activesupport 3.2.22.5 → 4.0.0

data/lib/active_support/multibyte/unicode.rb

@@ -5,17 +5,18 @@ module ActiveSupport
 
       extend self
 
-      # A list of all available normalization forms. See http://www.unicode.org/reports/tr15/tr15-29.html for more
+      # 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]
 
       # The Unicode version that is supported by the implementation
-      UNICODE_VERSION = '5.2.0'
+      UNICODE_VERSION = '6.2.0'
 
-      # The default normalization used for operations that require normalization. It can be set to any of the
-      # normalizations in NORMALIZATION_FORMS.
+      # The default normalization used for operations that require
+      # normalization. It can be set to any of the normalizations
+      # in NORMALIZATION_FORMS.
       #
-      # Example:
       #   ActiveSupport::Multibyte::Unicode.default_normalization_form = :c
       attr_accessor :default_normalization_form
       @default_normalization_form = :kc
@@ -50,32 +51,22 @@ module ActiveSupport
         0x3000,                # White_Space # Zs       IDEOGRAPHIC SPACE
       ].flatten.freeze
 
-      # BOM (byte order mark) can also be seen as whitespace, it's a non-rendering character used to distinguish
-      # between little and big endian. This is not an issue in utf-8, so it must be ignored.
+      # BOM (byte order mark) can also be seen as whitespace, it's a
+      # non-rendering character used to distinguish between little and big
+      # endian. This is not an issue in utf-8, so it must be ignored.
       LEADERS_AND_TRAILERS = WHITESPACE + [65279] # ZERO-WIDTH NO-BREAK SPACE aka BOM
 
-      # Returns a regular expression pattern that matches the passed Unicode codepoints
+      # Returns a regular expression pattern that matches the passed Unicode
+      # codepoints.
       def self.codepoints_to_pattern(array_of_codepoints) #:nodoc:
         array_of_codepoints.collect{ |e| [e].pack 'U*' }.join('|')
       end
       TRAILERS_PAT = /(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+\Z/u
       LEADERS_PAT = /\A(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+/u
 
-      # Unpack the string at codepoints boundaries. Raises an EncodingError when the encoding of the string isn't
-      # valid UTF-8.
-      #
-      # Example:
-      #   Unicode.u_unpack('Café') # => [67, 97, 102, 233]
-      def u_unpack(string)
-        begin
-          string.unpack 'U*'
-        rescue ArgumentError
-          raise EncodingError, 'malformed UTF-8 character'
-        end
-      end
-
-      # Detect whether the codepoint is in a certain character class. Returns +true+ when it's in the specified
-      # character class and +false+ otherwise. Valid character classes are: <tt>:cr</tt>, <tt>:lf</tt>, <tt>:l</tt>,
+      # Detect whether the codepoint is in a certain character class. Returns
+      # +true+ when it's in the specified character class and +false+ otherwise.
+      # Valid character classes are: <tt>:cr</tt>, <tt>:lf</tt>, <tt>:l</tt>,
       # <tt>:v</tt>, <tt>:lv</tt>, <tt>:lvt</tt> and <tt>:t</tt>.
       #
       # Primarily used by the grapheme cluster support.
@@ -83,13 +74,13 @@ module ActiveSupport
         classes.detect { |c| database.boundary[c] === codepoint } ? true : false
       end
 
-      # Unpack the string at grapheme boundaries. Returns a list of character lists.
+      # Unpack the string at grapheme boundaries. Returns a list of character
+      # lists.
       #
-      # Example:
-      #   Unicode.g_unpack('क्षि') # => [[2325, 2381], [2359], [2367]]
-      #   Unicode.g_unpack('Café') # => [[67], [97], [102], [233]]
-      def g_unpack(string)
-        codepoints = u_unpack(string)
+      #   Unicode.unpack_graphemes('क्षि') # => [[2325, 2381], [2359], [2367]]
+      #   Unicode.unpack_graphemes('Café') # => [[67], [97], [102], [233]]
+      def unpack_graphemes(string)
+        codepoints = string.codepoints.to_a
         unpacked = []
         pos = 0
         marker = 0
@@ -118,12 +109,11 @@ module ActiveSupport
         unpacked
       end
 
-      # Reverse operation of g_unpack.
+      # Reverse operation of unpack_graphemes.
       #
-      # Example:
-      #   Unicode.g_pack(Unicode.g_unpack('क्षि')) # => 'क्षि'
-      def g_pack(unpacked)
-        (unpacked.flatten).pack('U*')
+      #   Unicode.pack_graphemes(Unicode.unpack_graphemes('क्षि')) # => 'क्षि'
+      def pack_graphemes(unpacked)
+        unpacked.flatten.pack('U*')
       end
 
       # Re-order codepoints so the string becomes canonical.
@@ -143,7 +133,7 @@ module ActiveSupport
       end
 
       # Decompose composed characters to the decomposed form.
-      def decompose_codepoints(type, codepoints)
+      def decompose(type, codepoints)
         codepoints.inject([]) do |decomposed, cp|
           # if it's a hangul syllable starter character
           if HANGUL_SBASE <= cp and cp < HANGUL_SLAST
@@ -156,7 +146,7 @@ module ActiveSupport
             decomposed.concat ncp
           # if the codepoint is decomposable in with the current decomposition type
           elsif (ncp = database.codepoints[cp].decomp_mapping) and (!database.codepoints[cp].decomp_type || type == :compatability)
-            decomposed.concat decompose_codepoints(type, ncp.dup)
+            decomposed.concat decompose(type, ncp.dup)
           else
             decomposed << cp
           end
@@ -164,7 +154,7 @@ module ActiveSupport
       end
 
       # Compose decomposed characters to the composed form.
-      def compose_codepoints(codepoints)
+      def compose(codepoints)
         pos = 0
         eoa = codepoints.length - 1
         starter_pos = 0
@@ -222,9 +212,11 @@ module ActiveSupport
         codepoints
       end
 
-      # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent resulting in a valid UTF-8 string.
+      # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent
+      # resulting in a valid UTF-8 string.
       #
-      # Passing +true+ will forcibly tidy all bytes, assuming that the string's encoding is entirely CP1252 or ISO-8859-1.
+      # Passing +true+ will forcibly tidy all bytes, assuming that the string's
+      # encoding is entirely CP1252 or ISO-8859-1.
       def tidy_bytes(string, force = false)
         if force
           return string.unpack("C*").map do |b|
@@ -273,48 +265,54 @@ module ActiveSupport
         bytes.empty? ? "" : bytes.flatten.compact.pack("C*").unpack("U*").pack("U*")
       end
 
-      # Returns the KC normalization of the string by default. NFKC is considered the best normalization form for
-      # passing strings to databases and validations.
+      # Returns the KC normalization of the string by default. NFKC is
+      # considered the best normalization form for passing strings to databases
+      # and validations.
       #
       # * <tt>string</tt> - The string to perform normalization on.
-      # * <tt>form</tt> - The form you want to normalize in. Should be one of the following:
-      #   <tt>:c</tt>, <tt>:kc</tt>, <tt>:d</tt>, or <tt>:kd</tt>. Default is
-      #   ActiveSupport::Multibyte.default_normalization_form
+      # * <tt>form</tt> - The form you want to normalize in. Should be one of
+      #   the following: <tt>:c</tt>, <tt>:kc</tt>, <tt>:d</tt>, or <tt>:kd</tt>.
+      #   Default is ActiveSupport::Multibyte.default_normalization_form.
       def normalize(string, form=nil)
         form ||= @default_normalization_form
         # See http://www.unicode.org/reports/tr15, Table 1
-        codepoints = u_unpack(string)
+        codepoints = string.codepoints.to_a
         case form
           when :d
-            reorder_characters(decompose_codepoints(:canonical, codepoints))
+            reorder_characters(decompose(:canonical, codepoints))
           when :c
-            compose_codepoints(reorder_characters(decompose_codepoints(:canonical, codepoints)))
+            compose(reorder_characters(decompose(:canonical, codepoints)))
           when :kd
-            reorder_characters(decompose_codepoints(:compatability, codepoints))
+            reorder_characters(decompose(:compatability, codepoints))
           when :kc
-            compose_codepoints(reorder_characters(decompose_codepoints(:compatability, codepoints)))
+            compose(reorder_characters(decompose(:compatability, codepoints)))
           else
             raise ArgumentError, "#{form} is not a valid normalization variant", caller
         end.pack('U*')
       end
 
-      def apply_mapping(string, mapping) #:nodoc:
-        u_unpack(string).map do |codepoint|
-          cp = database.codepoints[codepoint]
-          if cp and (ncp = cp.send(mapping)) and ncp > 0
-            ncp
-          else
-            codepoint
-          end
-        end.pack('U*')
+      def downcase(string)
+        apply_mapping string, :lowercase_mapping
+      end
+
+      def upcase(string)
+        apply_mapping string, :uppercase_mapping
       end
 
-      # Holds data about a codepoint in the Unicode database
+      def swapcase(string)
+        apply_mapping string, :swapcase_mapping
+      end
+
+      # Holds data about a codepoint in the Unicode database.
       class Codepoint
         attr_accessor :code, :combining_class, :decomp_type, :decomp_mapping, :uppercase_mapping, :lowercase_mapping
+
+        def swapcase_mapping
+          uppercase_mapping > 0 ? uppercase_mapping : lowercase_mapping
+        end
       end
 
-      # Holds static data from the Unicode database
+      # Holds static data from the Unicode database.
       class UnicodeDatabase
         ATTRIBUTES = :codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252
 
@@ -338,11 +336,12 @@ module ActiveSupport
           EOS
         end
 
-        # Loads the Unicode database and returns all the internal objects of UnicodeDatabase.
+        # Loads the Unicode database and returns all the internal objects of
+        # UnicodeDatabase.
         def load
           begin
             @codepoints, @composition_exclusion, @composition_map, @boundary, @cp1252 = File.open(self.class.filename, 'rb') { |f| Marshal.load f.read }
-          rescue Exception => e
+          rescue => e
               raise IOError.new("Couldn't load the Unicode tables for UTF8Handler (#{e.message}), ActiveSupport::Multibyte is unusable")
           end
 
@@ -361,12 +360,12 @@ module ActiveSupport
           end
         end
 
-        # Returns the directory in which the data files are stored
+        # Returns the directory in which the data files are stored.
         def self.dirname
           File.dirname(__FILE__) + '/../values/'
         end
 
-        # Returns the filename for the data file for this version
+        # Returns the filename for the data file for this version.
         def self.filename
           File.expand_path File.join(dirname, "unicode_tables.dat")
         end
@@ -374,6 +373,17 @@ module ActiveSupport
 
       private
 
+      def apply_mapping(string, mapping) #:nodoc:
+        string.each_codepoint.map do |codepoint|
+          cp = database.codepoints[codepoint]
+          if cp and (ncp = cp.send(mapping)) and ncp > 0
+            ncp
+          else
+            codepoint
+          end
+        end.pack('U*')
+      end
+
       def tidy_byte(byte)
         if byte < 160
           [database.cp1252[byte] || byte].pack("U").unpack("C*")

data/lib/active_support/multibyte.rb

@@ -1,44 +1,21 @@
-# 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 :Unicode, 'active_support/multibyte/unicode'
 
-    # The proxy class returned when calling mb_chars. You can use this accessor to configure your own proxy
-    # class so you can support other encodings. See the ActiveSupport::Multibyte::Chars implementation for
-    # an example how to do this.
+    # The proxy class returned when calling mb_chars. You can use this accessor
+    # to configure your own proxy class so you can support other encodings. See
+    # the ActiveSupport::Multibyte::Chars implementation for an example how to
+    # do this.
     #
-    # Example:
     #   ActiveSupport::Multibyte.proxy_class = CharsForUTF32
     def self.proxy_class=(klass)
       @proxy_class = klass
     end
 
-    # Returns the current proxy class
+    # Returns the current proxy class.
     def self.proxy_class
       @proxy_class ||= ActiveSupport::Multibyte::Chars
     end
-
-    # Regular expressions that describe valid byte sequences for a character
-    VALID_CHARACTER = {
-      # Borrowed from the Kconv library by Shinji KONO - (also as seen on the W3C site)
-      'UTF-8' => /\A(?:
-                  [\x00-\x7f]                                         |
-                  [\xc2-\xdf] [\x80-\xbf]                             |
-                  \xe0        [\xa0-\xbf] [\x80-\xbf]                 |
-                  [\xe1-\xef] [\x80-\xbf] [\x80-\xbf]                 |
-                  \xf0        [\x90-\xbf] [\x80-\xbf] [\x80-\xbf]     |
-                  [\xf1-\xf3] [\x80-\xbf] [\x80-\xbf] [\x80-\xbf]     |
-                  \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
-    }
   end
 end
-
-require 'active_support/multibyte/utils'

data/lib/active_support/notifications/fanout.rb

@@ -1,24 +1,43 @@
+require 'mutex_m'
+require 'thread_safe'
+
 module ActiveSupport
   module Notifications
     # This is a default queue implementation that ships with Notifications.
     # It just pushes events to all registered log subscribers.
+    #
+    # This class is thread safe. All methods are reentrant.
     class Fanout
+      include Mutex_m
+
       def initialize
         @subscribers = []
-        @listeners_for = {}
+        @listeners_for = ThreadSafe::Cache.new
+        super
       end
 
       def subscribe(pattern = nil, block = Proc.new)
-        subscriber = Subscriber.new(pattern, block).tap do |s|
-          @subscribers << s
+        subscriber = Subscribers.new pattern, block
+        synchronize do
+          @subscribers << subscriber
+          @listeners_for.clear
         end
-        @listeners_for.clear
         subscriber
       end
 
       def unsubscribe(subscriber)
-        @subscribers.reject! {|s| s.matches?(subscriber)}
-        @listeners_for.clear
+        synchronize do
+          @subscribers.reject! { |s| s.matches?(subscriber) }
+          @listeners_for.clear
+        end
+      end
+
+      def start(name, id, payload)
+        listeners_for(name).each { |s| s.start(name, id, payload) }
+      end
+
+      def finish(name, id, payload)
+        listeners_for(name).each { |s| s.finish(name, id, payload) }
       end
 
       def publish(name, *args)
@@ -26,7 +45,11 @@ module ActiveSupport
       end
 
       def listeners_for(name)
-        @listeners_for[name] ||= @subscribers.select { |s| s.subscribed_to?(name) }
+        # this is correctly done double-checked locking (ThreadSafe::Cache's lookups have volatile semantics)
+        @listeners_for[name] || synchronize do
+          # use synchronisation when accessing @subscribers
+          @listeners_for[name] ||= @subscribers.select { |s| s.subscribed_to?(name) }
+        end
       end
 
       def listening?(name)
@@ -37,23 +60,94 @@ module ActiveSupport
       def wait
       end
 
-      class Subscriber #:nodoc:
-        def initialize(pattern, delegate)
-          @pattern = pattern
-          @delegate = delegate
+      module Subscribers # :nodoc:
+        def self.new(pattern, listener)
+          if listener.respond_to?(:start) and listener.respond_to?(:finish)
+            subscriber = Evented.new pattern, listener
+          else
+            subscriber = Timed.new pattern, listener
+          end
+
+          unless pattern
+            AllMessages.new(subscriber)
+          else
+            subscriber
+          end
         end
 
-        def publish(message, *args)
-          @delegate.call(message, *args)
+        class Evented #:nodoc:
+          def initialize(pattern, delegate)
+            @pattern = pattern
+            @delegate = delegate
+            @can_publish = delegate.respond_to?(:publish)
+          end
+
+          def publish(name, *args)
+            if @can_publish
+              @delegate.publish name, *args
+            end
+          end
+
+          def start(name, id, payload)
+            @delegate.start name, id, payload
+          end
+
+          def finish(name, id, payload)
+            @delegate.finish name, id, payload
+          end
+
+          def subscribed_to?(name)
+            @pattern === name.to_s
+          end
+
+          def matches?(subscriber_or_name)
+            self === subscriber_or_name ||
+              @pattern && @pattern === subscriber_or_name
+          end
         end
 
-        def subscribed_to?(name)
-          !@pattern || @pattern === name.to_s
+        class Timed < Evented
+          def initialize(pattern, delegate)
+            @timestack = []
+            super
+          end
+
+          def publish(name, *args)
+            @delegate.call name, *args
+          end
+
+          def start(name, id, payload)
+            @timestack.push Time.now
+          end
+
+          def finish(name, id, payload)
+            started = @timestack.pop
+            @delegate.call(name, started, Time.now, id, payload)
+          end
         end
 
-        def matches?(subscriber_or_name)
-          self === subscriber_or_name ||
-            @pattern && @pattern === subscriber_or_name
+        class AllMessages # :nodoc:
+          def initialize(delegate)
+            @delegate = delegate
+          end
+
+          def start(name, id, payload)
+            @delegate.start name, id, payload
+          end
+
+          def finish(name, id, payload)
+            @delegate.finish name, id, payload
+          end
+
+          def publish(name, *args)
+            @delegate.publish name, *args
+          end
+
+          def subscribed_to?(name)
+            true
+          end
+
+          alias :matches? :===
         end
       end
     end

data/lib/active_support/notifications/instrumenter.rb

@@ -1,39 +1,51 @@
-require 'active_support/core_ext/module/delegation'
+require 'securerandom'
 
 module ActiveSupport
   module Notifications
+    # Instrumenters are stored in a thread local.
     class Instrumenter
       attr_reader :id
 
       def initialize(notifier)
-        @id = unique_id
+        @id       = unique_id
         @notifier = notifier
       end
 
       # Instrument the given block by measuring the time taken to execute it
       # and publish it. Notice that events get sent even if an error occurs
-      # in the passed-in block
+      # in the passed-in block.
       def instrument(name, payload={})
-        started = Time.now
-
+        start name, payload
         begin
-          yield
+          yield payload
         rescue Exception => e
           payload[:exception] = [e.class.name, e.message]
           raise e
         ensure
-          @notifier.publish(name, started, Time.now, @id, payload)
+          finish name, payload
         end
       end
 
+      # Send a start notification with +name+ and +payload+.
+      def start(name, payload)
+        @notifier.start name, @id, payload
+      end
+
+      # Send a finish notification with +name+ and +payload+.
+      def finish(name, payload)
+        @notifier.finish name, @id, payload
+      end
+
       private
-        def unique_id
-          SecureRandom.hex(10)
-        end
+
+      def unique_id
+        SecureRandom.hex(10)
+      end
     end
 
     class Event
-      attr_reader :name, :time, :end, :transaction_id, :payload, :duration
+      attr_reader :name, :time, :transaction_id, :payload, :children
+      attr_accessor :end
 
       def initialize(name, start, ending, transaction_id, payload)
         @name           = name
@@ -41,12 +53,19 @@ module ActiveSupport
         @time           = start
         @transaction_id = transaction_id
         @end            = ending
-        @duration       = 1000.0 * (@end - @time)
+        @children       = []
+      end
+
+      def duration
+        1000.0 * (self.end - time)
+      end
+
+      def <<(event)
+        @children << event
       end
 
       def parent_of?(event)
-        start = (time - event.time) * 1000
-        start <= 0 && (start + duration >= event.duration)
+        @children.include? event
       end
     end
   end