BUG: read_msgpack raise an error when passed an non existent path in Python 2 (pandas-dev#16523)

* TST: Add tests for trying to read non-existent files pandas-dev#15296

* BUG: Fix passing non-existant file to read_msgpack pandas-dev#15296

* TST: Fix io.test_common.test_read_non_existant for external modules

* CLN: Import FileNotFoundError in tests/io/test_common.py

Author: chrisburr

doc/source/whatsnew/v0.22.0.txt

@@ -87,6 +87,8 @@ Documentation Changes
 Bug Fixes
 ~~~~~~~~~
 
+- Bug in ``pd.read_msgpack()`` with a non existent file is passed in Python 2 (:issue:`15296`)
+
 Conversion
 ^^^^^^^^^^
 

pandas/io/packers.py

@@ -192,7 +192,6 @@ def read(fh):
 
     # see if we have an actual file
     if isinstance(path_or_buf, compat.string_types):
-
         try:
             exists = os.path.exists(path_or_buf)
         except (TypeError, ValueError):
@@ -202,18 +201,21 @@ def read(fh):
             with open(path_or_buf, 'rb') as fh:
                 return read(fh)
 
-    # treat as a binary-like
     if isinstance(path_or_buf, compat.binary_type):
+        # treat as a binary-like
         fh = None
         try:
-            fh = compat.BytesIO(path_or_buf)
-            return read(fh)
+            # We can't distinguish between a path and a buffer of bytes in
+            # Python 2 so instead assume the first byte of a valid path is
+            # less than 0x80.
+            if compat.PY3 or ord(path_or_buf[0]) >= 0x80:
+                fh = compat.BytesIO(path_or_buf)
+                return read(fh)
         finally:
             if fh is not None:
                 fh.close()
-
-    # a buffer like
-    if hasattr(path_or_buf, 'read') and compat.callable(path_or_buf.read):
+    elif hasattr(path_or_buf, 'read') and compat.callable(path_or_buf.read):
+        # treat as a buffer like
         return read(path_or_buf)
 
     raise ValueError('path_or_buf needs to be a string file path or file-like')

pandas/tests/io/test_common.py

@@ -10,7 +10,7 @@
 import pandas.util.testing as tm
 
 from pandas.io import common
-from pandas.compat import is_platform_windows, StringIO
+from pandas.compat import is_platform_windows, StringIO, FileNotFoundError
 
 from pandas import read_csv, concat
 
@@ -125,6 +125,26 @@ def test_iterator(self):
         tm.assert_frame_equal(first, expected.iloc[[0]])
         tm.assert_frame_equal(concat(it), expected.iloc[1:])
 
+    @pytest.mark.parametrize('reader, module, error_class, fn_ext', [
+        (pd.read_csv, 'os', FileNotFoundError, 'csv'),
+        (pd.read_table, 'os', FileNotFoundError, 'csv'),
+        (pd.read_fwf, 'os', FileNotFoundError, 'txt'),
+        (pd.read_excel, 'xlrd', FileNotFoundError, 'xlsx'),
+        (pd.read_feather, 'feather', Exception, 'feather'),
+        (pd.read_hdf, 'tables', FileNotFoundError, 'h5'),
+        (pd.read_stata, 'os', FileNotFoundError, 'dta'),
+        (pd.read_sas, 'os', FileNotFoundError, 'sas7bdat'),
+        (pd.read_json, 'os', ValueError, 'json'),
+        (pd.read_msgpack, 'os', ValueError, 'mp'),
+        (pd.read_pickle, 'os', FileNotFoundError, 'pickle'),
+    ])
+    def test_read_non_existant(self, reader, module, error_class, fn_ext):
+        pytest.importorskip(module)
+
+        path = os.path.join(HERE, 'data', 'does_not_exist.' + fn_ext)
+        with pytest.raises(error_class):
+            reader(path)
+
     @pytest.mark.parametrize('reader, module, path', [
         (pd.read_csv, 'os', os.path.join(HERE, 'data', 'iris.csv')),
         (pd.read_table, 'os', os.path.join(HERE, 'data', 'iris.csv')),