/usr/lib/python2.7/dist-packages/bleach/tests/test_links.py is in python-bleach 1.4.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | try:
from urllib.parse import quote_plus
except ImportError:
from urllib import quote_plus
from html5lib.tokenizer import HTMLTokenizer
from nose.tools import eq_
from bleach import linkify, url_re, DEFAULT_CALLBACKS as DC
def test_url_re():
def no_match(s):
match = url_re.search(s)
if match:
assert not match, 'matched {0!s}'.format(s[slice(*match.span())])
yield no_match, 'just what i am looking for...it'
def test_empty():
eq_('', linkify(''))
def test_simple_link():
eq_('a <a href="http://example.com" rel="nofollow">http://example.com'
'</a> link',
linkify('a http://example.com link'))
eq_('a <a href="https://example.com" rel="nofollow">https://example.com'
'</a> link',
linkify('a https://example.com link'))
eq_('a <a href="http://example.com" rel="nofollow">example.com</a> link',
linkify('a example.com link'))
def test_trailing_slash():
eq_('<a href="http://examp.com/" rel="nofollow">http://examp.com/</a>',
linkify('http://examp.com/'))
eq_('<a href="http://example.com/foo/" rel="nofollow">'
'http://example.com/foo/</a>',
linkify('http://example.com/foo/'))
eq_('<a href="http://example.com/foo/bar/" rel="nofollow">'
'http://example.com/foo/bar/</a>',
linkify('http://example.com/foo/bar/'))
def test_mangle_link():
"""We can muck with the href attribute of the link."""
def filter_url(attrs, new=False):
quoted = quote_plus(attrs['href'])
attrs['href'] = 'http://bouncer/?u={0!s}'.format(quoted)
return attrs
eq_('<a href="http://bouncer/?u=http%3A%2F%2Fexample.com" rel="nofollow">'
'http://example.com</a>',
linkify('http://example.com', DC + [filter_url]))
def test_mangle_text():
"""We can muck with the inner text of a link."""
def ft(attrs, new=False):
attrs['_text'] = 'bar'
return attrs
eq_('<a href="http://ex.mp">bar</a> <a href="http://ex.mp/foo">bar</a>',
linkify('http://ex.mp <a href="http://ex.mp/foo">foo</a>', [ft]))
def test_email_link():
tests = (
('a james@example.com mailto', False, 'a james@example.com mailto'),
('a james@example.com.au mailto', False,
'a james@example.com.au mailto'),
('a <a href="mailto:james@example.com">james@example.com</a> mailto',
True, 'a james@example.com mailto'),
('aussie <a href="mailto:james@example.com.au">'
'james@example.com.au</a> mailto', True,
'aussie james@example.com.au mailto'),
# This is kind of a pathological case. I guess we do our best here.
('email to <a href="james@example.com" rel="nofollow">'
'james@example.com</a>',
True,
'email to <a href="james@example.com">james@example.com</a>'),
('<br><a href="mailto:jinkyun@example.com">'
'jinkyun@example.com</a>',
True,
'<br>jinkyun@example.com'),
)
def _check(o, p, i):
eq_(o, linkify(i, parse_email=p))
for (o, p, i) in tests:
yield _check, o, p, i
def test_email_link_escaping():
tests = (
('''<a href='mailto:"james"@example.com'>'''
'''"james"@example.com</a>''',
'"james"@example.com'),
('''<a href="mailto:"j'ames"@example.com">'''
'''"j'ames"@example.com</a>''',
'"j\'ames"@example.com'),
('''<a href='mailto:"ja>mes"@example.com'>'''
'''"ja>mes"@example.com</a>''',
'"ja>mes"@example.com'),
)
def _check(o, i):
eq_(o, linkify(i, parse_email=True))
for (o, i) in tests:
yield _check, o, i
def test_prevent_links():
"""Returning None from any callback should remove links or prevent them
from being created."""
def no_new_links(attrs, new=False):
if new:
return None
return attrs
def no_old_links(attrs, new=False):
if not new:
return None
return attrs
def noop(attrs, new=False):
return attrs
in_text = 'a ex.mp <a href="http://example.com">example</a>'
out_text = 'a <a href="http://ex.mp">ex.mp</a> example'
tests = (
([noop], ('a <a href="http://ex.mp">ex.mp</a> '
'<a href="http://example.com">example</a>'), 'noop'),
([no_new_links, noop], in_text, 'no new, noop'),
([noop, no_new_links], in_text, 'noop, no new'),
([no_old_links, noop], out_text, 'no old, noop'),
([noop, no_old_links], out_text, 'noop, no old'),
([no_old_links, no_new_links], 'a ex.mp example', 'no links'),
)
def _check(cb, o, msg):
eq_(o, linkify(in_text, cb), msg)
for (cb, o, msg) in tests:
yield _check, cb, o, msg
def test_set_attrs():
"""We can set random attributes on links."""
def set_attr(attrs, new=False):
attrs['rev'] = 'canonical'
return attrs
eq_('<a href="http://ex.mp" rev="canonical">ex.mp</a>',
linkify('ex.mp', [set_attr]))
def test_only_proto_links():
"""Only create links if there's a protocol."""
def only_proto(attrs, new=False):
if new and not attrs['_text'].startswith(('http:', 'https:')):
return None
return attrs
in_text = 'a ex.mp http://ex.mp <a href="/foo">bar</a>'
out_text = ('a ex.mp <a href="http://ex.mp">http://ex.mp</a> '
'<a href="/foo">bar</a>')
eq_(out_text, linkify(in_text, [only_proto]))
def test_stop_email():
"""Returning None should prevent a link from being created."""
def no_email(attrs, new=False):
if attrs['href'].startswith('mailto:'):
return None
return attrs
text = 'do not link james@example.com'
eq_(text, linkify(text, parse_email=True, callbacks=[no_email]))
def test_tlds():
eq_('<a href="http://example.com" rel="nofollow">example.com</a>',
linkify('example.com'))
eq_('<a href="http://example.co" rel="nofollow">example.co</a>',
linkify('example.co'))
eq_('<a href="http://example.co.uk" rel="nofollow">example.co.uk</a>',
linkify('example.co.uk'))
eq_('<a href="http://example.edu" rel="nofollow">example.edu</a>',
linkify('example.edu'))
eq_('<a href="http://example.xxx" rel="nofollow">example.xxx</a>',
linkify('example.xxx'))
eq_('example.yyy', linkify('example.yyy'))
eq_(' brie', linkify(' brie'))
eq_('<a href="http://bit.ly/fun" rel="nofollow">bit.ly/fun</a>',
linkify('bit.ly/fun'))
def test_escaping():
eq_('< unrelated', linkify('< unrelated'))
def test_nofollow_off():
eq_('<a href="http://example.com">example.com</a>',
linkify('example.com', []))
def test_link_in_html():
eq_('<i><a href="http://yy.com" rel="nofollow">http://yy.com</a></i>',
linkify('<i>http://yy.com</i>'))
eq_('<em><strong><a href="http://xx.com" rel="nofollow">http://xx.com'
'</a></strong></em>',
linkify('<em><strong>http://xx.com</strong></em>'))
def test_links_https():
eq_('<a href="https://yy.com" rel="nofollow">https://yy.com</a>',
linkify('https://yy.com'))
def test_add_rel_nofollow():
"""Verify that rel="nofollow" is added to an existing link"""
eq_('<a href="http://yy.com" rel="nofollow">http://yy.com</a>',
linkify('<a href="http://yy.com">http://yy.com</a>'))
def test_url_with_path():
eq_('<a href="http://example.com/path/to/file" rel="nofollow">'
'http://example.com/path/to/file</a>',
linkify('http://example.com/path/to/file'))
def test_link_ftp():
eq_('<a href="ftp://ftp.mozilla.org/some/file" rel="nofollow">'
'ftp://ftp.mozilla.org/some/file</a>',
linkify('ftp://ftp.mozilla.org/some/file'))
def test_link_query():
eq_('<a href="http://xx.com/?test=win" rel="nofollow">'
'http://xx.com/?test=win</a>',
linkify('http://xx.com/?test=win'))
eq_('<a href="http://xx.com/?test=win" rel="nofollow">'
'xx.com/?test=win</a>',
linkify('xx.com/?test=win'))
eq_('<a href="http://xx.com?test=win" rel="nofollow">'
'xx.com?test=win</a>',
linkify('xx.com?test=win'))
def test_link_fragment():
eq_('<a href="http://xx.com/path#frag" rel="nofollow">'
'http://xx.com/path#frag</a>',
linkify('http://xx.com/path#frag'))
def test_link_entities():
eq_('<a href="http://xx.com/?a=1&b=2" rel="nofollow">'
'http://xx.com/?a=1&b=2</a>',
linkify('http://xx.com/?a=1&b=2'))
def test_escaped_html():
"""If I pass in escaped HTML, it should probably come out escaped."""
s = '<em>strong</em>'
eq_(s, linkify(s))
def test_link_http_complete():
eq_('<a href="https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d'
'&e#f" rel="nofollow">'
'https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f</a>',
linkify('https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f'))
def test_non_url():
"""document.vulnerable should absolutely not be linkified."""
s = 'document.vulnerable'
eq_(s, linkify(s))
def test_javascript_url():
"""javascript: urls should never be linkified."""
s = 'javascript:document.vulnerable'
eq_(s, linkify(s))
def test_unsafe_url():
"""Any unsafe char ({}[]<>, etc.) in the path should end URL scanning."""
eq_('All your{"<a href="http://xx.yy.com/grover.png" '
'rel="nofollow">xx.yy.com/grover.png</a>"}base are',
linkify('All your{"xx.yy.com/grover.png"}base are'))
def test_skip_pre():
"""Skip linkification in <pre> tags."""
simple = 'http://xx.com <pre>http://xx.com</pre>'
linked = ('<a href="http://xx.com" rel="nofollow">http://xx.com</a> '
'<pre>http://xx.com</pre>')
all_linked = ('<a href="http://xx.com" rel="nofollow">http://xx.com</a> '
'<pre><a href="http://xx.com" rel="nofollow">http://xx.com'
'</a></pre>')
eq_(linked, linkify(simple, skip_pre=True))
eq_(all_linked, linkify(simple))
already_linked = '<pre><a href="http://xx.com">xx</a></pre>'
nofollowed = '<pre><a href="http://xx.com" rel="nofollow">xx</a></pre>'
eq_(nofollowed, linkify(already_linked))
eq_(nofollowed, linkify(already_linked, skip_pre=True))
def test_libgl():
"""libgl.so.1 should not be linkified."""
eq_('libgl.so.1', linkify('libgl.so.1'))
def test_end_of_sentence():
"""example.com. should match."""
out = '<a href="http://{0!s}" rel="nofollow">{0!s}</a>{1!s}'
intxt = '{0!s}{1!s}'
def check(u, p):
eq_(out.format(u, p),
linkify(intxt.format(u, p)))
tests = (
('example.com', '.'),
('example.com', '...'),
('ex.com/foo', '.'),
('ex.com/foo', '....'),
)
for u, p in tests:
yield check, u, p
def test_end_of_clause():
"""example.com/foo, shouldn't include the ,"""
eq_('<a href="http://ex.com/foo" rel="nofollow">ex.com/foo</a>, bar',
linkify('ex.com/foo, bar'))
def test_sarcasm():
"""Jokes should crash.<sarcasm/>"""
dirty = 'Yeah right <sarcasm/>'
clean = 'Yeah right <sarcasm/>'
eq_(clean, linkify(dirty))
def test_wrapping_parentheses():
"""URLs wrapped in parantheses should not include them."""
out = '{0!s}<a href="http://{1!s}" rel="nofollow">{2!s}</a>{3!s}'
tests = (
('(example.com)', ('(', 'example.com', 'example.com', ')')),
('(example.com/)', ('(', 'example.com/', 'example.com/', ')')),
('(example.com/foo)', ('(', 'example.com/foo',
'example.com/foo', ')')),
('(((example.com/))))', ('(((', 'example.com/)',
'example.com/)', ')))')),
('example.com/))', ('', 'example.com/))', 'example.com/))', '')),
('http://en.wikipedia.org/wiki/Test_(assessment)',
('', 'en.wikipedia.org/wiki/Test_(assessment)',
'http://en.wikipedia.org/wiki/Test_(assessment)', '')),
('(http://en.wikipedia.org/wiki/Test_(assessment))',
('(', 'en.wikipedia.org/wiki/Test_(assessment)',
'http://en.wikipedia.org/wiki/Test_(assessment)', ')')),
('((http://en.wikipedia.org/wiki/Test_(assessment))',
('((', 'en.wikipedia.org/wiki/Test_(assessment',
'http://en.wikipedia.org/wiki/Test_(assessment', '))')),
('(http://en.wikipedia.org/wiki/Test_(assessment)))',
('(', 'en.wikipedia.org/wiki/Test_(assessment))',
'http://en.wikipedia.org/wiki/Test_(assessment))', ')')),
('(http://en.wikipedia.org/wiki/)Test_(assessment',
('(', 'en.wikipedia.org/wiki/)Test_(assessment',
'http://en.wikipedia.org/wiki/)Test_(assessment', '')),
)
def check(test, expected_output):
eq_(out.format(*expected_output), linkify(test))
for test, expected_output in tests:
yield check, test, expected_output
def test_parentheses_with_removing():
expect = '(test.py)'
eq_(expect, linkify(expect, callbacks=[lambda *a: None]))
def test_ports():
"""URLs can contain port numbers."""
tests = (
('http://foo.com:8000', ('http://foo.com:8000', '')),
('http://foo.com:8000/', ('http://foo.com:8000/', '')),
('http://bar.com:xkcd', ('http://bar.com', ':xkcd')),
('http://foo.com:81/bar', ('http://foo.com:81/bar', '')),
('http://foo.com:', ('http://foo.com', ':')),
)
def check(test, output):
out = '<a href="{0}" rel="nofollow">{0}</a>{1}'
eq_(out.format(*output),
linkify(test))
for test, output in tests:
yield check, test, output
def test_tokenizer():
"""Linkify doesn't always have to sanitize."""
raw = '<em>test<x></x></em>'
eq_('<em>test<x></x></em>', linkify(raw))
eq_(raw, linkify(raw, tokenizer=HTMLTokenizer))
def test_ignore_bad_protocols():
eq_('foohttp://bar',
linkify('foohttp://bar'))
eq_('fohttp://<a href="http://exampl.com" rel="nofollow">exampl.com</a>',
linkify('fohttp://exampl.com'))
def test_max_recursion_depth():
"""If we hit the max recursion depth, just return the string."""
test = '<em>' * 2000 + 'foo' + '</em>' * 2000
eq_(test, linkify(test))
def test_link_emails_and_urls():
"""parse_email=True shouldn't prevent URLs from getting linkified."""
output = ('<a href="http://example.com" rel="nofollow">'
'http://example.com</a> <a href="mailto:person@example.com">'
'person@example.com</a>')
eq_(output, linkify('http://example.com person@example.com',
parse_email=True))
def test_links_case_insensitive():
"""Protocols and domain names are case insensitive."""
expect = ('<a href="HTTP://EXAMPLE.COM" rel="nofollow">'
'HTTP://EXAMPLE.COM</a>')
eq_(expect, linkify('HTTP://EXAMPLE.COM'))
def test_elements_inside_links():
eq_('<a href="#" rel="nofollow">hello<br></a>',
linkify('<a href="#">hello<br></a>'))
eq_('<a href="#" rel="nofollow"><strong>bold</strong> hello<br></a>',
linkify('<a href="#"><strong>bold</strong> hello<br></a>'))
def test_remove_first_childlink():
expect = '<p>something</p>'
callbacks = [lambda *a: None]
eq_(expect,
linkify('<p><a href="/foo">something</a></p>', callbacks=callbacks))
|