activesupport 2.3.5 → 3.0.0.beta3

data/lib/active_support/json/encoding.rb

@@ -1,7 +1,19 @@
 # encoding: utf-8
+require 'active_support/core_ext/array/wrap'
+require 'active_support/core_ext/hash/except'
+require 'active_support/core_ext/hash/slice'
 require 'active_support/core_ext/module/delegation'
+require 'active_support/core_ext/object/instance_variables'
 require 'active_support/deprecation'
 
+require 'active_support/time'
+
+# Hack to load json gem first so we can overwrite its to_json.
+begin
+  require 'json'
+rescue LoadError
+end
+
 module ActiveSupport
   class << self
     delegate :use_standard_json_time_format, :use_standard_json_time_format=,
@@ -13,15 +25,55 @@ module ActiveSupport
     # matches YAML-formatted dates
     DATE_REGEX = /^(?:\d{4}-\d{2}-\d{2}|\d{4}-\d{1,2}-\d{1,2}[ \t]+\d{1,2}:\d{2}:\d{2}(\.[0-9]*)?(([ \t]*)Z|[-+]\d{2}?(:\d{2})?))$/
 
-    class << self
-      delegate :encode, :to => :'ActiveSupport::JSON::Encoding'
+    # Dumps object in JSON (JavaScript Object Notation). See www.json.org for more info.
+    def self.encode(value, options = nil)
+      Encoding::Encoder.new(options).encode(value)
     end
 
     module Encoding #:nodoc:
-      class CircularReferenceError < StandardError
+      class CircularReferenceError < StandardError; end
+
+      class Encoder
+        attr_reader :options
+
+        def initialize(options = nil)
+          @options = options
+          @seen = []
+        end
+
+        def encode(value)
+          check_for_circular_references(value) do
+            value.as_json(options).encode_json(self)
+          end
+        end
+
+        def escape(string)
+          Encoding.escape(string)
+        end
+
+        private
+          def check_for_circular_references(value)
+            if @seen.any? { |object| object.equal?(value) }
+              raise CircularReferenceError, 'object references itself'
+            end
+            @seen.unshift value
+            yield
+          ensure
+            @seen.shift
+          end
       end
 
+
       ESCAPED_CHARS = {
+        "\x00" => '\u0000', "\x01" => '\u0001', "\x02" => '\u0002',
+        "\x03" => '\u0003', "\x04" => '\u0004', "\x05" => '\u0005',
+        "\x06" => '\u0006', "\x07" => '\u0007', "\x0B" => '\u000B',
+        "\x0E" => '\u000E', "\x0F" => '\u000F', "\x10" => '\u0010',
+        "\x11" => '\u0011', "\x12" => '\u0012', "\x13" => '\u0013',
+        "\x14" => '\u0014', "\x15" => '\u0015', "\x16" => '\u0016',
+        "\x17" => '\u0017', "\x18" => '\u0018', "\x19" => '\u0019',
+        "\x1A" => '\u001A', "\x1B" => '\u001B', "\x1C" => '\u001C',
+        "\x1D" => '\u001D', "\x1E" => '\u001E', "\x1F" => '\u001F',
         "\010" =>  '\b',
         "\f"   =>  '\f',
         "\n"   =>  '\n',
@@ -43,9 +95,9 @@ module ActiveSupport
         def escape_html_entities_in_json=(value)
           self.escape_regex = \
             if @escape_html_entities_in_json = value
-              /[\010\f\n\r\t"\\><&]/
+              /[\x00-\x1F"\\><&]/
             else
-              /[\010\f\n\r\t"\\]/
+              /[\x00-\x1F"\\]/
             end
         end
 
@@ -60,43 +112,120 @@ module ActiveSupport
           }
           %("#{json}")
         end
-
-        # Converts a Ruby object into a JSON string.
-        def encode(value, options = nil)
-          options = {} unless Hash === options
-          seen = (options[:seen] ||= [])
-          raise CircularReferenceError, 'object references itself' if seen.include?(value)
-          seen << value
-          value.to_json(options)
-        ensure
-          seen.pop
-        end
       end
 
-      self.escape_html_entities_in_json = true
+      self.use_standard_json_time_format = true
+      self.escape_html_entities_in_json  = false
     end
 
     CircularReferenceError = Deprecation::DeprecatedConstantProxy.new('ActiveSupport::JSON::CircularReferenceError', Encoding::CircularReferenceError)
   end
 end
 
-# Hack to load json gem first so we can overwrite its to_json.
-begin
-  require 'json'
-rescue LoadError
+class Object
+  # Dumps object in JSON (JavaScript Object Notation). See www.json.org for more info.
+  def to_json(options = nil)
+    ActiveSupport::JSON.encode(self, options)
+  end
+
+  def as_json(options = nil) instance_values end #:nodoc:
+end
+
+# A string that returns itself as its JSON-encoded form.
+class ActiveSupport::JSON::Variable < String
+  def as_json(options = nil) self end #:nodoc:
+  def encode_json(encoder) self end #:nodoc:
+end
+
+class TrueClass
+  AS_JSON = ActiveSupport::JSON::Variable.new('true').freeze
+  def as_json(options = nil) AS_JSON end #:nodoc:
+end
+
+class FalseClass
+  AS_JSON = ActiveSupport::JSON::Variable.new('false').freeze
+  def as_json(options = nil) AS_JSON end #:nodoc:
 end
 
-require 'active_support/json/variable'
-require 'active_support/json/encoders/date'
-require 'active_support/json/encoders/date_time'
-require 'active_support/json/encoders/enumerable'
-require 'active_support/json/encoders/false_class'
-require 'active_support/json/encoders/hash'
-require 'active_support/json/encoders/nil_class'
-require 'active_support/json/encoders/numeric'
-require 'active_support/json/encoders/object'
-require 'active_support/json/encoders/regexp'
-require 'active_support/json/encoders/string'
-require 'active_support/json/encoders/symbol'
-require 'active_support/json/encoders/time'
-require 'active_support/json/encoders/true_class'
+class NilClass
+  AS_JSON = ActiveSupport::JSON::Variable.new('null').freeze
+  def as_json(options = nil) AS_JSON end #:nodoc:
+end
+
+class String
+  def as_json(options = nil) self end #:nodoc:
+  def encode_json(encoder) encoder.escape(self) end #:nodoc:
+end
+
+class Symbol
+  def as_json(options = nil) to_s end #:nodoc:
+end
+
+class Numeric
+  def as_json(options = nil) self end #:nodoc:
+  def encode_json(encoder) to_s end #:nodoc:
+end
+
+class Regexp
+  def as_json(options = nil) self end #:nodoc:
+  def encode_json(encoder) inspect end #:nodoc:
+end
+
+module Enumerable
+  def as_json(options = nil) to_a end #:nodoc:
+end
+
+class Array
+  def as_json(options = nil) self end #:nodoc:
+  def encode_json(encoder) "[#{map { |v| encoder.encode(v) } * ','}]" end #:nodoc:
+end
+
+class Hash
+  def as_json(options = nil) #:nodoc:
+    if options
+      if attrs = options[:only]
+        slice(*Array.wrap(attrs))
+      elsif attrs = options[:except]
+        except(*Array.wrap(attrs))
+      else
+        self
+      end
+    else
+      self
+    end
+  end
+
+  def encode_json(encoder)
+    "{#{map { |k,v| "#{encoder.encode(k.to_s)}:#{encoder.encode(v)}" } * ','}}"
+  end
+end
+
+class Time
+  def as_json(options = nil) #:nodoc:
+    if ActiveSupport.use_standard_json_time_format
+      xmlschema
+    else
+      %(#{strftime("%Y/%m/%d %H:%M:%S")} #{formatted_offset(false)})
+    end
+  end
+end
+
+class Date
+  def as_json(options = nil) #:nodoc:
+    if ActiveSupport.use_standard_json_time_format
+      strftime("%Y-%m-%d")
+    else
+      strftime("%Y/%m/%d")
+    end
+  end
+end
+
+class DateTime
+  def as_json(options = nil) #:nodoc:
+    if ActiveSupport.use_standard_json_time_format
+      xmlschema
+    else
+      strftime('%Y/%m/%d %H:%M:%S %z')
+    end
+  end
+end

data/lib/active_support/json/variable.rb

@@ -2,9 +2,10 @@ module ActiveSupport
   module JSON
     # A string that returns itself as its JSON-encoded form.
     class Variable < String
-      def to_json(options=nil)
-        self
-      end
+      private
+        def rails_to_json(*)
+          self
+        end
     end
   end
 end

data/lib/active_support/lazy_load_hooks.rb

@@ -0,0 +1,17 @@
+module ActiveSupport
+  @load_hooks = Hash.new {|h,k| h[k] = [] }
+  @loaded = {}
+
+  def self.on_load(name, &block)
+    if base = @loaded[name]
+      base.instance_eval(&block)
+    else
+      @load_hooks[name] << block
+    end
+  end
+
+  def self.run_load_hooks(name, base = Object)
+    @load_hooks[name].each { |hook| base.instance_eval(&hook) }
+    @loaded[name] = base
+  end
+end

data/lib/active_support/memoizable.rb

@@ -1,3 +1,6 @@
+require 'active_support/core_ext/kernel/singleton_class'
+require 'active_support/core_ext/module/aliasing'
+
 module ActiveSupport
   module Memoizable
     def self.memoized_ivar_for(symbol)
@@ -41,10 +44,10 @@ module ActiveSupport
         end
       end
 
-      def flush_cache(*syms, &block)
+      def flush_cache(*syms)
         syms.each do |sym|
           (methods + private_methods + protected_methods).each do |m|
-            if m.to_s =~ /^_unmemoized_(#{sym})/
+            if m.to_s =~ /^_unmemoized_(#{sym.to_s.gsub(/\?\Z/, '\?')})/
               ivar = ActiveSupport::Memoizable.memoized_ivar_for($1)
               instance_variable_get(ivar).clear if instance_variable_defined?(ivar)
             end
@@ -58,7 +61,7 @@ module ActiveSupport
         original_method = :"_unmemoized_#{symbol}"
         memoized_ivar = ActiveSupport::Memoizable.memoized_ivar_for(symbol)
 
-        class_eval <<-EOS, __FILE__, __LINE__
+        class_eval <<-EOS, __FILE__, __LINE__ + 1
           include InstanceMethods                                                  # include InstanceMethods
                                                                                    #
           if method_defined?(:#{original_method})                                  # if method_defined?(:_unmemoized_mime_type)
@@ -69,7 +72,7 @@ module ActiveSupport
           if instance_method(:#{symbol}).arity == 0                                # if instance_method(:mime_type).arity == 0
             def #{symbol}(reload = false)                                          #   def mime_type(reload = false)
               if reload || !defined?(#{memoized_ivar}) || #{memoized_ivar}.empty?  #     if reload || !defined?(@_memoized_mime_type) || @_memoized_mime_type.empty?
-                #{memoized_ivar} = [#{original_method}.freeze]                     #       @_memoized_mime_type = [_unmemoized_mime_type.freeze]
+                #{memoized_ivar} = [#{original_method}]                            #       @_memoized_mime_type = [_unmemoized_mime_type]
               end                                                                  #     end
               #{memoized_ivar}[0]                                                  #     @_memoized_mime_type[0]
             end                                                                    #   end
@@ -82,7 +85,7 @@ module ActiveSupport
                 if !reload && #{memoized_ivar}.has_key?(args)                      #       if !reload && @_memoized_mime_type.has_key?(args)
                   #{memoized_ivar}[args]                                           #         @_memoized_mime_type[args]
                 elsif #{memoized_ivar}                                             #       elsif @_memoized_mime_type
-                  #{memoized_ivar}[args] = #{original_method}(*args).freeze        #         @_memoized_mime_type[args] = _unmemoized_mime_type(*args).freeze
+                  #{memoized_ivar}[args] = #{original_method}(*args)               #         @_memoized_mime_type[args] = _unmemoized_mime_type(*args)
                 end                                                                #       end
               else                                                                 #     else
                 #{original_method}(*args)                                          #       _unmemoized_mime_type(*args)

data/lib/active_support/message_encryptor.rb

@@ -1,4 +1,5 @@
 require 'openssl'
+require 'active_support/base64'
 
 module ActiveSupport
   # MessageEncryptor is a simple way to encrypt values which get stored somewhere 

data/lib/active_support/message_verifier.rb

@@ -1,3 +1,6 @@
+require 'active_support/base64'
+require 'active_support/core_ext/object/blank'
+
 module ActiveSupport
   # MessageVerifier makes it easy to generate and verify messages which are signed
   # to prevent tampering.
@@ -40,40 +43,20 @@ module ActiveSupport
     end
     
     private
-      if "foo".respond_to?(:force_encoding)
-        # constant-time comparison algorithm to prevent timing attacks
-        def secure_compare(a, b)
-          a = a.dup.force_encoding(Encoding::BINARY)
-          b = b.dup.force_encoding(Encoding::BINARY)
+      # constant-time comparison algorithm to prevent timing attacks
+      def secure_compare(a, b)
+        return false unless a.bytesize == b.bytesize
 
-          if a.length == b.length
-            result = 0
-            for i in 0..(a.length - 1)
-              result |= a[i].ord ^ b[i].ord
-            end
-            result == 0
-          else
-            false
-          end
-        end
-      else
-        # For <= 1.8.6
-        def secure_compare(a, b)
-          if a.length == b.length
-            result = 0
-            for i in 0..(a.length - 1)
-              result |= a[i] ^ b[i]
-            end
-            result == 0
-          else
-            false
-          end
-        end
+        l = a.unpack "C#{a.bytesize}"
+
+        res = 0
+        b.each_byte { |byte| res |= byte ^ l.shift }
+        res == 0
       end
 
       def generate_digest(data)
         require 'openssl' unless defined?(OpenSSL)
-        OpenSSL::HMAC.hexdigest(OpenSSL::Digest::Digest.new(@digest), @secret, data)
+        OpenSSL::HMAC.hexdigest(OpenSSL::Digest.const_get(@digest).new, @secret, data)
       end
   end
 end

data/lib/active_support/multibyte/chars.rb

@@ -1,4 +1,6 @@
 # encoding: utf-8
+require 'active_support/core_ext/string/access'
+require 'active_support/core_ext/string/behavior'
 
 module ActiveSupport #:nodoc:
   module Multibyte #:nodoc:
@@ -17,7 +19,7 @@ module ActiveSupport #:nodoc:
     #   bad.explicit_checking_method "T".mb_chars.downcase.to_s
     #
     # The default Chars implementation assumes that the encoding of the string is UTF-8, if you want to handle different
-    # encodings you can write your own multibyte string handler and configure it through 
+    # encodings you can write your own multibyte string handler and configure it through
     # ActiveSupport::Multibyte.proxy_class.
     #
     #   class CharsForUTF32
@@ -196,7 +198,7 @@ module ActiveSupport #:nodoc:
       #   '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
@@ -210,7 +212,7 @@ module ActiveSupport #:nodoc:
       #   '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
@@ -362,6 +364,16 @@ module ActiveSupport #:nodoc:
         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:
@@ -373,7 +385,7 @@ module ActiveSupport #:nodoc:
       # 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
@@ -446,8 +458,10 @@ module ActiveSupport #:nodoc:
       end
 
       # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent resulting in a valid UTF-8 string.
-      def tidy_bytes
-        chars(self.class.tidy_bytes(@wrapped_string))
+      #
+      # Passing +true+ will forcibly tidy all bytes, assuming that the string's encoding is entirely CP1252 or ISO-8859-1.
+      def tidy_bytes(force = false)
+        chars(self.class.tidy_bytes(@wrapped_string, force))
       end
 
       %w(lstrip rstrip strip reverse upcase downcase tidy_bytes capitalize).each do |method|
@@ -516,7 +530,7 @@ module ActiveSupport #:nodoc:
               unpacked << codepoints[marker..pos-1]
               marker = pos
             end
-          end 
+          end
           unpacked
         end
 
@@ -632,20 +646,67 @@ module ActiveSupport #:nodoc:
           codepoints
         end
 
+        def tidy_byte(byte)
+          if byte < 160
+            [UCD.cp1252[byte] || byte].pack("U").unpack("C*")
+          elsif byte < 192
+            [194, byte]
+          else
+            [195, byte - 64]
+          end
+        end
+        private :tidy_byte
+
         # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent resulting in a valid UTF-8 string.
-        def tidy_bytes(string)
-          string.split(//u).map do |c|
-            c.force_encoding(Encoding::ASCII) if c.respond_to?(:force_encoding)
-
-            if !ActiveSupport::Multibyte::VALID_CHARACTER['UTF-8'].match(c)
-              n = c.unpack('C')[0]
-              n < 128 ? n.chr :
-              n < 160 ? [UCD.cp1252[n] || n].pack('U') :
-              n < 192 ? "\xC2" + n.chr : "\xC3" + (n-64).chr
+        #
+        # Passing +true+ will forcibly tidy all bytes, assuming that the string's encoding is entirely CP-1252 or ISO-8859-1.
+        def tidy_bytes(string, force = false)
+          if force
+            return string.unpack("C*").map do |b|
+              tidy_byte(b)
+            end.flatten.compact.pack("C*").unpack("U*").pack("U*")
+          end
+
+          bytes = string.unpack("C*")
+          conts_expected = 0
+          last_lead = 0
+
+          bytes.each_index do |i|
+
+            byte          = bytes[i]
+            is_ascii      = byte < 128
+            is_cont       = byte > 127 && byte < 192
+            is_lead       = byte > 191 && byte < 245
+            is_unused     = byte > 240
+            is_restricted = byte > 244
+
+            # Impossible or highly unlikely byte? Clean it.
+            if is_unused || is_restricted
+              bytes[i] = tidy_byte(byte)
+            elsif is_cont
+              # Not expecting contination byte? Clean up. Otherwise, now expect one less.
+              conts_expected == 0 ? bytes[i] = tidy_byte(byte) : conts_expected -= 1
             else
-              c
+              if conts_expected > 0
+                # Expected continuation, but got ASCII or leading? Clean backwards up to
+                # the leading byte.
+                (1..(i - last_lead)).each {|j| bytes[i - j] = tidy_byte(bytes[i - j])}
+                conts_expected = 0
+              end
+              if is_lead
+                # Final byte is leading? Clean it.
+                if i == bytes.length - 1
+                  bytes[i] = tidy_byte(bytes.last)
+                else
+                  # Valid leading byte? Expect continuations determined by position of
+                  # first zero bit, with max of 3.
+                  conts_expected = byte < 224 ? 1 : byte < 240 ? 2 : 3
+                  last_lead = i
+                end
+              end
             end
-          end.join
+          end
+          bytes.empty? ? "" : bytes.flatten.compact.pack("C*").unpack("U*").pack("U*")
         end
       end
 
@@ -654,20 +715,16 @@ module ActiveSupport #:nodoc:
         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
 

data/lib/active_support/multibyte/unicode_database.rb

@@ -23,11 +23,11 @@ module ActiveSupport #:nodoc:
 
       # Lazy load the Unicode database so it's only loaded when it's actually used
       ATTRIBUTES.each do |attr_name|
-        class_eval(<<-EOS, __FILE__, __LINE__)
-          def #{attr_name}  # def codepoints
-            load            #   load
-            @#{attr_name}   #   @codepoints
-          end               # end
+        class_eval(<<-EOS, __FILE__, __LINE__ + 1)
+          def #{attr_name}     # def codepoints
+            load               #   load
+            @#{attr_name}      #   @codepoints
+          end                  # end
         EOS
       end
 

data/lib/active_support/multibyte/utils.rb

@@ -26,11 +26,11 @@ module ActiveSupport #:nodoc:
     else
       def self.verify(string)
         if expression = valid_character
-          for c in string.split(//)
-            return false unless expression.match(c)
-          end
+          # Splits the string on character boundaries, which are determined based on $KCODE.
+          string.split(//).all? { |c| expression =~ c }
+        else
+          true
         end
-        true
       end
     end
 
@@ -49,9 +49,8 @@ module ActiveSupport #:nodoc:
     else
       def self.clean(string)
         if expression = valid_character
-          stripped = []; for c in string.split(//)
-            stripped << c if expression.match(c)
-          end; stripped.join
+          # Splits the string on character boundaries, which are determined based on $KCODE.
+          string.split(//).grep(expression).join
         else
           string
         end

data/lib/active_support/multibyte.rb

@@ -1,7 +1,15 @@
 # encoding: utf-8
 
+require 'active_support/core_ext/module/attribute_accessors'
+
 module ActiveSupport #:nodoc:
   module Multibyte
+    autoload :EncodingError, 'active_support/multibyte/exceptions'
+    autoload :Chars, 'active_support/multibyte/chars'
+    autoload :UnicodeDatabase, 'active_support/multibyte/unicode_database'
+    autoload :Codepoint, 'active_support/multibyte/unicode_database'
+    autoload :UCD, 'active_support/multibyte/unicode_database'
+    
     # A list of all available normalization forms. See http://www.unicode.org/reports/tr15/tr15-29.html for more
     # information about normalization.
     NORMALIZATION_FORMS = [:c, :kc, :d, :kd]
@@ -45,13 +53,10 @@ module ActiveSupport #:nodoc:
                   \xf4        [\x80-\x8f] [\x80-\xbf] [\x80-\xbf])\z /xn,
       # Quick check for valid Shift-JIS characters, disregards the odd-even pairing
       'Shift_JIS' => /\A(?:
-                  [\x00-\x7e \xa1-\xdf]                                     |
-                  [\x81-\x9f \xe0-\xef] [\x40-\x7e \x80-\x9e \x9f-\xfc])\z /xn
+                  [\x00-\x7e\xa1-\xdf]                                     |
+                  [\x81-\x9f\xe0-\xef] [\x40-\x7e\x80-\x9e\x9f-\xfc])\z /xn
     }
   end
 end
 
-require 'active_support/multibyte/chars'
-require 'active_support/multibyte/exceptions'
-require 'active_support/multibyte/unicode_database'
-require 'active_support/multibyte/utils'
+require 'active_support/multibyte/utils'