activesupport 5.2.4.4 → 6.1.1

data/lib/active_support/multibyte/unicode.rb

@@ -5,215 +5,33 @@ module ActiveSupport
     module Unicode
       extend self
 
-      # 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 = "9.0.0"
-
-      # The default normalization used for operations that require
-      # normalization. It can be set to any of the normalizations
-      # in NORMALIZATION_FORMS.
-      #
-      #   ActiveSupport::Multibyte::Unicode.default_normalization_form = :c
-      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
-
-      # 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]
-
-          # See http://unicode.org/reports/tr29/#Grapheme_Cluster_Boundary_Rules
-          should_break =
-            if pos == eoc
-              true
-            # GB3. CR X LF
-            elsif previous == database.boundary[:cr] && current == database.boundary[:lf]
-              false
-            # GB4. (Control|CR|LF) ÷
-            elsif previous && in_char_class?(previous, [:control, :cr, :lf])
-              true
-            # GB5. ÷ (Control|CR|LF)
-            elsif in_char_class?(current, [:control, :cr, :lf])
-              true
-            # GB6. L X (L|V|LV|LVT)
-            elsif database.boundary[:l] === previous && in_char_class?(current, [:l, :v, :lv, :lvt])
-              false
-            # GB7. (LV|V) X (V|T)
-            elsif in_char_class?(previous, [:lv, :v]) && in_char_class?(current, [:v, :t])
-              false
-            # GB8. (LVT|T) X (T)
-            elsif in_char_class?(previous, [:lvt, :t]) && database.boundary[:t] === current
-              false
-            # GB9. X (Extend | ZWJ)
-            elsif in_char_class?(current, [:extend, :zwj])
-              false
-            # GB9a. X SpacingMark
-            elsif database.boundary[:spacingmark] === current
-              false
-            # GB9b. Prepend X
-            elsif database.boundary[:prepend] === previous
-              false
-            # GB10. (E_Base | EBG) Extend* X E_Modifier
-            elsif (marker...pos).any? { |i| in_char_class?(codepoints[i], [:e_base, :e_base_gaz]) && codepoints[i + 1...pos].all? { |c| database.boundary[:extend] === c } } && database.boundary[:e_modifier] === current
-              false
-            # GB11. ZWJ X (Glue_After_Zwj | EBG)
-            elsif database.boundary[:zwj] === previous && in_char_class?(current, [:glue_after_zwj, :e_base_gaz])
-              false
-            # GB12. ^ (RI RI)* RI X RI
-            # GB13. [^RI] (RI RI)* RI X RI
-            elsif codepoints[marker..pos].all? { |c| database.boundary[:regional_indicator] === c } && codepoints[marker..pos].count { |c| database.boundary[:regional_indicator] === c }.even?
-              false
-            # GB999. Any ÷ Any
-            else
-              true
-            end
+      UNICODE_VERSION = RbConfig::CONFIG["UNICODE_VERSION"]
 
-          if should_break
-            unpacked << codepoints[marker..pos - 1]
-            marker = pos
-          end
-        end
-        unpacked
+      def default_normalization_form
+        ActiveSupport::Deprecation.warn(
+          "ActiveSupport::Multibyte::Unicode.default_normalization_form is deprecated and will be removed in Rails 6.2."
+        )
       end
 
-      # Reverse operation of unpack_graphemes.
-      #
-      #   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.
-      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
+      def default_normalization_form=(_)
+        ActiveSupport::Deprecation.warn(
+          "ActiveSupport::Multibyte::Unicode.default_normalization_form= is deprecated and will be removed in Rails 6.2."
+        )
       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 && 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) && (!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 && lindex < HANGUL_LCOUNT
-            vindex = codepoints[starter_pos + 1] - HANGUL_VBASE rescue vindex = -1
-            if 0 <= vindex && vindex < HANGUL_VCOUNT
-              tindex = codepoints[starter_pos + 2] - HANGUL_TBASE rescue tindex = -1
-              if 0 <= tindex && 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
 
       # Rubinius' String#scrub, however, doesn't support ASCII-incompatible chars.
@@ -224,7 +42,7 @@ module ActiveSupport
         # 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)
-          return string if string.empty?
+          return string if string.empty? || string.ascii_only?
           return recode_windows1252_chars(string) if force
           string.scrub { |bad| recode_windows1252_chars(bad) }
         end
@@ -255,140 +73,10 @@ module ActiveSupport
         end
       end
 
-      # 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::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*".freeze)
-      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
-        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_key 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
-
-        # Returns the directory in which the data files are stored.
-        def self.dirname
-          File.expand_path("../values", __dir__)
-        end
-
-        # Returns the filename for the data file for this version.
-        def self.filename
-          File.expand_path File.join(dirname, "unicode_tables.dat")
-        end
-      end
-
       private
-
-        def apply_mapping(string, mapping)
-          database.codepoints
-          string.each_codepoint.map do |codepoint|
-            cp = database.codepoints[codepoint]
-            if cp && (ncp = cp.send(mapping)) && 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
     end
   end
 end

data/lib/active_support/notifications.rb

@@ -34,10 +34,23 @@ module ActiveSupport
   #     name    # => String, name of the event (such as 'render' from above)
   #     start   # => Time, when the instrumented block started execution
   #     finish  # => Time, when the instrumented block ended execution
-  #     id      # => String, unique ID for this notification
+  #     id      # => String, unique ID for the instrumenter that fired the event
   #     payload # => Hash, the payload
   #   end
   #
+  # Here, the +start+ and +finish+ values represent wall-clock time. If you are
+  # concerned about accuracy, you can register a monotonic subscriber.
+  #
+  #   ActiveSupport::Notifications.monotonic_subscribe('render') do |name, start, finish, id, payload|
+  #     name    # => String, name of the event (such as 'render' from above)
+  #     start   # => Monotonic time, when the instrumented block started execution
+  #     finish  # => Monotonic time, when the instrumented block ended execution
+  #     id      # => String, unique ID for the instrumenter that fired the event
+  #     payload # => Hash, the payload
+  #   end
+  #
+  # The +start+ and +finish+ values above represent monotonic time.
+  #
   # For instance, let's store all "render" events in an array:
   #
   #   events = []
@@ -59,7 +72,7 @@ module ActiveSupport
   #   event.payload   # => { extra: :information }
   #
   # The block in the <tt>subscribe</tt> call gets the name of the event, start
-  # timestamp, end timestamp, a string with a unique identifier for that event
+  # timestamp, end timestamp, a string with a unique identifier for that event's instrumenter
   # (something like "535801666f04d0298cd6"), and a hash with the payload, in
   # that order.
   #
@@ -67,9 +80,12 @@ module ActiveSupport
   # have a key <tt>:exception</tt> with an array of two elements as value: a string with
   # the name of the exception class, and the exception message.
   # The <tt>:exception_object</tt> key of the payload will have the exception
-  # itself as the value.
+  # itself as the value:
   #
-  # As the previous example depicts, the class <tt>ActiveSupport::Notifications::Event</tt>
+  #   event.payload[:exception]         # => ["ArgumentError", "Invalid value"]
+  #   event.payload[:exception_object]  # => #<ArgumentError: Invalid value>
+  #
+  # As the earlier example depicts, the class <tt>ActiveSupport::Notifications::Event</tt>
   # is able to take the arguments as they come and provide an object-oriented
   # interface to that data.
   #
@@ -132,6 +148,16 @@ module ActiveSupport
   # during the execution of the block. The callback is unsubscribed automatically
   # after that.
   #
+  # To record +started+ and +finished+ values with monotonic time,
+  # specify the optional <tt>:monotonic</tt> option to the
+  # <tt>subscribed</tt> method. The <tt>:monotonic</tt> option is set
+  # to +false+ by default.
+  #
+  #   callback = lambda {|name, started, finished, unique_id, payload| ... }
+  #   ActiveSupport::Notifications.subscribed(callback, "sql.active_record", monotonic: true) do
+  #     ...
+  #   end
+  #
   # === Manual Unsubscription
   #
   # The +subscribe+ method returns a subscriber object:
@@ -150,6 +176,15 @@ module ActiveSupport
   #
   #   ActiveSupport::Notifications.unsubscribe("render")
   #
+  # Subscribers using a regexp or other pattern-matching object will remain subscribed
+  # to all events that match their original pattern, unless those events match a string
+  # passed to `unsubscribe`:
+  #
+  #   subscriber = ActiveSupport::Notifications.subscribe(/render/) { }
+  #   ActiveSupport::Notifications.unsubscribe('render_template.action_view')
+  #   subscriber.matches?('render_template.action_view') # => false
+  #   subscriber.matches?('render_partial.action_view') # => true
+  #
   # == Default Queue
   #
   # Notifications ships with a queue implementation that consumes and publishes events
@@ -171,12 +206,41 @@ module ActiveSupport
         end
       end
 
-      def subscribe(*args, &block)
-        notifier.subscribe(*args, &block)
+      # Subscribe to a given event name with the passed +block+.
+      #
+      # You can subscribe to events by passing a String to match exact event
+      # names, or by passing a Regexp to match all events that match a pattern.
+      #
+      #   ActiveSupport::Notifications.subscribe(/render/) do |*args|
+      #     @event = ActiveSupport::Notifications::Event.new(*args)
+      #   end
+      #
+      # The +block+ will receive five parameters with information about the event:
+      #
+      #   ActiveSupport::Notifications.subscribe('render') do |name, start, finish, id, payload|
+      #     name    # => String, name of the event (such as 'render' from above)
+      #     start   # => Time, when the instrumented block started execution
+      #     finish  # => Time, when the instrumented block ended execution
+      #     id      # => String, unique ID for the instrumenter that fired the event
+      #     payload # => Hash, the payload
+      #   end
+      #
+      # If the block passed to the method only takes one parameter,
+      # it will yield an event object to the block:
+      #
+      #   ActiveSupport::Notifications.subscribe(/render/) do |event|
+      #     @event = event
+      #   end
+      def subscribe(pattern = nil, callback = nil, &block)
+        notifier.subscribe(pattern, callback, monotonic: false, &block)
+      end
+
+      def monotonic_subscribe(pattern = nil, callback = nil, &block)
+        notifier.subscribe(pattern, callback, monotonic: true, &block)
       end
 
-      def subscribed(callback, *args, &block)
-        subscriber = subscribe(*args, &callback)
+      def subscribed(callback, pattern = nil, monotonic: false, &block)
+        subscriber = notifier.subscribe(pattern, callback, monotonic: monotonic)
         yield
       ensure
         unsubscribe(subscriber)