diff options
Diffstat (limited to 'numpy/lib/npyio.py')
| -rw-r--r-- | numpy/lib/npyio.py | 556 |
1 files changed, 282 insertions, 274 deletions
diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py index 3414ecd81..0a284d78f 100644 --- a/numpy/lib/npyio.py +++ b/numpy/lib/npyio.py @@ -7,6 +7,7 @@ import functools import itertools import warnings import weakref +import contextlib from operator import itemgetter, index as opindex import numpy as np @@ -23,7 +24,8 @@ from ._iotools import ( ) from numpy.compat import ( - asbytes, asstr, asunicode, bytes, basestring, os_fspath, os_PathLike, pickle + asbytes, asstr, asunicode, bytes, basestring, os_fspath, os_PathLike, + pickle, contextlib_nullcontext ) if sys.version_info[0] >= 3: @@ -144,7 +146,11 @@ class NpzFile(Mapping): 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: True + 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 @@ -180,7 +186,7 @@ class NpzFile(Mapping): """ - def __init__(self, fid, own_fid=False, allow_pickle=True, + 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. @@ -283,7 +289,7 @@ class NpzFile(Mapping): @set_module('numpy') -def load(file, mmap_mode=None, allow_pickle=True, fix_imports=True, +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. @@ -311,8 +317,11 @@ def load(file, mmap_mode=None, allow_pickle=True, fix_imports=True, 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: True + 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` @@ -1732,300 +1741,299 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None, byte_converters = False # Initialize the filehandle, the LineSplitter and the NameValidator - own_fhd = False try: if isinstance(fname, os_PathLike): fname = os_fspath(fname) if isinstance(fname, basestring): - fhd = iter(np.lib._datasource.open(fname, 'rt', encoding=encoding)) - own_fhd = True + fid = np.lib._datasource.open(fname, 'rt', encoding=encoding) + fid_ctx = contextlib.closing(fid) else: - fhd = iter(fname) + fid = fname + fid_ctx = contextlib_nullcontext(fid) + fhd = iter(fid) except TypeError: raise TypeError( "fname must be a string, filehandle, list of strings, " "or generator. Got %s instead." % type(fname)) - split_line = LineSplitter(delimiter=delimiter, comments=comments, - autostrip=autostrip, encoding=encoding) - validate_names = NameValidator(excludelist=excludelist, - deletechars=deletechars, - case_sensitive=case_sensitive, - replace_space=replace_space) + with fid_ctx: + split_line = LineSplitter(delimiter=delimiter, comments=comments, + autostrip=autostrip, encoding=encoding) + validate_names = NameValidator(excludelist=excludelist, + deletechars=deletechars, + case_sensitive=case_sensitive, + replace_space=replace_space) - # Skip the first `skip_header` rows - for i in range(skip_header): - next(fhd) + # Skip the first `skip_header` rows + for i in range(skip_header): + next(fhd) - # Keep on until we find the first valid values - first_values = None - try: - while not first_values: - first_line = _decode_line(next(fhd), encoding) - if (names is True) and (comments is not None): - if comments in first_line: - first_line = ( - ''.join(first_line.split(comments)[1:])) - first_values = split_line(first_line) - except StopIteration: - # return an empty array if the datafile is empty - first_line = '' - first_values = [] - warnings.warn('genfromtxt: Empty input file: "%s"' % fname, stacklevel=2) - - # Should we take the first values as names ? - if names is True: - fval = first_values[0].strip() - if comments is not None: - if fval in comments: - del first_values[0] - - # Check the columns to use: make sure `usecols` is a list - if usecols is not None: + # Keep on until we find the first valid values + first_values = None try: - usecols = [_.strip() for _ in usecols.split(",")] - except AttributeError: + while not first_values: + first_line = _decode_line(next(fhd), encoding) + if (names is True) and (comments is not None): + if comments in first_line: + first_line = ( + ''.join(first_line.split(comments)[1:])) + first_values = split_line(first_line) + except StopIteration: + # return an empty array if the datafile is empty + first_line = '' + first_values = [] + warnings.warn('genfromtxt: Empty input file: "%s"' % fname, stacklevel=2) + + # Should we take the first values as names ? + if names is True: + fval = first_values[0].strip() + if comments is not None: + if fval in comments: + del first_values[0] + + # Check the columns to use: make sure `usecols` is a list + if usecols is not None: try: - usecols = list(usecols) - except TypeError: - usecols = [usecols, ] - nbcols = len(usecols or first_values) - - # Check the names and overwrite the dtype.names if needed - if names is True: - names = validate_names([str(_.strip()) for _ in first_values]) - first_line = '' - elif _is_string_like(names): - names = validate_names([_.strip() for _ in names.split(',')]) - elif names: - names = validate_names(names) - # Get the dtype - if dtype is not None: - dtype = easy_dtype(dtype, defaultfmt=defaultfmt, names=names, - excludelist=excludelist, - deletechars=deletechars, - case_sensitive=case_sensitive, - replace_space=replace_space) - # Make sure the names is a list (for 2.5) - if names is not None: - names = list(names) - - if usecols: - for (i, current) in enumerate(usecols): - # if usecols is a list of names, convert to a list of indices - if _is_string_like(current): - usecols[i] = names.index(current) - elif current < 0: - usecols[i] = current + len(first_values) - # If the dtype is not None, make sure we update it - if (dtype is not None) and (len(dtype) > nbcols): - descr = dtype.descr - dtype = np.dtype([descr[_] for _ in usecols]) - names = list(dtype.names) - # If `names` is not None, update the names - elif (names is not None) and (len(names) > nbcols): - names = [names[_] for _ in usecols] - elif (names is not None) and (dtype is not None): - names = list(dtype.names) - - # Process the missing values ............................... - # Rename missing_values for convenience - user_missing_values = missing_values or () - if isinstance(user_missing_values, bytes): - user_missing_values = user_missing_values.decode('latin1') - - # Define the list of missing_values (one column: one list) - missing_values = [list(['']) for _ in range(nbcols)] - - # We have a dictionary: process it field by field - if isinstance(user_missing_values, dict): - # Loop on the items - for (key, val) in user_missing_values.items(): - # Is the key a string ? - if _is_string_like(key): + usecols = [_.strip() for _ in usecols.split(",")] + except AttributeError: try: - # Transform it into an integer - key = names.index(key) - except ValueError: - # We couldn't find it: the name must have been dropped - continue - # Redefine the key as needed if it's a column number - if usecols: - try: - key = usecols.index(key) - except ValueError: - pass - # Transform the value as a list of string - if isinstance(val, (list, tuple)): - val = [str(_) for _ in val] + usecols = list(usecols) + except TypeError: + usecols = [usecols, ] + nbcols = len(usecols or first_values) + + # Check the names and overwrite the dtype.names if needed + if names is True: + names = validate_names([str(_.strip()) for _ in first_values]) + first_line = '' + elif _is_string_like(names): + names = validate_names([_.strip() for _ in names.split(',')]) + elif names: + names = validate_names(names) + # Get the dtype + if dtype is not None: + dtype = easy_dtype(dtype, defaultfmt=defaultfmt, names=names, + excludelist=excludelist, + deletechars=deletechars, + case_sensitive=case_sensitive, + replace_space=replace_space) + # Make sure the names is a list (for 2.5) + if names is not None: + names = list(names) + + if usecols: + for (i, current) in enumerate(usecols): + # if usecols is a list of names, convert to a list of indices + if _is_string_like(current): + usecols[i] = names.index(current) + elif current < 0: + usecols[i] = current + len(first_values) + # If the dtype is not None, make sure we update it + if (dtype is not None) and (len(dtype) > nbcols): + descr = dtype.descr + dtype = np.dtype([descr[_] for _ in usecols]) + names = list(dtype.names) + # If `names` is not None, update the names + elif (names is not None) and (len(names) > nbcols): + names = [names[_] for _ in usecols] + elif (names is not None) and (dtype is not None): + names = list(dtype.names) + + # Process the missing values ............................... + # Rename missing_values for convenience + user_missing_values = missing_values or () + if isinstance(user_missing_values, bytes): + user_missing_values = user_missing_values.decode('latin1') + + # Define the list of missing_values (one column: one list) + missing_values = [list(['']) for _ in range(nbcols)] + + # We have a dictionary: process it field by field + if isinstance(user_missing_values, dict): + # Loop on the items + for (key, val) in user_missing_values.items(): + # Is the key a string ? + if _is_string_like(key): + try: + # Transform it into an integer + key = names.index(key) + except ValueError: + # We couldn't find it: the name must have been dropped + continue + # Redefine the key as needed if it's a column number + if usecols: + try: + key = usecols.index(key) + except ValueError: + pass + # Transform the value as a list of string + if isinstance(val, (list, tuple)): + val = [str(_) for _ in val] + else: + val = [str(val), ] + # Add the value(s) to the current list of missing + if key is None: + # None acts as default + for miss in missing_values: + miss.extend(val) + else: + missing_values[key].extend(val) + # We have a sequence : each item matches a column + elif isinstance(user_missing_values, (list, tuple)): + for (value, entry) in zip(user_missing_values, missing_values): + value = str(value) + if value not in entry: + entry.append(value) + # We have a string : apply it to all entries + elif isinstance(user_missing_values, basestring): + user_value = user_missing_values.split(",") + for entry in missing_values: + entry.extend(user_value) + # We have something else: apply it to all entries + else: + for entry in missing_values: + entry.extend([str(user_missing_values)]) + + # Process the filling_values ............................... + # Rename the input for convenience + user_filling_values = filling_values + if user_filling_values is None: + user_filling_values = [] + # Define the default + filling_values = [None] * nbcols + # We have a dictionary : update each entry individually + if isinstance(user_filling_values, dict): + for (key, val) in user_filling_values.items(): + if _is_string_like(key): + try: + # Transform it into an integer + key = names.index(key) + except ValueError: + # We couldn't find it: the name must have been dropped, + continue + # Redefine the key if it's a column number and usecols is defined + if usecols: + try: + key = usecols.index(key) + except ValueError: + pass + # Add the value to the list + filling_values[key] = val + # We have a sequence : update on a one-to-one basis + elif isinstance(user_filling_values, (list, tuple)): + n = len(user_filling_values) + if (n <= nbcols): + filling_values[:n] = user_filling_values else: - val = [str(val), ] - # Add the value(s) to the current list of missing - if key is None: - # None acts as default - for miss in missing_values: - miss.extend(val) + filling_values = user_filling_values[:nbcols] + # We have something else : use it for all entries + else: + filling_values = [user_filling_values] * nbcols + + # Initialize the converters ................................ + if dtype is None: + # Note: we can't use a [...]*nbcols, as we would have 3 times the same + # ... converter, instead of 3 different converters. + converters = [StringConverter(None, missing_values=miss, default=fill) + for (miss, fill) in zip(missing_values, filling_values)] + else: + dtype_flat = flatten_dtype(dtype, flatten_base=True) + # Initialize the converters + if len(dtype_flat) > 1: + # Flexible type : get a converter from each dtype + zipit = zip(dtype_flat, missing_values, filling_values) + converters = [StringConverter(dt, locked=True, + missing_values=miss, default=fill) + for (dt, miss, fill) in zipit] else: - missing_values[key].extend(val) - # We have a sequence : each item matches a column - elif isinstance(user_missing_values, (list, tuple)): - for (value, entry) in zip(user_missing_values, missing_values): - value = str(value) - if value not in entry: - entry.append(value) - # We have a string : apply it to all entries - elif isinstance(user_missing_values, basestring): - user_value = user_missing_values.split(",") - for entry in missing_values: - entry.extend(user_value) - # We have something else: apply it to all entries - else: - for entry in missing_values: - entry.extend([str(user_missing_values)]) - - # Process the filling_values ............................... - # Rename the input for convenience - user_filling_values = filling_values - if user_filling_values is None: - user_filling_values = [] - # Define the default - filling_values = [None] * nbcols - # We have a dictionary : update each entry individually - if isinstance(user_filling_values, dict): - for (key, val) in user_filling_values.items(): - if _is_string_like(key): + # Set to a default converter (but w/ different missing values) + zipit = zip(missing_values, filling_values) + converters = [StringConverter(dtype, locked=True, + missing_values=miss, default=fill) + for (miss, fill) in zipit] + # Update the converters to use the user-defined ones + uc_update = [] + for (j, conv) in user_converters.items(): + # If the converter is specified by column names, use the index instead + if _is_string_like(j): try: - # Transform it into an integer - key = names.index(key) + j = names.index(j) + i = j except ValueError: - # We couldn't find it: the name must have been dropped, continue - # Redefine the key if it's a column number and usecols is defined - if usecols: + elif usecols: try: - key = usecols.index(key) + i = usecols.index(j) except ValueError: - pass - # Add the value to the list - filling_values[key] = val - # We have a sequence : update on a one-to-one basis - elif isinstance(user_filling_values, (list, tuple)): - n = len(user_filling_values) - if (n <= nbcols): - filling_values[:n] = user_filling_values - else: - filling_values = user_filling_values[:nbcols] - # We have something else : use it for all entries - else: - filling_values = [user_filling_values] * nbcols - - # Initialize the converters ................................ - if dtype is None: - # Note: we can't use a [...]*nbcols, as we would have 3 times the same - # ... converter, instead of 3 different converters. - converters = [StringConverter(None, missing_values=miss, default=fill) - for (miss, fill) in zip(missing_values, filling_values)] - else: - dtype_flat = flatten_dtype(dtype, flatten_base=True) - # Initialize the converters - if len(dtype_flat) > 1: - # Flexible type : get a converter from each dtype - zipit = zip(dtype_flat, missing_values, filling_values) - converters = [StringConverter(dt, locked=True, - missing_values=miss, default=fill) - for (dt, miss, fill) in zipit] - else: - # Set to a default converter (but w/ different missing values) - zipit = zip(missing_values, filling_values) - converters = [StringConverter(dtype, locked=True, - missing_values=miss, default=fill) - for (miss, fill) in zipit] - # Update the converters to use the user-defined ones - uc_update = [] - for (j, conv) in user_converters.items(): - # If the converter is specified by column names, use the index instead - if _is_string_like(j): - try: - j = names.index(j) + # Unused converter specified + continue + else: i = j - except ValueError: - continue - elif usecols: - try: - i = usecols.index(j) - except ValueError: - # Unused converter specified + # Find the value to test - first_line is not filtered by usecols: + if len(first_line): + testing_value = first_values[j] + else: + testing_value = None + if conv is bytes: + user_conv = asbytes + elif byte_converters: + # converters may use decode to workaround numpy's old behaviour, + # so encode the string again before passing to the user converter + def tobytes_first(x, conv): + if type(x) is bytes: + return conv(x) + return conv(x.encode("latin1")) + user_conv = functools.partial(tobytes_first, conv=conv) + else: + user_conv = conv + converters[i].update(user_conv, locked=True, + testing_value=testing_value, + default=filling_values[i], + missing_values=missing_values[i],) + uc_update.append((i, user_conv)) + # Make sure we have the corrected keys in user_converters... + user_converters.update(uc_update) + + # Fixme: possible error as following variable never used. + # miss_chars = [_.missing_values for _ in converters] + + # Initialize the output lists ... + # ... rows + rows = [] + append_to_rows = rows.append + # ... masks + if usemask: + masks = [] + append_to_masks = masks.append + # ... invalid + invalid = [] + append_to_invalid = invalid.append + + # Parse each line + for (i, line) in enumerate(itertools.chain([first_line, ], fhd)): + values = split_line(line) + nbvalues = len(values) + # Skip an empty line + if nbvalues == 0: continue - else: - i = j - # Find the value to test - first_line is not filtered by usecols: - if len(first_line): - testing_value = first_values[j] - else: - testing_value = None - if conv is bytes: - user_conv = asbytes - elif byte_converters: - # converters may use decode to workaround numpy's old behaviour, - # so encode the string again before passing to the user converter - def tobytes_first(x, conv): - if type(x) is bytes: - return conv(x) - return conv(x.encode("latin1")) - user_conv = functools.partial(tobytes_first, conv=conv) - else: - user_conv = conv - converters[i].update(user_conv, locked=True, - testing_value=testing_value, - default=filling_values[i], - missing_values=missing_values[i],) - uc_update.append((i, user_conv)) - # Make sure we have the corrected keys in user_converters... - user_converters.update(uc_update) - - # Fixme: possible error as following variable never used. - # miss_chars = [_.missing_values for _ in converters] - - # Initialize the output lists ... - # ... rows - rows = [] - append_to_rows = rows.append - # ... masks - if usemask: - masks = [] - append_to_masks = masks.append - # ... invalid - invalid = [] - append_to_invalid = invalid.append - - # Parse each line - for (i, line) in enumerate(itertools.chain([first_line, ], fhd)): - values = split_line(line) - nbvalues = len(values) - # Skip an empty line - if nbvalues == 0: - continue - if usecols: - # Select only the columns we need - try: - values = [values[_] for _ in usecols] - except IndexError: + if usecols: + # Select only the columns we need + try: + values = [values[_] for _ in usecols] + except IndexError: + append_to_invalid((i + skip_header + 1, nbvalues)) + continue + elif nbvalues != nbcols: append_to_invalid((i + skip_header + 1, nbvalues)) continue - elif nbvalues != nbcols: - append_to_invalid((i + skip_header + 1, nbvalues)) - continue - # Store the values - append_to_rows(tuple(values)) - if usemask: - append_to_masks(tuple([v.strip() in m - for (v, m) in zip(values, - missing_values)])) - if len(rows) == max_rows: - break - - if own_fhd: - fhd.close() + # Store the values + append_to_rows(tuple(values)) + if usemask: + append_to_masks(tuple([v.strip() in m + for (v, m) in zip(values, + missing_values)])) + if len(rows) == max_rows: + break # Upgrade the converters (if needed) if dtype is None: |