summaryrefslogtreecommitdiff
path: root/tests/tokenizer.py
blob: 1d561ae1b5dc06e74787d3d1610efca676118026 (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
# Copyright (C) 2003-2007, 2009-2011 Nominum, Inc.
#
# Permission to use, copy, modify, and distribute this software and its
# documentation for any purpose with or without fee is hereby granted,
# provided that the above copyright notice and this permission notice
# appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND NOMINUM DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL NOMINUM BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
# OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

import unittest

import dns.exception
import dns.tokenizer

Token = dns.tokenizer.Token

class TokenizerTestCase(unittest.TestCase):

    def testQuotedString1(self):
        tok = dns.tokenizer.Tokenizer(r'"foo"')
        token = tok.get()
        self.failUnless(token == Token(dns.tokenizer.QUOTED_STRING, 'foo'))

    def testQuotedString2(self):
        tok = dns.tokenizer.Tokenizer(r'""')
        token = tok.get()
        self.failUnless(token == Token(dns.tokenizer.QUOTED_STRING, ''))

    def testQuotedString3(self):
        tok = dns.tokenizer.Tokenizer(r'"\"foo\""')
        token = tok.get()
        self.failUnless(token == Token(dns.tokenizer.QUOTED_STRING, '"foo"'))

    def testQuotedString4(self):
        tok = dns.tokenizer.Tokenizer(r'"foo\010bar"')
        token = tok.get()
        self.failUnless(token == Token(dns.tokenizer.QUOTED_STRING, 'foo\x0abar'))

    def testQuotedString5(self):
        def bad():
            tok = dns.tokenizer.Tokenizer(r'"foo')
            token = tok.get()
        self.failUnlessRaises(dns.exception.UnexpectedEnd, bad)

    def testQuotedString6(self):
        def bad():
            tok = dns.tokenizer.Tokenizer(r'"foo\01')
            token = tok.get()
        self.failUnlessRaises(dns.exception.SyntaxError, bad)

    def testQuotedString7(self):
        def bad():
            tok = dns.tokenizer.Tokenizer('"foo\nbar"')
            token = tok.get()
        self.failUnlessRaises(dns.exception.SyntaxError, bad)

    def testEmpty1(self):
        tok = dns.tokenizer.Tokenizer('')
        token = tok.get()
        self.failUnless(token.is_eof())

    def testEmpty2(self):
        tok = dns.tokenizer.Tokenizer('')
        token1 = tok.get()
        token2 = tok.get()
        self.failUnless(token1.is_eof() and token2.is_eof())

    def testEOL(self):
        tok = dns.tokenizer.Tokenizer('\n')
        token1 = tok.get()
        token2 = tok.get()
        self.failUnless(token1.is_eol() and token2.is_eof())

    def testWS1(self):
        tok = dns.tokenizer.Tokenizer(' \n')
        token1 = tok.get()
        self.failUnless(token1.is_eol())

    def testWS2(self):
        tok = dns.tokenizer.Tokenizer(' \n')
        token1 = tok.get(want_leading=True)
        self.failUnless(token1.is_whitespace())

    def testComment1(self):
        tok = dns.tokenizer.Tokenizer(' ;foo\n')
        token1 = tok.get()
        self.failUnless(token1.is_eol())

    def testComment2(self):
        tok = dns.tokenizer.Tokenizer(' ;foo\n')
        token1 = tok.get(want_comment = True)
        token2 = tok.get()
        self.failUnless(token1 == Token(dns.tokenizer.COMMENT, 'foo') and
                        token2.is_eol())

    def testComment3(self):
        tok = dns.tokenizer.Tokenizer(' ;foo bar\n')
        token1 = tok.get(want_comment = True)
        token2 = tok.get()
        self.failUnless(token1 == Token(dns.tokenizer.COMMENT, 'foo bar') and
                        token2.is_eol())

    def testMultiline1(self):
        tok = dns.tokenizer.Tokenizer('( foo\n\n bar\n)')
        tokens = list(iter(tok))
        self.failUnless(tokens == [Token(dns.tokenizer.IDENTIFIER, 'foo'),
                                   Token(dns.tokenizer.IDENTIFIER, 'bar')])

    def testMultiline2(self):
        tok = dns.tokenizer.Tokenizer('( foo\n\n bar\n)\n')
        tokens = list(iter(tok))
        self.failUnless(tokens == [Token(dns.tokenizer.IDENTIFIER, 'foo'),
                                   Token(dns.tokenizer.IDENTIFIER, 'bar'),
                                   Token(dns.tokenizer.EOL, '\n')])
    def testMultiline3(self):
        def bad():
            tok = dns.tokenizer.Tokenizer('foo)')
            tokens = list(iter(tok))
        self.failUnlessRaises(dns.exception.SyntaxError, bad)

    def testMultiline4(self):
        def bad():
            tok = dns.tokenizer.Tokenizer('((foo)')
            tokens = list(iter(tok))
        self.failUnlessRaises(dns.exception.SyntaxError, bad)

    def testUnget1(self):
        tok = dns.tokenizer.Tokenizer('foo')
        t1 = tok.get()
        tok.unget(t1)
        t2 = tok.get()
        self.failUnless(t1 == t2 and t1.ttype == dns.tokenizer.IDENTIFIER and \
                        t1.value == 'foo')

    def testUnget2(self):
        def bad():
            tok = dns.tokenizer.Tokenizer('foo')
            t1 = tok.get()
            tok.unget(t1)
            tok.unget(t1)
        self.failUnlessRaises(dns.tokenizer.UngetBufferFull, bad)

    def testGetEOL1(self):
        tok = dns.tokenizer.Tokenizer('\n')
        t = tok.get_eol()
        self.failUnless(t == '\n')

    def testGetEOL2(self):
        tok = dns.tokenizer.Tokenizer('')
        t = tok.get_eol()
        self.failUnless(t == '')

    def testEscapedDelimiter1(self):
        tok = dns.tokenizer.Tokenizer(r'ch\ ld')
        t = tok.get()
        self.failUnless(t.ttype == dns.tokenizer.IDENTIFIER and t.value == r'ch\ ld')

    def testEscapedDelimiter2(self):
        tok = dns.tokenizer.Tokenizer(r'ch\032ld')
        t = tok.get()
        self.failUnless(t.ttype == dns.tokenizer.IDENTIFIER and t.value == r'ch\032ld')

    def testEscapedDelimiter3(self):
        tok = dns.tokenizer.Tokenizer(r'ch\ild')
        t = tok.get()
        self.failUnless(t.ttype == dns.tokenizer.IDENTIFIER and t.value == r'ch\ild')

    def testEscapedDelimiter1u(self):
        tok = dns.tokenizer.Tokenizer(r'ch\ ld')
        t = tok.get().unescape()
        self.failUnless(t.ttype == dns.tokenizer.IDENTIFIER and t.value == r'ch ld')

    def testEscapedDelimiter2u(self):
        tok = dns.tokenizer.Tokenizer(r'ch\032ld')
        t = tok.get().unescape()
        self.failUnless(t.ttype == dns.tokenizer.IDENTIFIER and t.value == 'ch ld')

    def testEscapedDelimiter3u(self):
        tok = dns.tokenizer.Tokenizer(r'ch\ild')
        t = tok.get().unescape()
        self.failUnless(t.ttype == dns.tokenizer.IDENTIFIER and t.value == r'child')

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