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
|
"""Tests for the blib2to3 tokenizer."""
import sys
import textwrap
from dataclasses import dataclass
import black
from blib2to3.pgen2 import token, tokenize
@dataclass
class Token:
type: str
string: str
start: tokenize.Coord
end: tokenize.Coord
def get_tokens(text: str) -> list[Token]:
"""Return the tokens produced by the tokenizer."""
return [
Token(token.tok_name[tok_type], string, start, end)
for tok_type, string, start, end, _ in tokenize.tokenize(text)
]
def assert_tokenizes(text: str, tokens: list[Token]) -> None:
"""Assert that the tokenizer produces the expected tokens."""
actual_tokens = get_tokens(text)
assert actual_tokens == tokens
def test_simple() -> None:
assert_tokenizes(
"1",
[Token("NUMBER", "1", (1, 0), (1, 1)), Token("ENDMARKER", "", (2, 0), (2, 0))],
)
assert_tokenizes(
"'a'",
[
Token("STRING", "'a'", (1, 0), (1, 3)),
Token("ENDMARKER", "", (2, 0), (2, 0)),
],
)
assert_tokenizes(
"a",
[Token("NAME", "a", (1, 0), (1, 1)), Token("ENDMARKER", "", (2, 0), (2, 0))],
)
def test_fstring() -> None:
assert_tokenizes(
'f"x"',
[
Token("FSTRING_START", 'f"', (1, 0), (1, 2)),
Token("FSTRING_MIDDLE", "x", (1, 2), (1, 3)),
Token("FSTRING_END", '"', (1, 3), (1, 4)),
Token("ENDMARKER", "", (2, 0), (2, 0)),
],
)
assert_tokenizes(
'f"{x}"',
[
Token("FSTRING_START", 'f"', (1, 0), (1, 2)),
Token("OP", "{", (1, 2), (1, 3)),
Token("NAME", "x", (1, 3), (1, 4)),
Token("OP", "}", (1, 4), (1, 5)),
Token("FSTRING_END", '"', (1, 5), (1, 6)),
Token("ENDMARKER", "", (2, 0), (2, 0)),
],
)
assert_tokenizes(
'f"{x:y}"\n',
[
Token(type="FSTRING_START", string='f"', start=(1, 0), end=(1, 2)),
Token(type="OP", string="{", start=(1, 2), end=(1, 3)),
Token(type="NAME", string="x", start=(1, 3), end=(1, 4)),
Token(type="OP", string=":", start=(1, 4), end=(1, 5)),
Token(type="FSTRING_MIDDLE", string="y", start=(1, 5), end=(1, 6)),
Token(type="OP", string="}", start=(1, 6), end=(1, 7)),
Token(type="FSTRING_END", string='"', start=(1, 7), end=(1, 8)),
Token(type="NEWLINE", string="\n", start=(1, 8), end=(1, 9)),
Token(type="ENDMARKER", string="", start=(2, 0), end=(2, 0)),
],
)
assert_tokenizes(
'f"x\\\n{a}"\n',
[
Token(type="FSTRING_START", string='f"', start=(1, 0), end=(1, 2)),
Token(type="FSTRING_MIDDLE", string="x\\\n", start=(1, 2), end=(2, 0)),
Token(type="OP", string="{", start=(2, 0), end=(2, 1)),
Token(type="NAME", string="a", start=(2, 1), end=(2, 2)),
Token(type="OP", string="}", start=(2, 2), end=(2, 3)),
Token(type="FSTRING_END", string='"', start=(2, 3), end=(2, 4)),
Token(type="NEWLINE", string="\n", start=(2, 4), end=(2, 5)),
Token(type="ENDMARKER", string="", start=(3, 0), end=(3, 0)),
],
)
# Run "echo some code | python tests/test_tokenize.py" to generate test cases.
if __name__ == "__main__":
code = sys.stdin.read()
tokens = get_tokens(code)
text = f"assert_tokenizes({code!r}, {tokens!r})"
text = black.format_str(text, mode=black.Mode())
print(textwrap.indent(text, " "))
|
