md-noko 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/.rspec +3 -0
- data/.travis.yml +5 -0
- data/Gemfile +6 -0
- data/README.md +73 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/md-noko.rb +1 -0
- data/lib/md/noko.rb +168 -0
- data/lib/md/noko/version.rb +5 -0
- data/md-noko.gemspec +33 -0
- metadata +129 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 9fde11dc2fda8402592b512221cf66545b1d17a9fcb79183ae4cc299449685d8
|
4
|
+
data.tar.gz: ea5ac14c87fde2826ad792007a2f38df8be6c4890b93a3915700fefb94cf6efe
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 80d7b6bbf6cf730a42780e8dcb2740f8e98b753303e736103734b38d7add4fa2d9cc4cb6911c7480e1b066cf279df6639b85469667d534c424c6ae9f9010c1d4
|
7
|
+
data.tar.gz: dad35e41c0a72f8af134896444f277bef50db97af43bfdacfa9484b9bf21753e2bb5578aeeff673387d1d585b72d17bb5bf7032003cbbb62a961eb61dde9241b
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
# MD::Noko: in goes Markdown, out comes Nokogiri
|
2
|
+
|
3
|
+
## Synopsis
|
4
|
+
|
5
|
+
```ruby
|
6
|
+
require 'md-noko'
|
7
|
+
|
8
|
+
mdnk = MD::Noko.new
|
9
|
+
doc = mdnk.ingest File.open('lolwut.md')
|
10
|
+
|
11
|
+
# or
|
12
|
+
|
13
|
+
doc = mdnk.ingest <<EOT
|
14
|
+
# Hi
|
15
|
+
|
16
|
+
Markdown here!
|
17
|
+
|
18
|
+
![lulz](meme.jpeg)
|
19
|
+
|
20
|
+
EOT
|
21
|
+
|
22
|
+
# doc is a Nokogiri::XML::Document
|
23
|
+
```
|
24
|
+
|
25
|
+
## Description
|
26
|
+
|
27
|
+
This is a simple module that encapsulates a set of desirable
|
28
|
+
manipulations to the (X)HTML output
|
29
|
+
of [Redcarpet](https://www.rubydoc.info/gems/redcarpet/). It exposes
|
30
|
+
(for now) a single method, `ingest`, which returns a [`Nokogiri::XML::Document`](https://www.rubydoc.info/gems/nokogiri/Nokogiri/XML/Document), for further manipulation. In particular, this module:
|
31
|
+
|
32
|
+
* Adds HTML preamble to produce a valid document,
|
33
|
+
* Creates a `<base href=""/>` element which you can pass a URL,
|
34
|
+
* Creates a hierarchy of `<section>` elements and places headings
|
35
|
+
and content inside,
|
36
|
+
* If the document contains exactly one `<h1>` which is the very first
|
37
|
+
thing in the file, it is copied into the `<title>`, and removed from
|
38
|
+
the document body if determined to be redundant (i.e. unless it
|
39
|
+
contains markup elements and not strictly text),
|
40
|
+
* A `<blockquote>` element containing exactly one nested
|
41
|
+
`<blockquote>` element is converted into a single `<aside role="note">`,
|
42
|
+
* Images on their own paragraph are transformed into a `<figure>`,
|
43
|
+
* Text nodes not descendants of `<pre>` are whitespace-normalized and
|
44
|
+
indentation is repaired.
|
45
|
+
|
46
|
+
The embedded `Redcarpet::Markdown` instance has the following flags set:
|
47
|
+
|
48
|
+
* `:tables`
|
49
|
+
* `:fenced_code_blocks`
|
50
|
+
* `:quote`
|
51
|
+
* `:highlight`
|
52
|
+
|
53
|
+
These are currently not exposed.
|
54
|
+
|
55
|
+
## Installation
|
56
|
+
|
57
|
+
The usual:
|
58
|
+
|
59
|
+
$ gem install md-noko
|
60
|
+
|
61
|
+
Or, [download it off rubygems.org](https://rubygems.org/gems/md-noko).
|
62
|
+
|
63
|
+
## Contributing
|
64
|
+
|
65
|
+
Bug reports and pull requests are welcome at
|
66
|
+
[the GitHub repository](https://github.com/doriantaylor/rb-md-noko).
|
67
|
+
|
68
|
+
## Copyright & License
|
69
|
+
|
70
|
+
©2018 [Dorian Taylor](https://doriantaylor.com/)
|
71
|
+
|
72
|
+
This software is provided under
|
73
|
+
the [Apache License, 2.0](https://www.apache.org/licenses/LICENSE-2.0).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "md/noko"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/lib/md-noko.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'md/noko'
|
data/lib/md/noko.rb
ADDED
@@ -0,0 +1,168 @@
|
|
1
|
+
require 'md/noko/version'
|
2
|
+
require 'redcarpet'
|
3
|
+
require 'xml-mixup'
|
4
|
+
|
5
|
+
class MD::Noko
|
6
|
+
include XML::Mixup
|
7
|
+
|
8
|
+
private
|
9
|
+
|
10
|
+
XHTML_BP = <<-BP
|
11
|
+
<!DOCTYPE html>
|
12
|
+
<html xmlns="http://www.w3.org/1999/xhtml">
|
13
|
+
<head>
|
14
|
+
<title/>
|
15
|
+
<base href="%s"/>
|
16
|
+
</head>
|
17
|
+
<body>
|
18
|
+
%s
|
19
|
+
</body>
|
20
|
+
</html>
|
21
|
+
BP
|
22
|
+
|
23
|
+
XPATH_NS = { html: 'http://www.w3.org/1999/xhtml' }.freeze
|
24
|
+
|
25
|
+
@@markdown = Redcarpet::Markdown.new(
|
26
|
+
Redcarpet::Render::XHTML.new(prettify: false),
|
27
|
+
tables: true, fenced_code_blocks: true, quote: true, highlight: true)
|
28
|
+
|
29
|
+
def h1_title body
|
30
|
+
heads = body.xpath('html:h1', XPATH_NS)
|
31
|
+
|
32
|
+
# set the title to the first and only h1 if it's the first element
|
33
|
+
if heads.length == 1 and not heads[0].previous_element
|
34
|
+
h1 = heads[0]
|
35
|
+
|
36
|
+
# assign document title to the header content
|
37
|
+
d = body.document
|
38
|
+
t = d.at_xpath('/html:html/html:head/html:title[1]', XPATH_NS)
|
39
|
+
t.content = h1.content
|
40
|
+
|
41
|
+
# unlink redundant h1 if it has no children (ie unformatted)
|
42
|
+
h1.unlink unless h1.at_xpath('*')
|
43
|
+
|
44
|
+
# only do h2 through h6
|
45
|
+
return true
|
46
|
+
end
|
47
|
+
|
48
|
+
# otherwise do nothing
|
49
|
+
false
|
50
|
+
end
|
51
|
+
|
52
|
+
def make_sections node, ranks=1..6
|
53
|
+
raise 'fail range' if ranks.nil? or ranks.size < 1
|
54
|
+
|
55
|
+
h = "html:h#{ranks.first}"
|
56
|
+
|
57
|
+
ranks = Range.new(ranks.first + 1, ranks.last)
|
58
|
+
|
59
|
+
headers = node.xpath(h, XPATH_NS).to_a
|
60
|
+
if headers.empty?
|
61
|
+
return make_sections node, ranks if ranks.size > 0
|
62
|
+
else
|
63
|
+
headers.each_index do |i|
|
64
|
+
hdr = headers[i]
|
65
|
+
xp = "following-sibling::node()[not(self::#{h})]"
|
66
|
+
if i < headers.length - 1
|
67
|
+
# note that this is always 1 because all preceding
|
68
|
+
# siblings prior to that will have been removed
|
69
|
+
xp += "[following-sibling::#{h}" +
|
70
|
+
"[count(preceding-sibling::#{h}) = #{1}]]"
|
71
|
+
end
|
72
|
+
|
73
|
+
# duplicate and nuke these elements
|
74
|
+
siblings = hdr.xpath(xp, XPATH_NS).to_a.map do |s|
|
75
|
+
# note that :unlink returns the node, but with a
|
76
|
+
# garbaged-up set of namespaces
|
77
|
+
o = s.dup; s.unlink; o
|
78
|
+
end
|
79
|
+
|
80
|
+
# add the header to the front of the list
|
81
|
+
siblings.unshift hdr.dup
|
82
|
+
siblings.unshift "\n"
|
83
|
+
|
84
|
+
# now construct the section
|
85
|
+
section = markup replace: hdr, spec: { nil => :section }
|
86
|
+
markup after: section, spec: "\n"
|
87
|
+
markup parent: section, spec: siblings
|
88
|
+
|
89
|
+
# now recurse
|
90
|
+
make_sections section, ranks
|
91
|
+
end
|
92
|
+
end
|
93
|
+
end
|
94
|
+
|
95
|
+
def bq_aside body
|
96
|
+
x = './/%s[not(parent::%s)][%s][count(*) = 1]' % (%w{html:blockquote} * 3)
|
97
|
+
body.xpath(x, XPATH_NS).each do |node|
|
98
|
+
fc = node.first_element_child
|
99
|
+
fc.name = 'aside'
|
100
|
+
fc[:role] = 'note'
|
101
|
+
node.replace fc
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
def img_figure body
|
106
|
+
body.xpath('.//html:p[html:img][count(*) = 1]', XPATH_NS).each do |node|
|
107
|
+
node.name = 'figure'
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
def prune_text body
|
112
|
+
doc = body.document
|
113
|
+
doc.xpath('//text()[not(ancestor::html:pre)]', XPATH_NS).each do |n|
|
114
|
+
n.content = n.content.gsub(/(?: |\t|\r|\n)+/, ' ')
|
115
|
+
# might as well fix the damn indentation while we're here
|
116
|
+
if n.content == ' '
|
117
|
+
a = n.ancestors.count - 1
|
118
|
+
if (p = n.previous_sibling)
|
119
|
+
# nth text node
|
120
|
+
if p.text? and p.content =~ /^\s+$/
|
121
|
+
n.unlink
|
122
|
+
else
|
123
|
+
a -= 1 unless n.next_sibling
|
124
|
+
n.content = "\n" + (' ' * a)
|
125
|
+
end
|
126
|
+
else
|
127
|
+
# first text node
|
128
|
+
n.content = "\n" + (' ' * a)
|
129
|
+
end
|
130
|
+
end
|
131
|
+
end
|
132
|
+
end
|
133
|
+
|
134
|
+
public
|
135
|
+
|
136
|
+
# Ingest a markdown file, with sensible defaults
|
137
|
+
#
|
138
|
+
# @param obj [String, IO] the content to be ingested
|
139
|
+
#
|
140
|
+
# @param uri [String, #to_s, nil] the document's base URI
|
141
|
+
#
|
142
|
+
# @return [Nokogiri::XML::Document]
|
143
|
+
|
144
|
+
def ingest obj, uri=nil
|
145
|
+
doc = obj.respond_to?(:read) ? obj.read : obj
|
146
|
+
doc = XHTML_BP % [uri ? uri.to_s : '', @@markdown.render(doc)]
|
147
|
+
doc = Nokogiri::XML.parse doc, uri
|
148
|
+
|
149
|
+
body = doc.at_xpath('/html:html/html:body[1]', XPATH_NS)
|
150
|
+
|
151
|
+
# default all six headers unless there's a lone h1
|
152
|
+
ranks = h1_title(body) ? 2..6 : 1..6
|
153
|
+
|
154
|
+
# markdown just makes a flat list of elements so let's plump it up
|
155
|
+
make_sections body, ranks
|
156
|
+
|
157
|
+
# redo double blockquotes as <aside role="note">
|
158
|
+
bq_aside body
|
159
|
+
|
160
|
+
# redo paragraphs containing only images as figures
|
161
|
+
img_figure body
|
162
|
+
|
163
|
+
# fix the damn text nodes
|
164
|
+
prune_text body
|
165
|
+
|
166
|
+
doc
|
167
|
+
end
|
168
|
+
end
|
data/md-noko.gemspec
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'md/noko/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = 'md-noko'
|
8
|
+
spec.version = MD::Noko::VERSION
|
9
|
+
spec.authors = ['Dorian Taylor']
|
10
|
+
spec.email = ['code@doriantaylor.com']
|
11
|
+
spec.license = 'Apache-2.0'
|
12
|
+
spec.summary = %q{In goes Markdown, out pops Nokogiri.}
|
13
|
+
spec.description = <<-DESC
|
14
|
+
This is a simple module that encapsulates a set of desirable
|
15
|
+
manipulations to the (X)HTML output of Redcarpet, producing a
|
16
|
+
Nokogiri::XML::Document which is amenable to further manipulation.
|
17
|
+
DESC
|
18
|
+
spec.homepage = 'https://github.com/doriantaylor/rb-md-noko'
|
19
|
+
|
20
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
21
|
+
spec.bindir = 'exe'
|
22
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
23
|
+
spec.require_paths = ['lib']
|
24
|
+
|
25
|
+
spec.required_ruby_version = '~> 2.0'
|
26
|
+
|
27
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
28
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
29
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
30
|
+
|
31
|
+
spec.add_runtime_dependency 'redcarpet', '~> 3.4.0'
|
32
|
+
spec.add_runtime_dependency 'xml-mixup', '~> 0.1.5'
|
33
|
+
end
|
metadata
ADDED
@@ -0,0 +1,129 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: md-noko
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Dorian Taylor
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-05-16 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.11'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.11'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: redcarpet
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 3.4.0
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 3.4.0
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: xml-mixup
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 0.1.5
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 0.1.5
|
83
|
+
description: |
|
84
|
+
This is a simple module that encapsulates a set of desirable
|
85
|
+
manipulations to the (X)HTML output of Redcarpet, producing a
|
86
|
+
Nokogiri::XML::Document which is amenable to further manipulation.
|
87
|
+
email:
|
88
|
+
- code@doriantaylor.com
|
89
|
+
executables: []
|
90
|
+
extensions: []
|
91
|
+
extra_rdoc_files: []
|
92
|
+
files:
|
93
|
+
- ".gitignore"
|
94
|
+
- ".rspec"
|
95
|
+
- ".travis.yml"
|
96
|
+
- Gemfile
|
97
|
+
- README.md
|
98
|
+
- Rakefile
|
99
|
+
- bin/console
|
100
|
+
- bin/setup
|
101
|
+
- lib/md-noko.rb
|
102
|
+
- lib/md/noko.rb
|
103
|
+
- lib/md/noko/version.rb
|
104
|
+
- md-noko.gemspec
|
105
|
+
homepage: https://github.com/doriantaylor/rb-md-noko
|
106
|
+
licenses:
|
107
|
+
- Apache-2.0
|
108
|
+
metadata: {}
|
109
|
+
post_install_message:
|
110
|
+
rdoc_options: []
|
111
|
+
require_paths:
|
112
|
+
- lib
|
113
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '2.0'
|
118
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
119
|
+
requirements:
|
120
|
+
- - ">="
|
121
|
+
- !ruby/object:Gem::Version
|
122
|
+
version: '0'
|
123
|
+
requirements: []
|
124
|
+
rubyforge_project:
|
125
|
+
rubygems_version: 2.7.6
|
126
|
+
signing_key:
|
127
|
+
specification_version: 4
|
128
|
+
summary: In goes Markdown, out pops Nokogiri.
|
129
|
+
test_files: []
|