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
|
# -*- coding: utf-8 -*-
import ast
import io
import sys
import token
import unittest
import astroid
import pytest
from .context import asttokens
from .tools import get_node_name
class TestUtil(unittest.TestCase):
def print_timing(self):
# pylint: disable=no-self-use
# Test the implementation of asttokens.util.walk, which uses the same approach as
# visit_tree(). This doesn't run as a normal unittest, but if you'd like to see timings, e.g.
# after experimenting with the implementation, run this to see them:
#
# nosetests -i print_timing -s tests.test_util
#
import timeit
import textwrap
setup = textwrap.dedent(
'''
import ast, asttokens
source = "foo(bar(1 + 2), 'hello' + ', ' + 'world')"
atok = asttokens.ASTTokens(source, parse=True)
''')
print("ast", sorted(timeit.repeat(
setup=setup, number=10000,
stmt='len(list(ast.walk(atok.tree)))')))
print("util", sorted(timeit.repeat(
setup=setup, number=10000,
stmt='len(list(asttokens.util.walk(atok.tree)))')))
source = "foo(bar(1 + 2), 'hello' + ', ' + 'world')"
def test_walk_ast(self):
atok = asttokens.ASTTokens(self.source, parse=True)
def view(node):
return "%s:%s" % (get_node_name(node), atok.get_text(node))
scan = [view(n) for n in asttokens.util.walk(atok.tree)]
self.assertEqual(scan, [
"Module:foo(bar(1 + 2), 'hello' + ', ' + 'world')",
"Expr:foo(bar(1 + 2), 'hello' + ', ' + 'world')",
"Call:foo(bar(1 + 2), 'hello' + ', ' + 'world')",
'Name:foo',
'Call:bar(1 + 2)',
'Name:bar',
'BinOp:1 + 2',
'Constant:1',
'Constant:2',
"BinOp:'hello' + ', ' + 'world'",
"BinOp:'hello' + ', '",
"Constant:'hello'",
"Constant:', '",
"Constant:'world'"
])
def test_walk_astroid(self):
atok = asttokens.ASTTokens(self.source, tree=astroid.builder.parse(self.source))
def view(node):
return "%s:%s" % (get_node_name(node), atok.get_text(node))
scan = [view(n) for n in asttokens.util.walk(atok.tree)]
self.assertEqual(scan, [
"Module:foo(bar(1 + 2), 'hello' + ', ' + 'world')",
"Expr:foo(bar(1 + 2), 'hello' + ', ' + 'world')",
"Call:foo(bar(1 + 2), 'hello' + ', ' + 'world')",
'Name:foo',
'Call:bar(1 + 2)',
'Name:bar',
'BinOp:1 + 2',
'Const:1',
'Const:2',
"BinOp:'hello' + ', ' + 'world'",
"BinOp:'hello' + ', '",
"Const:'hello'",
"Const:', '",
"Const:'world'"
])
def test_replace(self):
self.assertEqual(asttokens.util.replace("this is a test", [(0, 4, "X"), (8, 9, "THE")]),
"X is THE test")
self.assertEqual(asttokens.util.replace("this is a test", []), "this is a test")
self.assertEqual(asttokens.util.replace("this is a test", [(7,7," NOT")]), "this is NOT a test")
source = "foo(bar(1 + 2), 'hello' + ', ' + 'world')"
atok = asttokens.ASTTokens(source, parse=True)
names = [n for n in asttokens.util.walk(atok.tree) if isinstance(n, ast.Name)]
strings = [n for n in asttokens.util.walk(atok.tree) if isinstance(n, ast.Str)]
repl1 = [atok.get_text_range(n) + ('TEST',) for n in names]
repl2 = [atok.get_text_range(n) + ('val',) for n in strings]
self.assertEqual(asttokens.util.replace(source, repl1 + repl2),
"TEST(TEST(1 + 2), val + val + val)")
self.assertEqual(asttokens.util.replace(source, repl2 + repl1),
"TEST(TEST(1 + 2), val + val + val)")
def test_expect_token():
atok = asttokens.ASTTokens("a", parse=True)
tok = atok.tokens[0]
with pytest.raises(ValueError):
asttokens.util.expect_token(tok, token.OP)
def test_combine_tokens():
from tokenize import TokenInfo, generate_tokens, ERRORTOKEN, OP, NUMBER, NAME
from asttokens.util import combine_tokens, patched_generate_tokens
text = "℘·2=1"
original_tokens = []
for tok in generate_tokens(io.StringIO(text).readline):
original_tokens.append(tok)
if tok.type == OP:
break
correct_tokens = [
TokenInfo(NAME, string='℘·2', start=(1, 0), end=(1, 3), line='℘·2=1'),
TokenInfo(OP, string='=', start=(1, 3), end=(1, 4), line='℘·2=1'),
]
if sys.version_info >= (3, 12):
# The tokenizing bug was fixed in 3.12, so the original tokens are correct,
# rather than starting with false ERRORTOKENs.
assert original_tokens == correct_tokens
else:
assert original_tokens == [
TokenInfo(ERRORTOKEN, string='℘', start=(1, 0), end=(1, 1), line='℘·2=1'),
TokenInfo(ERRORTOKEN, string='·', start=(1, 1), end=(1, 2), line='℘·2=1'),
TokenInfo(NUMBER, string='2', start=(1, 2), end=(1, 3), line='℘·2=1'),
TokenInfo(OP, string='=', start=(1, 3), end=(1, 4), line='℘·2=1'),
]
assert combine_tokens(original_tokens[:1]) == [
TokenInfo(NAME, string='℘', start=(1, 0), end=(1, 1), line='℘·2=1'),
]
assert combine_tokens(original_tokens[:2]) == [
TokenInfo(NAME, string='℘·', start=(1, 0), end=(1, 2), line='℘·2=1'),
]
assert combine_tokens(original_tokens[:3]) == [
TokenInfo(NAME, string='℘·2', start=(1, 0), end=(1, 3), line='℘·2=1'),
]
assert list(patched_generate_tokens(iter(original_tokens))) == correct_tokens
assert list(patched_generate_tokens(iter(original_tokens[:-1]))) == [
TokenInfo(NAME, string='℘·2', start=(1, 0), end=(1, 3), line='℘·2=1'),
]
if __name__ == "__main__":
unittest.main()
|
