cpython/Lib/test/test_shlex.py

# -*- coding: iso-8859-1 -*-
import unittest
import os, sys
import shlex

from test import test_support

try:
    from cStringIO import StringIO
except ImportError:
    from StringIO import StringIO


# The original test data set was from shellwords, by Hartmut Goebel.

data = r"""x|x|
foo bar|foo|bar|
 foo bar|foo|bar|
 foo bar |foo|bar|
foo   bar    bla     fasel|foo|bar|bla|fasel|
x y  z              xxxx|x|y|z|xxxx|
\x bar|\|x|bar|
\ x bar|\|x|bar|
\ bar|\|bar|
foo \x bar|foo|\|x|bar|
foo \ x bar|foo|\|x|bar|
foo \ bar|foo|\|bar|
foo "bar" bla|foo|"bar"|bla|
"foo" "bar" "bla"|"foo"|"bar"|"bla"|
"foo" bar "bla"|"foo"|bar|"bla"|
"foo" bar bla|"foo"|bar|bla|
foo 'bar' bla|foo|'bar'|bla|
'foo' 'bar' 'bla'|'foo'|'bar'|'bla'|
'foo' bar 'bla'|'foo'|bar|'bla'|
'foo' bar bla|'foo'|bar|bla|
blurb foo"bar"bar"fasel" baz|blurb|foo"bar"bar"fasel"|baz|
blurb foo'bar'bar'fasel' baz|blurb|foo'bar'bar'fasel'|baz|
""|""|
''|''|
foo "" bar|foo|""|bar|
foo '' bar|foo|''|bar|
foo "" "" "" bar|foo|""|""|""|bar|
foo '' '' '' bar|foo|''|''|''|bar|
\""|\|""|
"\"|"\"|
"foo\ bar"|"foo\ bar"|
"foo\\ bar"|"foo\\ bar"|
"foo\\ bar\"|"foo\\ bar\"|
"foo\\" bar\""|"foo\\"|bar|\|""|
"foo\\ bar\" dfadf"|"foo\\ bar\"|dfadf"|
"foo\\\ bar\" dfadf"|"foo\\\ bar\"|dfadf"|
"foo\\\x bar\" dfadf"|"foo\\\x bar\"|dfadf"|
"foo\x bar\" dfadf"|"foo\x bar\"|dfadf"|
\''|\|''|
'foo\ bar'|'foo\ bar'|
'foo\\ bar'|'foo\\ bar'|
"foo\\\x bar\" df'a\ 'df'|"foo\\\x bar\"|df'a|\|'df'|
\"foo"|\|"foo"|
\"foo"\x|\|"foo"|\|x|
"foo\x"|"foo\x"|
"foo\ "|"foo\ "|
foo\ xx|foo|\|xx|
foo\ x\x|foo|\|x|\|x|
foo\ x\x\""|foo|\|x|\|x|\|""|
"foo\ x\x"|"foo\ x\x"|
"foo\ x\x\\"|"foo\ x\x\\"|
"foo\ x\x\\""foobar"|"foo\ x\x\\"|"foobar"|
"foo\ x\x\\"\''"foobar"|"foo\ x\x\\"|\|''|"foobar"|
"foo\ x\x\\"\'"fo'obar"|"foo\ x\x\\"|\|'"fo'|obar"|
"foo\ x\x\\"\'"fo'obar" 'don'\''t'|"foo\ x\x\\"|\|'"fo'|obar"|'don'|\|''|t'|
'foo\ bar'|'foo\ bar'|
'foo\\ bar'|'foo\\ bar'|
foo\ bar|foo|\|bar|
foo#bar\nbaz|foobaz|
:-) ;-)|:|-|)|;|-|)|
<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>|<EFBFBD>|<EFBFBD>|<EFBFBD>|<EFBFBD>|<EFBFBD>|
"""

posix_data = r"""x|x|
foo bar|foo|bar|
 foo bar|foo|bar|
 foo bar |foo|bar|
foo   bar    bla     fasel|foo|bar|bla|fasel|
x y  z              xxxx|x|y|z|xxxx|
\x bar|x|bar|
\ x bar| x|bar|
\ bar| bar|
foo \x bar|foo|x|bar|
foo \ x bar|foo| x|bar|
foo \ bar|foo| bar|
foo "bar" bla|foo|bar|bla|
"foo" "bar" "bla"|foo|bar|bla|
"foo" bar "bla"|foo|bar|bla|
"foo" bar bla|foo|bar|bla|
foo 'bar' bla|foo|bar|bla|
'foo' 'bar' 'bla'|foo|bar|bla|
'foo' bar 'bla'|foo|bar|bla|
'foo' bar bla|foo|bar|bla|
blurb foo"bar"bar"fasel" baz|blurb|foobarbarfasel|baz|
blurb foo'bar'bar'fasel' baz|blurb|foobarbarfasel|baz|
""||
''||
foo "" bar|foo||bar|
foo '' bar|foo||bar|
foo "" "" "" bar|foo||||bar|
foo '' '' '' bar|foo||||bar|
\"|"|
"\""|"|
"foo\ bar"|foo\ bar|
"foo\\ bar"|foo\ bar|
"foo\\ bar\""|foo\ bar"|
"foo\\" bar\"|foo\|bar"|
"foo\\ bar\" dfadf"|foo\ bar" dfadf|
"foo\\\ bar\" dfadf"|foo\\ bar" dfadf|
"foo\\\x bar\" dfadf"|foo\\x bar" dfadf|
"foo\x bar\" dfadf"|foo\x bar" dfadf|
\'|'|
'foo\ bar'|foo\ bar|
'foo\\ bar'|foo\\ bar|
"foo\\\x bar\" df'a\ 'df"|foo\\x bar" df'a\ 'df|
\"foo|"foo|
\"foo\x|"foox|
"foo\x"|foo\x|
"foo\ "|foo\ |
foo\ xx|foo xx|
foo\ x\x|foo xx|
foo\ x\x\"|foo xx"|
"foo\ x\x"|foo\ x\x|
"foo\ x\x\\"|foo\ x\x\|
"foo\ x\x\\""foobar"|foo\ x\x\foobar|
"foo\ x\x\\"\'"foobar"|foo\ x\x\'foobar|
"foo\ x\x\\"\'"fo'obar"|foo\ x\x\'fo'obar|
"foo\ x\x\\"\'"fo'obar" 'don'\''t'|foo\ x\x\'fo'obar|don't|
"foo\ x\x\\"\'"fo'obar" 'don'\''t' \\|foo\ x\x\'fo'obar|don't|\|
'foo\ bar'|foo\ bar|
'foo\\ bar'|foo\\ bar|
foo\ bar|foo bar|
foo#bar\nbaz|foo|baz|
:-) ;-)|:-)|;-)|
<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>|<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>|
"""

class ShlexTest(unittest.TestCase):
    def setUp(self):
        self.data = [x.split("|")[:-1]
                     for x in data.splitlines()]
        self.posix_data = [x.split("|")[:-1]
                           for x in posix_data.splitlines()]
        for item in self.data:
            item[0] = item[0].replace(r"\n", "\n")
        for item in self.posix_data:
            item[0] = item[0].replace(r"\n", "\n")

    def splitTest(self, data, posix, spaces):
        for i in range(len(data)):
            l = shlex.split(data[i][0], posix=posix, spaces=spaces)
            self.assertEqual(l, data[i][1:],
                             "%s: %s != %s" %
                             (data[i][0], l, data[i][1:]))

    def oldSplit(self, s):
        ret = []
        lex = shlex.shlex(StringIO(s))
        tok = lex.get_token()
        while tok:
            ret.append(tok)
            tok = lex.get_token()
        return ret
    
    def testSplit(self):
        """Test data splitting with non-posix parser"""
        self.splitTest(self.data, posix=0, spaces=0) 

    def testSplitPosix(self):
        """Test data splitting with posix parser"""
        self.splitTest(self.posix_data, posix=1, spaces=1) 

    def testCompat(self):
        """Test compatibility interface"""
        for i in range(len(self.data)):
            l = self.oldSplit(self.data[i][0])
            self.assertEqual(l, self.data[i][1:],
                             "%s: %s != %s" %
                             (self.data[i][0], l, self.data[i][1:]))

# Allow this test to be used with old shlex.py
if not getattr(shlex, "split", None):
    for methname in dir(ShlexTest):
        if methname.startswith("test") and methname != "testCompat":
            delattr(ShlexTest, methname)

def test_main():
    test_support.run_unittest(ShlexTest)

if __name__ == "__main__":
    test_main()