From 68721019efb16ba8acad036c331a9a195d6f7da0 Mon Sep 17 00:00:00 2001 From: Nadeem Vawda Date: Mon, 4 Jun 2012 23:21:38 +0200 Subject: [PATCH] Add fileobj support to gzip.open(). --- Doc/library/gzip.rst | 20 +++++++++++--------- Lib/gzip.py | 13 ++++++++++++- Lib/test/test_gzip.py | 13 +++++++++++++ Misc/NEWS | 2 ++ 4 files changed, 38 insertions(+), 10 deletions(-) diff --git a/Doc/library/gzip.rst b/Doc/library/gzip.rst index 861a59cd450..50d04627e77 100644 --- a/Doc/library/gzip.rst +++ b/Doc/library/gzip.rst @@ -14,10 +14,10 @@ like the GNU programs :program:`gzip` and :program:`gunzip` would. The data compression is provided by the :mod:`zlib` module. The :mod:`gzip` module provides the :class:`GzipFile` class, as well as the -:func:`gzip.open`, :func:`compress` and :func:`decompress` convenience -functions. The :class:`GzipFile` class reads and writes :program:`gzip`\ -format -files, automatically compressing or decompressing the data so that it looks like -an ordinary :term:`file object`. +:func:`.open`, :func:`compress` and :func:`decompress` convenience functions. +The :class:`GzipFile` class reads and writes :program:`gzip`\ -format files, +automatically compressing or decompressing the data so that it looks like an +ordinary :term:`file object`. Note that additional file formats which can be decompressed by the :program:`gzip` and :program:`gunzip` programs, such as those produced by @@ -28,9 +28,11 @@ The module defines the following items: .. function:: open(filename, mode='rb', compresslevel=9, encoding=None, errors=None, newline=None) - Open *filename* as a gzip-compressed file in binary or text mode. + Open a gzip-compressed file in binary or text mode, returning a :term:`file + object`. - Returns a :term:`file object`. + The *filename* argument can be an actual filename (a :class:`str` or + :class:`bytes` object), or an existing file object to read from or write to. The *mode* argument can be any of ``'r'``, ``'rb'``, ``'a'``, ``'ab'``, ``'w'``, or ``'wb'`` for binary mode, or ``'rt'``, ``'at'``, or ``'wt'`` for @@ -48,8 +50,8 @@ The module defines the following items: handling behavior, and line ending(s). .. versionchanged:: 3.3 - Support for text mode was added, along with the *encoding*, *errors* and - *newline* arguments. + Added support for *filename* being a file object, support for text mode, + and the *encoding*, *errors* and *newline* arguments. .. class:: GzipFile(filename=None, mode=None, compresslevel=9, fileobj=None, mtime=None) @@ -75,7 +77,7 @@ The module defines the following items: is the mode of *fileobj* if discernible; otherwise, the default is ``'rb'``. Note that the file is always opened in binary mode. To open a compressed file - in text mode, use :func:`gzip.open` (or wrap your :class:`GzipFile` with an + in text mode, use :func:`.open` (or wrap your :class:`GzipFile` with an :class:`io.TextIOWrapper`). The *compresslevel* argument is an integer from ``1`` to ``9`` controlling the diff --git a/Lib/gzip.py b/Lib/gzip.py index 2f53aa8aacf..412bf05495a 100644 --- a/Lib/gzip.py +++ b/Lib/gzip.py @@ -20,6 +20,9 @@ def open(filename, mode="rb", compresslevel=9, encoding=None, errors=None, newline=None): """Open a gzip-compressed file in binary or text mode. + The filename argument can be an actual filename (a str or bytes object), or + an existing file object to read from or write to. + The mode argument can be "r", "rb", "w", "wb", "a" or "ab" for binary mode, or "rt", "wt" or "at" for text mode. The default mode is "rb", and the default compresslevel is 9. @@ -43,7 +46,15 @@ def open(filename, mode="rb", compresslevel=9, raise ValueError("Argument 'errors' not supported in binary mode") if newline is not None: raise ValueError("Argument 'newline' not supported in binary mode") - binary_file = GzipFile(filename, mode.replace("t", ""), compresslevel) + + gz_mode = mode.replace("t", "") + if isinstance(filename, (str, bytes)): + binary_file = GzipFile(filename, gz_mode, compresslevel) + elif hasattr(filename, "read") or hasattr(filename, "write"): + binary_file = GzipFile(None, gz_mode, compresslevel, filename) + else: + raise TypeError("filename must be a str or bytes object, or a file") + if "t" in mode: return io.TextIOWrapper(binary_file, encoding, errors, newline) else: diff --git a/Lib/test/test_gzip.py b/Lib/test/test_gzip.py index 270411bd80c..bb9709776fd 100644 --- a/Lib/test/test_gzip.py +++ b/Lib/test/test_gzip.py @@ -424,8 +424,21 @@ class TestOpen(BaseTest): file_data = gzip.decompress(f.read()).decode("ascii") self.assertEqual(file_data, uncompressed_raw * 2) + def test_fileobj(self): + uncompressed_bytes = data1 * 50 + uncompressed_str = uncompressed_bytes.decode("ascii") + compressed = gzip.compress(uncompressed_bytes) + with gzip.open(io.BytesIO(compressed), "r") as f: + self.assertEqual(f.read(), uncompressed_bytes) + with gzip.open(io.BytesIO(compressed), "rb") as f: + self.assertEqual(f.read(), uncompressed_bytes) + with gzip.open(io.BytesIO(compressed), "rt") as f: + self.assertEqual(f.read(), uncompressed_str) + def test_bad_params(self): # Test invalid parameter combinations. + with self.assertRaises(TypeError): + gzip.open(123.456) with self.assertRaises(ValueError): gzip.open(self.filename, "wbt") with self.assertRaises(ValueError): diff --git a/Misc/NEWS b/Misc/NEWS index 479090f665c..46f3fd9cd26 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -15,6 +15,8 @@ Core and Builtins Library ------- +- gzip.open() now accepts file objects as well as filenames. + - Issue #14992: os.makedirs(path, exist_ok=True) would raise an OSError when the path existed and had the S_ISGID mode bit set when it was not explicitly asked for. This is no longer an exception as mkdir