Source

features/pep-382-2 / Lib / test / test_htmlparser.py

Full commit
  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
"""Tests for HTMLParser.py."""

import html.parser
import pprint
import unittest
from test import support


class EventCollector(html.parser.HTMLParser):

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

    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))

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


class EventCollectorExtra(EventCollector):

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


class TestCaseBase(unittest.TestCase):

    def _run_check(self, source, expected_events, collector=None):
        if collector is None:
            collector = EventCollector()
        parser = collector
        for s in source:
            parser.feed(s)
        parser.close()
        events = parser.get_events()
        if events != expected_events:
            self.fail("received events did not match expected events\n"
                      "Expected:\n" + pprint.pformat(expected_events) +
                      "\nReceived:\n" + pprint.pformat(events))

    def _run_check_extra(self, source, events):
        self._run_check(source, events, EventCollectorExtra())

    def _parse_error(self, source):
        def parse(source=source):
            parser = html.parser.HTMLParser()
            parser.feed(source)
            parser.close()
        self.assertRaises(html.parser.HTMLParseError, parse)


class HTMLParserTestCase(TestCaseBase):

    def test_processing_instruction_only(self):
        self._run_check("<?processing instruction>", [
            ("pi", "processing instruction"),
            ])
        self._run_check("<?processing instruction ?>", [
            ("pi", "processing instruction ?"),
            ])

    def test_simple_html(self):
        self._run_check("""
<!DOCTYPE html PUBLIC 'foo'>
<HTML>&entity;&#32;
<!--comment1a
-></foo><bar>&lt;<?pi?></foo<bar
comment1b-->
<Img sRc='Bar' isMAP>sample
text
&#x201C;
<!--comment2a-- --comment2b--><!>
</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"),
    ("charref", "x201C"),
    ("data", "\n"),
    ("comment", "comment2a-- --comment2b"),
    ("data", "\n"),
    ("endtag", "html"),
    ("data", "\n"),
    ])

    def test_malformatted_charref(self):
        self._run_check("<p>&#bad;</p>", [
            ("starttag", "p", []),
            ("data", "&#bad;"),
            ("endtag", "p"),
        ])

    def test_unclosed_entityref(self):
        self._run_check("&entityref foo", [
            ("entityref", "entityref"),
            ("data", " foo"),
            ])

    def test_doctype_decl(self):
        inside = """\
DOCTYPE html [
  <!ELEMENT html - O EMPTY>
  <!ATTLIST html
      version CDATA #IMPLIED
      profile CDATA 'DublinCore'>
  <!NOTATION datatype SYSTEM 'http://xml.python.org/notations/python-module'>
  <!ENTITY myEntity 'internal parsed entity'>
  <!ENTITY anEntity SYSTEM 'http://xml.python.org/entities/something.xml'>
  <!ENTITY % paramEntity 'name|name|name'>
  %paramEntity;
  <!-- comment -->
]"""
        self._run_check("<!%s>" % inside, [
            ("decl", inside),
            ])

    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.
        self._run_check("<a><b></a></b>", [
            ("starttag", "a", []),
            ("starttag", "b", []),
            ("endtag", "a"),
            ("endtag", "b"),
            ])

    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"),
            ])

    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_illegal_declarations(self):
        self._parse_error('<!spacer type="block" height="25">')

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

    def test_buffer_artefacts(self):
        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)

        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)

    def test_starttag_junk_chars(self):
        self._parse_error("</>")
        self._parse_error("</$>")
        self._parse_error("</")
        self._parse_error("</a")
        self._parse_error("<a<a>")
        self._parse_error("</a<a>")
        self._parse_error("<!")
        self._parse_error("<a $>")
        self._parse_error("<a")
        self._parse_error("<a foo='bar'")
        self._parse_error("<a foo='bar")
        self._parse_error("<a foo='>'")
        self._parse_error("<a foo='>")
        self._parse_error("<a foo=>")

    def test_declaration_junk_chars(self):
        self._parse_error("<!DOCTYPE foo $ >")

    def test_startendtag(self):
        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"),
            ])

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

    def test_cdata_content(self):
        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)])


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


class HTMLParserTolerantTestCase(TestCaseBase):

    def get_collector(self):
        return EventCollector(strict=False)

    def test_tolerant_parsing(self):
        self._run_check('<html <html>te>>xt&a<<bc</a></html>\n'
                        '<img src="URL><//img></html</html>', [
                             ('data', '<html '),
                             ('starttag', 'html', []),
                             ('data', 'te>>xt'),
                             ('entityref', 'a'),
                             ('data', '<<bc'),
                             ('endtag', 'a'),
                             ('endtag', 'html'),
                             ('data', '\n<img src="URL><//img></html'),
                             ('endtag', 'html')],
                        collector=self.get_collector())

    def test_with_unquoted_attributes(self):
        # see #12008
        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')
        ]

        self._run_check(html, expected, collector=self.get_collector())

    def test_comma_between_attributes(self):
        self._run_check('<form action="/xxx.php?a=1&amp;b=2&amp", '
                        'method="post">', [
                            ('starttag', 'form',
                                [('action', '/xxx.php?a=1&b=2&amp'),
                                 ('method', 'post')])],
                        collector=self.get_collector())

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

    def test_correct_detection_of_start_tags(self):
        # see #13273
        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')
        ]
        self._run_check(html, expected, collector=self.get_collector())

        html = '<div style="", foo = "bar" ><b>The <a href="some_url">rain</a>'
        expected = [
            ('starttag', 'div', [('style', ''), ('foo', 'bar')]),
            ('starttag', 'b', []),
            ('data', 'The '),
            ('starttag', 'a', [('href', 'some_url')]),
            ('data', 'rain'),
            ('endtag', 'a'),
        ]
        self._run_check(html, expected, collector=self.get_collector())

    def test_unescape_function(self):
        p = html.parser.HTMLParser()
        self.assertEqual(p.unescape('&#bad;'),'&#bad;')
        self.assertEqual(p.unescape('&#0038;'),'&')
        # see #12888
        self.assertEqual(p.unescape('&#123; ' * 1050), '{ ' * 1050)

def test_main():
    support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase)


if __name__ == "__main__":
    test_main()