commonmarker 0.22.0 → 0.23.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f5356237deaf85df9914e0c7fa3f121fa0301579653b83b006df4dd8404c65f2
-  data.tar.gz: 9d4a09830e1c107dec28e47a3c0ab96f2cc6bcd9786982e38607752022ec12f1
+  metadata.gz: c52b70b0c680aae2d46b089b673745cbe586f1e27589bd81b1f3f0f091a7659d
+  data.tar.gz: 400efb13ab3ba9c72d451be4cd4cac8ee17688f70733d6d57771a093e412b63f
 SHA512:
-  metadata.gz: 7e43f365eb266fa8c0627572999a2102df7dd65e0404917c5fa6054b532c526a35ad5d0ef9423cf68033edc52fb0c20da79ca73d7345b04d4493f33bff35ed73
-  data.tar.gz: 0e5da729c2247288a1bf60672f572f785def6e2a1726afeaf87aa1332d083e4834d52c403479a36437f9c0a9e99548569f7d5bc092a405304ccef81ac71096b1
+  metadata.gz: 99309c1ab3c30c524adac6be1f75b3e63fe166b9248f8a8e74bd228a2428b10c794a56a3d5390786e4b33a869531f5879461c73d1ae7aaea66be491000779761
+  data.tar.gz: 2c4ac9a297cfb0204eb4355f0aa3e8471ddd2f6bf9162e7db2a71f16e32f3470779f86082e8aa9473ddf0f45ee3df41d133a7f073209c3d1441da4468266297d

data/README.md

@@ -180,6 +180,76 @@ The available extensions are:
 * `:autolink` - This provides support for automatically converting URLs to anchor tags.
 * `:tagfilter` - This escapes [several "unsafe" HTML tags](https://github.github.com/gfm/#disallowed-raw-html-extension-), causing them to not have any effect.
 
+## Output formats
+
+Like CMark, CommonMarker can generate output in several formats: HTML, XML, plaintext, and commonmark are currently supported.
+
+### HTML
+
+The default output format, HTML, will be generated when calling `to_html` or using `--to=html` on the command line.
+
+```ruby
+doc = CommonMarker.render_doc('*Hello* world!', :DEFAULT)
+puts(doc.to_html)
+
+<p><em>Hello</em> world!</p>
+```
+
+### XML
+
+XML will be generated when calling `to_xml` or using `--to=xml` on the command line.
+
+```ruby
+doc = CommonMarker.render_doc('*Hello* world!', :DEFAULT)
+puts(doc.to_xml)
+
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE document SYSTEM "CommonMark.dtd">
+<document xmlns="http://commonmark.org/xml/1.0">
+  <paragraph>
+    <emph>
+      <text xml:space="preserve">Hello</text>
+    </emph>
+    <text xml:space="preserve"> world!</text>
+  </paragraph>
+</document>
+```
+
+### Plaintext
+
+Plaintext will be generated when calling `to_plaintext` or using `--to=plaintext` on the command line.
+
+```ruby
+doc = CommonMarker.render_doc('*Hello* world!', :DEFAULT)
+puts(doc.to_plaintext)
+
+Hello world!
+```
+
+### Commonmark
+
+Commonmark will be generated when calling `to_commonmark` or using `--to=commonmark` on the command line.
+
+``` ruby
+text = <<-TEXT
+1. I am a numeric list.
+2. I continue the list.
+* Suddenly, an unordered list!
+* What fun!
+TEXT
+
+doc = CommonMarker.render_doc(text, :DEFAULT)
+puts(doc.to_commonmark)
+
+1.  I am a numeric list.
+2.  I continue the list.
+
+<!-- end list -->
+
+  - Suddenly, an unordered list\!
+  - What fun\!
+```
+
 ## Developing locally
 
 After cloning the repo:

data/bin/commonmarker

@@ -15,13 +15,16 @@ def parse_options
   extensions = CommonMarker.extensions
   parse_options = CommonMarker::Config::OPTS.fetch(:parse)
   render_options = CommonMarker::Config::OPTS.fetch(:render)
+  format_options = CommonMarker::Config::OPTS.fetch(:format)
 
   options.active_extensions = []
   options.active_parse_options = [:DEFAULT]
   options.active_render_options = [:DEFAULT]
+  options.output_format = :html
 
   option_parser = OptionParser.new do |opts|
     opts.banner = 'Usage: commonmarker [--html-renderer] [--extension=EXTENSION]'
+    opts.separator '                    [--to=FORMAT]'
     opts.separator '                    [--parse-option=OPTION]'
     opts.separator '                    [--render-option=OPTION]'
     opts.separator '                    [FILE..]'
@@ -43,6 +46,7 @@ def parse_options
     opts.on('-h', '--help', 'Prints this help') do
       puts opts
       puts
+      puts "Available formats: #{format_options.join(', ')}"
       puts "Available extentions: #{extensions.join(', ')}"
       puts "Available parse options: #{parse_options.keys.join(', ')}"
       puts "Available render options: #{render_options.keys.join(', ')}"
@@ -51,7 +55,16 @@ def parse_options
       exit
     end
 
-    opts.on('--html-renderer', 'Use the HtmlRenderer renderer rather than the native C renderer') do
+    opts.on('-tFORMAT', '--to=FORMAT', String, 'Specify output FORMAT') do |value|
+      value = value.to_sym
+      if format_options.include?(value)
+        options.output_format = value
+      else
+        abort("format '#{value}' not found")
+      end
+    end
+
+    opts.on('--html-renderer', 'Use the HtmlRenderer renderer rather than the native C renderer (only valid when format is html)') do
       options.renderer = true
     end
 
@@ -88,11 +101,23 @@ end
 
 options = parse_options
 
+abort("format '#{options.output_format}' does not support using the HtmlRenderer renderer") if
+  options.renderer && options.output_format != :html
+
 doc = CommonMarker.render_doc(ARGF.read, options.active_parse_options, options.active_extensions)
 
-if options.renderer
-  renderer = CommonMarker::HtmlRenderer.new(extensions: options.active_extensions)
-  $stdout.write(renderer.render(doc))
-else
-  $stdout.write(doc.to_html(options.active_render_options, options.active_extensions))
+case options.output_format
+when :html
+  if options.renderer
+    renderer = CommonMarker::HtmlRenderer.new(options: options.active_render_options, extensions: options.active_extensions)
+    $stdout.write(renderer.render(doc))
+  else
+    $stdout.write(doc.to_html(options.active_render_options, options.active_extensions))
+  end
+when :xml
+  $stdout.write(doc.to_xml(options.active_render_options))
+when :commonmark
+  $stdout.write(doc.to_commonmark(options.active_render_options))
+when :plaintext
+  $stdout.write(doc.to_plaintext(options.active_render_options))
 end

data/ext/commonmarker/commonmarker.c

@@ -186,6 +186,40 @@ static VALUE rb_markdown_to_html(VALUE self, VALUE rb_text, VALUE rb_options, VA
   return ruby_html;
 }
 
+/*
+ * Internal: Parses a Markdown string into an HTML string.
+ *
+ */
+static VALUE rb_markdown_to_xml(VALUE self, VALUE rb_text, VALUE rb_options, VALUE rb_extensions) {
+  char *str, *xml;
+  int len;
+  cmark_parser *parser;
+  cmark_node *doc;
+  Check_Type(rb_text, T_STRING);
+  Check_Type(rb_options, T_FIXNUM);
+
+  parser = prepare_parser(rb_options, rb_extensions, cmark_get_arena_mem_allocator());
+
+  str = (char *)RSTRING_PTR(rb_text);
+  len = RSTRING_LEN(rb_text);
+
+  cmark_parser_feed(parser, str, len);
+  doc = cmark_parser_finish(parser);
+  if (doc == NULL) {
+    cmark_arena_reset();
+    rb_raise(rb_eNodeError, "error parsing document");
+  }
+
+  cmark_mem *default_mem = cmark_get_default_mem_allocator();
+  xml = cmark_render_xml_with_mem(doc, FIX2INT(rb_options), default_mem);
+  cmark_arena_reset();
+
+  VALUE ruby_xml = rb_str_new2(xml);
+  default_mem->free(xml);
+
+  return ruby_xml;
+}
+
 /*
  * Internal: Creates a node based on a node type.
  *
@@ -574,6 +608,28 @@ static VALUE rb_render_html(VALUE self, VALUE rb_options, VALUE rb_extensions) {
   return ruby_html;
 }
 
+/* Internal: Convert the node to an XML string.
+ *
+ * Returns a {String}.
+ */
+static VALUE rb_render_xml(VALUE self, VALUE rb_options) {
+  int options;
+  int i;
+  cmark_node *node;
+  Check_Type(rb_options, T_FIXNUM);
+
+  options = FIX2INT(rb_options);
+
+  Data_Get_Struct(self, cmark_node, node);
+
+  char *xml = cmark_render_xml(node, options);
+  VALUE ruby_xml = rb_str_new2(xml);
+
+  free(xml);
+
+  return ruby_xml;
+}
+
 /* Internal: Convert the node to a CommonMark string.
  *
  * Returns a {String}.
@@ -1216,6 +1272,8 @@ __attribute__((visibility("default"))) void Init_commonmarker() {
   rb_cNode = rb_define_class_under(module, "Node", rb_cObject);
   rb_define_singleton_method(rb_cNode, "markdown_to_html", rb_markdown_to_html,
                              3);
+  rb_define_singleton_method(rb_cNode, "markdown_to_xml", rb_markdown_to_xml,
+                             3);
   rb_define_singleton_method(rb_cNode, "new", rb_node_new, 1);
   rb_define_singleton_method(rb_cNode, "parse_document", rb_parse_document, 4);
   rb_define_method(rb_cNode, "string_content", rb_node_get_string_content, 0);
@@ -1228,6 +1286,7 @@ __attribute__((visibility("default"))) void Init_commonmarker() {
   rb_define_method(rb_cNode, "next", rb_node_next, 0);
   rb_define_method(rb_cNode, "insert_before", rb_node_insert_before, 1);
   rb_define_method(rb_cNode, "_render_html", rb_render_html, 2);
+  rb_define_method(rb_cNode, "_render_xml", rb_render_xml, 1);
   rb_define_method(rb_cNode, "_render_commonmark", rb_render_commonmark, -1);
   rb_define_method(rb_cNode, "_render_plaintext", rb_render_plaintext, -1);
   rb_define_method(rb_cNode, "insert_after", rb_node_insert_after, 1);

data/lib/commonmarker/config.rb

@@ -24,7 +24,8 @@ module CommonMarker
         FULL_INFO_STRING: (1 << 16),
         UNSAFE: (1 << 17),
         FOOTNOTES: (1 << 13)
-      }.freeze
+      }.freeze,
+      format: %i[html xml commonmark plaintext].freeze
     }.freeze
 
     def self.process_options(option, type)

data/lib/commonmarker/node.rb

@@ -30,6 +30,16 @@ module CommonMarker
       _render_html(opts, extensions).force_encoding('utf-8')
     end
 
+    # Public: Convert the node to an XML string.
+    #
+    # options - A {Symbol} or {Array of Symbol}s indicating the render options
+    #
+    # Returns a {String}.
+    def to_xml(options = :DEFAULT)
+      opts = Config.process_options(options, :render)
+      _render_xml(opts).force_encoding('utf-8')
+    end
+
     # Public: Convert the node to a CommonMark string.
     #
     # options - A {Symbol} or {Array of Symbol}s indicating the render options

data/lib/commonmarker/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CommonMarker
-  VERSION = '0.22.0'
+  VERSION = '0.23.0'
 end

data/test/test_commands.rb

@@ -28,4 +28,45 @@ class TestCommands < Minitest::Test
     assert_includes out, '<p><del>hi</del>'
     %w[<table> <tr> <th> a </th> <td> c </td>].each { |html| assert_includes out, html }
   end
+
+  def test_understands_html_format_with_renderer_and_extensions
+    out = make_bin('table.md', '--to=html --extension=table,strikethrough --html-renderer')
+    refute_includes out, '| a'
+    assert_includes out, '<p><del>hi</del>'
+    %w[<table> <tr> <th> a </th> <td> c </td>].each { |html| assert_includes out, html }
+  end
+
+  def test_understands_xml_format
+    out = make_bin('strong.md', '--to=xml')
+    assert_includes out, '<?xml version="1.0" encoding="UTF-8"?>'
+    assert_includes out, '<text xml:space="preserve">strong</text>'
+  end
+
+  def test_understands_commonmark_format
+    out = make_bin('strong.md', '--to=commonmark')
+    assert_equal('I am **strong**', out)
+  end
+
+  def test_understands_plaintext_format
+    out = make_bin('strong.md', '--to=plaintext')
+    assert_equal('I am strong', out)
+  end
+
+  def test_aborts_invalid_format
+    _out, err = capture_subprocess_io do
+      make_bin('strong.md', '--to=unknown')
+    end
+
+    assert_match "format 'unknown' not found", err
+  end
+
+  def test_aborts_format_and_html_renderer_combinations
+    (CommonMarker::Config::OPTS[:format] - [:html]).each do |format|
+      _out, err = capture_subprocess_io do
+        make_bin('strong.md', "--to=#{format} --html-renderer")
+      end
+
+      assert_match "format '#{format}' does not support using the HtmlRenderer renderer", err
+    end
+  end
 end

data/test/test_encoding.rb

@@ -9,6 +9,9 @@ class TestEncoding < Minitest::Test
     doc = CommonMarker.render_doc(contents, :SMART)
     render = doc.to_html
     assert_equal('<p>This curly quote “makes commonmarker throw an exception”.</p>', render.rstrip)
+
+    render = doc.to_xml
+    assert_includes(render, '<text xml:space="preserve">This curly quote “makes commonmarker throw an exception”.</text>')
   end
 
   def test_string_content_is_utf8

data/test/test_xml.rb

@@ -0,0 +1,107 @@
+# frozen_string_literal: true
+
+require 'test_helper'
+
+class TestXml < Minitest::Test
+  def setup
+    @markdown = <<~MD
+      Hi *there*!
+
+      1. I am a numeric list.
+      2. I continue the list.
+      * Suddenly, an unordered list!
+      * What fun!
+
+      Okay, _enough_.
+
+      | a   | b   |
+      | --- | --- |
+      | c   | d   |
+    MD
+  end
+
+  def render_doc(doc)
+    CommonMarker.render_doc(doc, :DEFAULT, [:table])
+  end
+
+  def test_to_xml
+    compare = render_doc(@markdown).to_xml(:SOURCEPOS)
+
+    assert_equal <<~XML, compare
+      <?xml version="1.0" encoding="UTF-8"?>
+      <!DOCTYPE document SYSTEM "CommonMark.dtd">
+      <document sourcepos="1:1-12:13" xmlns="http://commonmark.org/xml/1.0">
+        <paragraph sourcepos="1:1-1:11">
+          <text sourcepos="1:1-1:3" xml:space="preserve">Hi </text>
+          <emph sourcepos="1:4-1:10">
+            <text sourcepos="1:5-1:9" xml:space="preserve">there</text>
+          </emph>
+          <text sourcepos="1:11-1:11" xml:space="preserve">!</text>
+        </paragraph>
+        <list sourcepos="3:1-4:23" type="ordered" start="1" delim="period" tight="true">
+          <item sourcepos="3:1-3:23">
+            <paragraph sourcepos="3:4-3:23">
+              <text sourcepos="3:4-3:23" xml:space="preserve">I am a numeric list.</text>
+            </paragraph>
+          </item>
+          <item sourcepos="4:1-4:23">
+            <paragraph sourcepos="4:4-4:23">
+              <text sourcepos="4:4-4:23" xml:space="preserve">I continue the list.</text>
+            </paragraph>
+          </item>
+        </list>
+        <list sourcepos="5:1-7:0" type="bullet" tight="true">
+          <item sourcepos="5:1-5:30">
+            <paragraph sourcepos="5:3-5:30">
+              <text sourcepos="5:3-5:30" xml:space="preserve">Suddenly, an unordered list!</text>
+            </paragraph>
+          </item>
+          <item sourcepos="6:1-7:0">
+            <paragraph sourcepos="6:3-6:11">
+              <text sourcepos="6:3-6:11" xml:space="preserve">What fun!</text>
+            </paragraph>
+          </item>
+        </list>
+        <paragraph sourcepos="8:1-8:15">
+          <text sourcepos="8:1-8:6" xml:space="preserve">Okay, </text>
+          <emph sourcepos="8:7-8:14">
+            <text sourcepos="8:8-8:13" xml:space="preserve">enough</text>
+          </emph>
+          <text sourcepos="8:15-8:15" xml:space="preserve">.</text>
+        </paragraph>
+        <table sourcepos="10:1-12:13">
+          <table_header sourcepos="10:1-10:13">
+            <table_cell sourcepos="10:2-10:6">
+              <text sourcepos="10:3-10:3" xml:space="preserve">a</text>
+            </table_cell>
+            <table_cell sourcepos="10:8-10:12">
+              <text sourcepos="10:9-10:9" xml:space="preserve">b</text>
+            </table_cell>
+          </table_header>
+          <table_row sourcepos="12:1-12:13">
+            <table_cell sourcepos="12:2-12:6">
+              <text sourcepos="12:3-12:3" xml:space="preserve">c</text>
+            </table_cell>
+            <table_cell sourcepos="12:8-12:12">
+              <text sourcepos="12:9-12:9" xml:space="preserve">d</text>
+            </table_cell>
+          </table_row>
+        </table>
+      </document>
+    XML
+  end
+
+  def test_to_xml_with_quotes
+    compare = render_doc('"quotes" should be escaped').to_xml(:DEFAULT)
+
+    assert_equal <<~XML, compare
+      <?xml version="1.0" encoding="UTF-8"?>
+      <!DOCTYPE document SYSTEM "CommonMark.dtd">
+      <document xmlns="http://commonmark.org/xml/1.0">
+        <paragraph>
+          <text xml:space="preserve">&quot;quotes&quot; should be escaped</text>
+        </paragraph>
+      </document>
+    XML
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: commonmarker
 version: !ruby/object:Gem::Version
-  version: 0.22.0
+  version: 0.23.0
 platform: ruby
 authors:
 - Garen Torikian
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-06-20 00:00:00.000000000 Z
+date: 2021-08-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: awesome_print
@@ -254,6 +254,7 @@ files:
 - test/test_smartpunct.rb
 - test/test_spec.rb
 - test/test_tasklists.rb
+- test/test_xml.rb
 homepage: https://github.com/gjtorikian/commonmarker
 licenses:
 - MIT
@@ -306,6 +307,7 @@ test_files:
 - test/test_helper.rb
 - test/test_options.rb
 - test/benchmark.rb
+- test/test_xml.rb
 - test/test_basics.rb
 - test/test_renderer.rb
 - test/test_gc.rb