import sys
import os
import re
import functools
import itertools
import warnings
import weakref
import contextlib
from operator import itemgetter, index as opindex
from collections.abc import Mapping
import numpy as np
from . import format
from ._datasource import DataSource
from numpy.core import overrides
from numpy.core.multiarray import packbits, unpackbits
from numpy.core.overrides import set_module
from numpy.core._internal import recursive
from ._iotools import (
LineSplitter, NameValidator, StringConverter, ConverterError,
ConverterLockError, ConversionWarning, _is_string_like,
has_nested_fields, flatten_dtype, easy_dtype, _decode_line
)
from numpy.compat import (
asbytes, asstr, asunicode, bytes, os_fspath, os_PathLike,
pickle, contextlib_nullcontext
)
@set_module('numpy')
def loads(*args, **kwargs):
# NumPy 1.15.0, 2017-12-10
warnings.warn(
"np.loads is deprecated, use pickle.loads instead",
DeprecationWarning, stacklevel=2)
return pickle.loads(*args, **kwargs)
__all__ = [
'savetxt', 'loadtxt', 'genfromtxt', 'ndfromtxt', 'mafromtxt',
'recfromtxt', 'recfromcsv', 'load', 'loads', 'save', 'savez',
'savez_compressed', 'packbits', 'unpackbits', 'fromregex', 'DataSource'
]
array_function_dispatch = functools.partial(
overrides.array_function_dispatch, module='numpy')
class BagObj:
"""
BagObj(obj)
Convert attribute look-ups to getitems on the object passed in.
Parameters
----------
obj : class instance
Object on which attribute look-up is performed.
Examples
--------
>>> from numpy.lib.npyio import BagObj as BO
>>> class BagDemo:
... def __getitem__(self, key): # An instance of BagObj(BagDemo)
... # will call this method when any
... # attribute look-up is required
... result = "Doesn't matter what you want, "
... return result + "you're gonna get this"
...
>>> demo_obj = BagDemo()
>>> bagobj = BO(demo_obj)
>>> bagobj.hello_there
"Doesn't matter what you want, you're gonna get this"
>>> bagobj.I_can_be_anything
"Doesn't matter what you want, you're gonna get this"
"""
def __init__(self, obj):
# Use weakref to make NpzFile objects collectable by refcount
self._obj = weakref.proxy(obj)
def __getattribute__(self, key):
try:
return object.__getattribute__(self, '_obj')[key]
except KeyError:
raise AttributeError(key)
def __dir__(self):
"""
Enables dir(bagobj) to list the files in an NpzFile.
This also enables tab-completion in an interpreter or IPython.
"""
return list(object.__getattribute__(self, '_obj').keys())
def zipfile_factory(file, *args, **kwargs):
"""
Create a ZipFile.
Allows for Zip64, and the `file` argument can accept file, str, or
pathlib.Path objects. `args` and `kwargs` are passed to the zipfile.ZipFile
constructor.
"""
if not hasattr(file, 'read'):
file = os_fspath(file)
import zipfile
kwargs['allowZip64'] = True
return zipfile.ZipFile(file, *args, **kwargs)
class NpzFile(Mapping):
"""
NpzFile(fid)
A dictionary-like object with lazy-loading of files in the zipped
archive provided on construction.
`NpzFile` is used to load files in the NumPy ``.npz`` data archive
format. It assumes that files in the archive have a ``.npy`` extension,
other files are ignored.
The arrays and file strings are lazily loaded on either
getitem access using ``obj['key']`` or attribute lookup using
``obj.f.key``. A list of all files (without ``.npy`` extensions) can
be obtained with ``obj.files`` and the ZipFile object itself using
``obj.zip``.
Attributes
----------
files : list of str
List of all files in the archive with a ``.npy`` extension.
zip : ZipFile instance
The ZipFile object initialized with the zipped archive.
f : BagObj instance
An object on which attribute can be performed as an alternative
to getitem access on the `NpzFile` instance itself.
allow_pickle : bool, optional
Allow loading pickled data. Default: False
.. versionchanged:: 1.16.3
Made default False in response to CVE-2019-6446.
pickle_kwargs : dict, optional
Additional keyword arguments to pass on to pickle.load.
These are only useful when loading object arrays saved on
Python 2 when using Python 3.
Parameters
----------
fid : file or str
The zipped archive to open. This is either a file-like object
or a string containing the path to the archive.
own_fid : bool, optional
Whether NpzFile should close the file handle.
Requires that `fid` is a file-like object.
Examples
--------
>>> from tempfile import TemporaryFile
>>> outfile = TemporaryFile()
>>> x = np.arange(10)
>>> y = np.sin(x)
>>> np.savez(outfile, x=x, y=y)
>>> _ = outfile.seek(0)
>>> npz = np.load(outfile)
>>> isinstance(npz, np.lib.io.NpzFile)
True
>>> sorted(npz.files)
['x', 'y']
>>> npz['x'] # getitem access
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
>>> npz.f.x # attribute lookup
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
"""
def __init__(self, fid, own_fid=False, allow_pickle=False,
pickle_kwargs=None):
# Import is postponed to here since zipfile depends on gzip, an
# optional component of the so-called standard library.
_zip = zipfile_factory(fid)
self._files = _zip.namelist()
self.files = []
self.allow_pickle = allow_pickle
self.pickle_kwargs = pickle_kwargs
for x in self._files:
if x.endswith('.npy'):
self.files.append(x[:-4])
else:
self.files.append(x)
self.zip = _zip
self.f = BagObj(self)
if own_fid:
self.fid = fid
else:
self.fid = None
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
def close(self):
"""
Close the file.
"""
if self.zip is not None:
self.zip.close()
self.zip = None
if self.fid is not None:
self.fid.close()
self.fid = None
self.f = None # break reference cycle
def __del__(self):
self.close()
# Implement the Mapping ABC
def __iter__(self):
return iter(self.files)
def __len__(self):
return len(self.files)
def __getitem__(self, key):
# FIXME: This seems like it will copy strings around
# more than is strictly necessary. The zipfile
# will read the string and then
# the format.read_array will copy the string
# to another place in memory.
# It would be better if the zipfile could read
# (or at least uncompress) the data
# directly into the array memory.
member = False
if key in self._files:
member = True
elif key in self.files:
member = True
key += '.npy'
if member:
bytes = self.zip.open(key)
magic = bytes.read(len(format.MAGIC_PREFIX))
bytes.close()
if magic == format.MAGIC_PREFIX:
bytes = self.zip.open(key)
return format.read_array(bytes,
allow_pickle=self.allow_pickle,
pickle_kwargs=self.pickle_kwargs)
else:
return self.zip.read(key)
else:
raise KeyError("%s is not a file in the archive" % key)
# deprecate the python 2 dict apis that we supported by accident in
# python 3. We forgot to implement itervalues() at all in earlier
# versions of numpy, so no need to deprecated it here.
def iteritems(self):
# Numpy 1.15, 2018-02-20
warnings.warn(
"NpzFile.iteritems is deprecated in python 3, to match the "
"removal of dict.itertems. Use .items() instead.",
DeprecationWarning, stacklevel=2)
return self.items()
def iterkeys(self):
# Numpy 1.15, 2018-02-20
warnings.warn(
"NpzFile.iterkeys is deprecated in python 3, to match the "
"removal of dict.iterkeys. Use .keys() instead.",
DeprecationWarning, stacklevel=2)
return self.keys()
@set_module('numpy')
def load(file, mmap_mode=None, allow_pickle=False, fix_imports=True,
encoding='ASCII'):
"""
Load arrays or pickled objects from ``.npy``, ``.npz`` or pickled files.
.. warning:: Loading files that contain object arrays uses the ``pickle``
module, which is not secure against erroneous or maliciously
constructed data. Consider passing ``allow_pickle=False`` to
load data that is known not to contain object arrays for the
safer handling of untrusted sources.
Parameters
----------
file : file-like object, string, or pathlib.Path
The file to read. File-like objects must support the
``seek()`` and ``read()`` methods. Pickled files require that the
file-like object support the ``readline()`` method as well.
mmap_mode : {None, 'r+', 'r', 'w+', 'c'}, optional
If not None, then memory-map the file, using the given mode (see
`numpy.memmap` for a detailed description of the modes). A
memory-mapped array is kept on disk. However, it can be accessed
and sliced like any ndarray. Memory mapping is especially useful
for accessing small fragments of large files without reading the
entire file into memory.
allow_pickle : bool, optional
Allow loading pickled object arrays stored in npy files. Reasons for
disallowing pickles include security, as loading pickled data can
execute arbitrary code. If pickles are disallowed, loading object
arrays will fail. Default: False
.. versionchanged:: 1.16.3
Made default False in response to CVE-2019-6446.
fix_imports : bool, optional
Only useful when loading Python 2 generated pickled files on Python 3,
which includes npy/npz files containing object arrays. If `fix_imports`
is True, pickle will try to map the old Python 2 names to the new names
used in Python 3.
encoding : str, optional
What encoding to use when reading Python 2 strings. Only useful when
loading Python 2 generated pickled files in Python 3, which includes
npy/npz files containing object arrays. Values other than 'latin1',
'ASCII', and 'bytes' are not allowed, as they can corrupt numerical
data. Default: 'ASCII'
Returns
-------
result : array, tuple, dict, etc.
Data stored in the file. For ``.npz`` files, the returned instance
of NpzFile class must be closed to avoid leaking file descriptors.
Raises
------
IOError
If the input file does not exist or cannot be read.
ValueError
The file contains an object array, but allow_pickle=False given.
See Also
--------
save, savez, savez_compressed, loadtxt
memmap : Create a memory-map to an array stored in a file on disk.
Loading ...