def _encode_bytes(name, value, dummy0, dummy1):
"""Encode a python str (python 2.x)."""
try:
_utf_8_decode(value, None, True)
except UnicodeError:
raise InvalidStringData("strings in documents must be valid " "UTF-8: %r" % (value,))
return b"\x02" + name + _PACK_INT(len(value) + 1) + value + b"\x00"
def _encode_bytes(name, value, dummy0, dummy1):
"""Encode a python str (python 2.x)."""
try:
_utf_8_decode(value, None, True)
except UnicodeError:
raise InvalidStringData("strings in documents must be valid "
"UTF-8: %r" % (value, ))
return b"\x02" + name + _PACK_INT(len(value) + 1) + value + b"\x00"
def _make_c_string(string: Union[str, bytes]) -> bytes:
"""Make a 'C' string."""
if isinstance(string, bytes):
try:
_utf_8_decode(string, None, True)
return string + b"\x00"
except UnicodeError:
raise InvalidStringData("strings in documents must be valid UTF-8: %r" % string)
else:
return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
def _make_c_string(string):
"""Make a 'C' string."""
if isinstance(string, bytes):
try:
_utf_8_decode(string, None, True)
return string + b"\x00"
except UnicodeError:
raise InvalidStringData("strings in documents must be valid " "UTF-8: %r" % string)
else:
return _utf_8_encode(string)[0] + b"\x00"
def _make_c_string_check(string: Union[str, bytes]) -> bytes:
"""Make a 'C' string, checking for embedded NUL characters."""
if isinstance(string, bytes):
if b"\x00" in string:
raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
try:
_utf_8_decode(string, None, True)
return string + b"\x00"
except UnicodeError:
raise InvalidStringData("strings in documents must be valid UTF-8: %r" % string)
else:
if "\x00" in string:
raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
def _make_c_string_check(string):
"""Make a 'C' string, checking for embedded NUL characters."""
if isinstance(string, bytes):
if b"\x00" in string:
raise InvalidDocument("BSON keys / regex patterns must not " "contain a NUL character")
try:
_utf_8_decode(string, None, True)
return string + b"\x00"
except UnicodeError:
raise InvalidStringData("strings in documents must be valid " "UTF-8: %r" % string)
else:
if "\x00" in string:
raise InvalidDocument("BSON keys / regex patterns must not " "contain a NUL character")
return _utf_8_encode(string)[0] + b"\x00"
def _get_c_string(data, position, opts):
"""Decode a BSON 'C' string to python unicode string."""
if opts.use_unicode:
end = data.index(b"\x00", position)
return _utf_8_decode(data[position:end],
opts.unicode_decode_error_handler,
True)[0], end + 1
else:
return data[position:], len(data) - position
def _get_string(data, position, obj_end, dummy):
"""Decode a BSON string to python unicode string."""
length = _UNPACK_INT(data[position:position + 4])[0]
position += 4
if length < 1 or obj_end - position < length:
raise InvalidBSON("invalid string length")
end = position + length - 1
if data[end:end + 1] != b"\x00":
raise InvalidBSON("invalid end of string")
return _utf_8_decode(data[position:end], None, True)[0], end + 1
def _get_string(data, position, obj_end, dummy):
"""Decode a BSON string to python unicode string."""
length = _UNPACK_INT(data[position:position + 4])[0]
position += 4
if length < 1 or obj_end - position < length:
raise InvalidBSON("invalid string length")
end = position + length - 1
if data[end:end + 1] != b"\x00":
raise InvalidBSON("invalid end of string")
return _utf_8_decode(data[position:end], None, True)[0], end + 1
def _get_string(data, view, position, obj_end, opts, dummy):
"""Decode a BSON string to python unicode string."""
length = _UNPACK_INT_FROM(data, position)[0]
position += 4
if length < 1 or obj_end - position < length:
raise InvalidBSON("invalid string length")
end = position + length - 1
if data[end] != 0:
raise InvalidBSON("invalid end of string")
return _utf_8_decode(view[position:end], opts.unicode_decode_error_handler,
True)[0], end + 1
def _get_string(
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, dummy: Any
) -> Tuple[str, int]:
"""Decode a BSON string to python str."""
length = _UNPACK_INT_FROM(data, position)[0]
position += 4
if length < 1 or obj_end - position < length:
raise InvalidBSON("invalid string length")
end = position + length - 1
if data[end] != 0:
raise InvalidBSON("invalid end of string")
return _utf_8_decode(view[position:end], opts.unicode_decode_error_handler, True)[0], end + 1
def _get_string(data, position, obj_end, opts, dummy):
"""Decode a BSON string to python unicode string."""
length = _UNPACK_INT(data[position:position + 4])[0]
position += 4
if length < 1 or obj_end - position < length:
raise InvalidBSON("invalid string length")
if opts.use_unicode:
end = position + length - 1
if data[end:end + 1] != b"\x00":
raise InvalidBSON("invalid end of string")
return _utf_8_decode(data[position:end],
opts.unicode_decode_error_handler,
True)[0], end + 1
else:
return data[position:], len(data) - position
def _get_c_string(data, view, position, opts):
"""Decode a BSON 'C' string to python unicode string."""
end = data.index(b"\x00", position)
return _utf_8_decode(view[position:end], opts.unicode_decode_error_handler,
True)[0], end + 1
def _get_c_string(data, position):
"""Decode a BSON 'C' string to python unicode string."""
end = data.index(b"\x00", position)
return _utf_8_decode(data[position:end], None, True)[0], end + 1
def _get_c_string(data, position):
"""Decode a BSON 'C' string to python unicode string."""
end = data.index(b"\x00", position)
return _utf_8_decode(data[position:end], None, True)[0], end + 1
def _get_c_string(data, position, opts):
"""Decode a BSON 'C' string to python unicode string."""
end = data.index(b"\x00", position)
return _utf_8_decode(data[position:end],
opts.unicode_decode_error_handler, True)[0], end + 1
def _get_c_string(data: Any, view: Any, position: int, opts: CodecOptions) -> Tuple[str, int]:
"""Decode a BSON 'C' string to python str."""
end = data.index(b"\x00", position)
return _utf_8_decode(view[position:end], opts.unicode_decode_error_handler, True)[0], end + 1
