def decode_hex_string(string, raw=False):
'''
Takes a hex string (\\x..\\x..\\x..) as input and converts it back into
either an utf-8 formatted string or a raw bytes value.
Parameters:
string (string) Input hex string
raw (boolean) Return as bytes
Returns:
string (string/bytes) Decoded output
'''
plain = string.replace('\\x', '')
try:
b_array = bytearray.fromhex(plain)
except Exception:
raise VveException("Input is no valid hex string.")
if raw:
return bytes(b_array)
try:
return b_array.decode('utf-8')
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")
def decode_binary(string, raw=False):
'''
Takes a binary formatted string (containing only zeros and ones)
and tries to decode it as an utf-8 formatted string. Output can
also be obtained as raw bytes if raw=True.
Parameters:
string (string) Input binary string
raw (boolean) Return as bytes
Returns:
string (string/bytes) decoded output
'''
if re.search('[^01]', string):
raise VveException("Input string is not binary.")
b_array = bytearray()
for i in range(0, len(string), 8):
integer = int(string[i:i + 8], 2)
b_array.append(integer)
if raw:
return bytes(b_array)
try:
return b_array.decode('utf-8')
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")
def string_length_hex(string):
'''
A length function for hex inputs (plain 0x.. and \\x.. format).
Parameters:
string (string) input string
Returns:
None
'''
hex_format = _get_hex_format(string)
if hex_format == 'number':
length = len(string) // 2 - 1
elif hex_format == 'plain':
length = len(string) // 2
elif hex_format == 'formatted':
length = len(string) // 4
else:
raise VveException(f"Input string '{string}' is not in hex format.")
vim.command('redraw')
print(length)
def decode_ascii(string, raw=False):
'''
Opposite operation to encode_ascii. Searches for \\xXX sequences inside the input
string and converts them to their raw byte value. Afterwards, the whole string
is converted to bytes. If raw=True, this bytes object is returned. Otherwise, the
bytearray will be decoded as utf-8.
Paramaters:
string (string) Input string
raw (boolean) True -> type(output)=bytes
Returns:
decoded (string/bytes) Decoded output
'''
string = re.sub(r'\\x[0-9a-fA-F]{2}', _replace_hex, string)
decoded = encode_mixed(string)
if raw:
return decoded
try:
decoded = decoded.decode('utf-8')
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")
return decoded
def decode_html_full(string, raw=False):
'''
Applies HTML decoding to the input string.
Parameters:
string (string) Input string
raw (boolean) Return as bytes
Returns:
string (string/bytes) HTML decoded output
'''
string = re.sub(r'&#x[0-9a-fA-F]{2};', _replace_html_hex, string)
string = re.sub(r'&#[0-9]{1,6};', _replace_html_dec, string)
string = re.sub(r'&[a-zA-Z]+;', _replace_html_ent, string)
decoded = encode_mixed(string)
if raw:
return decoded
try:
decoded = decoded.decode('utf-8')
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")
return decoded
def decode_base64(string, raw=False):
'''
Takes a base64 input string and returns the decoded data. Padding
errors are corrected automatically (theoretically). Output can be
obtained as string or bytes depending on the value of raw.
Parameters:
string (string) Input string
raw (boolean) Return as bytes
Returns:
decoded (string/bytes) Base64 decoded data
'''
byte_form = string.encode('utf-8')
count = 0
while count < 3:
try:
decoded = base64.b64decode(byte_form, validate=True)
if raw:
return decoded
decoded = decoded.decode('utf-8')
break
except binascii.Error:
byte_form += b'='
decoded = string
count += 1
continue
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")
if count >= 3:
raise VveException("Input is no valid base64.")
return decoded
def encode_xml(string):
'''
Applies XML encoding to the input string for XML special characters.
Parameters:
string (string) Input string
Returns:
string (string) XML encoded output
'''
if isinstance(string, bytes):
raise VveException("XML encoding is only supported for UTF-8 data.")
return xml.sax.saxutils.escape(string)
def encode_html(string):
'''
Applies HTML encoding to special characrers inside the input string.
Parameters:
string (string) Input string
Returns:
string (string) HTML encoded output
'''
if isinstance(string, bytes):
raise VveException("HTML encoding is only supported for UTF-8 data.")
return html.escape(string)
def decode_hex(string, raw=False):
'''
Takes a stream of hex numbers (e.g. A01FE92...) and converts it, either
into an utf-8 formatted string or a raw bytes value.
Parameters:
string (string) Input hex stream
raw (boolean) Return as bytes
Returns:
string (string/bytes) UTF-8 formatted output
'''
try:
b_array = bytearray.fromhex(string)
except Exception:
raise VveException('Input is not in hex format.')
if raw:
return bytes(b_array)
try:
return b_array.decode('utf-8')
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")
def decode_url_full(string, raw=False):
'''
Applies URL decoding to the input string. Output can be obtained as
utf-8 string or raw byes.
Parameters:
string (string) Input string
raw (boolean) Return as bytes
Returns:
string (string/bytes) URL decoded output
'''
string = re.sub(r'%[0-9a-fA-F]{2}', _replace_url, string)
string = string.replace("+", " ")
decoded = encode_mixed(string)
if raw:
return decoded
try:
return decoded.decode('utf-8')
except Exception:
raise VveException("Decoded result cannot be encoded as UTF-8.")