Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / python / pycparser / 203b967867976e2d385fcb9d5bd25f83e1f53ba2 / . / tests / test_c_lexer.py
blob: 773e608345566db6d6f9908fc725ad42ed334234 [file] [log] [blame]
Eli Bendersky3921e8e2010-05-21 09:05:39 +0300[diff] [blame]1import re
2import sys
3import unittest
4
5sys.path.insert(0, '..')
6from pycparser.c_lexer import CLexer
7
8
9def token_list(clex):
10 return list(iter(clex.token, None))
11
12
13def token_types(clex):
14 return [i.type for i in token_list(clex)]
15
16
17class TestCLexerNoErrors(unittest.TestCase):
18 """ Test lexing of strings that are not supposed to cause
19 errors. Therefore, the error_func passed to the lexer
20 raises an exception.
21 """
22 def error_func(self, msg, line, column):
23 self.fail(msg)
24
25 def type_lookup_func(self, typ):
26 if typ.startswith('mytype'):
27 return True
28 else:
29 return False
30
31 def setUp(self):
32 self.clex = CLexer(self.error_func, self.type_lookup_func)
33 self.clex.build(optimize=False)
34
35 def assertTokensTypes(self, str, types):
36 self.clex.input(str)
37 self.assertEqual(token_types(self.clex), types)
38
39 def test_trivial_tokens(self):
40 self.assertTokensTypes('1', ['INT_CONST_DEC'])
41 self.assertTokensTypes('-', ['MINUS'])
42 self.assertTokensTypes('volatile', ['VOLATILE'])
43 self.assertTokensTypes('...', ['ELLIPSIS'])
44 self.assertTokensTypes('++', ['PLUSPLUS'])
45 self.assertTokensTypes('case int', ['CASE', 'INT'])
46 self.assertTokensTypes('caseint', ['ID'])
47 self.assertTokensTypes('i ^= 1;', ['ID', 'XOREQUAL', 'INT_CONST_DEC', 'SEMI'])
48
49 def test_id_typeid(self):
50 self.assertTokensTypes('myt', ['ID'])
51 self.assertTokensTypes('mytype', ['TYPEID'])
52 self.assertTokensTypes('mytype6 var', ['TYPEID', 'ID'])
53
54 def test_integer_constants(self):
55 self.assertTokensTypes('12', ['INT_CONST_DEC'])
56 self.assertTokensTypes('12u', ['INT_CONST_DEC'])
57 self.assertTokensTypes('199872Ul', ['INT_CONST_DEC'])
eli.bendersky98f45372010-10-30 09:46:29 +0200[diff] [blame]58 self.assertTokensTypes('199872LL', ['INT_CONST_DEC'])
59 self.assertTokensTypes('199872ull', ['INT_CONST_DEC'])
Eli Bendersky3921e8e2010-05-21 09:05:39 +0300[diff] [blame]60
61 self.assertTokensTypes('077', ['INT_CONST_OCT'])
62 self.assertTokensTypes('0123456L', ['INT_CONST_OCT'])
63
64 self.assertTokensTypes('0xf7', ['INT_CONST_HEX'])
65 self.assertTokensTypes('0x01202AAbbf7Ul', ['INT_CONST_HEX'])
66
67 # no 0 before x, so ID catches it
68 self.assertTokensTypes('xf7', ['ID'])
69
70 # - is MINUS, the rest a constnant
71 self.assertTokensTypes('-1', ['MINUS', 'INT_CONST_DEC'])
72
73 def test_floating_constants(self):
74 self.assertTokensTypes('1.5f', ['FLOAT_CONST'])
75 self.assertTokensTypes('01.5', ['FLOAT_CONST'])
76 self.assertTokensTypes('.15L', ['FLOAT_CONST'])
77 self.assertTokensTypes('0.', ['FLOAT_CONST'])
78
79 # but just a period is a period
80 self.assertTokensTypes('.', ['PERIOD'])
81
82 self.assertTokensTypes('3.3e-3', ['FLOAT_CONST'])
83 self.assertTokensTypes('.7e25L', ['FLOAT_CONST'])
84 self.assertTokensTypes('6.e+125f', ['FLOAT_CONST'])
85 self.assertTokensTypes('666e666', ['FLOAT_CONST'])
86 self.assertTokensTypes('00666e+3', ['FLOAT_CONST'])
87
88 # but this is a hex integer + 3
89 self.assertTokensTypes('0x0666e+3', ['INT_CONST_HEX', 'PLUS', 'INT_CONST_DEC'])
90
91 def test_char_constants(self):
92 self.assertTokensTypes(r"""'x'""", ['CHAR_CONST'])
93 self.assertTokensTypes(r"""L'x'""", ['WCHAR_CONST'])
94 self.assertTokensTypes(r"""'\t'""", ['CHAR_CONST'])
95 self.assertTokensTypes(r"""'\''""", ['CHAR_CONST'])
96 self.assertTokensTypes(r"""'\?'""", ['CHAR_CONST'])
97 self.assertTokensTypes(r"""'\012'""", ['CHAR_CONST'])
98 self.assertTokensTypes(r"""'\x2f'""", ['CHAR_CONST'])
99 self.assertTokensTypes(r"""'\x2f12'""", ['CHAR_CONST'])
100 self.assertTokensTypes(r"""L'\xaf'""", ['WCHAR_CONST'])
101
102 def test_string_literal(self):
103 self.assertTokensTypes('"a string"', ['STRING_LITERAL'])
104 self.assertTokensTypes('L"ing"', ['WSTRING_LITERAL'])
105 self.assertTokensTypes(
106 '"i am a string too \t"',
107 ['STRING_LITERAL'])
108 self.assertTokensTypes(
109 r'''"esc\ape \"\'\? \0234 chars \rule"''',
110 ['STRING_LITERAL'])
111 self.assertTokensTypes(
112 r'''"hello 'joe' wanna give it a \"go\"?"''',
113 ['STRING_LITERAL'])
114
115 def test_mess(self):
116 self.assertTokensTypes(
117 r'[{}]()',
118 ['LBRACKET',
119 'LBRACE', 'RBRACE',
120 'RBRACKET',
121 'LPAREN', 'RPAREN'])
122
123 self.assertTokensTypes(
124 r'()||!C&~Z?J',
125 ['LPAREN', 'RPAREN',
126 'LOR',
127 'LNOT', 'ID',
128 'AND',
129 'NOT', 'ID',
130 'CONDOP', 'ID'])
131
132 self.assertTokensTypes(
133 r'+-*/%|||&&&^><>=<===!=',
134 ['PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MOD',
135 'LOR', 'OR',
136 'LAND', 'AND',
137 'XOR',
138 'GT', 'LT', 'GE', 'LE', 'EQ', 'NE'])
139
140 self.assertTokensTypes(
141 r'++--->?.,;:',
142 ['PLUSPLUS', 'MINUSMINUS',
143 'ARROW', 'CONDOP',
144 'PERIOD', 'COMMA', 'SEMI', 'COLON'])
145
146 def test_exprs(self):
147 self.assertTokensTypes(
148 'bb-cc',
149 ['ID', 'MINUS', 'ID'])
150
151 self.assertTokensTypes(
152 'foo & 0xFF',
153 ['ID', 'AND', 'INT_CONST_HEX'])
154
155 self.assertTokensTypes(
156 '(2+k) * 62',
157 ['LPAREN', 'INT_CONST_DEC', 'PLUS', 'ID',
158 'RPAREN', 'TIMES', 'INT_CONST_DEC'],)
159
160 self.assertTokensTypes(
161 'x | y >> z',
162 ['ID', 'OR', 'ID', 'RSHIFT', 'ID'])
163
164 self.assertTokensTypes(
165 'x <<= z << 5',
166 ['ID', 'LSHIFTEQUAL', 'ID', 'LSHIFT', 'INT_CONST_DEC'])
167
168 self.assertTokensTypes(
169 'x = y > 0 ? y : -6',
170 ['ID', 'EQUALS',
171 'ID', 'GT', 'INT_CONST_OCT',
172 'CONDOP',
173 'ID',
174 'COLON',
175 'MINUS', 'INT_CONST_DEC'])
176
177 self.assertTokensTypes(
178 'a+++b',
179 ['ID', 'PLUSPLUS', 'PLUS', 'ID'])
180
181 def test_statements(self):
182 self.assertTokensTypes(
183 'for (int i = 0; i < n; ++i)',
184 ['FOR', 'LPAREN',
185 'INT', 'ID', 'EQUALS', 'INT_CONST_OCT', 'SEMI',
186 'ID', 'LT', 'ID', 'SEMI',
187 'PLUSPLUS', 'ID',
188 'RPAREN'])
189
190 self.assertTokensTypes(
191 'self: goto self;',
192 ['ID', 'COLON', 'GOTO', 'ID', 'SEMI'])
193
194 self.assertTokensTypes(
195 """ switch (typ)
196 {
197 case TYPE_ID:
198 m = 5;
199 break;
200 default:
201 m = 8;
202 }""",
203 ['SWITCH', 'LPAREN', 'ID', 'RPAREN',
204 'LBRACE',
205 'CASE', 'ID', 'COLON',
206 'ID', 'EQUALS', 'INT_CONST_DEC', 'SEMI',
207 'BREAK', 'SEMI',
208 'DEFAULT', 'COLON',
209 'ID', 'EQUALS', 'INT_CONST_DEC', 'SEMI',
210 'RBRACE'])
211
212 def test_preprocessor(self):
213 self.assertTokensTypes('#abracadabra', ['PPHASH', 'ID'])
214
215 str = r"""
216 546
217 #line 66 "kwas\df.h"
218 id 4
219 dsf
220 # 9
221 armo
eli.benderskybfa9a942011-11-12 13:18:40 +0200[diff] [blame]222 #line 10 "..\~..\test.h"
eli.bendersky49f3b632011-10-31 06:38:41 +0200[diff] [blame]223 tok1
224 #line 99999 "include/me.h"
225 tok2
Eli Bendersky3921e8e2010-05-21 09:05:39 +0300[diff] [blame]226 """
227
228 #~ self.clex.filename
229 self.clex.input(str)
230 self.clex.reset_lineno()
231
232 t1 = self.clex.token()
233 self.assertEqual(t1.type, 'INT_CONST_DEC')
234 self.assertEqual(t1.lineno, 2)
235
236 t2 = self.clex.token()
237 self.assertEqual(t2.type, 'ID')
238 self.assertEqual(t2.value, 'id')
239 self.assertEqual(t2.lineno, 66)
240 self.assertEqual(self.clex.filename, r'kwas\df.h')
241
242 for i in range(3):
243 t = self.clex.token()
244
245 self.assertEqual(t.type, 'ID')
246 self.assertEqual(t.value, 'armo')
247 self.assertEqual(t.lineno, 9)
248 self.assertEqual(self.clex.filename, r'kwas\df.h')
249
eli.bendersky49f3b632011-10-31 06:38:41 +0200[diff] [blame]250 t4 = self.clex.token()
251 self.assertEqual(t4.type, 'ID')
252 self.assertEqual(t4.value, 'tok1')
253 self.assertEqual(t4.lineno, 10)
eli.benderskybfa9a942011-11-12 13:18:40 +0200[diff] [blame]254 self.assertEqual(self.clex.filename, r'..\~..\test.h')
eli.bendersky49f3b632011-10-31 06:38:41 +0200[diff] [blame]255
256 t5 = self.clex.token()
257 self.assertEqual(t5.type, 'ID')
258 self.assertEqual(t5.value, 'tok2')
259 self.assertEqual(t5.lineno, 99999)
260 self.assertEqual(self.clex.filename, r'include/me.h')
261
Eli Bendersky3921e8e2010-05-21 09:05:39 +0300[diff] [blame]262
263
264# Keeps all the errors the lexer spits in one place, to allow
265# easier modification if the error syntax changes.
266#
267ERR_ILLEGAL_CHAR = 'Illegal character'
268ERR_OCTAL = 'Invalid octal constant'
269ERR_UNMATCHED_QUOTE = 'Unmatched \''
270ERR_INVALID_CCONST = 'Invalid char constant'
271ERR_STRING_ESCAPE = 'String contains invalid escape'
272
273ERR_FILENAME_BEFORE_LINE = 'filename before line'
274ERR_LINENUM_MISSING = 'line number missing'
275ERR_INVALID_LINE_DIRECTIVE = 'invalid #line directive'
276
277
278class TestCLexerErrors(unittest.TestCase):
279 """ Test lexing of erroneous strings.
280 Works by passing an error functions that saves the error
281 in an attribute for later perusal.
282 """
283 def error_func(self, msg, line, column):
284 self.error = msg
285
286 def type_lookup_func(self, typ):
287 return False
288
289 def setUp(self):
290 self.clex = CLexer(self.error_func, self.type_lookup_func)
291 self.clex.build(optimize=False)
292 self.error = ""
293
294 def assertLexerError(self, str, error_like):
295 # feed the string to the lexer
296 self.clex.input(str)
297
298 # Pulls all tokens from the string. Errors will
299 # be written into self.error by the error_func
300 # callback
301 #
302 token_types(self.clex)
303
304 # compare the error to the expected
305 self.failUnless(re.search(error_like, self.error),
306 "\nExpected error matching: %s\nGot: %s" %
307 (error_like, self.error))
308
309 # clear last error, for the sake of subsequent invocations
310 self.error = ""
311
312 def test_trivial_tokens(self):
313 self.assertLexerError('@', ERR_ILLEGAL_CHAR)
314 self.assertLexerError('$', ERR_ILLEGAL_CHAR)
315 self.assertLexerError('`', ERR_ILLEGAL_CHAR)
316 self.assertLexerError('\\', ERR_ILLEGAL_CHAR)
317
318 def test_integer_constants(self):
319 self.assertLexerError('029', ERR_OCTAL)
320 self.assertLexerError('012345678', ERR_OCTAL)
321
322 def test_char_constants(self):
323 self.assertLexerError("'", ERR_UNMATCHED_QUOTE)
324 self.assertLexerError("'b\n", ERR_UNMATCHED_QUOTE)
325
326 self.assertLexerError("'jx'", ERR_INVALID_CCONST)
327 self.assertLexerError("'\*'", ERR_INVALID_CCONST)
328 self.assertLexerError("'\9'", ERR_INVALID_CCONST)
329 self.assertLexerError("L'\9'", ERR_INVALID_CCONST)
330
331 def test_string_literals(self):
332 self.assertLexerError('"jx\9"', ERR_STRING_ESCAPE)
333 self.assertLexerError('"hekllo\* on ix"', ERR_STRING_ESCAPE)
334 self.assertLexerError('L"hekllo\* on ix"', ERR_STRING_ESCAPE)
335
336 def test_preprocessor(self):
337 self.assertLexerError('#line "ka"', ERR_FILENAME_BEFORE_LINE)
338 self.assertLexerError('#line df', ERR_INVALID_LINE_DIRECTIVE)
339 self.assertLexerError('#line \n', ERR_LINENUM_MISSING)
340
341
342if __name__ == '__main__':
343 unittest.main()
344
345