Kaydet (Commit) 050acaed authored tarafından Steve Dower's avatar Steve Dower

Issue #6135: Adds encoding and errors parameters to subprocess

üst 173a1f3d
This diff is collapsed.
......@@ -589,6 +589,9 @@ proc: ...``) or call explicitly the :meth:`~subprocess.Popen.wait` method to
read the exit status of the child process (Contributed by Victor Stinner in
:issue:`26741`).
The :class:`subprocess.Popen` constructor and all functions that pass arguments
through to it now accept *encoding* and *errors* arguments. Specifying either
of these will enable text mode for the *stdin*, *stdout* and *stderr* streams.
telnetlib
---------
......
......@@ -30,7 +30,8 @@ class Popen(args, bufsize=-1, executable=None,
preexec_fn=None, close_fds=True, shell=False,
cwd=None, env=None, universal_newlines=False,
startupinfo=None, creationflags=0,
restore_signals=True, start_new_session=False, pass_fds=()):
restore_signals=True, start_new_session=False, pass_fds=(),
*, encoding=None, errors=None):
Arguments are:
......@@ -104,20 +105,13 @@ in the child process prior to executing the command.
If env is not None, it defines the environment variables for the new
process.
If universal_newlines is False, the file objects stdin, stdout and stderr
are opened as binary files, and no line ending conversion is done.
If encoding or errors are specified or universal_newlines is True, the file
objects stdout and stderr are opened in text mode. See io.TextIOWrapper for
the interpretation of these parameters are used.
If universal_newlines is True, the file objects stdout and stderr are
opened as a text file, but lines may be terminated by any of '\n',
the Unix end-of-line convention, '\r', the old Macintosh convention or
'\r\n', the Windows convention. All of these external representations
are seen as '\n' by the Python program. Also, the newlines attribute
of the file objects stdout, stdin and stderr are not updated by the
communicate() method.
In either case, the process being communicated with should start up
expecting to receive bytes on its standard input and decode them with
the same encoding they are sent in.
If no encoding is specified and universal_newlines is False, the file
objects stdin, stdout and stderr are opened as binary files, and no
line ending conversion is done.
The startupinfo and creationflags, if given, will be passed to the
underlying CreateProcess() function. They can specify things such as
......@@ -234,11 +228,8 @@ communicate(input=None)
and stderr, until end-of-file is reached. Wait for process to
terminate. The optional input argument should be data to be
sent to the child process, or None, if no data should be sent to
the child. If the Popen instance was constructed with universal_newlines
set to True, the input argument should be a string and will be encoded
using the preferred system encoding (see locale.getpreferredencoding);
if universal_newlines is False, the input argument should be a
byte string.
the child. If the Popen instance was constructed in text mode, the
input argument should be a string. Otherwise, it should be bytes.
communicate() returns a tuple (stdout, stderr).
......@@ -808,8 +799,8 @@ def getstatusoutput(cmd):
""" Return (status, output) of executing cmd in a shell.
Execute the string 'cmd' in a shell with 'check_output' and
return a 2-tuple (status, output). Universal newlines mode is used,
meaning that the result with be decoded to a string.
return a 2-tuple (status, output). The locale encoding is used
to decode the output and process newlines.
A trailing newline is stripped from the output.
The exit status for the command can be interpreted
......@@ -859,7 +850,7 @@ class Popen(object):
shell=False, cwd=None, env=None, universal_newlines=False,
startupinfo=None, creationflags=0,
restore_signals=True, start_new_session=False,
pass_fds=()):
pass_fds=(), *, encoding=None, errors=None):
"""Create new Popen instance."""
_cleanup()
# Held while anything is calling waitpid before returncode has been
......@@ -912,6 +903,8 @@ class Popen(object):
self.pid = None
self.returncode = None
self.universal_newlines = universal_newlines
self.encoding = encoding
self.errors = errors
# Input and output objects. The general principle is like
# this:
......@@ -944,22 +937,28 @@ class Popen(object):
if errread != -1:
errread = msvcrt.open_osfhandle(errread.Detach(), 0)
if p2cwrite != -1:
self.stdin = io.open(p2cwrite, 'wb', bufsize)
if universal_newlines:
self.stdin = io.TextIOWrapper(self.stdin, write_through=True,
line_buffering=(bufsize == 1))
if c2pread != -1:
self.stdout = io.open(c2pread, 'rb', bufsize)
if universal_newlines:
self.stdout = io.TextIOWrapper(self.stdout)
if errread != -1:
self.stderr = io.open(errread, 'rb', bufsize)
if universal_newlines:
self.stderr = io.TextIOWrapper(self.stderr)
text_mode = encoding or errors or universal_newlines
self._closed_child_pipe_fds = False
try:
if p2cwrite != -1:
self.stdin = io.open(p2cwrite, 'wb', bufsize)
if text_mode:
self.stdin = io.TextIOWrapper(self.stdin, write_through=True,
line_buffering=(bufsize == 1),
encoding=encoding, errors=errors)
if c2pread != -1:
self.stdout = io.open(c2pread, 'rb', bufsize)
if text_mode:
self.stdout = io.TextIOWrapper(self.stdout,
encoding=encoding, errors=errors)
if errread != -1:
self.stderr = io.open(errread, 'rb', bufsize)
if text_mode:
self.stderr = io.TextIOWrapper(self.stderr,
encoding=encoding, errors=errors)
self._execute_child(args, executable, preexec_fn, close_fds,
pass_fds, cwd, env,
startupinfo, creationflags, shell,
......@@ -993,8 +992,8 @@ class Popen(object):
raise
def _translate_newlines(self, data, encoding):
data = data.decode(encoding)
def _translate_newlines(self, data, encoding, errors):
data = data.decode(encoding, errors)
return data.replace("\r\n", "\n").replace("\r", "\n")
def __enter__(self):
......@@ -1779,13 +1778,15 @@ class Popen(object):
# Translate newlines, if requested.
# This also turns bytes into strings.
if self.universal_newlines:
if self.encoding or self.errors or self.universal_newlines:
if stdout is not None:
stdout = self._translate_newlines(stdout,
self.stdout.encoding)
self.stdout.encoding,
self.stdout.errors)
if stderr is not None:
stderr = self._translate_newlines(stderr,
self.stderr.encoding)
self.stderr.encoding,
self.stderr.errors)
return (stdout, stderr)
......@@ -1797,8 +1798,10 @@ class Popen(object):
if self.stdin and self._input is None:
self._input_offset = 0
self._input = input
if self.universal_newlines and input is not None:
self._input = self._input.encode(self.stdin.encoding)
if input is not None and (
self.encoding or self.errors or self.universal_newlines):
self._input = self._input.encode(self.stdin.encoding,
self.stdin.errors)
def send_signal(self, sig):
......
......@@ -894,31 +894,42 @@ class ProcessTestCase(BaseTestCase):
#
# UTF-16 and UTF-32-BE are sufficient to check both with BOM and
# without, and UTF-16 and UTF-32.
import _bootlocale
for encoding in ['utf-16', 'utf-32-be']:
old_getpreferredencoding = _bootlocale.getpreferredencoding
# Indirectly via io.TextIOWrapper, Popen() defaults to
# locale.getpreferredencoding(False) and earlier in Python 3.2 to
# locale.getpreferredencoding().
def getpreferredencoding(do_setlocale=True):
return encoding
code = ("import sys; "
r"sys.stdout.buffer.write('1\r\n2\r3\n4'.encode('%s'))" %
encoding)
args = [sys.executable, '-c', code]
try:
_bootlocale.getpreferredencoding = getpreferredencoding
# We set stdin to be non-None because, as of this writing,
# a different code path is used when the number of pipes is
# zero or one.
popen = subprocess.Popen(args, universal_newlines=True,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
stdout, stderr = popen.communicate(input='')
finally:
_bootlocale.getpreferredencoding = old_getpreferredencoding
# We set stdin to be non-None because, as of this writing,
# a different code path is used when the number of pipes is
# zero or one.
popen = subprocess.Popen(args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
encoding=encoding)
stdout, stderr = popen.communicate(input='')
self.assertEqual(stdout, '1\n2\n3\n4')
def test_communicate_errors(self):
for errors, expected in [
('ignore', ''),
('replace', '\ufffd\ufffd'),
('surrogateescape', '\udc80\udc80'),
('backslashreplace', '\\x80\\x80'),
]:
code = ("import sys; "
r"sys.stdout.buffer.write(b'[\x80\x80]')")
args = [sys.executable, '-c', code]
# We set stdin to be non-None because, as of this writing,
# a different code path is used when the number of pipes is
# zero or one.
popen = subprocess.Popen(args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
encoding='utf-8',
errors=errors)
stdout, stderr = popen.communicate(input='')
self.assertEqual(stdout, '[{}]'.format(expected))
def test_no_leaking(self):
# Make sure we leak no resources
if not mswindows:
......@@ -2539,6 +2550,18 @@ class Win32ProcessTestCase(BaseTestCase):
with p:
self.assertIn(b"physalis", p.stdout.read())
def test_shell_encodings(self):
# Run command through the shell (string)
for enc in ['ansi', 'oem']:
newenv = os.environ.copy()
newenv["FRUIT"] = "physalis"
p = subprocess.Popen("set", shell=1,
stdout=subprocess.PIPE,
env=newenv,
encoding=enc)
with p:
self.assertIn("physalis", p.stdout.read(), enc)
def test_call_string(self):
# call() function with string argument on Windows
rc = subprocess.call(sys.executable +
......
......@@ -237,6 +237,8 @@ Build
Windows
-------
- Issue #6135: Adds encoding and errors parameters to subprocess.
- Issue #27959: Adds oem encoding, alias ansi to mbcs, move aliasmbcs to
codec lookup.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment