mdl 0.12.0 → 0.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 240bbb771676be213b572426ae6aa48dd810cb11769263a30ee1e2b98b6751d5
-  data.tar.gz: 0c474a99242d291a202b958294ba749977230b43b24a38342a00bc6675857d6b
+  metadata.gz: bb98b688ab9d9dc7bac3c169f20fefc7c0cb27ce5bf574bec52053d592b7a9c7
+  data.tar.gz: 873df51b4011d23617c1d73ab47a1928765fee0502b6f58853e2932bb3d5ec59
 SHA512:
-  metadata.gz: 538a08a57be028038bc8e1fe72c241e81e57261b84a0b58efb6875b515c8b0dfb01715826959778c6d88a9c6bb2b799b668a1662ac09e1a9d1c8a8a67817addd
-  data.tar.gz: 3104fb8e6bd66686b6268a5a5cb31f4bbdcef9fa7f7190f31b60a99c5acc489c47f19998c5bf40f9eff064c0f71cbeb73a8cb164a04899bb57666d041e85c125
+  metadata.gz: fea533cf2d4a61c4da291a094e3f94080acee8837919935e789e1b39c98d8bcc416cb9fcb143a10a1f63738ee993d3fe5ce89ca3dc664a9a11712796db8dbc4d
+  data.tar.gz: 8dc7470f981b1267dddb1f668afc4f85c742d6c467ae9a31bcaf24618792d6d9c7792a328ff3258d8efd071d9592b4a84600a2825e787b26d1cb5f7e979989af

data/lib/mdl/cli.rb

@@ -107,6 +107,12 @@ module MarkdownLint
            :description => 'JSON output',
            :boolean => true
 
+    option :sarif,
+           :short => '-S',
+           :long => '--sarif',
+           :description => 'SARIF output',
+           :boolean => true
+
     def run(argv = ARGV)
       parse_options(argv)
 

data/lib/mdl/doc.rb

@@ -268,6 +268,30 @@ module MarkdownLint
       lines
     end
 
+    ##
+    # Returns the element as plaintext
+
+    def extract_as_text(element)
+      quotes = {
+        :rdquo => '"',
+        :ldquo => '"',
+        :lsquo => "'",
+        :rsquo => "'",
+      }
+      # If anything goes amiss here, e.g. unknown type, then nil will be
+      # returned and we'll just not catch that part of the text, which seems
+      # like a sensible failure mode.
+      element.children.map do |e|
+        if e.type == :text || e.type == :codespan
+          e.value
+        elsif %i{strong em p a}.include?(e.type)
+          extract_as_text(e).join("\n")
+        elsif e.type == :smart_quote
+          quotes[e.value]
+        end
+      end.join.split("\n")
+    end
+
     private
 
     ##

data/lib/mdl/formatters/sarif.rb

@@ -0,0 +1,89 @@
+require 'json'
+
+module MarkdownLint
+  # SARIF formatter
+  #
+  # @see https://docs.oasis-open.org/sarif/sarif/v2.1.0/sarif-v2.1.0.html
+  class SarifFormatter
+    class << self
+      def generate(rules, results)
+        matched_rules_id = results.map { |result| result['rule'] }.uniq
+        matched_rules = rules.select { |id, _| matched_rules_id.include?(id) }
+        JSON.generate(generate_sarif(matched_rules, results))
+      end
+
+      def generate_sarif(rules, results)
+        {
+          :'$schema' => 'https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json',
+          :version => '2.1.0',
+          :runs => [
+            {
+              :tool => {
+                :driver => {
+                  :name => 'Markdown lint',
+                  :version => MarkdownLint::VERSION,
+                  :informationUri => 'https://github.com/markdownlint/markdownlint',
+                  :rules => generate_sarif_rules(rules),
+                },
+              },
+              :results => generate_sarif_results(rules, results),
+            }
+          ],
+        }
+      end
+
+      def generate_sarif_rules(rules)
+        rules.map do |id, rule|
+          {
+            :id => id,
+            :name => rule.aliases.first.split('-').map(&:capitalize).join,
+            :defaultConfiguration => {
+              :level => 'note',
+            },
+            :properties => {
+              :description => rule.description,
+              :tags => rule.tags,
+              :queryURI => rule.docs_url,
+            },
+            :shortDescription => {
+              :text => rule.description,
+            },
+            :fullDescription => {
+              :text => rule.description,
+            },
+            :helpUri => rule.docs_url,
+            :help => {
+              :text => "More info: #{rule.docs_url}",
+              :markdown => "[More info](#{rule.docs_url})",
+            },
+          }
+        end
+      end
+
+      def generate_sarif_results(rules, results)
+        results.map do |result|
+          {
+            :ruleId => result['rule'],
+            :ruleIndex => rules.find_index { |id, _| id == result['rule'] },
+            :message => {
+              :text => "#{result['rule']} - #{result['description']}",
+            },
+            :locations => [
+              {
+                :physicalLocation => {
+                  :artifactLocation => {
+                    :uri => result['filename'],
+                    :uriBaseId => '%SRCROOT%',
+                  },
+                  :region => {
+                    :startLine => result['line'],
+                  },
+                },
+              }
+            ],
+          }
+        end
+      end
+    end
+  end
+end

data/lib/mdl/rules.rb

@@ -1,7 +1,7 @@
 docs do |id, description|
   url_hash = [id.downcase,
               description.downcase.gsub(/[^a-z]+/, '-')].join('---')
-  "https://github.com/markdownlint/markdownlint/blob/master/docs/RULES.md##{url_hash}"
+  "https://github.com/markdownlint/markdownlint/blob/main/docs/RULES.md##{url_hash}"
 end
 
 rule 'MD001', 'Header levels should only increment by one level at a time' do
@@ -33,7 +33,7 @@ end
 
 rule 'MD003', 'Header style' do
   # Header styles are things like ### and adding underscores
-  # See http://daringfireball.net/projects/markdown/syntax#header
+  # See https://daringfireball.net/projects/markdown/syntax#header
   tags :headers
   aliases 'header-style'
   # :style can be one of :consistent, :atx, :atx_closed, :setext
@@ -126,7 +126,7 @@ rule 'MD005', 'Inconsistent indentation for list items at the same level' do
 end
 
 rule 'MD006', 'Consider starting bulleted lists at the beginning of the line' do
-  # Starting at the beginning of the line means that indendation for each
+  # Starting at the beginning of the line means that indentation for each
   # bullet level can be identical.
   tags :bullet, :ul, :indentation
   aliases 'ul-start-left'
@@ -161,7 +161,7 @@ end
 rule 'MD009', 'Trailing spaces' do
   tags :whitespace
   aliases 'no-trailing-spaces'
-  params :br_spaces => 0
+  params :br_spaces => 2
   check do |doc|
     errors = doc.matching_lines(/\s$/)
     if params[:br_spaces] > 1
@@ -458,7 +458,10 @@ rule 'MD027', 'Multiple spaces after blockquote symbol' do
     errors = []
     doc.find_type_elements(:blockquote).each do |e|
       linenum = doc.element_linenumber(e)
-      lines = doc.extract_text(e, /^\s*> /)
+      lines = doc.extract_as_text(e)
+      # Handle first line specially as whitespace is stripped from the text
+      # element
+      errors << linenum if doc.element_line(e).match(/^\s*>  /)
       lines.each do |line|
         errors << linenum if line.start_with?(' ')
         linenum += 1
@@ -619,8 +622,14 @@ end
 rule 'MD033', 'Inline HTML' do
   tags :html
   aliases 'no-inline-html'
+  params :allowed_elements => ''
   check do |doc|
     doc.element_linenumbers(doc.find_type(:html_element))
+    allowed = params[:allowed_elements].delete(" \t\r\n").downcase.split(',')
+    errors = doc.find_type_elements(:html_element).reject do |e|
+      allowed.include?(e.value)
+    end
+    doc.element_linenumbers(errors)
   end
 end
 
@@ -790,3 +799,92 @@ rule 'MD047', 'File should end with a single newline character' do
     error_lines
   end
 end
+
+rule 'MD055', 'Table row doesn\'t begin/end with pipes' do
+  tags :tables
+  aliases 'table-rows-start-and-end-with-pipes'
+  check do |doc|
+    error_lines = []
+    tables = doc.find_type_elements(:table)
+    lines = doc.lines
+
+    tables.each do |table|
+      table_pos = table.options[:location] - 1
+      table_rows = get_table_rows(lines, table_pos)
+
+      table_rows.each_with_index do |line, index|
+        if line.length < 2 || line[0] != '|' || line[-1] != '|'
+          error_lines << (table_pos + index + 1)
+        end
+      end
+    end
+
+    error_lines
+  end
+end
+
+rule 'MD056', 'Table has inconsistent number of columns' do
+  tags :tables
+  aliases 'inconsistent-columns-in-table'
+  check do |doc|
+    error_lines = []
+    tables = doc.find_type_elements(:table)
+    lines = doc.lines
+
+    tables.each do |table|
+      table_pos = table.options[:location] - 1
+      table_rows = get_table_rows(lines, table_pos)
+
+      num_headings = number_of_columns_in_a_table_row(lines[table_pos])
+
+      table_rows.each_with_index do |line, index|
+        if number_of_columns_in_a_table_row(line) != num_headings
+          error_lines << (table_pos + index + 1)
+        end
+      end
+    end
+
+    error_lines
+  end
+end
+
+rule 'MD057', 'Table has missing or invalid header separation (second row)' do
+  tags :tables
+  aliases 'table-invalid-second-row'
+  check do |doc|
+    error_lines = []
+    tables = doc.find_type_elements(:table)
+    lines = doc.lines
+
+    tables.each do |table|
+      second_row = ''
+
+      # line number of table start (1-indexed)
+      # which is equal to second row's index (0-indexed)
+      line_num = table.options[:location]
+      second_row = lines[line_num] if line_num < lines.length
+
+      # This pattern matches if
+      #   1) The row starts and stops with | characters
+      #   2) Only consists of characters '|', '-', ':' and whitespace
+      #   3) Each section between the separators (i.e. '|')
+      #      a) has at least three consecutive dashes
+      #      b) can have whitespace at the beginning or the end
+      #      c) can have colon before and/or after dashes (for alignment)
+      #   Some examples:
+      #       |-----|----|-------|      --> matches
+      #       |:---:|:---|-------|      --> matches
+      #       |  :------:  | ----|      --> matches
+      #       | - - - | - - - |         --> does NOT match
+      #       |::---|                   --> does NOT match
+      #       |----:|:--|----|          --> does NOT match
+      pattern = /^(\|\s*:?-{3,}:?\s*)+\|$/
+      unless second_row.match(pattern)
+        # Second row is not in the form described by the pattern
+        error_lines << (line_num + 1)
+      end
+    end
+
+    error_lines
+  end
+end

data/lib/mdl/ruleset.rb

@@ -48,6 +48,67 @@ module MarkdownLint
     def docs_url
       @generate_docs&.call(id, description)
     end
+
+    # This method calculates the number of columns in a table row
+    #
+    # @param [String] table_row A row of the table in question.
+    # @return [Numeric] Number of columns in the row
+    def number_of_columns_in_a_table_row(table_row)
+      columns = table_row.strip.split('|')
+
+      if columns.empty?
+        # The stripped line consists of zero or more pipe characters
+        # and nothing more.
+        #
+        # Examples of stripped rows:
+        #   '||' --> one column
+        #   '|||' --> two columns
+        #   '|' --> zero columns
+        [0, table_row.count('|') - 1].max
+      else
+        # Number of columns is the number of splited
+        # segments with pipe separator. The first segment
+        # is ignored when it's empty string because
+        # someting like '|1|2|' is split into ['', '1', '2']
+        # when using split('|') function.
+        #
+        # Some examples:
+        #   '|foo|bar|' --> two columns
+        #   '  |foo|bar|' --> two columns
+        #   '|foo|bar' --> two columns
+        #   'foo|bar' --> two columns
+        columns.size - (columns[0].empty? ? 1 : 0)
+      end
+    end
+
+    # This method returns all the rows of a table
+    #
+    # @param [Array<String>] lines Lines of a doc as an array
+    # @param [Numeric] pos Position/index of the table in the array
+    # @return [Array<String>] Rows of the table in an array
+    def get_table_rows(lines, pos)
+      table_rows = []
+      while pos < lines.length
+        line = lines[pos]
+
+        # If the previous line is a table and the current line
+        #   1) includes pipe character
+        #   2) does not start with code block identifiers
+        #     a) >= 4 spaces
+        #     b) < 4 spaces and ``` right after
+        #
+        # it is possibly a table row
+        unless line.include?('|') && !line.start_with?('    ') &&
+               !line.strip.start_with?('```')
+          break
+        end
+
+        table_rows << line
+        pos += 1
+      end
+
+      table_rows
+    end
   end
 
   # defines a ruleset

data/lib/mdl/style.rb

@@ -58,7 +58,7 @@ module MarkdownLint
           warn "#{style_file} does not appear to be a built-in style." +
                ' If you meant to pass in your own style file, it must contain' +
                " a '/' or end in '.rb'. See https://github.com/markdownlint/" +
-               'markdownlint/blob/master/docs/configuration.md'
+               'markdownlint/blob/main/docs/configuration.md'
           exit(1)
         end
         style_file = tmp

data/lib/mdl/version.rb

@@ -1,3 +1,3 @@
 module MarkdownLint
-  VERSION = '0.12.0'.freeze
+  VERSION = '0.13.0'.freeze
 end

data/lib/mdl.rb

@@ -1,3 +1,4 @@
+require_relative 'mdl/formatters/sarif'
 require_relative 'mdl/cli'
 require_relative 'mdl/config'
 require_relative 'mdl/doc'
@@ -103,7 +104,7 @@ module MarkdownLint
         status = 1
         error_lines.each do |line|
           line += doc.offset # Correct line numbers for any yaml front matter
-          if Config[:json]
+          if Config[:json] || Config[:sarif]
             results << {
               'filename' => filename,
               'line' => line,
@@ -118,12 +119,13 @@ module MarkdownLint
           end
         end
 
-        # If we're not in JSON mode (URLs are in the object), and we cannot
-        # make real links (checking if we have a TTY is an OK heuristic for
-        # that) then, instead of making the output ugly with long URLs, we
+        # If we're not in JSON or SARIF mode (URLs are in the object), and we
+        # cannot make real links (checking if we have a TTY is an OK heuristic
+        # for that) then, instead of making the output ugly with long URLs, we
         # print them at the end. And of course we only want to print each URL
         # once.
-        if !Config[:json] && !$stdout.tty? && !docs_to_print.include?(rule)
+        if !Config[:json] && !Config[:sarif] &&
+           !$stdout.tty? && !docs_to_print.include?(rule)
           docs_to_print << rule
         end
       end
@@ -132,6 +134,8 @@ module MarkdownLint
     if Config[:json]
       require 'json'
       puts JSON.generate(results)
+    elsif Config[:sarif]
+      puts SarifFormatter.generate(rules, results)
     elsif docs_to_print.any?
       puts "\nFurther documentation is available for these failures:"
       docs_to_print.each do |rule|

data/mdl.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.email = ['mark@mivok.net']
   spec.summary = 'Markdown lint tool'
   spec.description = 'Style checker/lint tool for markdown files'
-  spec.homepage = 'http://github.com/markdownlint/markdownlint'
+  spec.homepage = 'https://github.com/markdownlint/markdownlint'
   spec.license = 'MIT'
   spec.metadata['rubygems_mfa_required'] = 'true'
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mdl
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 0.13.0
 platform: ruby
 authors:
 - Mark Harrison
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-10-18 00:00:00.000000000 Z
+date: 2023-10-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: kramdown
@@ -189,6 +189,7 @@ files:
 - lib/mdl/cli.rb
 - lib/mdl/config.rb
 - lib/mdl/doc.rb
+- lib/mdl/formatters/sarif.rb
 - lib/mdl/kramdown_parser.rb
 - lib/mdl/rules.rb
 - lib/mdl/ruleset.rb
@@ -199,7 +200,7 @@ files:
 - lib/mdl/styles/relaxed.rb
 - lib/mdl/version.rb
 - mdl.gemspec
-homepage: http://github.com/markdownlint/markdownlint
+homepage: https://github.com/markdownlint/markdownlint
 licenses:
 - MIT
 metadata:
@@ -219,7 +220,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.3.15
 signing_key:
 specification_version: 4
 summary: Markdown lint tool