commonmarker 0.23.10 → 1.1.4

Sign up to get free protection for your applications and to get access to all the features.
Files changed (97) hide show
  1. checksums.yaml +4 -4
  2. data/Cargo.lock +1182 -0
  3. data/Cargo.toml +7 -0
  4. data/README.md +217 -170
  5. data/ext/commonmarker/Cargo.toml +20 -0
  6. data/ext/commonmarker/extconf.rb +3 -6
  7. data/ext/commonmarker/src/lib.rs +103 -0
  8. data/ext/commonmarker/src/node.rs +1151 -0
  9. data/ext/commonmarker/src/options.rs +175 -0
  10. data/ext/commonmarker/src/plugins/syntax_highlighting.rs +166 -0
  11. data/ext/commonmarker/src/plugins.rs +6 -0
  12. data/ext/commonmarker/src/utils.rs +8 -0
  13. data/lib/commonmarker/config.rb +92 -40
  14. data/lib/commonmarker/constants.rb +7 -0
  15. data/lib/commonmarker/extension.rb +14 -0
  16. data/lib/commonmarker/node/ast.rb +8 -0
  17. data/lib/commonmarker/node/inspect.rb +14 -4
  18. data/lib/commonmarker/node.rb +29 -47
  19. data/lib/commonmarker/renderer.rb +1 -127
  20. data/lib/commonmarker/utils.rb +22 -0
  21. data/lib/commonmarker/version.rb +2 -2
  22. data/lib/commonmarker.rb +27 -25
  23. metadata +38 -186
  24. data/Rakefile +0 -109
  25. data/bin/commonmarker +0 -118
  26. data/commonmarker.gemspec +0 -38
  27. data/ext/commonmarker/arena.c +0 -104
  28. data/ext/commonmarker/autolink.c +0 -508
  29. data/ext/commonmarker/autolink.h +0 -8
  30. data/ext/commonmarker/blocks.c +0 -1622
  31. data/ext/commonmarker/buffer.c +0 -278
  32. data/ext/commonmarker/buffer.h +0 -116
  33. data/ext/commonmarker/case_fold_switch.inc +0 -4327
  34. data/ext/commonmarker/chunk.h +0 -135
  35. data/ext/commonmarker/cmark-gfm-core-extensions.h +0 -54
  36. data/ext/commonmarker/cmark-gfm-extension_api.h +0 -737
  37. data/ext/commonmarker/cmark-gfm-extensions_export.h +0 -42
  38. data/ext/commonmarker/cmark-gfm.h +0 -833
  39. data/ext/commonmarker/cmark-gfm_export.h +0 -42
  40. data/ext/commonmarker/cmark-gfm_version.h +0 -7
  41. data/ext/commonmarker/cmark.c +0 -55
  42. data/ext/commonmarker/cmark_ctype.c +0 -44
  43. data/ext/commonmarker/cmark_ctype.h +0 -33
  44. data/ext/commonmarker/commonmark.c +0 -514
  45. data/ext/commonmarker/commonmarker.c +0 -1308
  46. data/ext/commonmarker/commonmarker.h +0 -16
  47. data/ext/commonmarker/config.h +0 -76
  48. data/ext/commonmarker/core-extensions.c +0 -27
  49. data/ext/commonmarker/entities.inc +0 -2138
  50. data/ext/commonmarker/ext_scanners.c +0 -879
  51. data/ext/commonmarker/ext_scanners.h +0 -24
  52. data/ext/commonmarker/footnotes.c +0 -63
  53. data/ext/commonmarker/footnotes.h +0 -27
  54. data/ext/commonmarker/houdini.h +0 -57
  55. data/ext/commonmarker/houdini_href_e.c +0 -100
  56. data/ext/commonmarker/houdini_html_e.c +0 -66
  57. data/ext/commonmarker/houdini_html_u.c +0 -149
  58. data/ext/commonmarker/html.c +0 -502
  59. data/ext/commonmarker/html.h +0 -27
  60. data/ext/commonmarker/inlines.c +0 -1788
  61. data/ext/commonmarker/inlines.h +0 -29
  62. data/ext/commonmarker/iterator.c +0 -159
  63. data/ext/commonmarker/iterator.h +0 -26
  64. data/ext/commonmarker/latex.c +0 -468
  65. data/ext/commonmarker/linked_list.c +0 -37
  66. data/ext/commonmarker/man.c +0 -274
  67. data/ext/commonmarker/map.c +0 -129
  68. data/ext/commonmarker/map.h +0 -44
  69. data/ext/commonmarker/node.c +0 -1045
  70. data/ext/commonmarker/node.h +0 -167
  71. data/ext/commonmarker/parser.h +0 -59
  72. data/ext/commonmarker/plaintext.c +0 -218
  73. data/ext/commonmarker/plugin.c +0 -36
  74. data/ext/commonmarker/plugin.h +0 -34
  75. data/ext/commonmarker/references.c +0 -43
  76. data/ext/commonmarker/references.h +0 -26
  77. data/ext/commonmarker/registry.c +0 -63
  78. data/ext/commonmarker/registry.h +0 -24
  79. data/ext/commonmarker/render.c +0 -213
  80. data/ext/commonmarker/render.h +0 -62
  81. data/ext/commonmarker/scanners.c +0 -14056
  82. data/ext/commonmarker/scanners.h +0 -70
  83. data/ext/commonmarker/scanners.re +0 -341
  84. data/ext/commonmarker/strikethrough.c +0 -167
  85. data/ext/commonmarker/strikethrough.h +0 -9
  86. data/ext/commonmarker/syntax_extension.c +0 -149
  87. data/ext/commonmarker/syntax_extension.h +0 -34
  88. data/ext/commonmarker/table.c +0 -917
  89. data/ext/commonmarker/table.h +0 -12
  90. data/ext/commonmarker/tagfilter.c +0 -60
  91. data/ext/commonmarker/tagfilter.h +0 -8
  92. data/ext/commonmarker/tasklist.c +0 -156
  93. data/ext/commonmarker/tasklist.h +0 -8
  94. data/ext/commonmarker/utf8.c +0 -317
  95. data/ext/commonmarker/utf8.h +0 -35
  96. data/ext/commonmarker/xml.c +0 -182
  97. data/lib/commonmarker/renderer/html_renderer.rb +0 -256
data/Cargo.toml ADDED
@@ -0,0 +1,7 @@
1
+ # This Cargo.toml is here to let externals tools (IDEs, etc.) know that this is
2
+ # a Rust project. Your extensions depedencies should be added to the Cargo.toml
3
+ # in the ext/ directory.
4
+
5
+ [workspace]
6
+ members = ["ext/commonmarker"]
7
+ resolver = "2"
data/README.md CHANGED
@@ -1,11 +1,10 @@
1
- # CommonMarker
1
+ # Commonmarker
2
2
 
3
- ![Build Status](https://github.com/gjtorikian/commonmarker/workflows/CI/badge.svg) [![Gem Version](https://badge.fury.io/rb/commonmarker.svg)](http://badge.fury.io/rb/commonmarker)
3
+ Ruby wrapper for Rust's [comrak](https://github.com/kivikakk/comrak) crate.
4
4
 
5
- Ruby wrapper for [libcmark-gfm](https://github.com/github/cmark),
6
- GitHub's fork of the reference parser for CommonMark. It passes all of the C tests, and is therefore spec-complete. It also includes extensions to the CommonMark spec as documented in the [GitHub Flavored Markdown spec](http://github.github.com/gfm/), such as support for tables, strikethroughs, and autolinking.
5
+ It passes all of the CommonMark test suite, and is therefore spec-complete. It also includes extensions to the CommonMark spec as documented in the [GitHub Flavored Markdown spec](http://github.github.com/gfm/), such as support for tables, strikethroughs, and autolinking.
7
6
 
8
- For more information on available extensions, see [the documentation below](#extensions).
7
+ For more information on available extensions, see [the documentation below](#extension-options).
9
8
 
10
9
  ## Installation
11
10
 
@@ -25,45 +24,75 @@ Or install it yourself as:
25
24
 
26
25
  ### Converting to HTML
27
26
 
28
- Call `render_html` on a string to convert it to HTML:
27
+ Call `to_html` on a string to convert it to HTML:
29
28
 
30
- ``` ruby
29
+ ```ruby
31
30
  require 'commonmarker'
32
- CommonMarker.render_html('Hi *there*', :DEFAULT)
33
- # <p>Hi <em>there</em></p>\n
31
+ Commonmarker.to_html('"Hi *there*"', options: {
32
+ parse: { smart: true }
33
+ })
34
+ # => <p>“Hi <em>there</em>”</p>\n
34
35
  ```
35
36
 
36
- The second argument is optional--[see below](#options) for more information.
37
+ (The second argument is optional--[see below](#options-and-plugins) for more information.)
37
38
 
38
39
  ### Generating a document
39
40
 
40
- You can also parse a string to receive a `Document` node. You can then print that node to HTML, iterate over the children, and other fun node stuff. For example:
41
+ You can also parse a string to receive a `:document` node. You can then print that node to HTML, iterate over the children, and do other fun node stuff. For example:
41
42
 
42
- ``` ruby
43
+ ```ruby
43
44
  require 'commonmarker'
44
45
 
45
- doc = CommonMarker.render_doc('*Hello* world', :DEFAULT)
46
- puts(doc.to_html) # <p>Hi <em>there</em></p>\n
46
+ doc = Commonmarker.parse("*Hello* world", options: {
47
+ parse: { smart: true }
48
+ })
49
+ puts(doc.to_html) # => <p><em>Hello</em> world</p>\n
47
50
 
48
51
  doc.walk do |node|
49
- puts node.type # [:document, :paragraph, :text, :emph, :text]
52
+ puts node.type # => [:document, :paragraph, :emph, :text, :text]
50
53
  end
51
54
  ```
52
55
 
53
- The second argument is optional--[see below](#options) for more information.
56
+ (The second argument is optional--[see below](#options-and-plugins) for more information.)
57
+
58
+ When it comes to modifying the document, you can perform the following operations:
59
+
60
+ - `insert_before`
61
+ - `insert_after`
62
+ - `prepend_child`
63
+ - `append_child`
64
+ - `delete`
54
65
 
55
- #### Example: walking the AST
66
+ You can also get the source position of a node by calling `source_position`:
67
+
68
+ ```ruby
69
+ doc = Commonmarker.parse("*Hello* world")
70
+ puts doc.first_child.first_child.source_position
71
+ # => {:start_line=>1, :start_column=>1, :end_line=>1, :end_column=>7}
72
+ ```
73
+
74
+ You can also modify the following attributes:
75
+
76
+ - `url`
77
+ - `title`
78
+ - `header_level`
79
+ - `list_type`
80
+ - `list_start`
81
+ - `list_tight`
82
+ - `fence_info`
83
+
84
+ #### Example: Walking the AST
56
85
 
57
86
  You can use `walk` or `each` to iterate over nodes:
58
87
 
59
88
  - `walk` will iterate on a node and recursively iterate on a node's children.
60
89
  - `each` will iterate on a node and its children, but no further.
61
90
 
62
- ``` ruby
91
+ ```ruby
63
92
  require 'commonmarker'
64
93
 
65
- # parse the files specified on the command line
66
- doc = CommonMarker.render_doc("# The site\n\n [GitHub](https://www.github.com)")
94
+ # parse some string
95
+ doc = Commonmarker.parse("# The site\n\n [GitHub](https://www.github.com)")
67
96
 
68
97
  # Walk tree and print out URLs for links
69
98
  doc.walk do |node|
@@ -71,17 +100,7 @@ doc.walk do |node|
71
100
  printf("URL = %s\n", node.url)
72
101
  end
73
102
  end
74
-
75
- # Capitalize all regular text in headers
76
- doc.walk do |node|
77
- if node.type == :header
78
- node.each do |subnode|
79
- if subnode.type == :text
80
- subnode.string_content = subnode.string_content.upcase
81
- end
82
- end
83
- end
84
- end
103
+ # => URL = https://www.github.com
85
104
 
86
105
  # Transform links to regular text
87
106
  doc.walk do |node|
@@ -90,169 +109,186 @@ doc.walk do |node|
90
109
  node.delete
91
110
  end
92
111
  end
112
+ # => <h1><a href=\"#the-site\"></a>The site</h1>\n<p>GitHub</p>\n
93
113
  ```
94
114
 
95
- ### Creating a custom renderer
115
+ #### Example: Converting a document back into raw CommonMark
96
116
 
97
- You can also derive a class from CommonMarker's `HtmlRenderer` class. This produces slower output, but is far more customizable. For example:
117
+ You can use `to_commonmark` on a node to render it as raw text:
98
118
 
99
- ``` ruby
100
- class MyHtmlRenderer < CommonMarker::HtmlRenderer
101
- def initialize
102
- super
103
- @headerid = 1
104
- end
119
+ ```ruby
120
+ require 'commonmarker'
121
+
122
+ # parse some string
123
+ doc = Commonmarker.parse("# The site\n\n [GitHub](https://www.github.com)")
105
124
 
106
- def header(node)
107
- block do
108
- out("<h", node.header_level, " id=\"", @headerid, "\">",
109
- :children, "</h", node.header_level, ">")
110
- @headerid += 1
111
- end
125
+ # Transform links to regular text
126
+ doc.walk do |node|
127
+ if node.type == :link
128
+ node.insert_before(node.first_child)
129
+ node.delete
112
130
  end
113
131
  end
114
132
 
115
- myrenderer = MyHtmlRenderer.new
116
- puts myrenderer.render(doc)
117
-
118
- # Print any warnings to STDERR
119
- renderer.warnings.each do |w|
120
- STDERR.write("#{w}\n")
121
- end
133
+ doc.to_commonmark
134
+ # => # The site\n\nGitHub\n
122
135
  ```
123
136
 
124
- ## Options
137
+ ## Options and plugins
125
138
 
126
- CommonMarker accepts the same options that CMark does, as symbols. Note that there is a distinction in CMark for "parse" options and "render" options, which are represented in the tables below.
139
+ ### Options
127
140
 
128
- ### Parse options
141
+ Commonmarker accepts the same parse, render, and extensions options that comrak does, as a hash dictionary with symbol keys:
129
142
 
130
- | Name | Description
131
- | ----------------------------- | -----------
132
- | `:DEFAULT` | The default parsing system.
133
- | `:SOURCEPOS` | Include source position in nodes
134
- | `:UNSAFE` | Allow raw/custom HTML and unsafe links.
135
- | `:VALIDATE_UTF8` | Replace illegal sequences with the replacement character `U+FFFD`.
136
- | `:SMART` | Use smart punctuation (curly quotes, etc.).
137
- | `:LIBERAL_HTML_TAG` | Support liberal parsing of inline HTML tags.
138
- | `:FOOTNOTES` | Parse footnotes.
139
- | `:STRIKETHROUGH_DOUBLE_TILDE` | Parse strikethroughs by double tildes (compatibility with [redcarpet](https://github.com/vmg/redcarpet))
143
+ ```ruby
144
+ Commonmarker.to_html('"Hi *there*"', options:{
145
+ parse: { smart: true },
146
+ render: { hardbreaks: false}
147
+ })
148
+ ```
140
149
 
141
- ### Render options
150
+ Note that there is a distinction in comrak for "parse" options and "render" options, which are represented in the tables below.
142
151
 
143
- | Name | Description |
144
- | ------------------ | ----------- |
145
- | `:DEFAULT` | The default rendering system. |
146
- | `:SOURCEPOS` | Include source position in rendered HTML. |
147
- | `:HARDBREAKS` | Treat `\n` as hardbreaks (by adding `<br/>`). |
148
- | `:UNSAFE` | Allow raw/custom HTML and unsafe links. |
149
- | `:NOBREAKS` | Translate `\n` in the source to a single whitespace. |
150
- | `:VALIDATE_UTF8` | Replace illegal sequences with the replacement character `U+FFFD`. |
151
- | `:SMART` | Use smart punctuation (curly quotes, etc.). |
152
- | `:GITHUB_PRE_LANG` | Use GitHub-style `<pre lang>` for fenced code blocks. |
153
- | `:LIBERAL_HTML_TAG` | Support liberal parsing of inline HTML tags. |
154
- | `:FOOTNOTES` | Render footnotes. |
155
- | `:STRIKETHROUGH_DOUBLE_TILDE` | Parse strikethroughs by double tildes (compatibility with [redcarpet](https://github.com/vmg/redcarpet)) |
156
- | `:TABLE_PREFER_STYLE_ATTRIBUTES` | Use `style` insted of `align` for table cells. |
157
- | `:FULL_INFO_STRING` | Include full info strings of code blocks in separate attribute. |
158
-
159
- ### Passing options
160
-
161
- To apply a single option, pass it in as a symbol argument:
162
-
163
- ``` ruby
164
- CommonMarker.render_doc("\"Hello,\" said the spider.", :SMART)
165
- # <p>“Hello,” said the spider.</p>\n
166
- ```
152
+ ### Parse options
167
153
 
168
- To have multiple options applied, pass in an array of symbols:
154
+ | Name | Description | Default |
155
+ | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ------- |
156
+ | `smart` | Punctuation (quotes, full-stops and hyphens) are converted into 'smart' punctuation. | `false` |
157
+ | `default_info_string` | The default info string for fenced code blocks. | `""` |
158
+ | `relaxed_autolinks` | Enable relaxing of the autolink extension parsing, allowing links to be recognized when in brackets, as well as permitting any url scheme. | `false` |
169
159
 
170
- ``` ruby
171
- CommonMarker.render_html("\"'Shelob' is my name.\"", [:HARDBREAKS, :SOURCEPOS])
172
- ```
160
+ ### Render options
173
161
 
174
- For more information on these options, see [the CMark documentation](https://git.io/v7nh1).
162
+ | Name | Description | Default |
163
+ | -------------------- | ------------------------------------------------------------------------------------------------------ | ------- |
164
+ | `hardbreaks` | [Soft line breaks](http://spec.commonmark.org/0.27/#soft-line-breaks) translate into hard line breaks. | `true` |
165
+ | `github_pre_lang` | GitHub-style `<pre lang="xyz">` is used for fenced code blocks with info tags. | `true` |
166
+ | `width` | The wrap column when outputting CommonMark. | `80` |
167
+ | `unsafe` | Allow rendering of raw HTML and potentially dangerous links. | `false` |
168
+ | `escape` | Escape raw HTML instead of clobbering it. | `false` |
169
+ | `sourcepos` | Include source position attribute in HTML and XML output. | `false` |
170
+ | `escaped_char_spans` | Wrap escaped characters in span tags | `true` |
175
171
 
176
- ## Extensions
172
+ As well, there are several extensions which you can toggle in the same manner:
177
173
 
178
- Both `render_html` and `render_doc` take an optional third argument defining the extensions you want enabled as your CommonMark document is being processed. The documentation for these extensions are [defined in this spec](https://github.github.com/gfm/), and the rationale is provided [in this blog post](https://githubengineering.com/a-formal-spec-for-github-markdown/).
174
+ ```ruby
175
+ Commonmarker.to_html('"Hi *there*"', options: {
176
+ extension: { footnotes: true, description_lists: true },
177
+ render: { hardbreaks: false}
178
+ })
179
+ ```
179
180
 
180
- The available extensions are:
181
+ ### Extension options
182
+
183
+ | Name | Description | Default |
184
+ | --------------------------- | ------------------------------------------------------------------------------------------------------------------- | ------- |
185
+ | `strikethrough` | Enables the [strikethrough extension](https://github.github.com/gfm/#strikethrough-extension-) from the GFM spec. | `true` |
186
+ | `tagfilter` | Enables the [tagfilter extension](https://github.github.com/gfm/#disallowed-raw-html-extension-) from the GFM spec. | `true` |
187
+ | `table` | Enables the [table extension](https://github.github.com/gfm/#tables-extension-) from the GFM spec. | `true` |
188
+ | `autolink` | Enables the [autolink extension](https://github.github.com/gfm/#autolinks-extension-) from the GFM spec. | `true` |
189
+ | `tasklist` | Enables the [task list extension](https://github.github.com/gfm/#task-list-items-extension-) from the GFM spec. | `true` |
190
+ | `superscript` | Enables the superscript Comrak extension. | `false` |
191
+ | `header_ids` | Enables the header IDs Comrak extension. from the GFM spec. | `""` |
192
+ | `footnotes` | Enables the footnotes extension per `cmark-gfm`. | `false` |
193
+ | `description_lists` | Enables the description lists extension. | `false` |
194
+ | `front_matter_delimiter` | Enables the front matter extension. | `""` |
195
+ | `shortcodes` | Enables the shortcodes extension. | `true` |
196
+ | `multiline_block_quotes` | Enables the multiline block quotes extension. | `false` |
197
+ | `math_dollars`, `math_code` | Enables the math extension. | `false` |
198
+
199
+ For more information on these options, see [the comrak documentation](https://github.com/kivikakk/comrak#usage).
200
+
201
+ ### Plugins
202
+
203
+ In addition to the possibilities provided by generic CommonMark rendering, Commonmarker also supports plugins as a means of
204
+ providing further niceties.
205
+
206
+ #### Syntax Highlighter Plugin
207
+
208
+ The library comes with [a set of pre-existing themes](https://docs.rs/syntect/5.0.0/syntect/highlighting/struct.ThemeSet.html#implementations) for highlighting code:
209
+
210
+ - `"base16-ocean.dark"`
211
+ - `"base16-eighties.dark"`
212
+ - `"base16-mocha.dark"`
213
+ - `"base16-ocean.light"`
214
+ - `"InspiredGitHub"`
215
+ - `"Solarized (dark)"`
216
+ - `"Solarized (light)"`
217
+
218
+ ````ruby
219
+ code = <<~CODE
220
+ ```ruby
221
+ def hello
222
+ puts "hello"
223
+ end
224
+ ```
225
+ CODE
181
226
 
182
- * `:table` - This provides support for tables.
183
- * `:tasklist` - This provides support for task list items.
184
- * `:strikethrough` - This provides support for strikethroughs.
185
- * `:autolink` - This provides support for automatically converting URLs to anchor tags.
186
- * `:tagfilter` - This escapes [several "unsafe" HTML tags](https://github.github.com/gfm/#disallowed-raw-html-extension-), causing them to not have any effect.
227
+ # pass in a theme name from a pre-existing set
228
+ puts Commonmarker.to_html(code, plugins: { syntax_highlighter: { theme: "InspiredGitHub" } })
187
229
 
188
- ## Output formats
230
+ # <pre style="background-color:#ffffff;" lang="ruby"><code>
231
+ # <span style="font-weight:bold;color:#a71d5d;">def </span><span style="font-weight:bold;color:#795da3;">hello
232
+ # </span><span style="color:#62a35c;">puts </span><span style="color:#183691;">&quot;hello&quot;
233
+ # </span><span style="font-weight:bold;color:#a71d5d;">end
234
+ # </span>
235
+ # </code></pre>
236
+ ````
189
237
 
190
- Like CMark, CommonMarker can generate output in several formats: HTML, XML, plaintext, and commonmark are currently supported.
238
+ By default, the plugin uses the `"base16-ocean.dark"` theme to syntax highlight code.
191
239
 
192
- ### HTML
240
+ To disable this plugin, set the value to `nil`:
193
241
 
194
- The default output format, HTML, will be generated when calling `to_html` or using `--to=html` on the command line.
242
+ ````ruby
243
+ code = <<~CODE
244
+ ```ruby
245
+ def hello
246
+ puts "hello"
247
+ end
248
+ ```
249
+ CODE
195
250
 
196
- ```ruby
197
- doc = CommonMarker.render_doc('*Hello* world!', :DEFAULT)
198
- puts(doc.to_html)
251
+ Commonmarker.to_html(code, plugins: { syntax_highlighter: nil })
199
252
 
200
- <p><em>Hello</em> world!</p>
201
- ```
253
+ # <pre lang="ruby"><code>def hello
254
+ # puts &quot;hello&quot;
255
+ # end
256
+ # </code></pre>
257
+ ````
202
258
 
203
- ### XML
259
+ To output CSS classes instead of `style` attributes, set the `theme` key to `""`:
204
260
 
205
- XML will be generated when calling `to_xml` or using `--to=xml` on the command line.
261
+ ````ruby
262
+ code = <<~CODE
263
+ ```ruby
264
+ def hello
265
+ puts "hello"
266
+ end
267
+ CODE
206
268
 
207
- ```ruby
208
- doc = CommonMarker.render_doc('*Hello* world!', :DEFAULT)
209
- puts(doc.to_xml)
210
-
211
- <?xml version="1.0" encoding="UTF-8"?>
212
- <!DOCTYPE document SYSTEM "CommonMark.dtd">
213
- <document xmlns="http://commonmark.org/xml/1.0">
214
- <paragraph>
215
- <emph>
216
- <text xml:space="preserve">Hello</text>
217
- </emph>
218
- <text xml:space="preserve"> world!</text>
219
- </paragraph>
220
- </document>
221
- ```
269
+ Commonmarker.to_html(code, plugins: { syntax_highlighter: { theme: "" } })
222
270
 
223
- ### Plaintext
271
+ # <pre class="syntax-highlighting"><code><span class="source ruby"><span class="meta function ruby"><span class="keyword control def ruby">def</span></span><span class="meta function ruby"> # <span class="entity name function ruby">hello</span></span>
272
+ # <span class="support function builtin ruby">puts</span> <span class="string quoted double ruby"><span class="punctuation definition string begin ruby">&quot;</span>hello<span class="punctuation definition string end ruby">&quot;</span></span>
273
+ # <span class="keyword control ruby">end</span>\n</span></code></pre>
274
+ ````
224
275
 
225
- Plaintext will be generated when calling `to_plaintext` or using `--to=plaintext` on the command line.
276
+ To use a custom theme, you can provide a `path` to a directory containing `.tmtheme` files to load:
226
277
 
227
278
  ```ruby
228
- doc = CommonMarker.render_doc('*Hello* world!', :DEFAULT)
229
- puts(doc.to_plaintext)
230
-
231
- Hello world!
279
+ Commonmarker.to_html(code, plugins: { syntax_highlighter: { theme: "Monokai", path: "./themes" } })
232
280
  ```
233
281
 
234
- ### Commonmark
235
-
236
- Commonmark will be generated when calling `to_commonmark` or using `--to=commonmark` on the command line.
237
-
238
- ``` ruby
239
- text = <<-TEXT
240
- 1. I am a numeric list.
241
- 2. I continue the list.
242
- * Suddenly, an unordered list!
243
- * What fun!
244
- TEXT
282
+ ## Output formats
245
283
 
246
- doc = CommonMarker.render_doc(text, :DEFAULT)
247
- puts(doc.to_commonmark)
284
+ Commonmarker can currently only generate output in one format: HTML.
248
285
 
249
- 1. I am a numeric list.
250
- 2. I continue the list.
286
+ ### HTML
251
287
 
252
- <!-- end list -->
288
+ ```ruby
289
+ puts Commonmarker.to_html('*Hello* world!')
253
290
 
254
- - Suddenly, an unordered list\!
255
- - What fun\!
291
+ # <p><em>Hello</em> world!</p>
256
292
  ```
257
293
 
258
294
  ## Developing locally
@@ -264,25 +300,36 @@ script/bootstrap
264
300
  bundle exec rake compile
265
301
  ```
266
302
 
267
- If there were no errors, you're done! Otherwise, make sure to follow the CMark dependency instructions.
303
+ If there were no errors, you're done! Otherwise, make sure to follow the comrak dependency instructions.
268
304
 
269
305
  ## Benchmarks
270
306
 
271
- Some rough benchmarks:
272
-
273
307
  ```
274
- $ bundle exec rake benchmark
275
-
276
- input size = 11063727 bytes
277
-
278
- redcarpet
279
- 0.070000 0.020000 0.090000 ( 0.079641)
280
- github-markdown
281
- 0.070000 0.010000 0.080000 ( 0.083535)
282
- commonmarker with to_html
283
- 0.100000 0.010000 0.110000 ( 0.111947)
284
- commonmarker with ruby HtmlRenderer
285
- 1.830000 0.030000 1.860000 ( 1.866203)
286
- kramdown
287
- 4.610000 0.070000 4.680000 ( 4.678398)
308
+ bundle exec rake benchmark
309
+ input size = 11064832 bytes
310
+
311
+ ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
312
+ Warming up --------------------------------------
313
+ Markly.render_html 1.000 i/100ms
314
+ Markly::Node#to_html 1.000 i/100ms
315
+ Commonmarker.to_html 1.000 i/100ms
316
+ Commonmarker::Node.to_html
317
+ 1.000 i/100ms
318
+ Kramdown::Document#to_html
319
+ 1.000 i/100ms
320
+ Calculating -------------------------------------
321
+ Markly.render_html 15.606 (±25.6%) i/s - 71.000 in 5.047132s
322
+ Markly::Node#to_html 15.692 (±25.5%) i/s - 72.000 in 5.095810s
323
+ Commonmarker.to_html 4.482 (± 0.0%) i/s - 23.000 in 5.137680s
324
+ Commonmarker::Node.to_html
325
+ 5.092 (±19.6%) i/s - 25.000 in 5.072220s
326
+ Kramdown::Document#to_html
327
+ 0.379 (± 0.0%) i/s - 2.000 in 5.277770s
328
+
329
+ Comparison:
330
+ Markly::Node#to_html: 15.7 i/s
331
+ Markly.render_html: 15.6 i/s - same-ish: difference falls within error
332
+ Commonmarker::Node.to_html: 5.1 i/s - 3.08x slower
333
+ Commonmarker.to_html: 4.5 i/s - 3.50x slower
334
+ Kramdown::Document#to_html: 0.4 i/s - 41.40x slower
288
335
  ```
@@ -0,0 +1,20 @@
1
+ [package]
2
+ name = "commonmarker"
3
+ version = "1.0.0"
4
+ edition = "2021"
5
+ rust-version = "1.75.0"
6
+ publish = false
7
+
8
+ [dependencies]
9
+ magnus = { version = "0.6", features = ["rb-sys"] }
10
+ rb-sys = { version = "*", default-features = false, features = [
11
+ "stable-api-compiled-fallback",
12
+ ] }
13
+ comrak = { version = "0.24", features = ["shortcodes"] }
14
+ syntect = { version = "5.2", features = ["plist-load"] }
15
+ typed-arena = "2.0"
16
+ rctree = "0.6"
17
+
18
+ [lib]
19
+ name = "commonmarker"
20
+ crate-type = ["cdylib"]
@@ -1,7 +1,4 @@
1
- # frozen_string_literal: true
1
+ require "mkmf"
2
+ require "rb_sys/mkmf"
2
3
 
3
- require 'mkmf'
4
-
5
- $CFLAGS << ' -std=c99'
6
-
7
- create_makefile('commonmarker/commonmarker')
4
+ create_rust_makefile("commonmarker/commonmarker")
@@ -0,0 +1,103 @@
1
+ extern crate core;
2
+
3
+ use comrak::{markdown_to_html_with_plugins, parse_document, ComrakOptions};
4
+ use magnus::{define_module, function, r_hash::ForEach, scan_args, Error, RHash, Symbol, Value};
5
+ use node::CommonmarkerNode;
6
+ use plugins::syntax_highlighting::construct_syntax_highlighter_from_plugin;
7
+
8
+ mod options;
9
+ use options::iterate_options_hash;
10
+
11
+ mod plugins;
12
+
13
+ use typed_arena::Arena;
14
+
15
+ mod node;
16
+ mod utils;
17
+
18
+ pub const EMPTY_STR: &str = "";
19
+
20
+ fn commonmark_parse(args: &[Value]) -> Result<CommonmarkerNode, magnus::Error> {
21
+ let args = scan_args::scan_args::<_, (), (), (), _, ()>(args)?;
22
+ let (rb_commonmark,): (String,) = args.required;
23
+
24
+ let kwargs =
25
+ scan_args::get_kwargs::<_, (), (Option<RHash>,), ()>(args.keywords, &[], &["options"])?;
26
+ let (rb_options,) = kwargs.optional;
27
+
28
+ let mut comrak_options = ComrakOptions::default();
29
+
30
+ if let Some(rb_options) = rb_options {
31
+ rb_options.foreach(|key: Symbol, value: RHash| {
32
+ iterate_options_hash(&mut comrak_options, key, value)?;
33
+ Ok(ForEach::Continue)
34
+ })?;
35
+ }
36
+
37
+ let arena = Arena::new();
38
+ let root = parse_document(&arena, &rb_commonmark, &comrak_options);
39
+
40
+ CommonmarkerNode::new_from_comrak_node(root)
41
+ }
42
+
43
+ fn commonmark_to_html(args: &[Value]) -> Result<String, magnus::Error> {
44
+ let args = scan_args::scan_args::<_, (), (), (), _, ()>(args)?;
45
+ let (rb_commonmark,): (String,) = args.required;
46
+
47
+ let kwargs = scan_args::get_kwargs::<_, (), (Option<RHash>, Option<RHash>), ()>(
48
+ args.keywords,
49
+ &[],
50
+ &["options", "plugins"],
51
+ )?;
52
+ let (rb_options, rb_plugins) = kwargs.optional;
53
+
54
+ let comrak_options = match format_options(rb_options) {
55
+ Ok(options) => options,
56
+ Err(err) => return Err(err),
57
+ };
58
+
59
+ let mut comrak_plugins = comrak::Plugins::default();
60
+
61
+ let syntect_adapter = match construct_syntax_highlighter_from_plugin(rb_plugins) {
62
+ Ok(Some(adapter)) => Some(adapter),
63
+ Ok(None) => None,
64
+ Err(err) => return Err(err),
65
+ };
66
+
67
+ match syntect_adapter {
68
+ Some(ref adapter) => comrak_plugins.render.codefence_syntax_highlighter = Some(adapter),
69
+ None => comrak_plugins.render.codefence_syntax_highlighter = None,
70
+ }
71
+
72
+ Ok(markdown_to_html_with_plugins(
73
+ &rb_commonmark,
74
+ &comrak_options,
75
+ &comrak_plugins,
76
+ ))
77
+ }
78
+
79
+ fn format_options(rb_options: Option<RHash>) -> Result<comrak::Options, magnus::Error> {
80
+ let mut comrak_options = ComrakOptions::default();
81
+
82
+ if let Some(rb_options) = rb_options {
83
+ rb_options.foreach(|key: Symbol, value: RHash| {
84
+ iterate_options_hash(&mut comrak_options, key, value)?;
85
+ Ok(ForEach::Continue)
86
+ })?;
87
+ }
88
+
89
+ Ok(comrak_options)
90
+ }
91
+
92
+ #[magnus::init]
93
+ fn init() -> Result<(), Error> {
94
+ let m_commonmarker = define_module("Commonmarker")?;
95
+
96
+ m_commonmarker.define_module_function("commonmark_parse", function!(commonmark_parse, -1))?;
97
+ m_commonmarker
98
+ .define_module_function("commonmark_to_html", function!(commonmark_to_html, -1))?;
99
+
100
+ node::init(m_commonmarker).expect("cannot define Commonmarker::Node class");
101
+
102
+ Ok(())
103
+ }