Closes #1521950: Made shlex parsing more shell-like.
diff --git a/Lib/shlex.py b/Lib/shlex.py
index f083918..e87266f 100644
--- a/Lib/shlex.py
+++ b/Lib/shlex.py
@@ -5,6 +5,7 @@
# 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
@@ -17,7 +18,8 @@
class shlex:
"A lexical analyzer class for simple shell-like syntaxes."
- def __init__(self, instream=None, infile=None, posix=False):
+ def __init__(self, instream=None, infile=None, posix=False,
+ punctuation_chars=False):
if isinstance(instream, str):
instream = StringIO(instream)
if instream is not None:
@@ -49,6 +51,19 @@
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)
def push_token(self, tok):
"Push a token onto the stack popped by the get_token method"
@@ -115,12 +130,15 @@
quoted = False
escapedstate = ' '
while True:
- nextchar = self.instream.read(1)
+ if self.punctuation_chars and self._pushback_chars:
+ nextchar = self._pushback_chars.pop()
+ else:
+ nextchar = self.instream.read(1)
if nextchar == '\n':
- self.lineno = self.lineno + 1
+ self.lineno += 1
if self.debug >= 3:
- print("shlex: in state", repr(self.state), \
- "I see character:", repr(nextchar))
+ print("shlex: in state %r I see character: %r" % (self.state,
+ nextchar))
if self.state is None:
self.token = '' # past end of file
break
@@ -137,13 +155,16 @@
continue
elif nextchar in self.commenters:
self.instream.readline()
- self.lineno = self.lineno + 1
+ 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
@@ -166,17 +187,17 @@
raise ValueError("No closing quotation")
if nextchar == self.state:
if not self.posix:
- self.token = self.token + nextchar
+ self.token += nextchar
self.state = ' '
break
else:
self.state = 'a'
- elif self.posix and nextchar in self.escape and \
- self.state in self.escapedquotes:
+ elif (self.posix and nextchar in self.escape and self.state
+ in self.escapedquotes):
escapedstate = self.state
self.state = nextchar
else:
- self.token = self.token + nextchar
+ self.token += nextchar
elif self.state in self.escape:
if not nextchar: # end of file
if self.debug >= 2:
@@ -185,12 +206,12 @@
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.token + self.state
- self.token = self.token + nextchar
+ 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 == 'a':
+ elif self.state in ('a', 'c'):
if not nextchar:
self.state = None # end of file
break
@@ -204,7 +225,7 @@
continue
elif nextchar in self.commenters:
self.instream.readline()
- self.lineno = self.lineno + 1
+ self.lineno += 1
if self.posix:
self.state = ' '
if self.token or (self.posix and quoted):
@@ -216,15 +237,26 @@
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:
- self.token = self.token + 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
else:
- self.pushback.appendleft(nextchar)
+ 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:
+ if self.token or (self.posix and quoted):
break # emit current token
else:
continue
diff --git a/Lib/test/test_shlex.py b/Lib/test/test_shlex.py
index 4fafdd4..3936c97 100644
--- a/Lib/test/test_shlex.py
+++ b/Lib/test/test_shlex.py
@@ -173,6 +173,118 @@
"%s: %s != %s" %
(self.data[i][0], l, self.data[i][1:]))
+ def testSyntaxSplitAmpersandAndPipe(self):
+ """Test handling of syntax splitting of &, |"""
+ # Could take these forms: &&, &, |&, ;&, ;;&
+ # of course, the same applies to | and ||
+ # these should all parse to the same output
+ for delimiter in ('&&', '&', '|&', ';&', ';;&',
+ '||', '|', '&|', ';|', ';;|'):
+ src = ['echo hi %s echo bye' % delimiter,
+ 'echo hi%secho bye' % delimiter]
+ ref = ['echo', 'hi', delimiter, 'echo', 'bye']
+ for ss in src:
+ s = shlex.shlex(ss, punctuation_chars=True)
+ result = list(s)
+ self.assertEqual(ref, result, "While splitting '%s'" % ss)
+
+ def testSyntaxSplitSemicolon(self):
+ """Test handling of syntax splitting of ;"""
+ # Could take these forms: ;, ;;, ;&, ;;&
+ # these should all parse to the same output
+ for delimiter in (';', ';;', ';&', ';;&'):
+ src = ['echo hi %s echo bye' % delimiter,
+ 'echo hi%s echo bye' % delimiter,
+ 'echo hi%secho bye' % delimiter]
+ ref = ['echo', 'hi', delimiter, 'echo', 'bye']
+ for ss in src:
+ s = shlex.shlex(ss, punctuation_chars=True)
+ result = list(s)
+ self.assertEqual(ref, result, "While splitting '%s'" % ss)
+
+ def testSyntaxSplitRedirect(self):
+ """Test handling of syntax splitting of >"""
+ # of course, the same applies to <, |
+ # these should all parse to the same output
+ for delimiter in ('<', '|'):
+ src = ['echo hi %s out' % delimiter,
+ 'echo hi%s out' % delimiter,
+ 'echo hi%sout' % delimiter]
+ ref = ['echo', 'hi', delimiter, 'out']
+ for ss in src:
+ s = shlex.shlex(ss, punctuation_chars=True)
+ result = list(s)
+ self.assertEqual(ref, result, "While splitting '%s'" % ss)
+
+ def testSyntaxSplitParen(self):
+ """Test handling of syntax splitting of ()"""
+ # these should all parse to the same output
+ src = ['( echo hi )',
+ '(echo hi)']
+ ref = ['(', 'echo', 'hi', ')']
+ for ss in src:
+ s = shlex.shlex(ss, punctuation_chars=True)
+ result = list(s)
+ self.assertEqual(ref, result, "While splitting '%s'" % ss)
+
+ def testSyntaxSplitCustom(self):
+ """Test handling of syntax splitting with custom chars"""
+ ref = ['~/a', '&', '&', 'b-c', '--color=auto', '||', 'd', '*.py?']
+ ss = "~/a && b-c --color=auto || d *.py?"
+ s = shlex.shlex(ss, punctuation_chars="|")
+ result = list(s)
+ self.assertEqual(ref, result, "While splitting '%s'" % ss)
+
+ def testTokenTypes(self):
+ """Test that tokens are split with types as expected."""
+ for source, expected in (
+ ('a && b || c',
+ [('a', 'a'), ('&&', 'c'), ('b', 'a'),
+ ('||', 'c'), ('c', 'a')]),
+ ):
+ s = shlex.shlex(source, punctuation_chars=True)
+ observed = []
+ while True:
+ t = s.get_token()
+ if t == s.eof:
+ break
+ if t[0] in s.punctuation_chars:
+ tt = 'c'
+ else:
+ tt = 'a'
+ observed.append((t, tt))
+ self.assertEqual(observed, expected)
+
+ def testPunctuationInWordChars(self):
+ """Test that any punctuation chars are removed from wordchars"""
+ s = shlex.shlex('a_b__c', punctuation_chars='_')
+ self.assertNotIn('_', s.wordchars)
+ self.assertEqual(list(s), ['a', '_', 'b', '__', 'c'])
+
+ def testPunctuationWithWhitespaceSplit(self):
+ """Test that with whitespace_split, behaviour is as expected"""
+ s = shlex.shlex('a && b || c', punctuation_chars='&')
+ # whitespace_split is False, so splitting will be based on
+ # punctuation_chars
+ self.assertEqual(list(s), ['a', '&&', 'b', '|', '|', 'c'])
+ s = shlex.shlex('a && b || c', punctuation_chars='&')
+ s.whitespace_split = True
+ # whitespace_split is True, so splitting will be based on
+ # white space
+ self.assertEqual(list(s), ['a', '&&', 'b', '||', 'c'])
+
+ def testEmptyStringHandling(self):
+ """Test that parsing of empty strings is correctly handled."""
+ # see Issue #21999
+ expected = ['', ')', 'abc']
+ for punct in (False, True):
+ s = shlex.shlex("'')abc", posix=True, punctuation_chars=punct)
+ slist = list(s)
+ self.assertEqual(slist, expected)
+ expected = ["''", ')', 'abc']
+ s = shlex.shlex("'')abc", punctuation_chars=True)
+ self.assertEqual(list(s), expected)
+
def testQuote(self):
safeunquoted = string.ascii_letters + string.digits + '@%_-+=:,./'
unicode_sample = '\xe9\xe0\xdf' # e + acute accent, a + grave, sharp s