marcosinger-css_parser 1.3.0

data/lib/css_parser.rb

@@ -0,0 +1,162 @@
+require 'uri'
+require 'net/https'
+require 'open-uri'
+require 'digest/md5'
+require 'zlib'
+require 'stringio'
+require 'iconv'
+
+module CssParser
+  VERSION = '1.2.0'
+
+  # Merge multiple CSS RuleSets by cascading according to the CSS 2.1 cascading rules 
+  # (http://www.w3.org/TR/REC-CSS2/cascade.html#cascading-order).
+  #
+  # Takes one or more RuleSet objects.
+  #
+  # Returns a RuleSet.
+  #
+  # ==== Cascading
+  # If a RuleSet object has its +specificity+ defined, that specificity is 
+  # used in the cascade calculations.  
+  #
+  # If no specificity is explicitly set and the RuleSet has *one* selector, 
+  # the specificity is calculated using that selector.
+  #
+  # If no selectors or multiple selectors are present, the specificity is 
+  # treated as 0.
+  #
+  # ==== Example #1
+  #   rs1 = RuleSet.new(nil, 'color: black;')
+  #   rs2 = RuleSet.new(nil, 'margin: 0px;')
+  #
+  #   merged = CssParser.merge(rs1, rs2)
+  #
+  #   puts merged
+  #   => "{ margin: 0px; color: black; }"
+  #
+  # ==== Example #2
+  #   rs1 = RuleSet.new(nil, 'background-color: black;')
+  #   rs2 = RuleSet.new(nil, 'background-image: none;')
+  #
+  #   merged = CssParser.merge(rs1, rs2)
+  #
+  #   puts merged
+  #   => "{ background: none black; }"
+  #--
+  # TODO: declaration_hashes should be able to contain a RuleSet
+  #       this should be a Class method
+  def CssParser.merge(*rule_sets)
+    @folded_declaration_cache = {}
+
+    # in case called like CssParser.merge([rule_set, rule_set])
+    rule_sets.flatten! if rule_sets[0].kind_of?(Array)
+    
+    unless rule_sets.all? {|rs| rs.kind_of?(CssParser::RuleSet)}
+      raise ArgumentError, "all parameters must be CssParser::RuleSets."
+    end
+
+    return rule_sets[0] if rule_sets.length == 1
+
+    # Internal storage of CSS properties that we will keep
+    properties = {}
+
+    rule_sets.each do |rule_set|
+      rule_set.expand_shorthand!
+      
+      specificity = rule_set.specificity
+      unless specificity
+        if rule_set.selectors.length == 1
+          specificity = calculate_specificity(rule_set.selectors[0])
+        else
+          specificity = 0
+        end
+      end
+
+      rule_set.each_declaration do |property, value, is_important|
+        # Add the property to the list to be folded per http://www.w3.org/TR/CSS21/cascade.html#cascading-order
+        if not properties.has_key?(property)
+          properties[property] = {:value => value, :specificity => specificity, :is_important => is_important}
+        elsif properties[property][:specificity] < specificity or properties[property][:specificity] == specificity
+          unless properties[property][:is_important]
+            properties[property] = {:value => value, :specificity => specificity, :is_important => is_important}            
+          end
+        end
+
+        if is_important
+            properties[property] = {:value => value, :specificity => specificity, :is_important => is_important}            
+        end        
+      end
+    end
+
+    merged = RuleSet.new(nil, nil)
+
+    properties.each do |property, details|
+      if details[:is_important]
+        merged[property.strip] = details[:value].strip.gsub(/\;\Z/, '') + '!important' 
+      else
+        merged[property.strip] = details[:value].strip
+      end
+    end
+
+    merged.create_shorthand!
+    merged
+  end
+
+  # Calculates the specificity of a CSS selector
+  # per http://www.w3.org/TR/CSS21/cascade.html#specificity
+  #
+  # Returns an integer.
+  #
+  # ==== Example
+  #  CssParser.calculate_specificity('#content div p:first-line a:link')
+  #  => 114
+  #--
+  # Thanks to Rafael Salazar and Nick Fitzsimons on the css-discuss list for their help.
+  #++
+  def CssParser.calculate_specificity(selector)
+    a = 0
+    b = selector.scan(/\#/).length
+    c = selector.scan(NON_ID_ATTRIBUTES_AND_PSEUDO_CLASSES_RX).length
+    d = selector.scan(ELEMENTS_AND_PSEUDO_ELEMENTS_RX).length
+
+    (a.to_s + b.to_s + c.to_s + d.to_s).to_i
+  rescue
+    return 0
+  end
+
+  # Make <tt>url()</tt> links absolute.
+  #
+  # Takes a block of CSS and returns it with all relative URIs converted to absolute URIs.
+  #
+  # "For CSS style sheets, the base URI is that of the style sheet, not that of the source document."
+  # per http://www.w3.org/TR/CSS21/syndata.html#uri
+  #
+  # Returns a string.
+  #
+  # ==== Example
+  #  CssParser.convert_uris("body { background: url('../style/yellow.png?abc=123') };", 
+  #               "http://example.org/style/basic.css").inspect
+  #  => "body { background: url('http://example.org/style/yellow.png?abc=123') };"
+  def self.convert_uris(css, base_uri)
+    out = ''
+    base_uri = URI.parse(base_uri) unless base_uri.kind_of?(URI)
+
+    out = css.gsub(URI_RX) do |s|
+      uri = $1.to_s
+      uri.gsub!(/["']+/, '')
+      # Don't process URLs that are already absolute
+      unless uri =~ /^[a-z]+\:\/\//i
+        begin
+          uri = base_uri.merge(uri) 
+        rescue; end
+      end
+      "url('" + uri.to_s + "')"
+    end
+    out
+  end
+end
+
+require File.dirname(__FILE__) + '/css_parser/rule_set'
+require File.dirname(__FILE__) + '/css_parser/regexps'
+require File.dirname(__FILE__) + '/css_parser/parser'

data/lib/css_parser/parser.rb

@@ -0,0 +1,454 @@
+module CssParser
+  # Exception class used for any errors encountered while downloading remote files.
+  class RemoteFileError < IOError; end
+
+  # Exception class used if a request is made to load a CSS file more than once.
+  class CircularReferenceError < StandardError; end
+
+
+  # == Parser class
+  #
+  # All CSS is converted to UTF-8.
+  #
+  # When calling Parser#new there are some configuaration options:
+  # [<tt>absolute_paths</tt>] Convert relative paths to absolute paths (<tt>href</tt>, <tt>src</tt> and <tt>url('')</tt>. Boolean, default is <tt>false</tt>.
+  # [<tt>import</tt>] Follow <tt>@import</tt> rules. Boolean, default is <tt>true</tt>.
+  # [<tt>io_exceptions</tt>] Throw an exception if a link can not be found. Boolean, default is <tt>true</tt>.
+  class Parser
+    USER_AGENT   = "Ruby CSS Parser/#{CssParser::VERSION} (http://github.com/alexdunae/css_parser)"
+
+    STRIP_CSS_COMMENTS_RX = /\/\*.*?\*\//m
+    STRIP_HTML_COMMENTS_RX = /\<\!\-\-|\-\-\>/m
+
+    # Initial parsing
+    RE_AT_IMPORT_RULE = /\@import\s*(?:url\s*)?(?:\()?(?:\s*)["']?([^'"\s\)]*)["']?\)?([\w\s\,^\])]*)\)?[;\n]?/
+
+     # Array of CSS files that have been loaded.
+    attr_reader   :loaded_uris
+
+    #attr_reader   :rules
+
+    #--
+    # Class variable? see http://www.oreillynet.com/ruby/blog/2007/01/nubygems_dont_use_class_variab_1.html
+    #++
+    @folded_declaration_cache = {}
+    class << self; attr_reader :folded_declaration_cache; end
+
+    def initialize(options = {})
+      @options = {:absolute_paths => false,
+                  :import => true,
+                  :io_exceptions => true}.merge(options)
+
+      # array of RuleSets
+      @rules = []
+    
+      
+      @loaded_uris = []
+    
+      # unprocessed blocks of CSS
+      @blocks = []
+      reset!
+    end
+
+    # Get declarations by selector.
+    #
+    # +media_types+ are optional, and can be a symbol or an array of symbols.
+    # The default value is <tt>:all</tt>.
+    #
+    # ==== Examples
+    #  find_by_selector('#content')
+    #  => 'font-size: 13px; line-height: 1.2;'
+    #
+    #  find_by_selector('#content', [:screen, :handheld])
+    #  => 'font-size: 13px; line-height: 1.2;'
+    #
+    #  find_by_selector('#content', :print)
+    #  => 'font-size: 11pt; line-height: 1.2;'
+    #
+    # Now you can use Regexp too
+    #
+    # ==== Examples
+    #  find_by_selector('/#content/')
+    #  => 'font-size: 13px; line-height: 1.2;'
+    #
+    #  find_by_selector('/\.content/') # Don't forget use escape with dot(\)
+    #  => 'float:left;'
+    #
+    #  find_by_selector('/content/')
+    #  => {'#content' => {'font-size' => '11pt;', 'line-height' => '1.2;'}, '.content' => {'float' => 'left'}}
+    #
+    # Returns an array or hash of declarations.
+    def find_by_selector(selector, media_types = :all)
+      out       = []
+      out_hash  = {}
+      
+      each_selector(media_types) do |sel, dec, spec|
+        if selector.is_a?(Regexp)
+          dec_hash = {}
+          dec.split(';').map{|x| dec_hash.merge!({x.split(':').first.lstrip => x.split(":").last.lstrip})}
+          out_hash.merge!({sel => dec_hash}){ |key, v1, v2| "#{v1} #{v2}"} if sel.strip =~ selector
+        elsif selector.is_a?(String)
+          out << dec if sel.strip == selector.strip;
+        end        
+      end
+      selector.is_a?(Regexp) ? (out_hash.size < 2 ? out_hash.values : out_hash) : out
+    end
+    alias_method :[], :find_by_selector
+
+
+    # Add a raw block of CSS.
+    #
+    # In order to follow +@import+ rules you must supply either a
+    # +:base_dir+ or +:base_uri+ option.
+    #
+    # Use the +:media_types+ option to set the media type(s) for this block.  Takes an array of symbols.
+    #
+    # Use the +:only_media_types+ option to selectively follow +@import+ rules.  Takes an array of symbols.
+    #
+    # ==== Example
+    #   css = <<-EOT
+    #     body { font-size: 10pt }
+    #     p { margin: 0px; }
+    #     @media screen, print {
+    #       body { line-height: 1.2 }
+    #     }
+    #   EOT
+    #
+    #   parser = CssParser::Parser.new
+    #   parser.add_block!(css)
+    def add_block!(block, options = {})
+      options = {:base_uri => nil, :base_dir => nil, :charset => nil, :media_types => :all, :only_media_types => :all}.merge(options)
+      options[:media_types] = [options[:media_types]].flatten
+      options[:only_media_types] = [options[:only_media_types]].flatten
+
+      block = cleanup_block(block)
+
+      if options[:base_uri] and @options[:absolute_paths]
+        block = CssParser.convert_uris(block, options[:base_uri])
+      end
+
+      # Load @imported CSS
+      block.scan(RE_AT_IMPORT_RULE).each do |import_rule|    
+        media_types = []
+        if media_string = import_rule[-1]
+          media_string.split(/\s|\,/).each do |t|
+            media_types << t.to_sym unless t.empty?
+          end
+        end
+
+        next unless options[:only_media_types].include?(:all) or media_types.length < 1 or (media_types & options[:only_media_types]).length > 0
+
+        import_path = import_rule[0].to_s.gsub(/['"]*/, '').strip
+
+        if options[:base_uri]
+          import_uri = URI.parse(options[:base_uri].to_s).merge(import_path)
+          load_uri!(import_uri, options[:base_uri], media_types)
+        elsif options[:base_dir]
+          load_file!(import_path, options[:base_dir], media_types)
+        end     
+      end
+
+      # Remove @import declarations
+      block.gsub!(RE_AT_IMPORT_RULE, '')
+      
+      parse_block_into_rule_sets!(block, options)
+    end
+
+    # Add a CSS rule by setting the +selectors+, +declarations+ and +media_types+.
+    #
+    # +media_types+ can be a symbol or an array of symbols.
+    def add_rule!(selectors, declarations, media_types = :all)
+      rule_set = RuleSet.new(selectors, declarations)
+      add_rule_set!(rule_set, media_types)
+    end
+
+    # Add a CssParser RuleSet object.
+    #
+    # +media_types+ can be a symbol or an array of symbols.
+    def add_rule_set!(ruleset, media_types = :all)
+      raise ArgumentError unless ruleset.kind_of?(CssParser::RuleSet)
+
+      media_types = [media_types] if media_types.kind_of?(Symbol)
+
+      @rules << {:media_types => media_types, :rules => ruleset}
+    end
+
+    # Iterate through RuleSet objects.
+    #
+    # +media_types+ can be a symbol or an array of symbols.
+    def each_rule_set(media_types = :all) # :yields: rule_set
+      media_types = [:all] if media_types.nil?
+      media_types = [media_types] if media_types.kind_of?(Symbol)
+
+      @rules.each do |block|
+        if media_types.include?(:all) or block[:media_types].any? { |mt| media_types.include?(mt) }
+          yield block[:rules]
+        end
+      end
+    end
+
+    # Iterate through CSS selectors.
+    #
+    # +media_types+ can be a symbol or an array of symbols.
+    # See RuleSet#each_selector for +options+.
+    def each_selector(media_types = :all, options = {}) # :yields: selectors, declarations, specificity
+      each_rule_set(media_types) do |rule_set|
+        #puts rule_set
+        rule_set.each_selector(options) do |selectors, declarations, specificity|
+          yield selectors, declarations, specificity
+        end
+      end
+    end
+
+    # Output all CSS rules as a single stylesheet.
+    def to_s(media_types = :all)
+      out = ''
+      each_selector(media_types) do |selectors, declarations, specificity|
+        out << "#{selectors} {\n#{declarations}\n}\n"
+      end
+      out
+    end
+
+    # Merge declarations with the same selector.
+    def compact! # :nodoc:
+      compacted = []
+
+      compacted
+    end
+
+    def parse_block_into_rule_sets!(block, options = {}) # :nodoc:
+      options = {:media_types => :all}.merge(options)
+      media_types = options[:media_types]
+
+      in_declarations = 0
+
+      block_depth = 0
+
+      # @charset is ignored for now
+      in_charset = false
+      in_string = false
+      in_at_media_rule = false
+
+      current_selectors = ''
+      current_declarations = ''
+
+      block.scan(/([\\]?[{}\s"]|(.[^\s"{}\\]*))/).each do |matches|
+      #block.scan(/((.[^{}"\n\r\f\s]*)[\s]|(.[^{}"\n\r\f]*)\{|(.[^{}"\n\r\f]*)\}|(.[^{}"\n\r\f]*)\"|(.*)[\s]+)/).each do |matches|
+        token = matches[0]
+
+        #puts "TOKEN: #{token}" unless token =~ /^[\s]*$/
+        if token =~ /\A"/ # found un-escaped double quote
+          in_string = !in_string
+        end       
+
+        if in_declarations > 0
+
+          # too deep, malformed declaration block
+          if in_declarations > 1
+            in_declarations -= 1 if token =~ /\}/
+            next
+          end
+          
+          if token =~ /\{/
+            in_declarations += 1
+            next
+          end
+        
+          current_declarations += token
+
+          if token =~ /\}/ and not in_string
+            current_declarations.gsub!(/\}[\s]*$/, '')
+            
+            in_declarations -= 1
+
+            unless current_declarations.strip.empty?
+              #puts "SAVING #{current_selectors} -> #{current_declarations}"
+              add_rule!(current_selectors, current_declarations, media_types)
+            end
+
+            current_selectors = ''
+            current_declarations = ''
+          end
+        elsif token =~ /@media/i
+          # found '@media', reset current media_types
+          in_at_media_rule = true
+          media_types = []
+        elsif in_at_media_rule
+          if token =~ /\{/
+            block_depth = block_depth + 1
+            in_at_media_rule = false
+          else
+            token.gsub!(/[,\s]*/, '')
+            media_types << token.strip.downcase.to_sym unless token.empty?
+          end
+        elsif in_charset or token =~ /@charset/i
+          # iterate until we are out of the charset declaration
+          in_charset = (token =~ /;/ ? false : true)
+        else
+          if token =~ /\}/ and not in_string
+            block_depth = block_depth - 1
+          else
+            if token =~ /\{/ and not in_string
+              current_selectors.gsub!(/^[\s]*/, '')
+              current_selectors.gsub!(/[\s]*$/, '')
+              in_declarations += 1
+            else
+              current_selectors += token
+            end
+          end
+        end
+      end
+
+      # check for unclosed braces          
+      if in_declarations > 0
+        add_rule!(current_selectors, current_declarations, media_types)
+      end        
+    end
+
+    # Load a remote CSS file.
+    #
+    # You can also pass in file://test.css
+    #
+    # See add_block! for options.
+    #
+    # Deprecated: originally accepted three params: `uri`, `base_uri` and `media_types`
+    def load_uri!(uri, options = {}, deprecated = nil)
+      uri = URI.parse(uri) unless uri.respond_to? :scheme
+      #base_uri = nil, media_types = :all, options = {}
+
+      opts = {:base_uri => nil, :media_types => :all}
+
+      if options.is_a? Hash
+        opts.merge!(options)
+      else
+        opts[:base_uri] = options if options.is_a? String
+        opts[:media_types] = deprecated if deprecated
+      end
+      
+      
+      if uri.scheme == 'file' or uri.scheme.nil?
+        uri.path = File.expand_path(uri.path)
+        uri.scheme = 'file'
+      end
+
+      opts[:base_uri] = uri if opts[:base_uri].nil?
+
+      src, charset = read_remote_file(uri)
+
+      if src
+        add_block!(src, opts)
+      end
+    end
+    
+    # Load a local CSS file.
+    def load_file!(file_name, base_dir = nil, media_types = :all)
+      file_name = File.expand_path(file_name, base_dir)
+      return unless File.readable?(file_name)
+
+      src = IO.read(file_name)
+      base_dir = File.dirname(file_name)
+
+      add_block!(src, {:media_types => media_types, :base_dir => base_dir})
+    end
+    
+    
+
+  protected
+    # Strip comments and clean up blank lines from a block of CSS.
+    #
+    # Returns a string.
+    def cleanup_block(block) # :nodoc:
+      # Strip CSS comments
+      block.gsub!(STRIP_CSS_COMMENTS_RX, '')
+
+      # Strip HTML comments - they shouldn't really be in here but 
+      # some people are just crazy...
+      block.gsub!(STRIP_HTML_COMMENTS_RX, '')
+
+      # Strip lines containing just whitespace
+      block.gsub!(/^\s+$/, "")
+
+      block
+    end
+
+    # Download a file into a string.
+    #
+    # Returns the file's data and character set in an array.
+    #--
+    # TODO: add option to fail silently or throw and exception on a 404
+    #++
+    def read_remote_file(uri) # :nodoc:
+      if @loaded_uris.include?(uri.to_s)
+        raise CircularReferenceError, "can't load #{uri.to_s} more than once" if @options[:io_exceptions]
+        return '', nil
+      end
+
+      @loaded_uris << uri.to_s
+
+      src = '', charset = nil
+
+      begin
+        uri = URI.parse(uri.to_s)    
+        http = Net::HTTP.new(uri.host, uri.port)
+
+        if uri.scheme == 'file'
+          # local file
+          fh = open(uri.path, 'rb')
+          src = fh.read
+          fh.close
+        else
+          # remote file
+          if uri.scheme == 'https'
+            http.use_ssl = true 
+            http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+          end
+
+          res, src = http.get(uri.path, {'User-Agent' => USER_AGENT, 'Accept-Encoding' => 'gzip'})
+          charset = fh.respond_to?(:charset) ? fh.charset : 'utf-8'
+
+          if res.code.to_i >= 400
+            raise RemoteFileError if @options[:io_exceptions]
+            return '', nil
+          end
+
+          case res['content-encoding']
+            when 'gzip'
+              io = Zlib::GzipReader.new(StringIO.new(res.body))
+              src = io.read
+            when 'deflate'
+              io = Zlib::Inflate.new
+              src = io.inflate(res.body)
+          end
+        end
+
+        if charset
+          ic = Iconv.new('UTF-8//IGNORE', charset)
+          src = ic.iconv(src)
+        end
+      rescue
+        raise RemoteFileError if @options[:io_exceptions]
+        return nil, nil
+      end
+
+      return src, charset  
+    end
+
+  private
+    # Save a folded declaration block to the internal cache.
+    def save_folded_declaration(block_hash, folded_declaration) # :nodoc:
+      @folded_declaration_cache[block_hash] = folded_declaration
+    end
+
+    # Retrieve a folded declaration block from the internal cache.
+    def get_folded_declaration(block_hash) # :nodoc:
+      return @folded_declaration_cache[block_hash] ||= nil
+    end
+
+    def reset! # :nodoc:
+      @folded_declaration_cache = {}
+      @css_source = ''
+      @css_rules = []
+      @css_warnings = []
+    end
+  end
+end