module CodeRay
module Scanners

  class CSS < Scanner

    register_for :css

    KINDS_NOT_LOC = [
      :comment,
      :class, :pseudo_class, :type,
      :constant, :directive,
      :key, :value, :operator, :color, :float,
      :error, :important,
    ]  # :nodoc:
    
    module RE  # :nodoc:
      NonASCII = /[\x80-\xFF]/
      Hex = /[0-9a-fA-F]/
      Unicode = /\\#{Hex}{1,6}(?:\r\n|\s)?/ # differs from standard because it allows uppercase hex too
      Escape = /#{Unicode}|\\[^\r\n\f0-9a-fA-F]/
      NMChar = /[-_a-zA-Z0-9]|#{NonASCII}|#{Escape}/
      NMStart = /[_a-zA-Z]|#{NonASCII}|#{Escape}/
      NL = /\r\n|\r|\n|\f/
      String1 = /"(?:[^\n\r\f\\"]|\\#{NL}|#{Escape})*"?/  # FIXME: buggy regexp
      String2 = /'(?:[^\n\r\f\\']|\\#{NL}|#{Escape})*'?/  # FIXME: buggy regexp
      String = /#{String1}|#{String2}/

      HexColor = /#(?:#{Hex}{6}|#{Hex}{3})/
      Color = /#{HexColor}/

      Num = /-?(?:[0-9]+|[0-9]*\.[0-9]+)/
      Name = /#{NMChar}+/
      Ident = /-?#{NMStart}#{NMChar}*/
      AtKeyword = /@#{Ident}/
      Percentage = /#{Num}%/

      reldimensions = %w[em ex px]
      absdimensions = %w[in cm mm pt pc]
      Unit = Regexp.union(*(reldimensions + absdimensions))

      Dimension = /#{Num}#{Unit}/

      Comment = %r! /\* (?: .*? \*/ | .* ) !mx
      Function = /(?:url|alpha|attr|counters?)\((?:[^)\n\r\f]|\\\))*\)?/

      Id = /##{Name}/
      Class = /\.#{Name}/
      PseudoClass = /:#{Name}/
      AttributeSelector = /\[[^\]]*\]?/
    end
    
  protected
    
    def scan_tokens encoder, options
      
      value_expected = nil
      states = [:initial]

      until eos?

        if match = scan(/\s+/)
          encoder.text_token match, :space

        elsif case states.last
          when :initial, :media
            if match = scan(/(?>#{RE::Ident})(?!\()|\*/ox)
              encoder.text_token match, :type
            elsif match = scan(RE::Class)
              encoder.text_token match, :class
            elsif match = scan(RE::Id)
              encoder.text_token match, :constant
            elsif match = scan(RE::PseudoClass)
              encoder.text_token match, :pseudo_class
            elsif match = scan(RE::AttributeSelector)
              # TODO: Improve highlighting inside of attribute selectors.
              encoder.text_token match[0,1], :operator
              encoder.text_token match[1..-2], :attribute_name if match.size > 2
              encoder.text_token match[-1,1], :operator if match[-1] == ?]
            elsif match = scan(/@media/)
              encoder.text_token match, :directive
              states.push :media_before_name
            end
          
          when :block
            if match = scan(/(?>#{RE::Ident})(?!\()/ox)
              if value_expected
                encoder.text_token match, :value
              else
                encoder.text_token match, :key
              end
            end

          when :media_before_name
            if match = scan(RE::Ident)
              encoder.text_token match, :type
              states[-1] = :media_after_name
            end
          
          when :media_after_name
            if match = scan(/\{/)
              encoder.text_token match, :operator
              states[-1] = :media
            end
          
          when :comment
            if match = scan(/(?:[^*\s]|\*(?!\/))+/)
              encoder.text_token match, :comment
            elsif match = scan(/\*\//)
              encoder.text_token match, :comment
              states.pop
            elsif match = scan(/\s+/)
              encoder.text_token match, :space
            end

          else
            raise_inspect 'Unknown state', encoder

          end

        elsif match = scan(/\/\*/)
          encoder.text_token match, :comment
          states.push :comment

        elsif match = scan(/\{/)
          value_expected = false
          encoder.text_token match, :operator
          states.push :block

        elsif match = scan(/\}/)
          value_expected = false
          if states.last == :block || states.last == :media
            encoder.text_token match, :operator
            states.pop
          else
            encoder.text_token match, :error
          end

        elsif match = scan(/#{RE::String}/o)
          encoder.begin_group :string
          encoder.text_token match[0, 1], :delimiter
          encoder.text_token match[1..-2], :content if match.size > 2
          encoder.text_token match[-1, 1], :delimiter if match.size >= 2
          encoder.end_group :string

        elsif match = scan(/#{RE::Function}/o)
          encoder.begin_group :string
          start = match[/^\w+\(/]
          encoder.text_token start, :delimiter
          if match[-1] == ?)
            encoder.text_token match[start.size..-2], :content
            encoder.text_token ')', :delimiter
          else
            encoder.text_token match[start.size..-1], :content
          end
          encoder.end_group :string

        elsif match = scan(/(?: #{RE::Dimension} | #{RE::Percentage} | #{RE::Num} )/ox)
          encoder.text_token match, :float

        elsif match = scan(/#{RE::Color}/o)
          encoder.text_token match, :color

        elsif match = scan(/! *important/)
          encoder.text_token match, :important

        elsif match = scan(/(?:rgb|hsl)a?\([^()\n]*\)?/)
          encoder.text_token match, :color

        elsif match = scan(RE::AtKeyword)
          encoder.text_token match, :directive

        elsif match = scan(/ [+>:;,.=()\/] /x)
          if match == ':'
            value_expected = true
          elsif match == ';'
            value_expected = false
          end
          encoder.text_token match, :operator

        else
          encoder.text_token getch, :error

        end

      end

      encoder
    end

  end

end
end