From da5c28a422e3966f6f6780d5e23f13eda4881108 Mon Sep 17 00:00:00 2001 From: Grzegorz Bizon Date: Mon, 14 May 2018 10:43:45 +0200 Subject: Backport EE-specific untrusted regexp implementation --- lib/gitlab/untrusted_regexp.rb | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/gitlab/untrusted_regexp.rb b/lib/gitlab/untrusted_regexp.rb index 7ce2e9d636e..75ba0799058 100644 --- a/lib/gitlab/untrusted_regexp.rb +++ b/lib/gitlab/untrusted_regexp.rb @@ -11,7 +11,11 @@ module Gitlab class UntrustedRegexp delegate :===, to: :regexp - def initialize(pattern) + def initialize(pattern, multiline: false) + if multiline + pattern = "(?m)#{pattern}" + end + @regexp = RE2::Regexp.new(pattern, log_errors: false) raise RegexpError.new(regexp.error) unless regexp.ok? @@ -31,6 +35,19 @@ module Gitlab RE2.Replace(text, regexp, rewrite) end + # Handles regular expressions with the preferred RE2 library where possible + # via UntustedRegex. Falls back to Ruby's built-in regular expression library + # when the syntax would be invalid in RE2. + # + # One difference between these is `(?m)` multi-line mode. Ruby regex enables + # this by default, but also handles `^` and `$` differently. + # See: https://www.regular-expressions.info/modifiers.html + def self.with_fallback(pattern, multiline: false) + UntrustedRegexp.new(pattern, multiline: multiline) + rescue RegexpError + Regexp.new(pattern) + end + private attr_reader :regexp -- cgit v1.2.1