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
|
"""Tests for HTMLParser.py."""
import HTMLParser
import pprint
import sys
import test_support
import unittest
class EventCollector(HTMLParser.HTMLParser):
def __init__(self):
self.events = []
self.append = self.events.append
HTMLParser.HTMLParser.__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 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))
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):
# Constant pieces of source and events
prologue = ""
epilogue = ""
initial_events = []
final_events = []
def _run_check(self, source, events, collector=EventCollector):
parser = collector()
parser.feed(self.prologue)
for s in source:
parser.feed(s)
for c in self.epilogue:
parser.feed(c)
parser.close()
events = parser.get_events()
self.assertEqual(events,
self.initial_events + events + self.final_events,
"got events:\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 = HTMLParser.HTMLParser()
parser.feed(source)
parser.close()
self.assertRaises(HTMLParser.HTMLParseError, parse)
class HTMLParserTestCase(TestCaseBase):
def test_processing_instruction_only(self):
self._run_check("<?processing instruction>", [
("pi", "processing instruction"),
])
def test_simple_html(self):
self._run_check("""
<!DOCTYPE html PUBLIC 'foo'>
<HTML>&entity; 
<!--comment1a
-></foo><bar><<?pi?></foo<bar
comment1b-->
<Img sRc='Bar' isMAP>sample
text
“
<!--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><<?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_doctype_decl(self):
inside = """\
DOCTYPE html [
<!ELEMENT html - O EMPTY>
<!ATTLIST html
version CDATA #IMPLIED '4.0'>
<!-- 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", "")]),
])
def test_attr_entity_replacement(self):
self._run_check("""<a b='&><"''>""", [
("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_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)
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):
s = """<script> <!-- not a comment --> ¬-an-entity-ref; </script>"""
self._run_check(s, [
("starttag", "script", []),
("data", " <!-- not a comment --> ¬-an-entity-ref; "),
("endtag", "script"),
])
s = """<script> <not a='start tag'> </script>"""
self._run_check(s, [
("starttag", "script", []),
("data", " <not a='start tag'> "),
("endtag", "script"),
])
test_support.run_unittest(HTMLParserTestCase)
|
