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
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
|
# -*- coding: utf-8 -* -
import pytest
from pypy.interpreter.astcompiler import consts
from pypy.interpreter.pyparser import pytokenizer
from pypy.interpreter.pyparser.parser import Token
from pypy.interpreter.pyparser.pygram import tokens
from pypy.interpreter.pyparser.error import TokenError
def tokenize(s, flags=0):
source_lines = s.splitlines(True)
if source_lines and not source_lines[-1].endswith("\n"):
source_lines[-1] += '\n'
return pytokenizer.generate_tokens(source_lines, flags)
def check_token_error(s, msg=None, pos=-1, line=-1):
error = pytest.raises(TokenError, tokenize, s)
if msg is not None:
assert error.value.msg == msg
if pos != -1:
assert error.value.offset == pos
if line != -1:
assert error.value.lineno == line
class TestTokenizer(object):
def test_simple(self):
line = "a+1\n"
tks = tokenize(line)
assert tks[:-3] == [
Token(tokens.NAME, 'a', 1, 0, line, 1, 1),
Token(tokens.PLUS, '+', 1, 1, line, 1, 2),
Token(tokens.NUMBER, '1', 1, 2, line, 1, 3),
]
def test_error_parenthesis(self):
for paren in "([{":
check_token_error(paren + "1 + 2",
"'%s' was never closed" % paren,
1)
for paren in ")]}":
check_token_error("1 + 2" + paren,
"unmatched '%s'" % (paren, ),
6)
for i, opening in enumerate("([{"):
for j, closing in enumerate(")]}"):
if i == j:
continue
check_token_error(opening + "1\n" + closing,
"closing parenthesis '%s' does not match opening parenthesis '%s' on line 1" % (closing, opening),
pos=1, line=2)
check_token_error(opening + "1" + closing,
"closing parenthesis '%s' does not match opening parenthesis '%s'" % (closing, opening),
pos=3, line=1)
check_token_error(opening + closing,
"closing parenthesis '%s' does not match opening parenthesis '%s'" % (closing, opening),
pos=2, line=1)
def test_unknown_char(self):
check_token_error("?", "invalid character '?' (U+003F)", 1)
check_token_error("$", "invalid character '$' (U+0024)", 1)
check_token_error("⫛", "invalid character '⫛' (U+2ADB)", 1)
check_token_error("\x17", "invalid non-printable character U+0017", 1)
def test_eol_string(self):
check_token_error("x = 'a", pos=5, line=1)
def test_eof_triple_quoted(self):
check_token_error("'''", pos=1, line=1)
def test_type_comments(self):
line = "a = 5 # type: int\n"
tks = tokenize(line, flags=consts.PyCF_TYPE_COMMENTS)
assert tks[:-3] == [
Token(tokens.NAME, 'a', 1, 0, line, 1, 1),
Token(tokens.EQUAL, '=', 1, 2, line, 1, 3),
Token(tokens.NUMBER, '5', 1, 4, line, 1, 5),
Token(tokens.TYPE_COMMENT, 'int', 1, 6, line),
]
def test_type_comment_bug(self):
lines = ['# type: int\n', '']
pytokenizer.generate_tokens(lines, flags=consts.PyCF_TYPE_COMMENTS)
def test_type_ignore(self):
line = "a = 5 # type: ignore@teyit\n"
tks = tokenize(line, flags=consts.PyCF_TYPE_COMMENTS)
assert tks[:-3] == [
Token(tokens.NAME, 'a', 1, 0, line, 1, 1),
Token(tokens.EQUAL, '=', 1, 2, line, 1, 3),
Token(tokens.NUMBER, '5', 1, 4, line, 1, 5),
Token(tokens.TYPE_IGNORE, '@teyit', 1, 6, line),
]
def test_walrus(self):
line = "a:=1\n"
tks = tokenize(line)
assert tks[:-3] == [
Token(tokens.NAME, 'a', 1, 0, line, 1, 1),
Token(tokens.COLONEQUAL, ':=', 1, 1, line, 1, 3),
Token(tokens.NUMBER, '1', 1, 3, line, 1, 4),
]
def test_triple_quoted(self):
input = '''x = """
hello
content
whatisthis""" + "a"\n'''
s = '''"""
hello
content
whatisthis"""'''
tks = tokenize(input)
lines = input.splitlines(True)
assert tks[:3] == [
Token(tokens.NAME, 'x', 1, 0, lines[0], 1, 1),
Token(tokens.EQUAL, '=', 1, 2, lines[0], 1, 3),
Token(tokens.STRING, s, 1, 4, lines[3], 4, 13),
]
def test_parenthesis_positions(self):
input = '( ( ( a ) ) ) ( )'
tks = tokenize(input)[:-3]
columns = [t.column for t in tks]
assert columns == [0, 2, 4, 6, 8, 10, 12, 14, 16]
assert [t.end_column - 1 for t in tks] == columns
def test_PyCF_DONT_IMPLY_DEDENT(self):
input = "if 1:\n 1\n"
# regular mode
tks = tokenize(input)
lines = input.splitlines(True)
del tks[-2] # new parser deletes one newline anyway
assert tks == [
Token(tokens.NAME, 'if', 1, 0, lines[0], 1, 2),
Token(tokens.NUMBER, '1', 1, 3, lines[0], 1, 4),
Token(tokens.COLON, ':', 1, 4, lines[0], 1, 5),
Token(tokens.NEWLINE, '', 1, 5, lines[0], -1, -1),
Token(tokens.INDENT, ' ', 2, 0, lines[1], 2, 2),
Token(tokens.NUMBER, '1', 2, 2, lines[1], 2, 3),
Token(tokens.NEWLINE, '', 2, 3, lines[1], -1, -1),
Token(tokens.DEDENT, '', 2, 0, '', -1, -1),
Token(tokens.ENDMARKER, '', 2, 0, '', -1, -1),
]
# single mode
tks = tokenize(input, flags=consts.PyCF_DONT_IMPLY_DEDENT)
lines = input.splitlines(True)
del tks[-2] # new parser deletes one newline anyway
assert tks == [
Token(tokens.NAME, 'if', 1, 0, lines[0], 1, 2),
Token(tokens.NUMBER, '1', 1, 3, lines[0], 1, 4),
Token(tokens.COLON, ':', 1, 4, lines[0], 1, 5),
Token(tokens.NEWLINE, '', 1, 5, lines[0], -1, -1),
Token(tokens.INDENT, ' ', 2, 0, lines[1], 2, 2),
Token(tokens.NUMBER, '1', 2, 2, lines[1], 2, 3),
Token(tokens.NEWLINE, '', 2, 3, lines[1], -1, -1),
Token(tokens.ENDMARKER, '', 2, 0, '', -1, -1),
]
def test_ignore_just_linecont(self):
input = "pass\n \\\n\npass"
tks = tokenize(input)
tps = [tk.token_type for tk in tks]
assert tps == [tokens.NAME, tokens.NEWLINE, tokens.NAME,
tokens.NEWLINE, tokens.NEWLINE, tokens.ENDMARKER]
def test_error_linecont(self):
check_token_error("a \\ b",
"unexpected character after line continuation character",
4)
def test_continuation_and_indentation_levels(self):
# Make sure the '\` generates indent/dedent tokens
input1 = r"""\
def fib(n):
\
'''Print a Fibonacci series up to n.'''
\
a, b = 0, 1
"""
input2 = r"""\
def fib(n):
'''Print a Fibonacci series up to n.'''
a, b = 0, 1
"""
def base_eq(tok1, tok2):
# Line numbers differ because of `\`, so only compare type and value
return all([(t1.token_type == t2.token_type and t1.value == t2.value) for t1, t2 in zip(tok1, tok2)])
tks1 = tokenize(input1)
tks2 = tokenize(input2)
if not base_eq(tks1, tks2):
# get better error message
assert tks1 == tks2
def test_formfeed1(self):
# issue gh-5221
input = " \\\n \ndef(a=1,b:bool=False): pass"
tks = tokenize(input)
assert tks[0].token_type != tokens.INDENT
def test_formfeed2(self):
# issue gh-5221
input = " \\\n#\n"
tks = tokenize(input)
assert tks[0].token_type != tokens.INDENT
def test_backslash_before_indent1(self):
# issue gh-5221
input1 = r"""\
class AnotherCase:
'''Some Docstring
'''"""
input2 = r"""\
class AnotherCase:
\
'''Some Docstring
'''"""
tks1 = tokenize(input1)
tps1 = [tk.token_type for tk in tks1]
tks2 = tokenize(input2)
tps2 = [tk.token_type for tk in tks2]
assert tps1 == tps2
def test_backslash_before_indent2(self):
# issue gh-5221
input1 = r"""\
class Plotter:
\
pass
"""
input2 = r"""\
class Plotter:
pass
"""
tks1 = tokenize(input1)
tps1 = [tk.token_type for tk in tks1]
tks2 = tokenize(input2)
tps2 = [tk.token_type for tk in tks2]
assert tps1 == tps2
def test_error_integers(self):
check_token_error("0b106",
"invalid digit '6' in binary literal",
5)
check_token_error("0b10_6",
"invalid digit '6' in binary literal",
5)
check_token_error("0b6",
"invalid digit '6' in binary literal",
3)
check_token_error("0b \n",
"invalid binary literal",
2)
check_token_error("0o129",
"invalid digit '9' in octal literal",
5)
check_token_error("0o12_9",
"invalid digit '9' in octal literal",
5)
check_token_error("0o9",
"invalid digit '9' in octal literal",
3)
check_token_error("0o \n",
"invalid octal literal",
2)
check_token_error("0x1__ \n",
"invalid hexadecimal literal",
4)
check_token_error("0x\n",
"invalid hexadecimal literal",
2)
check_token_error("1_ \n",
"invalid decimal literal",
2)
check_token_error("0b1_ \n",
"invalid binary literal",
3)
check_token_error("01212 \n",
"leading zeros in decimal integer literals are not permitted; use an 0o prefix for octal integers",
1)
tokenize("1 2 \n") # does not raise
tokenize("1 _ \n") # does not raise
def test_invalid_identifier(self):
check_token_error("aänc€",
"invalid character '€' (U+20AC)",
6)
check_token_error("a\xc2\xa0b",
"invalid non-printable character U+00A0",
2)
class TestTokenizer310Changes(object):
def test_single_quoted(self):
check_token_error('s = "abc\n', "unterminated string literal (detected at line 1)", pos=5)
def test_triple_quoted(self):
check_token_error('"""abc\n', "unterminated triple-quoted string literal (detected at line 1)")
def test_single_quoted_detected(self):
check_token_error('s = "abc\n', "unterminated string literal (detected at line 1)")
check_token_error('s = "abc\\\na\\\nb\n', "unterminated string literal (detected at line 3)", pos=5)
def test_triple_quoted_detected(self):
check_token_error('s = """', "unterminated triple-quoted string literal (detected at line 1)")
check_token_error('s = """abc\\\na\\\nb\n\n\n\n\n', "unterminated triple-quoted string literal (detected at line 7)")
def test_warn_number_followed_by_keyword(self):
line = "0x1for\n"
tks = tokenize(line)
assert tks[:-3] == [
Token(tokens.NUMBER, '0x1f', 1, 0, line, 1, 4),
Token(tokens.WARNING, 'invalid hexadecimal literal', 1, 0, line),
Token(tokens.NAME, 'or', 1, 4, line, 1, 6),
]
for line in ("1in 3", "0b01010111and 4", "1 if 0o21231else 2"):
tks = tokenize(line)
assert any(tokens.WARNING == tok.token_type for tok in tks)
def test_error_number_by_non_keyword_name(self):
check_token_error("1a 2", "invalid decimal literal")
def test_levels(self):
line = 'a b (c + d) [[e, f]]'
tks = tokenize(line)
levels = [token.level for token in tks]
assert levels == [0, 0, 1, 1, 1, 1, 0, 1, 2, 2, 2, 2, 1, 0, 0, 0, 0]
|
