reverse-markdown 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/reverse-markdown.rb +201 -0
- metadata +56 -0
@@ -0,0 +1,201 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# file: reverse-markdown.rb
|
4
|
+
|
5
|
+
# it is forked from https://github.com/xijo/reverse-markdown/blob/master/reverse_markdown.rb
|
6
|
+
require 'rexml/document'
|
7
|
+
require 'benchmark'
|
8
|
+
include REXML
|
9
|
+
include Benchmark
|
10
|
+
|
11
|
+
class ReverseMarkdown
|
12
|
+
|
13
|
+
# set basic variables:
|
14
|
+
# - @li_counter: numbering list item (li) tags in an ordered list (ol)
|
15
|
+
# - @links: hold the links for adding them to the bottom of the @output
|
16
|
+
# this means 'reference style', please take a look at http://daringfireball.net/projects/markdown/syntax#link
|
17
|
+
# - @outout: fancy markdown code in here!
|
18
|
+
# - @indent: control indention level for nested lists
|
19
|
+
# - @errors: appearing errors, like unknown tags, go into this array
|
20
|
+
def initialize()
|
21
|
+
@li_counter = 0
|
22
|
+
@links = []
|
23
|
+
@output = ""
|
24
|
+
@indent = 0
|
25
|
+
@errors = []
|
26
|
+
end
|
27
|
+
|
28
|
+
# Invokes the HTML parsing by using a string. Returns the markdown code in @output.
|
29
|
+
# To garantuee well-formed xml for REXML a <root> element will be added, but has no effect.
|
30
|
+
# After parsing all elements, the 'reference style'-links will be inserted.
|
31
|
+
def parse_string(string)
|
32
|
+
doc = Document.new("<root>\n"+string+"\n</root>")
|
33
|
+
root = doc.root
|
34
|
+
root.elements.each do |element|
|
35
|
+
parse_element(element, :root)
|
36
|
+
end
|
37
|
+
insert_links()
|
38
|
+
@output
|
39
|
+
end
|
40
|
+
|
41
|
+
# Parsing an element and its children (recursive) and writing its markdown code to @output
|
42
|
+
# 1. do indent for nested list items
|
43
|
+
# 2. add the markdown opening tag for this element
|
44
|
+
# 3a. if element only contains text, handle it like a text node
|
45
|
+
# 3b. if element is a container handle its children, which may be text- or element nodes
|
46
|
+
# 4. finally add the markdown ending tag for this element
|
47
|
+
def parse_element(element, parent)
|
48
|
+
name = element.name.to_sym
|
49
|
+
# 1.
|
50
|
+
@output << indent() if name.eql?(:li)
|
51
|
+
# 2.
|
52
|
+
@output << opening(element, parent)
|
53
|
+
|
54
|
+
# 3a.
|
55
|
+
if (element.has_text? and element.children.size < 2)
|
56
|
+
@output << text_node(element, parent)
|
57
|
+
end
|
58
|
+
|
59
|
+
# 3b.
|
60
|
+
if element.has_elements?
|
61
|
+
element.children.each do |child|
|
62
|
+
# increase indent if nested list
|
63
|
+
@indent += 1 if element.name=~/(ul|ol)/ and parent.eql?(:li)
|
64
|
+
|
65
|
+
if child.node_type.eql?(:element)
|
66
|
+
parse_element(child, element.name.to_sym)
|
67
|
+
else
|
68
|
+
if parent.eql?(:blockquote)
|
69
|
+
@output << child.to_s.gsub("\n ", "\n>")
|
70
|
+
else
|
71
|
+
@output << child.to_s
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
# decrease indent if end of nested list
|
76
|
+
@indent -= 1 if element.name=~/(ul|ol)/ and parent.eql?(:li)
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
# 4.
|
81
|
+
@output << ending(element, parent)
|
82
|
+
end
|
83
|
+
|
84
|
+
# Returns opening markdown tag for the element. Its parent matters sometimes!
|
85
|
+
def opening(type, parent)
|
86
|
+
case type.name.to_sym
|
87
|
+
when :h1
|
88
|
+
"# "
|
89
|
+
when :li
|
90
|
+
parent.eql?(:ul) ? " - " : " "+(@li_counter+=1).to_s+". "
|
91
|
+
when :ol
|
92
|
+
@li_counter = 0
|
93
|
+
""
|
94
|
+
when :ul
|
95
|
+
""
|
96
|
+
when :h2
|
97
|
+
"## "
|
98
|
+
when :em
|
99
|
+
"*"
|
100
|
+
when :strong
|
101
|
+
"**"
|
102
|
+
when :blockquote
|
103
|
+
# remove leading newline
|
104
|
+
type.children.first.value = ""
|
105
|
+
"> "
|
106
|
+
when :code
|
107
|
+
parent.eql?(:pre) ? " " : "`"
|
108
|
+
when :a
|
109
|
+
"["
|
110
|
+
when :img
|
111
|
+
"!["
|
112
|
+
when :hr
|
113
|
+
"----------\n\n"
|
114
|
+
else
|
115
|
+
@errors << "unknown start tag: "+type.name.to_s
|
116
|
+
""
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
# Returns the closing markdown tag, like opening()
|
121
|
+
def ending(type, parent)
|
122
|
+
case type.name.to_sym
|
123
|
+
when :h1
|
124
|
+
" #\n\n"
|
125
|
+
when :h2
|
126
|
+
" ##\n\n"
|
127
|
+
when :p
|
128
|
+
parent.eql?(:root) ? "\n\n" : "\n"
|
129
|
+
when :ol
|
130
|
+
parent.eql?(:li) ? "" : "\n"
|
131
|
+
when :ul
|
132
|
+
parent.eql?(:li) ? "" : "\n"
|
133
|
+
when :em
|
134
|
+
"*"
|
135
|
+
when :strong
|
136
|
+
"**"
|
137
|
+
when :li
|
138
|
+
""
|
139
|
+
when :blockquote
|
140
|
+
""
|
141
|
+
when :code
|
142
|
+
parent.eql?(:pre) ? "" : "`"
|
143
|
+
when :a
|
144
|
+
@links << type.attribute('href').to_s
|
145
|
+
"][" + @links.size.to_s + "] "
|
146
|
+
when :img
|
147
|
+
@links << type.attribute('src').to_s
|
148
|
+
"" + type.attribute('alt').to_s + "][" + @links.size.to_s + "] "
|
149
|
+
"#{type.attribute('alt')}][#{@links.size}] "
|
150
|
+
else
|
151
|
+
@errors << " unknown end tag: "+type.name.to_s
|
152
|
+
""
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
# Perform indent: two space, @indent times - quite simple! :)
|
157
|
+
def indent
|
158
|
+
str = ""
|
159
|
+
@indent.times do
|
160
|
+
str << " "
|
161
|
+
end
|
162
|
+
str
|
163
|
+
end
|
164
|
+
|
165
|
+
# Return the content of element, which should be just text.
|
166
|
+
# If its a code block to indent of 4 spaces.
|
167
|
+
# For block quotation add a leading '>'
|
168
|
+
def text_node(element, parent)
|
169
|
+
if element.name.to_sym.eql?(:code) and parent.eql?(:pre)
|
170
|
+
element.text.gsub("\n","\n ") << "\n"
|
171
|
+
elsif parent.eql?(:blockquote)
|
172
|
+
element.text.gsub!("\n ","\n>")
|
173
|
+
else
|
174
|
+
element.text
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
# Insert the mentioned reference style links.
|
179
|
+
def insert_links
|
180
|
+
@output << "\n"
|
181
|
+
@links.each_index do |index|
|
182
|
+
@output << " [#{index+1}]: #{@links[index]}\n"
|
183
|
+
end
|
184
|
+
end
|
185
|
+
|
186
|
+
# Print out all errors, that occured and have been written to @errors.
|
187
|
+
def print_errors
|
188
|
+
@errors.each do |error|
|
189
|
+
puts error
|
190
|
+
end
|
191
|
+
end
|
192
|
+
|
193
|
+
# Perform a benchmark on a given string n-times.
|
194
|
+
def speed_benchmark(string, n)
|
195
|
+
initialize()
|
196
|
+
bm(15) do |test|
|
197
|
+
test.report("reverse markdown:") { n.times do; parse_string(string); initialize(); end; }
|
198
|
+
end
|
199
|
+
end
|
200
|
+
|
201
|
+
end
|
metadata
ADDED
@@ -0,0 +1,56 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: reverse-markdown
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease:
|
5
|
+
version: 0.1.0
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- James Robertson
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
|
13
|
+
date: 2011-08-17 00:00:00 +01:00
|
14
|
+
default_executable:
|
15
|
+
dependencies: []
|
16
|
+
|
17
|
+
description:
|
18
|
+
email:
|
19
|
+
executables: []
|
20
|
+
|
21
|
+
extensions: []
|
22
|
+
|
23
|
+
extra_rdoc_files: []
|
24
|
+
|
25
|
+
files:
|
26
|
+
- lib/reverse-markdown.rb
|
27
|
+
has_rdoc: true
|
28
|
+
homepage:
|
29
|
+
licenses: []
|
30
|
+
|
31
|
+
post_install_message:
|
32
|
+
rdoc_options: []
|
33
|
+
|
34
|
+
require_paths:
|
35
|
+
- lib
|
36
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
37
|
+
none: false
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: "0"
|
42
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
43
|
+
none: false
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: "0"
|
48
|
+
requirements: []
|
49
|
+
|
50
|
+
rubyforge_project:
|
51
|
+
rubygems_version: 1.5.2
|
52
|
+
signing_key:
|
53
|
+
specification_version: 3
|
54
|
+
summary: reverse-markdown
|
55
|
+
test_files: []
|
56
|
+
|