diff options
author | Serhiy Storchaka <storchaka@gmail.com> | 2015-02-20 21:46:06 (GMT) |
---|---|---|
committer | Serhiy Storchaka <storchaka@gmail.com> | 2015-02-20 21:46:06 (GMT) |
commit | 5e3d7a401d8568d3308b8928b146a9c306bc3ca8 (patch) | |
tree | 03ed582741171729bef1b65c37c406d6ac5e866e | |
parent | e55181f517bbfc875065ce86ed3e05cf0e0246fa (diff) | |
download | cpython-5e3d7a401d8568d3308b8928b146a9c306bc3ca8.zip cpython-5e3d7a401d8568d3308b8928b146a9c306bc3ca8.tar.gz cpython-5e3d7a401d8568d3308b8928b146a9c306bc3ca8.tar.bz2 |
Issue #23374: Fixed pydoc failure with non-ASCII files when stdout encoding
differs from file system encoding (e.g. on Mac OS).
-rwxr-xr-x | Lib/pydoc.py | 22 | ||||
-rw-r--r-- | Lib/test/test_pydoc.py | 9 | ||||
-rw-r--r-- | Misc/NEWS | 3 |
3 files changed, 25 insertions, 9 deletions
diff --git a/Lib/pydoc.py b/Lib/pydoc.py index d37ebf1..8bbebc9 100755 --- a/Lib/pydoc.py +++ b/Lib/pydoc.py @@ -1407,9 +1407,6 @@ class _PlainTextDoc(TextDoc): def pager(text): """The first time this is called, determine what kind of pager to use.""" global pager - # Escape non-encodable characters to avoid encoding errors later - encoding = sys.getfilesystemencoding() - text = text.encode(encoding, 'backslashreplace').decode(encoding) pager = getpager() pager(text) @@ -1452,10 +1449,12 @@ def plain(text): def pipepager(text, cmd): """Page through text by feeding it to another program.""" - pipe = os.popen(cmd, 'w') + import subprocess + proc = subprocess.Popen(cmd, shell=True, stdin=subprocess.PIPE) try: - pipe.write(text) - pipe.close() + with proc: + with io.TextIOWrapper(proc.stdin, errors='backslashreplace') as pipe: + pipe.write(text) except OSError: pass # Ignore broken pipes caused by quitting the pager program. @@ -1463,16 +1462,21 @@ def tempfilepager(text, cmd): """Page through text by invoking a program on a temporary file.""" import tempfile filename = tempfile.mktemp() - with open(filename, 'w') as file: + with open(filename, 'w', errors='backslashreplace') as file: file.write(text) try: os.system(cmd + ' "' + filename + '"') finally: os.unlink(filename) +def _escape_stdout(text): + # Escape non-encodable characters to avoid encoding errors later + encoding = getattr(sys.stdout, 'encoding', None) or 'utf-8' + return text.encode(encoding, 'backslashreplace').decode(encoding) + def ttypager(text): """Page through text on a text terminal.""" - lines = plain(text).split('\n') + lines = plain(_escape_stdout(text)).split('\n') try: import tty fd = sys.stdin.fileno() @@ -1516,7 +1520,7 @@ def ttypager(text): def plainpager(text): """Simply print unformatted text. This is the ultimate fallback.""" - sys.stdout.write(plain(text)) + sys.stdout.write(plain(_escape_stdout(text))) def describe(thing): """Produce a short description of the given thing.""" diff --git a/Lib/test/test_pydoc.py b/Lib/test/test_pydoc.py index 1427c77..6a44c22 100644 --- a/Lib/test/test_pydoc.py +++ b/Lib/test/test_pydoc.py @@ -35,6 +35,10 @@ try: except ImportError: threading = None +class nonascii: + 'Це не латиниця' + pass + if test.support.HAVE_DOCSTRINGS: expected_data_docstrings = ( 'dictionary for instance variables (if defined)', @@ -474,6 +478,11 @@ class PydocDocTest(unittest.TestCase): self.assertEqual(expected, result, "documentation for missing module found") + def test_not_ascii(self): + result = run_pydoc('test.test_pydoc.nonascii', PYTHONIOENCODING='ascii') + encoded = nonascii.__doc__.encode('ascii', 'backslashreplace') + self.assertIn(encoded, result) + def test_input_strip(self): missing_module = " test.i_am_not_here " result = str(run_pydoc(missing_module), 'ascii') @@ -13,6 +13,9 @@ Core and Builtins Library ------- +- Issue #23374: Fixed pydoc failure with non-ASCII files when stdout encoding + differs from file system encoding (e.g. on Mac OS). + - Issue #23481: Remove RC4 from the SSL module's default cipher list. - Issue #21548: Fix pydoc.synopsis() and pydoc.apropos() on modules with empty |