Moving posix version of arg_split to _process_common.

IPython/utils/_process_common.py

@@ -1,145 +1,170 b''
 """Common utilities for the various process_* implementations.
 
 This file is only meant to be imported by the platform-specific implementations
 of subprocess utilities, and it contains tools that are common to all of them.
 """
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 import subprocess
+import shlex
 import sys
 
 from IPython.utils import py3compat
 
 #-----------------------------------------------------------------------------
 # Function definitions
 #-----------------------------------------------------------------------------
 
 def read_no_interrupt(p):
     """Read from a pipe ignoring EINTR errors.
 
     This is necessary because when reading from pipes with GUI event loops
     running in the background, often interrupts are raised that stop the
     command from completing."""
     import errno
 
     try:
         return p.read()
     except IOError, err:
         if err.errno != errno.EINTR:
             raise
 
 
 def process_handler(cmd, callback, stderr=subprocess.PIPE):
     """Open a command in a shell subprocess and execute a callback.
 
     This function provides common scaffolding for creating subprocess.Popen()
     calls.  It creates a Popen object and then calls the callback with it.
 
     Parameters
     ----------
     cmd : str
       A string to be executed with the underlying system shell (by calling
     :func:`Popen` with ``shell=True``.
 
     callback : callable
       A one-argument function that will be called with the Popen object.
 
     stderr : file descriptor number, optional
       By default this is set to ``subprocess.PIPE``, but you can also pass the
       value ``subprocess.STDOUT`` to force the subprocess' stderr to go into
       the same file descriptor as its stdout.  This is useful to read stdout
       and stderr combined in the order they are generated.
 
     Returns
     -------
     The return value of the provided callback is returned.
     """
     sys.stdout.flush()
     sys.stderr.flush()
     # On win32, close_fds can't be true when using pipes for stdin/out/err
     close_fds = sys.platform != 'win32'
     p = subprocess.Popen(cmd, shell=True,
                          stdin=subprocess.PIPE,
                          stdout=subprocess.PIPE,
                          stderr=stderr,
                          close_fds=close_fds)
 
     try:
         out = callback(p)
     except KeyboardInterrupt:
         print('^C')
         sys.stdout.flush()
         sys.stderr.flush()
         out = None
     finally:
         # Make really sure that we don't leave processes behind, in case the
         # call above raises an exception
         # We start by assuming the subprocess finished (to avoid NameErrors
         # later depending on the path taken)
         if p.returncode is None:
             try:
                 p.terminate()
                 p.poll()
             except OSError:
                 pass
         # One last try on our way out
         if p.returncode is None:
             try:
                 p.kill()
             except OSError:
                 pass
 
     return out
 
 
 def getoutput(cmd):
     """Return standard output of executing cmd in a shell.
 
     Accepts the same arguments as os.system().
 
     Parameters
     ----------
     cmd : str
       A command to be executed in the system shell.
 
     Returns
     -------
     stdout : str
     """
 
     out = process_handler(cmd, lambda p: p.communicate()[0], subprocess.STDOUT)
     if out is None:
         return ''
     return py3compat.bytes_to_str(out)
 
 
 def getoutputerror(cmd):
     """Return (standard output, standard error) of executing cmd in a shell.
 
     Accepts the same arguments as os.system().
 
     Parameters
     ----------
     cmd : str
       A command to be executed in the system shell.
 
     Returns
     -------
     stdout : str
     stderr : str
     """
 
     out_err = process_handler(cmd, lambda p: p.communicate())
     if out_err is None:
         return '', ''
     out, err = out_err
     return py3compat.bytes_to_str(out), py3compat.bytes_to_str(err)
+
+
+def arg_split(s, posix=False):
+    """Split a command line's arguments in a shell-like manner.
+
+    This is a modified version of the standard library's shlex.split()
+    function, but with a default of posix=False for splitting, so that quotes
+    in inputs are respected."""
+
+    # Unfortunately, python's shlex module is buggy with unicode input:
+    # http://bugs.python.org/issue1170
+    # At least encoding the input when it's unicode seems to help, but there
+    # may be more problems lurking.  Apparently this is fixed in python3.
+    is_unicode = False
+    if (not py3compat.PY3) and isinstance(s, unicode):
+        is_unicode = True
+        s = s.encode('utf-8')
+    lex = shlex.shlex(s, posix=posix)
+    lex.whitespace_split = True
+    tokens = list(lex)
+    if is_unicode:
+        # Convert the tokens back to unicode.
+        tokens = [x.decode('utf-8') for x in tokens]
+    return tokens

IPython/utils/_process_posix.py

@@ -1,221 +1,197 b''
 """Posix-specific implementation of process utilities.
 
 This file is only meant to be imported by process.py, not by end-users.
 """
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 from __future__ import print_function
 
 # Stdlib
 import subprocess as sp
 import sys
-import shlex
 
 from IPython.external import pexpect
 
 # Our own
 from .autoattr import auto_attr
-from ._process_common import getoutput
+from ._process_common import getoutput, arg_split
 from IPython.utils import text
 from IPython.utils import py3compat
 
 #-----------------------------------------------------------------------------
 # Function definitions
 #-----------------------------------------------------------------------------
 
 def _find_cmd(cmd):
     """Find the full path to a command using which."""
 
     path = sp.Popen(['/usr/bin/env', 'which', cmd],
                     stdout=sp.PIPE).communicate()[0]
     return py3compat.bytes_to_str(path)
 
 
 class ProcessHandler(object):
     """Execute subprocesses under the control of pexpect.
     """
     # Timeout in seconds to wait on each reading of the subprocess' output.
     # This should not be set too low to avoid cpu overusage from our side,
     # since we read in a loop whose period is controlled by this timeout.
     read_timeout = 0.05
 
     # Timeout to give a process if we receive SIGINT, between sending the
     # SIGINT to the process and forcefully terminating it.
     terminate_timeout = 0.2
 
     # File object where stdout and stderr of the subprocess will be written
     logfile = None
 
     # Shell to call for subprocesses to execute
     sh = None
 
     @auto_attr
     def sh(self):
         sh = pexpect.which('sh')
         if sh is None:
             raise OSError('"sh" shell not found')
         return sh
 
     def __init__(self, logfile=None, read_timeout=None, terminate_timeout=None):
         """Arguments are used for pexpect calls."""
         self.read_timeout = (ProcessHandler.read_timeout if read_timeout is
                              None else read_timeout)
         self.terminate_timeout = (ProcessHandler.terminate_timeout if
                                   terminate_timeout is None else
                                   terminate_timeout)
         self.logfile = sys.stdout if logfile is None else logfile
 
     def getoutput(self, cmd):
         """Run a command and return its stdout/stderr as a string.
 
         Parameters
         ----------
         cmd : str
           A command to be executed in the system shell.
 
         Returns
         -------
         output : str
           A string containing the combination of stdout and stderr from the
         subprocess, in whatever order the subprocess originally wrote to its
         file descriptors (so the order of the information in this string is the
         correct order as would be seen if running the command in a terminal).
         """
         try:
             return pexpect.run(self.sh, args=['-c', cmd]).replace('\r\n', '\n')
         except KeyboardInterrupt:
             print('^C', file=sys.stderr, end='')
 
     def getoutput_pexpect(self, cmd):
         """Run a command and return its stdout/stderr as a string.
 
         Parameters
         ----------
         cmd : str
           A command to be executed in the system shell.
 
         Returns
         -------
         output : str
           A string containing the combination of stdout and stderr from the
         subprocess, in whatever order the subprocess originally wrote to its
         file descriptors (so the order of the information in this string is the
         correct order as would be seen if running the command in a terminal).
         """
         try:
             return pexpect.run(self.sh, args=['-c', cmd]).replace('\r\n', '\n')
         except KeyboardInterrupt:
             print('^C', file=sys.stderr, end='')
 
     def system(self, cmd):
         """Execute a command in a subshell.
 
         Parameters
         ----------
         cmd : str
           A command to be executed in the system shell.
 
         Returns
         -------
         int : child's exitstatus
         """
         # Get likely encoding for the output.
         enc = text.getdefaultencoding()
         
         # Patterns to match on the output, for pexpect.  We read input and
         # allow either a short timeout or EOF
         patterns = [pexpect.TIMEOUT, pexpect.EOF]
         # the index of the EOF pattern in the list.
         # even though we know it's 1, this call means we don't have to worry if
         # we change the above list, and forget to change this value:
         EOF_index = patterns.index(pexpect.EOF)
         # The size of the output stored so far in the process output buffer.
         # Since pexpect only appends to this buffer, each time we print we
         # record how far we've printed, so that next time we only print *new*
         # content from the buffer.
         out_size = 0
         try:
             # Since we're not really searching the buffer for text patterns, we
             # can set pexpect's search window to be tiny and it won't matter.
             # We only search for the 'patterns' timeout or EOF, which aren't in
             # the text itself.
             #child = pexpect.spawn(pcmd, searchwindowsize=1)
             if hasattr(pexpect, 'spawnb'):
                 child = pexpect.spawnb(self.sh, args=['-c', cmd]) # Pexpect-U
             else:
                 child = pexpect.spawn(self.sh, args=['-c', cmd])  # Vanilla Pexpect
             flush = sys.stdout.flush
             while True:
                 # res is the index of the pattern that caused the match, so we
                 # know whether we've finished (if we matched EOF) or not
                 res_idx = child.expect_list(patterns, self.read_timeout)
                 print(child.before[out_size:].decode(enc, 'replace'), end='')
                 flush()
                 if res_idx==EOF_index:
                     break
                 # Update the pointer to what we've already printed
                 out_size = len(child.before)
         except KeyboardInterrupt:
             # We need to send ^C to the process.  The ascii code for '^C' is 3
             # (the character is known as ETX for 'End of Text', see
             # curses.ascii.ETX).
             child.sendline(chr(3))
             # Read and print any more output the program might produce on its
             # way out.
             try:
                 out_size = len(child.before)
                 child.expect_list(patterns, self.terminate_timeout)
                 print(child.before[out_size:].decode(enc, 'replace'), end='')
                 sys.stdout.flush()
             except KeyboardInterrupt:
                 # Impatient users tend to type it multiple times
                 pass
             finally:
                 # Ensure the subprocess really is terminated
                 child.terminate(force=True)
         # add isalive check, to ensure exitstatus is set:
         child.isalive()
         return child.exitstatus
 
 
 # Make system() with a functional interface for outside use.  Note that we use
 # getoutput() from the _common utils, which is built on top of popen(). Using
 # pexpect to get subprocess output produces difficult to parse output, since
 # programs think they are talking to a tty and produce highly formatted output
 # (ls is a good example) that makes them hard.
 system = ProcessHandler().system
 
-def arg_split(s, posix=False):
-    """Split a command line's arguments in a shell-like manner.
-
-    This is a modified version of the standard library's shlex.split()
-    function, but with a default of posix=False for splitting, so that quotes
-    in inputs are respected."""
-
-    # Unfortunately, python's shlex module is buggy with unicode input:
-    # http://bugs.python.org/issue1170
-    # At least encoding the input when it's unicode seems to help, but there
-    # may be more problems lurking.  Apparently this is fixed in python3.
-    is_unicode = False
-    if (not py3compat.PY3) and isinstance(s, unicode):
-        is_unicode = True
-        s = s.encode('utf-8')
-    lex = shlex.shlex(s, posix=posix)
-    lex.whitespace_split = True
-    tokens = list(lex)
-    if is_unicode:
-        # Convert the tokens back to unicode.
-        tokens = [x.decode('utf-8') for x in tokens]
-    return tokens
-
 
 

IPython/utils/_process_win32.py

@@ -1,201 +1,178 b''
 """Windows-specific implementation of process utilities.
 
 This file is only meant to be imported by process.py, not by end-users.
 """
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 from __future__ import print_function
 
 # stdlib
 import os
 import sys
 import ctypes
 
 from ctypes import c_int, POINTER
 from ctypes.wintypes import LPCWSTR, HLOCAL
 from subprocess import STDOUT
 
 # our own imports
 from ._process_common import read_no_interrupt, process_handler
 from . import py3compat
 from . import text
 
 #-----------------------------------------------------------------------------
 # Function definitions
 #-----------------------------------------------------------------------------
 
 class AvoidUNCPath(object):
     """A context manager to protect command execution from UNC paths.
 
     In the Win32 API, commands can't be invoked with the cwd being a UNC path.
     This context manager temporarily changes directory to the 'C:' drive on
     entering, and restores the original working directory on exit.
 
     The context manager returns the starting working directory *if* it made a
     change and None otherwise, so that users can apply the necessary adjustment
     to their system calls in the event of a change.
 
     Example
     -------
     ::
         cmd = 'dir'
         with AvoidUNCPath() as path:
             if path is not None:
                 cmd = '"pushd %s &&"%s' % (path, cmd)
             os.system(cmd)
     """
     def __enter__(self):
         self.path = os.getcwdu()
         self.is_unc_path = self.path.startswith(r"\\")
         if self.is_unc_path:
             # change to c drive (as cmd.exe cannot handle UNC addresses)
             os.chdir("C:")
             return self.path
         else:
             # We return None to signal that there was no change in the working
             # directory
             return None
 
     def __exit__(self, exc_type, exc_value, traceback):
         if self.is_unc_path:
             os.chdir(self.path)
 
 
 def _find_cmd(cmd):
     """Find the full path to a .bat or .exe using the win32api module."""
     try:
         from win32api import SearchPath
     except ImportError:
         raise ImportError('you need to have pywin32 installed for this to work')
     else:
         PATH = os.environ['PATH']
         extensions = ['.exe', '.com', '.bat', '.py']
         path = None
         for ext in extensions:
             try:
                 path = SearchPath(PATH, cmd + ext)[0]
             except:
                 pass
         if path is None:
             raise OSError("command %r not found" % cmd)
         else:
             return path
 
 
 def _system_body(p):
     """Callback for _system."""
     enc = text.getdefaultencoding()
     for line in read_no_interrupt(p.stdout).splitlines():
         line = line.decode(enc, 'replace')
         print(line, file=sys.stdout)
     for line in read_no_interrupt(p.stderr).splitlines():
         line = line.decode(enc, 'replace')
         print(line, file=sys.stderr)
 
     # Wait to finish for returncode
     return p.wait()
 
 
 def system(cmd):
     """Win32 version of os.system() that works with network shares.
 
     Note that this implementation returns None, as meant for use in IPython.
 
     Parameters
     ----------
     cmd : str
       A command to be executed in the system shell.
 
     Returns
     -------
     None : we explicitly do NOT return the subprocess status code, as this
     utility is meant to be used extensively in IPython, where any return value
     would trigger :func:`sys.displayhook` calls.
     """
     with AvoidUNCPath() as path:
         if path is not None:
             cmd = '"pushd %s &&"%s' % (path, cmd)
         return process_handler(cmd, _system_body)
 
 
 def getoutput(cmd):
     """Return standard output of executing cmd in a shell.
 
     Accepts the same arguments as os.system().
 
     Parameters
     ----------
     cmd : str
       A command to be executed in the system shell.
 
     Returns
     -------
     stdout : str
     """
 
     with AvoidUNCPath() as path:
         if path is not None:
             cmd = '"pushd %s &&"%s' % (path, cmd)
         out = process_handler(cmd, lambda p: p.communicate()[0], STDOUT)
 
     if out is None:
         out = ''
     return out
 
 try:
     CommandLineToArgvW = ctypes.windll.shell32.CommandLineToArgvW
     CommandLineToArgvW.arg_types = [LPCWSTR, POINTER(c_int)]
     CommandLineToArgvW.res_types = [POINTER(LPCWSTR)]
     LocalFree = ctypes.windll.kernel32.LocalFree
     LocalFree.res_type = HLOCAL
     LocalFree.arg_types = [HLOCAL]
     
     def arg_split(commandline, posix=False):
         """Split a command line's arguments in a shell-like manner.
 
         This is a special version for windows that use a ctypes call to CommandLineToArgvW
         to do the argv splitting. The posix paramter is ignored.
         """
         #CommandLineToArgvW returns path to executable if called with empty string.
         if commandline.strip() == "":
             return []
         argvn = c_int()
         result_pointer = CommandLineToArgvW(py3compat.cast_unicode(commandline.lstrip()), ctypes.byref(argvn))
         result_array_type = LPCWSTR * argvn.value
         result = [arg for arg in result_array_type.from_address(result_pointer)]
         retval = LocalFree(result_pointer)
         return result
 except AttributeError:
-    import shlex
-    #alternative if CommandLineToArgvW is not available
-    def arg_split(s, posix=False):
-        """Split a command line's arguments in a shell-like manner.
-
-        This is a modified version of the standard library's shlex.split()
-        function, but with a default of posix=False for splitting, so that quotes
-        in inputs are respected."""
-
-        # Unfortunately, python's shlex module is buggy with unicode input:
-        # http://bugs.python.org/issue1170
-        # At least encoding the input when it's unicode seems to help, but there
-        # may be more problems lurking.  Apparently this is fixed in python3.
-        is_unicode = False
-        if (not py3compat.PY3) and isinstance(s, unicode):
-            is_unicode = True
-            s = s.encode('utf-8')
-        lex = shlex.shlex(s, posix=posix)
-        lex.whitespace_split = True
-        tokens = list(lex)
-        if is_unicode:
-            # Convert the tokens back to unicode.
-            tokens = [x.decode('utf-8') for x in tokens]
-        return tokens
+    from ._process_common import arg_split