Initial (manual) import.

1 files changed, 42 insertions, 0 deletions

diff --git a/TODO b/TODO
new file mode 100644
index 0000000..84fa273
--- /dev/null
+++ b/TODO
@@ -0,0 +1,42 @@
+Here are some unit tests that fail with HTMLParser.
+
+    def testValidButBogusDeclarationFAILS(self):
+        self.assertSoupEquals('<! Foo >a', '<!Foo >a')
+
+    def testIncompleteDeclarationAtEndFAILS(self):
+        self.assertSoupEquals('a<!b')
+
+    def testIncompleteEntityAtEndFAILS(self):
+        self.assertSoupEquals('&lt;Hello&gt')
+
+        # This is not what the original author had in mind, but it's
+        # a legitimate interpretation of what they wrote.
+        self.assertSoupEquals("""<a href="foo</a>, </a><a href="bar">baz</a>""",
+        '<a href="foo&lt;/a&gt;, &lt;/a&gt;&lt;a href="></a>, <a href="bar">baz</a>')
+        # SGMLParser generates bogus parse events when attribute values
+        # contain embedded brackets, but at least Beautiful Soup fixes
+        # it up a little.
+        self.assertSoupEquals('<a b="<a>">', '<a b="&lt;a&gt;"></a><a>"></a>')
+        self.assertSoupEquals('<a href="http://foo.com/<a> and blah and blah',
+                              """<a href='"http://foo.com/'></a><a> and blah and blah</a>""")
+
+        invalidEntity = "foo&#bar;baz"
+        soup = BeautifulStoneSoup\
+               (invalidEntity,
+                convertEntities=htmlEnt)
+        self.assertEquals(str(soup), invalidEntity)
+
+
+Tag names that contain Unicode characters crash the parser:
+    def testUnicodeTagNamesFAILS(self):
+	self.assertSoupEquals("<デダ芻デダtext>2PM</デダ芻デダtext>")
+
+Here's the implementation of NavigableString.__unicode__:
+
+    def __unicode__(self):
+        return unicode(str(self))
+
+It converts the Unicode to a string, and then back to Unicode. I can't
+find any other way of turning an element of a Unicode subclass into a
+normal Unicode object. This is pretty bad and a better technique is
+welcome.