diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 0f3cf801faa..e0e212c27a5 100755
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -100,12 +100,12 @@ class TestCaseBase(unittest.TestCase):
class HTMLParserTestCase(TestCaseBase):
- def check_processing_instruction_only(self):
+ def test_processing_instruction_only(self):
self._run_check("", [
("pi", "processing instruction"),
])
- def check_simple_html(self):
+ def test_simple_html(self):
self._run_check("""
&entity;
@@ -114,6 +114,7 @@ class HTMLParserTestCase(TestCaseBase):
comment1b-->
sample
text
+“
""", [
@@ -128,13 +129,18 @@ text
("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 check_bad_nesting(self):
+ 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("", [
("starttag", "a", []),
("starttag", "b", []),
@@ -142,7 +148,7 @@ text
("endtag", "b"),
])
- def check_attr_syntax(self):
+ def test_attr_syntax(self):
output = [
("starttag", "a", [("b", "v"), ("c", "v"), ("d", "v"), ("e", None)])
]
@@ -151,7 +157,7 @@ text
self._run_check("""""", output)
self._run_check("""""", output)
- def check_attr_values(self):
+ def test_attr_values(self):
self._run_check("""""",
[("starttag", "a", [("b", "xxx\n\txxx"),
("c", "yyy\t\nyyy"),
@@ -161,21 +167,21 @@ text
("starttag", "a", [("b", ""), ("c", "")]),
])
- def check_attr_entity_replacement(self):
+ def test_attr_entity_replacement(self):
self._run_check("""""", [
("starttag", "a", [("b", "&><\"'")]),
])
- def check_attr_funky_names(self):
+ def test_attr_funky_names(self):
self._run_check("""""", [
("starttag", "a", [("a.b", "v"), ("c:d", "v"), ("e-f", "v")]),
])
- def check_starttag_end_boundary(self):
+ def test_starttag_end_boundary(self):
self._run_check("""""", [("starttag", "a", [("b", "<")])])
self._run_check("""""", [("starttag", "a", [("b", ">")])])
- def check_buffer_artefacts(self):
+ def test_buffer_artefacts(self):
output = [("starttag", "a", [("b", "<")])]
self._run_check([""], output)
self._run_check([""], output)
@@ -192,7 +198,7 @@ text
self._run_check([""], output)
self._run_check([""], output)
- def check_starttag_junk_chars(self):
+ def test_starttag_junk_chars(self):
self._parse_error("<")
self._parse_error("<>")
self._parse_error("")
@@ -212,10 +218,10 @@ text
self._parse_error("