def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters_for_re = []
# &apos is an XHTML entity and an HTML 5, but not an HTML 4
# entity. We don't want to use it, but we want to recognize it on the way in.
#
# TODO: Ideally we would be able to recognize all HTML 5 named
# entities, but that's a little tricky.
extra = [(39, 'apos')]
for codepoint, name in list(codepoint2name.items()) + extra:
character = unichr(codepoint)
if codepoint not in (34, 39):
# There's no point in turning the quotation mark into
# " or the single quote into ', unless it
# happens within an attribute value, which is handled
# elsewhere.
characters_for_re.append(character)
lookup[character] = name
# But we do want to recognize those entities on the way in and
# convert them to Unicode characters.
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters = []
for codepoint, name in codepoint2name.items():
if codepoint == 34:
# There's no point in turning the quotation mark into
# ", unless it happens within an attribute value, which
# is handled elsewhere.
continue
character = unichr(codepoint)
characters.append(character)
lookup[character] = name
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters)
return lookup, reverse_lookup, re.compile(re_definition)
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters = []
for codepoint, name in list(codepoint2name.items()):
if codepoint == 34:
# There's no point in turning the quotation mark into
# ", unless it happens within an attribute value, which
# is handled elsewhere.
continue
character = unichr(codepoint)
characters.append(character)
lookup[character] = name
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters)
return lookup, reverse_lookup, re.compile(re_definition)
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters_for_re = []
for codepoint, name in list(codepoint2name.items()):
character = unichr(codepoint)
if codepoint != 34:
# There's no point in turning the quotation mark into
# ", unless it happens within an attribute value, which
# is handled elsewhere.
characters_for_re.append(character)
lookup[character] = name
# But we do want to turn " into the quotation mark.
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
def _populate_class_variables(self):
lookup = {}
reverse_lookup = {}
characters_for_re = []
for codepoint, name in list(codepoint2name.items()):
character = unichr(codepoint)
if codepoint != 34:
# There's no point in turning the quotation mark into
# ", unless it happens within an attribute value, which
# is handled elsewhere.
characters_for_re.append(character)
lookup[character] = name
# But we do want to turn " into the quotation mark.
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters_for_re = []
for codepoint, name in list(codepoint2name.items()):
character = unichr(codepoint)
if codepoint != 34:
characters_for_re.append(character)
lookup[character] = name
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
def encode_htmlentities(string, encoding="utf-8"):
"""
Encodes the string with html entities.
"""
if isinstance(string, unicode):
was_unicode = True
else:
was_unicode = False
string = string.decode(encoding)
string = string.replace("&", "&")
for codepoint, name in cp2n.items():
if name != "amp":
string = string.replace(unichr(codepoint), "&%s;" % name)
if not was_unicode:
string = string.encode(encoding)
return string
