xml_escape.rb in chef-0.9.10.rc.0

- old
+ new
@@ -44,71 +44,97 @@
 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 # THE SOFTWARE.
 
+require 'chef/log'
 
+begin
+  require 'fast_xs'
+rescue LoadError
+  Chef::Log.info "The fast_xs gem is not installed, slower pure ruby XML escaping will be used."
+end
+
 class Chef
   module Mixin
     module XMLEscape
-      extend self
 
-      CP1252 = {
-        128 => 8364, # euro sign
-        130 => 8218, # single low-9 quotation mark
-        131 =>  402, # latin small letter f with hook
-        132 => 8222, # double low-9 quotation mark
-        133 => 8230, # horizontal ellipsis
-        134 => 8224, # dagger
-        135 => 8225, # double dagger
-        136 =>  710, # modifier letter circumflex accent
-        137 => 8240, # per mille sign
-        138 =>  352, # latin capital letter s with caron
-        139 => 8249, # single left-pointing angle quotation mark
-        140 =>  338, # latin capital ligature oe
-        142 =>  381, # latin capital letter z with caron
-        145 => 8216, # left single quotation mark
-        146 => 8217, # right single quotation mark
-        147 => 8220, # left double quotation mark
-        148 => 8221, # right double quotation mark
-        149 => 8226, # bullet
-        150 => 8211, # en dash
-        151 => 8212, # em dash
-        152 =>  732, # small tilde
-        153 => 8482, # trade mark sign
-        154 =>  353, # latin small letter s with caron
-        155 => 8250, # single right-pointing angle quotation mark
-        156 =>  339, # latin small ligature oe
-        158 =>  382, # latin small letter z with caron
-        159 =>  376 # latin capital letter y with diaeresis
-      }
+      module PureRuby
+        extend self
 
-      # http://www.w3.org/TR/REC-xml/#dt-chardata
-      PREDEFINED = {
-        38 => '&amp;', # ampersand
-        60 => '&lt;',  # left angle bracket
-        62 => '&gt;'  # right angle bracket
-      }
+        CP1252 = {
+          128 => 8364, # euro sign
+          130 => 8218, # single low-9 quotation mark
+          131 =>  402, # latin small letter f with hook
+          132 => 8222, # double low-9 quotation mark
+          133 => 8230, # horizontal ellipsis
+          134 => 8224, # dagger
+          135 => 8225, # double dagger
+          136 =>  710, # modifier letter circumflex accent
+          137 => 8240, # per mille sign
+          138 =>  352, # latin capital letter s with caron
+          139 => 8249, # single left-pointing angle quotation mark
+          140 =>  338, # latin capital ligature oe
+          142 =>  381, # latin capital letter z with caron
+          145 => 8216, # left single quotation mark
+          146 => 8217, # right single quotation mark
+          147 => 8220, # left double quotation mark
+          148 => 8221, # right double quotation mark
+          149 => 8226, # bullet
+          150 => 8211, # en dash
+          151 => 8212, # em dash
+          152 =>  732, # small tilde
+          153 => 8482, # trade mark sign
+          154 =>  353, # latin small letter s with caron
+          155 => 8250, # single right-pointing angle quotation mark
+          156 =>  339, # latin small ligature oe
+          158 =>  382, # latin small letter z with caron
+          159 =>  376 # latin capital letter y with diaeresis
+        }
 
-      # http://www.w3.org/TR/REC-xml/#charsets
-      VALID = [[0x9, 0xA, 0xD], (0x20..0xD7FF), 
-        (0xE000..0xFFFD), (0x10000..0x10FFFF)]
+        # http://www.w3.org/TR/REC-xml/#dt-chardata
+        PREDEFINED = {
+          38 => '&amp;', # ampersand
+          60 => '&lt;',  # left angle bracket
+          62 => '&gt;'  # right angle bracket
+        }
 
-      def xml_escape(unescaped_str)
-        begin
-          unescaped_str.unpack("U*").map {|char| xml_escape_char!(char)}.join
-        rescue
-          unescaped_str.unpack("C*").map {|char| xml_escape_char!(char)}.join
+        # http://www.w3.org/TR/REC-xml/#charsets
+        VALID = [[0x9, 0xA, 0xD], (0x20..0xD7FF), 
+          (0xE000..0xFFFD), (0x10000..0x10FFFF)]
+
+        def xml_escape(unescaped_str)
+          begin
+            unescaped_str.unpack("U*").map {|char| xml_escape_char!(char)}.join
+          rescue
+            unescaped_str.unpack("C*").map {|char| xml_escape_char!(char)}.join
+          end
         end
+
+        private
+
+        def xml_escape_char!(char)
+          char = CP1252[char] || char
+          char = 42 unless VALID.detect {|range| range.include? char}
+          char = PREDEFINED[char] || (char<128 ? char.chr : "&##{char};")
+        end
       end
+      
+      module FastXS
+        extend self
 
-      private
+        def xml_escape(string)
+          string.fast_xs
+        end
 
-      def xml_escape_char!(char)
-        char = CP1252[char] || char
-        char = 42 unless VALID.detect {|range| range.include? char}
-        char = PREDEFINED[char] || (char<128 ? char.chr : "&##{char};")
       end
 
+      if "strings".respond_to?(:fast_xs)
+        include FastXS
+        extend FastXS
+      else
+        include PureRuby
+        extend PureRuby
+      end
     end
   end
 end