Add minimal encoding support to String#inspect

kernel/common/string.rb

@@ -446,10 +446,6 @@ def insert(index, other)
   ControlCharacters = [10, 9, 7, 11, 12, 13, 27, 8]
   ControlPrintValue = ["\\n", "\\t", "\\a", "\\v", "\\f", "\\r", "\\e", "\\b"]
 
-  def inspect
-    "\"#{transform(Rubinius::CType::Printed, true)}\""
-  end
-
   def ljust(width, padstr=" ")
     justify(width, :left, padstr)
   end

kernel/common/string18.rb

@@ -685,4 +685,8 @@ def []=(index, replacement, three=undefined)
     end
     return replacement
   end
+
+  def inspect
+    "\"#{transform(Rubinius::CType::Printed, true)}\""
+  end
 end

kernel/common/string19.rb

@@ -810,4 +810,34 @@ def []=(index, replacement, three=undefined)
     end
     return replacement
   end
+
+  def inspect
+    current_encoding = encoding
+    desired_encoding = Encoding.default_internal || Encoding.default_external
+
+    string = generate_inspected_string(current_encoding, desired_encoding)
+
+    "\"#{string}\""
+  end
+
+  def generate_inspected_string(current_encoding, desired_encoding)
+    if current_encoding == desired_encoding and
+       current_encoding == Encoding::UTF_8
+      table = Rubinius::CType::UTF8Printed
+
+      inspected_string = each_char.collect do |char|
+        if not char.valid_encoding? or char.ord < 256
+          table[char.force_encoding(Encoding::BINARY).ord]
+        else
+          char
+        end
+      end.join
+      inspected_string.gsub!(/(#[$@{])/, '\\\\\1')
+
+      Rubinius::Type.infect(inspected_string, self)
+      inspected_string
+    else
+      transform(Rubinius::CType::Printed, true)
+    end
+  end
 end

kernel/delta/ctype.rb

@@ -1,7 +1,7 @@
 # -*- encoding: us-ascii -*-
 
 module Rubinius::CType
-  def self.toprint(num)
+  def self.toprint(num, utf8=false)
     # The character literals (?x) are Fixnums in 1.8 and Strings in 1.9
     # so we use literal values instead so this is 1.8/1.9 compatible.
     case num
@@ -14,11 +14,20 @@ def self.toprint(num)
     when 13; '\r'
     when 27; '\e'
     when 34; '\"'
-    when 35;  Rubinius::Tuple['#$', '\#$', '#@', '\#@', '#{', '\#{', '#', '#']
+    when 35;
+      unless utf8
+        Rubinius::Tuple['#$', '\#$', '#@', '\#@', '#{', '\#{', '#', '#']
+      else
+        '#' # TODO: '#' escaping is handled by String#generate_inspected_string
+      end
     when 92; '\\\\'
     else
       if num < 32 || num > 126
-        unprintable_chr(num)
+        unless utf8
+          unprintable_chr(num)
+        else
+          unprintable_utf8_chr(num)
+        end
       else
         num.chr
       end
@@ -32,6 +41,13 @@ def self.toprint(num)
     i += 1
   end
 
+  UTF8Printed = Rubinius::Tuple.new 256
+  i = 0
+  while i < 256
+    UTF8Printed[i] = toprint(i, true)
+    i += 1
+  end
+
   def toprint
     Printed[self]
   end

kernel/delta/ctype18.rb

@@ -6,4 +6,8 @@ def self.unprintable_chr(num)
     c = num.to_s 8
     str.copy_from c, 0, c.size, 4-c.size
   end
-end
+
+  def self.unprintable_utf8_chr(num)
+    unprintable_chr(num)
+  end
+end

kernel/delta/ctype19.rb

@@ -6,4 +6,16 @@ def self.unprintable_chr(num)
     c = num.to_s(16).upcase
     str.copy_from c, 0, c.size, 4-c.size
   end
-end
+
+  def self.unprintable_utf8_chr(num)
+    if num <= 0x7f
+      str = "\\u0000"
+      str.modify!
+
+      c = num.to_s(16).upcase
+      str.copy_from c, 0, c.size, 6-c.size
+    else
+      unprintable_chr(num)
+    end
+  end
+end