activesupport 5.0.0 → 6.1.0

data/lib/active_support/multibyte/chars.rb

@@ -1,7 +1,10 @@
-require 'active_support/json'
-require 'active_support/core_ext/string/access'
-require 'active_support/core_ext/string/behavior'
-require 'active_support/core_ext/module/delegation'
+# frozen_string_literal: true
+
+require "active_support/json"
+require "active_support/core_ext/string/access"
+require "active_support/core_ext/string/behavior"
+require "active_support/core_ext/symbol/starts_ends_with"
+require "active_support/core_ext/module/delegation"
 
 module ActiveSupport #:nodoc:
   module Multibyte #:nodoc:
@@ -15,7 +18,8 @@ module ActiveSupport #:nodoc:
     # through the +mb_chars+ method. Methods which would normally return a
     # String object now return a Chars object so methods can be chained.
     #
-    #   'The Perfect String  '.mb_chars.downcase.strip.normalize # => "the perfect string"
+    #   'The Perfect String  '.mb_chars.downcase.strip
+    #   # => #<ActiveSupport::Multibyte::Chars:0x007fdc434ccc10 @wrapped_string="the perfect string">
     #
     # Chars objects are perfectly interchangeable with String objects as long as
     # no explicit class checks are made. If certain methods do explicitly check
@@ -45,7 +49,7 @@ module ActiveSupport #:nodoc:
       alias to_s wrapped_string
       alias to_str wrapped_string
 
-      delegate :<=>, :=~, :acts_like_string?, :to => :wrapped_string
+      delegate :<=>, :=~, :match?, :acts_like_string?, to: :wrapped_string
 
       # Creates a new Chars instance by wrapping _string_.
       def initialize(string)
@@ -56,7 +60,7 @@ module ActiveSupport #:nodoc:
       # Forward all undefined methods to the wrapped string.
       def method_missing(method, *args, &block)
         result = @wrapped_string.__send__(method, *args, &block)
-        if method.to_s =~ /!$/
+        if method.end_with?("!")
           self if result
         else
           result.kind_of?(String) ? chars(result) : result
@@ -70,12 +74,6 @@ module ActiveSupport #:nodoc:
         @wrapped_string.respond_to?(method, include_private)
       end
 
-      # Returns +true+ when the proxy class can handle the string. Returns
-      # +false+ otherwise.
-      def self.consumes?(string)
-        string.encoding == Encoding::UTF_8
-      end
-
       # Works just like <tt>String#split</tt>, with the exception that the items
       # in the resulting list are Chars instances instead of String. This makes
       # chaining methods easier.
@@ -86,7 +84,7 @@ module ActiveSupport #:nodoc:
       end
 
       # Works like <tt>String#slice!</tt>, but returns an instance of
-      # Chars, or nil if the string was not modified. The string will not be
+      # Chars, or +nil+ if the string was not modified. The string will not be
       # modified if the range given is out of bounds
       #
       #   string = 'Welcome'
@@ -105,7 +103,7 @@ module ActiveSupport #:nodoc:
       #
       #   'Café'.mb_chars.reverse.to_s # => 'éfaC'
       def reverse
-        chars(Unicode.unpack_graphemes(@wrapped_string).reverse.flatten.pack('U*'))
+        chars(@wrapped_string.scan(/\X/).reverse.join)
       end
 
       # Limits the byte size of the string to a number of bytes without breaking
@@ -114,63 +112,24 @@ module ActiveSupport #:nodoc:
       #
       #   'こんにちは'.mb_chars.limit(7).to_s # => "こん"
       def limit(limit)
-        slice(0...translate_offset(limit))
-      end
-
-      # Converts characters in the string to uppercase.
-      #
-      #   'Laurent, où sont les tests ?'.mb_chars.upcase.to_s # => "LAURENT, OÙ SONT LES TESTS ?"
-      def upcase
-        chars Unicode.upcase(@wrapped_string)
-      end
-
-      # Converts characters in the string to lowercase.
-      #
-      #   'VĚDA A VÝZKUM'.mb_chars.downcase.to_s # => "věda a výzkum"
-      def downcase
-        chars Unicode.downcase(@wrapped_string)
-      end
-
-      # Converts characters in the string to the opposite case.
-      #
-      #    'El Cañón".mb_chars.swapcase.to_s # => "eL cAÑÓN"
-      def swapcase
-        chars Unicode.swapcase(@wrapped_string)
-      end
-
-      # Converts the first character to uppercase and the remainder to lowercase.
-      #
-      #  'über'.mb_chars.capitalize.to_s # => "Über"
-      def capitalize
-        (slice(0) || chars('')).upcase + (slice(1..-1) || chars('')).downcase
+        chars(@wrapped_string.truncate_bytes(limit, omission: nil))
       end
 
       # Capitalizes the first letter of every word, when possible.
       #
-      #   "ÉL QUE SE ENTERÓ".mb_chars.titleize    # => "Él Que Se Enteró"
-      #   "日本語".mb_chars.titleize                 # => "日本語"
+      #   "ÉL QUE SE ENTERÓ".mb_chars.titleize.to_s    # => "Él Que Se Enteró"
+      #   "日本語".mb_chars.titleize.to_s               # => "日本語"
       def titleize
-        chars(downcase.to_s.gsub(/\b('?\S)/u) { Unicode.upcase($1)})
+        chars(downcase.to_s.gsub(/\b('?\S)/u) { $1.upcase })
       end
       alias_method :titlecase, :titleize
 
-      # Returns the KC normalization of the string by default. NFKC is
-      # considered the best normalization form for passing strings to databases
-      # and validations.
-      #
-      # * <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(form = nil)
-        chars(Unicode.normalize(@wrapped_string, form))
-      end
-
       # Performs canonical decomposition on all the characters.
       #
       #   'é'.length                         # => 2
       #   'é'.mb_chars.decompose.to_s.length # => 3
       def decompose
-        chars(Unicode.decompose(:canonical, @wrapped_string.codepoints.to_a).pack('U*'))
+        chars(Unicode.decompose(:canonical, @wrapped_string.codepoints.to_a).pack("U*"))
       end
 
       # Performs composition on all the characters.
@@ -178,7 +137,7 @@ module ActiveSupport #:nodoc:
       #   'é'.length                       # => 3
       #   'é'.mb_chars.compose.to_s.length # => 2
       def compose
-        chars(Unicode.compose(@wrapped_string.codepoints.to_a).pack('U*'))
+        chars(Unicode.compose(@wrapped_string.codepoints.to_a).pack("U*"))
       end
 
       # Returns the number of grapheme clusters in the string.
@@ -186,7 +145,7 @@ module ActiveSupport #:nodoc:
       #   'क्षि'.mb_chars.length   # => 4
       #   'क्षि'.mb_chars.grapheme_length # => 3
       def grapheme_length
-        Unicode.unpack_graphemes(@wrapped_string).length
+        @wrapped_string.scan(/\X/).length
       end
 
       # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent
@@ -202,28 +161,15 @@ module ActiveSupport #:nodoc:
         to_s.as_json(options)
       end
 
-      %w(capitalize downcase reverse tidy_bytes upcase).each do |method|
+      %w(reverse tidy_bytes).each do |method|
         define_method("#{method}!") do |*args|
-          @wrapped_string = send(method, *args).to_s
+          @wrapped_string = public_send(method, *args).to_s
           self
         end
       end
 
-      protected
-
-        def translate_offset(byte_offset) #:nodoc:
-          return nil if byte_offset.nil?
-          return 0   if @wrapped_string == ''
-
-          begin
-            @wrapped_string.byteslice(0...byte_offset).unpack('U*').length
-          rescue ArgumentError
-            byte_offset -= 1
-            retry
-          end
-        end
-
-        def chars(string) #:nodoc:
+      private
+        def chars(string)
           self.class.new(string)
         end
     end

data/lib/active_support/multibyte/unicode.rb

@@ -1,238 +1,37 @@
+# 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
-      # 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
+      UNICODE_VERSION = RbConfig::CONFIG["UNICODE_VERSION"]
 
-      # Reverse operation of unpack_graphemes.
-      #
-      #   Unicode.pack_graphemes(Unicode.unpack_graphemes('क्षि')) # => 'क्षि'
-      def pack_graphemes(unpacked)
-        unpacked.flatten.pack('U*')
+      def default_normalization_form
+        ActiveSupport::Deprecation.warn(
+          "ActiveSupport::Multibyte::Unicode.default_normalization_form is deprecated and will be removed in Rails 6.2."
+        )
       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 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
 
       # Rubinius' String#scrub, however, doesn't support ASCII-incompatible chars.
@@ -243,7 +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
@@ -259,7 +58,7 @@ 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)
@@ -274,140 +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.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
+        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