reverse-markdown 0.1.1 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/reverse-markdown.rb +125 -31
- metadata +4 -5
data/lib/reverse-markdown.rb
CHANGED
@@ -1,15 +1,22 @@
|
|
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
1
|
require 'rexml/document'
|
7
2
|
require 'benchmark'
|
8
3
|
include REXML
|
9
4
|
include Benchmark
|
10
5
|
|
6
|
+
# reverse markdown for ruby
|
7
|
+
# author: JO
|
8
|
+
# e-mail: xijo@gmx.de
|
9
|
+
# date: 14.7.2009
|
10
|
+
# version: 0.1
|
11
|
+
# license: GPL
|
12
|
+
# taken from https://github.com/xijo/reverse-markdown/raw/master/reverse_markdown.rb
|
13
|
+
|
14
|
+
# TODO
|
15
|
+
# - ol numbering is buggy, in fact doesn't matter for markdown code
|
16
|
+
# -
|
17
|
+
|
11
18
|
class ReverseMarkdown
|
12
|
-
|
19
|
+
|
13
20
|
# set basic variables:
|
14
21
|
# - @li_counter: numbering list item (li) tags in an ordered list (ol)
|
15
22
|
# - @links: hold the links for adding them to the bottom of the @output
|
@@ -24,20 +31,17 @@ class ReverseMarkdown
|
|
24
31
|
@indent = 0
|
25
32
|
@errors = []
|
26
33
|
end
|
27
|
-
|
34
|
+
|
28
35
|
# Invokes the HTML parsing by using a string. Returns the markdown code in @output.
|
29
36
|
# To garantuee well-formed xml for REXML a <root> element will be added, but has no effect.
|
30
37
|
# After parsing all elements, the 'reference style'-links will be inserted.
|
31
38
|
def parse_string(string)
|
32
39
|
doc = Document.new("<root>\n"+string+"\n</root>")
|
33
|
-
|
34
|
-
root.elements.each do |element|
|
35
|
-
parse_element(element, :root)
|
36
|
-
end
|
40
|
+
parse_element(doc.root, :none)
|
37
41
|
insert_links()
|
38
42
|
@output
|
39
43
|
end
|
40
|
-
|
44
|
+
|
41
45
|
# Parsing an element and its children (recursive) and writing its markdown code to @output
|
42
46
|
# 1. do indent for nested list items
|
43
47
|
# 2. add the markdown opening tag for this element
|
@@ -50,33 +54,33 @@ class ReverseMarkdown
|
|
50
54
|
@output << indent() if name.eql?(:li)
|
51
55
|
# 2.
|
52
56
|
@output << opening(element, parent)
|
53
|
-
|
57
|
+
|
54
58
|
# 3a.
|
55
59
|
if (element.has_text? and element.children.size < 2)
|
56
60
|
@output << text_node(element, parent)
|
57
61
|
end
|
58
|
-
|
62
|
+
|
59
63
|
# 3b.
|
60
64
|
if element.has_elements?
|
61
65
|
element.children.each do |child|
|
62
66
|
# increase indent if nested list
|
63
67
|
@indent += 1 if element.name=~/(ul|ol)/ and parent.eql?(:li)
|
64
|
-
|
68
|
+
|
65
69
|
if child.node_type.eql?(:element)
|
66
70
|
parse_element(child, element.name.to_sym)
|
67
71
|
else
|
68
72
|
if parent.eql?(:blockquote)
|
69
|
-
@output << child.to_s.gsub("\n", "\n>")
|
73
|
+
@output << child.to_s.gsub("\n ", "\n>")
|
70
74
|
else
|
71
75
|
@output << child.to_s
|
72
76
|
end
|
73
77
|
end
|
74
|
-
|
78
|
+
|
75
79
|
# decrease indent if end of nested list
|
76
80
|
@indent -= 1 if element.name=~/(ul|ol)/ and parent.eql?(:li)
|
77
81
|
end
|
78
82
|
end
|
79
|
-
|
83
|
+
|
80
84
|
# 4.
|
81
85
|
@output << ending(element, parent)
|
82
86
|
end
|
@@ -95,16 +99,22 @@ class ReverseMarkdown
|
|
95
99
|
""
|
96
100
|
when :h2
|
97
101
|
"## "
|
102
|
+
when :h3
|
103
|
+
"### "
|
104
|
+
when :h4
|
105
|
+
"#### "
|
106
|
+
when :h5
|
107
|
+
"##### "
|
108
|
+
when :h6
|
109
|
+
"###### "
|
98
110
|
when :em
|
99
111
|
"*"
|
100
|
-
when :br
|
101
|
-
"\n"
|
102
|
-
"\n>" if parent.eql?(:blockquote)
|
103
112
|
when :strong
|
104
113
|
"**"
|
105
114
|
when :blockquote
|
106
|
-
|
107
|
-
"
|
115
|
+
# remove leading newline
|
116
|
+
type.children.first.value = ""
|
117
|
+
"> "
|
108
118
|
when :code
|
109
119
|
parent.eql?(:pre) ? " " : "`"
|
110
120
|
when :a
|
@@ -113,12 +123,14 @@ class ReverseMarkdown
|
|
113
123
|
"!["
|
114
124
|
when :hr
|
115
125
|
"----------\n\n"
|
126
|
+
when :root
|
127
|
+
""
|
116
128
|
else
|
117
129
|
@errors << "unknown start tag: "+type.name.to_s
|
118
130
|
""
|
119
131
|
end
|
120
132
|
end
|
121
|
-
|
133
|
+
|
122
134
|
# Returns the closing markdown tag, like opening()
|
123
135
|
def ending(type, parent)
|
124
136
|
case type.name.to_sym
|
@@ -126,6 +138,14 @@ class ReverseMarkdown
|
|
126
138
|
" #\n\n"
|
127
139
|
when :h2
|
128
140
|
" ##\n\n"
|
141
|
+
when :h3
|
142
|
+
" ###\n\n"
|
143
|
+
when :h4
|
144
|
+
" ####\n\n"
|
145
|
+
when :h5
|
146
|
+
" #####\n\n"
|
147
|
+
when :h6
|
148
|
+
" ######\n\n"
|
129
149
|
when :p
|
130
150
|
parent.eql?(:root) ? "\n\n" : "\n"
|
131
151
|
when :ol
|
@@ -149,12 +169,14 @@ class ReverseMarkdown
|
|
149
169
|
@links << type.attribute('src').to_s
|
150
170
|
"" + type.attribute('alt').to_s + "][" + @links.size.to_s + "] "
|
151
171
|
"#{type.attribute('alt')}][#{@links.size}] "
|
172
|
+
when :root
|
173
|
+
""
|
152
174
|
else
|
153
175
|
@errors << " unknown end tag: "+type.name.to_s
|
154
176
|
""
|
155
177
|
end
|
156
178
|
end
|
157
|
-
|
179
|
+
|
158
180
|
# Perform indent: two space, @indent times - quite simple! :)
|
159
181
|
def indent
|
160
182
|
str = ""
|
@@ -163,7 +185,7 @@ class ReverseMarkdown
|
|
163
185
|
end
|
164
186
|
str
|
165
187
|
end
|
166
|
-
|
188
|
+
|
167
189
|
# Return the content of element, which should be just text.
|
168
190
|
# If its a code block to indent of 4 spaces.
|
169
191
|
# For block quotation add a leading '>'
|
@@ -171,12 +193,12 @@ class ReverseMarkdown
|
|
171
193
|
if element.name.to_sym.eql?(:code) and parent.eql?(:pre)
|
172
194
|
element.text.gsub("\n","\n ") << "\n"
|
173
195
|
elsif parent.eql?(:blockquote)
|
174
|
-
element.text.gsub("\n","\n>")
|
196
|
+
element.text.gsub!("\n ","\n>")
|
175
197
|
else
|
176
198
|
element.text
|
177
199
|
end
|
178
200
|
end
|
179
|
-
|
201
|
+
|
180
202
|
# Insert the mentioned reference style links.
|
181
203
|
def insert_links
|
182
204
|
@output << "\n"
|
@@ -184,14 +206,14 @@ class ReverseMarkdown
|
|
184
206
|
@output << " [#{index+1}]: #{@links[index]}\n"
|
185
207
|
end
|
186
208
|
end
|
187
|
-
|
209
|
+
|
188
210
|
# Print out all errors, that occured and have been written to @errors.
|
189
211
|
def print_errors
|
190
212
|
@errors.each do |error|
|
191
213
|
puts error
|
192
214
|
end
|
193
215
|
end
|
194
|
-
|
216
|
+
|
195
217
|
# Perform a benchmark on a given string n-times.
|
196
218
|
def speed_benchmark(string, n)
|
197
219
|
initialize()
|
@@ -199,5 +221,77 @@ class ReverseMarkdown
|
|
199
221
|
test.report("reverse markdown:") { n.times do; parse_string(string); initialize(); end; }
|
200
222
|
end
|
201
223
|
end
|
202
|
-
|
224
|
+
|
203
225
|
end
|
226
|
+
|
227
|
+
if __FILE__ == $0
|
228
|
+
|
229
|
+
# Example HTML Code for parsing
|
230
|
+
example = <<-EOF
|
231
|
+
This text, though not within an element, should also be shown.
|
232
|
+
|
233
|
+
<h2>heading 1.1</h2>
|
234
|
+
|
235
|
+
<p>text *italic* and **bold**.</p>
|
236
|
+
|
237
|
+
<pre><code>text *italic* and **bold**.
|
238
|
+
sdfsdff
|
239
|
+
sdfsd
|
240
|
+
sdf sdfsdf
|
241
|
+
</code></pre>
|
242
|
+
|
243
|
+
<blockquote>
|
244
|
+
<p>text <em>italic</em> and <strong>bold</strong>. sdfsdff
|
245
|
+
sdfsd sdf sdfsdf</p>
|
246
|
+
</blockquote>
|
247
|
+
|
248
|
+
<p>asdasd <code>sdfsdfsdf</code> asdad <a href="http://www.bla.de">link text</a></p>
|
249
|
+
|
250
|
+
<p><a href="http://www.bla.de">link <strong>text</strong></a></p>
|
251
|
+
|
252
|
+
<ol>
|
253
|
+
<li>List item</li>
|
254
|
+
<li>List <em>item</em>
|
255
|
+
<ol><li>List item</li>
|
256
|
+
<li>dsfdsf
|
257
|
+
<ul><li>dfwe</li>
|
258
|
+
<li>dsfsdfsdf</li></ul></li>
|
259
|
+
<li>lidsf <img src="http://www.dfgdfg.de/dsf.jpe" alt="item" title="" /></li></ol></li>
|
260
|
+
<li>sdfsdfsdf
|
261
|
+
<ul><li>sdfsdfsdf</li>
|
262
|
+
<li>sdfsdfsdf <strong>sdfsdf</strong></li></ul></li>
|
263
|
+
</ol>
|
264
|
+
|
265
|
+
<blockquote>
|
266
|
+
<p>Lorem ipsum dolor sit amet, consetetur
|
267
|
+
voluptua. At vero eos et accusam et
|
268
|
+
justo duo dolores et ea rebum. Stet
|
269
|
+
clita kasd gubergren, no sea takimata
|
270
|
+
sanctus est Lorem ipsum dolor sit
|
271
|
+
amet. <em>italic</em></p>
|
272
|
+
</blockquote>
|
273
|
+
|
274
|
+
<hr />
|
275
|
+
|
276
|
+
<blockquote>
|
277
|
+
<p>Lorem ipsum dolor sit amet, consetetur
|
278
|
+
sadipscing elitr, sed diam nonumy
|
279
|
+
eirmod tempor invidunt ut labore et
|
280
|
+
dolore magna aliquyam erat, sed</p>
|
281
|
+
</blockquote>
|
282
|
+
|
283
|
+
This should also be shown, even if it's not wrapped in an element.
|
284
|
+
|
285
|
+
<p>nur ein text! nur eine maschine!</p>
|
286
|
+
|
287
|
+
This text should not be invisible!
|
288
|
+
EOF
|
289
|
+
|
290
|
+
r = ReverseMarkdown.new
|
291
|
+
|
292
|
+
puts r.parse_string(example)
|
293
|
+
|
294
|
+
#r.print_errors
|
295
|
+
|
296
|
+
#r.speed_benchmark(example, 100)
|
297
|
+
end
|
metadata
CHANGED
@@ -2,16 +2,16 @@
|
|
2
2
|
name: reverse-markdown
|
3
3
|
version: !ruby/object:Gem::Version
|
4
4
|
prerelease:
|
5
|
-
version: 0.1.
|
5
|
+
version: 0.1.2
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
8
8
|
- James Robertson
|
9
|
+
- JO
|
9
10
|
autorequire:
|
10
11
|
bindir: bin
|
11
12
|
cert_chain: []
|
12
13
|
|
13
|
-
date:
|
14
|
-
default_executable:
|
14
|
+
date: 2012-05-26 00:00:00 Z
|
15
15
|
dependencies: []
|
16
16
|
|
17
17
|
description:
|
@@ -24,7 +24,6 @@ extra_rdoc_files: []
|
|
24
24
|
|
25
25
|
files:
|
26
26
|
- lib/reverse-markdown.rb
|
27
|
-
has_rdoc: true
|
28
27
|
homepage:
|
29
28
|
licenses: []
|
30
29
|
|
@@ -48,7 +47,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
48
47
|
requirements: []
|
49
48
|
|
50
49
|
rubyforge_project:
|
51
|
-
rubygems_version: 1.
|
50
|
+
rubygems_version: 1.8.23
|
52
51
|
signing_key:
|
53
52
|
specification_version: 3
|
54
53
|
summary: reverse-markdown
|