Initial pandas.typing Module (#25884)

Author: WillAyd

pandas/_typing.py

@@ -0,0 +1,4 @@
+from pathlib import Path
+from typing import IO, AnyStr, Union
+
+FilePathOrBuffer = Union[str, Path, IO[AnyStr]]

pandas/io/gcs.py

@@ -12,5 +12,6 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
         mode = 'rb'
 
     fs = gcsfs.GCSFileSystem()
-    filepath_or_buffer = fs.open(filepath_or_buffer, mode)
+    filepath_or_buffer = fs.open(
+        filepath_or_buffer, mode)  # type: gcsfs.GCSFile
     return filepath_or_buffer, None, compression, True

pandas/io/parsers.py

@@ -30,6 +30,7 @@
 from pandas.core.dtypes.dtypes import CategoricalDtype
 from pandas.core.dtypes.missing import isna
 
+from pandas._typing import FilePathOrBuffer
 from pandas.core import algorithms
 from pandas.core.arrays import Categorical
 from pandas.core.frame import DataFrame
@@ -400,7 +401,7 @@ def _validate_names(names):
     return names
 
 
-def _read(filepath_or_buffer, kwds):
+def _read(filepath_or_buffer: FilePathOrBuffer, kwds):
     """Generic reader of line files."""
     encoding = kwds.get('encoding', None)
     if encoding is not None:
@@ -409,7 +410,12 @@ def _read(filepath_or_buffer, kwds):
 
     compression = kwds.get('compression', 'infer')
     compression = _infer_compression(filepath_or_buffer, compression)
-    filepath_or_buffer, _, compression, should_close = get_filepath_or_buffer(
+
+    # TODO: get_filepath_or_buffer could return
+    # Union[FilePathOrBuffer, s3fs.S3File, gcsfs.GCSFile]
+    # though mypy handling of conditional imports is difficult.
+    # See https://github.com/python/mypy/issues/1297
+    fp_or_buf, _, compression, should_close = get_filepath_or_buffer(
         filepath_or_buffer, encoding, compression)
     kwds['compression'] = compression
 
@@ -426,7 +432,7 @@ def _read(filepath_or_buffer, kwds):
     _validate_names(kwds.get("names", None))
 
     # Create the parser.
-    parser = TextFileReader(filepath_or_buffer, **kwds)
+    parser = TextFileReader(fp_or_buf, **kwds)
 
     if chunksize or iterator:
         return parser
@@ -438,7 +444,7 @@ def _read(filepath_or_buffer, kwds):
 
     if should_close:
         try:
-            filepath_or_buffer.close()
+            fp_or_buf.close()
         except ValueError:
             pass
 
@@ -533,7 +539,7 @@ def _make_parser_function(name, default_sep=','):
     else:
         sep = default_sep
 
-    def parser_f(filepath_or_buffer,
+    def parser_f(filepath_or_buffer: FilePathOrBuffer,
                  sep=sep,
                  delimiter=None,
 
@@ -725,8 +731,11 @@ def parser_f(filepath_or_buffer,
                       )(read_table)
 
 
-def read_fwf(filepath_or_buffer, colspecs='infer', widths=None,
-             infer_nrows=100, **kwds):
+def read_fwf(filepath_or_buffer: FilePathOrBuffer,
+             colspecs='infer',
+             widths=None,
+             infer_nrows=100,
+             **kwds):
 
     r"""
     Read a table of fixed-width formatted lines into DataFrame.

pandas/io/s3.py

@@ -31,5 +31,6 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
         # A NoCredentialsError is raised if you don't have creds
         # for that bucket.
         fs = s3fs.S3FileSystem(anon=True)
-        filepath_or_buffer = fs.open(_strip_schema(filepath_or_buffer), mode)
+        filepath_or_buffer = fs.open(
+            _strip_schema(filepath_or_buffer), mode)  # type: s3fs.S3File
     return filepath_or_buffer, None, compression, True