Strict parsing only on Liquid::Variable

Add a link to the LiquidDoc tooling reference in `doc` tag documentation

.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: "3.4.0-rc1", allowed-failure: false } # latest
+          - { 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 @@
-3.3.6
+3.4.1

CONTRIBUTING.md

@@ -26,3 +26,11 @@
 * If it makes sense, add tests for your code and/or run a performance benchmark
 * Make sure all tests pass (`bundle exec rake`)
 * Create a pull request
+
+## Releasing
+
+* Bump the version in `lib/liquid/version.rb`
+* Update the `History.md` file
+* Open a PR like [this one](https://github.com/Shopify/liquid/pull/1894) and merge it to `main`
+* Create a new release using the [GitHub UI](https://github.com/Shopify/liquid/releases/new)
+

Gemfile

@@ -20,6 +20,10 @@ group :benchmark, :test do
   end
 end
 
+group :development do
+  gem "webrick"
+end
+
 group :test do
   gem 'rubocop', '~> 1.61.0'
   gem 'rubocop-shopify', '~> 2.12.0', require: false

History.md

@@ -1,12 +1,76 @@
 # Liquid Change Log
 
-## 5.6.0 (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 [Guilherme Carreiro]
+
+## 5.7.1 2025-01-24
+
+* 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 [Guilherme Carreiro]
+* Compatibility with Ruby 3.4 [Ian Ker-Seymer]
+
+## 5.6.4 2025-01-14
 
 ### Fixes
+* Add a default `string_scanner` to avoid errors with `Liquid::VariableLookup.parse("foo.bar")` [Ian Ker-Seymer]
 
+## 5.6.3 2025-01-13
+* Remove `lru_redux` dependency [Michael Go]
+
+## 5.6.2 2025-01-13
+
+### Fixes
+* Preserve the old behavior of requiring floats to start with a digit [Michael Go]
+
+## 5.6.1 2025-01-13
+
+### Performance improvements
+* Faster Expression parser / Tokenizer with StringScanner [Michael Go]
+
+## 5.6.0 2024-12-19
+
+### Architectural changes
+* Added new `Environment` class to manage configuration and state that was previously stored in `Template` [Ian Ker-Seymer]
+* Moved tag registration from `Template` to `Environment` [Ian Ker-Seymer]
+* Removed `StrainerFactory` in favor of `Environment`-based strainer creation [Ian Ker-Seymer]
+* Consolidated standard tags into a new `Tags` module with `STANDARD_TAGS` constant [Ian Ker-Seymer]
+
+### Performance improvements
+* Optimized `Lexer` with a new `Lexer2` implementation using jump tables for faster tokenization, requires Ruby 3.4 [Ian Ker-Seymer]
+* Improved variable rendering with specialized handling for different types [Michael Go]
+* Reduced array allocations by using frozen empty constants [Michael Go]
+
+### API changes
+* Deprecated several `Template` class methods in favor of `Environment` methods [Ian Ker-Seymer]
+* Added deprecation warnings system [Ian Ker-Seymer]
+* Changed how filters and tags are registered to use Environment [Ian Ker-Seymer]
+
+### Fixes
+* Fixed table row handling of break interrupts [Alex Coco]
+* Improved variable output handling for arrays [Ian Ker-Seymer]
 * Fix Tokenizer to handle null source value (#1873) [Bahar Pourazar]
 
-
 ## 5.5.0 2024-03-21
 
 Please reference the GitHub release for more information.

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/standardfilters.rb

@@ -64,7 +64,7 @@ module Liquid
     # @liquid_syntax string | downcase
     # @liquid_return [string]
     def downcase(input)
-      input.to_s.downcase
+      Utils.to_s(input).downcase
     end
 
     # @liquid_public_docs
@@ -75,7 +75,7 @@ module Liquid
     # @liquid_syntax string | upcase
     # @liquid_return [string]
     def upcase(input)
-      input.to_s.upcase
+      Utils.to_s(input).upcase
     end
 
     # @liquid_public_docs
@@ -86,7 +86,7 @@ module Liquid
     # @liquid_syntax string | capitalize
     # @liquid_return [string]
     def capitalize(input)
-      input.to_s.capitalize
+      Utils.to_s(input).capitalize
     end
 
     # @liquid_public_docs
@@ -97,7 +97,7 @@ module Liquid
     # @liquid_syntax string | escape
     # @liquid_return [string]
     def escape(input)
-      CGI.escapeHTML(input.to_s) unless input.nil?
+      CGI.escapeHTML(Utils.to_s(input)) unless input.nil?
     end
     alias_method :h, :escape
 
@@ -109,7 +109,7 @@ module Liquid
     # @liquid_syntax string | escape_once
     # @liquid_return [string]
     def escape_once(input)
-      input.to_s.gsub(HTML_ESCAPE_ONCE_REGEXP, HTML_ESCAPE)
+      Utils.to_s(input).gsub(HTML_ESCAPE_ONCE_REGEXP, HTML_ESCAPE)
     end
 
     # @liquid_public_docs
@@ -124,7 +124,7 @@ module Liquid
     # @liquid_syntax string | url_encode
     # @liquid_return [string]
     def url_encode(input)
-      CGI.escape(input.to_s) unless input.nil?
+      CGI.escape(Utils.to_s(input)) unless input.nil?
     end
 
     # @liquid_public_docs
@@ -138,7 +138,7 @@ module Liquid
     def url_decode(input)
       return if input.nil?
 
-      result = CGI.unescape(input.to_s)
+      result = CGI.unescape(Utils.to_s(input))
       raise Liquid::ArgumentError, "invalid byte sequence in #{result.encoding}" unless result.valid_encoding?
 
       result
@@ -152,7 +152,7 @@ module Liquid
     # @liquid_syntax string | base64_encode
     # @liquid_return [string]
     def base64_encode(input)
-      Base64.strict_encode64(input.to_s)
+      Base64.strict_encode64(Utils.to_s(input))
     end
 
     # @liquid_public_docs
@@ -163,7 +163,7 @@ module Liquid
     # @liquid_syntax string | base64_decode
     # @liquid_return [string]
     def base64_decode(input)
-      input = input.to_s
+      input = Utils.to_s(input)
       StandardFilters.try_coerce_encoding(Base64.strict_decode64(input), encoding: input.encoding)
     rescue ::ArgumentError
       raise Liquid::ArgumentError, "invalid base64 provided to base64_decode"
@@ -177,7 +177,7 @@ module Liquid
     # @liquid_syntax string | base64_url_safe_encode
     # @liquid_return [string]
     def base64_url_safe_encode(input)
-      Base64.urlsafe_encode64(input.to_s)
+      Base64.urlsafe_encode64(Utils.to_s(input))
     end
 
     # @liquid_public_docs
@@ -188,7 +188,7 @@ module Liquid
     # @liquid_syntax string | base64_url_safe_decode
     # @liquid_return [string]
     def base64_url_safe_decode(input)
-      input = input.to_s
+      input = Utils.to_s(input)
       StandardFilters.try_coerce_encoding(Base64.urlsafe_decode64(input), encoding: input.encoding)
     rescue ::ArgumentError
       raise Liquid::ArgumentError, "invalid base64 provided to base64_url_safe_decode"
@@ -212,7 +212,7 @@ module Liquid
         if input.is_a?(Array)
           input.slice(offset, length) || []
         else
-          input.to_s.slice(offset, length) || ''
+          Utils.to_s(input).slice(offset, length) || ''
         end
       rescue RangeError
         if I64_RANGE.cover?(length) && I64_RANGE.cover?(offset)
@@ -236,10 +236,10 @@ module Liquid
     # @liquid_return [string]
     def truncate(input, length = 50, truncate_string = "...")
       return if input.nil?
-      input_str = input.to_s
+      input_str = Utils.to_s(input)
       length    = Utils.to_integer(length)
 
-      truncate_string_str = truncate_string.to_s
+      truncate_string_str = Utils.to_s(truncate_string)
 
       l = length - truncate_string_str.length
       l = 0 if l < 0
@@ -263,7 +263,7 @@ module Liquid
     # @liquid_return [string]
     def truncatewords(input, words = 15, truncate_string = "...")
       return if input.nil?
-      input = input.to_s
+      input = Utils.to_s(input)
       words = Utils.to_integer(words)
       words = 1 if words <= 0
 
@@ -277,7 +277,8 @@ module Liquid
       return input if wordlist.length <= words
 
       wordlist.pop
-      wordlist.join(" ").concat(truncate_string.to_s)
+      truncate_string = Utils.to_s(truncate_string)
+      wordlist.join(" ").concat(truncate_string)
     end
 
     # @liquid_public_docs
@@ -288,7 +289,9 @@ module Liquid
     # @liquid_syntax string | split: string
     # @liquid_return [array[string]]
     def split(input, pattern)
-      input.to_s.split(pattern.to_s)
+      pattern = Utils.to_s(pattern)
+      input = Utils.to_s(input)
+      input.split(pattern)
     end
 
     # @liquid_public_docs
@@ -299,7 +302,8 @@ module Liquid
     # @liquid_syntax string | strip
     # @liquid_return [string]
     def strip(input)
-      input.to_s.strip
+      input = Utils.to_s(input)
+      input.strip
     end
 
     # @liquid_public_docs
@@ -310,7 +314,8 @@ module Liquid
     # @liquid_syntax string | lstrip
     # @liquid_return [string]
     def lstrip(input)
-      input.to_s.lstrip
+      input = Utils.to_s(input)
+      input.lstrip
     end
 
     # @liquid_public_docs
@@ -321,7 +326,8 @@ module Liquid
     # @liquid_syntax string | rstrip
     # @liquid_return [string]
     def rstrip(input)
-      input.to_s.rstrip
+      input = Utils.to_s(input)
+      input.rstrip
     end
 
     # @liquid_public_docs
@@ -332,8 +338,9 @@ module Liquid
     # @liquid_syntax string | strip_html
     # @liquid_return [string]
     def strip_html(input)
+      input = Utils.to_s(input)
       empty  = ''
-      result = input.to_s.gsub(STRIP_HTML_BLOCKS, empty)
+      result = input.gsub(STRIP_HTML_BLOCKS, empty)
       result.gsub!(STRIP_HTML_TAGS, empty)
       result
     end
@@ -346,7 +353,8 @@ module Liquid
     # @liquid_syntax string | strip_newlines
     # @liquid_return [string]
     def strip_newlines(input)
-      input.to_s.gsub(/\r?\n/, '')
+      input = Utils.to_s(input)
+      input.gsub(/\r?\n/, '')
     end
 
     # @liquid_public_docs
@@ -357,6 +365,7 @@ module Liquid
     # @liquid_syntax array | join
     # @liquid_return [string]
     def join(input, glue = ' ')
+      glue = Utils.to_s(glue)
       InputIterator.new(input, context).join(glue)
     end
 
@@ -424,29 +433,59 @@ module Liquid
     # @liquid_syntax array | where: string, string
     # @liquid_return [array[untyped]]
     def where(input, property, target_value = nil)
-      ary = InputIterator.new(input, context)
+      filter_array(input, property, target_value) { |ary, &block| ary.select(&block) }
+    end
 
-      if ary.empty?
-        []
-      elsif target_value.nil?
-        ary.select do |item|
-          item[property]
-        rescue TypeError
-          raise_property_error(property)
-        rescue NoMethodError
-          return nil unless item.respond_to?(:[])
-          raise
-        end
-      else
-        ary.select do |item|
-          item[property] == target_value
-        rescue TypeError
-          raise_property_error(property)
-        rescue NoMethodError
-          return nil unless item.respond_to?(:[])
-          raise
-        end
-      end
+    # @liquid_public_docs
+    # @liquid_type filter
+    # @liquid_category array
+    # @liquid_summary
+    #   Filters an array to exclude items with a specific property value.
+    # @liquid_description
+    #   This requires you to provide both the property name and the associated value.
+    # @liquid_syntax array | reject: string, string
+    # @liquid_return [array[untyped]]
+    def reject(input, property, target_value = nil)
+      filter_array(input, property, target_value) { |ary, &block| ary.reject(&block) }
+    end
+
+    # @liquid_public_docs
+    # @liquid_type filter
+    # @liquid_category array
+    # @liquid_summary
+    #   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 | 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) }
+    end
+
+    # @liquid_public_docs
+    # @liquid_type filter
+    # @liquid_category array
+    # @liquid_summary
+    #   Returns the first item in an array with a specific property value.
+    # @liquid_description
+    #   This requires you to provide both the property name and the associated value.
+    # @liquid_syntax array | find: string, string
+    # @liquid_return [untyped]
+    def find(input, property, target_value = nil)
+      filter_array(input, property, target_value, nil) { |ary, &block| ary.find(&block) }
+    end
+
+    # @liquid_public_docs
+    # @liquid_type filter
+    # @liquid_category array
+    # @liquid_summary
+    #   Returns the index of the first item in an array with a specific property value.
+    # @liquid_description
+    #   This requires you to provide both the property name and the associated value.
+    # @liquid_syntax array | find_index: string, string
+    # @liquid_return [number]
+    def find_index(input, property, target_value = nil)
+      filter_array(input, property, target_value, nil) { |ary, &block| ary.find_index(&block) }
     end
 
     # @liquid_public_docs
@@ -543,7 +582,10 @@ module Liquid
     # @liquid_syntax string | replace: string, string
     # @liquid_return [string]
     def replace(input, string, replacement = '')
-      input.to_s.gsub(string.to_s, replacement.to_s)
+      string = Utils.to_s(string)
+      replacement = Utils.to_s(replacement)
+      input = Utils.to_s(input)
+      input.gsub(string, replacement)
     end
 
     # @liquid_public_docs
@@ -554,7 +596,10 @@ module Liquid
     # @liquid_syntax string | replace_first: string, string
     # @liquid_return [string]
     def replace_first(input, string, replacement = '')
-      input.to_s.sub(string.to_s, replacement.to_s)
+      string = Utils.to_s(string)
+      replacement = Utils.to_s(replacement)
+      input = Utils.to_s(input)
+      input.sub(string, replacement)
     end
 
     # @liquid_public_docs
@@ -565,9 +610,9 @@ module Liquid
     # @liquid_syntax string | replace_last: string, string
     # @liquid_return [string]
     def replace_last(input, string, replacement)
-      input = input.to_s
-      string = string.to_s
-      replacement = replacement.to_s
+      input = Utils.to_s(input)
+      string = Utils.to_s(string)
+      replacement = Utils.to_s(replacement)
 
       start_index = input.rindex(string)
 
@@ -619,7 +664,9 @@ module Liquid
     # @liquid_syntax string | append: string
     # @liquid_return [string]
     def append(input, string)
-      input.to_s + string.to_s
+      input = Utils.to_s(input)
+      string = Utils.to_s(string)
+      input + string
     end
 
     # @liquid_public_docs
@@ -648,7 +695,9 @@ module Liquid
     # @liquid_syntax string | prepend: string
     # @liquid_return [string]
     def prepend(input, string)
-      string.to_s + input.to_s
+      input = Utils.to_s(input)
+      string = Utils.to_s(string)
+      string + input
     end
 
     # @liquid_public_docs
@@ -659,10 +708,20 @@ module Liquid
     # @liquid_syntax string | newline_to_br
     # @liquid_return [string]
     def newline_to_br(input)
-      input.to_s.gsub(/\r?\n/, "<br />\n")
+      input = Utils.to_s(input)
+      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'')
@@ -691,14 +750,15 @@ 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)
-      return input if format.to_s.empty?
+      str_format = Utils.to_s(format)
+      return input if str_format.empty?
 
       return input unless (date = Utils.to_date(input))
 
-      date.strftime(format.to_s)
+      date.strftime(str_format)
     end
 
     # @liquid_public_docs
@@ -918,6 +978,25 @@ module Liquid
 
     attr_reader :context
 
+    def filter_array(input, property, target_value, default_value = [], &block)
+      ary = InputIterator.new(input, context)
+
+      return default_value if ary.empty?
+
+      block.call(ary) do |item|
+        if target_value.nil?
+          item[property]
+        else
+          item[property] == target_value
+        end
+      rescue TypeError
+        raise_property_error(property)
+      rescue NoMethodError
+        return nil unless item.respond_to?(:[])
+        raise
+      end
+    end
+
     def raise_property_error(property)
       raise Liquid::ArgumentError, "cannot select the property '#{property}'"
     end
@@ -968,7 +1047,18 @@ module Liquid
       end
 
       def join(glue)
-        to_a.join(glue.to_s)
+        first = true
+        output = +""
+        each do |item|
+          if first
+            first = false
+          else
+            output << glue
+          end
+
+          output << Liquid::Utils.to_s(item)
+        end
+        output
       end
 
       def concat(args)

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/doc.rb

@@ -0,0 +1,78 @@
+# 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 %}
+  #   {{ foo }}, {{ bar }}!
+  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/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/utils.rb

@@ -89,5 +89,101 @@ module Liquid
       # Otherwise return the object itself
       obj
     end
+
+    def self.to_s(obj, seen = {})
+      case obj
+      when Hash
+        # If the custom hash implementation overrides `#to_s`, use their
+        # custom implementation. Otherwise we use Liquid's default
+        # implementation.
+        if obj.class.instance_method(:to_s) == HASH_TO_S_METHOD
+          hash_inspect(obj, seen)
+        else
+          obj.to_s
+        end
+      when Array
+        array_inspect(obj, seen)
+      else
+        obj.to_s
+      end
+    end
+
+    def self.inspect(obj, seen = {})
+      case obj
+      when Hash
+        # If the custom hash implementation overrides `#inspect`, use their
+        # custom implementation. Otherwise we use Liquid's default
+        # implementation.
+        if obj.class.instance_method(:inspect) == HASH_INSPECT_METHOD
+          hash_inspect(obj, seen)
+        else
+          obj.inspect
+        end
+      when Array
+        array_inspect(obj, seen)
+      else
+        obj.inspect
+      end
+    end
+
+    def self.array_inspect(arr, seen = {})
+      if seen[arr.object_id]
+        return "[...]"
+      end
+
+      seen[arr.object_id] = true
+      str = +"["
+      cursor = 0
+      len = arr.length
+
+      while cursor < len
+        if cursor > 0
+          str << ", "
+        end
+
+        item_str = inspect(arr[cursor], seen)
+        str << item_str
+        cursor += 1
+      end
+
+      str << "]"
+      str
+    ensure
+      seen.delete(arr.object_id)
+    end
+
+    def self.hash_inspect(hash, seen = {})
+      if seen[hash.object_id]
+        return "{...}"
+      end
+      seen[hash.object_id] = true
+
+      str = +"{"
+      first = true
+      hash.each do |key, value|
+        if first
+          first = false
+        else
+          str << ", "
+        end
+
+        key_str = inspect(key, seen)
+        str << key_str
+        str << "=>"
+
+        value_str = inspect(value, seen)
+        str << value_str
+      end
+      str << "}"
+      str
+    ensure
+      seen.delete(hash.object_id)
+    end
+
+    HASH_TO_S_METHOD = Hash.instance_method(:to_s)
+    private_constant :HASH_TO_S_METHOD
+
+    HASH_INSPECT_METHOD = Hash.instance_method(:inspect)
+    private_constant :HASH_INSPECT_METHOD
   end
 end

lib/liquid/variable.rb

@@ -30,7 +30,7 @@ module Liquid
       @parse_context = parse_context
       @line_number   = parse_context.line_number
 
-      strict_parse_with_error_mode_fallback(markup)
+      strict_parse_with_error_context(markup)
     end
 
     def raw
@@ -41,22 +41,12 @@ module Liquid
       "in \"{{#{markup}}}\""
     end
 
-    def lax_parse(markup)
-      @filters = []
-      return unless markup =~ MarkupWithQuotedFragment
-
-      name_markup   = Regexp.last_match(1)
-      filter_markup = Regexp.last_match(2)
-      @name         = parse_context.parse_expression(name_markup)
-      if filter_markup =~ FilterMarkupRegex
-        filters = Regexp.last_match(1).scan(FilterParser)
-        filters.each do |f|
-          next unless f =~ /\w+/
-          filtername = Regexp.last_match(0)
-          filterargs = f.scan(FilterArgsRegex).flatten
-          @filters << parse_filter_expressions(filtername, filterargs)
-        end
-      end
+    def strict_parse_with_error_context(markup)
+      strict_parse(markup)
+    rescue SyntaxError => e
+      e.line_number    = line_number
+      e.markup_context = markup_context(markup)
+      raise e
     end
 
     def strict_parse(markup)
@@ -107,8 +97,8 @@ module Liquid
         obj.each do |o|
           render_obj_to_output(o, output)
         end
-      when
-        output << obj.to_s
+      else
+        output << Liquid::Utils.to_s(obj)
       end
     end
 

lib/liquid/version.rb

@@ -2,5 +2,5 @@
 # frozen_string_literal: true
 
 module Liquid
-  VERSION = "5.6.4"
+  VERSION = "5.8.1"
 end

test/integration/hash_rendering_test.rb

@@ -0,0 +1,106 @@
+# frozen_string_literal: true
+
+require 'test_helper'
+
+class HashRenderingTest < Minitest::Test
+  def test_render_empty_hash
+    assert_template_result("{}", "{{ my_hash }}", { "my_hash" => {} })
+  end
+
+  def test_render_hash_with_string_keys_and_values
+    assert_template_result("{\"key1\"=>\"value1\", \"key2\"=>\"value2\"}", "{{ my_hash }}", { "my_hash" => { "key1" => "value1", "key2" => "value2" } })
+  end
+
+  def test_render_hash_with_symbol_keys_and_integer_values
+    assert_template_result("{:key1=>1, :key2=>2}", "{{ my_hash }}", { "my_hash" => { key1: 1, key2: 2 } })
+  end
+
+  def test_render_nested_hash
+    assert_template_result("{\"outer\"=>{\"inner\"=>\"value\"}}", "{{ my_hash }}", { "my_hash" => { "outer" => { "inner" => "value" } } })
+  end
+
+  def test_render_hash_with_array_values
+    assert_template_result("{\"numbers\"=>[1, 2, 3]}", "{{ my_hash }}", { "my_hash" => { "numbers" => [1, 2, 3] } })
+  end
+
+  def test_render_recursive_hash
+    recursive_hash = { "self" => {} }
+    recursive_hash["self"]["self"] = recursive_hash
+    assert_template_result("{\"self\"=>{\"self\"=>{...}}}", "{{ my_hash }}", { "my_hash" => recursive_hash })
+  end
+
+  def test_hash_with_downcase_filter
+    assert_template_result("{\"key\"=>\"value\", \"anotherkey\"=>\"anothervalue\"}", "{{ my_hash | downcase }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_upcase_filter
+    assert_template_result("{\"KEY\"=>\"VALUE\", \"ANOTHERKEY\"=>\"ANOTHERVALUE\"}", "{{ my_hash | upcase }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_strip_filter
+    assert_template_result("{\"Key\"=>\"Value\", \"AnotherKey\"=>\"AnotherValue\"}", "{{ my_hash | strip }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_escape_filter
+    assert_template_result("{&quot;Key&quot;=&gt;&quot;Value&quot;, &quot;AnotherKey&quot;=&gt;&quot;AnotherValue&quot;}", "{{ my_hash | escape }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_url_encode_filter
+    assert_template_result("%7B%22Key%22%3D%3E%22Value%22%2C+%22AnotherKey%22%3D%3E%22AnotherValue%22%7D", "{{ my_hash | url_encode }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_strip_html_filter
+    assert_template_result("{\"Key\"=>\"Value\", \"AnotherKey\"=>\"AnotherValue\"}", "{{ my_hash | strip_html }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_truncate__20_filter
+    assert_template_result("{\"Key\"=>\"Value\", ...", "{{ my_hash | truncate: 20 }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_replace___key____replaced_key__filter
+    assert_template_result("{\"Key\"=>\"Value\", \"AnotherKey\"=>\"AnotherValue\"}", "{{ my_hash | replace: 'key', 'replaced_key' }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_append____appended_text__filter
+    assert_template_result("{\"Key\"=>\"Value\", \"AnotherKey\"=>\"AnotherValue\"} appended text", "{{ my_hash | append: ' appended text' }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_hash_with_prepend___prepended_text___filter
+    assert_template_result("prepended text {\"Key\"=>\"Value\", \"AnotherKey\"=>\"AnotherValue\"}", "{{ my_hash | prepend: 'prepended text ' }}", { "my_hash" => { "Key" => "Value", "AnotherKey" => "AnotherValue" } })
+  end
+
+  def test_render_hash_with_array_values_empty
+    assert_template_result("{\"numbers\"=>[]}", "{{ my_hash }}", { "my_hash" => { "numbers" => [] } })
+  end
+
+  def test_render_hash_with_array_values_hash
+    assert_template_result("{\"numbers\"=>[{:foo=>42}]}", "{{ my_hash }}", { "my_hash" => { "numbers" => [{ foo: 42 }] } })
+  end
+
+  def test_join_filter_with_hash
+    array = [{ "key1" => "value1" }, { "key2" => "value2" }]
+    glue = { "lol" => "wut" }
+    assert_template_result("{\"key1\"=>\"value1\"}{\"lol\"=>\"wut\"}{\"key2\"=>\"value2\"}", "{{ my_array | join: glue }}", { "my_array" => array, "glue" => glue })
+  end
+
+  def test_render_hash_with_hash_key
+    assert_template_result("{{\"foo\"=>\"bar\"}=>42}", "{{ my_hash }}", { "my_hash" => { Hash["foo" => "bar"] => 42 } })
+  end
+
+  def test_rendering_hash_with_custom_to_s_method_uses_custom_to_s
+    my_hash = Class.new(Hash) do
+      def to_s
+        "kewl"
+      end
+    end.new
+
+    assert_template_result("kewl", "{{ my_hash }}", { "my_hash" => my_hash })
+  end
+
+  def test_rendering_hash_without_custom_to_s_uses_default_inspect
+    my_hash = Class.new(Hash).new
+    my_hash[:foo] = :bar
+
+    assert_template_result("{:foo=>:bar}", "{{ my_hash }}", { "my_hash" => my_hash })
+  end
+end

test/integration/standard_filter_test.rb

@@ -133,6 +133,18 @@ class StandardFiltersTest < Minitest::Test
     assert_equal([], @filters.slice(input, -(1 << 63), 6))
   end
 
+  def test_find_on_empty_array
+    assert_nil(@filters.find([], 'foo', 'bar'))
+  end
+
+  def test_find_index_on_empty_array
+    assert_nil(@filters.find_index([], 'foo', 'bar'))
+  end
+
+  def test_has_on_empty_array
+    refute(@filters.has([], 'foo', 'bar'))
+  end
+
   def test_truncate
     assert_equal('1234...', @filters.truncate('1234567890', 7))
     assert_equal('1234567890', @filters.truncate('1234567890', 20))
@@ -281,6 +293,16 @@ class StandardFiltersTest < Minitest::Test
     assert_equal('1121314', @filters.join([1, 2, 3, 4], 1))
   end
 
+  def test_join_calls_to_liquid_on_each_element
+    drop = Class.new(Liquid::Drop) do
+      def to_liquid
+        'i did it'
+      end
+    end
+
+    assert_equal('i did it, i did it', @filters.join([drop.new, drop.new], ", "))
+  end
+
   def test_sort
     assert_equal([1, 2, 3, 4], @filters.sort([4, 3, 2, 1]))
     assert_equal([{ "a" => 1 }, { "a" => 2 }, { "a" => 3 }, { "a" => 4 }], @filters.sort([{ "a" => 4 }, { "a" => 3 }, { "a" => 1 }, { "a" => 2 }], "a"))
@@ -827,21 +849,216 @@ class StandardFiltersTest < Minitest::Test
     assert_template_result('abc', "{{ 'abc' | date: '%D' }}")
   end
 
-  def test_where
-    input = [
+  def test_reject
+    array = [
       { "handle" => "alpha", "ok" => true },
       { "handle" => "beta", "ok" => false },
       { "handle" => "gamma", "ok" => false },
       { "handle" => "delta", "ok" => true },
     ]
 
-    expectation = [
+    template = "{{ array | reject: 'ok' | map: 'handle' | join: ' ' }}"
+    expected_output = "beta gamma"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_reject_with_value
+    array = [
       { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
       { "handle" => "delta", "ok" => true },
     ]
 
-    assert_equal(expectation, @filters.where(input, "ok", true))
-    assert_equal(expectation, @filters.where(input, "ok"))
+    template = "{{ array | reject: 'ok', true | map: 'handle' | join: ' ' }}"
+    expected_output = "beta gamma"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_reject_with_false_value
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => true },
+    ]
+
+    template = "{{ array | reject: 'ok', false | map: 'handle' | join: ' ' }}"
+    expected_output = "alpha delta"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_has
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => false },
+    ]
+
+    expected_output = "true"
+
+    assert_template_result(expected_output, "{{ array | has: 'ok' }}", { "array" => array })
+    assert_template_result(expected_output, "{{ array | has: 'ok', true }}", { "array" => array })
+  end
+
+  def test_has_when_does_not_have_it
+    array = [
+      { "handle" => "alpha", "ok" => false },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => false },
+    ]
+
+    expected_output = "false"
+
+    assert_template_result(expected_output, "{{ array | has: 'ok' }}", { "array" => array })
+    assert_template_result(expected_output, "{{ array | has: 'ok', true }}", { "array" => array })
+  end
+
+  def test_has_with_empty_arrays
+    template = <<~LIQUID
+      {%- assign has_product = products | has: 'title.content', 'Not found' -%}
+      {%- unless has_product -%}
+        Product not found.
+      {%- endunless -%}
+    LIQUID
+    expected_output = "Product not found."
+
+    assert_template_result(expected_output, template, { "products" => [] })
+  end
+
+  def test_has_with_false_value
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => true },
+    ]
+
+    template = "{{ array | has: 'ok', false }}"
+    expected_output = "true"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_has_with_false_value_when_does_not_have_it
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => true },
+      { "handle" => "gamma", "ok" => true },
+      { "handle" => "delta", "ok" => true },
+    ]
+
+    template = "{{ array | has: 'ok', false }}"
+    expected_output = "false"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_find_with_value
+    products = [
+      { "title" => "Pro goggles",    "price" => 1299 },
+      { "title" => "Thermal gloves", "price" => 1499 },
+      { "title" => "Alpine jacket",  "price" => 3999 },
+      { "title" => "Mountain boots", "price" => 3899 },
+      { "title" => "Safety helmet",  "price" => 1999 }
+    ]
+
+    template = <<~LIQUID
+      {%- assign product = products | find: 'price', 3999 -%}
+      {{- product.title -}}
+    LIQUID
+    expected_output = "Alpine jacket"
+
+    assert_template_result(expected_output, template, { "products" => products })
+  end
+
+  def test_find_with_empty_arrays
+    template = <<~LIQUID
+      {%- assign product = products | find: 'title.content', 'Not found' -%}
+      {%- unless product -%}
+        Product not found.
+      {%- endunless -%}
+    LIQUID
+    expected_output = "Product not found."
+
+    assert_template_result(expected_output, template, { "products" => [] })
+  end
+
+  def test_find_index_with_value
+    products = [
+      { "title" => "Pro goggles",    "price" => 1299 },
+      { "title" => "Thermal gloves", "price" => 1499 },
+      { "title" => "Alpine jacket",  "price" => 3999 },
+      { "title" => "Mountain boots", "price" => 3899 },
+      { "title" => "Safety helmet",  "price" => 1999 }
+    ]
+
+    template = <<~LIQUID
+      {%- assign index = products | find_index: 'price', 3999 -%}
+      {{- index -}}
+    LIQUID
+    expected_output = "2"
+
+    assert_template_result(expected_output, template, { "products" => products })
+  end
+
+  def test_find_index_with_empty_arrays
+    template = <<~LIQUID
+      {%- assign index = products | find_index: 'title.content', 'Not found' -%}
+      {%- unless index -%}
+        Index not found.
+      {%- endunless -%}
+    LIQUID
+    expected_output = "Index not found."
+
+    assert_template_result(expected_output, template, { "products" => [] })
+  end
+
+  def test_where
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => true },
+    ]
+
+    template = "{{ array | where: 'ok' | map: 'handle' | join: ' ' }}"
+    expected_output = "alpha delta"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_where_with_value
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => true },
+    ]
+
+    template = "{{ array | where: 'ok', true | map: 'handle' | join: ' ' }}"
+    expected_output = "alpha delta"
+
+    assert_template_result(expected_output, template, { "array" => array })
+  end
+
+  def test_where_with_false_value
+    array = [
+      { "handle" => "alpha", "ok" => true },
+      { "handle" => "beta", "ok" => false },
+      { "handle" => "gamma", "ok" => false },
+      { "handle" => "delta", "ok" => true },
+    ]
+
+    template = "{{ array | where: 'ok', false | map: 'handle' | join: ' ' }}"
+    expected_output = "beta gamma"
+
+    assert_template_result(expected_output, template, { "array" => array })
   end
 
   def test_where_string_keys

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