devcenter-parser 1.3.9 → 1.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/README.md +7 -1
- data/lib/devcenter-parser.rb +24 -75
- data/lib/devcenter-parser/github_parser.rb +35 -0
- data/lib/devcenter-parser/header_id_generator.rb +69 -0
- data/lib/devcenter-parser/maruku_parser.rb +23 -0
- data/lib/devcenter-parser/version.rb +2 -2
- data/test/devcenter-parser_test.rb +11 -35
- data/test/header_id_generator_test.rb +63 -0
- metadata +14 -9
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: 731e954adb885153b1d9f5cecb351e93af1c249d
|
4
|
+
data.tar.gz: bc8bca7b5de1f10ff4400b43da93c93b299bf352
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: dbfa585bb7106530d36e94166f845acd49c96c952fab64a1a96e89eb0fc3d76772ff6537357047388d40596e264132d96eaa7d2c1a7f479c6d8f70676317b4da
|
7
|
+
data.tar.gz: 443d781a6d537f9612f8b8dcb4809a8d766f31c362f9826ecccb4c56892f11654a89a54c7461027405c5598afbe4ad25b012f3eeea41f1a67b40e2f901310627
|
data/README.md
CHANGED
@@ -20,8 +20,14 @@ Usage:
|
|
20
20
|
end
|
21
21
|
```
|
22
22
|
|
23
|
+
Test:
|
24
|
+
|
25
|
+
```bash
|
26
|
+
$ rake
|
27
|
+
```
|
28
|
+
|
23
29
|
## License
|
24
30
|
See the LICENSE file included in the distribution.
|
25
31
|
|
26
32
|
## Copyright
|
27
|
-
Copyright (C) 2013 Heroku <raul@heroku.com>.
|
33
|
+
Copyright (C) 2013 Heroku <raul@heroku.com>.
|
data/lib/devcenter-parser.rb
CHANGED
@@ -3,45 +3,29 @@ require 'redcarpet'
|
|
3
3
|
require 'nokogiri'
|
4
4
|
require 'uri'
|
5
5
|
require 'sanitize'
|
6
|
+
require 'ostruct'
|
7
|
+
require_relative './devcenter-parser/header_id_generator'
|
8
|
+
require_relative './devcenter-parser/github_parser'
|
9
|
+
require_relative './devcenter-parser/maruku_parser'
|
6
10
|
|
7
11
|
module DevcenterParser
|
8
|
-
|
9
12
|
AVAILABLE_FLAVOURS = [:github, :maruku]
|
10
13
|
|
11
14
|
class InvalidMarkdownError < Exception; end
|
12
15
|
class InvalidRawHTMLError < Exception; end
|
13
16
|
class UnknownFlavourError < Exception; end
|
14
17
|
|
15
|
-
class HTMLWithPantsRenderer < Redcarpet::Render::HTML
|
16
|
-
include Redcarpet::Render::SmartyPants
|
17
|
-
end
|
18
|
-
|
19
18
|
def self.to_html(markdown, flavour)
|
20
19
|
html = to_unsanitized_html(markdown, flavour.to_sym)
|
21
20
|
sanitize(html)
|
22
21
|
end
|
23
22
|
|
24
23
|
def self.to_unsanitized_html(markdown, flavour)
|
25
|
-
|
26
|
-
markdown =
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
doc = Nokogiri::HTML::DocumentFragment.parse(html)
|
31
|
-
maruku_code_blocks(doc)
|
32
|
-
maruku_underscores_to_dashes_in_subheader_anchors(doc)
|
33
|
-
when :github
|
34
|
-
html = github_parser.render(markdown.to_s)
|
35
|
-
doc = Nokogiri::HTML::DocumentFragment.parse(html)
|
36
|
-
github_parse_special_blocks(doc)
|
37
|
-
github_underscores_to_dashes_in_subheader_anchors(doc)
|
38
|
-
else
|
39
|
-
raise UnknownFlavourError, "Markdown flavour '#{flavour}' not supported"
|
40
|
-
end
|
41
|
-
convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc)
|
42
|
-
html = doc.to_html(:encoding => 'utf-8')
|
43
|
-
verify_raw_html(html)
|
44
|
-
html
|
24
|
+
raise(UnknownFlavourError, "Markdown flavour '#{flavour}' not supported") unless %w{ maruku github }.include?(flavour.to_s)
|
25
|
+
markdown = normalize_markdown(markdown)
|
26
|
+
markdown_parser = flavour.to_s == 'maruku' ? MarukuParser : GitHubParser
|
27
|
+
doc = markdown_parser.parse(markdown)
|
28
|
+
doc_to_html(doc)
|
45
29
|
rescue InvalidRawHTMLError => e
|
46
30
|
raise InvalidMarkdownError, e.message
|
47
31
|
rescue => e
|
@@ -54,9 +38,22 @@ module DevcenterParser
|
|
54
38
|
|
55
39
|
private
|
56
40
|
|
41
|
+
def self.doc_to_html(doc)
|
42
|
+
HeaderIdGenerator.apply!(doc)
|
43
|
+
convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc)
|
44
|
+
html = doc.to_html(:encoding => 'utf-8')
|
45
|
+
verify_raw_html(html)
|
46
|
+
html
|
47
|
+
end
|
48
|
+
|
49
|
+
def self.normalize_markdown(markdown)
|
50
|
+
markdown = normalize_newlines(markdown.to_s)
|
51
|
+
separate_consecutive_blockquote_blocks(markdown)
|
52
|
+
end
|
53
|
+
|
57
54
|
# The current parsers consider something like:
|
58
55
|
# > foo
|
59
|
-
#
|
56
|
+
#
|
60
57
|
# > bar
|
61
58
|
# as a single blockquote, while we want it to be two different ones.
|
62
59
|
# This method adds an empty paragraph between consecutive blocks so parsers process them separately
|
@@ -69,10 +66,6 @@ module DevcenterParser
|
|
69
66
|
markdown.lines.map{ |l| l.rstrip }.join("\n")
|
70
67
|
end
|
71
68
|
|
72
|
-
def self.github_parser
|
73
|
-
@@github_parser ||= Redcarpet::Markdown.new(HTMLWithPantsRenderer, fenced_code_blocks: true, tables: true)
|
74
|
-
end
|
75
|
-
|
76
69
|
def self.sanitize_config
|
77
70
|
return @@sanitize_config if defined?(@@sanitize_config)
|
78
71
|
config = Sanitize::Config::RELAXED
|
@@ -92,50 +85,6 @@ module DevcenterParser
|
|
92
85
|
@@sanitize_config = config.merge({remove_contents: true, allow_comments: true})
|
93
86
|
end
|
94
87
|
|
95
|
-
def self.maruku_code_blocks(doc)
|
96
|
-
doc.css('pre>code').each do |node|
|
97
|
-
if match = node.content.match(/\A\s*:::\s*(\w+)/)
|
98
|
-
lang = match[1]
|
99
|
-
node.content = node.content.gsub(/\A\s*:::\s*\w+\n/, '')
|
100
|
-
node['class'] = lang
|
101
|
-
end
|
102
|
-
end
|
103
|
-
doc
|
104
|
-
end
|
105
|
-
|
106
|
-
def self.maruku_underscores_to_dashes_in_subheader_anchors(doc)
|
107
|
-
doc.css("h2,h3,h4,h5,h6").each do |node|
|
108
|
-
node['id'] = subheader_id(node.content)
|
109
|
-
end
|
110
|
-
doc
|
111
|
-
end
|
112
|
-
|
113
|
-
def self.github_underscores_to_dashes_in_subheader_anchors(doc)
|
114
|
-
doc.css("h2,h3,h4,h5,h6").each do |node|
|
115
|
-
node['id'] = subheader_id(node.content)
|
116
|
-
end
|
117
|
-
doc
|
118
|
-
end
|
119
|
-
|
120
|
-
def self.subheader_id(content)
|
121
|
-
content.to_s.downcase.gsub(/\W+/, '-').gsub(/\A-+|-+\Z/, '')
|
122
|
-
end
|
123
|
-
|
124
|
-
def self.github_parse_special_blocks(doc)
|
125
|
-
doc.css('blockquote>p:first').each do |node|
|
126
|
-
if match = node.inner_html.match(/\A\W*(callout|warning|note)\W/)
|
127
|
-
node.parent.name = 'div'
|
128
|
-
node.parent['class'] = match[1]
|
129
|
-
|
130
|
-
new_html = node.inner_html.gsub(/\A\W*(callout|warning|note)\W/, '')
|
131
|
-
|
132
|
-
# Assigning inner_html directly causes encoding issues in old libxml versions,
|
133
|
-
# workaround from https://github.com/sparklemotion/nokogiri/issues/458#issuecomment-3136620
|
134
|
-
node.children = Nokogiri::HTML.fragment(new_html, 'utf-8')
|
135
|
-
end
|
136
|
-
end
|
137
|
-
end
|
138
|
-
|
139
88
|
def self.convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc)
|
140
89
|
doc.css('a').each do |node|
|
141
90
|
unless node['href'].nil? || node['href'] =~ /\Ahttp|\A\/|\Amailto\:|\A#/
|
@@ -164,4 +113,4 @@ module DevcenterParser
|
|
164
113
|
broken_html = html.match(/REXML could not parse this XML\/HTML\:(.+)<\/pre>/m)[1].strip rescue nil
|
165
114
|
broken_html.nil? ? "Contains broken raw HTML." : "This raw HTML is invalid: #{CGI.unescapeHTML(broken_html)}"
|
166
115
|
end
|
167
|
-
end
|
116
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
module GitHubParser
|
2
|
+
extend self
|
3
|
+
|
4
|
+
class HTMLWithPantsRenderer < Redcarpet::Render::HTML
|
5
|
+
include Redcarpet::Render::SmartyPants
|
6
|
+
end
|
7
|
+
|
8
|
+
def self.parse(markdown)
|
9
|
+
html = github_parser.render(markdown.to_s)
|
10
|
+
doc = Nokogiri::HTML::DocumentFragment.parse(html)
|
11
|
+
special_blocks(doc)
|
12
|
+
doc
|
13
|
+
end
|
14
|
+
|
15
|
+
private
|
16
|
+
|
17
|
+
def self.github_parser
|
18
|
+
@@github_parser ||= Redcarpet::Markdown.new(HTMLWithPantsRenderer, fenced_code_blocks: true, tables: true)
|
19
|
+
end
|
20
|
+
|
21
|
+
def self.special_blocks(doc)
|
22
|
+
doc.css('blockquote>p:first').each do |node|
|
23
|
+
if match = node.inner_html.match(/\A\W*(callout|warning|note)\W/)
|
24
|
+
node.parent.name = 'div'
|
25
|
+
node.parent['class'] = match[1]
|
26
|
+
|
27
|
+
new_html = node.inner_html.gsub(/\A\W*(callout|warning|note)\W/, '')
|
28
|
+
|
29
|
+
# Assigning inner_html directly causes encoding issues in old libxml versions,
|
30
|
+
# workaround from https://github.com/sparklemotion/nokogiri/issues/458#issuecomment-3136620
|
31
|
+
node.children = Nokogiri::HTML.fragment(new_html, 'utf-8')
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
@@ -0,0 +1,69 @@
|
|
1
|
+
# Generates header -> ids in the given doc, calculating the ids from the heading
|
2
|
+
# text and ensuring that there are no duplicated ids
|
3
|
+
class HeaderIdGenerator
|
4
|
+
|
5
|
+
def self.apply!(doc)
|
6
|
+
self.new(doc)
|
7
|
+
end
|
8
|
+
|
9
|
+
def initialize(doc)
|
10
|
+
@doc = doc
|
11
|
+
@header_nodes = @doc.css("h2,h3,h4,h5,h6").to_a
|
12
|
+
|
13
|
+
# { node -> id } hash
|
14
|
+
@nodes_ids = @header_nodes.inject({}){ |hash, node| hash[node] = nil; hash }
|
15
|
+
|
16
|
+
add_default_ids
|
17
|
+
prepend_parents_on_conflicts
|
18
|
+
append_numbers_on_conflicts
|
19
|
+
|
20
|
+
@nodes_ids.each{ |node, id| node['id'] = id }
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
# Parent != DOM nesting, but in the context of the content <h2></h2> ... <h3></h3>
|
26
|
+
|
27
|
+
def prepend_parents_on_conflicts
|
28
|
+
conflicts(@nodes_ids).each do |node, id|
|
29
|
+
parent_contents = parent_header_nodes(node).map{ |parent_node| parent_node.content }
|
30
|
+
content = (parent_contents + [node.content]).join(' ')
|
31
|
+
@nodes_ids[node] = subheader_id(content.to_s)
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
def parent_header_nodes(node)
|
36
|
+
parent_tags(node.name).map do |parent_tag|
|
37
|
+
@header_nodes[0..@header_nodes.index(node)-1].select{ |sibling| sibling.name == parent_tag }.last
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
# "h4" -> ["h2", "h3"]
|
42
|
+
def parent_tags(tag)
|
43
|
+
level = tag.gsub('h','').to_i
|
44
|
+
(2..level-1).map{ |n| "h#{n}" }
|
45
|
+
end
|
46
|
+
|
47
|
+
|
48
|
+
def append_numbers_on_conflicts
|
49
|
+
conflicts(@nodes_ids).group_by{ |node, id| id }.each do |id, id_conflicts|
|
50
|
+
id_conflicts.each_with_index do |conflict, n|
|
51
|
+
node = conflict[0]
|
52
|
+
new_id = "#{id}-#{n+1}"
|
53
|
+
@nodes_ids[node] = new_id
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def conflicts(hash)
|
59
|
+
hash.select{ |node1, id1| hash.select{ |node1, id2| id1 == id2 }.size > 1 }
|
60
|
+
end
|
61
|
+
|
62
|
+
def add_default_ids
|
63
|
+
@nodes_ids.each{ |node, id| @nodes_ids[node] = subheader_id(node.content) }
|
64
|
+
end
|
65
|
+
|
66
|
+
def subheader_id(content)
|
67
|
+
content.to_s.downcase.gsub(/\W+/, '-').gsub(/\A-+|-+\Z/, '')
|
68
|
+
end
|
69
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module MarukuParser
|
2
|
+
extend self
|
3
|
+
|
4
|
+
def self.parse(markdown)
|
5
|
+
html = Maruku.new(markdown, :on_error => :raise).to_html
|
6
|
+
doc = Nokogiri::HTML::DocumentFragment.parse(html)
|
7
|
+
code_blocks(doc)
|
8
|
+
doc
|
9
|
+
end
|
10
|
+
|
11
|
+
private
|
12
|
+
|
13
|
+
def self.code_blocks(doc)
|
14
|
+
doc.css('pre>code').each do |node|
|
15
|
+
if match = node.content.match(/\A\s*:::\s*(\w+)/)
|
16
|
+
lang = match[1]
|
17
|
+
node.content = node.content.gsub(/\A\s*:::\s*\w+\n/, '')
|
18
|
+
node['class'] = lang
|
19
|
+
end
|
20
|
+
end
|
21
|
+
doc
|
22
|
+
end
|
23
|
+
end
|
@@ -1,3 +1,3 @@
|
|
1
1
|
module DevcenterParser
|
2
|
-
VERSION = '1.
|
3
|
-
end
|
2
|
+
VERSION = '1.4.0'
|
3
|
+
end
|
@@ -5,7 +5,7 @@ require_relative '../lib/devcenter-parser'
|
|
5
5
|
describe 'DevcenterParser' do
|
6
6
|
|
7
7
|
describe '.to_unsanitized_html' do
|
8
|
-
|
8
|
+
|
9
9
|
it 'returns empty string for nil input' do
|
10
10
|
assert_parsing_unsanitized_result nil, :maruku, ''
|
11
11
|
assert_parsing_unsanitized_result nil, :maruku, ''
|
@@ -13,7 +13,7 @@ describe 'DevcenterParser' do
|
|
13
13
|
|
14
14
|
it 'maintains script tags' do
|
15
15
|
md = '<script>alert("hi")</script>'
|
16
|
-
assert_parsing_unsanitized_result md, :maruku, '<script
|
16
|
+
assert_parsing_unsanitized_result md, :maruku, '<script>alert("hi")</script>'
|
17
17
|
assert_parsing_unsanitized_result md, :github, '<script>alert("hi")</script>'
|
18
18
|
end
|
19
19
|
|
@@ -33,13 +33,6 @@ describe 'DevcenterParser' do
|
|
33
33
|
end
|
34
34
|
end
|
35
35
|
|
36
|
-
it 'respects existing ids' do
|
37
|
-
md = '<strong id="foo">clean</strong>'
|
38
|
-
html = '<p><strong id="foo">clean</strong></p>'
|
39
|
-
assert_maruku_result md, html
|
40
|
-
assert_github_result md, html
|
41
|
-
end
|
42
|
-
|
43
36
|
it 'removes script tags and their content' do
|
44
37
|
md = '<strong>clean<script>alert("hack!")</script></strong>'
|
45
38
|
html = '<p><strong>clean</strong></p>'
|
@@ -47,28 +40,6 @@ describe 'DevcenterParser' do
|
|
47
40
|
assert_github_result md, html
|
48
41
|
end
|
49
42
|
|
50
|
-
it 'includes ids in subheaders' do
|
51
|
-
md = <<-MARKDOWN
|
52
|
-
## Foo Bar Header 123
|
53
|
-
|
54
|
-
Foo bar content
|
55
|
-
MARKDOWN
|
56
|
-
assert DevcenterParser.to_html(md, :github).include?('<h2 id="foo-bar-header-123">Foo Bar Header 123</h2>')
|
57
|
-
assert DevcenterParser.to_html(md, :maruku).include?('<h2 id="foo-bar-header-123">Foo Bar Header 123</h2>')
|
58
|
-
end
|
59
|
-
|
60
|
-
it 'generates ids replacing inner non-alphanum chars with dashes' do
|
61
|
-
['Foo Bar', 'Foo-Bar', 'Foo#bar', 'Foo##Bar', 'Foo##Bar', '-$Foo##Bar$-'].each do |title|
|
62
|
-
md = <<-MARKDOWN
|
63
|
-
## #{title}
|
64
|
-
|
65
|
-
Foo bar content
|
66
|
-
MARKDOWN
|
67
|
-
assert DevcenterParser.to_html(md, :github).include?("<h2 id=\"foo-bar\">#{title}</h2>"), "GitHub with title #{title}: " + DevcenterParser.to_html(md, :github)
|
68
|
-
assert DevcenterParser.to_html(md, :maruku).include?("<h2 id=\"foo-bar\">#{title}</h2>"), "Maruku: " + DevcenterParser.to_html(md, :maruku)
|
69
|
-
end
|
70
|
-
end
|
71
|
-
|
72
43
|
describe 'github markdown' do
|
73
44
|
|
74
45
|
it 'generates apostrophes from single quotes in plain text' do
|
@@ -241,7 +212,7 @@ Testing
|
|
241
212
|
|
242
213
|
> callout
|
243
214
|
> **strong**
|
244
|
-
> more callout
|
215
|
+
> more callout
|
245
216
|
|
246
217
|
> normal
|
247
218
|
|
@@ -253,7 +224,7 @@ Testing
|
|
253
224
|
|
254
225
|
>callout
|
255
226
|
>**strong**
|
256
|
-
>more callout
|
227
|
+
>more callout
|
257
228
|
|
258
229
|
>normal
|
259
230
|
|
@@ -312,7 +283,7 @@ more callout</p>
|
|
312
283
|
| A | B |
|
313
284
|
| --- | --- |
|
314
285
|
| 1 | 2 |
|
315
|
-
| 3 | 4 |
|
286
|
+
| 3 | 4 |
|
316
287
|
MARKDOWN
|
317
288
|
|
318
289
|
html = <<-HTML
|
@@ -430,4 +401,9 @@ more callout</p>
|
|
430
401
|
assert_equal expected.strip, result.strip, "Failed when parsing on unsanitized mode\n#{md}\nwith the #{flavour} flavour.\n\nExpected:\n#{expected}\n\nActual result:\n#{result}\n\n"
|
431
402
|
end
|
432
403
|
|
433
|
-
|
404
|
+
def assert_header_id(md, header, id)
|
405
|
+
assert DevcenterParser.to_html(md, :github).include?("<#{header} id=\"#{id}\">"), "GitHub does not generate a #{header} with id #{id}"
|
406
|
+
assert DevcenterParser.to_html(md, :maruku).include?("<#{header} id=\"#{id}\">"), "Maruku does not generate a #{header} with id #{id}"
|
407
|
+
end
|
408
|
+
|
409
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'nokogiri'
|
3
|
+
require_relative '../lib/devcenter-parser/header_id_generator'
|
4
|
+
|
5
|
+
describe 'HeaderIdGeneratorTest' do
|
6
|
+
it 'respects existing ids in non-header elements' do
|
7
|
+
html = '<strong id="foo">clean</strong>'
|
8
|
+
assert_equal html, result(html)
|
9
|
+
end
|
10
|
+
|
11
|
+
it 'inserts ids in subheaders' do
|
12
|
+
html = '<h2>Foo Bar Header 123</h2>'
|
13
|
+
assert_id result(html), 'h2', 'foo-bar-header-123'
|
14
|
+
end
|
15
|
+
|
16
|
+
it 'generates ids replacing inner non-alphanum chars with dashes' do
|
17
|
+
['Foo Bar', 'Foo-Bar', 'Foo#bar', 'Foo##Bar', 'Foo##Bar', '-$Foo##Bar$-'].each do |title|
|
18
|
+
html = "<h2>#{title}</h2>"
|
19
|
+
assert_id result(html), 'h2', 'foo-bar'
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
|
24
|
+
describe 'ensures that there are not collisions between ids in subheaders' do
|
25
|
+
it 'by prepending the id of the previous H2 if possible' do
|
26
|
+
html = <<-HTML
|
27
|
+
<h2>A</h2>
|
28
|
+
<h3>B</h3>
|
29
|
+
<h4>Z</h4>
|
30
|
+
<h2>C</h2>
|
31
|
+
<h3>B</h3>
|
32
|
+
<h4>Z</h4>
|
33
|
+
HTML
|
34
|
+
result = result(html)
|
35
|
+
%w{ a c }.each{ |id| assert_id(result, 'h2', id) }
|
36
|
+
%w{ a-b c-b }.each{ |id| assert_id(result, 'h3', id) }
|
37
|
+
%w{ a-b-z c-b-z }.each{ |id| assert_id(result, 'h4', id) }
|
38
|
+
end
|
39
|
+
|
40
|
+
it 'by appending numbers for those subheaders with same nesting level and parent header name' do
|
41
|
+
html = <<-HTML
|
42
|
+
<h2>A</h2>
|
43
|
+
<h3>B</h3>
|
44
|
+
<h3>B</h3>
|
45
|
+
<h2>C</h2>
|
46
|
+
<h2>C</h2>
|
47
|
+
HTML
|
48
|
+
result = result(html)
|
49
|
+
%w{ a c-1 c-2 }.each{ |id| assert_id(result, 'h2', id) }
|
50
|
+
%w{ a-b-1 a-b-2 }.each{ |id| assert_id(result, 'h3', id) }
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
def assert_id(html, tag, id)
|
55
|
+
assert html.include?("<#{tag} id=\"#{id}\">"), "<#{tag} id=\"#{id}\"> not found"
|
56
|
+
end
|
57
|
+
|
58
|
+
def result(html)
|
59
|
+
doc = Nokogiri::HTML::DocumentFragment.parse(html)
|
60
|
+
HeaderIdGenerator.new(doc)
|
61
|
+
doc.to_html
|
62
|
+
end
|
63
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: devcenter-parser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Heroku
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2014-03-11 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: maruku
|
@@ -28,14 +28,14 @@ dependencies:
|
|
28
28
|
name: nokogiri
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - '>='
|
31
|
+
- - ! '>='
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: 1.4.4
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - '>='
|
38
|
+
- - ! '>='
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: 1.4.4
|
41
41
|
- !ruby/object:Gem::Dependency
|
@@ -70,14 +70,14 @@ dependencies:
|
|
70
70
|
name: minitest
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- - '>'
|
73
|
+
- - ! '>'
|
74
74
|
- !ruby/object:Gem::Version
|
75
75
|
version: '2.0'
|
76
76
|
type: :development
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- - '>'
|
80
|
+
- - ! '>'
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: '2.0'
|
83
83
|
description: Parser for Heroku Dev Center's content
|
@@ -92,8 +92,12 @@ files:
|
|
92
92
|
- README.md
|
93
93
|
- devcenter-parser.gemspec
|
94
94
|
- lib/devcenter-parser.rb
|
95
|
+
- lib/devcenter-parser/github_parser.rb
|
96
|
+
- lib/devcenter-parser/header_id_generator.rb
|
97
|
+
- lib/devcenter-parser/maruku_parser.rb
|
95
98
|
- lib/devcenter-parser/version.rb
|
96
99
|
- test/devcenter-parser_test.rb
|
100
|
+
- test/header_id_generator_test.rb
|
97
101
|
homepage: https://devcenter.heroku.com
|
98
102
|
licenses: []
|
99
103
|
metadata: {}
|
@@ -103,19 +107,20 @@ require_paths:
|
|
103
107
|
- lib
|
104
108
|
required_ruby_version: !ruby/object:Gem::Requirement
|
105
109
|
requirements:
|
106
|
-
- - '>='
|
110
|
+
- - ! '>='
|
107
111
|
- !ruby/object:Gem::Version
|
108
112
|
version: '0'
|
109
113
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
110
114
|
requirements:
|
111
|
-
- - '>='
|
115
|
+
- - ! '>='
|
112
116
|
- !ruby/object:Gem::Version
|
113
117
|
version: '0'
|
114
118
|
requirements: []
|
115
119
|
rubyforge_project:
|
116
|
-
rubygems_version: 2.
|
120
|
+
rubygems_version: 2.2.2
|
117
121
|
signing_key:
|
118
122
|
specification_version: 4
|
119
123
|
summary: Parser for Heroku Dev Center's content
|
120
124
|
test_files:
|
121
125
|
- test/devcenter-parser_test.rb
|
126
|
+
- test/header_id_generator_test.rb
|