ENH: Infer compression from non-string paths (pandas-dev#17206)

Author: dhimmel

Diff for: doc/source/whatsnew/v0.21.0.txt

@@ -127,6 +127,7 @@ Other Enhancements
 - :func:`read_html` handles colspan and rowspan arguments and attempts to infer a header if the header is not explicitly specified (:issue:`17054`)
 - Integration with `Apache Parquet <https://parquet.apache.org/>`__, including a new top-level :func:`read_parquet` and :func:`DataFrame.to_parquet` method, see :ref:`here <io.parquet>`.
 - :func:`DataFrame.add_prefix` and :func:`DataFrame.add_suffix` now accept strings containing the '%' character. (:issue:`17151`)
+- `read_*` methods can now infer compression from non-string paths, such as ``pathlib.Path`` objects (:issue:`17206`).
 
 .. _whatsnew_0210.api_breaking:
 

Diff for: pandas/io/common.py

@@ -272,13 +272,15 @@ def _infer_compression(filepath_or_buffer, compression):
     if compression is None:
         return None
 
-    # Cannot infer compression of a buffer. Hence assume no compression.
-    is_path = isinstance(filepath_or_buffer, compat.string_types)
-    if compression == 'infer' and not is_path:
-        return None
-
-    # Infer compression from the filename/URL extension
+    # Infer compression
     if compression == 'infer':
+        # Convert all path types (e.g. pathlib.Path) to strings
+        filepath_or_buffer = _stringify_path(filepath_or_buffer)
+        if not isinstance(filepath_or_buffer, compat.string_types):
+            # Cannot infer compression of a buffer, assume no compression
+            return None
+
+        # Infer compression from the filename/URL extension
         for compression, extension in _compression_to_extension.items():
             if filepath_or_buffer.endswith(extension):
                 return compression

Diff for: pandas/io/parsers.py

@@ -208,11 +208,11 @@
     <http://pandas.pydata.org/pandas-docs/stable/io.html#io-chunking>`_
     for more information on ``iterator`` and ``chunksize``.
 compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer'
-    For on-the-fly decompression of on-disk data. If 'infer', then use gzip,
-    bz2, zip or xz if filepath_or_buffer is a string ending in '.gz', '.bz2',
-    '.zip', or 'xz', respectively, and no decompression otherwise. If using
-    'zip', the ZIP file must contain only one data file to be read in.
-    Set to None for no decompression.
+    For on-the-fly decompression of on-disk data. If 'infer' and
+    `filepath_or_buffer` is path-like, then detect compression from the
+    following extensions: '.gz', '.bz2', '.zip', or '.xz' (otherwise no
+    decompression). If using 'zip', the ZIP file must contain only one data
+    file to be read in. Set to None for no decompression.
 
     .. versionadded:: 0.18.1 support for 'zip' and 'xz' compression.
 

Diff for: pandas/io/pickle.py

@@ -62,8 +62,8 @@ def read_pickle(path, compression='infer'):
         File path
     compression : {'infer', 'gzip', 'bz2', 'xz', 'zip', None}, default 'infer'
         For on-the-fly decompression of on-disk data. If 'infer', then use
-        gzip, bz2, xz or zip if path is a string ending in '.gz', '.bz2', 'xz',
-        or 'zip' respectively, and no decompression otherwise.
+        gzip, bz2, xz or zip if path ends in '.gz', '.bz2', '.xz',
+        or '.zip' respectively, and no decompression otherwise.
         Set to None for no decompression.
 
         .. versionadded:: 0.20.0

Diff for: pandas/tests/io/test_common.py

@@ -14,16 +14,6 @@
 
 from pandas import read_csv, concat
 
-try:
-    from pathlib import Path
-except ImportError:
-    pass
-
-try:
-    from py.path import local as LocalPath
-except ImportError:
-    pass
-
 
 class CustomFSPath(object):
     """For testing fspath on unknown objects"""
@@ -34,6 +24,21 @@ def __fspath__(self):
         return self.path
 
 
+# Functions that consume a string path and return a string or path-like object
+path_types = [str, CustomFSPath]
+
+try:
+    from pathlib import Path
+    path_types.append(Path)
+except ImportError:
+    pass
+
+try:
+    from py.path import local as LocalPath
+    path_types.append(LocalPath)
+except ImportError:
+    pass
+
 HERE = os.path.dirname(__file__)
 
 
@@ -83,6 +88,19 @@ def test_stringify_path_fspath(self):
         result = common._stringify_path(p)
         assert result == 'foo/bar.csv'
 
+    @pytest.mark.parametrize('extension,expected', [
+        ('', None),
+        ('.gz', 'gzip'),
+        ('.bz2', 'bz2'),
+        ('.zip', 'zip'),
+        ('.xz', 'xz'),
+    ])
+    @pytest.mark.parametrize('path_type', path_types)
+    def test_infer_compression_from_path(self, extension, expected, path_type):
+        path = path_type('foo/bar.csv' + extension)
+        compression = common._infer_compression(path, compression='infer')
+        assert compression == expected
+
     def test_get_filepath_or_buffer_with_path(self):
         filename = '~/sometest'
         filepath_or_buffer, _, _ = common.get_filepath_or_buffer(filename)