Improve performance of URI::MailTo::EMAIL_REGEXP

nobu · nobu · commit 7363a134ac91 · 2025-07-12T19:31:31.000+09:00
Fix the performance regression at #172 for valid emails. ``` yml prelude: | require 'uri/mailto' n = 1000 re = URI::MailTo::EMAIL_REGEXP benchmark: n.t..t.: re.match?("n.t..t.@docomo.ne.jp") example: re.match?("example@example.info") ``` | |released| 788274b| c5974f0| this| |:--------|-------:|-------:|-------:|-------:| |n.t..t. | 3.795M| 4.864M| 4.993M| 8.739M| | | -| 1.28x| 1.32x| 2.30x| |example | 3.911M| 3.740M| 2.838M| 3.880M| | | 1.38x| 1.32x| -| 1.37x|
diff --git a/lib/uri/mailto.rb b/lib/uri/mailto.rb
@@ -52,7 +52,11 @@ class MailTo < Generic
     HEADER_REGEXP  = /\A(?<hfield>(?:%\h\h|[!$'-.0-;@-Z_a-z~])*=(?:%\h\h|[!$'-.0-;@-Z_a-z~])*)(?:&\g<hfield>)*\z/
     # practical regexp for email address
     # https://html.spec.whatwg.org/multipage/input.html#valid-e-mail-address
-    EMAIL_REGEXP = /\A(?!\.)(?!.*\.{2})[a-zA-Z0-9.!\#$%&'*+\/=?^_`{|}~-]+(?<!\.)@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*\z/
+    EMAIL_REGEXP = %r[\A#{
+      atext = %q[(?:[a-zA-Z0-9!\#$%&'*+\/=?^_`{|}~-]+)]
+    }(?:\.#{atext})*@#{
+      label = %q[(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)]
+    }(?:\.#{label})*\z]
     # :startdoc:
 
     #
diff --git a/test/uri/test_mailto.rb b/test/uri/test_mailto.rb
@@ -210,6 +210,22 @@ def test_check_to
     end
   end
 
+  def test_email_regexp
+    re = URI::MailTo::EMAIL_REGEXP
+
+    rate = 1000
+    longlabel = '.' + 'invalid'.ljust(63, 'd')
+    endlabel = ''
+    pre = ->(n) {'a@invalid' + longlabel*(n*rate) + endlabel}
+    assert_linear_performance(1..10, pre: pre) do |to|
+      re =~ to or flunk
+    end
+    endlabel = '.' + 'email'.rjust(64, 'd')
+    assert_linear_performance(1..10, pre: pre) do |to|
+      re =~ to and flunk
+    end
+  end
+
   def test_to_s
     u = URI::MailTo.build([nil, 'subject=Ruby'])
 
