123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350 |
- """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.
- import os
- import re
- import sys
- from collections import deque
- from io import StringIO
- __all__ = ["shlex", "split", "quote", "join"]
- class shlex:
- "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)
- if instream is not None:
- self.instream = instream
- self.infile = infile
- else:
- self.instream = sys.stdin
- self.infile = None
- self.posix = posix
- if posix:
- self.eof = None
- else:
- self.eof = ''
- self.commenters = '#'
- self.wordchars = ('abcdfeghijklmnopqrstuvwxyz'
- 'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_')
- if self.posix:
- self.wordchars += ('ßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ'
- 'ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ')
- self.whitespace = ' \t\r\n'
- self.whitespace_split = False
- self.quotes = '\'"'
- self.escape = '\\'
- self.escapedquotes = '"'
- self.state = ' '
- self.pushback = deque()
- self.lineno = 1
- self.debug = 0
- self.token = ''
- self.filestack = deque()
- self.source = None
- if not punctuation_chars:
- punctuation_chars = ''
- elif punctuation_chars is True:
- punctuation_chars = '();<>|&'
- self._punctuation_chars = punctuation_chars
- if 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)
- @property
- 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"
- if self.debug >= 1:
- 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.infile = newfile
- self.instream = newstream
- self.lineno = 1
- if self.debug:
- if newfile is not None:
- print('shlex: pushing to file %s' % (self.infile,))
- else:
- print('shlex: pushing to stream %s' % (self.instream,))
- def pop_source(self):
- "Pop the input source stack."
- self.instream.close()
- (self.infile, self.instream, self.lineno) = self.filestack.popleft()
- if self.debug:
- print('shlex: popping to %s, line %d' \
- % (self.instream, self.lineno))
- self.state = ' '
- def get_token(self):
- "Get a token from the input stream (or from stack if it's nonempty)"
- if self.pushback:
- tok = self.pushback.popleft()
- if self.debug >= 1:
- print("shlex: popping token " + repr(tok))
- return tok
- # No pushback. Get a token.
- raw = self.read_token()
- # Handle inclusions
- if self.source is not None:
- while raw == self.source:
- spec = self.sourcehook(self.read_token())
- if spec:
- (newfile, newstream) = spec
- self.push_source(newstream, newfile)
- raw = self.get_token()
- # Maybe we got EOF instead?
- while raw == self.eof:
- if not self.filestack:
- return self.eof
- else:
- self.pop_source()
- raw = self.get_token()
- # Neither inclusion nor EOF
- if self.debug >= 1:
- if raw != self.eof:
- print("shlex: token=" + repr(raw))
- else:
- print("shlex: token=EOF")
- return raw
- def read_token(self):
- quoted = False
- escapedstate = ' '
- while True:
- if self.punctuation_chars and self._pushback_chars:
- nextchar = self._pushback_chars.pop()
- else:
- nextchar = self.instream.read(1)
- if nextchar == '\n':
- self.lineno += 1
- if self.debug >= 3:
- print("shlex: in state %r I see character: %r" % (self.state,
- nextchar))
- if self.state is None:
- self.token = '' # past end of file
- break
- elif self.state == ' ':
- if not nextchar:
- self.state = None # end of file
- break
- elif nextchar in self.whitespace:
- if self.debug >= 2:
- print("shlex: I see whitespace in whitespace state")
- if self.token or (self.posix and quoted):
- break # emit current token
- else:
- continue
- elif nextchar in self.commenters:
- self.instream.readline()
- self.lineno += 1
- elif self.posix and nextchar in self.escape:
- escapedstate = 'a'
- self.state = nextchar
- elif nextchar in self.wordchars:
- self.token = nextchar
- self.state = 'a'
- elif nextchar in self.punctuation_chars:
- self.token = nextchar
- self.state = 'c'
- elif nextchar in self.quotes:
- if not self.posix:
- self.token = nextchar
- self.state = nextchar
- elif self.whitespace_split:
- self.token = nextchar
- self.state = 'a'
- else:
- self.token = nextchar
- if self.token or (self.posix and quoted):
- break # emit current token
- else:
- continue
- elif self.state in self.quotes:
- quoted = True
- if not nextchar: # end of file
- if self.debug >= 2:
- print("shlex: I see EOF in quotes state")
- # XXX what error should be raised here?
- raise ValueError("No closing quotation")
- if nextchar == self.state:
- if not self.posix:
- self.token += nextchar
- self.state = ' '
- break
- else:
- self.state = 'a'
- elif (self.posix and nextchar in self.escape and self.state
- in self.escapedquotes):
- escapedstate = self.state
- self.state = nextchar
- else:
- self.token += nextchar
- elif self.state in self.escape:
- if not nextchar: # end of file
- if self.debug >= 2:
- 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.token += self.state
- self.token += nextchar
- self.state = escapedstate
- elif self.state in ('a', 'c'):
- if not nextchar:
- self.state = None # end of file
- break
- elif nextchar in self.whitespace:
- if self.debug >= 2:
- print("shlex: I see whitespace in word state")
- self.state = ' '
- if self.token or (self.posix and quoted):
- break # emit current token
- else:
- continue
- elif nextchar in self.commenters:
- self.instream.readline()
- self.lineno += 1
- if self.posix:
- self.state = ' '
- if self.token or (self.posix and quoted):
- break # emit current token
- else:
- continue
- elif self.state == 'c':
- if nextchar in self.punctuation_chars:
- self.token += nextchar
- else:
- if nextchar not in self.whitespace:
- self._pushback_chars.append(nextchar)
- self.state = ' '
- break
- elif self.posix and nextchar in self.quotes:
- self.state = nextchar
- elif self.posix and nextchar in self.escape:
- escapedstate = 'a'
- self.state = nextchar
- elif (nextchar in self.wordchars or nextchar in self.quotes
- or (self.whitespace_split and
- nextchar not in self.punctuation_chars)):
- self.token += nextchar
- else:
- if self.punctuation_chars:
- self._pushback_chars.append(nextchar)
- else:
- self.pushback.appendleft(nextchar)
- if self.debug >= 2:
- print("shlex: I see punctuation in word state")
- self.state = ' '
- if self.token or (self.posix and quoted):
- break # emit current token
- else:
- continue
- result = self.token
- self.token = ''
- if self.posix and not quoted and result == '':
- result = None
- if self.debug > 1:
- if result:
- print("shlex: raw token=" + repr(result))
- else:
- print("shlex: raw token=EOF")
- return result
- def sourcehook(self, newfile):
- "Hook called on a filename to be sourced."
- if newfile[0] == '"':
- newfile = newfile[1:-1]
- # 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."
- if infile is None:
- infile = self.infile
- if lineno is None:
- lineno = self.lineno
- return "\"%s\", line %d: " % (infile, lineno)
- def __iter__(self):
- return self
- def __next__(self):
- token = self.get_token()
- if token == self.eof:
- raise StopIteration
- return token
- def split(s, comments=False, posix=True):
- """Split the string *s* using shell-like syntax."""
- if s is None:
- import warnings
- warnings.warn("Passing None for 's' to shlex.split() is deprecated.",
- DeprecationWarning, stacklevel=2)
- lex = shlex(s, posix=posix)
- lex.whitespace_split = True
- if not comments:
- lex.commenters = ''
- return list(lex)
- def join(split_command):
- """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
- def quote(s):
- """Return a shell-escaped version of the string *s*."""
- if not s:
- return "''"
- if _find_unsafe(s) is None:
- return s
- # 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):
- while 1:
- tt = lexer.get_token()
- if not tt:
- break
- print("Token: " + repr(tt))
- if __name__ == '__main__':
- if len(sys.argv) == 1:
- _print_tokens(shlex())
- else:
- fn = sys.argv[1]
- with open(fn) as f:
- _print_tokens(shlex(f, fn))
|