commonmarker 1.0.4-x86_64-linux → 1.1.0-x86_64-linux
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +150 -45
- data/lib/commonmarker/3.1/commonmarker.so +0 -0
- data/lib/commonmarker/3.2/commonmarker.so +0 -0
- data/lib/commonmarker/3.3/commonmarker.so +0 -0
- data/lib/commonmarker/config.rb +5 -0
- data/lib/commonmarker/node/ast.rb +8 -0
- data/lib/commonmarker/node/inspect.rb +57 -0
- data/lib/commonmarker/node.rb +65 -0
- data/lib/commonmarker/version.rb +1 -1
- data/lib/commonmarker.rb +17 -0
- metadata +5 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b1fbef976fa499ad11eda24defd31c042e7b00fdb7b74628e60f69a040350095
|
4
|
+
data.tar.gz: 82127aa8f6d20bddce76cd9a08bfa310d14bca0e1ad50e582ef0888c69144279
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b36b64733bbf6c0c7dd731a00a4b8d01dcc1873a1dd64dd80dfd519a40044bd7ccd098a6dad6bf384dc06fe064e74f3159cfca137ebebef8c8859aedfd2f583f
|
7
|
+
data.tar.gz: e56a57ea63c04fb0f6104aea0f423320d4f5e9555b3bb7daf4256c80298542b1b596ba5f6f017a2f7a81d1fa22544a833a0fb3e266630f74d023f8c521bc2c67
|
data/README.md
CHANGED
@@ -1,8 +1,5 @@
|
|
1
1
|
# Commonmarker
|
2
2
|
|
3
|
-
> **Note**
|
4
|
-
> This README refers to the behavior in the new 1.0.0.pre gem.
|
5
|
-
|
6
3
|
Ruby wrapper for Rust's [comrak](https://github.com/kivikakk/comrak) crate.
|
7
4
|
|
8
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.
|
@@ -34,10 +31,108 @@ require 'commonmarker'
|
|
34
31
|
Commonmarker.to_html('"Hi *there*"', options: {
|
35
32
|
parse: { smart: true }
|
36
33
|
})
|
37
|
-
# <p>“Hi <em>there</em>”</p>\n
|
34
|
+
# => <p>“Hi <em>there</em>”</p>\n
|
35
|
+
```
|
36
|
+
|
37
|
+
(The second argument is optional--[see below](#options-and-plugins) for more information.)
|
38
|
+
|
39
|
+
### Generating a document
|
40
|
+
|
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:
|
42
|
+
|
43
|
+
```ruby
|
44
|
+
require 'commonmarker'
|
45
|
+
|
46
|
+
doc = Commonmarker.parse("*Hello* world", options: {
|
47
|
+
parse: { smart: true }
|
48
|
+
})
|
49
|
+
puts(doc.to_html) # => <p><em>Hello</em> world</p>\n
|
50
|
+
|
51
|
+
doc.walk do |node|
|
52
|
+
puts node.type # => [:document, :paragraph, :emph, :text, :text]
|
53
|
+
end
|
38
54
|
```
|
39
55
|
|
40
|
-
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`
|
65
|
+
|
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
|
85
|
+
|
86
|
+
You can use `walk` or `each` to iterate over nodes:
|
87
|
+
|
88
|
+
- `walk` will iterate on a node and recursively iterate on a node's children.
|
89
|
+
- `each` will iterate on a node and its children, but no further.
|
90
|
+
|
91
|
+
```ruby
|
92
|
+
require 'commonmarker'
|
93
|
+
|
94
|
+
# parse some string
|
95
|
+
doc = Commonmarker.parse("# The site\n\n [GitHub](https://www.github.com)")
|
96
|
+
|
97
|
+
# Walk tree and print out URLs for links
|
98
|
+
doc.walk do |node|
|
99
|
+
if node.type == :link
|
100
|
+
printf("URL = %s\n", node.url)
|
101
|
+
end
|
102
|
+
end
|
103
|
+
# => URL = https://www.github.com
|
104
|
+
|
105
|
+
# Transform links to regular text
|
106
|
+
doc.walk do |node|
|
107
|
+
if node.type == :link
|
108
|
+
node.insert_before(node.first_child)
|
109
|
+
node.delete
|
110
|
+
end
|
111
|
+
end
|
112
|
+
# => <h1><a href=\"#the-site\"></a>The site</h1>\n<p>GitHub</p>\n
|
113
|
+
```
|
114
|
+
|
115
|
+
#### Example: Converting a document back into raw CommonMark
|
116
|
+
|
117
|
+
You can use `to_commonmark` on a node to render it as raw text:
|
118
|
+
|
119
|
+
```ruby
|
120
|
+
require 'commonmarker'
|
121
|
+
|
122
|
+
# parse some string
|
123
|
+
doc = Commonmarker.parse("# The site\n\n [GitHub](https://www.github.com)")
|
124
|
+
|
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
|
130
|
+
end
|
131
|
+
end
|
132
|
+
|
133
|
+
doc.to_commonmark
|
134
|
+
# => # The site\n\nGitHub\n
|
135
|
+
```
|
41
136
|
|
42
137
|
## Options and plugins
|
43
138
|
|
@@ -56,21 +151,23 @@ Note that there is a distinction in comrak for "parse" options and "render" opti
|
|
56
151
|
|
57
152
|
### Parse options
|
58
153
|
|
59
|
-
| Name | Description
|
60
|
-
| --------------------- |
|
61
|
-
| `smart` | Punctuation (quotes, full-stops and hyphens) are converted into 'smart' punctuation.
|
62
|
-
| `default_info_string` | The default info string for fenced code blocks.
|
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` |
|
63
159
|
|
64
160
|
### Render options
|
65
161
|
|
66
|
-
| Name
|
67
|
-
|
|
68
|
-
| `hardbreaks`
|
69
|
-
| `github_pre_lang`
|
70
|
-
| `width`
|
71
|
-
| `unsafe`
|
72
|
-
| `escape`
|
73
|
-
| `sourcepos`
|
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` |
|
74
171
|
|
75
172
|
As well, there are several extensions which you can toggle in the same manner:
|
76
173
|
|
@@ -83,19 +180,21 @@ Commonmarker.to_html('"Hi *there*"', options: {
|
|
83
180
|
|
84
181
|
### Extension options
|
85
182
|
|
86
|
-
| Name
|
87
|
-
|
|
88
|
-
| `strikethrough`
|
89
|
-
| `tagfilter`
|
90
|
-
| `table`
|
91
|
-
| `autolink`
|
92
|
-
| `tasklist`
|
93
|
-
| `superscript`
|
94
|
-
| `header_ids`
|
95
|
-
| `footnotes`
|
96
|
-
| `description_lists`
|
97
|
-
| `front_matter_delimiter`
|
98
|
-
| `shortcodes`
|
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` |
|
99
198
|
|
100
199
|
For more information on these options, see [the comrak documentation](https://github.com/kivikakk/comrak#usage).
|
101
200
|
|
@@ -205,26 +304,32 @@ If there were no errors, you're done! Otherwise, make sure to follow the comrak
|
|
205
304
|
|
206
305
|
## Benchmarks
|
207
306
|
|
208
|
-
Some rough benchmarks:
|
209
|
-
|
210
307
|
```
|
211
|
-
|
212
|
-
|
308
|
+
❯ bundle exec rake benchmark
|
213
309
|
input size = 11064832 bytes
|
214
310
|
|
311
|
+
ruby 3.3.0 (2023-12-25 revision 5124f9ac75) [arm64-darwin23]
|
215
312
|
Warming up --------------------------------------
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
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
|
220
320
|
Calculating -------------------------------------
|
221
|
-
|
222
|
-
|
223
|
-
|
224
|
-
|
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
|
225
328
|
|
226
329
|
Comparison:
|
227
|
-
|
228
|
-
|
229
|
-
|
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
|
230
335
|
```
|
Binary file
|
Binary file
|
Binary file
|
data/lib/commonmarker/config.rb
CHANGED
@@ -8,6 +8,7 @@ module Commonmarker
|
|
8
8
|
parse: {
|
9
9
|
smart: false,
|
10
10
|
default_info_string: "",
|
11
|
+
relaxed_autolinks: false,
|
11
12
|
}.freeze,
|
12
13
|
render: {
|
13
14
|
hardbreaks: true,
|
@@ -16,6 +17,7 @@ module Commonmarker
|
|
16
17
|
unsafe: false,
|
17
18
|
escape: false,
|
18
19
|
sourcepos: false,
|
20
|
+
escaped_char_spans: true,
|
19
21
|
}.freeze,
|
20
22
|
extension: {
|
21
23
|
strikethrough: true,
|
@@ -29,6 +31,9 @@ module Commonmarker
|
|
29
31
|
description_lists: false,
|
30
32
|
front_matter_delimiter: "",
|
31
33
|
shortcodes: true,
|
34
|
+
multiline_block_quotes: false,
|
35
|
+
math_dollars: false,
|
36
|
+
math_code: false,
|
32
37
|
},
|
33
38
|
format: [:html].freeze,
|
34
39
|
}.freeze
|
@@ -0,0 +1,57 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "pp"
|
4
|
+
|
5
|
+
module Commonmarker
|
6
|
+
class Node
|
7
|
+
module Inspect
|
8
|
+
PP_INDENT_SIZE = 2
|
9
|
+
|
10
|
+
def inspect
|
11
|
+
PP.pp(self, +"", Float::INFINITY)
|
12
|
+
end
|
13
|
+
|
14
|
+
# @param printer [PrettyPrint] pp
|
15
|
+
def pretty_print(printer)
|
16
|
+
printer.group(PP_INDENT_SIZE, "#<#{self.class}(#{type}):", ">") do
|
17
|
+
printer.breakable
|
18
|
+
|
19
|
+
attrs = [
|
20
|
+
:source_position,
|
21
|
+
:string_content,
|
22
|
+
:url,
|
23
|
+
:title,
|
24
|
+
:header_level,
|
25
|
+
:list_type,
|
26
|
+
:list_start,
|
27
|
+
:list_tight,
|
28
|
+
:fence_info,
|
29
|
+
].filter_map do |name|
|
30
|
+
[name, __send__(name)]
|
31
|
+
rescue StandardError
|
32
|
+
nil
|
33
|
+
end.compact
|
34
|
+
|
35
|
+
printer.seplist(attrs) do |name, value|
|
36
|
+
printer.text("#{name}=")
|
37
|
+
printer.pp(value)
|
38
|
+
end
|
39
|
+
|
40
|
+
if first_child
|
41
|
+
printer.breakable
|
42
|
+
printer.group(PP_INDENT_SIZE) do
|
43
|
+
children = []
|
44
|
+
node = first_child
|
45
|
+
while node
|
46
|
+
children << node
|
47
|
+
node = node.next_sibling
|
48
|
+
end
|
49
|
+
printer.text("children=")
|
50
|
+
printer.pp(children)
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "commonmarker/node/ast"
|
4
|
+
require "commonmarker/node/inspect"
|
5
|
+
|
6
|
+
module Commonmarker
|
7
|
+
class Node
|
8
|
+
include Enumerable
|
9
|
+
include Inspect
|
10
|
+
|
11
|
+
# Public: An iterator that "walks the tree," descending into children recursively.
|
12
|
+
#
|
13
|
+
# blk - A {Proc} representing the action to take for each child
|
14
|
+
def walk(&block)
|
15
|
+
return enum_for(:walk) unless block
|
16
|
+
|
17
|
+
yield self
|
18
|
+
each do |child|
|
19
|
+
child.walk(&block)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
# Public: Iterate over the children (if any) of the current pointer.
|
24
|
+
def each
|
25
|
+
return enum_for(:each) unless block_given?
|
26
|
+
|
27
|
+
child = first_child
|
28
|
+
while child
|
29
|
+
next_child = child.next_sibling
|
30
|
+
yield child
|
31
|
+
child = next_child
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
# Public: Converts a node to an HTML string.
|
36
|
+
#
|
37
|
+
# options - A {Hash} of render, parse, and extension options to transform the text.
|
38
|
+
# plugins - A {Hash} of additional plugins.
|
39
|
+
#
|
40
|
+
# Returns a {String} of HTML.
|
41
|
+
def to_html(options: Commonmarker::Config::OPTIONS, plugins: Commonmarker::Config::PLUGINS)
|
42
|
+
raise TypeError, "options must be a Hash; got a #{options.class}!" unless options.is_a?(Hash)
|
43
|
+
|
44
|
+
opts = Config.process_options(options)
|
45
|
+
plugins = Config.process_plugins(plugins)
|
46
|
+
|
47
|
+
node_to_html(options: opts, plugins: plugins).force_encoding("utf-8")
|
48
|
+
end
|
49
|
+
|
50
|
+
# Public: Convert the node to a CommonMark string.
|
51
|
+
#
|
52
|
+
# options - A {Symbol} or {Array of Symbol}s indicating the render options
|
53
|
+
# plugins - A {Hash} of additional plugins.
|
54
|
+
#
|
55
|
+
# Returns a {String}.
|
56
|
+
def to_commonmark(options: Commonmarker::Config::OPTIONS, plugins: Commonmarker::Config::PLUGINS)
|
57
|
+
raise TypeError, "options must be a Hash; got a #{options.class}!" unless options.is_a?(Hash)
|
58
|
+
|
59
|
+
opts = Config.process_options(options)
|
60
|
+
plugins = Config.process_plugins(plugins)
|
61
|
+
|
62
|
+
node_to_commonmark(options: opts, plugins: plugins).force_encoding("utf-8")
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
data/lib/commonmarker/version.rb
CHANGED
data/lib/commonmarker.rb
CHANGED
@@ -3,12 +3,29 @@
|
|
3
3
|
require_relative "commonmarker/extension"
|
4
4
|
|
5
5
|
require "commonmarker/utils"
|
6
|
+
require "commonmarker/node"
|
6
7
|
require "commonmarker/config"
|
7
8
|
require "commonmarker/renderer"
|
8
9
|
require "commonmarker/version"
|
9
10
|
|
10
11
|
module Commonmarker
|
11
12
|
class << self
|
13
|
+
# Public: Parses a CommonMark string into an HTML string.
|
14
|
+
#
|
15
|
+
# text - A {String} of text
|
16
|
+
# options - A {Hash} of render, parse, and extension options to transform the text.
|
17
|
+
#
|
18
|
+
# Returns the `parser` node.
|
19
|
+
def parse(text, options: Commonmarker::Config::OPTIONS)
|
20
|
+
raise TypeError, "text must be a String; got a #{text.class}!" unless text.is_a?(String)
|
21
|
+
raise TypeError, "text must be UTF-8 encoded; got #{text.encoding}!" unless text.encoding.name == "UTF-8"
|
22
|
+
raise TypeError, "options must be a Hash; got a #{options.class}!" unless options.is_a?(Hash)
|
23
|
+
|
24
|
+
opts = Config.process_options(options)
|
25
|
+
|
26
|
+
commonmark_parse(text, options: opts)
|
27
|
+
end
|
28
|
+
|
12
29
|
# Public: Parses a CommonMark string into an HTML string.
|
13
30
|
#
|
14
31
|
# text - A {String} of text
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: commonmarker
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0
|
4
|
+
version: 1.1.0
|
5
5
|
platform: x86_64-linux
|
6
6
|
authors:
|
7
7
|
- Garen Torikian
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: exe
|
11
11
|
cert_chain: []
|
12
|
-
date: 2024-
|
12
|
+
date: 2024-04-30 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: rake
|
@@ -55,6 +55,9 @@ files:
|
|
55
55
|
- lib/commonmarker/config.rb
|
56
56
|
- lib/commonmarker/constants.rb
|
57
57
|
- lib/commonmarker/extension.rb
|
58
|
+
- lib/commonmarker/node.rb
|
59
|
+
- lib/commonmarker/node/ast.rb
|
60
|
+
- lib/commonmarker/node/inspect.rb
|
58
61
|
- lib/commonmarker/renderer.rb
|
59
62
|
- lib/commonmarker/utils.rb
|
60
63
|
- lib/commonmarker/version.rb
|