Edit File: my_shlex.py
# -*- coding: utf-8 -*- # This copy of shlex.py is distributed with argcomplete. # It incorporates changes proposed in http://bugs.python.org/issue1521950 and changes to allow it to match Unicode # word characters. """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, January 2012. import os.path, sys, re from collections import deque # Note: cStringIO is not compatible with Unicode try: from StringIO import StringIO except ImportError: from io import StringIO try: basestring except NameError: basestring = str __all__ = ["shlex", "split"] class UnicodeWordchars: ''' A replacement for shlex.wordchars that also matches (__contains__) any Unicode wordchars. ''' def __init__(self, wordchars): self.wordchars = wordchars self.uw_regex = re.compile('\w', flags=re.UNICODE) def __contains__(self, c): return c in self.wordchars or self.uw_regex.match(c) 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, basestring): 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_') 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 self.wordchars = ''.join(c for c in self.wordchars if c not in self.punctuation_chars) for c in punctuation_chars: if c in self.wordchars: self.wordchars.remove(c) if self.posix: self.wordchars = UnicodeWordchars(self.wordchars) self.first_colon_pos = None def push_token(self, tok): "Push a token onto the stack popped by the get_token method" 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, basestring): newstream = StringIO(newstream) self.filestack.appendleft((self.infile, self.instream, self.lineno)) self.infile = newfile self.instream = newstream self.lineno = 1 def pop_source(self): "Pop the input source stack." self.instream.close() (self.infile, self.instream, self.lineno) = self.filestack.popleft() 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() 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 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.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.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 # 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 # 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: 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.posix and nextchar in self.quotes: self.state = nextchar elif self.posix and nextchar in self.escape: escapedstate = 'a' self.state = nextchar 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 (nextchar in self.wordchars or nextchar in self.quotes or self.whitespace_split): self.token += nextchar if nextchar == ':': self.first_colon_pos = len(self.token) - 1 else: if self.punctuation_chars: self._pushback_chars.append(nextchar) else: self.pushback.appendleft(nextchar) self.state = ' ' if self.token: break # emit current token else: continue result = self.token self.token = '' if self.posix and not quoted and result == '': result = None 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, basestring) 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, punctuation_chars=False): lex = shlex(s, posix=posix, punctuation_chars=punctuation_chars) lex.whitespace_split = True if not comments: lex.commenters = '' return list(lex)