def handle_starttag(self, tag, attrs):
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types.keys():
target = attr_d.get(self.link_types[tag], "")
if target:
if "#" in target:
target = target[:target.index('#')]
self.process_link(target, tag, title)
elif tag == 'base':
self.base = attr_d.get('href', self.base)
elif tag == 'meta' and \
attr_d.get('http-equiv', '').lower() == 'content-type':
ct = attr_d.get('content', None)
if ct:
try:
media_type, params = ct.split(";", 1)
except ValueError:
media_type, params = ct, ''
media_type = media_type.lower()
param_dict = {}
for param in rh.split_string(
params, syntax.PARAMETER, "\s*;\s*"
):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = rh.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.doc_enc = param_dict.get('charset', self.doc_enc)
def handle_starttag(self, tag, attrs):
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types.keys():
target = attr_d.get(self.link_types[tag], "")
if target:
if "#" in target:
target = target[:target.index('#')]
self.process_link(target, tag, title)
elif tag == 'base':
self.base = attr_d.get('href', self.base)
elif tag == 'meta' and \
attr_d.get('http-equiv', '').lower() == 'content-type':
ct = attr_d.get('content', None)
if ct:
try:
media_type, params = ct.split(";", 1)
except ValueError:
media_type, params = ct, ''
media_type = media_type.lower()
param_dict = {}
for param in rh.split_string(params, syntax.PARAMETER,
"\s*;\s*"):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = rh.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.doc_enc = param_dict.get('charset', self.doc_enc)
def parse(subject, value, red):
try:
attr, attr_val = value.split("=", 1)
attr_val = rh.unquote_string(attr_val)
except ValueError:
attr = value
attr_val = None
return (attr.lower(), attr_val)
def parse(subject, value, red):
try:
attr, attr_val = value.split("=", 1)
attr_val = rh.unquote_string(attr_val)
except ValueError:
attr = value
attr_val = None
return (attr.lower(), attr_val)
def parse(subject, value, red):
try:
directive_name, directive_val = value.split("=", 1)
directive_val = rh.unquote_string(directive_val)
except ValueError:
directive_name = value
directive_val = None
directive_name = directive_name.lower()
# TODO: warn on upper-cased directives?
if directive_name in ['max-age', 's-maxage']:
try:
directive_val = int(directive_val)
except (ValueError, TypeError):
red.set_message(subject, rs.BAD_CC_SYNTAX,
bad_cc_attr=directive_name
)
return None
return (directive_name, directive_val)
def test_unquote_string(self):
i = 0
for (instr, expected_str, expected_msgs) in [
('foo', 'foo', []),
('"foo"', 'foo', []),
(r'"fo\"o"', 'fo"o', []),
(r'"f\"o\"o"', 'f"o"o', []),
(r'"fo\\o"', r'fo\o', []),
(r'"f\\o\\o"', r'f\o\o', []),
(r'"fo\o"', 'foo', []),
]:
self.red.__init__()
out_str = rh.unquote_string(unicode(instr))
diff = set([n.__name__ for n in expected_msgs
]).symmetric_difference(set(self.red.msg_classes))
self.assertEqual(len(diff), 0,
"[%s] Mismatched messages: %s" % (i, diff))
self.assertEqual(
expected_str, out_str,
"[%s] %s != %s" % (i, str(expected_str), str(out_str)))
i += 1
def test_unquote_string(self):
i = 0
for (instr, expected_str, expected_msgs) in [
('foo', 'foo', []),
('"foo"', 'foo', []),
(r'"fo\"o"', 'fo"o', []),
(r'"f\"o\"o"', 'f"o"o', []),
(r'"fo\\o"', r'fo\o', []),
(r'"f\\o\\o"', r'f\o\o', []),
(r'"fo\o"', 'foo', []),
]:
self.red.__init__()
out_str = rh.unquote_string(unicode(instr))
diff = set(
[n.__name__ for n in expected_msgs]).symmetric_difference(
set(self.red.msg_classes)
)
self.assertEqual(len(diff), 0,
"[%s] Mismatched messages: %s" % (i, diff)
)
self.assertEqual(expected_str, out_str,
"[%s] %s != %s" % (i, str(expected_str), str(out_str)))
i += 1
def parse(subject, value, red):
if value[:2] == 'W/':
return (True, rh.unquote_string(value[2:]))
else:
return (False, rh.unquote_string(value))
def parse(subject, value, red):
if value[:2] == 'W/':
return (True, rh.unquote_string(value[2:]))
else:
return (False, rh.unquote_string(value))
