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
|
import unittest
from sqlglot.tokens import Tokenizer, TokenType
class TestTokens(unittest.TestCase):
def test_comment_attachment(self):
tokenizer = Tokenizer()
sql_comment = [
("/*comment*/ foo", ["comment"]),
("/*comment*/ foo --test", ["comment", "test"]),
("--comment\nfoo --test", ["comment", "test"]),
("foo --comment", ["comment"]),
("foo", []),
("foo /*comment 1*/ /*comment 2*/", ["comment 1", "comment 2"]),
]
for sql, comment in sql_comment:
self.assertEqual(tokenizer.tokenize(sql)[0].comments, comment)
def test_jinja(self):
tokenizer = Tokenizer()
tokens = tokenizer.tokenize(
"""
SELECT
{{ x }},
{{- x -}},
{% for x in y -%}
a {{+ b }}
{% endfor %};
"""
)
tokens = [(token.token_type, token.text) for token in tokens]
self.assertEqual(
tokens,
[
(TokenType.SELECT, "SELECT"),
(TokenType.L_BRACE, "{"),
(TokenType.L_BRACE, "{"),
(TokenType.VAR, "x"),
(TokenType.R_BRACE, "}"),
(TokenType.R_BRACE, "}"),
(TokenType.COMMA, ","),
(TokenType.BLOCK_START, "{{-"),
(TokenType.VAR, "x"),
(TokenType.BLOCK_END, "-}}"),
(TokenType.COMMA, ","),
(TokenType.BLOCK_START, "{%"),
(TokenType.FOR, "for"),
(TokenType.VAR, "x"),
(TokenType.IN, "in"),
(TokenType.VAR, "y"),
(TokenType.BLOCK_END, "-%}"),
(TokenType.VAR, "a"),
(TokenType.BLOCK_START, "{{+"),
(TokenType.VAR, "b"),
(TokenType.R_BRACE, "}"),
(TokenType.R_BRACE, "}"),
(TokenType.BLOCK_START, "{%"),
(TokenType.VAR, "endfor"),
(TokenType.BLOCK_END, "%}"),
(TokenType.SEMICOLON, ";"),
],
)
|
