lib/active_support/multibyte/chars.rb in activesupport-2.3.18 vs lib/active_support/multibyte/chars.rb in activesupport-3.0.0.beta

@@ -1,6 +1,8 @@
 # encoding: utf-8
+require 'active_support/core_ext/string/access'
+require 'active_support/core_ext/string/behavior'
 
 module ActiveSupport #:nodoc:
   module Multibyte #:nodoc:
     # Chars enables you to work transparently with UTF-8 encoding in the Ruby String class without having extensive
     # knowledge about the encoding. A Chars object accepts a string upon initialization and proxies String methods in an
@@ -194,11 +196,11 @@
       #
       # Example:
       #   'Café périferôl'.mb_chars.index('ô') #=> 12
       #   'Café périferôl'.mb_chars.index(/\w/u) #=> 0
       def index(needle, offset=0)
-        wrapped_offset = self.first(offset).wrapped_string.length
+        wrapped_offset = first(offset).wrapped_string.length
         index = @wrapped_string.index(needle, wrapped_offset)
         index ? (self.class.u_unpack(@wrapped_string.slice(0...index)).size) : nil
       end
 
       # Returns the position _needle_ in the string, counting in
@@ -208,11 +210,11 @@
       # Example:
       #   'Café périferôl'.mb_chars.rindex('é') #=> 6
       #   'Café périferôl'.mb_chars.rindex(/\w/u) #=> 13
       def rindex(needle, offset=nil)
         offset ||= length
-        wrapped_offset = self.first(offset).wrapped_string.length
+        wrapped_offset = first(offset).wrapped_string.length
         index = @wrapped_string.rindex(needle, wrapped_offset)
         index ? (self.class.u_unpack(@wrapped_string.slice(0...index)).size) : nil
       end
 
       # Like <tt>String#[]=</tt>, except instead of byte offsets you specify character offsets.
@@ -360,10 +362,20 @@
         slice = self[*args]
         self[*args] = ''
         slice
       end
 
+      # Limit the byte size of the string to a number of bytes without breaking characters. Usable
+      # when the storage for a string is limited for some reason.
+      #
+      # Example:
+      #   s = 'こんにちは'
+      #   s.mb_chars.limit(7) #=> "こに"
+      def limit(limit)
+        slice(0...translate_offset(limit))
+      end
+
       # Returns the codepoint of the first character in the string.
       #
       # Example:
       #   'こんにちは'.mb_chars.ord #=> 12371
       def ord
@@ -371,11 +383,11 @@
       end
 
       # Convert characters in the string to uppercase.
       #
       # Example:
-      #   'Laurent, òu sont les tests?'.mb_chars.upcase.to_s #=> "LAURENT, ÒU SONT LES TESTS?"
+      #   'Laurent, où sont les tests ?'.mb_chars.upcase.to_s #=> "LAURENT, OÙ SONT LES TESTS ?"
       def upcase
         apply_mapping :uppercase_mapping
       end
 
       # Convert characters in the string to lowercase.
@@ -648,27 +660,23 @@
           end.join
         end
       end
 
       protected
-
+        
         def translate_offset(byte_offset) #:nodoc:
           return nil if byte_offset.nil?
           return 0   if @wrapped_string == ''
-          chunk = @wrapped_string[0..byte_offset]
+          
+          if @wrapped_string.respond_to?(:force_encoding)
+            @wrapped_string = @wrapped_string.dup.force_encoding(Encoding::ASCII_8BIT)
+          end
+          
           begin
-            begin
-              chunk.unpack('U*').length - 1
-            rescue ArgumentError => e
-              chunk = @wrapped_string[0..(byte_offset+=1)]
-              # Stop retrying at the end of the string
-              raise e unless byte_offset < chunk.length 
-              # We damaged a character, retry
-              retry
-            end
-          # Catch the ArgumentError so we can throw our own
-          rescue ArgumentError 
-            raise EncodingError, 'malformed UTF-8 character'
+            @wrapped_string[0...byte_offset].unpack('U*').length
+          rescue ArgumentError => e
+            byte_offset -= 1
+            retry
           end
         end
 
         def justify(integer, way, padstr=' ') #:nodoc:
           raise ArgumentError, "zero width padding" if padstr.length == 0