/>/i, '\1')
+    # replace images with their alt attributes
+    # for img tags with "" for attribute quotes
+    # with or without closing tag
+    # eg. the following formats:
+    # <img alt="" />
+    # <img alt="">
+    txt.gsub!(/<img.+?alt=\"([^\"]*)\"[^>]*\>/i, '\1')
+
+    # for img tags with '' for attribute quotes
+    # with or without closing tag
+    # eg. the following formats:
+    # <img alt='' />
+    # <img alt=''>
+    txt.gsub!(/<img.+?alt=\'([^\']*)\'[^>]*\>/i, '\1')
 
     # links
-    txt.gsub!(/<a.+?href=\"([^\"]*)\"[^>]*>(.+?)<\/a>/i) do |s|
-      $2.strip + ' ( ' + $1.strip + ' )'
+    txt.gsub!(/<a.+?href=\"(mailto:)?([^\"]*)\"[^>]*>((.|\s)*?)<\/a>/i) do |s|
+      if $3.empty?
+        ''
+      else
+        $3.strip + ' ( ' + $2.strip + ' )'
+      end
     end
 
-    txt.gsub!(/<a.+?href='([^\']*)\'[^>]*>(.+?)<\/a>/i) do |s|
-      $2.strip + ' ( ' + $1.strip + ' )'
+    txt.gsub!(/<a.+?href='(mailto:)?([^\']*)\'[^>]*>((.|\s)*?)<\/a>/i) do |s|
+      if $3.empty?
+        ''
+      else
+        $3.strip + ' ( ' + $2.strip + ' )'
+      end
     end
 
 
@@ -73,7 +89,7 @@ module HtmlToPlainText
     txt.gsub!(/<\/?[^>]*>/, '')
 
     txt = word_wrap(txt, line_length)
-    
+
     # remove linefeeds (\r\n and \r -> \n)
     txt.gsub!(/\r\n?/, "\n")
 
@@ -87,7 +103,7 @@ module HtmlToPlainText
 
     # no more than two consecutive spaces
     txt.gsub!(/ {2,}/, " ")
-    
+
     # the word messes up the parens
     txt.gsub!(/\([ \n](http[^)]+)[\n ]\)/) do |s|
       "( " + $1 + " )"

data/lib/premailer/premailer.rb

@@ -1,47 +1,88 @@
-# Premailer by Alex Dunae (dunae.ca, e-mail 'code' at the same domain), 2008-10
-#
 # Premailer processes HTML and CSS to improve e-mail deliverability.
 #
 # Premailer's main function is to render all CSS as inline <tt>style</tt>
 # attributes. It also converts relative links to absolute links and checks
 # the 'safety' of CSS properties against a CSS support chart.
 #
-# = Example
-#  premailer = Premailer.new('http://example.com/myfile.html', :warn_level => Premailer::Warnings::SAFE)
+# ## Example of use
+#
+# ```ruby
+# premailer = Premailer.new('http://example.com/myfile.html', :warn_level => Premailer::Warnings::SAFE)
+#
+# # Write the HTML output
+# fout = File.open("output.html", "w")
+# fout.puts premailer.to_inline_css
+# fout.close
 #
-#  # Write the HTML output
-#  fout = File.open("output.html", "w")
-#  fout.puts premailer.to_inline_css
-#  fout.close
+# # Write the plain-text output
+# fout = File.open("ouput.txt", "w")
+# fout.puts premailer.to_plain_text
+# fout.close
 #
-#  # Write the plain-text output
-#  fout = File.open("ouput.txt", "w")
-#  fout.puts premailer.to_plain_text
-#  fout.close
+# # List any CSS warnings
+# puts premailer.warnings.length.to_s + ' warnings found'
+# premailer.warnings.each do |w|
+#   puts "#{w[:message]} (#{w[:level]}) may not render properly in #{w[:clients]}"
+# end
 #
-#  # List any CSS warnings
-#  puts premailer.warnings.length.to_s + ' warnings found'
-#  premailer.warnings.each do |w|
-#    puts "#{w[:message]} (#{w[:level]}) may not render properly in #{w[:clients]}"
-#  end
+# premailer = Premailer.new(html_file, :warn_level => Premailer::Warnings::SAFE)
+# puts premailer.to_inline_css
+# ```
 #
-#  premailer = Premailer.new(html_file, :warn_level => Premailer::Warnings::SAFE)
-#  puts premailer.to_inline_css
+require 'premailer/version'
+
 class Premailer
   include HtmlToPlainText
   include CssParser
 
-  VERSION = '1.7.3'
-
   CLIENT_SUPPORT_FILE = File.dirname(__FILE__) + '/../../misc/client_support.yaml'
 
+  # Unmergable selectors regexp.
   RE_UNMERGABLE_SELECTORS = /(\:(visited|active|hover|focus|after|before|selection|target|first\-(line|letter))|^\@)/i
+  # Reset selectors regexp.
   RE_RESET_SELECTORS = /^(\:\#outlook|body.*|\.ReadMsgBody|\.ExternalClass|img|\#backgroundTable)$/
 
+  # list of HTMLEntities to fix
+  # source: http://stackoverflow.com/questions/2812781/how-to-convert-webpage-apostrophe-8217-to-ascii-39-in-ruby-1-
+  HTML_ENTITIES = {
+    "1.8" => {
+      "\342\200\231" => "'",
+      "\342\200\246" => "...",
+      "\342\200\176" => "'",
+      "\342\200\177" => "'",
+      "\342\200\230" => "'",
+      "\342\200\231" => "'",
+      "\342\200\232" => ',',
+      "\342\200\233" => "'",
+      "\342\200\234" => '"',
+      "\342\200\235" => '"',
+      "\342\200\041" => '-',
+      "\342\200\174" => '-',
+      "\342\200\220" => '-',
+      "\342\200\223" => '-',
+      "\342\200\224" => '--',
+      "\342\200\225" => '--',
+      "\342\200\042" => '--'
+    },
+    "1.9" => {
+      "&#8217;" => "'",
+      "&#8230;" => "...",
+      "&#8216;" => "'",
+      "&#8218;" => ',',
+      "&#8219;" => "'",
+      "&#8220;" => '"',
+      "&#8221;" => '"',
+      "&#8208;" => '-',
+      "&#8211;" => '-',
+      "&#8212;" => '--',
+      "&#8213;" => '--'
+    }
+  }
+
   # list of CSS attributes that can be rendered as HTML attributes
   #
-  # TODO: too much repetition
-  # TODO: background=""
+  # @todo too much repetition
+  # @todo background=""
   RELATED_ATTRIBUTES = {
     'h1' => {'text-align' => 'align'},
     'h2' => {'text-align' => 'align'},
@@ -55,6 +96,7 @@ class Premailer
     'body' => {'background-color' => 'bgcolor'},
     'table' => {
       'background-color' => 'bgcolor',
+      'background-image' => 'background',
       '-premailer-width' => 'width',
       '-premailer-height' => 'height',
       '-premailer-cellpadding' => 'cellpadding',
@@ -77,8 +119,7 @@ class Premailer
       'background-color' => 'bgcolor',
       'vertical-align' => 'valign',
       '-premailer-width' => 'width',
-      '-premailer-height' => 'height',
-      '-premailer-colspan' => 'colspan'
+      '-premailer-height' => 'height'
     },
     'img' => {'float' => 'align'}
   }
@@ -90,6 +131,7 @@ class Premailer
   attr_reader   :base_url
 
   # base directory used to resolve links for local files
+  # @return [String] base directory
   attr_reader   :base_dir
 
   # unmergeable CSS rules to be preserved in the head (CssParser)
@@ -101,38 +143,49 @@ class Premailer
   # source HTML document (Hpricot/Nokogiri)
   attr_reader   :doc
 
+  # Warning levels
   module Warnings
+    # No warnings
     NONE = 0
+    # Safe
     SAFE = 1
+    # Poor
     POOR = 2
+    # Risky
     RISKY = 3
   end
   include Warnings
 
+  # Waning level names
   WARN_LABEL = %w(NONE SAFE POOR RISKY)
 
   # Create a new Premailer object.
   #
-  # +html+ is the HTML data to process. It can be either an IO object, the URL of a
-  # remote file, a local path or a raw HTML string.  If passing an HTML string you
-  # must set the +:with_html_string+ option to +true+.
+  # @param html is the HTML data to process. It can be either an IO object, the URL of a
+  #   remote file, a local path or a raw HTML string.  If passing an HTML string you
+  #   must set the with_html_string option to true.
   #
-  # ==== Options
-  # [+line_length+] Line length used by to_plain_text. Boolean, default is 65.
-  # [+warn_level+] What level of CSS compatibility warnings to show (see Warnings).
-  # [+link_query_string+] A string to append to every <tt>a href=""</tt> link. Do not include the initial <tt>?</tt>.
-  # [+base_url+] Used to calculate absolute URLs for local files.
-  # [+css+] Manually specify CSS stylesheets.
-  # [+css_to_attributes+] Copy related CSS attributes into HTML attributes (e.g. +background-color+ to +bgcolor+)
-  # [+css_string+] Pass CSS as a string
-  # [+remove_ids+] Remove ID attributes whenever possible and convert IDs used as anchors to hashed to avoid collisions in webmail programs.  Default is +false+.
-  # [+remove_classes+] Remove class attributes. Default is +false+.
-  # [+remove_comments+] Remove html comments. Default is +false+.
-  # [+preserve_styles+] Whether to preserve any <tt>link rel=stylesheet</tt> and <tt>style</tt> elements.  Default is +false+.
-  # [+preserve_reset+] Whether to preserve styles associated with the MailChimp reset code
-  # [+with_html_string+] Whether the +html+ param should be treated as a raw string.
-  # [+verbose+] Whether to print errors and warnings to <tt>$stderr</tt>.  Default is +false+.
-  # [+adapter+] Which HTML parser to use, either <tt>:nokogiri</tt> or <tt>:hpricot</tt>.  Default is <tt>:hpricot</tt>.
+  # @param [Hash] options the options to handle html with.
+  # @option options [FixNum] :line_length Line length used by to_plain_text. Default is 65.
+  # @option options [FixNum] :warn_level What level of CSS compatibility warnings to show (see {Premailer::Warnings}).
+  # @option options [String] :link_query_string A string to append to every <tt>a href=""</tt> link. Do not include the initial <tt>?</tt>.
+  # @option options [String] :base_url Used to calculate absolute URLs for local files.
+  # @option options [Array(String)] :css Manually specify CSS stylesheets.
+  # @option options [Boolean] :css_to_attributes Copy related CSS attributes into HTML attributes (e.g. background-color to bgcolor)
+  # @option options [String] :css_string Pass CSS as a string
+  # @option options [Boolean] :remove_ids Remove ID attributes whenever possible and convert IDs used as anchors to hashed to avoid collisions in webmail programs.  Default is false.
+  # @option options [Boolean] :remove_classes Remove class attributes. Default is false.
+  # @option options [Boolean] :remove_comments Remove html comments. Default is false.
+  # @option options [Boolean] :remove_scripts Remove <tt>script</tt> elements. Default is true.
+  # @option options [Boolean] :preserve_styles Whether to preserve any <tt>link rel=stylesheet</tt> and <tt>style</tt> elements.  Default is false.
+  # @option options [Boolean] :preserve_reset Whether to preserve styles associated with the MailChimp reset code.
+  # @option options [Boolean] :with_html_string Whether the html param should be treated as a raw string.
+  # @option options [Boolean] :verbose Whether to print errors and warnings to <tt>$stderr</tt>.  Default is false.
+  # @option options [Boolean] :include_link_tags Whether to include css from <tt>link rel=stylesheet</tt> tags.  Default is true.
+  # @option options [Boolean] :include_style_tags Whether to include css from <tt>style</tt> tags.  Default is true.
+  # @option options [String] :input_encoding Manually specify the source documents encoding. This is a good idea.
+  # @option options [Boolean] :replace_html_entities Convert HTML entities to actual characters. Default is false.
+  # @option options [Symbol] :adapter Which HTML parser to use, either <tt>:nokogiri</tt> or <tt>:hpricot</tt>.  Default is <tt>:hpricot</tt>.
   def initialize(html, options = {})
     @options = {:warn_level => Warnings::SAFE,
                 :line_length => 65,
@@ -141,6 +194,7 @@ class Premailer
                 :remove_classes => false,
                 :remove_ids => false,
                 :remove_comments => false,
+                :remove_scripts => true,
                 :css => [],
                 :css_to_attributes => true,
                 :with_html_string => false,
@@ -150,7 +204,12 @@ class Premailer
                 :verbose => false,
                 :debug => false,
                 :io_exceptions => false,
-                :adapter => Adapter.use}.merge(options)
+                :include_link_tags => true,
+                :include_style_tags => true,
+                :input_encoding => 'ASCII-8BIT',
+                :replace_html_entities => false,
+                :adapter => Adapter.use,
+                }.merge(options)
 
     @html_file = html
     @is_local_file = @options[:with_html_string] || Premailer.local_data?(html)
@@ -190,7 +249,8 @@ class Premailer
     load_css_from_html!
   end
 
-  # Array containing a hash of CSS warnings.
+  # CSS warnings.
+  # @return [Array(Hash)] Array of warnings.
   def warnings
     return [] if @options[:warn_level] == Warnings::NONE
     @css_warnings = check_client_support if @css_warnings.empty?
@@ -200,6 +260,7 @@ class Premailer
 protected
   def load_css_from_local_file!(path)
     css_block = ''
+    path.gsub!(/\Afile:/, '')
     begin
       File.open(path, "r") do |file|
         while line = file.gets
@@ -215,6 +276,7 @@ protected
     @css_parser.add_block!(css_string, {:base_uri => @base_url, :base_dir => @base_dir, :only_media_types => [:screen, :handheld]})
   end
 
+  # @private
   def load_css_from_options! # :nodoc:
     load_css_from_string(@options[:css_string]) if @options[:css_string]
 
@@ -229,21 +291,26 @@ protected
 
     # Load CSS included in <tt>style</tt> and <tt>link</tt> tags from an HTML document.
   def load_css_from_html! # :nodoc:
-    if tags = @doc.search("link[@rel='stylesheet'], style")
+    if (@options[:adapter] == :nokogiri)
+      tags = @doc.search("link[@rel='stylesheet']", "//style[not(contains(@data-premailer,'ignore'))]")
+    else
+      tags = @doc.search("link[@rel='stylesheet'], style:not([@data-premailer='ignore'])")
+    end
+    if tags
       tags.each do |tag|
-        if tag.to_s.strip =~ /^\<link/i && tag.attributes['href'] && media_type_ok?(tag.attributes['media'])
+        if tag.to_s.strip =~ /^\<link/i && tag.attributes['href'] && media_type_ok?(tag.attributes['media']) && @options[:include_link_tags]
           # A user might want to <link /> to a local css file that is also mirrored on the site
           # but the local one is different (e.g. newer) than the live file, premailer will now choose the local file
-          
+
           if tag.attributes['href'].to_s.include? @base_url.to_s and @html_file.kind_of?(String)
             link_uri = File.join(File.dirname(@html_file), tag.attributes['href'].to_s.sub!(@base_url.to_s, ''))
           end
-          
+
           # if the file does not exist locally, try to grab the remote reference
           if link_uri.nil? or not File.exists?(link_uri)
             link_uri = Premailer.resolve_link(tag.attributes['href'].to_s, @html_file)
           end
-          
+
           if Premailer.local_data?(link_uri)
             $stderr.puts "Loading css from local file: " + link_uri if @options[:verbose]
             load_css_from_local_file!(link_uri)
@@ -252,7 +319,7 @@ protected
             @css_parser.load_uri!(link_uri, {:only_media_types => [:screen, :handheld]})
           end
 
-        elsif tag.to_s.strip =~ /^\<style/i
+        elsif tag.to_s.strip =~ /^\<style/i && @options[:include_style_tags]
           @css_parser.add_block!(tag.inner_html, :base_uri => @base_url, :base_dir => @base_dir, :only_media_types => [:screen, :handheld])
         end
       end
@@ -264,6 +331,8 @@ protected
 
 # here be deprecated methods
 public
+  # @private
+  # @deprecated
   def local_uri?(uri) # :nodoc:
     warn "[DEPRECATION] `local_uri?` is deprecated.  Please use `Premailer.local_data?` instead."
     Premailer.local_data?(uri)
@@ -271,11 +340,11 @@ public
 
 # here be instance methods
 
-  def media_type_ok?(media_types) # :nodoc:
+  # @private
+  def media_type_ok?(media_types)
+    media_types = media_types.to_s
     return true if media_types.nil? or media_types.empty?
     media_types.split(/[\s]+|,/).any? { |media_type| media_type.strip =~ /screen|handheld|all/i }
-  rescue
-    true
   end
 
   def append_query_string(doc, qs)
@@ -295,7 +364,7 @@ public
     doc.search('a').each do|el|
       href = el.attributes['href'].to_s.strip
       next if href.nil? or href.empty?
-      
+
       next if href[0,1] =~ /[\#\{\[\<\%]/ # don't bother with anchors or special-looking links
 
       begin
@@ -327,7 +396,7 @@ public
     doc
   end
 
-    # Check for an XHTML doctype
+  # Check for an XHTML doctype
   def is_xhtml?
     intro = @doc.to_html.strip.split("\n")[0..2].join(' ')
     is_xhtml = !!(intro =~ /w3c\/\/[\s]*dtd[\s]+xhtml/i)
@@ -335,7 +404,7 @@ public
     is_xhtml
   end
 
-    # Convert relative links to absolute links.
+  # Convert relative links to absolute links.
   #
   # Processes <tt>href</tt> <tt>src</tt> and <tt>background</tt> attributes
   # as well as CSS <tt>url()</tt> declarations found in inline <tt>style</tt> attributes.
@@ -356,7 +425,7 @@ public
       tags.each do |tag|
         # skip links that look like they have merge tags
         # and mailto, ftp, etc...
-        if tag.attributes[attribute].to_s =~ /^([\%\<\{\#\[]|data:|tel:|file:|sms:|callto:|facetime:|mailto:|ftp:|gopher:)/i
+        if tag.attributes[attribute].to_s =~ /^([\%\<\{\#\[]|data:|tel:|file:|sms:|callto:|facetime:|mailto:|ftp:|gopher:|cid:)/i
           next
         end
 
@@ -387,20 +456,22 @@ public
   end
 
 
+  # @private
   def self.escape_string(str) # :nodoc:
     str.gsub(/"/ , "'")
   end
 
+  # @private
   def self.resolve_link(path, base_path) # :nodoc:
     path.strip!
     resolved = nil
-    if path =~ /(http[s]?|ftp):\/\//i
+    if path =~ /\A(?:(https?|ftp|file):)\/\//i
       resolved = path
       Premailer.canonicalize(resolved)
     elsif base_path.kind_of?(URI)
       resolved = base_path.merge(path)
       Premailer.canonicalize(resolved)
-    elsif base_path.kind_of?(String) and base_path =~ /^(http[s]?|ftp):\/\//i
+    elsif base_path.kind_of?(String) and base_path =~ /\A(?:(?:https?|ftp|file):)\/\//i
       resolved = URI.parse(base_path)
       resolved = resolved.merge(path)
       Premailer.canonicalize(resolved)
@@ -413,8 +484,9 @@ public
   #
   # IO objects return true, as do strings that look like URLs.
   def self.local_data?(data)
-    return true if data.is_a?(IO) || data.is_a?(StringIO)
-    return false if data =~ /^(http|https|ftp)\:\/\//i
+    return true   if data.is_a?(IO) || data.is_a?(StringIO)
+    return true   if data =~ /\Afile:\/\//i
+    return false  if data =~ /\A(?:(https?|ftp):)\/\//i
     true
   end