FM / library

/usr/share/doc/python3-docs/html/_sources/library/

/usr/share/doc/python3-docs/html/_sources/library

Name	Size	Mode	Actions
2to3.rst.txt	15898	0644	edit dl rm
abc.rst.txt	11805	0644	edit dl rm
aifc.rst.txt	7503	0644	edit dl rm
allos.rst.txt	678	0644	edit dl rm
archiving.rst.txt	440	0644	edit dl rm
argparse.rst.txt	77480	0644	edit dl rm
array.rst.txt	10812	0644	edit dl rm
ast.rst.txt	10159	0644	edit dl rm
asynchat.rst.txt	8528	0644	edit dl rm
asyncio-dev.rst.txt	13398	0644	edit dl rm
asyncio-eventloop.rst.txt	33701	0644	edit dl rm
asyncio-eventloops.rst.txt	7660	0644	edit dl rm
asyncio-protocol.rst.txt	25170	0644	edit dl rm
asyncio-queue.rst.txt	4328	0644	edit dl rm
asyncio-stream.rst.txt	14363	0644	edit dl rm
asyncio-subprocess.rst.txt	15544	0644	edit dl rm
asyncio-sync.rst.txt	9078	0644	edit dl rm
asyncio-task.rst.txt	25406	0644	edit dl rm
asyncio.rst.txt	2272	0644	edit dl rm
asyncore.rst.txt	13624	0644	edit dl rm
atexit.rst.txt	3669	0644	edit dl rm
audioop.rst.txt	10712	0644	edit dl rm
base64.rst.txt	10371	0644	edit dl rm
bdb.rst.txt	12985	0644	edit dl rm
binary.rst.txt	654	0644	edit dl rm
binascii.rst.txt	6539	0644	edit dl rm
binhex.rst.txt	1709	0644	edit dl rm
bisect.rst.txt	5398	0644	edit dl rm
builtins.rst.txt	1465	0644	edit dl rm
bz2.rst.txt	8825	0644	edit dl rm
calendar.rst.txt	10988	0644	edit dl rm
cgi.rst.txt	22650	0644	edit dl rm
cgitb.rst.txt	2918	0644	edit dl rm
chunk.rst.txt	5094	0644	edit dl rm
cmath.rst.txt	9326	0644	edit dl rm
cmd.rst.txt	13795	0644	edit dl rm
code.rst.txt	7817	0644	edit dl rm
codecs.rst.txt	75564	0644	edit dl rm
codeop.rst.txt	3021	0644	edit dl rm
collections.abc.rst.txt	12861	0644	edit dl rm
collections.rst.txt	46063	0644	edit dl rm
colorsys.rst.txt	1820	0644	edit dl rm
compileall.rst.txt	8975	0644	edit dl rm
concurrency.rst.txt	673	0644	edit dl rm
concurrent.futures.rst.txt	16910	0644	edit dl rm
concurrent.rst.txt	171	0644	edit dl rm
configparser.rst.txt	48756	0644	edit dl rm
constants.rst.txt	3331	0644	edit dl rm
contextlib.rst.txt	28175	0644	edit dl rm
copy.rst.txt	3378	0644	edit dl rm
copyreg.rst.txt	2182	0644	edit dl rm
crypt.rst.txt	5122	0644	edit dl rm
crypto.rst.txt	411	0644	edit dl rm
csv.rst.txt	19902	0644	edit dl rm
ctypes.rst.txt	88613	0644	edit dl rm
curses.ascii.rst.txt	8920	0644	edit dl rm
curses.panel.rst.txt	2764	0644	edit dl rm
curses.rst.txt	76397	0644	edit dl rm
custominterp.rst.txt	569	0644	edit dl rm
datatypes.rst.txt	751	0644	edit dl rm
datetime.rst.txt	90524	0644	edit dl rm
dbm.rst.txt	14293	0644	edit dl rm
debug.rst.txt	471	0644	edit dl rm
decimal.rst.txt	74869	0644	edit dl rm
development.rst.txt	704	0644	edit dl rm
difflib.rst.txt	29861	0644	edit dl rm
dis.rst.txt	32567	0644	edit dl rm
distribution.rst.txt	452	0644	edit dl rm
distutils.rst.txt	1974	0644	edit dl rm
doctest.rst.txt	71743	0644	edit dl rm
dummy_threading.rst.txt	784	0644	edit dl rm
email.charset.rst.txt	9293	0644	edit dl rm
email.compat32-message.rst.txt	33493	0644	edit dl rm
email.contentmanager.rst.txt	9112	0644	edit dl rm
email.encoders.rst.txt	2715	0644	edit dl rm
email.errors.rst.txt	4792	0644	edit dl rm
email.examples.rst.txt	1915	0644	edit dl rm
email.generator.rst.txt	13637	0644	edit dl rm
email.header.rst.txt	9188	0644	edit dl rm
email.headerregistry.rst.txt	17957	0644	edit dl rm
email.iterators.rst.txt	2795	0644	edit dl rm
email.message.rst.txt	33008	0644	edit dl rm
email.mime.rst.txt	11721	0644	edit dl rm
email.parser.rst.txt	14092	0644	edit dl rm
email.policy.rst.txt	27022	0644	edit dl rm
email.rst.txt	6785	0644	edit dl rm
email.util.rst.txt	9214	0644	edit dl rm
ensurepip.rst.txt	4987	0644	edit dl rm
enum.rst.txt	32751	0644	edit dl rm
errno.rst.txt	6811	0644	edit dl rm
exceptions.rst.txt	25570	0644	edit dl rm
faulthandler.rst.txt	6136	0644	edit dl rm
fcntl.rst.txt	7152	0644	edit dl rm
filecmp.rst.txt	5623	0644	edit dl rm
fileformats.rst.txt	287	0644	edit dl rm
fileinput.rst.txt	8051	0644	edit dl rm
filesys.rst.txt	961	0644	edit dl rm
fnmatch.rst.txt	3103	0644	edit dl rm
formatter.rst.txt	13242	0644	edit dl rm
fpectl.rst.txt	4180	0644	edit dl rm
fractions.rst.txt	6364	0644	edit dl rm
frameworks.rst.txt	391	0644	edit dl rm
ftplib.rst.txt	17552	0644	edit dl rm
functional.rst.txt	365	0644	edit dl rm
functions.rst.txt	71621	0644	edit dl rm
functools.rst.txt	18503	0644	edit dl rm
gc.rst.txt	9694	0644	edit dl rm
getopt.rst.txt	6557	0644	edit dl rm
getpass.rst.txt	1882	0644	edit dl rm
gettext.rst.txt	25588	0644	edit dl rm
glob.rst.txt	3508	0644	edit dl rm
grp.rst.txt	2417	0644	edit dl rm
gzip.rst.txt	8301	0644	edit dl rm
hashlib.rst.txt	26523	0644	edit dl rm
heapq.rst.txt	13402	0644	edit dl rm
hmac.rst.txt	4020	0644	edit dl rm
html.entities.rst.txt	1319	0644	edit dl rm
html.parser.rst.txt	11275	0644	edit dl rm
html.rst.txt	1304	0644	edit dl rm
http.client.rst.txt	18870	0644	edit dl rm
http.cookiejar.rst.txt	27832	0644	edit dl rm
http.cookies.rst.txt	8645	0644	edit dl rm
http.rst.txt	7096	0644	edit dl rm
http.server.rst.txt	17639	0644	edit dl rm
i18n.rst.txt	408	0644	edit dl rm
idle.rst.txt	25834	0644	edit dl rm
imaplib.rst.txt	20367	0644	edit dl rm
imghdr.rst.txt	2938	0644	edit dl rm
imp.rst.txt	15548	0644	edit dl rm
importlib.rst.txt	53563	0644	edit dl rm
index.rst.txt	2258	0644	edit dl rm
inspect.rst.txt	53928	0644	edit dl rm
internet.rst.txt	992	0644	edit dl rm
intro.rst.txt	2645	0644	edit dl rm
io.rst.txt	40328	0644	edit dl rm
ipaddress.rst.txt	32340	0644	edit dl rm
ipc.rst.txt	649	0644	edit dl rm
itertools.rst.txt	38459	0644	edit dl rm
json.rst.txt	27876	0644	edit dl rm
keyword.rst.txt	617	0644	edit dl rm
language.rst.txt	522	0644	edit dl rm
linecache.rst.txt	2408	0644	edit dl rm
locale.rst.txt	25470	0644	edit dl rm
logging.config.rst.txt	33886	0644	edit dl rm
logging.handlers.rst.txt	42497	0644	edit dl rm
logging.rst.txt	60479	0644	edit dl rm
lzma.rst.txt	17361	0644	edit dl rm
macpath.rst.txt	707	0644	edit dl rm
mailbox.rst.txt	63055	0644	edit dl rm
mailcap.rst.txt	3691	0644	edit dl rm
markup.rst.txt	679	0644	edit dl rm
marshal.rst.txt	4855	0644	edit dl rm
math.rst.txt	14375	0644	edit dl rm
mimetypes.rst.txt	9839	0644	edit dl rm
misc.rst.txt	247	0644	edit dl rm
mm.rst.txt	431	0644	edit dl rm
mmap.rst.txt	11232	0644	edit dl rm
modulefinder.rst.txt	3240	0644	edit dl rm
modules.rst.txt	355	0644	edit dl rm
msilib.rst.txt	18612	0644	edit dl rm
msvcrt.rst.txt	4392	0644	edit dl rm
multiprocessing.rst.txt	104494	0644	edit dl rm
netdata.rst.txt	339	0644	edit dl rm
netrc.rst.txt	3007	0644	edit dl rm
nis.rst.txt	1993	0644	edit dl rm
nntplib.rst.txt	21821	0644	edit dl rm
numbers.rst.txt	8089	0644	edit dl rm
numeric.rst.txt	696	0644	edit dl rm
operator.rst.txt	18989	0644	edit dl rm
optparse.rst.txt	76996	0644	edit dl rm
os.path.rst.txt	16419	0644	edit dl rm
os.rst.txt	137534	0644	edit dl rm
ossaudiodev.rst.txt	17845	0644	edit dl rm
othergui.rst.txt	2822	0644	edit dl rm
parser.rst.txt	15148	0644	edit dl rm
pathlib.rst.txt	30045	0644	edit dl rm
pdb.rst.txt	19454	0644	edit dl rm
persistence.rst.txt	591	0644	edit dl rm
pickle.rst.txt	37440	0644	edit dl rm
pickletools.rst.txt	3729	0644	edit dl rm
pipes.rst.txt	2557	0644	edit dl rm
pkgutil.rst.txt	8730	0644	edit dl rm
platform.rst.txt	9624	0644	edit dl rm
plistlib.rst.txt	7398	0644	edit dl rm
poplib.rst.txt	8197	0644	edit dl rm
posix.rst.txt	3694	0644	edit dl rm
pprint.rst.txt	14274	0644	edit dl rm
profile.rst.txt	27969	0644	edit dl rm
pty.rst.txt	3123	0644	edit dl rm
pwd.rst.txt	2739	0644	edit dl rm
pyclbr.rst.txt	3297	0644	edit dl rm
pydoc.rst.txt	4688	0644	edit dl rm
pyexpat.rst.txt	28620	0644	edit dl rm
python.rst.txt	475	0644	edit dl rm
py_compile.rst.txt	3851	0644	edit dl rm
queue.rst.txt	7268	0644	edit dl rm
quopri.rst.txt	2571	0644	edit dl rm
random.rst.txt	18503	0644	edit dl rm
re.rst.txt	64936	0644	edit dl rm
readline.rst.txt	11943	0644	edit dl rm
reprlib.rst.txt	5162	0644	edit dl rm
resource.rst.txt	12291	0644	edit dl rm
rlcompleter.rst.txt	2294	0644	edit dl rm
runpy.rst.txt	8285	0644	edit dl rm
sched.rst.txt	4842	0644	edit dl rm
secrets.rst.txt	5930	0644	edit dl rm
select.rst.txt	28175	0644	edit dl rm
selectors.rst.txt	8925	0644	edit dl rm
shelve.rst.txt	8390	0644	edit dl rm
shlex.rst.txt	16441	0644	edit dl rm
shutil.rst.txt	26014	0644	edit dl rm
signal.rst.txt	17218	0644	edit dl rm
site.rst.txt	9628	0644	edit dl rm
smtpd.rst.txt	10806	0644	edit dl rm
smtplib.rst.txt	23439	0644	edit dl rm
sndhdr.rst.txt	1994	0644	edit dl rm
socket.rst.txt	68202	0644	edit dl rm
socketserver.rst.txt	23712	0644	edit dl rm
spwd.rst.txt	2958	0644	edit dl rm
sqlite3.rst.txt	39215	0644	edit dl rm
ssl.rst.txt	96021	0644	edit dl rm
stat.rst.txt	9805	0644	edit dl rm
statistics.rst.txt	15301	0644	edit dl rm
stdtypes.rst.txt	179240	0644	edit dl rm
string.rst.txt	35374	0644	edit dl rm
stringprep.rst.txt	4279	0644	edit dl rm
struct.rst.txt	19581	0644	edit dl rm
subprocess.rst.txt	45793	0644	edit dl rm
sunau.rst.txt	7390	0644	edit dl rm
superseded.rst.txt	258	0644	edit dl rm
symbol.rst.txt	975	0644	edit dl rm
symtable.rst.txt	4964	0644	edit dl rm
sys.rst.txt	58273	0644	edit dl rm
sysconfig.rst.txt	8749	0644	edit dl rm
syslog.rst.txt	4302	0644	edit dl rm
tabnanny.rst.txt	2007	0644	edit dl rm
tarfile.rst.txt	31749	0644	edit dl rm
telnetlib.rst.txt	7899	0644	edit dl rm
tempfile.rst.txt	13857	0644	edit dl rm
termios.rst.txt	3751	0644	edit dl rm
test.rst.txt	25764	0644	edit dl rm
text.rst.txt	584	0644	edit dl rm
textwrap.rst.txt	10519	0644	edit dl rm
threading.rst.txt	39257	0644	edit dl rm
time.rst.txt	32967	0644	edit dl rm
timeit.rst.txt	13000	0644	edit dl rm
tk.rst.txt	1639	0644	edit dl rm
tkinter.rst.txt	33027	0644	edit dl rm
tkinter.scrolledtext.rst.txt	1255	0644	edit dl rm
tkinter.tix.rst.txt	22653	0644	edit dl rm
tkinter.ttk.rst.txt	58489	0644	edit dl rm
token.rst.txt	2607	0644	edit dl rm
tokenize.rst.txt	10002	0644	edit dl rm
trace.rst.txt	6914	0644	edit dl rm
traceback.rst.txt	17854	0644	edit dl rm
tracemalloc.rst.txt	22089	0644	edit dl rm
tty.rst.txt	1097	0644	edit dl rm
turtle.rst.txt	71221	0644	edit dl rm
types.rst.txt	9999	0644	edit dl rm
typing.rst.txt	34332	0644	edit dl rm
undoc.rst.txt	780	0644	edit dl rm
unicodedata.rst.txt	5762	0644	edit dl rm
unittest.mock-examples.rst.txt	46206	0644	edit dl rm
unittest.mock.rst.txt	85991	0644	edit dl rm
unittest.rst.txt	93304	0644	edit dl rm
unix.rst.txt	446	0644	edit dl rm
urllib.error.rst.txt	2199	0644	edit dl rm
urllib.parse.rst.txt	27332	0644	edit dl rm
urllib.request.rst.txt	59360	0644	edit dl rm
urllib.robotparser.rst.txt	2969	0644	edit dl rm
urllib.rst.txt	466	0644	edit dl rm
uu.rst.txt	2387	0644	edit dl rm
uuid.rst.txt	8760	0644	edit dl rm
venv.rst.txt	20621	0644	edit dl rm
warnings.rst.txt	20152	0644	edit dl rm
wave.rst.txt	6870	0644	edit dl rm
weakref.rst.txt	21328	0644	edit dl rm
webbrowser.rst.txt	9783	0644	edit dl rm
windows.rst.txt	272	0644	edit dl rm
winreg.rst.txt	24073	0644	edit dl rm
winsound.rst.txt	5134	0644	edit dl rm
wsgiref.rst.txt	33047	0644	edit dl rm
xdrlib.rst.txt	8078	0644	edit dl rm
xml.dom.minidom.rst.txt	10198	0644	edit dl rm
xml.dom.pulldom.rst.txt	5186	0644	edit dl rm
xml.dom.rst.txt	39507	0644	edit dl rm
xml.etree.elementtree.rst.txt	43871	0644	edit dl rm
xml.rst.txt	6071	0644	edit dl rm
xml.sax.handler.rst.txt	15399	0644	edit dl rm
xml.sax.reader.rst.txt	12133	0644	edit dl rm
xml.sax.rst.txt	7159	0644	edit dl rm
xml.sax.utils.rst.txt	3901	0644	edit dl rm
xmlrpc.client.rst.txt	23071	0644	edit dl rm
xmlrpc.rst.txt	475	0644	edit dl rm
xmlrpc.server.rst.txt	14990	0644	edit dl rm
zipapp.rst.txt	17392	0644	edit dl rm
zipfile.rst.txt	24005	0644	edit dl rm
zipimport.rst.txt	5805	0644	edit dl rm
zlib.rst.txt	13912	0644	edit dl rm
_dummy_thread.rst.txt	762	0644	edit dl rm
_thread.rst.txt	6886	0644	edit dl rm
__future__.rst.txt	5245	0644	edit dl rm
__main__.rst.txt	904	0644	edit dl rm

Edit: /usr/share/doc/python3-docs/html/_sources/library/shlex.rst.txt (16441B)

:mod:`shlex` --- Simple lexical analysis
========================================

.. module:: shlex
   :synopsis: Simple lexical analysis for Unix shell-like languages.

.. moduleauthor:: Eric S. Raymond <esr@snark.thyrsus.com>
.. moduleauthor:: Gustavo Niemeyer <niemeyer@conectiva.com>
.. sectionauthor:: Eric S. Raymond <esr@snark.thyrsus.com>
.. sectionauthor:: Gustavo Niemeyer <niemeyer@conectiva.com>

**Source code:** :source:`Lib/shlex.py`

--------------

The :class:`~shlex.shlex` class makes it easy to write lexical analyzers for
simple syntaxes resembling that of the Unix shell.  This will often be useful
for writing minilanguages, (for example, in run control files for Python
applications) or for parsing quoted strings.

The :mod:`shlex` module defines the following functions:

.. function:: split(s, comments=False, posix=True)

Split the string *s* using shell-like syntax. If *comments* is :const:`False`
   (the default), the parsing of comments in the given string will be disabled
   (setting the :attr:`~shlex.commenters` attribute of the
   :class:`~shlex.shlex` instance to the empty string).  This function operates
   in POSIX mode by default, but uses non-POSIX mode if the *posix* argument is
   false.

.. note::

Since the :func:`split` function instantiates a :class:`~shlex.shlex`
      instance, passing ``None`` for *s* will read the string to split from
      standard input.

.. function:: quote(s)

Return a shell-escaped version of the string *s*.  The returned value is a
   string that can safely be used as one token in a shell command line, for
   cases where you cannot use a list.

This idiom would be unsafe::

>>> filename = 'somefile; rm -rf ~'
      >>> command = 'ls -l {}'.format(filename)
      >>> print(command)  # executed by a shell: boom!
      ls -l somefile; rm -rf ~

:func:`quote` lets you plug the security hole::

>>> command = 'ls -l {}'.format(quote(filename))
      >>> print(command)
      ls -l 'somefile; rm -rf ~'
      >>> remote_command = 'ssh home {}'.format(quote(command))
      >>> print(remote_command)
      ssh home 'ls -l '"'"'somefile; rm -rf ~'"'"''

The quoting is compatible with UNIX shells and with :func:`split`:

>>> remote_command = split(remote_command)
      >>> remote_command
      ['ssh', 'home', "ls -l 'somefile; rm -rf ~'"]
      >>> command = split(remote_command[-1])
      >>> command
      ['ls', '-l', 'somefile; rm -rf ~']

.. versionadded:: 3.3

The :mod:`shlex` module defines the following class:

.. class:: shlex(instream=None, infile=None, posix=False, punctuation_chars=False)

A :class:`~shlex.shlex` instance or subclass instance is a lexical analyzer
   object.  The initialization argument, if present, specifies where to read
   characters from.  It must be a file-/stream-like object with
   :meth:`~io.TextIOBase.read` and :meth:`~io.TextIOBase.readline` methods, or
   a string.  If no argument is given, input will be taken from ``sys.stdin``.
   The second optional argument is a filename string, which sets the initial
   value of the :attr:`~shlex.infile` attribute.  If the *instream*
   argument is omitted or equal to ``sys.stdin``, this second argument
   defaults to "stdin".  The *posix* argument defines the operational mode:
   when *posix* is not true (default), the :class:`~shlex.shlex` instance will
   operate in compatibility mode.  When operating in POSIX mode,
   :class:`~shlex.shlex` will try to be as close as possible to the POSIX shell
   parsing rules.  The *punctuation_chars* argument provides a way to make the
   behaviour even closer to how real shells parse.  This can take a number of
   values: the default value, ``False``, preserves the behaviour seen under
   Python 3.5 and earlier.  If set to ``True``, then parsing of the characters
   ``();<>|&`` is changed: any run of these characters (considered punctuation
   characters) is returned as a single token.  If set to a non-empty string of
   characters, those characters will be used as the punctuation characters.  Any
   characters in the :attr:`wordchars` attribute that appear in
   *punctuation_chars* will be removed from :attr:`wordchars`.  See
   :ref:`improved-shell-compatibility` for more information.

.. versionchanged:: 3.6
      The *punctuation_chars* parameter was added.

.. seealso::

Module :mod:`configparser`
      Parser for configuration files similar to the Windows :file:`.ini` files.

.. _shlex-objects:

shlex Objects
-------------

A :class:`~shlex.shlex` instance has the following methods:

.. method:: shlex.get_token()

Return a token.  If tokens have been stacked using :meth:`push_token`, pop a
   token off the stack.  Otherwise, read one from the input stream.  If reading
   encounters an immediate end-of-file, :attr:`eof` is returned (the empty
   string (``''``) in non-POSIX mode, and ``None`` in POSIX mode).

.. method:: shlex.push_token(str)

Push the argument onto the token stack.

.. method:: shlex.read_token()

Read a raw token.  Ignore the pushback stack, and do not interpret source
   requests.  (This is not ordinarily a useful entry point, and is documented here
   only for the sake of completeness.)

.. method:: shlex.sourcehook(filename)

When :class:`~shlex.shlex` detects a source request (see :attr:`source`
   below) this method is given the following token as argument, and expected
   to return a tuple consisting of a filename and an open file-like object.

Normally, this method first strips any quotes off the argument.  If the result
   is an absolute pathname, or there was no previous source request in effect, or
   the previous source was a stream (such as ``sys.stdin``), the result is left
   alone.  Otherwise, if the result is a relative pathname, the directory part of
   the name of the file immediately before it on the source inclusion stack is
   prepended (this behavior is like the way the C preprocessor handles ``#include
   "file.h"``).

The result of the manipulations is treated as a filename, and returned as the
   first component of the tuple, with :func:`open` called on it to yield the second
   component. (Note: this is the reverse of the order of arguments in instance
   initialization!)

This hook is exposed so that you can use it to implement directory search paths,
   addition of file extensions, and other namespace hacks. There is no
   corresponding 'close' hook, but a shlex instance will call the
   :meth:`~io.IOBase.close` method of the sourced input stream when it returns
   EOF.

For more explicit control of source stacking, use the :meth:`push_source` and
   :meth:`pop_source` methods.

.. method:: shlex.push_source(newstream, newfile=None)

Push an input source stream onto the input stack.  If the filename argument is
   specified it will later be available for use in error messages.  This is the
   same method used internally by the :meth:`sourcehook` method.

.. method:: shlex.pop_source()

Pop the last-pushed input source from the input stack. This is the same method
   used internally when the lexer reaches EOF on a stacked input stream.

.. method:: shlex.error_leader(infile=None, lineno=None)

This method generates an error message leader in the format of a Unix C compiler
   error label; the format is ``'"%s", line %d: '``, where the ``%s`` is replaced
   with the name of the current source file and the ``%d`` with the current input
   line number (the optional arguments can be used to override these).

This convenience is provided to encourage :mod:`shlex` users to generate error
   messages in the standard, parseable format understood by Emacs and other Unix
   tools.

Instances of :class:`~shlex.shlex` subclasses have some public instance
variables which either control lexical analysis or can be used for debugging:

.. attribute:: shlex.commenters

The string of characters that are recognized as comment beginners. All
   characters from the comment beginner to end of line are ignored. Includes just
   ``'#'`` by default.

.. attribute:: shlex.wordchars

The string of characters that will accumulate into multi-character tokens.  By
   default, includes all ASCII alphanumerics and underscore.  In POSIX mode, the
   accented characters in the Latin-1 set are also included.  If
   :attr:`punctuation_chars` is not empty, the characters ``~-./*?=``, which can
   appear in filename specifications and command line parameters, will also be
   included in this attribute, and any characters which appear in
   ``punctuation_chars`` will be removed from ``wordchars`` if they are present
   there.

.. attribute:: shlex.whitespace

Characters that will be considered whitespace and skipped.  Whitespace bounds
   tokens.  By default, includes space, tab, linefeed and carriage-return.

.. attribute:: shlex.escape

Characters that will be considered as escape. This will be only used in POSIX
   mode, and includes just ``'\'`` by default.

.. attribute:: shlex.quotes

Characters that will be considered string quotes.  The token accumulates until
   the same quote is encountered again (thus, different quote types protect each
   other as in the shell.)  By default, includes ASCII single and double quotes.

.. attribute:: shlex.escapedquotes

Characters in :attr:`quotes` that will interpret escape characters defined in
   :attr:`escape`.  This is only used in POSIX mode, and includes just ``'"'`` by
   default.

.. attribute:: shlex.whitespace_split

If ``True``, tokens will only be split in whitespaces.  This is useful, for
   example, for parsing command lines with :class:`~shlex.shlex`, getting
   tokens in a similar way to shell arguments.  If this attribute is ``True``,
   :attr:`punctuation_chars` will have no effect, and splitting will happen
   only on whitespaces.  When using :attr:`punctuation_chars`, which is
   intended to provide parsing closer to that implemented by shells, it is
   advisable to leave ``whitespace_split`` as ``False`` (the default value).

.. attribute:: shlex.infile

The name of the current input file, as initially set at class instantiation time
   or stacked by later source requests.  It may be useful to examine this when
   constructing error messages.

.. attribute:: shlex.instream

The input stream from which this :class:`~shlex.shlex` instance is reading
   characters.

.. attribute:: shlex.source

This attribute is ``None`` by default.  If you assign a string to it, that
   string will be recognized as a lexical-level inclusion request similar to the
   ``source`` keyword in various shells.  That is, the immediately following token
   will be opened as a filename and input will be taken from that stream until
   EOF, at which point the :meth:`~io.IOBase.close` method of that stream will be
   called and the input source will again become the original input stream.  Source
   requests may be stacked any number of levels deep.

.. attribute:: shlex.debug

If this attribute is numeric and ``1`` or more, a :class:`~shlex.shlex`
   instance will print verbose progress output on its behavior.  If you need
   to use this, you can read the module source code to learn the details.

.. attribute:: shlex.lineno

Source line number (count of newlines seen so far plus one).

.. attribute:: shlex.token

The token buffer.  It may be useful to examine this when catching exceptions.

.. attribute:: shlex.eof

Token used to determine end of file. This will be set to the empty string
   (``''``), in non-POSIX mode, and to ``None`` in POSIX mode.

.. attribute:: shlex.punctuation_chars

Characters that will be considered punctuation. Runs of punctuation
   characters will be returned as a single token. However, note that no
   semantic validity checking will be performed: for example, '>>>' could be
   returned as a token, even though it may not be recognised as such by shells.

.. versionadded:: 3.6

.. _shlex-parsing-rules:

Parsing Rules
-------------

When operating in non-POSIX mode, :class:`~shlex.shlex` will try to obey to the
following rules.

* Quote characters are not recognized within words (``Do"Not"Separate`` is
  parsed as the single word ``Do"Not"Separate``);

* Escape characters are not recognized;

* Enclosing characters in quotes preserve the literal value of all characters
  within the quotes;

* Closing quotes separate words (``"Do"Separate`` is parsed as ``"Do"`` and
  ``Separate``);

* If :attr:`~shlex.whitespace_split` is ``False``, any character not
  declared to be a word character, whitespace, or a quote will be returned as
  a single-character token. If it is ``True``, :class:`~shlex.shlex` will only
  split words in whitespaces;

* EOF is signaled with an empty string (``''``);

* It's not possible to parse empty strings, even if quoted.

When operating in POSIX mode, :class:`~shlex.shlex` will try to obey to the
following parsing rules.

* Quotes are stripped out, and do not separate words (``"Do"Not"Separate"`` is
  parsed as the single word ``DoNotSeparate``);

* Non-quoted escape characters (e.g. ``'\'``) preserve the literal value of the
  next character that follows;

* Enclosing characters in quotes which are not part of
  :attr:`~shlex.escapedquotes` (e.g. ``"'"``) preserve the literal value
  of all characters within the quotes;

* Enclosing characters in quotes which are part of
  :attr:`~shlex.escapedquotes` (e.g. ``'"'``) preserves the literal value
  of all characters within the quotes, with the exception of the characters
  mentioned in :attr:`~shlex.escape`.  The escape characters retain its
  special meaning only when followed by the quote in use, or the escape
  character itself. Otherwise the escape character will be considered a
  normal character.

* EOF is signaled with a :const:`None` value;

* Quoted empty strings (``''``) are allowed.

.. _improved-shell-compatibility:

Improved Compatibility with Shells
----------------------------------

.. versionadded:: 3.6

The :class:`shlex` class provides compatibility with the parsing performed by
common Unix shells like ``bash``, ``dash``, and ``sh``.  To take advantage of
this compatibility, specify the ``punctuation_chars`` argument in the
constructor.  This defaults to ``False``, which preserves pre-3.6 behaviour.
However, if it is set to ``True``, then parsing of the characters ``();<>|&``
is changed: any run of these characters is returned as a single token.  While
this is short of a full parser for shells (which would be out of scope for the
standard library, given the multiplicity of shells out there), it does allow
you to perform processing of command lines more easily than you could
otherwise.  To illustrate, you can see the difference in the following snippet:

.. doctest::
   :options: +NORMALIZE_WHITESPACE

>>> import shlex
    >>> text = "a && b; c && d || e; f >'abc'; (def \"ghi\")"
    >>> list(shlex.shlex(text))
    ['a', '&', '&', 'b', ';', 'c', '&', '&', 'd', '|', '|', 'e', ';', 'f', '>',
    "'abc'", ';', '(', 'def', '"ghi"', ')']
    >>> list(shlex.shlex(text, punctuation_chars=True))
    ['a', '&&', 'b', ';', 'c', '&&', 'd', '||', 'e', ';', 'f', '>', "'abc'",
    ';', '(', 'def', '"ghi"', ')']

Of course, tokens will be returned which are not valid for shells, and you'll
need to implement your own error checks on the returned tokens.

Instead of passing ``True`` as the value for the punctuation_chars parameter,
you can pass a string with specific characters, which will be used to determine
which characters constitute punctuation. For example::

>>> import shlex
    >>> s = shlex.shlex("a && b || c", punctuation_chars="|")
    >>> list(s)
    ['a', '&', '&', 'b', '||', 'c']

.. note:: When ``punctuation_chars`` is specified, the :attr:`~shlex.wordchars`
   attribute is augmented with the characters ``~-./*?=``.  That is because these
   characters can appear in file names (including wildcards) and command-line
   arguments (e.g. ``--color=auto``). Hence::

>>> import shlex
      >>> s = shlex.shlex('~/a && b-c --color=auto || d *.py?',
      ...                 punctuation_chars=True)
      >>> list(s)
      ['~/a', '&&', 'b-c', '--color=auto', '||', 'd', '*.py?']

For best effect, ``punctuation_chars`` should be set in conjunction with
``posix=True``. (Note that ``posix=False`` is the default for
:class:`~shlex.shlex`.)

:mod:`shlex` --- Simple lexical analysis ======================================== .. module:: shlex :synopsis: Simple lexical analysis for Unix shell-like languages. .. moduleauthor:: Eric S. Raymond .. moduleauthor:: Gustavo Niemeyer .. sectionauthor:: Eric S. Raymond .. sectionauthor:: Gustavo Niemeyer **Source code:** :source:`Lib/shlex.py` -------------- The :class:`~shlex.shlex` class makes it easy to write lexical analyzers for simple syntaxes resembling that of the Unix shell. This will often be useful for writing minilanguages, (for example, in run control files for Python applications) or for parsing quoted strings. The :mod:`shlex` module defines the following functions: .. function:: split(s, comments=False, posix=True) Split the string *s* using shell-like syntax. If *comments* is :const:`False` (the default), the parsing of comments in the given string will be disabled (setting the :attr:`~shlex.commenters` attribute of the :class:`~shlex.shlex` instance to the empty string). This function operates in POSIX mode by default, but uses non-POSIX mode if the *posix* argument is false. .. note:: Since the :func:`split` function instantiates a :class:`~shlex.shlex` instance, passing ``None`` for *s* will read the string to split from standard input. .. function:: quote(s) Return a shell-escaped version of the string *s*. The returned value is a string that can safely be used as one token in a shell command line, for cases where you cannot use a list. This idiom would be unsafe:: >>> filename = 'somefile; rm -rf ~' >>> command = 'ls -l {}'.format(filename) >>> print(command) # executed by a shell: boom! ls -l somefile; rm -rf ~ :func:`quote` lets you plug the security hole:: >>> command = 'ls -l {}'.format(quote(filename)) >>> print(command) ls -l 'somefile; rm -rf ~' >>> remote_command = 'ssh home {}'.format(quote(command)) >>> print(remote_command) ssh home 'ls -l '"'"'somefile; rm -rf ~'"'"'' The quoting is compatible with UNIX shells and with :func:`split`: >>> remote_command = split(remote_command) >>> remote_command ['ssh', 'home', "ls -l 'somefile; rm -rf ~'"] >>> command = split(remote_command[-1]) >>> command ['ls', '-l', 'somefile; rm -rf ~'] .. versionadded:: 3.3 The :mod:`shlex` module defines the following class: .. class:: shlex(instream=None, infile=None, posix=False, punctuation_chars=False) A :class:`~shlex.shlex` instance or subclass instance is a lexical analyzer object. The initialization argument, if present, specifies where to read characters from. It must be a file-/stream-like object with :meth:`~io.TextIOBase.read` and :meth:`~io.TextIOBase.readline` methods, or a string. If no argument is given, input will be taken from ``sys.stdin``. The second optional argument is a filename string, which sets the initial value of the :attr:`~shlex.infile` attribute. If the *instream* argument is omitted or equal to ``sys.stdin``, this second argument defaults to "stdin". The *posix* argument defines the operational mode: when *posix* is not true (default), the :class:`~shlex.shlex` instance will operate in compatibility mode. When operating in POSIX mode, :class:`~shlex.shlex` will try to be as close as possible to the POSIX shell parsing rules. The *punctuation_chars* argument provides a way to make the behaviour even closer to how real shells parse. This can take a number of values: the default value, ``False``, preserves the behaviour seen under Python 3.5 and earlier. If set to ``True``, then parsing of the characters ``();<>|&`` is changed: any run of these characters (considered punctuation characters) is returned as a single token. If set to a non-empty string of characters, those characters will be used as the punctuation characters. Any characters in the :attr:`wordchars` attribute that appear in *punctuation_chars* will be removed from :attr:`wordchars`. See :ref:`improved-shell-compatibility` for more information. .. versionchanged:: 3.6 The *punctuation_chars* parameter was added. .. seealso:: Module :mod:`configparser` Parser for configuration files similar to the Windows :file:`.ini` files. .. _shlex-objects: shlex Objects ------------- A :class:`~shlex.shlex` instance has the following methods: .. method:: shlex.get_token() Return a token. If tokens have been stacked using :meth:`push_token`, pop a token off the stack. Otherwise, read one from the input stream. If reading encounters an immediate end-of-file, :attr:`eof` is returned (the empty string (``''``) in non-POSIX mode, and ``None`` in POSIX mode). .. method:: shlex.push_token(str) Push the argument onto the token stack. .. method:: shlex.read_token() Read a raw token. Ignore the pushback stack, and do not interpret source requests. (This is not ordinarily a useful entry point, and is documented here only for the sake of completeness.) .. method:: shlex.sourcehook(filename) When :class:`~shlex.shlex` detects a source request (see :attr:`source` below) this method is given the following token as argument, and expected to return a tuple consisting of a filename and an open file-like object. Normally, this method first strips any quotes off the argument. If the result is an absolute pathname, or there was no previous source request in effect, or the previous source was a stream (such as ``sys.stdin``), the result is left alone. Otherwise, if the result is a relative pathname, the directory part of the name of the file immediately before it on the source inclusion stack is prepended (this behavior is like the way the C preprocessor handles ``#include "file.h"``). The result of the manipulations is treated as a filename, and returned as the first component of the tuple, with :func:`open` called on it to yield the second component. (Note: this is the reverse of the order of arguments in instance initialization!) This hook is exposed so that you can use it to implement directory search paths, addition of file extensions, and other namespace hacks. There is no corresponding 'close' hook, but a shlex instance will call the :meth:`~io.IOBase.close` method of the sourced input stream when it returns EOF. For more explicit control of source stacking, use the :meth:`push_source` and :meth:`pop_source` methods. .. method:: shlex.push_source(newstream, newfile=None) Push an input source stream onto the input stack. If the filename argument is specified it will later be available for use in error messages. This is the same method used internally by the :meth:`sourcehook` method. .. method:: shlex.pop_source() Pop the last-pushed input source from the input stack. This is the same method used internally when the lexer reaches EOF on a stacked input stream. .. method:: shlex.error_leader(infile=None, lineno=None) This method generates an error message leader in the format of a Unix C compiler error label; the format is ``'"%s", line %d: '``, where the ``%s`` is replaced with the name of the current source file and the ``%d`` with the current input line number (the optional arguments can be used to override these). This convenience is provided to encourage :mod:`shlex` users to generate error messages in the standard, parseable format understood by Emacs and other Unix tools. Instances of :class:`~shlex.shlex` subclasses have some public instance variables which either control lexical analysis or can be used for debugging: .. attribute:: shlex.commenters The string of characters that are recognized as comment beginners. All characters from the comment beginner to end of line are ignored. Includes just ``'#'`` by default. .. attribute:: shlex.wordchars The string of characters that will accumulate into multi-character tokens. By default, includes all ASCII alphanumerics and underscore. In POSIX mode, the accented characters in the Latin-1 set are also included. If :attr:`punctuation_chars` is not empty, the characters ``~-./*?=``, which can appear in filename specifications and command line parameters, will also be included in this attribute, and any characters which appear in ``punctuation_chars`` will be removed from ``wordchars`` if they are present there. .. attribute:: shlex.whitespace Characters that will be considered whitespace and skipped. Whitespace bounds tokens. By default, includes space, tab, linefeed and carriage-return. .. attribute:: shlex.escape Characters that will be considered as escape. This will be only used in POSIX mode, and includes just ``'\'`` by default. .. attribute:: shlex.quotes Characters that will be considered string quotes. The token accumulates until the same quote is encountered again (thus, different quote types protect each other as in the shell.) By default, includes ASCII single and double quotes. .. attribute:: shlex.escapedquotes Characters in :attr:`quotes` that will interpret escape characters defined in :attr:`escape`. This is only used in POSIX mode, and includes just ``'"'`` by default. .. attribute:: shlex.whitespace_split If ``True``, tokens will only be split in whitespaces. This is useful, for example, for parsing command lines with :class:`~shlex.shlex`, getting tokens in a similar way to shell arguments. If this attribute is ``True``, :attr:`punctuation_chars` will have no effect, and splitting will happen only on whitespaces. When using :attr:`punctuation_chars`, which is intended to provide parsing closer to that implemented by shells, it is advisable to leave ``whitespace_split`` as ``False`` (the default value). .. attribute:: shlex.infile The name of the current input file, as initially set at class instantiation time or stacked by later source requests. It may be useful to examine this when constructing error messages. .. attribute:: shlex.instream The input stream from which this :class:`~shlex.shlex` instance is reading characters. .. attribute:: shlex.source This attribute is ``None`` by default. If you assign a string to it, that string will be recognized as a lexical-level inclusion request similar to the ``source`` keyword in various shells. That is, the immediately following token will be opened as a filename and input will be taken from that stream until EOF, at which point the :meth:`~io.IOBase.close` method of that stream will be called and the input source will again become the original input stream. Source requests may be stacked any number of levels deep. .. attribute:: shlex.debug If this attribute is numeric and ``1`` or more, a :class:`~shlex.shlex` instance will print verbose progress output on its behavior. If you need to use this, you can read the module source code to learn the details. .. attribute:: shlex.lineno Source line number (count of newlines seen so far plus one). .. attribute:: shlex.token The token buffer. It may be useful to examine this when catching exceptions. .. attribute:: shlex.eof Token used to determine end of file. This will be set to the empty string (``''``), in non-POSIX mode, and to ``None`` in POSIX mode. .. attribute:: shlex.punctuation_chars Characters that will be considered punctuation. Runs of punctuation characters will be returned as a single token. However, note that no semantic validity checking will be performed: for example, '>>>' could be returned as a token, even though it may not be recognised as such by shells. .. versionadded:: 3.6 .. _shlex-parsing-rules: Parsing Rules ------------- When operating in non-POSIX mode, :class:`~shlex.shlex` will try to obey to the following rules. * Quote characters are not recognized within words (``Do"Not"Separate`` is parsed as the single word ``Do"Not"Separate``); * Escape characters are not recognized; * Enclosing characters in quotes preserve the literal value of all characters within the quotes; * Closing quotes separate words (``"Do"Separate`` is parsed as ``"Do"`` and ``Separate``); * If :attr:`~shlex.whitespace_split` is ``False``, any character not declared to be a word character, whitespace, or a quote will be returned as a single-character token. If it is ``True``, :class:`~shlex.shlex` will only split words in whitespaces; * EOF is signaled with an empty string (``''``); * It's not possible to parse empty strings, even if quoted. When operating in POSIX mode, :class:`~shlex.shlex` will try to obey to the following parsing rules. * Quotes are stripped out, and do not separate words (``"Do"Not"Separate"`` is parsed as the single word ``DoNotSeparate``); * Non-quoted escape characters (e.g. ``'\'``) preserve the literal value of the next character that follows; * Enclosing characters in quotes which are not part of :attr:`~shlex.escapedquotes` (e.g. ``"'"``) preserve the literal value of all characters within the quotes; * Enclosing characters in quotes which are part of :attr:`~shlex.escapedquotes` (e.g. ``'"'``) preserves the literal value of all characters within the quotes, with the exception of the characters mentioned in :attr:`~shlex.escape`. The escape characters retain its special meaning only when followed by the quote in use, or the escape character itself. Otherwise the escape character will be considered a normal character. * EOF is signaled with a :const:`None` value; * Quoted empty strings (``''``) are allowed. .. _improved-shell-compatibility: Improved Compatibility with Shells ---------------------------------- .. versionadded:: 3.6 The :class:`shlex` class provides compatibility with the parsing performed by common Unix shells like ``bash``, ``dash``, and ``sh``. To take advantage of this compatibility, specify the ``punctuation_chars`` argument in the constructor. This defaults to ``False``, which preserves pre-3.6 behaviour. However, if it is set to ``True``, then parsing of the characters ``();<>|&`` is changed: any run of these characters is returned as a single token. While this is short of a full parser for shells (which would be out of scope for the standard library, given the multiplicity of shells out there), it does allow you to perform processing of command lines more easily than you could otherwise. To illustrate, you can see the difference in the following snippet: .. doctest:: :options: +NORMALIZE_WHITESPACE >>> import shlex >>> text = "a && b; c && d || e; f >'abc'; (def \"ghi\")" >>> list(shlex.shlex(text)) ['a', '&', '&', 'b', ';', 'c', '&', '&', 'd', '|', '|', 'e', ';', 'f', '>', "'abc'", ';', '(', 'def', '"ghi"', ')'] >>> list(shlex.shlex(text, punctuation_chars=True)) ['a', '&&', 'b', ';', 'c', '&&', 'd', '||', 'e', ';', 'f', '>', "'abc'", ';', '(', 'def', '"ghi"', ')'] Of course, tokens will be returned which are not valid for shells, and you'll need to implement your own error checks on the returned tokens. Instead of passing ``True`` as the value for the punctuation_chars parameter, you can pass a string with specific characters, which will be used to determine which characters constitute punctuation. For example:: >>> import shlex >>> s = shlex.shlex("a && b || c", punctuation_chars="|") >>> list(s) ['a', '&', '&', 'b', '||', 'c'] .. note:: When ``punctuation_chars`` is specified, the :attr:`~shlex.wordchars` attribute is augmented with the characters ``~-./*?=``. That is because these characters can appear in file names (including wildcards) and command-line arguments (e.g. ``--color=auto``). Hence:: >>> import shlex >>> s = shlex.shlex('~/a && b-c --color=auto || d *.py?', ... punctuation_chars=True) >>> list(s) ['~/a', '&&', 'b-c', '--color=auto', '||', 'd', '*.py?'] For best effect, ``punctuation_chars`` should be set in conjunction with ``posix=True``. (Note that ``posix=False`` is the default for :class:`~shlex.shlex`.)