From afdc028516f27651d4d94ffd568765cf640c0c44 Mon Sep 17 00:00:00 2001
From: Yorick Peterse <yorickpeterse@gmail.com>
Date: Tue, 20 Oct 2015 15:49:11 +0200
Subject: Speed up searching for text references a bit

If a node is ignored there's no need for searching for a given pattern.
In turn, when searching for the pattern there's no need to construct a
MatchData object as we only care about presence (or lack thereof), not
the resulting matches.

In terms of performance this cuts down about 200 ms when loading
issue #2164 locally, though this varies a bit depending on system load.
---
 CHANGELOG                               | 1 +
 lib/gitlab/markdown/reference_filter.rb | 8 ++++----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG b/CHANGELOG
index 5671d8b1d81..3044ebbd7e4 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -1,6 +1,7 @@
 Please view this file on the master branch, on stable branches it's out of date.
 
 v 8.2.0 (unreleased)
+  - Improved performance of replacing references in comments
   - Fix duplicate repositories in GitHub import page (Stan Hu)
   - Show last project commit to default branch on project home page
   - Highlight comment based on anchor in URL
diff --git a/lib/gitlab/markdown/reference_filter.rb b/lib/gitlab/markdown/reference_filter.rb
index adaca78ba27..a4c560f578c 100644
--- a/lib/gitlab/markdown/reference_filter.rb
+++ b/lib/gitlab/markdown/reference_filter.rb
@@ -15,7 +15,7 @@ module Gitlab
       LazyReference = Struct.new(:klass, :ids) do
         def self.load(refs)
           lazy_references, values = refs.partition { |ref| ref.is_a?(self) }
-          
+
           lazy_values = lazy_references.group_by(&:klass).flat_map do |klass, refs|
             ids = refs.flat_map(&:ids)
             klass.where(id: ids)
@@ -107,10 +107,10 @@ module Gitlab
         return doc if project.nil?
 
         search_text_nodes(doc).each do |node|
-          content = node.to_html
-
-          next unless content.match(pattern)
           next if ignored_ancestry?(node)
+          next unless node.text =~ pattern
+
+          content = node.to_html
 
           html = yield content
 
-- 
cgit v1.2.1


From e1c3077e4bb718ce841fad175f708623d8375818 Mon Sep 17 00:00:00 2001
From: Yorick Peterse <yorickpeterse@gmail.com>
Date: Tue, 20 Oct 2015 15:51:02 +0200
Subject: Added benchmark for ReferenceFilter

---
 .../lib/gitlab/markdown/reference_filter_spec.rb   | 41 ++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 spec/benchmarks/lib/gitlab/markdown/reference_filter_spec.rb

diff --git a/spec/benchmarks/lib/gitlab/markdown/reference_filter_spec.rb b/spec/benchmarks/lib/gitlab/markdown/reference_filter_spec.rb
new file mode 100644
index 00000000000..34cd9f7e4eb
--- /dev/null
+++ b/spec/benchmarks/lib/gitlab/markdown/reference_filter_spec.rb
@@ -0,0 +1,41 @@
+require 'spec_helper'
+
+describe Gitlab::Markdown::ReferenceFilter, benchmark: true do
+  let(:input) do
+    html = <<-EOF
+<p>Hello @alice and @bob, how are you doing today?</p>
+<p>This is simple @dummy text to see how the @ReferenceFilter class performs
+when @processing HTML.</p>
+    EOF
+
+    Nokogiri::HTML.fragment(html)
+  end
+
+  let(:project) { create(:empty_project) }
+
+  let(:filter) { described_class.new(input, project: project) }
+
+  describe '#replace_text_nodes_matching' do
+    let(:iterations) { 6000 }
+
+    describe 'with identical input and output HTML' do
+      benchmark_subject do
+        filter.replace_text_nodes_matching(User.reference_pattern) do |content|
+          content
+        end
+      end
+
+      it { is_expected.to iterate_per_second(iterations) }
+    end
+
+    describe 'with different input and output HTML' do
+      benchmark_subject do
+        filter.replace_text_nodes_matching(User.reference_pattern) do |content|
+          '@eve'
+        end
+      end
+
+      it { is_expected.to iterate_per_second(iterations) }
+    end
+  end
+end
-- 
cgit v1.2.1