Class: TC_TestHTMLTokenizer

Inherits:
Test::Unit::TestCase
  • Object
show all
Defined in:
lib/html/htmltokenizer.rb

Instance Method Summary collapse

Instance Method Details



307
308
309
310
 
# File 'lib/html/htmltokenizer.rb', line 307

def test_bad_link
  toke = HTMLTokenizer.new("<p><a href=http://bad.com/link>foo</a></p>")
  assert("http://bad.com/link" == toke.getTag("a").attr_hash['href'])
end

#test_comment ⇒ Object 



317
318
319
320
321
322
 
# File 'lib/html/htmltokenizer.rb', line 317

def test_comment
  toke = HTMLTokenizer.new("<!-- comment on me -->")
  t = toke.getNextToken
  assert(HTMLComment == t.class)
  assert("comment on me" == t.contents)
end

#test_full ⇒ Object 



325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
 
# File 'lib/html/htmltokenizer.rb', line 325

def test_full
  page = "<HTML>
<HEAD>
<TITLE>This is the title</TITLE>
</HEAD>
<!-- Here comes the <a href=\"missing.link\">blah</a>
comment body
 -->
<BODY>
  <H1>This is the header</H1>
  <P>
This is the paragraph, it contains
<a href=\"link.html\">links</a>, 
<img src=\"blah.gif\" optional alt='images
are
really cool'>.  Ok, here is some more text and
<A href=\"http://another.link.com/\" target=\"_blank\">another link</A>.
  </P>
</body>
</HTML>
"
  toke = HTMLTokenizer.new(page)

  assert("<h1>" == toke.getTag("h1", "h2", "h3").to_s.downcase)
  assert(HTMLTag.new("<a href=\"link.html\">") == toke.getTag("IMG", "A"))
  assert("links" == toke.getTrimmedText)
  assert(toke.getTag("IMG", "A").attr_hash['optional'])
  assert("_blank" == toke.getTag("IMG", "A").attr_hash['target'])
end

#test_namespace ⇒ Object 



312
313
314
315
 
# File 'lib/html/htmltokenizer.rb', line 312

def test_namespace
  toke = HTMLTokenizer.new("<f:table xmlns:f=\"http://www.com/foo\">")
  assert("http://www.com/foo" == toke.getTag("f:table").attr_hash['xmlns:f'])
end