ENH: Add support for third-party path-like objects by backporting os.fspath

eric-wieser · eric-wieser · commit 489362c0779b · 2018-10-12T08:39:40.000-07:00
diff --git a/numpy/compat/py3k.py b/numpy/compat/py3k.py
@@ -8,13 +8,13 @@
            'unicode', 'asunicode', 'asbytes_nested', 'asunicode_nested',
            'asstr', 'open_latin1', 'long', 'basestring', 'sixu',
            'integer_types', 'is_pathlib_path', 'npy_load_module', 'Path',
-           'contextlib_nullcontext']
+           'contextlib_nullcontext', 'os_fspath', 'os_PathLike']
 
 import sys
 try:
-    from pathlib import Path
+    from pathlib import Path, PurePath
 except ImportError:
-    Path = None
+    Path = PurePath = None
 
 if sys.version_info[0] >= 3:
     import io
@@ -95,6 +95,8 @@ def asunicode_nested(x):
 def is_pathlib_path(obj):
     """
     Check whether obj is a pathlib.Path object.
+
+    Prefer using `isinstance(obj, os_PathLike)` instead of this function.
     """
     return Path is not None and isinstance(obj, Path)
 
@@ -177,3 +179,65 @@ def npy_load_module(name, fn, info=None):
         finally:
             fo.close()
         return mod
+
+# backport abc.ABC
+import abc
+if sys.version_info[:2] >= (3, 4):
+    abc_ABC = abc.ABC
+else:
+    abc_ABC = abc.ABCMeta('ABC', (object,), {'__slots__': ()})
+
+
+# Backport os.fs_path, os.PathLike, and PurePath.__fspath__
+if sys.version_info[:2] >= (3, 6):
+    import os
+    os_fspath = os.fspath
+    os_PathLike = os.PathLike
+else:
+    def _PurePath__fspath__(self):
+        return str(self)
+
+    class os_PathLike(abc_ABC):
+        """Abstract base class for implementing the file system path protocol."""
+
+        @abc.abstractmethod
+        def __fspath__(self):
+            """Return the file system path representation of the object."""
+            raise NotImplementedError
+
+        @classmethod
+        def __subclasshook__(cls, subclass):
+            if PurePath is not None and issubclass(subclass, PurePath):
+                return True
+            return hasattr(subclass, '__fspath__')
+
+
+    def os_fspath(path):
+        """Return the path representation of a path-like object.
+        If str or bytes is passed in, it is returned unchanged. Otherwise the
+        os.PathLike interface is used to get the path representation. If the
+        path representation is not str or bytes, TypeError is raised. If the
+        provided path is not str, bytes, or os.PathLike, TypeError is raised.
+        """
+        if isinstance(path, (str, bytes)):
+            return path
+
+        # Work from the object's type to match method resolution of other magic
+        # methods.
+        path_type = type(path)
+        try:
+            path_repr = path_type.__fspath__(path)
+        except AttributeError:
+            if hasattr(path_type, '__fspath__'):
+                raise
+            elif PurePath is not None and issubclass(path_type, PurePath):
+                return _PurePath__fspath__(path)
+            else:
+                raise TypeError("expected str, bytes or os.PathLike object, "
+                                "not " + path_type.__name__)
+        if isinstance(path_repr, (str, bytes)):
+            return path_repr
+        else:
+            raise TypeError("expected {}.__fspath__() to return str or bytes, "
+                            "not {}".format(path_type.__name__,
+                                            type(path_repr).__name__))
diff --git a/numpy/core/memmap.py b/numpy/core/memmap.py
@@ -3,7 +3,7 @@
 import numpy as np
 from .numeric import uint8, ndarray, dtype
 from numpy.compat import (
-    long, basestring, is_pathlib_path, contextlib_nullcontext
+    long, basestring, os_fspath, contextlib_nullcontext, is_pathlib_path
 )
 
 __all__ = ['memmap']
@@ -218,10 +218,8 @@ def __new__(subtype, filename, dtype=uint8, mode='r+', offset=0,
 
         if hasattr(filename, 'read'):
             f_ctx = contextlib_nullcontext(filename)
-        elif is_pathlib_path(filename):
-            f_ctx = filename.open(('r' if mode == 'c' else mode)+'b')
         else:
-            f_ctx = open(filename, ('r' if mode == 'c' else mode)+'b')
+            f_ctx = open(os_fspath(filename), ('r' if mode == 'c' else mode)+'b')
 
         with f_ctx as fid:
             fid.seek(0, 2)
@@ -268,14 +266,13 @@ def __new__(subtype, filename, dtype=uint8, mode='r+', offset=0,
             self.offset = offset
             self.mode = mode
 
-            if isinstance(filename, basestring):
-                self.filename = os.path.abspath(filename)
-            elif is_pathlib_path(filename):
+            if is_pathlib_path(filename):
+                # special case - if we were constructed with a pathlib.path,
+                # then filename is a path object, not a string
                 self.filename = filename.resolve()
-            # py3 returns int for TemporaryFile().name
-            elif (hasattr(filename, "name") and
-                  isinstance(filename.name, basestring)):
-                self.filename = os.path.abspath(filename.name)
+            elif hasattr(fid, "name") and isinstance(fid.name, basestring):
+                # py3 returns int for TemporaryFile().name
+                self.filename = os.path.abspath(fid.name)
             # same as memmap copies (e.g. memmap + 1)
             else:
                 self.filename = None
diff --git a/numpy/lib/npyio.py b/numpy/lib/npyio.py
@@ -21,7 +21,7 @@
 
 from numpy.compat import (
     asbytes, asstr, asunicode, asbytes_nested, bytes, basestring, unicode,
-    is_pathlib_path
+    os_fspath, os_PathLike
     )
 from numpy.core.numeric import pickle
 
@@ -104,8 +104,8 @@ def zipfile_factory(file, *args, **kwargs):
     pathlib.Path objects. `args` and `kwargs` are passed to the zipfile.ZipFile
     constructor.
     """
-    if is_pathlib_path(file):
-        file = str(file)
+    if not hasattr(file, 'read'):
+        file = os_fspath(file)
     import zipfile
     kwargs['allowZip64'] = True
     return zipfile.ZipFile(file, *args, **kwargs)
@@ -399,15 +399,12 @@ def load(file, mmap_mode=None, allow_pickle=True, fix_imports=True,
         pickle_kwargs = {}
 
     # TODO: Use contextlib.ExitStack once we drop Python 2
-    if isinstance(file, basestring):
-        fid = open(file, "rb")
-        own_fid = True
-    elif is_pathlib_path(file):
-        fid = file.open("rb")
-        own_fid = True
-    else:
+    if hasattr(file, 'read'):
         fid = file
         own_fid = False
+    else:
+        fid = open(os_fspath(file), "rb")
+        own_fid = True
 
     try:
         # Code to distinguish from NumPy binary files and pickles.
@@ -497,18 +494,14 @@ def save(file, arr, allow_pickle=True, fix_imports=True):
 
     """
     own_fid = False
-    if isinstance(file, basestring):
+    if hasattr(file, 'read'):
+        fid = file
+    else:
+        file = os_fspath(file)
         if not file.endswith('.npy'):
             file = file + '.npy'
         fid = open(file, "wb")
         own_fid = True
-    elif is_pathlib_path(file):
-        if not file.name.endswith('.npy'):
-            file = file.parent / (file.name + '.npy')
-        fid = file.open("wb")
-        own_fid = True
-    else:
-        fid = file
 
     if sys.version_info[0] >= 3:
         pickle_kwargs = dict(fix_imports=fix_imports)
@@ -673,12 +666,10 @@ def _savez(file, args, kwds, compress, allow_pickle=True, pickle_kwargs=None):
     # component of the so-called standard library.
     import zipfile
 
-    if isinstance(file, basestring):
+    if not hasattr(file, 'read'):
+        file = os_fspath(file)
         if not file.endswith('.npz'):
             file = file + '.npz'
-    elif is_pathlib_path(file):
-        if not file.name.endswith('.npz'):
-            file = file.parent / (file.name + '.npz')
 
     namedict = kwds
     for i, val in enumerate(args):
@@ -926,8 +917,8 @@ def loadtxt(fname, dtype=float, comments='#', delimiter=None,
 
     fown = False
     try:
-        if is_pathlib_path(fname):
-            fname = str(fname)
+        if isinstance(fname, os_PathLike):
+            fname = os_fspath(fname)
         if _is_string_like(fname):
             fh = np.lib._datasource.open(fname, 'rt', encoding=encoding)
             fencoding = getattr(fh, 'encoding', 'latin1')
@@ -1315,8 +1306,8 @@ def first_write(self, v):
                 self.write = self.write_bytes
 
     own_fh = False
-    if is_pathlib_path(fname):
-        fname = str(fname)
+    if isinstance(fname, os_PathLike):
+        fname = os_fspath(fname)
     if _is_string_like(fname):
         # datasource doesn't support creating a new file ...
         open(fname, 'wt').close()
@@ -1699,8 +1690,8 @@ def genfromtxt(fname, dtype=float, comments='#', delimiter=None,
     # Initialize the filehandle, the LineSplitter and the NameValidator
     own_fhd = False
     try:
-        if is_pathlib_path(fname):
-            fname = str(fname)
+        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
