Deprecate Unicode#normalize and Chars#normalize (#34202)

3 files changed, 44 insertions, 16 deletions

diff --git a/activesupport/lib/active_support/inflector/transliterate.rb b/activesupport/lib/active_support/inflector/transliterate.rb
index dbc8b8a2fa..0d2a17970f 100644
--- a/activesupport/lib/active_support/inflector/transliterate.rb
+++ b/activesupport/lib/active_support/inflector/transliterate.rb
@@ -62,9 +62,9 @@ module ActiveSupport
       raise ArgumentError, "Can only transliterate strings. Received #{string.class.name}" unless string.is_a?(String)
 
       I18n.transliterate(
-        ActiveSupport::Multibyte::Unicode.normalize(
-          ActiveSupport::Multibyte::Unicode.tidy_bytes(string), :c),
-        replacement: replacement)
+        ActiveSupport::Multibyte::Unicode.tidy_bytes(string).unicode_normalize(:nfc),
+        replacement: replacement
+      )
     end
 
     # Replaces special characters in a string so that it may be used as part of
diff --git a/activesupport/lib/active_support/multibyte/chars.rb b/activesupport/lib/active_support/multibyte/chars.rb
index 01a0cc131f..3e846271b2 100644
--- a/activesupport/lib/active_support/multibyte/chars.rb
+++ b/activesupport/lib/active_support/multibyte/chars.rb
@@ -17,7 +17,7 @@ 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  '.mb_chars.downcase.strip
     #   # => #<ActiveSupport::Multibyte::Chars:0x007fdc434ccc10 @wrapped_string="the perfect string">
     #
     # Chars objects are perfectly interchangeable with String objects as long as
@@ -137,7 +137,24 @@ module ActiveSupport #:nodoc:
       #   <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))
+        form ||= Unicode.default_normalization_form
+
+        # See https://www.unicode.org/reports/tr15, Table 1
+        if alias_form = Unicode::NORMALIZATION_FORM_ALIASES[form]
+          ActiveSupport::Deprecation.warn(<<-MSG.squish)
+            ActiveSupport::Multibyte::Chars#normalize is deprecated and will be
+            removed from Rails 6.1. Use #unicode_normalize(:#{alias_form}) instead.
+          MSG
+
+          send(:unicode_normalize, alias_form)
+        else
+          ActiveSupport::Deprecation.warn(<<-MSG.squish)
+            ActiveSupport::Multibyte::Chars#normalize is deprecated and will be
+            removed from Rails 6.1. Use #unicode_normalize instead.
+          MSG
+
+          raise ArgumentError, "#{form} is not a valid normalization variant", caller
+        end
       end
 
       # Performs canonical decomposition on all the characters.
diff --git a/activesupport/lib/active_support/multibyte/unicode.rb b/activesupport/lib/active_support/multibyte/unicode.rb
index a3261126d6..43d196eeeb 100644
--- a/activesupport/lib/active_support/multibyte/unicode.rb
+++ b/activesupport/lib/active_support/multibyte/unicode.rb
@@ -6,10 +6,17 @@ module ActiveSupport
       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 = RbConfig::CONFIG["UNICODE_VERSION"]
 
@@ -100,17 +107,21 @@ module ActiveSupport
       #   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
-        case form
-        when :d
-          string.unicode_normalize(:nfd)
-        when :c
-          string.unicode_normalize(:nfc)
-        when :kd
-          string.unicode_normalize(:nfkd)
-        when :kc
-          string.unicode_normalize(:nfkc)
+
+        # 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