"""A lexical analyzer class for simple shell-like syntaxes."""
# Module and documentation by Eric S. Raymond, 21 Dec 1998
# Input stacking and error message cleanup added by ESR, March 2000
# push_source() and pop_source() made explicit by ESR, January 2001.
# Posix compliance, split(), string arguments, and
# iterator interface by Gustavo Niemeyer, April 2003.
# changes to tokenize more like Posix shells by Vinay Sajip, July 2016.
from collections import deque
__all__ = ["shlex", "split", "quote", "join"]
"A lexical analyzer class for simple shell-like syntaxes."
def __init__(self, instream=None, infile=None, posix=False,
punctuation_chars=False):
if isinstance(instream, str):
instream = StringIO(instream)
self.instream = sys.stdin
self.wordchars = ('abcdfeghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_')
self.wordchars += ('ßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ'
'ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ')
self.whitespace = ' \t\r\n'
self.whitespace_split = False
if not punctuation_chars:
elif punctuation_chars is True:
punctuation_chars = '();<>|&'
self._punctuation_chars = punctuation_chars
# _pushback_chars is a push back queue used by lookahead logic
self._pushback_chars = deque()
# these chars added because allowed in file names, args, wildcards
self.wordchars += '~-./*?='
#remove any punctuation chars from wordchars
t = self.wordchars.maketrans(dict.fromkeys(punctuation_chars))
self.wordchars = self.wordchars.translate(t)
def punctuation_chars(self):
return self._punctuation_chars
def push_token(self, tok):
"Push a token onto the stack popped by the get_token method"
print("shlex: pushing token " + repr(tok))
self.pushback.appendleft(tok)
def push_source(self, newstream, newfile=None):
"Push an input source onto the lexer's input source stack."
if isinstance(newstream, str):
newstream = StringIO(newstream)
self.filestack.appendleft((self.infile, self.instream, self.lineno))
self.instream = newstream
print('shlex: pushing to file %s' % (self.infile,))
print('shlex: pushing to stream %s' % (self.instream,))
"Pop the input source stack."
(self.infile, self.instream, self.lineno) = self.filestack.popleft()
print('shlex: popping to %s, line %d' \
% (self.instream, self.lineno))
"Get a token from the input stream (or from stack if it's nonempty)"
tok = self.pushback.popleft()
print("shlex: popping token " + repr(tok))
# No pushback. Get a token.
if self.source is not None:
while raw == self.source:
spec = self.sourcehook(self.read_token())
(newfile, newstream) = spec
self.push_source(newstream, newfile)
# Maybe we got EOF instead?
# Neither inclusion nor EOF
print("shlex: token=" + repr(raw))
print("shlex: token=EOF")
if self.punctuation_chars and self._pushback_chars:
nextchar = self._pushback_chars.pop()
nextchar = self.instream.read(1)
print("shlex: in state %r I see character: %r" % (self.state,
self.token = '' # past end of file
self.state = None # end of file
elif nextchar in self.whitespace:
print("shlex: I see whitespace in whitespace state")
if self.token or (self.posix and quoted):
break # emit current token
elif nextchar in self.commenters:
elif self.posix and nextchar in self.escape:
elif nextchar in self.wordchars:
elif nextchar in self.punctuation_chars:
elif nextchar in self.quotes:
elif self.whitespace_split:
if self.token or (self.posix and quoted):
break # emit current token
elif self.state in self.quotes:
if not nextchar: # end of file
print("shlex: I see EOF in quotes state")
# XXX what error should be raised here?
raise ValueError("No closing quotation")
if nextchar == self.state:
elif (self.posix and nextchar in self.escape and self.state
escapedstate = self.state
elif self.state in self.escape:
if not nextchar: # end of file
print("shlex: I see EOF in escape state")
# XXX what error should be raised here?
raise ValueError("No escaped character")
# In posix shells, only the quote itself or the escape
# character may be escaped within quotes.
if (escapedstate in self.quotes and
nextchar != self.state and nextchar != escapedstate):
self.state = escapedstate
elif self.state in ('a', 'c'):
self.state = None # end of file
elif nextchar in self.whitespace:
print("shlex: I see whitespace in word state")
if self.token or (self.posix and quoted):
break # emit current token
elif nextchar in self.commenters:
if self.token or (self.posix and quoted):
break # emit current token
if nextchar in self.punctuation_chars:
if nextchar not in self.whitespace:
self._pushback_chars.append(nextchar)
elif self.posix and nextchar in self.quotes:
elif self.posix and nextchar in self.escape:
elif (nextchar in self.wordchars or nextchar in self.quotes
or (self.whitespace_split and
nextchar not in self.punctuation_chars)):
if self.punctuation_chars:
self._pushback_chars.append(nextchar)
self.pushback.appendleft(nextchar)
print("shlex: I see punctuation in word state")
if self.token or (self.posix and quoted):
break # emit current token
if self.posix and not quoted and result == '':
print("shlex: raw token=" + repr(result))
print("shlex: raw token=EOF")
def sourcehook(self, newfile):
"Hook called on a filename to be sourced."
# This implements cpp-like semantics for relative-path inclusion.
if isinstance(self.infile, str) and not os.path.isabs(newfile):
newfile = os.path.join(os.path.dirname(self.infile), newfile)
return (newfile, open(newfile, "r"))
def error_leader(self, infile=None, lineno=None):
"Emit a C-compiler-like, Emacs-friendly error-message leader."
return "\"%s\", line %d: " % (infile, lineno)
def split(s, comments=False, posix=True):
"""Split the string *s* using shell-like syntax."""
warnings.warn("Passing None for 's' to shlex.split() is deprecated.",
DeprecationWarning, stacklevel=2)
lex = shlex(s, posix=posix)
lex.whitespace_split = True
"""Return a shell-escaped string from *split_command*."""
return ' '.join(quote(arg) for arg in split_command)
_find_unsafe = re.compile(r'[^\w@%+=:,./-]', re.ASCII).search
"""Return a shell-escaped version of the string *s*."""
if _find_unsafe(s) is None:
# use single quotes, and put single quotes into double quotes
# the string $'b is then quoted as '$'"'"'b'
return "'" + s.replace("'", "'\"'\"'") + "'"
def _print_tokens(lexer):
print("Token: " + repr(tt))
if __name__ == '__main__':
_print_tokens(shlex(f, fn))
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
