"""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 sys 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): from collections import deque # deferred import for performance 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." import os.path 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: raise ValueError("s argument must not be None") 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) def quote(s): """Return a shell-escaped version of the string *s*.""" if not s: return "''" if not isinstance(s, str): raise TypeError(f"expected string object, got {type(s).__name__!r}") # Use bytes.translate() for performance safe_chars = (b'%+,-./0123456789:=@' b'ABCDEFGHIJKLMNOPQRSTUVWXYZ_' b'abcdefghijklmnopqrstuvwxyz') # No quoting is needed if `s` is an ASCII string consisting only of `safe_chars` if s.isascii() and not s.encode().translate(None, delete=safe_chars): 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 tt := lexer.get_token(): 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))