summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_sgmllib.py
blob: 374b92130083eab434122bf3ab1d302d501a87fd (plain)
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
import pprint
import re
import sgmllib
import unittest
from test import test_support


class EventCollector(sgmllib.SGMLParser):

    def __init__(self):
        self.events = []
        self.append = self.events.append
        sgmllib.SGMLParser.__init__(self)

    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 unknown_starttag(self, tag, attrs):
        self.append(("starttag", tag, attrs))

    def unknown_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, decl):
        self.append(("decl", decl))

    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 CDATAEventCollector(EventCollector):
    def start_cdata(self, attrs):
        self.append(("starttag", "cdata", attrs))
        self.setliteral()


class HTMLEntityCollector(EventCollector):

    entity_or_charref = re.compile('(?:&([a-zA-Z][-.a-zA-Z0-9]*)'
        '|&#(x[0-9a-zA-Z]+|[0-9]+))(;?)')

    def convert_charref(self, name):
        self.append(("charref", "convert", name))
        if name[0] != "x":
            return EventCollector.convert_charref(self, name)

    def convert_codepoint(self, codepoint):
        self.append(("codepoint", "convert", codepoint))
        EventCollector.convert_codepoint(self, codepoint)

    def convert_entityref(self, name):
        self.append(("entityref", "convert", name))
        return EventCollector.convert_entityref(self, name)

    # These to record that they were called, then pass the call along
    # to the default implementation so that it's actions can be
    # recorded.

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

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


class SGMLParserTestCase(unittest.TestCase):

    collector = EventCollector

    def get_events(self, source):
        parser = self.collector()
        try:
            for s in source:
                parser.feed(s)
            parser.close()
        except:
            #self.events = parser.events
            raise
        return parser.get_events()

    def check_events(self, source, expected_events):
        try:
            events = self.get_events(source)
        except:
            #import sys
            #print >>sys.stderr, pprint.pformat(self.events)
            raise
        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 check_parse_error(self, source):
        parser = EventCollector()
        try:
            parser.feed(source)
            parser.close()
        except sgmllib.SGMLParseError:
            pass
        else:
            self.fail("expected SGMLParseError for %r\nReceived:\n%s"
                      % (source, pprint.pformat(parser.get_events())))

    def test_doctype_decl_internal(self):
        inside = """\
DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'
             SYSTEM 'http://www.w3.org/TR/html401/strict.dtd' [
  <!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.check_events(["<!%s>" % inside], [
            ("decl", inside),
            ])

    def test_doctype_decl_external(self):
        inside = "DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'"
        self.check_events("<!%s>" % inside, [
            ("decl", inside),
            ])

    def test_underscore_in_attrname(self):
        # SF bug #436621
        """Make sure attribute names with underscores are accepted"""
        self.check_events("<a has_under _under>", [
            ("starttag", "a", [("has_under", "has_under"),
                               ("_under", "_under")]),
            ])

    def test_underscore_in_tagname(self):
        # SF bug #436621
        """Make sure tag names with underscores are accepted"""
        self.check_events("<has_under></has_under>", [
            ("starttag", "has_under", []),
            ("endtag", "has_under"),
            ])

    def test_quotes_in_unquoted_attrs(self):
        # SF bug #436621
        """Be sure quotes in unquoted attributes are made part of the value"""
        self.check_events("<a href=foo'bar\"baz>", [
            ("starttag", "a", [("href", "foo'bar\"baz")]),
            ])

    def test_xhtml_empty_tag(self):
        """Handling of XHTML-style empty start tags"""
        self.check_events("<br />text<i></i>", [
            ("starttag", "br", []),
            ("data", "text"),
            ("starttag", "i", []),
            ("endtag", "i"),
            ])

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

    def test_bad_nesting(self):
        self.check_events("<a><b></a></b>", [
            ("starttag", "a", []),
            ("starttag", "b", []),
            ("endtag", "a"),
            ("endtag", "b"),
            ])

    def test_bare_ampersands(self):
        self.check_events("this text & contains & ampersands &", [
            ("data", "this text & contains & ampersands &"),
            ])

    def test_bare_pointy_brackets(self):
        self.check_events("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", "e")])
          ]
        self.check_events("""<a b='v' c="v" d=v e>""", output)
        self.check_events("""<a  b = 'v' c = "v" d = v e>""", output)
        self.check_events("""<a\nb\n=\n'v'\nc\n=\n"v"\nd\n=\nv\ne>""", output)
        self.check_events("""<a\tb\t=\t'v'\tc\t=\t"v"\td\t=\tv\te>""", output)

    def test_attr_values(self):
        self.check_events("""<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.check_events("""<a b='' c="">""", [
            ("starttag", "a", [("b", ""), ("c", "")]),
            ])
        # URL construction stuff from RFC 1808:
        safe = "$-_.+"
        extra = "!*'(),"
        reserved = ";/?:@&="
        url = "http://example.com:8080/path/to/file?%s%s%s" % (
            safe, extra, reserved)
        self.check_events("""<e a=%s>""" % url, [
            ("starttag", "e", [("a", url)]),
            ])
        # Regression test for SF patch #669683.
        self.check_events("<e a=rgb(1,2,3)>", [
            ("starttag", "e", [("a", "rgb(1,2,3)")]),
            ])

    def test_attr_values_entities(self):
        """Substitution of entities and charrefs in attribute values"""
        # SF bug #1452246
        self.check_events("""<a b=&lt; c=&lt;&gt; d=&lt-&gt; e='&lt; '
                                f="&xxx;" g='&#32;&#33;' h='&#500;'
                                i='x?a=b&c=d;'
                                j='&amp;#42;' k='&#38;#42;'>""",
            [("starttag", "a", [("b", "<"),
                                ("c", "<>"),
                                ("d", "&lt->"),
                                ("e", "< "),
                                ("f", "&xxx;"),
                                ("g", " !"),
                                ("h", "&#500;"),
                                ("i", "x?a=b&c=d;"),
                                ("j", "&#42;"),
                                ("k", "&#42;"),
                                ])])

    def test_convert_overrides(self):
        # This checks that the character and entity reference
        # conversion helpers are called at the documented times.  No
        # attempt is made to really change what the parser accepts.
        #
        self.collector = HTMLEntityCollector
        self.check_events(('<a title="&ldquo;test&#x201d;">foo</a>'
                           '&foobar;&#42;'), [
            ('entityref', 'convert', 'ldquo'),
            ('charref', 'convert', 'x201d'),
            ('starttag', 'a', [('title', '&ldquo;test&#x201d;')]),
            ('data', 'foo'),
            ('endtag', 'a'),
            ('entityref', 'foobar'),
            ('entityref', 'convert', 'foobar'),
            ('charref', '42'),
            ('charref', 'convert', '42'),
            ('codepoint', 'convert', 42),
            ])

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

    def test_attr_value_ip6_url(self):
        # http://www.python.org/sf/853506
        self.check_events(("<a href='http://[1080::8:800:200C:417A]/'>"
                           "<a href=http://[1080::8:800:200C:417A]/>"), [
            ("starttag", "a", [("href", "http://[1080::8:800:200C:417A]/")]),
            ("starttag", "a", [("href", "http://[1080::8:800:200C:417A]/")]),
            ])

    def test_illegal_declarations(self):
        s = 'abc<!spacer type="block" height="25">def'
        self.check_events(s, [
            ("data", "abc"),
            ("unknown decl", 'spacer type="block" height="25"'),
            ("data", "def"),
            ])

    def test_weird_starttags(self):
        self.check_events("<a<a>", [
            ("starttag", "a", []),
            ("starttag", "a", []),
            ])
        self.check_events("</a<a>", [
            ("endtag", "a"),
            ("starttag", "a", []),
            ])

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

    def test_get_starttag_text(self):
        s = """<foobar   \n   one="1"\ttwo=2   >"""
        self.check_events(s, [
            ("starttag", "foobar", [("one", "1"), ("two", "2")]),
            ])

    def test_cdata_content(self):
        s = ("<cdata> <!-- not a comment --> &not-an-entity-ref; </cdata>"
             "<notcdata> <!-- comment --> </notcdata>")
        self.collector = CDATAEventCollector
        self.check_events(s, [
            ("starttag", "cdata", []),
            ("data", " <!-- not a comment --> &not-an-entity-ref; "),
            ("endtag", "cdata"),
            ("starttag", "notcdata", []),
            ("data", " "),
            ("comment", " comment "),
            ("data", " "),
            ("endtag", "notcdata"),
            ])
        s = """<cdata> <not a='start tag'> </cdata>"""
        self.check_events(s, [
            ("starttag", "cdata", []),
            ("data", " <not a='start tag'> "),
            ("endtag", "cdata"),
            ])

    def test_illegal_declarations(self):
        s = 'abc<!spacer type="block" height="25">def'
        self.check_events(s, [
            ("data", "abc"),
            ("unknown decl", 'spacer type="block" height="25"'),
            ("data", "def"),
            ])

    def test_enumerated_attr_type(self):
        s = "<!DOCTYPE doc [<!ATTLIST doc attr (a | b) >]>"
        self.check_events(s, [
            ('decl', 'DOCTYPE doc [<!ATTLIST doc attr (a | b) >]'),
            ])

    def test_read_chunks(self):
        # SF bug #1541697, this caused sgml parser to hang
        # Just verify this code doesn't cause a hang.
        CHUNK = 1024  # increasing this to 8212 makes the problem go away

        f = open(test_support.findfile('sgml_input.html'), encoding="latin-1")
        fp = sgmllib.SGMLParser()
        while 1:
            data = f.read(CHUNK)
            fp.feed(data)
            if len(data) != CHUNK:
                break

    # XXX These tests have been disabled by prefixing their names with
    # an underscore.  The first two exercise outstanding bugs in the
    # sgmllib module, and the third exhibits questionable behavior
    # that needs to be carefully considered before changing it.

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

    def _test_buffer_artefacts(self):
        output = [("starttag", "a", [("b", "<")])]
        self.check_events(["<a b='<'>"], output)
        self.check_events(["<a ", "b='<'>"], output)
        self.check_events(["<a b", "='<'>"], output)
        self.check_events(["<a b=", "'<'>"], output)
        self.check_events(["<a b='<", "'>"], output)
        self.check_events(["<a b='<'", ">"], output)

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

        output = [("comment", "abc")]
        self.check_events(["", "<!--abc-->"], output)
        self.check_events(["<", "!--abc-->"], output)
        self.check_events(["<!", "--abc-->"], output)
        self.check_events(["<!-", "-abc-->"], output)
        self.check_events(["<!--", "abc-->"], output)
        self.check_events(["<!--a", "bc-->"], output)
        self.check_events(["<!--ab", "c-->"], output)
        self.check_events(["<!--abc", "-->"], output)
        self.check_events(["<!--abc-", "->"], output)
        self.check_events(["<!--abc--", ">"], output)
        self.check_events(["<!--abc-->", ""], output)

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


def test_main():
    test_support.run_unittest(SGMLParserTestCase)


if __name__ == "__main__":
    test_main()