def encode_character(self, immune, char):
"""
Encodes a single character according to the spec at
U{W3.org<http://www.w3.org/TR/html401/interact/forms.html#h-17.13.4.1>}.
Spaces are replaced by '+'. All characters not in immune are escaped
as described in U{this document<http://tools.ietf.org/html/rfc3986#section-2.1>}.
"""
# check for immunes
if char in immune:
return char
if char == ' ':
return '+'
# Only look at 8-bit
if not codec.is_8bit(char):
return char
# Pass alphanumerics
if char.isalnum():
return char
hex_str = codec.get_hex_for_char(char).upper()
if ord(char) < 0x10:
hex_str = '0' + hex_str
return '%' + hex_str
def encode_character(self, immune, char):
"""
Encodes a character for safe use in an HTML entity field.
"""
# Check for immune
if char in immune:
return char
# Only look at 8-bit
if not codec.is_8bit(char):
return char
# Pass alphanumerics
if char.isalnum():
return char
# Check for illegal characters
if (codec.is_control_char(char) and char != "\t" and char != "\n"
and char != "\r"):
return " "
# Check if there's a defined entity
entity_name = self.entity_values_to_names.get(ord(char), None)
if entity_name is not None:
return "&" + entity_name + ";"
# Return the hex entity as suggested in the spec
hex_str = codec.get_hex_for_char(char).lower()
return "&#x" + hex_str + ";"
def encode_character(self, immune, char):
"""
Encodes a single character according to the spec at
U{W3.org<http://www.w3.org/TR/html401/interact/forms.html#h-17.13.4.1>}.
Spaces are replaced by '+'. All characters not in immune are escaped
as described in U{this document<http://tools.ietf.org/html/rfc3986#section-2.1>}.
"""
# check for immunes
if char in immune:
return char
if char == ' ':
return '+'
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
hex_str = codec.get_hex_for_char(ord_char).upper()
if ord_char < 0x10:
hex_str = '0' + hex_str
return '%' + hex_str
def encode_character(self, immune, char):
"""
Encodes a character for safe use in an HTML entity field.
"""
# Check for immune
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
# Check for illegal characters
if (codec.is_control_char(ord_char) and
char != "\t" and
char != "\n" and
char != "\r"):
return " "
# Check if there's a defined entity
entity_name = self.entity_values_to_names.get(ord_char, None)
if entity_name is not None:
return "&" + entity_name + ";"
# Return the hex entity as suggested in the spec
hex_str = codec.get_hex_for_char(ord_char).lower()
return "&#x" + hex_str + ";"
def encode_character(self, immune, char):
"""
Returns a backslash encoded numeric format. Does not use backslash
character escapes as these can be used in attacks.
"""
# Check for immunes
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
# encode up to 256 with \\xHH
temp = codec.get_hex_for_char(ord_char).upper()
if ord(char) < 256:
padding = '00'[len(temp):]
return u"\\x" + padding + temp
# otherwise encode with \\uHHHH
# Will never get here because 8-bit implies < 256
padding = '0000'[len(temp):]
return u"\\u" + padding + temp
def encode_character(self, immune, char):
"""
Returns a backslash encoded numeric format. Does not use backslash
character escapes as these can be used in attacks.
"""
# Check for immunes
if char in immune:
return char
# Only look at 8-bit
if not codec.is_8bit(char):
return char
# Pass alphanumerics
if char.isalnum():
return char
# encode up to 256 with \\xHH
temp = codec.get_hex_for_char(char).upper()
if ord(char) < 256:
padding = '00'[len(temp):]
return u"\\x" + padding + temp
# otherwise encode with \\uHHHH
# Will never get here because 8-bit implies < 256
padding = '0000'[len(temp):]
return u"\\u" + padding + temp
def encode_character(self, immune, char):
"""
Returns a quote-encoded character.
"""
# Check for immunes
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
if self.mode == MySQLCodec.MYSQL_MODE:
return self.encode_character_mysql(char, ord_char)
elif self.mode == MySQLCodec.ANSI_MODE:
return self.encode_character_ansi(char)
else:
raise BadModeError()
return None
def encode_character(self, immune, char):
"""
Returns backslash-encoded character
"""
# Check for immune
if char in immune:
return char
# Only look at 8-bit
if not codec.is_8bit(char):
return char
# Pass alphanumerics
if char.isalnum():
return char
return "\\" + char
def encode_character(self, immune, char):
"""
Returns a quote-encoded character.
"""
# Check for immunes
if char in immune:
return char
# Only look at 8-bit
if not codec.is_8bit(char):
return char
# Pass alphanumerics
if char.isalnum():
return char
return "chrw(" + str(ord(char)) + ")"
def encode_character(self, immune, char):
"""
Returns backslash-encoded character
"""
# Check for immune
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
return "\\" + char
def encode_character(self, immune, char):
"""
Encodes a character using CSS backslash style.
"""
# Check for immunes
if char in immune:
return char
# Only look at 8-bit
if not codec.is_8bit(char):
return char
# Pass alphanumerics
if char.isalnum():
return char
# Return the hex and end in whitespace to terminate
hex_str = codec.get_hex_for_char(char)
return "\\" + hex_str + " "
def encode_character(self, immune, char):
"""
Returns caret-encoded character.
"""
# Check for immune
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
return "^" + char
def encode_character(self, immune, char):
"""
Returns a quote-encoded character.
"""
# Check for immunes
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
return "chrw(" + str(ord_char) + ")"
def encode_character(self, immune, char):
"""
Encodes a character using CSS backslash style.
"""
# Check for immunes
if char in immune:
return char
ord_char = ord(char)
# Only look at 8-bit
if not codec.is_8bit(ord_char):
return char
# Pass alphanumerics
if char.isalnum():
return char
# Return the hex and end in whitespace to terminate
hex_str = codec.get_hex_for_char(ord_char)
return "\\" + hex_str + " "