Add support for pathlib.Path. Fix #170 (#175)

* Support opening pathlib.Path

* Edited opening pathlib.Path test which skips if not available

* Added pathlib2 backport support including tests

* Added pathlib2 to test_require for supporting pathlib backport

* Fix author/maintainer fields in `setup.py`, avoid bug from `setuptools==39.0.0`. Fix #176 (#178)

* fix author/maintainer fields

* attemp to resolve problem with botocore

* try other workaround for botocore

* next attemp

* bump version to 1.5.7

* bump changelos to 1.5.7

* Reduced code logic redundancy in pathlib.Path test

setup.py

@@ -19,6 +19,7 @@ def read(fname):
 tests_require = [
     'mock',
     'moto==0.4.31',
+    'pathlib2',
     'responses',
 ]
 

smart_open/smart_open_lib.py

@@ -27,9 +27,20 @@
 import subprocess
 import sys
 import requests
+import importlib
 import io
 import warnings
 
+# Import ``pathlib`` if the builtin ``pathlib`` or the backport ``pathlib2`` are
+# available. The builtin ``pathlib`` will be imported with higher precedence.
+for pathlib_module in ('pathlib', 'pathlib2'):
+    try:
+        pathlib = importlib.import_module(pathlib_module)
+        PATHLIB_SUPPORT = True
+        break
+    except ImportError:
+        PATHLIB_SUPPORT = False
+
 from boto.compat import BytesIO, urlsplit, six
 import boto.s3.connection
 import boto.s3.key
@@ -102,6 +113,7 @@ def smart_open(uri, mode="rb", **kw):
     3. a URI for Amazon's S3 (can also supply credentials inside the URI):
        `s3://my_bucket/lines.txt`, `s3://my_aws_key_id:key_secret@my_bucket/lines.txt`
     4. an instance of the boto.s3.key.Key class.
+    5. an instance of the pathlib.Path class.
 
     Examples::
 
@@ -163,6 +175,10 @@ def smart_open(uri, mode="rb", **kw):
     if not isinstance(mode, six.string_types):
         raise TypeError('mode should be a string')
 
+    # Support opening ``pathlib.Path`` objects by casting them to strings.
+    if PATHLIB_SUPPORT and isinstance(uri, pathlib.Path):
+        uri = str(uri)
+
     if isinstance(uri, six.string_types):
         # this method just routes the request to classes handling the specific storage
         # schemes, depending on the URI protocol in `uri`

smart_open/tests/test_smart_open.py

@@ -191,6 +191,20 @@ def test_open_with_keywords_explicit_r(self):
             actual = fin.read()
         self.assertEqual(expected, actual)
 
+    @unittest.skipUnless(
+        smart_open_lib.PATHLIB_SUPPORT,
+        "do not test pathlib support if pathlib or backport are not available")
+    def test_open_and_read_pathlib_path(self):
+        """If ``pathlib.Path`` is available we should be able to open and read."""
+        from smart_open.smart_open_lib import pathlib
+
+        fpath = os.path.join(CURR_DIR, 'test_data/cp852.tsv.txt')
+        with open(fpath, 'rb') as fin:
+            expected = fin.read().decode('cp852')
+        with smart_open.smart_open(pathlib.Path(fpath), mode='r', encoding='cp852') as fin:
+            actual = fin.read()
+        self.assertEqual(expected, actual)
+
     @mock_s3
     def test_read_never_returns_none(self):
         """read should never return None."""