summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_shlex.py
blob: 3936c97c8b997d78ffdb9dd034c1a11c069e64a8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
import io
import shlex
import string
import unittest



# 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|
:-) ;-)|:|-|)|;|-|)|
áéíóú|á|é|í|ó|ú|
"""

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|
:-) ;-)|:-)|;-)|
áéíóú|áéíóú|
"""

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

    def oldSplit(self, s):
        ret = []
        lex = shlex.shlex(io.StringIO(s))
        tok = lex.get_token()
        while tok:
            ret.append(tok)
            tok = lex.get_token()
        return ret

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

    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:]))

    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
        unsafe = '"`$\\!' + unicode_sample

        self.assertEqual(shlex.quote(''), "''")
        self.assertEqual(shlex.quote(safeunquoted), safeunquoted)
        self.assertEqual(shlex.quote('test file name'), "'test file name'")
        for u in unsafe:
            self.assertEqual(shlex.quote('test%sname' % u),
                             "'test%sname'" % u)
        for u in unsafe:
            self.assertEqual(shlex.quote("test%s'name'" % u),
                             "'test%s'\"'\"'name'\"'\"''" % u)

# 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)

if __name__ == "__main__":
    unittest.main()