├── .rspec
├── README.mdown
├── convert.rb
├── example.rb
├── html2confluence.gemspec
├── lib
    └── html2confluence.rb
└── spec
    ├── checkbox_examples_spec.rb
    ├── combination_examples_spec.rb
    ├── complex_tables_spec.rb
    ├── html2confluence_spec.rb
    └── jira_examples_spec.rb


/.rspec:
--------------------------------------------------------------------------------
1 | --color


--------------------------------------------------------------------------------
/README.mdown:
--------------------------------------------------------------------------------
 1 | # HTML2Confluence #
 2 | 
 3 | A quick and simple way to convert HTML to Confluence Wiki Markup, based on
 4 | html2textile.
 5 | 
 6 |     parser = HTMLToConfluenceParser.new
 7 |     parser.feed(your_html)
 8 |     puts parser.to_wiki_markup
 9 | 
10 | There are some JIRA/Confluence markup that we do not support:
11 | 
12 | * The [mailto:] tag.
13 | * The {anchor:} tag.
14 | 
15 | 
16 | ## Installation ##
17 | 
18 |     $ gem build html2confluence.gemspec
19 |     $ gem install html2confluence-1.3.18.gem
20 | 
21 | ## Command line usage ##
22 | 
23 |     $ ruby convert.rb /path/to/file.html
24 | 


--------------------------------------------------------------------------------
/convert.rb:
--------------------------------------------------------------------------------
 1 | require 'html2confluence'
 2 | 
 3 | if ARGV.empty?
 4 |   puts "Error: Pass HTML file as first argument"
 5 |   exit 1
 6 | end
 7 | 
 8 | file = File.open(ARGV[0])
 9 | parser = HTMLToConfluenceParser.new
10 | parser.feed(file.read)
11 | puts parser.to_wiki_markup
12 | 


--------------------------------------------------------------------------------
/example.rb:
--------------------------------------------------------------------------------
 1 | require 'html2confluence'
 2 | 
 3 | first_block = <<END
 4 | <div class="column span-3">
 5 |   <h3 class="storytitle entry-title" id="post-312">
 6 |     <a href="http://jystewart.net/process/2007/11/converting-html-to-textile-with-ruby/" rel="bookmark">Converting HTML to Textile with Ruby</a>
 7 |   </h3>
 8 | 
 9 |   <p>
10 |     <span>23 November 2007</span>
11 |     (<abbr class="updated" title="2007-11-23T19:51:54+00:00">7:51 pm</abbr>)
12 |   </p>
13 | 
14 |   <p>
15 |     <input type="checkbox">
16 |     <input type="checkbox" checked="">
17 |   </p>
18 | 
19 |   <p>
20 |     By <span class="author vcard fn">James Stewart</span>
21 |     <br />filed under:
22 |       <a href="http://jystewart.net/process/category/snippets/" title="View all posts in Snippets" rel="category tag">Snippets</a>
23 |       <br />tagged: <a href="http://jystewart.net/process/tag/content-management/" rel="tag">content management</a>,
24 |       <a href="http://jystewart.net/process/tag/conversion/" rel="tag">conversion</a>,
25 |       <a href="http://jystewart.net/process/tag/html/" rel="tag">html</a>,
26 |       <a href="http://jystewart.net/process/tag/python/" rel="tag">Python</a>,
27 |       <a href="http://jystewart.net/process/tag/ruby/" rel="tag">ruby</a>,
28 |       <a href="http://jystewart.net/process/tag/textile/" rel="tag">textile</a>
29 |   </p>
30 | 
31 | 
32 |   <div class="feedback">
33 |     <script src="http://feeds.feedburner.com/~s/jystewart/iLiN?i=http://jystewart.net/process/2007/11/converting-html-to-textile-with-ruby/" type="text/javascript" charset="utf-8"></script>
34 |   </div>
35 | </div>
36 | END
37 | 
38 | parser = HTMLToConfluenceParser.new
39 | parser.feed(first_block)
40 | puts parser.to_wiki_markup
41 | 


--------------------------------------------------------------------------------
/html2confluence.gemspec:
--------------------------------------------------------------------------------
 1 | Gem::Specification.new do |s|
 2 |   s.platform    = Gem::Platform::RUBY
 3 |   s.name        = 'html2confluence'
 4 |   s.version     = "1.3.23"
 5 |   s.summary     = 'Converter from HTML to Confluence Wiki Markup'
 6 |   s.description = 'Provides an SGML parser to convert HTML into the Wiki Markup format'
 7 | 
 8 |   s.required_ruby_version     = '>= 1.8.6'
 9 |   s.required_rubygems_version = ">= 1.3.6"
10 | 
11 |   s.authors           = ['k1w1', 'James Stewart', 'Mark Woods']
12 |   s.homepage          = 'http://github.com/k1w1/html2confluence'
13 | 
14 |   s.require_path = 'lib'
15 |   s.files        = Dir.glob("{lib,spec}/**/*") + %w(example.rb README.mdown)
16 | 
17 |   s.add_dependency "nokogiri"
18 | end
19 | 


--------------------------------------------------------------------------------
/lib/html2confluence.rb:
--------------------------------------------------------------------------------
  1 | require 'rexml/document'
  2 | 
  3 | require 'nokogiri' # For validating html from our editor
  4 | 
  5 | # A class to convert HTML to confluence markup. Based on the python parser
  6 | # found at http://aftnn.org/content/code/html2textile/
  7 | #
  8 | # Author::    James Stewart  (mailto:james@jystewart.net)
  9 | # Copyright:: Copyright (c) 2007 James Stewart
 10 | # License::   Distributes under the same terms as Ruby
 11 | 
 12 | # This class is an implementation of an SGMLParser designed to convert
 13 | # HTML to atlassian confluence wiki markup.
 14 | #
 15 | # Example usage:
 16 | #   parser = HTMLToConfluenceParser.new
 17 | #   parser.feed(input_html)
 18 | #   puts parser.to_wiki_markup
 19 | class HTMLToConfluenceParser
 20 | 
 21 |   attr_accessor :result
 22 |   attr_accessor :data_stack
 23 |   attr_accessor :a_href
 24 |   attr_accessor :a_title
 25 |   attr_accessor :list_stack
 26 | 
 27 |   def initialize(verbose=nil)
 28 |     @output = String.new
 29 |     @stack = []
 30 |     @preserveWhitespace = false
 31 |     @last_write = ""
 32 |     @tableHeaderRow = false
 33 |     self.result = []
 34 |     self.data_stack = []
 35 |     self.list_stack = []
 36 |   end
 37 | 
 38 |   # Normalise space in the same manner as HTML. Any substring of multiple
 39 |   # whitespace characters will be replaced with a single space char.
 40 |   def normalise_space(s)
 41 |     return s if @preserveWhitespace
 42 |     s.to_s.gsub(/\s+/x, ' ')
 43 |   end
 44 | 
 45 |   # Escape any special characters.
 46 |   def escape_special_characters(s)
 47 |     return s
 48 |     # Escaping is disabled now since it caused more problems that not having
 49 |     # it. The insertion of unecessary escaping was annoying for JIRA users.
 50 |     s.to_s.gsub(/[*#+\-_{}|]/) do |s|
 51 |       "\\#{s}"
 52 |     end
 53 |   end
 54 | 
 55 |   def make_block_start_pair(tag, attributes)
 56 |     if tag == 'p'
 57 |       # don't markup paragraphs explicitly unless necessary (i.e. there are id or class attributes)
 58 |       write("\n\n")
 59 |     else
 60 |       write("\n\n#{tag}. ")
 61 |     end
 62 |     start_capture(tag)
 63 |   end
 64 | 
 65 |   def make_block_end_pair
 66 |     stop_capture_and_write
 67 |     write("\n\n")
 68 |   end
 69 | 
 70 |   def make_quicktag_start_pair(tag, wrapchar, attributes)
 71 |     @skip_quicktag = ( tag == 'span')
 72 |     start_capture(tag)
 73 |   end
 74 | 
 75 |   def make_quicktag_end_pair(wrapchar)
 76 |     content = stop_capture
 77 | 
 78 |     # Don't make quicktags with empty content.
 79 |     if content.join("").strip.empty?
 80 |       write(content)
 81 |       return
 82 |     end
 83 | 
 84 |     unless @skip_quicktag
 85 |       unless in_nested_quicktag?
 86 |         #write([" "])
 87 |       end
 88 |       write(["#{wrapchar}"])
 89 |     end
 90 |     write(content.collect(&:strip))
 91 |     write([wrapchar]) unless @skip_quicktag
 92 |     unless in_nested_quicktag?
 93 |       #write([" "])
 94 |     end
 95 |   end
 96 | 
 97 |   def in_nested_quicktag?
 98 |     @quicktags ||= QUICKTAGS.keys
 99 |     @stack.size > 1 && @quicktags.include?(@stack[@stack.size-1]) && @quicktags.include?(@stack[@stack.size-2])
100 |   end
101 | 
102 |   def write(d)
103 |     @last_write = Array(d).join("")
104 |     if self.data_stack.size < 2
105 |       self.result += Array(d)
106 |     else
107 |       self.data_stack[-1] += Array(d)
108 |     end
109 |   end
110 | 
111 |   def start_capture(tag)
112 |     self.data_stack.push([])
113 |   end
114 | 
115 |   def stop_capture
116 |     self.data_stack.pop
117 |   end
118 | 
119 |   def stop_capture_and_write
120 |     self.write(self.data_stack.pop)
121 |   end
122 | 
123 |   def handle_data(data)
124 |     if @preserveWhitespace
125 |       write(data)
126 |     else
127 |       data ||= ""
128 |       data = normalise_space(escape_special_characters(data))
129 |       if @last_write[-1] =~ /\s/
130 |         data = data.lstrip # Collapse whitespace if the previous character was whitespace.
131 |       end
132 | 
133 |       write(data)
134 |     end
135 |   end
136 | 
137 |   %w[1 2 3 4 5 6].each do |num|
138 |     define_method "start_h#{num}" do |attributes|
139 |       make_block_start_pair("h#{num}", attributes)
140 |     end
141 | 
142 |     define_method "end_h#{num}" do
143 |       make_block_end_pair
144 |     end
145 |   end
146 | 
147 |   PAIRS = { 'bq' => 'bq', 'p' => 'p' }
148 |   QUICKTAGS = { 'b' => '*', 'strong' => '*', 'del' => '-',  'strike' => '-',
149 |     'i' => '_', 'ins' => '+', 'u' => '+', 'em' => '_', 'cite' => '??',
150 |     'sup' => '^', 'sub' => '~'}
151 | 
152 |   PAIRS.each do |key, value|
153 |     define_method "start_#{key}" do |attributes|
154 |       make_block_start_pair(value, attributes)
155 |     end
156 | 
157 |     define_method "end_#{key}" do
158 |       make_block_end_pair
159 |     end
160 |   end
161 | 
162 |   QUICKTAGS.each do |key, value|
163 |     define_method "start_#{key}" do |attributes|
164 |       make_quicktag_start_pair(key, value, attributes)
165 |     end
166 | 
167 |     define_method "end_#{key}" do
168 |       make_quicktag_end_pair(value)
169 |     end
170 |   end
171 | 
172 |   def start_div(attrs)
173 |     write("\n\n")
174 |     start_capture("div")
175 |   end
176 | 
177 |   def end_div
178 |     stop_capture_and_write
179 |     write("\n\n")
180 |   end
181 | 
182 |   def start_tt(attrs)
183 |     write("{{")
184 |   end
185 | 
186 |   def end_tt
187 |     write("}}")
188 |   end
189 | 
190 |   def start_ol(attrs)
191 |     self.list_stack.push :ol
192 |   end
193 | 
194 |   def end_ol
195 |     self.list_stack.pop
196 |     if self.list_stack.empty?
197 |       write("\n")
198 |     end
199 |   end
200 | 
201 |   def start_ul(attrs)
202 |     if attrs['type'] == "square"
203 |       self.list_stack.push :ul_square
204 |     else
205 |       self.list_stack.push :ul
206 |     end
207 |   end
208 | 
209 |   def end_ul
210 |     self.list_stack.pop
211 |     if self.list_stack.empty?
212 |       write("\n")
213 |     end
214 |   end
215 | 
216 |   def start_li(attrs)
217 |     write("\n")
218 |     write(self.list_stack.collect {|s|
219 |         case s
220 |         when :ol then "#"
221 |         when :ul then "*"
222 |         when :ul_square then "-"
223 |         end
224 |       }.join(""))
225 |     write(" ")
226 |     start_capture("li")
227 |   end
228 | 
229 |   def end_li
230 |     stop_capture_and_write
231 |   end
232 | 
233 |   def start_a(attrs)
234 |     self.a_href = attrs['href']
235 |     self.a_title = attrs['title']
236 |     if self.a_href
237 |       write("[")
238 |       start_capture("a")
239 |     end
240 |   end
241 | 
242 |   def start_input(attrs)
243 |     if attrs['type'] == "checkbox"
244 |       if attrs['checked']
245 |         write("(/) ")
246 |       else
247 |         write("(x) ")
248 |       end
249 |     end
250 |   end
251 | 
252 |   # Jira doesn't like it when there's space padding around images in links, like thumbnails.
253 |   # By checking to see if the link content is a single image, we can strip those out and preserve the link function
254 |   def link_content_filtering_out_images(content)
255 |     if content.join("").match(/\A\s*!(.+)!\s*\Z/)
256 |       ["!" + $1 + "!"]
257 |     else
258 |       content
259 |     end
260 |   end
261 | 
262 |   def end_a
263 |     if self.a_href
264 |       content = stop_capture
265 |       if self.a_href.gsub(/^#/, "") == content.join("")
266 |         write([self.a_href, "] "])
267 |       else
268 |         write(link_content_filtering_out_images(content))
269 |         write(["|", self.a_href, "] "])
270 |       end
271 | 
272 |       self.a_href = self.a_title = false
273 |     end
274 |   end
275 | 
276 |   def start_font(attrs)
277 |     color = attrs['color']
278 |     write("{color:#{color}}")
279 |   end
280 | 
281 |   def end_font
282 |     write("{color}")
283 |   end
284 | 
285 |   def start_img(attrs)
286 |     write([" !", attrs["src"], "! "])
287 |   end
288 | 
289 |   def end_img
290 |   end
291 | 
292 |   def start_table(attrs)
293 |    write("\n\n")
294 |  end
295 | 
296 |   def end_table
297 |    write("\n\n")
298 |   end
299 | 
300 |   def start_caption(attrs)
301 |    write("\n")
302 |  end
303 | 
304 |   def end_caption
305 |    write("\n")
306 |   end
307 | 
308 |   def start_tr(attrs)
309 |     write("\n")
310 |   end
311 | 
312 |   def end_tr
313 |     if @tableHeaderRow
314 |       write("||")
315 |     else
316 |       write("|")
317 |     end
318 |   end
319 | 
320 |   def start_th(attrs)
321 |     write("||")
322 |     start_capture("th")
323 |     @tableHeaderRow = true
324 |   end
325 | 
326 |   def end_th
327 |     s = stop_capture
328 |     write(cleanup_table_cell(s))
329 |   end
330 | 
331 |   def start_td(attrs)
332 |     write("|")
333 |     start_capture("td")
334 |     @tableHeaderRow = false
335 |   end
336 | 
337 |   def end_td
338 |     s = stop_capture
339 |     write(cleanup_table_cell(s))
340 |   end
341 | 
342 |   def cleanup_table_cell(s)
343 |     clean_content = (s || []).join("").strip.gsub(/\n{2,}/, "\n" + '\\\\\\' + "\n")
344 |     # Don't allow a completely empty cell because that will look like a header.
345 |     clean_content = " " if clean_content.empty?
346 |     [clean_content]
347 |   end
348 | 
349 |   def start_br(attrs)
350 |     write("\n")
351 |   end
352 | 
353 |   def start_hr(attrs)
354 |     write("----")
355 |   end
356 | 
357 |   def start_blockquote(attrs)
358 |     write("\n{quote}\n")
359 |     start_capture("blockquote")
360 |   end
361 | 
362 |   def end_blockquote
363 |     stop_capture_and_write
364 |     write("\n{quote}\n")
365 |   end
366 | 
367 |   def start_code(attrs)
368 |     @preserveWhitespace = true
369 |     write("{code}")
370 |   end
371 | 
372 |   def end_code
373 |     stop_capture_and_write
374 |     write("{code}")
375 |     @preserveWhitespace = false
376 |   end
377 | 
378 |   def start_pre(attrs)
379 |     @preserveWhitespace = true
380 |     write("{noformat}\n")
381 |   end
382 | 
383 |   def end_pre
384 |     stop_capture_and_write
385 |     write("{noformat}")
386 |     @preserveWhitespace = false
387 |   end
388 | 
389 |   def preprocess(data)
390 |     # clean up leading and trailing spaces within phrase modifier tags
391 |     quicktags_for_re = QUICKTAGS.keys.uniq.join('|')
392 |     leading_spaces_re = /(<(?:#{quicktags_for_re})(?:\s+[^>]*)?>)( +|<br\s*\/?>)/
393 |     tailing_spaces_re = /( +|<br\s*\/?>)(<\/(?:#{quicktags_for_re})(?:\s+[^>]*)?>)/
394 |     while data =~ leading_spaces_re
395 |       data.gsub!(leading_spaces_re,'\2\1')
396 |     end
397 |     while data =~ tailing_spaces_re
398 |       data.gsub!(tailing_spaces_re,'\2\1')
399 |     end
400 |     # replace non-breaking spaces
401 |     data.gsub!(/&(nbsp|#160);/,' ')
402 |     # replace special entities.
403 |     data.gsub!(/&(mdash|#8212);/,'---')
404 |     data.gsub!(/&(ndash|#8211);/,'--')
405 | 
406 |     # remove empty blockquotes and list items (other empty elements are easy enough to deal with)
407 |     data.gsub!(/<blockquote>\s*(<br[^>]*>)?\s*<\/blockquote>/x,' ')
408 | 
409 |     # Fix unclosed <br>
410 |     data.gsub!(/<br[^>]*>/, "<br/>")
411 | 
412 |     # Remove <wbr>
413 |     data.gsub!(/<wbr[^>]*>/, "")
414 | 
415 |     # Fix unclosed <hr>
416 |     data.gsub!(/<hr[^>]*>/, "<hr/>")
417 | 
418 |     # Fix unclosed <img>
419 |     data.gsub!(/(<img[^>]+)(?<!\/)>/, '\1 />')
420 | 
421 |     # Convert jira emoji
422 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/smile\.(gif|png)"[^<>]*>/, ":)")
423 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/sad\.(gif|png)"[^<>]*>/, ":(")
424 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/tongue\.(gif|png)"[^<>]*>/, ":P")
425 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/biggrin\.(gif|png)"[^<>]*>/, ":D")
426 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/wink\.(gif|png)"[^<>]*>/, ";)")
427 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/thumbs_up\.(gif|png)"[^<>]*>/, "(y)")
428 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/thumbs_down\.(gif|png)"[^<>]*>/, "(n)")
429 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/information\.(gif|png)"[^<>]*>/, "(i)")
430 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/check\.(gif|png)"[^<>]*>/, "(/)")
431 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/error\.(gif|png)"[^<>]*>/, "(x)")
432 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/warning\.(gif|png)"[^<>]*>/, "(!)")
433 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/add\.(gif|png)"[^<>]*>/, "(+)")
434 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/forbidden\.(gif|png)"[^<>]*>/, "(-)")
435 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/help_16\.(gif|png)"[^<>]*>/, "(?)")
436 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/lightbulb_on\.(gif|png)"[^<>]*>/, "(on)")
437 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/lightbulb\.(gif|png)"[^<>]*>/, "(off)")
438 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/star_yellow\.(gif|png)"[^<>]*>/, "(*)")
439 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/star_red\.(gif|png)"[^<>]*>/, "(*r)")
440 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/star_green\.(gif|png)"[^<>]*>/, "(*g)")
441 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/star_blue\.(gif|png)"[^<>]*>/, "(*b)")
442 |     data.gsub!(/<img[^<>]*src="([\w.-_:\/]+|\/)images\/icons\/emoticons\/star_yellow\.(gif|png)"[^<>]*>/, "(*y)")
443 | 
444 |     # Parse with nokogiri to ensure not tags are left unclosed
445 |     # Ensure a parsing error from Nokogiri can't stop processing to get better error from REXML
446 |     begin
447 |       validated_data = Nokogiri::HTML::fragment(data.gsub('&', '&_')).to_xml
448 |       data = validated_data.gsub('&amp;_', '&')
449 |     rescue Nokogiri::XML::SyntaxError => e
450 |     end
451 | 
452 |     data
453 |   end
454 | 
455 |   # Return the textile after processing
456 |   def to_wiki_markup
457 |     fix_textile_whitespace!(result.join).gsub(/\n(\*|#)+\s*\n(\*|#)+/) do |match|
458 |       "\n#{match.split("\n").last.squeeze(' ')}"
459 |     end
460 |   end
461 | 
462 |   def fix_textile_whitespace!(output)
463 |     # fixes multiple blank lines, blockquote indicator followed by blank lines, and trailing whitespace after quicktags
464 |     # modifies input string and also returns it
465 |     output.gsub!(/(\n\s*){2,}/,"\n\n")
466 |     output.gsub!(/bq. \n+(\w)/,'bq. \1')
467 |     QUICKTAGS.values.uniq.each do |t|
468 |       output.gsub!(/ #{Regexp.escape(t)}[ \t]+#{Regexp.escape(t)} /,' ') # removes empty quicktags
469 |       #output.gsub!(/(\[?#{Regexp.escape(t)})(\w+)([^#{Regexp.escape(t)}]+)(\s+)(#{Regexp.escape(t)}\]?)/,'\1\2\3\5\4') # fixes trailing whitespace before closing quicktags
470 |     end
471 |     #output.squeeze!(' ')
472 |     #output.gsub!(/^[ \t]/,'') # leading whitespace
473 |     #output.gsub!(/[ \t]$/,'') # trailing whitespace
474 |     output.strip!
475 |     return output
476 |   end
477 | 
478 |   def feed(data)
479 |     stream = StringIO.new(preprocess("<div>#{data}</div>"))
480 | 
481 |     REXML::Document.parse_stream(stream, self)
482 |   end
483 | 
484 |   def tag_start(name, attributes = {})
485 |     #puts "<p>Start #{name}</p>"
486 |     @stack.push(name)
487 |     if self.respond_to?("start_#{name}")
488 |       self.send("start_#{name}", attributes)
489 |     end
490 |   end
491 | 
492 |   def tag_end(name)
493 |     #puts "<p>End #{name}</p>"
494 |     if self.respond_to?("end_#{name}")
495 |       self.send("end_#{name}")
496 |     end
497 |     @stack.pop
498 |   end
499 | 
500 |   def text(string)
501 |     handle_data(string)
502 |   end
503 | 
504 |   def comment(comment)
505 |     # Comments are ignored.
506 |   end
507 | 
508 |   def cdata(data)
509 |     # CDATA is ignored.
510 |   end
511 | end
512 | 


--------------------------------------------------------------------------------
/spec/checkbox_examples_spec.rb:
--------------------------------------------------------------------------------
 1 | # encoding: utf-8
 2 | $LOAD_PATH << File.join(File.dirname(__FILE__), '..', 'lib')
 3 | require 'html2confluence'
 4 | 
 5 | describe HTMLToConfluenceParser, "when running checkbox examples" do
 6 | 
 7 |   it "should match checkboxes" do
 8 |     html = <<-END
 9 |     <div class="wiki text common-markdown"><ul class="markdown-checkbox-list">
10 |     <li><label><input type="checkbox" data-position="0" checked="">Example 1</label></li>
11 |     <li><label><input type="checkbox" data-position="1" checked="">Example 2</label></li>
12 |     <li><label><input type="checkbox" data-position="2">Example 3</label></li>
13 |     <li><label><input type="checkbox" data-position="3" checked="">Example 4</label></li>
14 |     <li><label><input type="checkbox" data-position="4">Example 5</label></li>
15 |     </ul>
16 |     </div>
17 |     END
18 | 
19 |     markup = <<-END
20 | * (/) Example 1
21 | * (/) Example 2
22 | * (x) Example 3
23 | * (/) Example 4
24 | * (x) Example 5
25 |     END
26 | 
27 |     parser = HTMLToConfluenceParser.new
28 |     parser.feed(html)
29 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
30 |   end
31 |   
32 | end
33 | 


--------------------------------------------------------------------------------
/spec/combination_examples_spec.rb:
--------------------------------------------------------------------------------
  1 | # encoding: utf-8
  2 | $LOAD_PATH << File.join(File.dirname(__FILE__), '..', 'lib')
  3 | require 'html2confluence'
  4 | 
  5 | describe HTMLToConfluenceParser, "when running combination examples" do
  6 |   
  7 |   it "should match complex examples" do
  8 |     html = <<-END
  9 | <ol>
 10 | 	<li>a</li>
 11 | 	<li>numbered <b>item</b> that is <u>underlined</u>.</li>
 12 | 	<li>list</li>
 13 | </ol>
 14 |     END
 15 |     
 16 |     markup = <<-END
 17 | # a 
 18 | # numbered *item* that is +underlined+. 
 19 | # list
 20 |     END
 21 |     
 22 |     
 23 |     parser = HTMLToConfluenceParser.new
 24 |     parser.feed(html)
 25 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
 26 |   end
 27 | 
 28 |    it "should match nested lists" do
 29 |     html = <<-END
 30 |     <p>One line</p>
 31 |     <ul>
 32 |       <li>Nested</li>
 33 |       <li>
 34 |         <ol>
 35 |           <li>bullets</li>
 36 |           <li>go</li>
 37 |           <li>here</li>
 38 |           <li>
 39 |             <ol>
 40 |               <li>dfsdf</li>
 41 |               <li>dsfs</li>
 42 |             </ol>
 43 |           </li>
 44 |         </ol>
 45 |       </li>
 46 |       <li>Final bullet</li>
 47 |     </ul>
 48 | 
 49 |     <p>More stuff too</p>
 50 | 
 51 |     <ul>
 52 |       <li>In</li>
 53 |       <li>
 54 |         <ul>
 55 |           <li>and</li>
 56 |         </ul>
 57 |       </li>
 58 |       <li>out</li>
 59 |       <li>
 60 |         <ol>
 61 |           <li>with numbers</li>
 62 |           <li>
 63 |             <ul>
 64 |               <li>and sub-bullets</li>
 65 |             </ul>
 66 |           </li>
 67 |         </ol>
 68 |       </li>
 69 |       <li>and back out</li>
 70 |     </ul>
 71 |     
 72 |     <h1>With <u>nice</u> formatting.</h1>
 73 |     END
 74 | 
 75 |     markup = <<-END
 76 | One line
 77 | 
 78 | * Nested 
 79 | *# bullets 
 80 | *# go 
 81 | *# here 
 82 | *## dfsdf 
 83 | *## dsfs  
 84 | * Final bullet 
 85 | 
 86 | More stuff too
 87 | 
 88 | * In 
 89 | ** and 
 90 | * out 
 91 | *# with numbers 
 92 | *#* and sub-bullets  
 93 | * and back out 
 94 | 
 95 | h1. With +nice+ formatting.
 96 |     END
 97 | 
 98 |     parser = HTMLToConfluenceParser.new
 99 |     parser.feed(html)
100 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
101 |   end
102 |   
103 |   it "should match nested blockquotes" do
104 |     html = <<-END
105 | <blockquote><blockquote>content here</blockquote></blockquote>
106 |     END
107 | 
108 |     markup = <<-END
109 | {quote}\nbq. content here\n{quote}
110 |     END
111 | 
112 |     parser = HTMLToConfluenceParser.new
113 |     parser.feed(html)
114 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
115 |   end
116 |   
117 |   it "should handle empty paragraphs" do
118 |     html = <<-END
119 |     <p>Previous</p><p><br></p><p><b>Scenario 4a: Existing deletes their ID</b><br>
120 |     <b>Given</b> I am an existing user</p>
121 |     END
122 | 
123 |     markup = "Previous\n\n*Scenario 4a: Existing deletes their ID*\n*Given* I am an existing user"
124 | 
125 |     parser = HTMLToConfluenceParser.new
126 |     parser.feed(html)
127 |     expect(parser.to_wiki_markup.strip).to eq(markup)
128 |   end
129 |   
130 |   it "should handle empty bold sections" do
131 |     html = <<-END
132 |     <p>Previous line</p>
133 |     <p><b><br></b> <b>Scenario 4a: Existing deletes their ID</b><br>
134 |     <b>Given</b> I am an existing user</p>
135 |     END
136 | 
137 |     markup = "Previous line\n\n*Scenario 4a: Existing deletes their ID*\n*Given* I am an existing user"
138 | 
139 |     parser = HTMLToConfluenceParser.new
140 |     parser.feed(html)
141 |     expect(parser.to_wiki_markup.strip).to eq(markup)
142 |   end
143 |   
144 |   it "doesn't remove extra newlines" do
145 |     html = "<p><b>And</b> first line</p>\n\n<p><b><br></b></p><p><b>second line</b></p>\n\n"
146 | 
147 |     markup = "*And* first line\n\n*second line*"
148 | 
149 |     parser = HTMLToConfluenceParser.new
150 |     parser.feed(html)
151 |     expect(parser.to_wiki_markup.strip).to eq(markup)
152 |   end
153 |   
154 |   it "handles unclosed img tags" do
155 |     html = "<div><img src='a source'></div>\n\n"
156 | 
157 |     markup = "!a source!"
158 | 
159 |     parser = HTMLToConfluenceParser.new
160 |     parser.feed(html)
161 |     expect(parser.to_wiki_markup.strip).to eq(markup)
162 |   end
163 |   
164 |   it "handles wbr tags" do
165 |     html = "<div>familiar with the XML<wbr>Http<wbr>Request Object</div>\n\n"
166 | 
167 |     markup = "familiar with the XMLHttpRequest Object"
168 |     parser = HTMLToConfluenceParser.new
169 |     parser.feed(html)
170 |     expect(parser.to_wiki_markup.strip).to eq(markup)
171 |     
172 |   end
173 |   
174 |   it "should handle unclosed tags" do
175 |     html = <<-END
176 |     <p>Previous line</p>
177 |     <hr>
178 |     END
179 | 
180 |     markup = "Previous line\n\n----"
181 | 
182 |     parser = HTMLToConfluenceParser.new
183 |     parser.feed(html)
184 |     expect(parser.to_wiki_markup.strip).to eq(markup)
185 |   end
186 |   
187 |   it "should handle HTML comments" do
188 |     html = <<-END
189 |     <p><!--?rh-implicit_p?--><span style=\"font-style: italic;\">A</span></p>
190 |     END
191 | 
192 |     markup = "A"
193 | 
194 |     parser = HTMLToConfluenceParser.new
195 |     parser.feed(html)
196 |     expect(parser.to_wiki_markup.strip).to eq(markup)
197 |   end
198 |   
199 |   it "should handle CDATA elements" do
200 |     html = <<-END
201 |     <p>A</p>
202 |     <![CDATA[Comment inside cdata]]>
203 |     END
204 | 
205 |     markup = "A"
206 | 
207 |     parser = HTMLToConfluenceParser.new
208 |     parser.feed(html)
209 |     expect(parser.to_wiki_markup.strip).to eq(markup)
210 |   end
211 |   
212 | end
213 | 
214 | 
215 | 
216 | 


--------------------------------------------------------------------------------
/spec/complex_tables_spec.rb:
--------------------------------------------------------------------------------
 1 | # encoding: utf-8
 2 | $LOAD_PATH << File.join(File.dirname(__FILE__), '..', 'lib')
 3 | require 'html2confluence'
 4 | 
 5 | describe HTMLToConfluenceParser, "when running complex tables examples" do
 6 |   
 7 |    it "should handle table with newlines" do
 8 |     html = <<-END
 9 |     <table class="mce-item-table"><tbody><tr><td>As a...</td><td>I would like...</td><td>Because...</td></tr><tr><td><p>Student<br>or</p><p>Teacher</p></td><td>There to be more candy</td><td><p>Candy is:</p><ul><li>Delicious</li><li>Shiny</li><li>Good for my teeth</li></ul></td></tr></tbody></table>
10 |     END
11 | 
12 |     markup = <<-END
13 | |As a...|I would like...|Because...|
14 | |Student
15 | or
16 | \\\\
17 | Teacher|There to be more candy|Candy is:
18 | \\\\
19 | * Delicious
20 | * Shiny
21 | * Good for my teeth|
22 |     END
23 | 
24 |     parser = HTMLToConfluenceParser.new
25 |     parser.feed(html)
26 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
27 |   end
28 |   
29 |    it "should handle table empty cells" do
30 |     html = <<-END
31 |     <table class="mce-item-table"><tbody><tr><td><p><br data-mce-bogus="1"></p></td><td>Empty</td><td><p><br data-mce-bogus="1"></p></td></tr></tbody></table>
32 |     END
33 | 
34 |     markup = <<-END
35 | | |Empty| |
36 |     END
37 | 
38 |     parser = HTMLToConfluenceParser.new
39 |     parser.feed(html)
40 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
41 |   end
42 |   
43 |    it "should handle pre in table empty cells" do
44 |     html = <<-END
45 |     <table><tbody><tr><td><pre>a</pre></td><td>d</td></tr><tr><td><pre>b</pre></td><td>c</td></tr></tbody></table>
46 |     END
47 | 
48 |     markup = <<-END
49 | |{noformat}
50 | a{noformat} |d |
51 | |{noformat}
52 | b{noformat} |c |
53 |     END
54 | 
55 |     parser = HTMLToConfluenceParser.new
56 |     parser.feed(html)
57 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
58 |   end
59 |   
60 |    it "should handle pre in table" do
61 |     html = <<-END
62 |     <table><tbody>
63 |       <tr>
64 |         <td>A </td>
65 |         <td><tt>B</tt> </td>
66 |         <td>C </td>
67 |       </tr>
68 |       <tr>
69 |         <td>1 </td>
70 |         <td><pre>2</pre></td>
71 |         <td>3 </td>
72 |       </tr>
73 |     </tbody></table>
74 |     END
75 | 
76 |     markup = <<-END
77 | |A |{{B}} |C | 
78 | |1 |{noformat}
79 | 2{noformat} |3  |
80 |     END
81 | 
82 |     parser = HTMLToConfluenceParser.new
83 |     parser.feed(html)
84 |     expect(parser.to_wiki_markup.strip).to include(markup.strip)
85 |   end
86 |   
87 | end
88 | 
89 | 
90 | 
91 | 


--------------------------------------------------------------------------------
/spec/html2confluence_spec.rb:
--------------------------------------------------------------------------------
  1 | # encoding: utf-8
  2 | $LOAD_PATH << File.join(File.dirname(__FILE__), '..', 'lib')
  3 | require 'html2confluence'
  4 | 
  5 | describe HTMLToConfluenceParser, "when converting html to textile" do
  6 |   context "in a large html document" do
  7 |     before :all do
  8 |       html = <<-END
  9 |       <div>
 10 | 
 11 |         Some text inside a div<br/>with two lines
 12 |         <h1 class="story.title entry-title" id="post-312">
 13 |         <img src="path_to_image.png" alt="Converting HTML to Textile with Ruby" />
 14 |           <a href="http://jystewart.net/process/2007/11/converting-html-to-textile-with-ruby/" rel="bookmark">Converting HTML to Textile with Ruby</a>
 15 |         </h1>
 16 | 
 17 |         <div class="note">A note</div><div class="note">Followed by another note</div>
 18 | 
 19 |         <p>
 20 |           <span>23 November 2007</span>
 21 |           (<abbr class="updated" title="2007-11-23T19:51:54+00:00">7:51 pm</abbr>)
 22 |         </p>
 23 | 
 24 |         <p class='test'>
 25 |           By <span class="author vcard fn">James Stewart</span> <br />filed under:
 26 |             <a href="http://jystewart.net/process/category/snippets/" title="View all posts in Snippets" rel="category tag">Snippets</a>
 27 |             <br />tagged: <a href="http://jystewart.net/process/tag/content-management/" rel="tag">content management</a>,
 28 |             <a href="http://jystewart.net/process/tag/conversion/" rel="tag">conversion</a>,
 29 |             <a href="http://jystewart.net/process/tag/html/" rel="tag">html</a>,
 30 |             <a href="http://jystewart.net/process/tag/python/" rel="tag">Python</a>,
 31 |             <a href="http://jystewart.net/process/tag/ruby/" rel="tag">ruby</a>,
 32 |             <a href="http://jystewart.net/process/tag/textile/" rel="tag">textile</a>
 33 |         </p>
 34 | 
 35 |         <p>test paragraph without id or class attributes</p>
 36 | 
 37 |         <p>test paragraph without closing tag</p>
 38 | 
 39 |         <p>Break not closed<br> at all</p>
 40 | 
 41 |         <li>test<strong> invalid </strong>list item 1</li>
 42 |         <li>test invalid list item 2</li>
 43 | 
 44 |         <ol>
 45 |           <li>test 1</li>
 46 |           <li>test 2<br/>with a line break in the middle</li>
 47 |           <li>test 3</li>
 48 |           <li> <br/></li>
 49 |         </ol>
 50 | 
 51 |         x&gt; y
 52 | 
 53 |         <blockquote>
 54 |           <p>paragraph inside a blockquote</p>
 55 |           <p>another paragraph inside a blockquote</p>
 56 |         </blockquote>
 57 | 
 58 |         <p>
 59 |           Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
 60 |           Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure
 61 |           dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
 62 |           proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
 63 |         </p>
 64 |         <table cellpadding="3" style="color:red;" summary="a table with a caption">
 65 |           <caption>table caption</caption>
 66 |           <tr>
 67 |             <th>heading 1</th>
 68 |             <th>heading 2</th>
 69 |           </tr>
 70 |           <tr>
 71 |             <td>value 1</td>
 72 |             <td>value 2</td>
 73 |           </tr>
 74 |         </table>
 75 | 
 76 |         Hughes &amp; Hughes
 77 | 
 78 |         Something &amp; something else and <span rel="test">a useless span</span>
 79 | 
 80 |         Some text before a table<table summary="a table without a caption">
 81 |           <tr>
 82 |             <th>heading 1</th>
 83 |             <th>heading 2</th>
 84 |           </tr>
 85 |           <tr>
 86 |             <td>value 1</td>
 87 |             <td>value 2</td>
 88 |           </tr>
 89 |         </table>
 90 | 
 91 |         <p>
 92 |           <strong>Please apply online at:<br /></strong><a href="http://www.something.co.uk/careers">www.something.co.uk/careers</a></p>
 93 | 
 94 |         <p>test <strong><em>test emphasised bold text</em> </strong>test
 95 |         An ordinal number - 1<sup>st </sup>
 96 |         </p>
 97 | 
 98 |         <div class="feedback">
 99 |           Leave some feedback...<br/>
100 |           <script src="http://feeds.feedburner.com/~s/jystewart/iLiN?i=http://jystewart.net/process/2007/11/converting-html-to-textile-with-ruby/" type="text/javascript" charset="utf-8"></script>
101 |         </div>
102 | 
103 |         <p>&nbsp;<br/></p>
104 |         <blockquote>&nbsp;<br/></blockquote>
105 |         <strong>more bold text</strong><strong><br /></strong>
106 | 
107 |         <p>Some text with <u>underlining</u> is here.</p>
108 | 
109 |         <p>Æïœü</p>
110 | 
111 |         <code>some_good_code</code>
112 | 
113 |         &copy; Copyright statement, let's see what happens to this&#8230; &euro; 100
114 | 
115 |         An unknown named entity reference - &unknownref;
116 | 
117 |         <strike>strike 1</strike>
118 |         <del>strike 2</del>
119 | 
120 |         # Not a list
121 |         * Not a list
122 |         - Not a list
123 |         *Not bold*
124 |         _Not a emph_
125 |         {Not curly}
126 |         |Not table
127 |       </div>
128 |       END
129 |       parser = HTMLToConfluenceParser.new
130 |       parser.feed(html)
131 |       @textile = parser.to_wiki_markup
132 |     end
133 | 
134 |     it "should convert heading tags" do
135 |       expect(@textile).to match(/^h1(\([^\)]+\))?\./)
136 |     end
137 | 
138 |     it "should convert underline tags" do
139 |       expect(@textile).to include("text with +underlining+ is here")
140 |     end
141 | 
142 |     it "should not explicitly markup paragraphs unnecessarily" do
143 |       expect(@textile).to_not include("p. test paragraph without id or class attributes")
144 |     end
145 | 
146 |     it "should treat divs as block level elements, but ignore any attributes (effectively converting them to paragraphs)" do
147 |       expect(@textile).to include("\n\nA note\n\nFollowed by another note\n\n")
148 |     end
149 | 
150 |     it "should not convert pointless spans to textile (i.e. without supported attributes)" do
151 |       expect(@textile).to_not include("%a useless span%")
152 |     end
153 | 
154 |     it "should convert class and id attributes" do
155 |       # We don't convert classes. expect(@textile).to include("h1(story.title entry-title#post-312).")
156 |     end
157 | 
158 |     it "should convert tables" do
159 |       expect(@textile).to include("\n\n||heading 1 ||heading 2 || \n|value 1 |value 2 | \n")
160 |     end
161 | 
162 |     it "should convert tables with text immediately preceding the opening table tag" do
163 |       expect(@textile).to include("Some text before a table\n\n||heading 1 ||heading 2 || \n|value 1 |value 2 | \n")
164 |     end
165 | 
166 |     it "should respect line breaks within block level elements" do
167 |       expect(@textile).to include("\n# test 1 \n# test 2\nwith a line break in the middle")
168 |     end
169 | 
170 |     it "should handle paragraphs nested within blockquote" do
171 |       expect(@textile).to include("{quote}\n\nparagraph inside a blockquote\n\nanother paragraph inside a blockquote\n\n{quote}")
172 |     end
173 | 
174 |     it "should retain leading and trailing whitespace within inline elements" do
175 |       expect(@textile).to include("test *invalid* list item 1")
176 |     end
177 | 
178 |     it "should respect trailing line break tags within other elements" do
179 |       expect(@textile).to include("*Please apply online at:*\n[www.something.co.uk/careers|http://www.something.co.uk/careers]")
180 |     end
181 | 
182 |     it "should handle nested inline elements" do
183 |       expect(@textile).to include(" *_test emphasised bold text_* test")
184 |     end
185 | 
186 |     it "should remove empty quicktags before returning" do
187 |       expect(@textile).to_not include("*more bold text* *\n*")
188 |     end
189 | 
190 |     it "should remove unsupported elements (e.g. script)" do
191 |       expect(@textile).to_not include('script')
192 |     end
193 | 
194 |     it "should remove unsupported attributes (i.e. everything but class and id)" do
195 |       expect(@textile).to_not include('summary')
196 |       expect(@textile).to_not include('a table with a caption')
197 |       expect(@textile).to_not include('style')
198 |       expect(@textile).to_not include('color:red;')
199 |     end
200 | 
201 |     it "should clean up multiple blank lines created by tolerant parsing before returning" do
202 |       expect(@textile).to_not match(/(\n\n\s*){2,}/)
203 |     end
204 | 
205 |     it "should keep entity references" do
206 |       expect(@textile).to include("&copy;")
207 |     end
208 | 
209 |     it "should output unknown named entity references" do
210 |       expect(@textile).to include("&unknownref;")
211 |     end
212 | 
213 |     it "should convert numerical entity references to a utf-8 character" do
214 |       expect(@textile).to include("…")
215 |     end
216 | 
217 |     it "should ignore entities that are already converted" do
218 |       expect(@textile).to include("Æïœü")
219 |     end
220 | 
221 |     it "should ignore ampersands that are not part of an entity reference" do
222 |       expect(@textile).to include("Hughes & Hughes")
223 |     end
224 | 
225 |     it "should retain whitespace surrounding entity references" do
226 |       expect(@textile).to include("… &euro; 100")
227 |       expect(@textile).to include("Something & something")
228 |     end
229 | 
230 |     it "should escape special characters" do
231 |       # This test currently fails. We would like it to pass, but only by escaping
232 |       # characters that would otherwise be mistaken for markup. It should not
233 |       # escape every instance of these characters.
234 |       pending 'only escape correct characters'
235 |       expect(@textile).to include("\\# Not a list")
236 |       expect(@textile).to include("\\* Not a list")
237 |       expect(@textile).to include("\\- Not a list")
238 |       expect(@textile).to include("\\*Not bold\\*")
239 |       expect(@textile).to include("\\_Not a emph\\_")
240 |       expect(@textile).to include("\\{Not curly\\}")
241 |       expect(@textile).to include("\\|Not table")
242 |     end
243 | 
244 |     it "should support strikethrough" do
245 |       expect(@textile).to include("-strike 1-")
246 |       expect(@textile).to include("-strike 2-")
247 |     end
248 | 
249 |     it "should transform code" do
250 |       expect(@textile).to include("{code}some_good_code{code}")
251 |     end
252 |   end
253 | 
254 |   it "should convert ending blockquotes" do
255 |     html = <<-END
256 |     <blockquote>
257 |       <pre>
258 |       </pre>
259 |       <div>
260 |         <div>
261 |           <pre>
262 |           </pre>
263 |         </div>
264 |       </div>
265 |     </blockquote>
266 |     END
267 | 
268 |     parser = HTMLToConfluenceParser.new
269 |     parser.feed(html)
270 |     @textile = parser.to_wiki_markup
271 | 
272 |     expect(@textile).to eq("{quote}\n{noformat}\n\n{noformat} \n\n{noformat}\n\n{noformat} \n\n{quote}")
273 |   end
274 | 
275 |   it "should convert ending blockquotes without a leading pre" do
276 |     html = <<-END
277 |     <blockquote>
278 |       <div>
279 |         <div>
280 |           <pre>
281 |           </pre>
282 |         </div>
283 |       </div>
284 |     </blockquote>
285 |     END
286 | 
287 |     parser = HTMLToConfluenceParser.new
288 |     parser.feed(html)
289 |     @textile = parser.to_wiki_markup
290 | 
291 |     expect(@textile).to eq("{quote}\n\n{noformat}\n\n{noformat} \n\n{quote}")
292 |   end
293 | 
294 |   it "should convert ending blockquotes without a nested pre" do
295 |     html = <<-END
296 |     <blockquote>
297 |       <pre>
298 |       </pre>
299 |       <div>
300 |         <div>
301 |         </div>
302 |       </div>
303 |     </blockquote>
304 |     END
305 | 
306 |     parser = HTMLToConfluenceParser.new
307 |     parser.feed(html)
308 |     @textile = parser.to_wiki_markup
309 | 
310 |     expect(@textile).to eq("{quote}\n{noformat}\n\n{noformat} \n\n{quote}")
311 |   end
312 | end
313 | 


--------------------------------------------------------------------------------
/spec/jira_examples_spec.rb:
--------------------------------------------------------------------------------
  1 | # encoding: utf-8
  2 | $LOAD_PATH << File.join(File.dirname(__FILE__), '..', 'lib')
  3 | require 'html2confluence'
  4 | 
  5 | describe HTMLToConfluenceParser, "when running JIRA examples" do
  6 |   
  7 |   before :all do
  8 |     html = <<-END
  9 | <h1><a name="Biggestheading"></a>Biggest heading</h1>
 10 | <h2><a name="Biggerheading"></a>Bigger heading</h2>
 11 | <h3><a name="Bigheading"></a>Big heading</h3>
 12 | <h4><a name="Normalheading"></a>Normal heading</h4>
 13 | <h5><a name="Smallheading"></a>Small heading</h5>
 14 | <h6><a name="Smallestheading"></a>Smallest heading</h6>
 15 | 
 16 | <p><b>strong</b><br/>
 17 | <em>emphasis</em><br/>
 18 | <cite>citation</cite><br/>
 19 | <del>deleted</del><br/>
 20 | <ins>inserted</ins><br/>
 21 | <sup>superscript</sup><br/>
 22 | <sub>subscript</sub><br/>
 23 | <tt>monospaced</tt></p>
 24 | <blockquote>Some block quoted text</blockquote>
 25 | 
 26 | <blockquote>
 27 | <p> here is quotable<br/>
 28 |  content to be quoted</p></blockquote>
 29 | 
 30 | <p><font color="red"><br/>
 31 |     look ma, red text!</font></p>
 32 | 
 33 | <p>a<br class="atl-forced-newline" />b</p>
 34 | 
 35 | <p>a<br/>
 36 | b</p>
 37 | 
 38 | <hr />
 39 | 
 40 | <p>a &#8211; b<br/>
 41 | a &#8212; b</p>
 42 | 
 43 | <p><a href="#anchor">anchor</a></p>
 44 | 
 45 | <p><a href="http://jira.atlassian.com" class="external-link" rel="nofollow">http://jira.atlassian.com</a><br/>
 46 | <a href="http://atlassian.com" class="external-link" rel="nofollow">Atlassian</a></p>
 47 | 
 48 | <p><a href="file:///c:/temp/foo.txt" class="external-link" rel="nofollow">file:///c:/temp/foo.txt</a></p>
 49 | 
 50 | <p><a name="anchorname"></a></p>
 51 | 
 52 | <ul>
 53 |   <li>some</li>
 54 |   <li>bullet
 55 |   <ul>
 56 |     <li>indented</li>
 57 |     <li>bullets</li>
 58 |   </ul>
 59 |   </li>
 60 |   <li>points</li>
 61 | </ul>
 62 | 
 63 | 
 64 | <ul class="alternate" type="square">
 65 |   <li>different</li>
 66 |   <li>bullet</li>
 67 |   <li>types</li>
 68 | </ul>
 69 | 
 70 | 
 71 | <ol>
 72 |   <li>a</li>
 73 |   <li>numbered</li>
 74 |   <li>list</li>
 75 | </ol>
 76 | 
 77 | 
 78 | <ol>
 79 |   <li>a</li>
 80 |   <li>numbered
 81 |   <ul>
 82 |     <li>with</li>
 83 |     <li>nested</li>
 84 |     <li>bullet</li>
 85 |   </ul>
 86 |   </li>
 87 |   <li>list</li>
 88 | </ol>
 89 | 
 90 | 
 91 | <ul>
 92 |   <li>a</li>
 93 |   <li>bulleted
 94 |   <ol>
 95 |     <li>with</li>
 96 |     <li>nested</li>
 97 |     <li>numbered</li>
 98 |   </ol>
 99 |   </li>
100 |   <li>list</li>
101 | </ul>
102 | 
103 | 
104 | <table class='confluenceTable'><tbody>
105 | <tr>
106 | <th class='confluenceTh'>heading 1</th>
107 | <th class='confluenceTh'>heading 2</th>
108 | <th class='confluenceTh'>heading 3</th>
109 | </tr>
110 | <tr>
111 | <td class='confluenceTd'>col A1</td>
112 | <td class='confluenceTd'>col A2</td>
113 | <td class='confluenceTd'>col A3</td>
114 | </tr>
115 | <tr>
116 | <td class='confluenceTd'>col B1</td>
117 | <td class='confluenceTd'>col B2</td>
118 | <td class='confluenceTd'>col B3</td>
119 | </tr>
120 | </tbody></table>
121 | 
122 | <img src="https://somdomain.net/images/icons/emoticons/smile.gif">
123 | <img src="https://somdomain.net/images/icons/emoticons/warning.gif">
124 | <img src="/images/icons/emoticons/lightbulb.gif">
125 | <img src="https://bigaha.atlassian.net/images/icons/emoticons/check.png" />
126 | 
127 | <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent">
128 | <pre>preformatted piece of text
129 |  so *no* further _formatting_ is done here
130 | </pre>
131 | </div></div>
132 |     END
133 |     
134 |     markup = <<-END
135 |   h1. Biggest heading
136 | h2. Bigger heading
137 | h3. Big heading
138 | h4. Normal heading
139 | h5. Small heading
140 | h6. Smallest heading
141 | 
142 | *strong*
143 | _emphasis_
144 | ??citation??
145 | -deleted-
146 | +inserted+
147 | ^superscript^
148 | ~subscript~
149 | {{monospaced}}
150 | bq. Some block quoted text
151 | 
152 | {quote}
153 |  here is quotable
154 |  content to be quoted
155 | {quote}
156 | 
157 | {color:red}
158 |     look ma, red text!
159 | {color}
160 | 
161 | a\\b
162 | 
163 | a
164 | b
165 | 
166 | ----
167 | 
168 | a -- b
169 | a --- b
170 | 
171 | [#anchor]
172 | 
173 | [http://jira.atlassian.com]
174 | [Atlassian|http://atlassian.com]
175 | 
176 | [file:///c:/temp/foo.txt]
177 | 
178 | {anchor:anchorname}
179 | 
180 | * some
181 | * bullet
182 | ** indented
183 | ** bullets
184 | * points
185 | 
186 | - different
187 | - bullet
188 | - types
189 | 
190 | # a
191 | # numbered
192 | # list
193 | 
194 | # a
195 | # numbered
196 | #* with
197 | #* nested
198 | #* bullet
199 | # list
200 | 
201 | * a
202 | * bulleted
203 | *# with
204 | *# nested
205 | *# numbered
206 | * list
207 | 
208 | ||heading 1||heading 2||heading 3||
209 | |col A1|col A2|col A3|
210 | |col B1|col B2|col B3|
211 | 
212 | {noformat}
213 | preformatted piece of text
214 |  so *no* further _formatting_ is done here
215 | {noformat}
216 |     END
217 |     
218 |     
219 |     parser = HTMLToConfluenceParser.new
220 |     parser.feed(html)
221 |     @textile = parser.to_wiki_markup
222 |     #puts @textile
223 |     #puts RedCloth.new(@textile).to_html
224 |   end
225 | 
226 |   it "should convert images within a link" do
227 |     imagetarget = "https://example.com/image.jpg"
228 |     link = "https://example.com/index.html"
229 |     test_html = %{
230 |       <p>
231 |         <a href="#{link}" target="_blank">
232 |           <img src="#{imagetarget}"
233 |           alt=""
234 |           width="300" />
235 |         </a>
236 |       </p>
237 |     }
238 | 
239 |     parser = HTMLToConfluenceParser.new
240 |     parser.feed test_html
241 |     @textile = parser.to_wiki_markup
242 | 
243 |     expect(@textile).to eq("[!#{imagetarget}!|#{link}]")
244 |   end
245 | 
246 |   it "should convert heading tags" do
247 |     expect(@textile).to match(/^h1. Biggest heading/)
248 |     expect(@textile).to match(/^h2. Bigger heading/)
249 |     expect(@textile).to match(/^h3. Big heading/)
250 |     expect(@textile).to match(/^h4. Normal heading/)
251 |     expect(@textile).to match(/^h5. Small heading/)
252 |     expect(@textile).to match(/^h6. Smallest heading/)
253 |   end
254 |   
255 |   it "should convert inline formatting" do
256 |     expect(@textile).to match(/^\*strong\*/)
257 |     expect(@textile).to match(/^_emphasis_/)
258 |     expect(@textile).to match(/^\?\?citation\?\?/)
259 |     expect(@textile).to match(/^-deleted-/)
260 |     expect(@textile).to match(/^\+inserted\+/)
261 |     expect(@textile).to match(/^\^superscript\^/)
262 |     expect(@textile).to match(/^\~subscript\~/)
263 |     expect(@textile).to match(/^\{\{monospaced\}\}/)
264 |   end
265 |   
266 |   it "should convert block quotes" do
267 |     expect(@textile).to match(/^bq. Some block quoted text/)
268 |     expect(@textile).to match(/^\{quote\}\s*here is quotable\s*content to be quoted\s*{quote}/)
269 |   end
270 |   
271 |   it "should handle text color" do
272 |     expect(@textile).to match(/^\{color\:red\}\s*look ma, red text!\s*\{color\}/)
273 |   end
274 |   
275 |   it "should convert horizontal rules" do
276 |     expect(@textile).to match(/^----/)
277 |   end
278 |   
279 |   it "should convert dashes" do
280 |     expect(@textile).to match(/^a -- b/)
281 |     expect(@textile).to match(/^a --- b/)
282 |   end
283 |   
284 |   it "should convert links" do
285 |     expect(@textile).to match(/^\[\#anchor\]/)
286 |     expect(@textile).to match(/^\[http\:\/\/jira.atlassian.com\]/)
287 |     expect(@textile).to match(/^\[Atlassian\|http\:\/\/atlassian.com\]/)
288 |     expect(@textile).to match(/^\[file\:\/\/\/c\:\/temp\/foo.txt\]/)
289 |   end
290 |   
291 |   it "should convert bullets" do
292 |     expect(@textile).to match(/\* some\s*\* bullet\s*\*\* indented\s*\*\* bullets\s*\* points/)
293 |     expect(@textile).to match(/- different\s*- bullet\s*- types/)
294 |     expect(@textile).to match(/# a\s*# numbered\s*# list/)
295 |     expect(@textile).to match(/# a\s*# numbered\s*#\* with\s*#\* nested\s*#\* bullet\s*# list/)
296 |     expect(@textile).to match(/\* a\s*\* bulleted\s*\*# with\s*\*# nested\s*\*# numbered\s*\* list/)
297 |   end
298 |   
299 |   it "should convert pre blocks" do
300 |     expect(@textile).to match(/^\{noformat\}\s*preformatted piece of text\s*so \*no\* further _formatting_ is done here\s*\{noformat\}/)
301 |   end
302 |   
303 |   it "should convert tables" do
304 |     expect(@textile).to include("||heading 1 ||heading 2 ||heading 3 ||")
305 |     expect(@textile).to include("|col A1 |col A2 |col A3 |")
306 |     expect(@textile).to include("|col B1 |col B2 |col B3 |")
307 |   end
308 | 
309 |   it "should convert emoji from jira" do
310 |     expect(@textile).to include(":)")
311 |     expect(@textile).to include("(!)")
312 |     expect(@textile).to include("(off)")
313 |     expect(@textile).to include("(/)")
314 |   end
315 |   
316 | end
317 | 


--------------------------------------------------------------------------------