activesupport 4.2.11.1 → 6.0.3.1

data/lib/active_support/multibyte/unicode.rb

@@ -1,17 +1,24 @@
-# encoding: utf-8
+# frozen_string_literal: true
+
 module ActiveSupport
   module Multibyte
     module Unicode
-
       extend self
 
       # A list of all available normalization forms.
-      # See http://www.unicode.org/reports/tr15/tr15-29.html for more
+      # See https://www.unicode.org/reports/tr15/tr15-29.html for more
       # information about normalization.
       NORMALIZATION_FORMS = [:c, :kc, :d, :kd]
 
+      NORMALIZATION_FORM_ALIASES = { # :nodoc:
+        c: :nfc,
+        d: :nfd,
+        kc: :nfkc,
+        kd: :nfkd
+      }
+
       # The Unicode version that is supported by the implementation
-      UNICODE_VERSION = '7.0.0'
+      UNICODE_VERSION = RbConfig::CONFIG["UNICODE_VERSION"]
 
       # The default normalization used for operations that require
       # normalization. It can be set to any of the normalizations
@@ -21,199 +28,48 @@ module ActiveSupport
       attr_accessor :default_normalization_form
       @default_normalization_form = :kc
 
-      # Hangul character boundaries and properties
-      HANGUL_SBASE = 0xAC00
-      HANGUL_LBASE = 0x1100
-      HANGUL_VBASE = 0x1161
-      HANGUL_TBASE = 0x11A7
-      HANGUL_LCOUNT = 19
-      HANGUL_VCOUNT = 21
-      HANGUL_TCOUNT = 28
-      HANGUL_NCOUNT = HANGUL_VCOUNT * HANGUL_TCOUNT
-      HANGUL_SCOUNT = 11172
-      HANGUL_SLAST = HANGUL_SBASE + HANGUL_SCOUNT
-      HANGUL_JAMO_FIRST = 0x1100
-      HANGUL_JAMO_LAST = 0x11FF
-
-      # All the unicode whitespace
-      WHITESPACE = [
-        (0x0009..0x000D).to_a, # White_Space # Cc   [5] <control-0009>..<control-000D>
-        0x0020,                # White_Space # Zs       SPACE
-        0x0085,                # White_Space # Cc       <control-0085>
-        0x00A0,                # White_Space # Zs       NO-BREAK SPACE
-        0x1680,                # White_Space # Zs       OGHAM SPACE MARK
-        (0x2000..0x200A).to_a, # White_Space # Zs  [11] EN QUAD..HAIR SPACE
-        0x2028,                # White_Space # Zl       LINE SEPARATOR
-        0x2029,                # White_Space # Zp       PARAGRAPH SEPARATOR
-        0x202F,                # White_Space # Zs       NARROW NO-BREAK SPACE
-        0x205F,                # White_Space # Zs       MEDIUM MATHEMATICAL SPACE
-        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.
-      LEADERS_AND_TRAILERS = WHITESPACE + [65279] # ZERO-WIDTH NO-BREAK SPACE aka BOM
-
-      # 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
-
-      # 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.
-      def in_char_class?(codepoint, classes)
-        classes.detect { |c| database.boundary[c] === codepoint } ? true : false
-      end
-
       # Unpack the string at grapheme boundaries. Returns a list of character
       # lists.
       #
       #   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
-        eoc = codepoints.length
-        while(pos < eoc)
-          pos += 1
-          previous = codepoints[pos-1]
-          current = codepoints[pos]
-          if (
-              # CR X LF
-              ( previous == database.boundary[:cr] and current == database.boundary[:lf] ) or
-              # L X (L|V|LV|LVT)
-              ( database.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or
-              # (LV|V) X (V|T)
-              ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or
-              # (LVT|T) X (T)
-              ( in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current ) or
-              # X Extend
-              (database.boundary[:extend] === current)
-            )
-          else
-            unpacked << codepoints[marker..pos-1]
-            marker = pos
-          end
-        end
-        unpacked
+        ActiveSupport::Deprecation.warn(<<-MSG.squish)
+          ActiveSupport::Multibyte::Unicode#unpack_graphemes is deprecated and will be
+          removed from Rails 6.1. Use string.scan(/\X/).map(&:codepoints) instead.
+        MSG
+
+        string.scan(/\X/).map(&:codepoints)
       end
 
       # Reverse operation of unpack_graphemes.
       #
       #   Unicode.pack_graphemes(Unicode.unpack_graphemes('क्षि')) # => 'क्षि'
       def pack_graphemes(unpacked)
-        unpacked.flatten.pack('U*')
-      end
+        ActiveSupport::Deprecation.warn(<<-MSG.squish)
+          ActiveSupport::Multibyte::Unicode#pack_graphemes is deprecated and will be
+          removed from Rails 6.1. Use array.flatten.pack("U*") instead.
+        MSG
 
-      # Re-order codepoints so the string becomes canonical.
-      def reorder_characters(codepoints)
-        length = codepoints.length- 1
-        pos = 0
-        while pos < length do
-          cp1, cp2 = database.codepoints[codepoints[pos]], database.codepoints[codepoints[pos+1]]
-          if (cp1.combining_class > cp2.combining_class) && (cp2.combining_class > 0)
-            codepoints[pos..pos+1] = cp2.code, cp1.code
-            pos += (pos > 0 ? -1 : 1)
-          else
-            pos += 1
-          end
-        end
-        codepoints
+        unpacked.flatten.pack("U*")
       end
 
       # Decompose composed characters to the decomposed form.
       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
-            sindex = cp - HANGUL_SBASE
-            ncp = [] # new codepoints
-            ncp << HANGUL_LBASE + sindex / HANGUL_NCOUNT
-            ncp << HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT
-            tindex = sindex % HANGUL_TCOUNT
-            ncp << (HANGUL_TBASE + tindex) unless tindex == 0
-            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 == :compatibility)
-            decomposed.concat decompose(type, ncp.dup)
-          else
-            decomposed << cp
-          end
+        if type == :compatibility
+          codepoints.pack("U*").unicode_normalize(:nfkd).codepoints
+        else
+          codepoints.pack("U*").unicode_normalize(:nfd).codepoints
         end
       end
 
       # Compose decomposed characters to the composed form.
       def compose(codepoints)
-        pos = 0
-        eoa = codepoints.length - 1
-        starter_pos = 0
-        starter_char = codepoints[0]
-        previous_combining_class = -1
-        while pos < eoa
-          pos += 1
-          lindex = starter_char - HANGUL_LBASE
-          # -- Hangul
-          if 0 <= lindex and lindex < HANGUL_LCOUNT
-            vindex = codepoints[starter_pos+1] - HANGUL_VBASE rescue vindex = -1
-            if 0 <= vindex and vindex < HANGUL_VCOUNT
-              tindex = codepoints[starter_pos+2] - HANGUL_TBASE rescue tindex = -1
-              if 0 <= tindex and tindex < HANGUL_TCOUNT
-                j = starter_pos + 2
-                eoa -= 2
-              else
-                tindex = 0
-                j = starter_pos + 1
-                eoa -= 1
-              end
-              codepoints[starter_pos..j] = (lindex * HANGUL_VCOUNT + vindex) * HANGUL_TCOUNT + tindex + HANGUL_SBASE
-            end
-            starter_pos += 1
-            starter_char = codepoints[starter_pos]
-          # -- Other characters
-          else
-            current_char = codepoints[pos]
-            current = database.codepoints[current_char]
-            if current.combining_class > previous_combining_class
-              if ref = database.composition_map[starter_char]
-                composition = ref[current_char]
-              else
-                composition = nil
-              end
-              unless composition.nil?
-                codepoints[starter_pos] = composition
-                starter_char = composition
-                codepoints.delete_at pos
-                eoa -= 1
-                pos -= 1
-                previous_combining_class = -1
-              else
-                previous_combining_class = current.combining_class
-              end
-            else
-              previous_combining_class = current.combining_class
-            end
-            if current.combining_class == 0
-              starter_pos = pos
-              starter_char = codepoints[pos]
-            end
-          end
-        end
-        codepoints
+        codepoints.pack("U*").unicode_normalize(:nfc).codepoints
       end
 
-      # Ruby >= 2.1 has String#scrub, which is faster than the workaround used for < 2.1.
       # Rubinius' String#scrub, however, doesn't support ASCII-incompatible chars.
-      if '<3'.respond_to?(:scrub) && !defined?(Rubinius)
+      if !defined?(Rubinius)
         # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent
         # resulting in a valid UTF-8 string.
         #
@@ -236,7 +92,7 @@ module ActiveSupport
           reader = Encoding::Converter.new(Encoding::UTF_8, Encoding::UTF_16LE)
 
           source = string.dup
-          out = ''.force_encoding(Encoding::UTF_16LE)
+          out = "".force_encoding(Encoding::UTF_16LE)
 
           loop do
             reader.primitive_convert(source, out)
@@ -258,133 +114,43 @@ module ActiveSupport
       # * <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.
-      def normalize(string, form=nil)
+      #   Default is ActiveSupport::Multibyte::Unicode.default_normalization_form.
+      def normalize(string, form = nil)
         form ||= @default_normalization_form
-        # See http://www.unicode.org/reports/tr15, Table 1
-        codepoints = string.codepoints.to_a
-        case form
-          when :d
-            reorder_characters(decompose(:canonical, codepoints))
-          when :c
-            compose(reorder_characters(decompose(:canonical, codepoints)))
-          when :kd
-            reorder_characters(decompose(:compatibility, codepoints))
-          when :kc
-            compose(reorder_characters(decompose(:compatibility, codepoints)))
-          else
-            raise ArgumentError, "#{form} is not a valid normalization variant", caller
-        end.pack('U*')
-      end
-
-      def downcase(string)
-        apply_mapping string, :lowercase_mapping
-      end
-
-      def upcase(string)
-        apply_mapping string, :uppercase_mapping
-      end
-
-      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
-
-        # Initializing Codepoint object with default values
-        def initialize
-          @combining_class = 0
-          @uppercase_mapping = 0
-          @lowercase_mapping = 0
-        end
 
-        def swapcase_mapping
-          uppercase_mapping > 0 ? uppercase_mapping : lowercase_mapping
+        # See https://www.unicode.org/reports/tr15, Table 1
+        if alias_form = NORMALIZATION_FORM_ALIASES[form]
+          ActiveSupport::Deprecation.warn(<<-MSG.squish)
+            ActiveSupport::Multibyte::Unicode#normalize is deprecated and will be
+            removed from Rails 6.1. Use String#unicode_normalize(:#{alias_form}) instead.
+          MSG
+
+          string.unicode_normalize(alias_form)
+        else
+          ActiveSupport::Deprecation.warn(<<-MSG.squish)
+            ActiveSupport::Multibyte::Unicode#normalize is deprecated and will be
+            removed from Rails 6.1. Use String#unicode_normalize instead.
+          MSG
+
+          raise ArgumentError, "#{form} is not a valid normalization variant", caller
         end
       end
 
-      # Holds static data from the Unicode database.
-      class UnicodeDatabase
-        ATTRIBUTES = :codepoints, :composition_exclusion, :composition_map, :boundary, :cp1252
-
-        attr_writer(*ATTRIBUTES)
-
-        def initialize
-          @codepoints = Hash.new(Codepoint.new)
-          @composition_exclusion = []
-          @composition_map = {}
-          @boundary = {}
-          @cp1252 = {}
-        end
-
-        # 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__ + 1)
-            def #{attr_name}     # def codepoints
-              load               #   load
-              @#{attr_name}      #   @codepoints
-            end                  # end
-          EOS
-        end
-
-        # 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 => e
-            raise IOError.new("Couldn't load the Unicode tables for UTF8Handler (#{e.message}), ActiveSupport::Multibyte is unusable")
-          end
-
-          # Redefine the === method so we can write shorter rules for grapheme cluster breaks
-          @boundary.each do |k,_|
-            @boundary[k].instance_eval do
-              def ===(other)
-                detect { |i| i === other } ? true : false
-              end
-            end if @boundary[k].kind_of?(Array)
-          end
-
-          # define attr_reader methods for the instance variables
-          class << self
-            attr_reader(*ATTRIBUTES)
-          end
-        end
+      %w(downcase upcase swapcase).each do |method|
+        define_method(method) do |string|
+          ActiveSupport::Deprecation.warn(<<-MSG.squish)
+          ActiveSupport::Multibyte::Unicode##{method} is deprecated and
+          will be removed from Rails 6.1. Use String methods directly.
+          MSG
 
-        # 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.
-        def self.filename
-          File.expand_path File.join(dirname, "unicode_tables.dat")
+          string.send(method)
         end
       end
 
       private
-
-      def apply_mapping(string, mapping) #:nodoc:
-        database.codepoints
-        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 recode_windows1252_chars(string)
-        string.encode(Encoding::UTF_8, Encoding::Windows_1252, invalid: :replace, undef: :replace)
-      end
-
-      def database
-        @database ||= UnicodeDatabase.new
-      end
+        def recode_windows1252_chars(string)
+          string.encode(Encoding::UTF_8, Encoding::Windows_1252, invalid: :replace, undef: :replace)
+        end
     end
   end
 end

data/lib/active_support/multibyte.rb

@@ -1,7 +1,9 @@
+# frozen_string_literal: true
+
 module ActiveSupport #:nodoc:
   module Multibyte
-    autoload :Chars, 'active_support/multibyte/chars'
-    autoload :Unicode, 'active_support/multibyte/unicode'
+    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

data/lib/active_support/notifications/fanout.rb

@@ -1,5 +1,8 @@
-require 'mutex_m'
-require 'thread_safe'
+# frozen_string_literal: true
+
+require "mutex_m"
+require "concurrent/map"
+require "set"
 
 module ActiveSupport
   module Notifications
@@ -11,16 +14,22 @@ module ActiveSupport
       include Mutex_m
 
       def initialize
-        @subscribers = []
-        @listeners_for = ThreadSafe::Cache.new
+        @string_subscribers = Hash.new { |h, k| h[k] = [] }
+        @other_subscribers = []
+        @listeners_for = Concurrent::Map.new
         super
       end
 
-      def subscribe(pattern = nil, block = Proc.new)
-        subscriber = Subscribers.new pattern, block
+      def subscribe(pattern = nil, callable = nil, &block)
+        subscriber = Subscribers.new(pattern, callable || block)
         synchronize do
-          @subscribers << subscriber
-          @listeners_for.clear
+          if String === pattern
+            @string_subscribers[pattern] << subscriber
+            @listeners_for.delete(pattern)
+          else
+            @other_subscribers << subscriber
+            @listeners_for.clear
+          end
         end
         subscriber
       end
@@ -29,12 +38,19 @@ module ActiveSupport
         synchronize do
           case subscriber_or_name
           when String
-            @subscribers.reject! { |s| s.matches?(subscriber_or_name) }
+            @string_subscribers[subscriber_or_name].clear
+            @listeners_for.delete(subscriber_or_name)
+            @other_subscribers.each { |sub| sub.unsubscribe!(subscriber_or_name) }
           else
-            @subscribers.delete(subscriber_or_name)
+            pattern = subscriber_or_name.try(:pattern)
+            if String === pattern
+              @string_subscribers[pattern].delete(subscriber_or_name)
+              @listeners_for.delete(pattern)
+            else
+              @other_subscribers.delete(subscriber_or_name)
+              @listeners_for.clear
+            end
           end
-
-          @listeners_for.clear
         end
       end
 
@@ -42,8 +58,8 @@ module ActiveSupport
         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) }
+      def finish(name, id, payload, listeners = listeners_for(name))
+        listeners.each { |s| s.finish(name, id, payload) }
       end
 
       def publish(name, *args)
@@ -51,10 +67,11 @@ module ActiveSupport
       end
 
       def listeners_for(name)
-        # this is correctly done double-checked locking (ThreadSafe::Cache's lookups have volatile semantics)
+        # this is correctly done double-checked locking (Concurrent::Map'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) }
+          @listeners_for[name] ||=
+            @string_subscribers[name] + @other_subscribers.select { |s| s.subscribed_to?(name) }
         end
       end
 
@@ -68,12 +85,29 @@ module ActiveSupport
 
       module Subscribers # :nodoc:
         def self.new(pattern, listener)
-          if listener.respond_to?(:start) and listener.respond_to?(:finish)
-            subscriber = Evented.new pattern, listener
+          subscriber_class = Timed
+
+          if listener.respond_to?(:start) && listener.respond_to?(:finish)
+            subscriber_class = Evented
           else
-            subscriber = Timed.new pattern, listener
+            # Doing all this to detect a block like `proc { |x| }` vs
+            # `proc { |*x| }` or `proc { |**x| }`
+            if listener.respond_to?(:parameters)
+              params = listener.parameters
+              if params.length == 1 && params.first.first == :opt
+                subscriber_class = EventObject
+              end
+            end
           end
 
+          wrap_all pattern, subscriber_class.new(pattern, listener)
+        end
+
+        def self.event_object_subscriber(pattern, block)
+          wrap_all pattern, EventObject.new(pattern, block)
+        end
+
+        def self.wrap_all(pattern, subscriber)
           unless pattern
             AllMessages.new(subscriber)
           else
@@ -81,9 +115,33 @@ module ActiveSupport
           end
         end
 
+        class Matcher #:nodoc:
+          attr_reader :pattern, :exclusions
+
+          def self.wrap(pattern)
+            return pattern if String === pattern
+            new(pattern)
+          end
+
+          def initialize(pattern)
+            @pattern = pattern
+            @exclusions = Set.new
+          end
+
+          def unsubscribe!(name)
+            exclusions << -name if pattern === name
+          end
+
+          def ===(name)
+            pattern === name && !exclusions.include?(name)
+          end
+        end
+
         class Evented #:nodoc:
+          attr_reader :pattern
+
           def initialize(pattern, delegate)
-            @pattern = pattern
+            @pattern = Matcher.wrap(pattern)
             @delegate = delegate
             @can_publish = delegate.respond_to?(:publish)
           end
@@ -103,11 +161,15 @@ module ActiveSupport
           end
 
           def subscribed_to?(name)
-            @pattern === name
+            pattern === name
           end
 
           def matches?(name)
-            @pattern && @pattern === name
+            pattern && pattern === name
+          end
+
+          def unsubscribe!(name)
+            pattern.unsubscribe!(name)
           end
         end
 
@@ -128,6 +190,27 @@ module ActiveSupport
           end
         end
 
+        class EventObject < Evented
+          def start(name, id, payload)
+            stack = Thread.current[:_event_stack] ||= []
+            event = build_event name, id, payload
+            event.start!
+            stack.push event
+          end
+
+          def finish(name, id, payload)
+            stack = Thread.current[:_event_stack]
+            event = stack.pop
+            event.finish!
+            @delegate.call event
+          end
+
+          private
+            def build_event(name, id, payload)
+              ActiveSupport::Notifications::Event.new name, nil, nil, id, payload
+            end
+        end
+
         class AllMessages # :nodoc:
           def initialize(delegate)
             @delegate = delegate
@@ -149,6 +232,10 @@ module ActiveSupport
             true
           end
 
+          def unsubscribe!(*)
+            false
+          end
+
           alias :matches? :===
         end
       end