def handle_starttag(self, tag, attrs):
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types.keys():
url_attr, rels = self.link_types[tag]
if not rels or attr_d.get("rel", None) in rels:
target = attr_d.get(url_attr, "")
if target:
if "#" in target:
target = target[:target.index('#')]
for proc in self.link_procs:
proc(self.base, 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: str, attrs: List[Tuple[str, str]]) -> None:
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types:
url_attr, rels = self.link_types[tag]
if not rels or attr_d.get("rel", None) in rels:
target = attr_d.get(url_attr, "")
if target:
if "#" in target:
target = target[:target.index('#')]
for proc in self.link_procs:
proc(self.message.base_uri, target, tag, title)
elif tag == 'base':
self.message.base_uri = attr_d.get('href', self.message.base_uri)
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 headers.split_string(params, rfc7231.parameter,
r"\s*;\s*"):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = headers.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.message.character_encoding = param_dict.get(
'charset', self.message.character_encoding)
def handle_starttag(self, tag: str, attrs: List[Tuple[str, str]]) -> None:
attr_d = dict(attrs)
title = attr_d.get('title', '').strip()
if tag in self.link_types:
url_attr, rels = self.link_types[tag]
if not rels or attr_d.get("rel", None) in rels:
target = attr_d.get(url_attr, "")
if target:
if "#" in target:
target = target[:target.index('#')]
for proc in self.link_procs:
proc(self.message.base_uri, target, tag, title)
elif tag == 'base':
self.message.base_uri = attr_d.get('href', self.message.base_uri)
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 headers.split_string(params, rfc7231.parameter, r"\s*;\s*"):
try:
a, v = param.split("=", 1)
param_dict[a.lower()] = headers.unquote_string(v)
except ValueError:
param_dict[param.lower()] = None
self.message.character_encoding = param_dict.get('charset',
self.message.character_encoding)
def parse(self, field_value: str, add_note: AddNoteMethodType) -> Tuple[str, str]:
try:
attr, attr_val = field_value.split("=", 1)
attr_val = headers.unquote_string(attr_val)
except ValueError:
attr = field_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(self, field_value: str,
add_note: AddNoteMethodType) -> Tuple[str, str]:
try:
attr, attr_val = field_value.split("=", 1)
attr_val = headers.unquote_string(attr_val)
except ValueError:
attr = field_value
attr_val = None
return (attr.lower(), attr_val)
def test_unquote_string(self):
i = 0
for (instr, expected_str, expected_notes) 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', []),
]:
out_str = headers.unquote_string(str(instr))
self.assertEqual(expected_str, out_str,
"[%s] %s != %s" % (i, str(expected_str), str(out_str)))
i += 1
def parse(self, field_value: str, add_note: AddNoteMethodType) -> Tuple[str, str]:
try:
directive_name, directive_val = field_value.split("=", 1)
directive_val = headers.unquote_string(directive_val)
except ValueError:
directive_name = field_value
directive_val = None
directive_name = directive_name.lower()
if directive_name in ["max-age", "s-maxage"]:
try:
directive_val = int(directive_val) # type: ignore
except (ValueError, TypeError):
add_note(BAD_CC_SYNTAX, bad_cc_attr=directive_name)
raise ValueError
return (directive_name, directive_val)
def test_unquote_string(self):
i = 0
for (instr, expected_str, expected_notes) 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', []),
]:
out_str = headers.unquote_string(str(instr))
self.assertEqual(
expected_str, out_str,
"[%s] %s != %s" % (i, str(expected_str), str(out_str)))
i += 1
def parse(self, field_value: str,
add_note: AddNoteMethodType) -> Tuple[str, str]:
try:
directive_name, directive_val = field_value.split("=", 1)
directive_val = headers.unquote_string(directive_val)
except ValueError:
directive_name = field_value
directive_val = None
directive_name = directive_name.lower()
if directive_name in ['max-age', 's-maxage']:
try:
directive_val = int(directive_val) # type: ignore
except (ValueError, TypeError):
add_note(BAD_CC_SYNTAX, bad_cc_attr=directive_name)
raise ValueError
return (directive_name, directive_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.add_note(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_notes) 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 = headers.unquote_string(unicode(instr))
diff = set(
[n.__name__ for n in expected_notes]).symmetric_difference(
set(self.red.note_classes)
)
self.assertEqual(len(diff), 0,
"[%s] Mismatched notes: %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(self, field_value: str,
add_note: AddNoteMethodType) -> Tuple[bool, str]:
if field_value[:2] == 'W/':
return (True, headers.unquote_string(field_value[2:]))
else:
return (False, headers.unquote_string(field_value))
def parse(self, field_value: str, add_note: AddNoteMethodType) -> Tuple[bool, str]:
if field_value[:2] == 'W/':
return (True, headers.unquote_string(field_value[2:]))
else:
return (False, headers.unquote_string(field_value))