Merge pull request #31049 from gwincr11/cg-blank

Add support for multiple encodings in String.blank?

activesupport/lib/active_support/core_ext/object/blank.rb

 # frozen_string_literal: true
 
 require "active_support/core_ext/regexp"
+require "concurrent/map"
 
 class Object
   # An object is blank if it's false, empty, or a whitespace string.
@@ -102,6 +103,9 @@ class Hash
 
 class String
   BLANK_RE = /\A[[:space:]]*\z/
+  ENCODED_BLANKS = Concurrent::Map.new do |h, enc|
+    h[enc] = Regexp.new(BLANK_RE.source.encode(enc), BLANK_RE.options | Regexp::FIXEDENCODING)
+  end
 
   # A string is blank if it's empty or contains whitespaces only:
   #
@@ -119,7 +123,12 @@ def blank?
     # The regexp that matches blank strings is expensive. For the case of empty
     # strings we can speed up this method (~3.5x) with an empty? call. The
     # penalty for the rest of strings is marginal.
-    empty? || BLANK_RE.match?(self)
+    empty? ||
+      begin
+        BLANK_RE.match?(self)
+      rescue Encoding::CompatibilityError
+        ENCODED_BLANKS[self.encoding].match?(self)
+      end
   end
 end
 

activesupport/test/core_ext/object/blank_test.rb

@@ -16,8 +16,8 @@ def empty?
     end
   end
 
-  BLANK = [ EmptyTrue.new, nil, false, "", "   ", "  \n\t  \r ", "　", "\u00a0", [], {} ]
-  NOT   = [ EmptyFalse.new, Object.new, true, 0, 1, "a", [nil], { nil => 0 }, Time.now ]
+  BLANK = [ EmptyTrue.new, nil, false, "", "   ", "  \n\t  \r ", "　", "\u00a0", [], {}, " ".encode("UTF-16LE")]
+  NOT   = [ EmptyFalse.new, Object.new, true, 0, 1, "a", [nil], { nil => 0 }, Time.now , "my value".encode("UTF-16LE")]
 
   def test_blank
     BLANK.each { |v| assert_equal true, v.blank?,  "#{v.inspect} should be blank" }