Refactor limit tracking using render_score flag

Remove reached_limit field; use render_score == -1 to indicate limits reached. Update related methods accordingly for clarity and consistency.

.github/workflows/liquid.yml

@@ -14,8 +14,21 @@ jobs:
           - { ruby: 3.0, allowed-failure: false } # minimum supported
           - { ruby: 3.2, allowed-failure: false }
           - { ruby: 3.3, allowed-failure: false }
+          - { ruby: 3.3, allowed-failure: false }
           - { ruby: 3.4, allowed-failure: false } # latest
+          - {
+              ruby: 3.4,
+              allowed-failure: false,
+              rubyopt: "--enable-frozen-string-literal",
+            }
+          - { ruby: 3.4, allowed-failure: false, rubyopt: "--yjit" }
           - { ruby: ruby-head, allowed-failure: false }
+          - {
+              ruby: ruby-head,
+              allowed-failure: false,
+              rubyopt: "--enable-frozen-string-literal",
+            }
+          - { ruby: ruby-head, allowed-failure: false, rubyopt: "--yjit" }
     name: Test Ruby ${{ matrix.entry.ruby }}
     steps:
       - uses: actions/checkout@v3
@@ -26,6 +39,8 @@ jobs:
           bundler: latest
       - run: bundle exec rake
         continue-on-error: ${{ matrix.entry.allowed-failure }}
+        env:
+          RUBYOPT: ${{ matrix.entry.rubyopt }}
 
   memory_profile:
     runs-on: ubuntu-latest

.ruby-version

@@ -1 +1 @@
-3.4.1
+3.4.3

History.md

@@ -1,22 +1,34 @@
 # Liquid Change Log
 
-## 5.8.0 (unreleased)
+## 5.8.1 (unreleased)
+
+## 5.8.1
+
+* Fix `{% doc %}` tag to be visitable [Guilherme Carreiro]
+
+## 5.8.0
+
+* Introduce the new `{% doc %}` tag [Guilherme Carreiro]
+
+## 5.7.3
+
+* Raise Liquid::SyntaxError when parsing invalidly encoded strings [Chris AtLee]
 
 ## 5.7.2 2025-01-31
 
-* Fix array filters to not support nested properties
+* Fix array filters to not support nested properties [Guilherme Carreiro]
 
 ## 5.7.1 2025-01-24
 
-* Fix the `find` and `find_index`filters to return `nil` when filtering empty arrays
-* Fix the `has` filter to return `false` when filtering empty arrays
+* Fix the `find` and `find_index`filters to return `nil` when filtering empty arrays [Guilherme Carreiro]
+* Fix the `has` filter to return `false` when filtering empty arrays [Guilherme Carreiro]
 
 ## 5.7.0 2025-01-16
 
 ### Features
 
-* Add `find`, `find_index`, `has`, and `reject` filters to arrays
-* Compatibility with Ruby 3.4
+* Add `find`, `find_index`, `has`, and `reject` filters to arrays [Guilherme Carreiro]
+* Compatibility with Ruby 3.4 [Ian Ker-Seymer]
 
 ## 5.6.4 2025-01-14
 

lib/liquid/lexer.rb

@@ -161,6 +161,12 @@ module Liquid
         end
         # rubocop:enable Metrics/BlockNesting
         output << EOS
+      rescue ::ArgumentError => e
+        if e.message == "invalid byte sequence in #{ss.string.encoding}"
+          raise SyntaxError, "Invalid byte sequence in #{ss.string.encoding}"
+        else
+          raise
+        end
       end
 
       def raise_syntax_error(start_pos, ss)

lib/liquid/locales/en.yml

@@ -2,12 +2,14 @@
   errors:
     syntax:
       tag_unexpected_args: "Syntax Error in '%{tag}' - Valid syntax: %{tag}"
+      block_tag_unexpected_args: "Syntax Error in '%{tag}' - Valid syntax: {% %{tag} %}{% end%{tag} %}"
       assign: "Syntax Error in 'assign' - Valid syntax: assign [var] = [source]"
       capture: "Syntax Error in 'capture' - Valid syntax: capture [var]"
       case: "Syntax Error in 'case' - Valid syntax: case [condition]"
       case_invalid_when: "Syntax Error in tag 'case' - Valid when condition: {% when [condition] [or condition2...] %}"
       case_invalid_else: "Syntax Error in tag 'case' - Valid else condition: {% else %} (no parameters) "
       cycle: "Syntax Error in 'cycle' - Valid syntax: cycle [name :] var [, var2, var3 ...]"
+      doc_invalid_nested: "Syntax Error in 'doc' - Nested doc tags are not allowed"
       for: "Syntax Error in 'for loop' - Valid syntax: for [item] in [collection]"
       for_invalid_in: "For loops require an 'in' clause"
       for_invalid_attribute: "Invalid attribute in for loop. Valid attributes are limit and offset"

lib/liquid/resource_limits.rb

@@ -1,61 +1,52 @@
 # frozen_string_literal: true
 
 module Liquid
-  class ResourceLimits
-    attr_accessor :render_length_limit, :render_score_limit, :assign_score_limit
-    attr_reader :render_score, :assign_score
-
-    def initialize(limits)
-      @render_length_limit = limits[:render_length_limit]
-      @render_score_limit  = limits[:render_score_limit]
-      @assign_score_limit  = limits[:assign_score_limit]
-      reset
-    end
-
+  class ResourceLimits < Struct.new(:render_length_limit, :render_score_limit, :assign_score_limit, :render_score, :assign_score, :last_capture_length, keyword_init: true)
     def increment_render_score(amount)
-      @render_score += amount
-      raise_limits_reached if @render_score_limit && @render_score > @render_score_limit
+      self.render_score ||= 0
+      self.render_score += amount
+      raise_limits_reached if render_score_limit && render_score > render_score_limit
     end
 
     def increment_assign_score(amount)
-      @assign_score += amount
-      raise_limits_reached if @assign_score_limit && @assign_score > @assign_score_limit
+      self.assign_score ||= 0
+      self.assign_score += amount
+      raise_limits_reached if assign_score_limit && assign_score > assign_score_limit
     end
 
     # update either render_length or assign_score based on whether or not the writes are captured
     def increment_write_score(output)
-      if (last_captured = @last_capture_length)
+      if (last_captured = last_capture_length)
         captured = output.bytesize
         increment = captured - last_captured
-        @last_capture_length = captured
+        self.last_capture_length = captured
         increment_assign_score(increment)
-      elsif @render_length_limit && output.bytesize > @render_length_limit
+      elsif render_length_limit && output.bytesize > render_length_limit
         raise_limits_reached
       end
     end
 
     def raise_limits_reached
-      @reached_limit = true
+      self.render_score = -1
       raise MemoryError, "Memory limits exceeded"
     end
 
     def reached?
-      @reached_limit
+      self.render_score == -1
     end
 
     def reset
-      @reached_limit = false
-      @last_capture_length = nil
-      @render_score = @assign_score = 0
+      self.last_capture_length = nil
+      self.render_score = self.assign_score = 0
     end
 
     def with_capture
-      old_capture_length = @last_capture_length
+      old_capture_length = last_capture_length
       begin
-        @last_capture_length = 0
+        self.last_capture_length = 0
         yield
       ensure
-        @last_capture_length = old_capture_length
+        self.last_capture_length = old_capture_length
       end
     end
   end

lib/liquid/standardfilters.rb

@@ -3,7 +3,6 @@
 require 'cgi'
 require 'base64'
 require 'bigdecimal'
-
 module Liquid
   module StandardFilters
     MAX_I32 = (1 << 31) - 1
@@ -456,7 +455,7 @@ module Liquid
     #   Tests if any item in an array has a specific property value.
     # @liquid_description
     #   This requires you to provide both the property name and the associated value.
-    # @liquid_syntax array | some: string, string
+    # @liquid_syntax array | has: string, string
     # @liquid_return [boolean]
     def has(input, property, target_value = nil)
       filter_array(input, property, target_value, false) { |ary, &block| ary.any?(&block) }
@@ -712,7 +711,16 @@ module Liquid
       input.gsub(/\r?\n/, "<br />\n")
     end
 
-    # Reformat a date using Ruby's core Time#strftime( string ) -> string
+    # @liquid_public_docs
+    # @liquid_type filter
+    # @liquid_category date
+    # @liquid_summary
+    #   Formats a date according to a specified format string.
+    # @liquid_description
+    #   This filter formats a date using various format specifiers. If the format string is empty,
+    #   the original input is returned. If the input cannot be converted to a date, the original input is returned.
+    #
+    #   The following format specifiers can be used:
     #
     #   %a - The abbreviated weekday name (``Sun'')
     #   %A - The  full  weekday  name (``Sunday'')
@@ -741,8 +749,8 @@ module Liquid
     #   %Y - Year with century
     #   %Z - Time zone name
     #   %% - Literal ``%'' character
-    #
-    #   See also: http://www.ruby-doc.org/core/Time.html#method-i-strftime
+    # @liquid_syntax date | date: string
+    # @liquid_return [string]
     def date(input, format)
       str_format = Utils.to_s(format)
       return input if str_format.empty?
@@ -989,7 +997,7 @@ module Liquid
     end
 
     def raise_property_error(property)
-      raise Liquid::ArgumentError, "cannot select the property '#{property}'"
+      raise Liquid::ArgumentError, "cannot select the property '#{Utils.to_s(property)}'"
     end
 
     def apply_operation(input, operand, operation)
@@ -1061,7 +1069,10 @@ module Liquid
       end
 
       def uniq(&block)
-        to_a.uniq(&block)
+        to_a.uniq do |item|
+          item = Utils.to_liquid_value(item)
+          block ? yield(item) : item
+        end
       end
 
       def compact

lib/liquid/tags.rb

@@ -19,6 +19,7 @@ require_relative "tags/comment"
 require_relative "tags/raw"
 require_relative "tags/render"
 require_relative "tags/cycle"
+require_relative "tags/doc"
 
 module Liquid
   module Tags
@@ -42,6 +43,7 @@ module Liquid
       'if' => If,
       'echo' => Echo,
       'tablerow' => TableRow,
+      'doc' => Doc,
     }.freeze
   end
 end

lib/liquid/tags/decrement.rb

@@ -10,7 +10,7 @@ module Liquid
   # @liquid_description
   #   Variables that are declared with `decrement` are unique to the [layout](/themes/architecture/layouts), [template](/themes/architecture/templates),
   #   or [section](/themes/architecture/sections) file that they're created in. However, the variable is shared across
-  #   [snippets](/themes/architecture#snippets) included in the file.
+  #   [snippets](/themes/architecture/snippets) included in the file.
   #
   #   Similarly, variables that are created with `decrement` are independent from those created with [`assign`](/docs/api/liquid/tags/assign)
   #   and [`capture`](/docs/api/liquid/tags/capture). However, `decrement` and [`increment`](/docs/api/liquid/tags/increment) share

lib/liquid/tags/doc.rb

@@ -0,0 +1,77 @@
+# frozen_string_literal: true
+
+module Liquid
+  # @liquid_public_docs
+  # @liquid_type tag
+  # @liquid_category syntax
+  # @liquid_name doc
+  # @liquid_summary
+  #   Documents template elements with annotations.
+  # @liquid_description
+  #   The `doc` tag allows developers to include documentation within Liquid
+  #   templates. Any content inside `doc` tags is not rendered or outputted.
+  #   Liquid code inside will be parsed but not executed. This facilitates
+  #   tooling support for features like code completion, linting, and inline
+  #   documentation.
+  #
+  #   For detailed documentation syntax and examples, see the
+  #   [`LiquidDoc` reference](/docs/storefronts/themes/tools/liquid-doc).
+  #
+  # @liquid_syntax
+  #   {% doc %}
+  #     Renders a message.
+  #
+  #     @param {string} foo - A string value.
+  #     @param {string} [bar] - An optional string value.
+  #
+  #     @example
+  #     {% render 'message', foo: 'Hello', bar: 'World' %}
+  #   {% enddoc %}
+  class Doc < Block
+    NO_UNEXPECTED_ARGS = /\A\s*\z/
+
+    def initialize(tag_name, markup, parse_context)
+      super
+      ensure_valid_markup(tag_name, markup, parse_context)
+    end
+
+    def parse(tokens)
+      while (token = tokens.shift)
+        tag_name = token =~ BlockBody::FullTokenPossiblyInvalid && Regexp.last_match(2)
+
+        raise_nested_doc_error if tag_name == @tag_name
+
+        if tag_name == block_delimiter
+          parse_context.trim_whitespace = (token[-3] == WhitespaceControl)
+          return
+        end
+      end
+
+      raise_tag_never_closed(block_name)
+    end
+
+    def render_to_output_buffer(_context, output)
+      output
+    end
+
+    def blank?
+      true
+    end
+
+    def nodelist
+      []
+    end
+
+    private
+
+    def ensure_valid_markup(tag_name, markup, parse_context)
+      unless NO_UNEXPECTED_ARGS.match?(markup)
+        raise SyntaxError, parse_context.locale.t("errors.syntax.block_tag_unexpected_args", tag: tag_name)
+      end
+    end
+
+    def raise_nested_doc_error
+      raise SyntaxError, parse_context.locale.t("errors.syntax.doc_invalid_nested")
+    end
+  end
+end

lib/liquid/tags/include.rb

@@ -6,7 +6,7 @@ module Liquid
   # @liquid_category theme
   # @liquid_name include
   # @liquid_summary
-  #   Renders a [snippet](/themes/architecture#snippets).
+  #   Renders a [snippet](/themes/architecture/snippets).
   # @liquid_description
   #   Inside the snippet, you can access and alter variables that are [created](/docs/api/liquid/tags/variable-tags) outside of the
   #   snippet.

lib/liquid/tags/increment.rb

@@ -10,7 +10,7 @@ module Liquid
   # @liquid_description
   #   Variables that are declared with `increment` are unique to the [layout](/themes/architecture/layouts), [template](/themes/architecture/templates),
   #   or [section](/themes/architecture/sections) file that they're created in. However, the variable is shared across
-  #   [snippets](/themes/architecture#snippets) included in the file.
+  #   [snippets](/themes/architecture/snippets) included in the file.
   #
   #   Similarly, variables that are created with `increment` are independent from those created with [`assign`](/docs/api/liquid/tags/assign)
   #   and [`capture`](/docs/api/liquid/tags/capture). However, `increment` and [`decrement`](/docs/api/liquid/tags/decrement) share

lib/liquid/tags/render.rb

@@ -6,7 +6,7 @@ module Liquid
   # @liquid_category theme
   # @liquid_name render
   # @liquid_summary
-  #   Renders a [snippet](/themes/architecture#snippets) or [app block](/themes/architecture/sections/section-schema#render-app-blocks).
+  #   Renders a [snippet](/themes/architecture/snippets) or [app block](/themes/architecture/sections/section-schema#render-app-blocks).
   # @liquid_description
   #   Inside snippets and app blocks, you can't directly access variables that are [created](/docs/api/liquid/tags/variable-tags) outside
   #   of the snippet or app block. However, you can [specify variables as parameters](/docs/api/liquid/tags/render#render-passing-variables-to-a-snippet)

lib/liquid/tokenizer.rb

@@ -103,6 +103,12 @@ module Liquid
 
       pos = @ss.pos -= 2
       @source.byteslice(start, pos - start)
+    rescue ::ArgumentError => e
+      if e.message == "invalid byte sequence in #{@ss.string.encoding}"
+        raise SyntaxError, "Invalid byte sequence in #{@ss.string.encoding}"
+      else
+        raise
+      end
     end
 
     def next_variable_token

lib/liquid/version.rb

@@ -2,5 +2,5 @@
 # frozen_string_literal: true
 
 module Liquid
-  VERSION = "5.7.2"
+  VERSION = "5.8.6"
 end

test/integration/standard_filter_test.rb

@@ -560,12 +560,23 @@ class StandardFiltersTest < Minitest::Test
     end
   end
 
-  def test_map_returns_empty_with_no_property
+  def test_map_with_value_property
+    array = [
+      { "handle" => "alpha", "value" => "A" },
+      { "handle" => "beta", "value" => "B" },
+      { "handle" => "gamma", "value" => "C" }
+    ]
+
+    assert_template_result("A B C", "{{ array | map: 'value' | join: ' ' }}", { "array" => array })
+  end
+
+  def test_map_returns_input_with_no_property
     foo = [
       [1],
       [2],
       [3],
     ]
+
     assert_raises(Liquid::ArgumentError) do
       @filters.map(foo, nil)
     end
@@ -1033,6 +1044,23 @@ class StandardFiltersTest < Minitest::Test
     assert_template_result(expected_output, template, { "array" => array })
   end
 
+  def test_where_with_empty_string_is_a_no_op
+    environment = { "array" => ["alpha", "beta", "gamma"] }
+    expected_output = "alpha beta gamma"
+    template = "{{ array | where: '' | join: ' ' }}"
+
+    assert_template_result(expected_output, template, environment)
+  end
+
+  def test_where_with_nil_is_a_no_op
+    environment = { "array" => ["alpha", "beta", "gamma"] }
+    template = "{{ array | where: nil | join: ' ' }}"
+
+    assert_raises(Liquid::ArgumentError) do
+      assert_template_result("alpha beta gamma", template, environment)
+    end
+  end
+
   def test_where_with_value
     array = [
       { "handle" => "alpha", "ok" => true },
@@ -1268,6 +1296,33 @@ class StandardFiltersTest < Minitest::Test
     assert_template_result("0", "{{ input | sum: 'subtotal' }}", { "input" => input })
   end
 
+  def test_sum_with_non_string_property
+    input = [{ true => 1 }, { 1.0 => 0.2, 1 => -0.3 }, { 1..5 => 0.4 }]
+
+    assert_equal(1, @filters.sum(input, true))
+    assert_equal(0.2, @filters.sum(input, 1.0))
+    assert_equal(-0.3, @filters.sum(input, 1))
+    assert_equal(0.4, @filters.sum(input, (1..5)))
+    assert_equal(0, @filters.sum(input, nil))
+    assert_equal(0, @filters.sum(input, ""))
+  end
+
+  def test_uniq_with_to_liquid_value
+    input = [StringDrop.new("foo"), StringDrop.new("bar"), "foo"]
+    expected = [StringDrop.new("foo"), StringDrop.new("bar")]
+    result = @filters.uniq(input)
+
+    assert_equal(expected, result)
+  end
+
+  def test_uniq_with_to_liquid_value_pick_correct_classes
+    input = ["foo", StringDrop.new("foo"), StringDrop.new("bar")]
+    expected = [String, StringDrop]
+    result = @filters.uniq(input).map(&:class)
+
+    assert_equal(expected, result)
+  end
+
   private
 
   def with_timezone(tz)

test/test_helper.rb

@@ -146,6 +146,35 @@ class BooleanDrop < Liquid::Drop
   end
 end
 
+class StringDrop < Liquid::Drop
+  include Comparable
+
+  def initialize(value)
+    super()
+    @value = value
+  end
+
+  def to_liquid_value
+    @value
+  end
+
+  def to_s
+    @value
+  end
+
+  def to_str
+    @value
+  end
+
+  def inspect
+    "#<StringDrop @value=#{@value.inspect}>"
+  end
+
+  def <=>(other)
+    to_liquid_value <=> Liquid::Utils.to_liquid_value(other)
+  end
+end
+
 class ErrorDrop < Liquid::Drop
   def standard_error
     raise Liquid::StandardError, 'standard error'

test/unit/block_unit_test.rb

@@ -47,12 +47,18 @@ class BlockUnitTest < Minitest::Test
     )
   end
 
-  def test_with_block
+  def test_comment_tag_with_block
     template = Liquid::Template.parse("  {% comment %} {% endcomment %} ")
     assert_equal([String, Comment, String], block_types(template.root.nodelist))
     assert_equal(3, template.root.nodelist.size)
   end
 
+  def test_doc_tag_with_block
+    template = Liquid::Template.parse("  {% doc %} {% enddoc %} ")
+    assert_equal([String, Doc, String], block_types(template.root.nodelist))
+    assert_equal(3, template.root.nodelist.size)
+  end
+
   private
 
   def block_types(nodelist)

test/unit/lexer_unit_test.rb

@@ -131,6 +131,16 @@ class LexerUnitTest < Minitest::Test
     assert_equal([[:id, "false"], [:number, "1"], [:end_of_string]], tokenize("false 1"))
   end
 
+  def test_error_with_invalid_utf8
+    error = assert_raises(SyntaxError) do
+      tokenize("\x00\xff")
+    end
+    assert_equal(
+      'Liquid syntax error: Invalid byte sequence in UTF-8',
+      error.message,
+    )
+  end
+
   private
 
   def tokenize(input)

test/unit/tags/doc_tag_unit_test.rb

@@ -0,0 +1,184 @@
+# frozen_string_literal: true
+
+require 'test_helper'
+
+class DocTagUnitTest < Minitest::Test
+  def test_doc_tag
+    template = <<~LIQUID.chomp
+      {% doc %}
+        Renders loading-spinner.
+
+        @param {string} foo - some foo
+        @param {string} [bar] - optional bar
+
+        @example
+        {% render 'loading-spinner', foo: 'foo' %}
+        {% render 'loading-spinner', foo: 'foo', bar: 'bar' %}
+      {% enddoc %}
+    LIQUID
+
+    assert_template_result('', template)
+  end
+
+  def test_doc_tag_does_not_support_extra_arguments
+    error = assert_raises(Liquid::SyntaxError) do
+      template = <<~LIQUID.chomp
+        {% doc extra %}
+        {% enddoc %}
+      LIQUID
+
+      Liquid::Template.parse(template)
+    end
+
+    exp_error = "Liquid syntax error: Syntax Error in 'doc' - Valid syntax: {% doc %}{% enddoc %}"
+    act_error = error.message
+
+    assert_equal(exp_error, act_error)
+  end
+
+  def test_doc_tag_must_support_valid_tags
+    assert_match_syntax_error("Liquid syntax error (line 1): 'doc' tag was never closed", '{% doc %} foo')
+    assert_match_syntax_error("Liquid syntax error (line 1): Syntax Error in 'doc' - Valid syntax: {% doc %}{% enddoc %}", '{% doc } foo {% enddoc %}')
+    assert_match_syntax_error("Liquid syntax error (line 1): Syntax Error in 'doc' - Valid syntax: {% doc %}{% enddoc %}", '{% doc } foo %}{% enddoc %}')
+  end
+
+  def test_doc_tag_ignores_liquid_nodes
+    template = <<~LIQUID.chomp
+      {% doc %}
+        {% if true %}
+        {% if ... %}
+        {%- for ? -%}
+        {% while true %}
+        {%
+          unless if
+        %}
+        {% endcase %}
+      {% enddoc %}
+    LIQUID
+
+    assert_template_result('', template)
+  end
+
+  def test_doc_tag_ignores_unclosed_liquid_tags
+    template = <<~LIQUID.chomp
+      {% doc %}
+        {% if true %}
+      {% enddoc %}
+    LIQUID
+
+    assert_template_result('', template)
+  end
+
+  def test_doc_tag_does_not_allow_nested_docs
+    error = assert_raises(Liquid::SyntaxError) do
+      template = <<~LIQUID.chomp
+        {% doc %}
+          {% doc %}
+            {% doc %}
+        {% enddoc %}
+      LIQUID
+
+      Liquid::Template.parse(template)
+    end
+
+    exp_error = "Liquid syntax error: Syntax Error in 'doc' - Nested doc tags are not allowed"
+    act_error = error.message
+
+    assert_equal(exp_error, act_error)
+  end
+
+  def test_doc_tag_ignores_nested_raw_tags
+    template = <<~LIQUID.chomp
+      {% doc %}
+        {% raw %}
+      {% enddoc %}
+    LIQUID
+
+    assert_template_result('', template)
+  end
+
+  def test_doc_tag_ignores_unclosed_assign
+    template = <<~LIQUID.chomp
+      {% doc %}
+        {% assign foo = "1"
+      {% enddoc %}
+    LIQUID
+
+    assert_template_result('', template)
+  end
+
+  def test_doc_tag_ignores_malformed_syntax
+    template = <<~LIQUID.chomp
+      {% doc %}
+      {% {{ {%- enddoc %}
+    LIQUID
+
+    assert_template_result('', template)
+  end
+
+  def test_doc_tag_preserves_error_line_numbers
+    template = Liquid::Template.parse(<<~LIQUID.chomp, line_numbers: true)
+      {% doc %}
+        {% if true %}
+      {% enddoc %}
+      {{ errors.standard_error }}
+    LIQUID
+
+    expected = <<~TEXT.chomp
+
+      Liquid error (line 4): standard error
+    TEXT
+
+    assert_equal(expected, template.render('errors' => ErrorDrop.new))
+  end
+
+  def test_doc_tag_whitespace_control
+    # Basic whitespace control
+    assert_template_result("Hello!", "      {%- doc -%}123{%- enddoc -%}Hello!")
+    assert_template_result("Hello!", "{%- doc -%}123{%- enddoc -%}     Hello!")
+    assert_template_result("Hello!", "      {%- doc -%}123{%- enddoc -%}     Hello!")
+    assert_template_result("Hello!", <<~LIQUID.chomp)
+      {%- doc %}Whitespace control!{% enddoc -%}
+      Hello!
+    LIQUID
+  end
+
+  def test_doc_tag_delimiter_handling
+    assert_template_result('', <<~LIQUID.chomp)
+      {% if true %}
+        {% doc %}
+          {% docEXTRA %}wut{% enddocEXTRA %}xyz
+        {% enddoc %}
+      {% endif %}
+    LIQUID
+
+    assert_template_result('', "{% doc %}123{% enddoc xyz %}")
+    assert_template_result('', "{% doc %}123{% enddoc\txyz %}")
+    assert_template_result('', "{% doc %}123{% enddoc\nxyz %}")
+    assert_template_result('', "{% doc %}123{% enddoc\n   xyz  enddoc %}")
+  end
+
+  def test_doc_tag_visitor
+    template_source = '{% doc %}{% enddoc %}'
+
+    assert_equal(
+      [Liquid::Doc],
+      visit(template_source),
+    )
+  end
+
+  private
+
+  def traversal(template)
+    ParseTreeVisitor
+      .for(Template.parse(template).root)
+      .add_callback_for(Liquid::Doc) do |tag|
+        tag_class = tag.class
+        tag_class
+      end
+  end
+
+  def visit(template)
+    traversal(template).visit.flatten.compact
+  end
+end

test/unit/template_unit_test.rb

@@ -35,4 +35,15 @@ class TemplateUnitTest < Minitest::Test
   def test_template_inheritance
     assert_equal("foo", TemplateSubclass.parse("foo").render)
   end
+
+  def test_invalid_utf8
+    input = "\xff\x00"
+    error = assert_raises(SyntaxError) do
+      Liquid::Tokenizer.new(source: input, string_scanner: StringScanner.new(input))
+    end
+    assert_equal(
+      'Liquid syntax error: Invalid byte sequence in UTF-8',
+      error.message,
+    )
+  end
 end