COMPAT: Consider Python 2.x tarfiles file-like

Tarfile.ExFileObject has no "next" method in
Python 2.x, making it an invalid file-like
object in read_csv. However, they can be
read in just fine, meaning our check is too
strict for file-like. This commit relaxes
the check to just look for "__iter__".

Closes pandas-devgh-16530.

Author: gfyoung

doc/source/whatsnew/v0.20.2.txt

@@ -64,6 +64,7 @@ I/O
 - Bug in pd.read_csv() when comment is passed in space deliminted text files (:issue:`16472`)
 - Bug that would force importing of the clipboard routines unnecessarily, potentially causing an import error on startup (:issue:`16288`)
 - Bug that raised IndexError HTML-rendering an empty DataFrame (:issue:`15953`)
+- Bug in ``pd.read_csv()`` in which tarfile object inputs were raising an error in Python 2.x (:issue:`16530`)
 
 
 Plotting

pandas/core/dtypes/inference.py

@@ -171,7 +171,7 @@ def is_file_like(obj):
     if not (hasattr(obj, 'read') or hasattr(obj, 'write')):
         return False
 
-    if not is_iterator(obj):
+    if not hasattr(obj, "__iter__"):
         return False
 
     return True

pandas/tests/dtypes/test_inference.py

@@ -120,9 +120,9 @@ class MockFile(object):
     m = MockFile()
     assert not is_file(m)
 
+    # gh-16530: Valid iterator just means we have the
+    # __iter__ attribute for our purposes.
     MockFile.__iter__ = lambda self: self
-    MockFile.__next__ = lambda self: 0
-    MockFile.next = MockFile.__next__
 
     # Valid write-only file
     m = MockFile()

pandas/tests/io/parser/common.py

@@ -3,6 +3,7 @@
 import csv
 import os
 import platform
+import tarfile
 import codecs
 
 import re
@@ -1702,17 +1703,26 @@ class InvalidBuffer(object):
         # Thus, while the object may look "invalid" (these
         # methods are attributes of the `StringIO` class),
         # it is still a valid file-object for our purposes.
-        class NoSeekTellBuffer(StringIO):
+        #
+        # gh-16530: Valid iterator just means we have the
+        # "__iter__" attribute (don't need "next" or "__next__")
+        class NoSeekTellNextBuffer(StringIO):
             def tell(self):
                 raise AttributeError("No tell method")
 
             def seek(self, pos, whence=0):
                 raise AttributeError("No seek method")
 
+            def next(self):
+                raise AttributeError("No next method")
+
+            def __next__(self):
+                raise AttributeError("No __next__ method")
+
         data = "a\n1"
 
         expected = pd.DataFrame({"a": [1]})
-        result = self.read_csv(NoSeekTellBuffer(data))
+        result = self.read_csv(NoSeekTellNextBuffer(data))
 
         tm.assert_frame_equal(result, expected)
 
@@ -1754,3 +1764,24 @@ def test_skip_bad_lines(self):
         val = sys.stderr.getvalue()
         assert 'Skipping line 3' in val
         assert 'Skipping line 5' in val
+
+    def test_read_tarfile(self):
+        # see gh-16530
+        expected = pd.DataFrame({"a": [1]})
+
+        tar_path = u("__%s__.tar" % tm.rands(10))
+        file_path = u("__%s__.csv" % tm.rands(10))
+
+        with tm.ensure_clean(tar_path) as full_tar_path:
+            with tm.ensure_clean(file_path) as full_file_path:
+                expected.to_csv(full_file_path, index=False)
+
+                tar = tarfile.open(full_tar_path, "w")
+                tar.add(file_path)
+                tar.close()
+
+                tar = tarfile.open(full_tar_path, "r")
+                data_file = tar.extractfile(file_path)
+                out = self.read_csv(data_file)
+
+                tm.assert_frame_equal(out, expected)