def safe_join(base, *paths):
"""
Join one or more path components to the base path component intelligently.
Return a normalized, absolute version of the final path.
Raise ValueError if the final path isn't located inside of the base path
component.
"""
base = force_text(base)
paths = [force_text(p) for p in paths]
final_path = abspath(join(base, *paths))
base_path = abspath(base)
# Ensure final_path starts with base_path (using normcase to ensure we
# don't false-negative on case insensitive operating systems like Windows),
# further, one of the following conditions must be true:
# a) The next character is the path separator (to prevent conditions like
# safe_join("/dir", "/../d"))
# b) The final path must be the same as the base path.
# c) The base path must be the most root path (meaning either "/" or "C:\\")
if (not normcase(final_path).startswith(normcase(base_path + sep))
and normcase(final_path) != normcase(base_path)
and dirname(normcase(base_path)) != normcase(base_path)):
raise SuspiciousFileOperation(
'The joined path ({}) is located outside of the base path '
'component ({})'.format(final_path, base_path))
return final_path
def test_force_text_DjangoUnicodeDecodeError(self):
msg = (
"'utf-8' codec can't decode byte 0xff in position 0: invalid "
"start byte. You passed in b'\\xff' (<class 'bytes'>)"
)
with self.assertRaisesMessage(DjangoUnicodeDecodeError, msg):
force_text(b'\xff')
def test_force_text_exception(self):
"""
Broken __str__ actually raises an error.
"""
class MyString:
def __str__(self):
return b'\xc3\xb6\xc3\xa4\xc3\xbc'
# str(s) raises a TypeError if the result is not a text type.
with self.assertRaises(TypeError):
force_text(MyString())
def __init__(self, param, cursor, strings_only=False):
# With raw SQL queries, datetimes can reach this function
# without being converted by DateTimeField.get_db_prep_value.
if settings.USE_TZ and (isinstance(param, datetime.datetime)
and not isinstance(param, Oracle_datetime)):
param = Oracle_datetime.from_datetime(param)
string_size = 0
# Oracle doesn't recognize True and False correctly.
if param is True:
param = 1
elif param is False:
param = 0
if hasattr(param, 'bind_parameter'):
self.force_bytes = param.bind_parameter(cursor)
elif isinstance(param, (Database.Binary, datetime.timedelta)):
self.force_bytes = param
else:
# To transmit to the database, we need Unicode if supported
# To get size right, we must consider bytes.
self.force_bytes = force_text(param, cursor.charset, strings_only)
if isinstance(self.force_bytes, str):
# We could optimize by only converting up to 4000 bytes here
string_size = len(
force_bytes(param, cursor.charset, strings_only))
if hasattr(param, 'input_size'):
# If parameter has `input_size` attribute, use that.
self.input_size = param.input_size
elif string_size > 4000:
# Mark any string param greater than 4000 characters as a CLOB.
self.input_size = Database.CLOB
elif isinstance(param, datetime.datetime):
self.input_size = Database.TIMESTAMP
else:
self.input_size = None
def fields(self):
"Return a list of fields in the Feature."
return [
force_text(capi.get_field_name(
capi.get_field_defn(self._layer._ldefn, i)),
self.encoding,
strings_only=True) for i in range(self.num_fields)
]
def fields(self):
"""
Return a list of string names corresponding to each of the Fields
available in this Layer.
"""
return [force_text(capi.get_field_name(capi.get_field_defn(self._ldefn, i)),
self._ds.encoding, strings_only=True)
for i in range(self.num_fields)]
def units(self):
"""
Return a 2-tuple of the units value and the units name. Automatically
determine whether to return the linear or angular units.
"""
units, name = None, None
if self.projected or self.local:
units, name = capi.linear_units(self.ptr, byref(c_char_p()))
elif self.geographic:
units, name = capi.angular_units(self.ptr, byref(c_char_p()))
if name is not None:
name = force_text(name)
return (units, name)
def as_string(self):
"Retrieve the Field's value as a string."
string = capi.get_field_as_string(self._feat.ptr, self._index)
return force_text(string,
encoding=self._feat.encoding,
strings_only=True)
def name(self):
"""
Return the name of this raster. Corresponds to filename
for file-based rasters.
"""
return force_text(capi.get_ds_description(self._ptr))
def name(self):
"Return the name of this layer in the Data Source."
name = capi.get_fd_name(self._ldefn)
return force_text(name, self._ds.encoding, strings_only=True)
def __init__(self, geo_input, srid=None):
"""
The base constructor for GEOS geometry objects. It may take the
following inputs:
* strings:
- WKT
- HEXEWKB (a PostGIS-specific canonical form)
- GeoJSON (requires GDAL)
* buffer:
- WKB
The `srid` keyword specifies the Source Reference Identifier (SRID)
number for this Geometry. If not provided, it defaults to None.
"""
input_srid = None
if isinstance(geo_input, bytes):
geo_input = force_text(geo_input)
if isinstance(geo_input, str):
wkt_m = wkt_regex.match(geo_input)
if wkt_m:
# Handle WKT input.
if wkt_m.group('srid'):
input_srid = int(wkt_m.group('srid'))
g = self._from_wkt(force_bytes(wkt_m.group('wkt')))
elif hex_regex.match(geo_input):
# Handle HEXEWKB input.
g = wkb_r().read(force_bytes(geo_input))
elif json_regex.match(geo_input):
# Handle GeoJSON input.
ogr = gdal.OGRGeometry.from_json(geo_input)
g = ogr._geos_ptr()
input_srid = ogr.srid
else:
raise ValueError(
'String input unrecognized as WKT EWKT, and HEXEWKB.')
elif isinstance(geo_input, GEOM_PTR):
# When the input is a pointer to a geometry (GEOM_PTR).
g = geo_input
elif isinstance(geo_input, memoryview):
# When the input is a buffer (WKB).
g = wkb_r().read(geo_input)
elif isinstance(geo_input, GEOSGeometry):
g = capi.geom_clone(geo_input.ptr)
else:
raise TypeError('Improper geometry input type: %s' %
type(geo_input))
if not g:
raise GEOSException(
'Could not initialize GEOS Geometry with given input.')
input_srid = input_srid or capi.geos_get_srid(g) or None
if input_srid and srid and input_srid != srid:
raise ValueError('Input geometry already has SRID: %d.' %
input_srid)
super().__init__(g, None)
# Set the SRID, if given.
srid = input_srid or srid
if srid and isinstance(srid, int):
self.srid = srid
def name(self):
"""
Return description/name string for this driver.
"""
return force_text(rcapi.get_driver_description(self.ptr))
def convert_textfield_value(self, value, expression, connection):
if value is not None:
value = force_text(value)
return value
def last_executed_query(self, cursor, sql, params):
# With MySQLdb, cursor objects have an (undocumented) "_last_executed"
# attribute where the exact query sent to the database is saved.
# See MySQLdb/cursors.py in the source distribution.
return force_text(getattr(cursor, '_last_executed', None),
errors='replace')
def test_force_text_lazy(self):
s = SimpleLazyObject(lambda: 'x')
self.assertIs(type(force_text(s)), str)
def layer_name(self):
"Return the name of the layer for the feature."
name = capi.get_feat_name(self._layer._ldefn)
return force_text(name, self.encoding, strings_only=True)
def verify_ogr_field(self, ogr_field, model_field):
"""
Verify if the OGR Field contents are acceptable to the model field. If
they are, return the verified value, otherwise raise an exception.
"""
if (isinstance(ogr_field, OFTString)
and isinstance(model_field,
(models.CharField, models.TextField))):
if self.encoding:
# The encoding for OGR data sources may be specified here
# (e.g., 'cp437' for Census Bureau boundary files).
val = force_text(ogr_field.value, self.encoding)
else:
val = ogr_field.value
if model_field.max_length and len(val) > model_field.max_length:
raise InvalidString(
'%s model field maximum string length is %s, given %s characters.'
% (model_field.name, model_field.max_length, len(val)))
elif isinstance(ogr_field, OFTReal) and isinstance(
model_field, models.DecimalField):
try:
# Creating an instance of the Decimal value to use.
d = Decimal(str(ogr_field.value))
except DecimalInvalidOperation:
raise InvalidDecimal('Could not construct decimal from: %s' %
ogr_field.value)
# Getting the decimal value as a tuple.
dtup = d.as_tuple()
digits = dtup[1]
d_idx = dtup[2] # index where the decimal is
# Maximum amount of precision, or digits to the left of the decimal.
max_prec = model_field.max_digits - model_field.decimal_places
# Getting the digits to the left of the decimal place for the
# given decimal.
if d_idx < 0:
n_prec = len(digits[:d_idx])
else:
n_prec = len(digits) + d_idx
# If we have more than the maximum digits allowed, then throw an
# InvalidDecimal exception.
if n_prec > max_prec:
raise InvalidDecimal(
'A DecimalField with max_digits %d, decimal_places %d must '
'round to an absolute value less than 10^%d.' %
(model_field.max_digits, model_field.decimal_places,
max_prec))
val = d
elif isinstance(ogr_field, (OFTReal, OFTString)) and isinstance(
model_field, models.IntegerField):
# Attempt to convert any OFTReal and OFTString value to an OFTInteger.
try:
val = int(ogr_field.value)
except ValueError:
raise InvalidInteger('Could not construct integer from: %s' %
ogr_field.value)
else:
val = ogr_field.value
return val
def to_string(s):
return force_text(s, strings_only=True, errors='replace')
def name(self):
"Return the name of the data source."
name = capi.get_ds_name(self._ptr)
return force_text(name, self.encoding, strings_only=True)
def description(self):
"""
Return the description string of the band.
"""
return force_text(capi.get_band_description(self._ptr))
def name(self):
"Return the name of this Field."
name = capi.get_field_name(self.ptr)
return force_text(name,
encoding=self._feat.encoding,
strings_only=True)
