From 369a6c55e349e8785f1c5964f65db3258b210688 Mon Sep 17 00:00:00 2001
From: Michael Go <michael.go@shopify.com>
Date: Fri, 5 Jan 2024 17:53:29 -0400
Subject: [PATCH] check template UTF8 validity before parsing

---
 lib/liquid/locales/en.yml         |  1 +
 lib/liquid/template.rb            |  5 +++++
 test/integration/template_test.rb | 12 ++++++++++++
 3 files changed, 18 insertions(+)

diff --git a/lib/liquid/locales/en.yml b/lib/liquid/locales/en.yml
index 7e232de4..f33c61ce 100644
--- a/lib/liquid/locales/en.yml
+++ b/lib/liquid/locales/en.yml
@@ -15,6 +15,7 @@
       include: "Error in tag 'include' - Valid syntax: include '[template]' (with|for) [object|collection]"
       inline_comment_invalid: "Syntax error in tag '#' - Each line of comments must be prefixed by the '#' character"
       invalid_delimiter: "'%{tag}' is not a valid delimiter for %{block_name} tags. use %{block_delimiter}"
+      invalid_template_encoding: "Invalid template encoding"
       render: "Syntax error in tag 'render' - Template name must be a quoted string"
       table_row: "Syntax Error in 'table_row loop' - Valid syntax: table_row [item] in [collection] cols=3"
       tag_never_closed: "'%{block_name}' tag was never closed"
diff --git a/lib/liquid/template.rb b/lib/liquid/template.rb
index 30742dd6..de06a6fa 100644
--- a/lib/liquid/template.rb
+++ b/lib/liquid/template.rb
@@ -107,6 +107,11 @@ module Liquid
     # Returns self for easy chaining
     def parse(source, options = {})
       parse_context = configure_options(options)
+
+      unless source.valid_encoding?
+        raise SyntaxError, parse_context.locale.t("errors.syntax.invalid_template_encoding")
+      end
+
       tokenizer     = parse_context.new_tokenizer(source, start_line_number: @line_numbers && 1)
       @root         = Document.parse(tokenizer, parse_context)
       self
diff --git a/test/integration/template_test.rb b/test/integration/template_test.rb
index d2225489..2ed1a6fa 100644
--- a/test/integration/template_test.rb
+++ b/test/integration/template_test.rb
@@ -337,4 +337,16 @@ class TemplateTest < Minitest::Test
     assert_equal("x=2", output)
     assert_instance_of(String, output)
   end
+
+  def test_raises_error_with_invalid_utf8
+    e = assert_raises(SyntaxError) do
+      Template.parse(<<~LIQUID)
+        {% comment %}
+          \xC0
+        {% endcomment %}
+      LIQUID
+    end
+
+    assert_equal('Liquid syntax error: Invalid template encoding', e.message)
+  end
 end