diff options
| author | Nobuyoshi Nakada <nobu@ruby-lang.org> | 2025-07-12 19:31:31 +0900 |
|---|---|---|
| committer | git <svn-admin@ruby-lang.org> | 2025-07-12 10:32:48 +0000 |
| commit | cf7b871a94f2d44eb35676a3dbf9278a73a612c1 (patch) | |
| tree | 0f2197c630e56da95c4187706c4728dd1e71e587 | |
| parent | 22b81b5bf56d7c5053008697d9e6b2a9c4eb79f4 (diff) | |
[ruby/uri] Improve performance of `URI::MailTo::EMAIL_REGEXP`
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|
https://github.com/ruby/uri/commit/7363a134ac
| -rw-r--r-- | lib/uri/mailto.rb | 6 | ||||
| -rw-r--r-- | test/uri/test_mailto.rb | 16 |
2 files changed, 21 insertions, 1 deletions
diff --git a/lib/uri/mailto.rb b/lib/uri/mailto.rb index bd63aa0334..f747b79ec7 100644 --- a/lib/uri/mailto.rb +++ b/lib/uri/mailto.rb @@ -52,7 +52,11 @@ module URI 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 index 36e28df2e7..66f3edd05f 100644 --- a/test/uri/test_mailto.rb +++ b/test/uri/test_mailto.rb @@ -210,6 +210,22 @@ class URI::TestMailTo < Test::Unit::TestCase 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']) |