activesupport 5.0.7.1

data/lib/active_support/multibyte/unicode.rb

@@ -0,0 +1,413 @@
+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
+      # information about normalization.
+      NORMALIZATION_FORMS = [:c, :kc, :d, :kd]
+
+      # The Unicode version that is supported by the implementation
+      UNICODE_VERSION = '8.0.0'
+
+      # 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
+      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*'.freeze }.join('|'.freeze)
+      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]
+
+          should_break =
+            # GB3. CR X LF
+            if previous == database.boundary[:cr] and current == database.boundary[:lf]
+              false
+            # GB4. (Control|CR|LF) ÷
+            elsif previous and 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 and in_char_class?(current, [:l,:v,:lv,:lvt])
+              false
+            # GB7. (LV|V) X (V|T)
+            elsif in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t])
+              false
+            # GB8. (LVT|T) X (T)
+            elsif in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current
+              false
+            # GB8a. Regional_Indicator X Regional_Indicator
+            elsif database.boundary[:regional_indicator] === previous and database.boundary[:regional_indicator] === current
+              false
+            # GB9. X Extend
+            elsif database.boundary[:extend] === current
+              false
+            # GB9a. X SpacingMark
+            elsif database.boundary[:spacingmark] === current
+              false
+            # GB9b. Prepend X
+            elsif database.boundary[:prepend] === previous
+              false
+            # GB10. Any ÷ Any
+            else
+              true
+            end
+
+          if should_break
+            unpacked << codepoints[marker..pos-1]
+            marker = pos
+          end
+        end
+        unpacked
+      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
+      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
+        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
+      end
+
+      # Rubinius' String#scrub, however, doesn't support ASCII-incompatible chars.
+      if !defined?(Rubinius)
+        # 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.
+        def tidy_bytes(string, force = false)
+          return string if string.empty?
+          return recode_windows1252_chars(string) if force
+          string.scrub { |bad| recode_windows1252_chars(bad) }
+        end
+      else
+        def tidy_bytes(string, force = false)
+          return string if string.empty?
+          return recode_windows1252_chars(string) if force
+
+          # We can't transcode to the same format, so we choose a nearly-identical encoding.
+          # We're going to 'transcode' bytes from UTF-8 when possible, then fall back to
+          # CP1252 when we get errors. The final string will be 'converted' back to UTF-8
+          # before returning.
+          reader = Encoding::Converter.new(Encoding::UTF_8, Encoding::UTF_16LE)
+
+          source = string.dup
+          out = ''.force_encoding(Encoding::UTF_16LE)
+
+          loop do
+            reader.primitive_convert(source, out)
+            _, _, _, error_bytes, _ = reader.primitive_errinfo
+            break if error_bytes.nil?
+            out << error_bytes.encode(Encoding::UTF_16LE, Encoding::Windows_1252, invalid: :replace, undef: :replace)
+          end
+
+          reader.finish
+
+          out.encode!(Encoding::UTF_8)
+        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.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")
+        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
+    end
+  end
+end

data/lib/active_support/notifications.rb

@@ -0,0 +1,212 @@
+require 'active_support/notifications/instrumenter'
+require 'active_support/notifications/fanout'
+require 'active_support/per_thread_registry'
+
+module ActiveSupport
+  # = Notifications
+  #
+  # <tt>ActiveSupport::Notifications</tt> provides an instrumentation API for
+  # Ruby.
+  #
+  # == Instrumenters
+  #
+  # To instrument an event you just need to do:
+  #
+  #   ActiveSupport::Notifications.instrument('render', extra: :information) do
+  #     render text: 'Foo'
+  #   end
+  #
+  # That first executes the block and then notifies all subscribers once done.
+  #
+  # In the example above +render+ is the name of the event, and the rest is called
+  # the _payload_. The payload is a mechanism that allows instrumenters to pass
+  # extra information to subscribers. Payloads consist of a hash whose contents
+  # are arbitrary and generally depend on the event.
+  #
+  # == Subscribers
+  #
+  # You can consume those events and the information they provide by registering
+  # a subscriber.
+  #
+  #   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 this notification
+  #     payload # => Hash, the payload
+  #   end
+  #
+  # For instance, let's store all "render" events in an array:
+  #
+  #   events = []
+  #
+  #   ActiveSupport::Notifications.subscribe('render') do |*args|
+  #     events << ActiveSupport::Notifications::Event.new(*args)
+  #   end
+  #
+  # That code returns right away, you are just subscribing to "render" events.
+  # The block is saved and will be called whenever someone instruments "render":
+  #
+  #   ActiveSupport::Notifications.instrument('render', extra: :information) do
+  #     render text: 'Foo'
+  #   end
+  #
+  #   event = events.first
+  #   event.name      # => "render"
+  #   event.duration  # => 10 (in milliseconds)
+  #   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
+  # (something like "535801666f04d0298cd6"), and a hash with the payload, in
+  # that order.
+  #
+  # If an exception happens during that particular instrumentation the payload will
+  # 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.
+  #
+  # As the previous 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.
+  #
+  # It is also possible to pass an object which responds to <tt>call</tt> method
+  # as the second parameter to the <tt>subscribe</tt> method instead of a block:
+  #
+  #   module ActionController
+  #     class PageRequest
+  #       def call(name, started, finished, unique_id, payload)
+  #         Rails.logger.debug ['notification:', name, started, finished, unique_id, payload].join(' ')
+  #       end
+  #     end
+  #   end
+  #
+  #   ActiveSupport::Notifications.subscribe('process_action.action_controller', ActionController::PageRequest.new)
+  #
+  # resulting in the following output within the logs including a hash with the payload:
+  #
+  #   notification: process_action.action_controller 2012-04-13 01:08:35 +0300 2012-04-13 01:08:35 +0300 af358ed7fab884532ec7 {
+  #      controller: "Devise::SessionsController",
+  #      action: "new",
+  #      params: {"action"=>"new", "controller"=>"devise/sessions"},
+  #      format: :html,
+  #      method: "GET",
+  #      path: "/login/sign_in",
+  #      status: 200,
+  #      view_runtime: 279.3080806732178,
+  #      db_runtime: 40.053
+  #    }
+  #
+  # You can also subscribe to all events whose name matches a certain regexp:
+  #
+  #   ActiveSupport::Notifications.subscribe(/render/) do |*args|
+  #     ...
+  #   end
+  #
+  # and even pass no argument to <tt>subscribe</tt>, in which case you are subscribing
+  # to all events.
+  #
+  # == Temporary Subscriptions
+  #
+  # Sometimes you do not want to subscribe to an event for the entire life of
+  # the application. There are two ways to unsubscribe.
+  #
+  # WARNING: The instrumentation framework is designed for long-running subscribers,
+  # use this feature sparingly because it wipes some internal caches and that has
+  # a negative impact on performance.
+  #
+  # === Subscribe While a Block Runs
+  #
+  # You can subscribe to some event temporarily while some block runs. For
+  # example, in
+  #
+  #   callback = lambda {|*args| ... }
+  #   ActiveSupport::Notifications.subscribed(callback, "sql.active_record") do
+  #     ...
+  #   end
+  #
+  # the callback will be called for all "sql.active_record" events instrumented
+  # during the execution of the block. The callback is unsubscribed automatically
+  # after that.
+  #
+  # === Manual Unsubscription
+  #
+  # The +subscribe+ method returns a subscriber object:
+  #
+  #   subscriber = ActiveSupport::Notifications.subscribe("render") do |*args|
+  #     ...
+  #   end
+  #
+  # To prevent that block from being called anymore, just unsubscribe passing
+  # that reference:
+  #
+  #   ActiveSupport::Notifications.unsubscribe(subscriber)
+  #
+  # You can also unsubscribe by passing the name of the subscriber object. Note
+  # that this will unsubscribe all subscriptions with the given name:
+  #
+  #   ActiveSupport::Notifications.unsubscribe("render")
+  #
+  # == Default Queue
+  #
+  # Notifications ships with a queue implementation that consumes and publishes events
+  # to all log subscribers. You can use any queue implementation you want.
+  #
+  module Notifications
+    class << self
+      attr_accessor :notifier
+
+      def publish(name, *args)
+        notifier.publish(name, *args)
+      end
+
+      def instrument(name, payload = {})
+        if notifier.listening?(name)
+          instrumenter.instrument(name, payload) { yield payload if block_given? }
+        else
+          yield payload if block_given?
+        end
+      end
+
+      def subscribe(*args, &block)
+        notifier.subscribe(*args, &block)
+      end
+
+      def subscribed(callback, *args, &block)
+        subscriber = subscribe(*args, &callback)
+        yield
+      ensure
+        unsubscribe(subscriber)
+      end
+
+      def unsubscribe(subscriber_or_name)
+        notifier.unsubscribe(subscriber_or_name)
+      end
+
+      def instrumenter
+        InstrumentationRegistry.instance.instrumenter_for(notifier)
+      end
+    end
+
+    # This class is a registry which holds all of the +Instrumenter+ objects
+    # in a particular thread local. To access the +Instrumenter+ object for a
+    # particular +notifier+, you can call the following method:
+    #
+    #   InstrumentationRegistry.instrumenter_for(notifier)
+    #
+    # The instrumenters for multiple notifiers are held in a single instance of
+    # this class.
+    class InstrumentationRegistry # :nodoc:
+      extend ActiveSupport::PerThreadRegistry
+
+      def initialize
+        @registry = {}
+      end
+
+      def instrumenter_for(notifier)
+        @registry[notifier] ||= Instrumenter.new(notifier)
+      end
+    end
+
+    self.notifier = Fanout.new
+  end
+end