test_htmlparser.py 31.9 KB
Newer Older
1 2
"""Tests for HTMLParser.py."""

3
import html.parser
4
import pprint
5 6 7
import unittest


8
class EventCollector(html.parser.HTMLParser):
9

10
    def __init__(self, *args, **kw):
11 12
        self.events = []
        self.append = self.events.append
13
        html.parser.HTMLParser.__init__(self, *args, **kw)
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

    def get_events(self):
        # Normalize the list of events so that buffer artefacts don't
        # separate runs of contiguous characters.
        L = []
        prevtype = None
        for event in self.events:
            type = event[0]
            if type == prevtype == "data":
                L[-1] = ("data", L[-1][1] + event[1])
            else:
                L.append(event)
            prevtype = type
        self.events = L
        return L

    # structure markup

    def handle_starttag(self, tag, attrs):
        self.append(("starttag", tag, attrs))

    def handle_startendtag(self, tag, attrs):
        self.append(("startendtag", tag, attrs))

    def handle_endtag(self, tag):
        self.append(("endtag", tag))

    # all other markup

    def handle_comment(self, data):
        self.append(("comment", data))

    def handle_charref(self, data):
        self.append(("charref", data))

    def handle_data(self, data):
        self.append(("data", data))

    def handle_decl(self, data):
        self.append(("decl", data))

    def handle_entityref(self, data):
        self.append(("entityref", data))

    def handle_pi(self, data):
        self.append(("pi", data))

61 62 63
    def unknown_decl(self, decl):
        self.append(("unknown decl", decl))

64 65 66 67 68 69 70 71

class EventCollectorExtra(EventCollector):

    def handle_starttag(self, tag, attrs):
        EventCollector.handle_starttag(self, tag, attrs)
        self.append(("starttag_text", self.get_starttag_text()))


72 73 74 75 76 77 78 79 80
class EventCollectorCharrefs(EventCollector):

    def handle_charref(self, data):
        self.fail('This should never be called with convert_charrefs=True')

    def handle_entityref(self, data):
        self.fail('This should never be called with convert_charrefs=True')


81 82
class TestCaseBase(unittest.TestCase):

83
    def get_collector(self):
84
        return EventCollector(convert_charrefs=False)
85

86 87
    def _run_check(self, source, expected_events, collector=None):
        if collector is None:
88
            collector = self.get_collector()
89
        parser = collector
90 91 92
        for s in source:
            parser.feed(s)
        parser.close()
93
        events = parser.get_events()
94
        if events != expected_events:
95 96 97
            self.fail("received events did not match expected events" +
                      "\nSource:\n" + repr(source) +
                      "\nExpected:\n" + pprint.pformat(expected_events) +
98
                      "\nReceived:\n" + pprint.pformat(events))
99 100

    def _run_check_extra(self, source, events):
101 102
        self._run_check(source, events,
                        EventCollectorExtra(convert_charrefs=False))
103

104

105
class HTMLParserTestCase(TestCaseBase):
106

107
    def test_processing_instruction_only(self):
108 109 110
        self._run_check("<?processing instruction>", [
            ("pi", "processing instruction"),
            ])
111 112 113
        self._run_check("<?processing instruction ?>", [
            ("pi", "processing instruction ?"),
            ])
114

115
    def test_simple_html(self):
116 117 118 119 120 121 122 123
        self._run_check("""
<!DOCTYPE html PUBLIC 'foo'>
<HTML>&entity;&#32;
<!--comment1a
-></foo><bar>&lt;<?pi?></foo<bar
comment1b-->
<Img sRc='Bar' isMAP>sample
text
124
&#x201C;
125
<!--comment2a-- --comment2b-->
126 127 128 129 130 131 132 133 134 135 136 137 138
</Html>
""", [
    ("data", "\n"),
    ("decl", "DOCTYPE html PUBLIC 'foo'"),
    ("data", "\n"),
    ("starttag", "html", []),
    ("entityref", "entity"),
    ("charref", "32"),
    ("data", "\n"),
    ("comment", "comment1a\n-></foo><bar>&lt;<?pi?></foo<bar\ncomment1b"),
    ("data", "\n"),
    ("starttag", "img", [("src", "Bar"), ("ismap", None)]),
    ("data", "sample\ntext\n"),
139 140
    ("charref", "x201C"),
    ("data", "\n"),
141 142 143 144 145 146
    ("comment", "comment2a-- --comment2b"),
    ("data", "\n"),
    ("endtag", "html"),
    ("data", "\n"),
    ])

147 148 149 150 151 152
    def test_malformatted_charref(self):
        self._run_check("<p>&#bad;</p>", [
            ("starttag", "p", []),
            ("data", "&#bad;"),
            ("endtag", "p"),
        ])
153 154 155 156 157 158
        # add the [] as a workaround to avoid buffering (see #20288)
        self._run_check(["<div>&#bad;</div>"], [
            ("starttag", "div", []),
            ("data", "&#bad;"),
            ("endtag", "div"),
        ])
159

160 161 162 163 164 165
    def test_unclosed_entityref(self):
        self._run_check("&entityref foo", [
            ("entityref", "entityref"),
            ("data", " foo"),
            ])

166 167 168 169
    def test_bad_nesting(self):
        # Strangely, this *is* supposed to test that overlapping
        # elements are allowed.  HTMLParser is more geared toward
        # lexing the input that parsing the structure.
170 171 172 173 174 175 176
        self._run_check("<a><b></a></b>", [
            ("starttag", "a", []),
            ("starttag", "b", []),
            ("endtag", "a"),
            ("endtag", "b"),
            ])

177 178 179 180 181 182 183 184 185 186
    def test_bare_ampersands(self):
        self._run_check("this text & contains & ampersands &", [
            ("data", "this text & contains & ampersands &"),
            ])

    def test_bare_pointy_brackets(self):
        self._run_check("this < text > contains < bare>pointy< brackets", [
            ("data", "this < text > contains < bare>pointy< brackets"),
            ])

187
    def test_starttag_end_boundary(self):
188 189 190
        self._run_check("""<a b='<'>""", [("starttag", "a", [("b", "<")])])
        self._run_check("""<a b='>'>""", [("starttag", "a", [("b", ">")])])

191
    def test_buffer_artefacts(self):
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
        output = [("starttag", "a", [("b", "<")])]
        self._run_check(["<a b='<'>"], output)
        self._run_check(["<a ", "b='<'>"], output)
        self._run_check(["<a b", "='<'>"], output)
        self._run_check(["<a b=", "'<'>"], output)
        self._run_check(["<a b='<", "'>"], output)
        self._run_check(["<a b='<'", ">"], output)

        output = [("starttag", "a", [("b", ">")])]
        self._run_check(["<a b='>'>"], output)
        self._run_check(["<a ", "b='>'>"], output)
        self._run_check(["<a b", "='>'>"], output)
        self._run_check(["<a b=", "'>'>"], output)
        self._run_check(["<a b='>", "'>"], output)
        self._run_check(["<a b='>'", ">"], output)

208 209 210 211 212 213 214 215 216 217 218 219 220
        output = [("comment", "abc")]
        self._run_check(["", "<!--abc-->"], output)
        self._run_check(["<", "!--abc-->"], output)
        self._run_check(["<!", "--abc-->"], output)
        self._run_check(["<!-", "-abc-->"], output)
        self._run_check(["<!--", "abc-->"], output)
        self._run_check(["<!--a", "bc-->"], output)
        self._run_check(["<!--ab", "c-->"], output)
        self._run_check(["<!--abc", "-->"], output)
        self._run_check(["<!--abc-", "->"], output)
        self._run_check(["<!--abc--", ">"], output)
        self._run_check(["<!--abc-->", ""], output)

221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
    def test_valid_doctypes(self):
        # from http://www.w3.org/QA/2002/04/valid-dtd-list.html
        dtds = ['HTML',  # HTML5 doctype
                ('HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
                 '"http://www.w3.org/TR/html4/strict.dtd"'),
                ('HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" '
                 '"http://www.w3.org/TR/html4/loose.dtd"'),
                ('html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" '
                 '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"'),
                ('html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" '
                 '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd"'),
                ('math PUBLIC "-//W3C//DTD MathML 2.0//EN" '
                 '"http://www.w3.org/Math/DTD/mathml2/mathml2.dtd"'),
                ('html PUBLIC "-//W3C//DTD '
                 'XHTML 1.1 plus MathML 2.0 plus SVG 1.1//EN" '
                 '"http://www.w3.org/2002/04/xhtml-math-svg/xhtml-math-svg.dtd"'),
                ('svg PUBLIC "-//W3C//DTD SVG 1.1//EN" '
                 '"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"'),
                'html PUBLIC "-//IETF//DTD HTML 2.0//EN"',
                'html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"']
        for dtd in dtds:
            self._run_check("<!DOCTYPE %s>" % dtd,
                            [('decl', 'DOCTYPE ' + dtd)])

245
    def test_startendtag(self):
246 247 248 249 250 251 252 253 254 255 256 257 258
        self._run_check("<p/>", [
            ("startendtag", "p", []),
            ])
        self._run_check("<p></p>", [
            ("starttag", "p", []),
            ("endtag", "p"),
            ])
        self._run_check("<p><img src='foo' /></p>", [
            ("starttag", "p", []),
            ("startendtag", "img", [("src", "foo")]),
            ("endtag", "p"),
            ])

259
    def test_get_starttag_text(self):
260 261 262 263 264
        s = """<foo:bar   \n   one="1"\ttwo=2   >"""
        self._run_check_extra(s, [
            ("starttag", "foo:bar", [("one", "1"), ("two", "2")]),
            ("starttag_text", s)])

265
    def test_cdata_content(self):
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
        contents = [
            '<!-- not a comment --> &not-an-entity-ref;',
            "<not a='start tag'>",
            '<a href="" /> <p> <span></span>',
            'foo = "</scr" + "ipt>";',
            'foo = "</SCRIPT" + ">";',
            'foo = <\n/script> ',
            '<!-- document.write("</scr" + "ipt>"); -->',
            ('\n//<![CDATA[\n'
             'document.write(\'<s\'+\'cript type="text/javascript" '
             'src="http://www.example.org/r=\'+new '
             'Date().getTime()+\'"><\\/s\'+\'cript>\');\n//]]>'),
            '\n<!-- //\nvar foo = 3.14;\n// -->\n',
            'foo = "</sty" + "le>";',
            '<!-- \u2603 -->',
            # these two should be invalid according to the HTML 5 spec,
            # section 8.1.2.2
            #'foo = </\nscript>',
            #'foo = </ script>',
        ]
        elements = ['script', 'style', 'SCRIPT', 'STYLE', 'Script', 'Style']
        for content in contents:
            for element in elements:
                element_lower = element.lower()
                s = '<{element}>{content}</{element}>'.format(element=element,
                                                               content=content)
                self._run_check(s, [("starttag", element_lower, []),
                                    ("data", content),
                                    ("endtag", element_lower)])

296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315
    def test_cdata_with_closing_tags(self):
        # see issue #13358
        # make sure that HTMLParser calls handle_data only once for each CDATA.
        # The normal event collector normalizes  the events in get_events,
        # so we override it to return the original list of events.
        class Collector(EventCollector):
            def get_events(self):
                return self.events

        content = """<!-- not a comment --> &not-an-entity-ref;
                  <a href="" /> </p><p> <span></span></style>
                  '</script' + '>'"""
        for element in [' script', 'script ', ' script ',
                        '\nscript', 'script\n', '\nscript\n']:
            element_lower = element.lower().strip()
            s = '<script>{content}</{element}>'.format(element=element,
                                                       content=content)
            self._run_check(s, [("starttag", element_lower, []),
                                ("data", content),
                                ("endtag", element_lower)],
316
                            collector=Collector(convert_charrefs=False))
317

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
    def test_comments(self):
        html = ("<!-- I'm a valid comment -->"
                '<!--me too!-->'
                '<!------>'
                '<!---->'
                '<!----I have many hyphens---->'
                '<!-- I have a > in the middle -->'
                '<!-- and I have -- in the middle! -->')
        expected = [('comment', " I'm a valid comment "),
                    ('comment', 'me too!'),
                    ('comment', '--'),
                    ('comment', ''),
                    ('comment', '--I have many hyphens--'),
                    ('comment', ' I have a > in the middle '),
                    ('comment', ' and I have -- in the middle! ')]
        self._run_check(html, expected)

335 336 337 338 339 340 341 342 343
    def test_condcoms(self):
        html = ('<!--[if IE & !(lte IE 8)]>aren\'t<![endif]-->'
                '<!--[if IE 8]>condcoms<![endif]-->'
                '<!--[if lte IE 7]>pretty?<![endif]-->')
        expected = [('comment', "[if IE & !(lte IE 8)]>aren't<![endif]"),
                    ('comment', '[if IE 8]>condcoms<![endif]'),
                    ('comment', '[if lte IE 7]>pretty?<![endif]')]
        self._run_check(html, expected)

344
    def test_convert_charrefs(self):
345 346
        # default value for convert_charrefs is now True
        collector = lambda: EventCollectorCharrefs()
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
        self.assertTrue(collector().convert_charrefs)
        charrefs = ['&quot;', '&#34;', '&#x22;', '&quot', '&#34', '&#x22']
        # check charrefs in the middle of the text/attributes
        expected = [('starttag', 'a', [('href', 'foo"zar')]),
                    ('data', 'a"z'), ('endtag', 'a')]
        for charref in charrefs:
            self._run_check('<a href="foo{0}zar">a{0}z</a>'.format(charref),
                            expected, collector=collector())
        # check charrefs at the beginning/end of the text/attributes
        expected = [('data', '"'),
                    ('starttag', 'a', [('x', '"'), ('y', '"X'), ('z', 'X"')]),
                    ('data', '"'), ('endtag', 'a'), ('data', '"')]
        for charref in charrefs:
            self._run_check('{0}<a x="{0}" y="{0}X" z="X{0}">'
                            '{0}</a>{0}'.format(charref),
                            expected, collector=collector())
        # check charrefs in <script>/<style> elements
        for charref in charrefs:
            text = 'X'.join([charref]*3)
            expected = [('data', '"'),
                        ('starttag', 'script', []), ('data', text),
                        ('endtag', 'script'), ('data', '"'),
                        ('starttag', 'style', []), ('data', text),
                        ('endtag', 'style'), ('data', '"')]
            self._run_check('{1}<script>{0}</script>{1}'
                            '<style>{0}</style>{1}'.format(text, charref),
                            expected, collector=collector())
        # check truncated charrefs at the end of the file
        html = '&quo &# &#x'
        for x in range(1, len(html)):
            self._run_check(html[:x], [('data', html[:x])],
                            collector=collector())
        # check a string with no charrefs
        self._run_check('no charrefs here', [('data', 'no charrefs here')],
                        collector=collector())

383 384
    # the remaining tests were for the "tolerant" parser (which is now
    # the default), and check various kind of broken markup
385 386 387
    def test_tolerant_parsing(self):
        self._run_check('<html <html>te>>xt&a<<bc</a></html>\n'
                        '<img src="URL><//img></html</html>', [
388 389 390
                            ('starttag', 'html', [('<html', None)]),
                            ('data', 'te>>xt'),
                            ('entityref', 'a'),
391 392
                            ('data', '<'),
                            ('starttag', 'bc<', [('a', None)]),
393
                            ('endtag', 'html'),
394 395 396
                            ('data', '\n<img src="URL>'),
                            ('comment', '/img'),
                            ('endtag', 'html<')])
397

398 399 400 401 402
    def test_starttag_junk_chars(self):
        self._run_check("</>", [])
        self._run_check("</$>", [('comment', '$')])
        self._run_check("</", [('data', '</')])
        self._run_check("</a", [('data', '</a')])
403
        self._run_check("<a<a>", [('starttag', 'a<a', [])])
404 405 406 407 408 409 410
        self._run_check("</a<a>", [('endtag', 'a<a')])
        self._run_check("<!", [('data', '<!')])
        self._run_check("<a", [('data', '<a')])
        self._run_check("<a foo='bar'", [('data', "<a foo='bar'")])
        self._run_check("<a foo='bar", [('data', "<a foo='bar")])
        self._run_check("<a foo='>'", [('data', "<a foo='>'")])
        self._run_check("<a foo='>", [('data', "<a foo='>")])
411 412 413 414 415
        self._run_check("<a$>", [('starttag', 'a$', [])])
        self._run_check("<a$b>", [('starttag', 'a$b', [])])
        self._run_check("<a$b/>", [('startendtag', 'a$b', [])])
        self._run_check("<a$b  >", [('starttag', 'a$b', [])])
        self._run_check("<a$b  />", [('startendtag', 'a$b', [])])
416

417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436
    def test_slashes_in_starttag(self):
        self._run_check('<a foo="var"/>', [('startendtag', 'a', [('foo', 'var')])])
        html = ('<img width=902 height=250px '
                'src="/sites/default/files/images/homepage/foo.jpg" '
                '/*what am I doing here*/ />')
        expected = [(
            'startendtag', 'img',
            [('width', '902'), ('height', '250px'),
             ('src', '/sites/default/files/images/homepage/foo.jpg'),
             ('*what', None), ('am', None), ('i', None),
             ('doing', None), ('here*', None)]
        )]
        self._run_check(html, expected)
        html = ('<a / /foo/ / /=/ / /bar/ / />'
                '<a / /foo/ / /=/ / /bar/ / >')
        expected = [
            ('startendtag', 'a', [('foo', None), ('=', None), ('bar', None)]),
            ('starttag', 'a', [('foo', None), ('=', None), ('bar', None)])
        ]
        self._run_check(html, expected)
437 438 439 440 441 442 443 444 445 446
        #see issue #14538
        html = ('<meta><meta / ><meta // ><meta / / >'
                '<meta/><meta /><meta //><meta//>')
        expected = [
            ('starttag', 'meta', []), ('starttag', 'meta', []),
            ('starttag', 'meta', []), ('starttag', 'meta', []),
            ('startendtag', 'meta', []), ('startendtag', 'meta', []),
            ('startendtag', 'meta', []), ('startendtag', 'meta', []),
        ]
        self._run_check(html, expected)
447

448
    def test_declaration_junk_chars(self):
449
        self._run_check("<!DOCTYPE foo $ >", [('decl', 'DOCTYPE foo $ ')])
450 451 452 453 454

    def test_illegal_declarations(self):
        self._run_check('<!spacer type="block" height="25">',
                        [('comment', 'spacer type="block" height="25"')])

Ezio Melotti's avatar
Ezio Melotti committed
455
    def test_with_unquoted_attributes(self):
456
        # see #12008
Ezio Melotti's avatar
Ezio Melotti committed
457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476
        html = ("<html><body bgcolor=d0ca90 text='181008'>"
                "<table cellspacing=0 cellpadding=1 width=100% ><tr>"
                "<td align=left><font size=-1>"
                "- <a href=/rabota/><span class=en> software-and-i</span></a>"
                "- <a href='/1/'><span class=en> library</span></a></table>")
        expected = [
            ('starttag', 'html', []),
            ('starttag', 'body', [('bgcolor', 'd0ca90'), ('text', '181008')]),
            ('starttag', 'table',
                [('cellspacing', '0'), ('cellpadding', '1'), ('width', '100%')]),
            ('starttag', 'tr', []),
            ('starttag', 'td', [('align', 'left')]),
            ('starttag', 'font', [('size', '-1')]),
            ('data', '- '), ('starttag', 'a', [('href', '/rabota/')]),
            ('starttag', 'span', [('class', 'en')]), ('data', ' software-and-i'),
            ('endtag', 'span'), ('endtag', 'a'),
            ('data', '- '), ('starttag', 'a', [('href', '/1/')]),
            ('starttag', 'span', [('class', 'en')]), ('data', ' library'),
            ('endtag', 'span'), ('endtag', 'a'), ('endtag', 'table')
        ]
477
        self._run_check(html, expected)
Ezio Melotti's avatar
Ezio Melotti committed
478

479 480 481 482
    def test_comma_between_attributes(self):
        self._run_check('<form action="/xxx.php?a=1&amp;b=2&amp", '
                        'method="post">', [
                            ('starttag', 'form',
483
                                [('action', '/xxx.php?a=1&b=2&'),
484
                                 (',', None), ('method', 'post')])])
485 486 487 488

    def test_weird_chars_in_unquoted_attribute_values(self):
        self._run_check('<form action=bogus|&#()value>', [
                            ('starttag', 'form',
489
                                [('action', 'bogus|&#()value')])])
490

491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528
    def test_invalid_end_tags(self):
        # A collection of broken end tags. <br> is used as separator.
        # see http://www.w3.org/TR/html5/tokenization.html#end-tag-open-state
        # and #13993
        html = ('<br></label</p><br></div end tmAd-leaderBoard><br></<h4><br>'
                '</li class="unit"><br></li\r\n\t\t\t\t\t\t</ul><br></><br>')
        expected = [('starttag', 'br', []),
                    # < is part of the name, / is discarded, p is an attribute
                    ('endtag', 'label<'),
                    ('starttag', 'br', []),
                    # text and attributes are discarded
                    ('endtag', 'div'),
                    ('starttag', 'br', []),
                    # comment because the first char after </ is not a-zA-Z
                    ('comment', '<h4'),
                    ('starttag', 'br', []),
                    # attributes are discarded
                    ('endtag', 'li'),
                    ('starttag', 'br', []),
                    # everything till ul (included) is discarded
                    ('endtag', 'li'),
                    ('starttag', 'br', []),
                    # </> is ignored
                    ('starttag', 'br', [])]
        self._run_check(html, expected)

    def test_broken_invalid_end_tag(self):
        # This is technically wrong (the "> shouldn't be included in the 'data')
        # but is probably not worth fixing it (in addition to all the cases of
        # the previous test, it would require a full attribute parsing).
        # see #13993
        html = '<b>This</b attr=">"> confuses the parser'
        expected = [('starttag', 'b', []),
                    ('data', 'This'),
                    ('endtag', 'b'),
                    ('data', '"> confuses the parser')]
        self._run_check(html, expected)

529 530
    def test_correct_detection_of_start_tags(self):
        # see #13273
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548
        html = ('<div style=""    ><b>The <a href="some_url">rain</a> '
                '<br /> in <span>Spain</span></b></div>')
        expected = [
            ('starttag', 'div', [('style', '')]),
            ('starttag', 'b', []),
            ('data', 'The '),
            ('starttag', 'a', [('href', 'some_url')]),
            ('data', 'rain'),
            ('endtag', 'a'),
            ('data', ' '),
            ('startendtag', 'br', []),
            ('data', ' in '),
            ('starttag', 'span', []),
            ('data', 'Spain'),
            ('endtag', 'span'),
            ('endtag', 'b'),
            ('endtag', 'div')
        ]
549
        self._run_check(html, expected)
550 551 552

        html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>'
        expected = [
553
            ('starttag', 'div', [('style', ''), (',', None), ('foo', 'bar')]),
554 555 556 557 558 559
            ('starttag', 'b', []),
            ('data', 'The '),
            ('starttag', 'a', [('href', 'some_url')]),
            ('data', 'rain'),
            ('endtag', 'a'),
        ]
560
        self._run_check(html, expected)
561

562 563 564 565 566 567 568 569 570 571 572 573 574 575
    def test_EOF_in_charref(self):
        # see #17802
        # This test checks that the UnboundLocalError reported in the issue
        # is not raised, however I'm not sure the returned values are correct.
        # Maybe HTMLParser should use self.unescape for these
        data = [
            ('a&', [('data', 'a&')]),
            ('a&b', [('data', 'ab')]),
            ('a&b ', [('data', 'a'), ('entityref', 'b'), ('data', ' ')]),
            ('a&b;', [('data', 'a'), ('entityref', 'b')]),
        ]
        for html, expected in data:
            self._run_check(html, expected)

576 577 578 579 580 581 582
    def test_unescape_method(self):
        from html import unescape
        p = self.get_collector()
        with self.assertWarns(DeprecationWarning):
            s = '&quot;&#34;&#x22;&quot&#34&#x22&#bad;'
            self.assertEqual(p.unescape(s), unescape(s))

583 584 585 586
    def test_broken_comments(self):
        html = ('<! not really a comment >'
                '<! not a comment either -->'
                '<! -- close enough -->'
587
                '<!><!<-- this was an empty comment>'
588 589 590 591 592
                '<!!! another bogus comment !!!>')
        expected = [
            ('comment', ' not really a comment '),
            ('comment', ' not a comment either --'),
            ('comment', ' -- close enough --'),
593 594
            ('comment', ''),
            ('comment', '<-- this was an empty comment'),
595 596 597 598
            ('comment', '!! another bogus comment !!!'),
        ]
        self._run_check(html, expected)

599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631
    def test_broken_condcoms(self):
        # these condcoms are missing the '--' after '<!' and before the '>'
        html = ('<![if !(IE)]>broken condcom<![endif]>'
                '<![if ! IE]><link href="favicon.tiff"/><![endif]>'
                '<![if !IE 6]><img src="firefox.png" /><![endif]>'
                '<![if !ie 6]><b>foo</b><![endif]>'
                '<![if (!IE)|(lt IE 9)]><img src="mammoth.bmp" /><![endif]>')
        # According to the HTML5 specs sections "8.2.4.44 Bogus comment state"
        # and "8.2.4.45 Markup declaration open state", comment tokens should
        # be emitted instead of 'unknown decl', but calling unknown_decl
        # provides more flexibility.
        # See also Lib/_markupbase.py:parse_declaration
        expected = [
            ('unknown decl', 'if !(IE)'),
            ('data', 'broken condcom'),
            ('unknown decl', 'endif'),
            ('unknown decl', 'if ! IE'),
            ('startendtag', 'link', [('href', 'favicon.tiff')]),
            ('unknown decl', 'endif'),
            ('unknown decl', 'if !IE 6'),
            ('startendtag', 'img', [('src', 'firefox.png')]),
            ('unknown decl', 'endif'),
            ('unknown decl', 'if !ie 6'),
            ('starttag', 'b', []),
            ('data', 'foo'),
            ('endtag', 'b'),
            ('unknown decl', 'endif'),
            ('unknown decl', 'if (!IE)|(lt IE 9)'),
            ('startendtag', 'img', [('src', 'mammoth.bmp')]),
            ('unknown decl', 'endif')
        ]
        self._run_check(html, expected)

632 633 634 635 636 637 638 639 640 641 642 643
    def test_convert_charrefs_dropped_text(self):
        # #23144: make sure that all the events are triggered when
        # convert_charrefs is True, even if we don't call .close()
        parser = EventCollector(convert_charrefs=True)
        # before the fix, bar & baz was missing
        parser.feed("foo <a>link</a> bar &amp; baz")
        self.assertEqual(
            parser.get_events(),
            [('data', 'foo '), ('starttag', 'a', []), ('data', 'link'),
             ('endtag', 'a'), ('data', ' bar & baz')]
        )

644

645
class AttributesTestCase(TestCaseBase):
646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701

    def test_attr_syntax(self):
        output = [
          ("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)])
        ]
        self._run_check("""<a b='v' c="v" d=v e>""", output)
        self._run_check("""<a  b = 'v' c = "v" d = v e>""", output)
        self._run_check("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)
        self._run_check("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)

    def test_attr_values(self):
        self._run_check("""<a b='xxx\n\txxx' c="yyy\t\nyyy" d='\txyz\n'>""",
                        [("starttag", "a", [("b", "xxx\n\txxx"),
                                            ("c", "yyy\t\nyyy"),
                                            ("d", "\txyz\n")])])
        self._run_check("""<a b='' c="">""",
                        [("starttag", "a", [("b", ""), ("c", "")])])
        # Regression test for SF patch #669683.
        self._run_check("<e a=rgb(1,2,3)>",
                        [("starttag", "e", [("a", "rgb(1,2,3)")])])
        # Regression test for SF bug #921657.
        self._run_check(
            "<a href=mailto:xyz@example.com>",
            [("starttag", "a", [("href", "mailto:xyz@example.com")])])

    def test_attr_nonascii(self):
        # see issue 7311
        self._run_check(
            "<img src=/foo/bar.png alt=\u4e2d\u6587>",
            [("starttag", "img", [("src", "/foo/bar.png"),
                                  ("alt", "\u4e2d\u6587")])])
        self._run_check(
            "<a title='\u30c6\u30b9\u30c8' href='\u30c6\u30b9\u30c8.html'>",
            [("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
                                ("href", "\u30c6\u30b9\u30c8.html")])])
        self._run_check(
            '<a title="\u30c6\u30b9\u30c8" href="\u30c6\u30b9\u30c8.html">',
            [("starttag", "a", [("title", "\u30c6\u30b9\u30c8"),
                                ("href", "\u30c6\u30b9\u30c8.html")])])

    def test_attr_entity_replacement(self):
        self._run_check(
            "<a b='&amp;&gt;&lt;&quot;&apos;'>",
            [("starttag", "a", [("b", "&><\"'")])])

    def test_attr_funky_names(self):
        self._run_check(
            "<a a.b='v' c:d=v e-f=v>",
            [("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")])])

    def test_entityrefs_in_attributes(self):
        self._run_check(
            "<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>",
            [("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])])


702 703
    def test_attr_funky_names2(self):
        self._run_check(
704
            r"<a $><b $=%><c \=/>",
705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
            [("starttag", "a", [("$", None)]),
             ("starttag", "b", [("$", "%")]),
             ("starttag", "c", [("\\", "/")])])

    def test_entities_in_attribute_value(self):
        # see #1200313
        for entity in ['&', '&amp;', '&#38;', '&#x26;']:
            self._run_check('<a href="%s">' % entity,
                            [("starttag", "a", [("href", "&")])])
            self._run_check("<a href='%s'>" % entity,
                            [("starttag", "a", [("href", "&")])])
            self._run_check("<a href=%s>" % entity,
                            [("starttag", "a", [("href", "&")])])

    def test_malformed_attributes(self):
        # see #13357
        html = (
            "<a href=test'style='color:red;bad1'>test - bad1</a>"
            "<a href=test'+style='color:red;ba2'>test - bad2</a>"
            "<a href=test'&nbsp;style='color:red;bad3'>test - bad3</a>"
            "<a href = test'&nbsp;style='color:red;bad4'  >test - bad4</a>"
        )
        expected = [
            ('starttag', 'a', [('href', "test'style='color:red;bad1'")]),
            ('data', 'test - bad1'), ('endtag', 'a'),
            ('starttag', 'a', [('href', "test'+style='color:red;ba2'")]),
            ('data', 'test - bad2'), ('endtag', 'a'),
            ('starttag', 'a', [('href', "test'\xa0style='color:red;bad3'")]),
            ('data', 'test - bad3'), ('endtag', 'a'),
            ('starttag', 'a', [('href', "test'\xa0style='color:red;bad4'")]),
            ('data', 'test - bad4'), ('endtag', 'a')
        ]
        self._run_check(html, expected)

    def test_malformed_adjacent_attributes(self):
        # see #12629
        self._run_check('<x><y z=""o"" /></x>',
                        [('starttag', 'x', []),
                            ('startendtag', 'y', [('z', ''), ('o""', None)]),
                            ('endtag', 'x')])
        self._run_check('<x><y z="""" /></x>',
                        [('starttag', 'x', []),
                            ('startendtag', 'y', [('z', ''), ('""', None)]),
                            ('endtag', 'x')])

    # see #755670 for the following 3 tests
    def test_adjacent_attributes(self):
        self._run_check('<a width="100%"cellspacing=0>',
                        [("starttag", "a",
                          [("width", "100%"), ("cellspacing","0")])])

        self._run_check('<a id="foo"class="bar">',
                        [("starttag", "a",
                          [("id", "foo"), ("class","bar")])])

    def test_missing_attribute_value(self):
        self._run_check('<a v=>',
                        [("starttag", "a", [("v", "")])])

    def test_javascript_attribute_value(self):
        self._run_check("<a href=javascript:popup('/popup/help.html')>",
                        [("starttag", "a",
                          [("href", "javascript:popup('/popup/help.html')")])])

    def test_end_tag_in_attribute_value(self):
        # see #1745761
        self._run_check("<a href='http://www.example.org/\">;'>spam</a>",
                        [("starttag", "a",
                          [("href", "http://www.example.org/\">;")]),
                         ("data", "spam"), ("endtag", "a")])


777
if __name__ == "__main__":
778
    unittest.main()