mdl 0.17.0 → 0.18.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5f3b2d8b702d0c1f3e4401b5c0a997d76f13368f57fc1be5d52acd2ca9ea35c2
-  data.tar.gz: f65a08dd97130930b44e93cb65cc318f218210b99d74ff915cd5842e17dca188
+  metadata.gz: fec16e614604e88653070c37b0d3a6eed2c3a3bd5eafc4c632c4183380aea42e
+  data.tar.gz: 296754842f0a085ce6973bdbf95fc77bfd5f0119347b07eb140b1ada10dd9afe
 SHA512:
-  metadata.gz: 0a63864cdb9583963ff12d78ccfd5d304b8162c464842140ceae23d5b14afab9d8f4fd60e473634bb0fdf3f2580a68ca8aca451559df058276fc3cb235dc8290
-  data.tar.gz: d381798b1c293e45a237368232429e0ab1e9812c1963b674383c61b0301fdcd72f3f34c285bcd58ea5ed1695fa5fd0fbf01514929aa49ded6a4df74472ce1822
+  metadata.gz: acc0a0484292c8e67c05662b2752db9d7920c97300544e868969540ec22209071e8998b1366877c1535da8791b0a8fc7aafd4ad377febea11f6e2b4612c8b991
+  data.tar.gz: 386804f3431fad7ca7a6fc3e68a93131357175ec5298e7b2b780d768628085131b201409b08cebe6b66942d5003c387faa4333ff61eb53792c0ca18720889dc2

data/Gemfile

@@ -4,8 +4,8 @@ gemspec
 group :development, :test do
   gem 'base64'
   gem 'bundler', '>= 1.12', '< 5'
-  gem 'minitest', '~> 5.26', '>= 5.26.2'
-  gem 'pry', '~> 0.15.2'
+  gem 'minitest', '~> 6.0'
+  gem 'pry', '~> 0.16.0'
   gem 'rake', '~> 13.3', '>= 13.3.1'
   gem 'rubocop', '~> 1.81'
 end

data/lib/mdl/cli.rb

@@ -29,12 +29,31 @@ module MarkdownLint
            :description => 'Increase verbosity',
            :boolean => true
 
+    option :html_to_native,
+           :short => '-n',
+           :long => '--[no-]html-to-native',
+           :boolean => true,
+           :description => 'Convert HTML elements to native elements'
+
     option :ignore_front_matter,
            :short => '-i',
            :long => '--[no-]ignore-front-matter',
            :boolean => true,
            :description => 'Ignore YAML front matter'
 
+    option :parse_block_html,
+           :short => '-b',
+           :long => '--[no-]parse-block-html',
+           :boolean => true,
+           :description => 'Process kramdown syntax in block HTML tags'
+
+    option :parse_span_html,
+           :short => '-p',
+           :long => '--[no-]parse-span-html',
+           :boolean => true,
+           :default => true,
+           :description => 'Process kramdown syntax in span HTML tags'
+
     option :show_kramdown_warnings,
            :short => '-w',
            :long => '--[no-]warnings',

data/lib/mdl/doc.rb

@@ -26,7 +26,7 @@ module MarkdownLint
     ##
     # Create a new document given a string containing the markdown source
 
-    def initialize(text, ignore_front_matter = false)
+    def initialize(text, ignore_front_matter = false, **)
       regex = /\A---\n(.*?)---\n\n?/m
       if ignore_front_matter && regex.match(text)
         @front_matter = regex.match(text).to_s
@@ -39,7 +39,7 @@ module MarkdownLint
       # The -1 is to cause split to preserve an extra entry in the array so we
       # can tell if there's a final newline in the file or not.
       @lines = text.split(/\R/, -1)
-      @parsed = Kramdown::Document.new(text, :input => 'MarkdownLint')
+      @parsed = Kramdown::Document.new(text, :input => 'MarkdownLint', **)
       @elements = @parsed.root.children
       add_annotations(@elements)
     end
@@ -47,13 +47,14 @@ module MarkdownLint
     ##
     # Alternate 'constructor' passing in a filename
 
-    def self.new_from_file(filename, ignore_front_matter = false)
+    def self.new_from_file(filename, ignore_front_matter = false, **)
       if filename == '-'
-        new($stdin.read.scrub, ignore_front_matter)
+        new($stdin.read.scrub, ignore_front_matter, **)
       else
         new(
           File.read(filename, :encoding => 'UTF-8').scrub,
           ignore_front_matter,
+          **,
         )
       end
     end

data/lib/mdl/kramdown_parser.rb

@@ -14,8 +14,14 @@ module Kramdown
         @block_parsers.insert(i, :codeblock_fenced_gfm)
       end
 
-      # Regular kramdown parser, but with GFM style fenced code blocks
-      FENCED_CODEBLOCK_MATCH = Kramdown::Parser::GFM::FENCED_CODEBLOCK_MATCH
+      # GFM fenced code blocks, extended to allow spaces in the info string
+      # (e.g. ```c hlines=2). The GFM regex restricts the info string to a
+      # single non-whitespace token, which causes kramdown to miss blocks whose
+      # info string contains a space, leading to false positives inside them.
+      # Capture groups match GFM's: 1=fence, 2=fence-char, 3=full-info,
+      # 4=first-word, 5=content.
+      FENCED_CODEBLOCK_MATCH =
+        /^ {0,3}(([~`]){3,})\s*?((\S+?)[^\n]*)?\n(.*?)^ {0,3}\1\2*\s*?\n/m
 
       # End paragraphs when a fenced code block starts, matching GFM
       # behavior. Without this, fenced code blocks without a preceding

data/lib/mdl/rules.rb

@@ -1,3 +1,12 @@
+require 'uri'
+
+uri_parser = if URI.const_defined?(:RFC2396_PARSER, false)
+               URI::RFC2396_PARSER
+             else
+               URI::DEFAULT_PARSER
+             end
+URI_REGEXP = uri_parser.make_regexp
+
 docs do |id, description|
   url_hash = [id.downcase,
               description.downcase.gsub(/[^a-z]+/, '-')].join('---')
@@ -7,9 +16,12 @@ end
 rule 'MD001', 'Header levels should only increment by one level at a time' do
   tags :headers
   aliases 'header-increment'
+  params :front_matter_title => /^\s*title\s*[:=]/
   check do |doc|
     headers = doc.find_type(:header)
-    old_level = nil
+    has = params[:front_matter_title]
+    has &&= doc.front_matter.match(params[:front_matter_title])
+    old_level = 1 if has
     errors = []
     headers.each do |h|
       errors << h[:location] if old_level && (h[:level] > old_level + 1)
@@ -22,8 +34,12 @@ end
 rule 'MD002', 'First header should be a top level header' do
   tags :headers
   aliases 'first-header-h1'
-  params :level => 1
+  params :level => 1, :front_matter_title => /^\s*title\s*[:=]/
   check do |doc|
+    has = params[:front_matter_title]
+    has &&= doc.front_matter.match(params[:front_matter_title])
+    next [] if has
+
     first_header = doc.find_type(:header).first
     if first_header && (first_header[:level] != @params[:level])
       [first_header[:location]]
@@ -288,7 +304,17 @@ rule 'MD013', 'Line length' do
     header_lines = doc.find_type_elements(:header).map do |e|
       doc.element_linenumber(e)
     end
+    # Every line that is a link reference:
+    #
+    # This link is referenced[1] at the bottom
+    #
+    # [1]: https://example.com
+    link_reference_lines = doc.matching_lines(/^\[.*\]: #{URI_REGEXP}$/)
+
     overlines = doc.matching_lines(/^.{#{@params[:line_length]}}.+/)
+
+    overlines -= link_reference_lines if params[:treat_links_as_single_words]
+
     overlines -= single_word_lines
     if !params[:code_blocks] || params[:ignore_code_blocks]
       overlines -= codeblock_lines
@@ -486,7 +512,7 @@ rule 'MD024', 'Multiple headers with the same content' do
           stack.pop
         elsif current_level < level
           stack.push([text])
-        elsif stack.last.include?(text)
+        elsif stack&.last&.include?(text)
           same_nesting_duplicates.add(header)
         end
 
@@ -503,13 +529,16 @@ end
 rule 'MD025', 'Multiple top level headers in the same document' do
   tags :headers
   aliases 'single-h1'
-  params :level => 1
+  params :level => 1, :front_matter_title => /^\s*title\s*[:=]/
   check do |doc|
     headers = doc.find_type(:header, false).select do |h|
       h[:level] == params[:level]
     end
-    if !headers.empty? && (doc.element_linenumber(headers[0]) == 1)
-      headers[1..].map { |h| doc.element_linenumber(h) }
+    has = params[:front_matter_title]
+    has &&= doc.front_matter.match(params[:front_matter_title])
+    if !headers.empty? && (doc.element_linenumber(headers[0]) == 1 || has)
+      headers = headers[1..] unless has
+      headers.map { |h| doc.element_linenumber(h) }
     end
   end
 end
@@ -712,8 +741,8 @@ rule 'MD032', 'Lists should be surrounded by blank lines' do
       end
       line.strip.match(/^(`{3,}|~{3,})/)
       if Regexp.last_match(1) && (
-          !in_code || (Regexp.last_match(1).slice(0, fence.length) == fence)
-        )
+        !in_code || (Regexp.last_match(1).slice(0, fence.length) == fence)
+      )
         fence = in_code ? nil : Regexp.last_match(1)
         in_code = !in_code
         in_list = false
@@ -741,6 +770,7 @@ end
 rule 'MD034', 'Bare URL used' do
   tags :links, :url
   aliases 'no-bare-urls'
+  params :allow_quoted => false
   check do |doc|
     errors = doc.matching_text_element_lines(
       %r{https?://}, %i{a html_element}
@@ -774,7 +804,17 @@ rule 'MD034', 'Bare URL used' do
       next false if line.nil?
 
       # Strip URLs inside markdown links, then check if a bare URL remains
-      line.gsub(%r{\]\(https?://[^)]*\)}, '').match?(%r{https?://})
+      line = line.gsub(%r{\]\(https?://[^)]*\)}, '')
+
+      if params[:allow_quoted]
+        # If allow_quoted is set, also strip any URL directly en-quoted,
+        # check if a bare url remains
+        line = line
+               .gsub(%r{"https?://\S*?"}, '')
+               .gsub(%r{'https?://\S*?'}, '')
+      end
+
+      line.match?(%r{https?://})
     end
   end
 end
@@ -883,11 +923,14 @@ end
 rule 'MD041', 'First line in file should be a top level header' do
   tags :headers
   aliases 'first-line-h1'
-  params :level => 1
+  params :level => 1, :front_matter_title => /^\s*title\s*[:=]/
   check do |doc|
     first_header = doc.find_type(:header).first
-    [1] if first_header.nil? || (first_header[:location] != 1) \
-      || (first_header[:level] != params[:level])
+    first = first_header.nil? || (first_header[:location] != 1)
+    first ||= first_header[:level] != params[:level]
+    has = params[:front_matter_title]
+    has &&= doc.front_matter.match(params[:front_matter_title])
+    [1] if first && !has
   end
 end
 

data/lib/mdl/version.rb

@@ -1,3 +1,3 @@
 module MarkdownLint
-  VERSION = '0.17.0'.freeze
+  VERSION = '0.18.1'.freeze
 end

data/lib/mdl.rb

@@ -67,9 +67,9 @@ module MarkdownLint
         if Config[:git_recurse]
           Dir.chdir(filename) do
             cli.cli_arguments[i] =
-              Mixlib::ShellOut.new("git ls-files '*.md' '*.markdown'")
-                              .run_command.stdout.lines
-                              .map { |m| File.join(filename, m.strip) }
+              Mixlib::ShellOut.new("git ls-files -z '*.md' '*.markdown'")
+                              .run_command.stdout.split("\x00")
+                              .map { |m| File.join(filename, m) }
           end
         else
           cli.cli_arguments[i] = Dir["#{filename}/**/*.{md,markdown}"]
@@ -95,7 +95,12 @@ module MarkdownLint
         text = original_text.dup
       end
 
-      doc = Doc.new_from_file(filename, Config[:ignore_front_matter])
+      options = {
+        :parse_block_html => Config[:parse_block_html],
+        :parse_span_html => Config[:parse_span_html],
+        :html_to_native => Config[:html_to_native],
+      }
+      doc = Doc.new_from_file(filename, Config[:ignore_front_matter], **options)
       filename = '(stdin)' if filename == '-'
       if Config[:show_kramdown_warnings]
         status = 2 unless doc.parsed.warnings.empty?
@@ -113,7 +118,7 @@ module MarkdownLint
         if Config[:fix] && filename != '(stdin)' && rule.fix
           rule.fix.call(doc, error_lines)
           text = doc.to_s
-          doc = Doc.new(text.dup, Config[:ignore_front_matter])
+          doc = Doc.new(text.dup, Config[:ignore_front_matter], **options)
           corrected = true
         end
 

data/mdl.gemspec

@@ -26,4 +26,5 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'mixlib-cli'
   spec.add_dependency 'mixlib-config'
   spec.add_dependency 'mixlib-shellout'
+  spec.add_dependency 'uri'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mdl
 version: !ruby/object:Gem::Version
-  version: 0.17.0
+  version: 0.18.1
 platform: ruby
 authors:
 - Phil Dibowitz
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-06-03 00:00:00.000000000 Z
+date: 2026-08-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: kramdown
@@ -80,6 +80,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: uri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Style checker/lint tool for markdown files
 email:
 - phil@ipom.com