diff options
Diffstat (limited to 'numpy/lib/format.py')
| -rw-r--r-- | numpy/lib/format.py | 55 |
1 files changed, 47 insertions, 8 deletions
diff --git a/numpy/lib/format.py b/numpy/lib/format.py index e25868236..10945e5e8 100644 --- a/numpy/lib/format.py +++ b/numpy/lib/format.py @@ -161,7 +161,9 @@ import sys import io import warnings from numpy.lib.utils import safe_eval -from numpy.compat import asbytes, asstr, isfileobj, long, basestring +from numpy.compat import ( + asbytes, asstr, isfileobj, long, os_fspath + ) from numpy.core.numeric import pickle @@ -257,6 +259,43 @@ def dtype_to_descr(dtype): else: return dtype.str +def descr_to_dtype(descr): + ''' + descr may be stored as dtype.descr, which is a list of + (name, format, [shape]) tuples. Offsets are not explicitly saved, rather + empty fields with name,format == '', '|Vn' are added as padding. + + This function reverses the process, eliminating the empty padding fields. + ''' + if isinstance(descr, (str, dict)): + # No padding removal needed + return numpy.dtype(descr) + + fields = [] + offset = 0 + for field in descr: + if len(field) == 2: + name, descr_str = field + dt = descr_to_dtype(descr_str) + else: + name, descr_str, shape = field + dt = numpy.dtype((descr_to_dtype(descr_str), shape)) + + # Ignore padding bytes, which will be void bytes with '' as name + # Once support for blank names is removed, only "if name == ''" needed) + is_pad = (name == '' and dt.type is numpy.void and dt.names is None) + if not is_pad: + fields.append((name, dt, offset)) + + offset += dt.itemsize + + names, formats, offsets = zip(*fields) + # names may be (title, names) tuples + nametups = (n if isinstance(n, tuple) else (None, n) for n in names) + titles, names = zip(*nametups) + return numpy.dtype({'names': names, 'formats': formats, 'titles': titles, + 'offsets': offsets, 'itemsize': offset}) + def header_data_from_array_1_0(array): """ Get the dictionary of header metadata from a numpy.ndarray. @@ -521,7 +560,7 @@ def _read_array_header(fp, version): msg = "fortran_order is not a valid bool: %r" raise ValueError(msg % (d['fortran_order'],)) try: - dtype = numpy.dtype(d['descr']) + dtype = descr_to_dtype(d['descr']) except TypeError as e: msg = "descr is not a valid dtype descriptor: %r" raise ValueError(msg % (d['descr'],)) @@ -706,7 +745,7 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, Parameters ---------- - filename : str + filename : str or path-like The name of the file on disk. This may *not* be a file-like object. mode : str, optional @@ -747,9 +786,9 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, memmap """ - if not isinstance(filename, basestring): - raise ValueError("Filename must be a string. Memmap cannot use" - " existing file handles.") + if isfileobj(filename): + raise ValueError("Filename must be a string or a path-like object." + " Memmap cannot use existing file handles.") if 'w' in mode: # We are creating the file, not reading it. @@ -767,7 +806,7 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, shape=shape, ) # If we got here, then it should be safe to create the file. - fp = open(filename, mode+'b') + fp = open(os_fspath(filename), mode+'b') try: used_ver = _write_array_header(fp, d, version) # this warning can be removed when 1.9 has aged enough @@ -779,7 +818,7 @@ def open_memmap(filename, mode='r+', dtype=None, shape=None, fp.close() else: # Read the header of the file first. - fp = open(filename, 'rb') + fp = open(os_fspath(filename), 'rb') try: version = read_magic(fp) _check_version(version) |