blob: 32f3a92dc5b9055990df508e91000992b82e5af5 (
plain)
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
|
from __future__ import annotations
import typing as t
from sqlglot import exp
from sqlglot._typing import E
from sqlglot.dialects.dialect import Dialect, DialectType
@t.overload
def normalize_identifiers(expression: E, dialect: DialectType = None) -> E:
...
@t.overload
def normalize_identifiers(expression: str, dialect: DialectType = None) -> exp.Expression:
...
def normalize_identifiers(expression, dialect=None):
"""
Normalize all unquoted identifiers to either lower or upper case, depending
on the dialect. This essentially makes those identifiers case-insensitive.
It's possible to make this a no-op by adding a special comment next to the
identifier of interest:
SELECT a /* sqlglot.meta case_sensitive */ FROM table
In this example, the identifier `a` will not be normalized.
Note:
Some dialects (e.g. BigQuery) treat identifiers as case-insensitive even
when they're quoted, so in these cases all identifiers are normalized.
Example:
>>> import sqlglot
>>> expression = sqlglot.parse_one('SELECT Bar.A AS A FROM "Foo".Bar')
>>> normalize_identifiers(expression).sql()
'SELECT bar.a AS a FROM "Foo".bar'
>>> normalize_identifiers("foo", dialect="snowflake").sql(dialect="snowflake")
'FOO'
Args:
expression: The expression to transform.
dialect: The dialect to use in order to decide how to normalize identifiers.
Returns:
The transformed expression.
"""
if isinstance(expression, str):
expression = exp.to_identifier(expression)
dialect = Dialect.get_or_raise(dialect)
def _normalize(node: E) -> E:
if not node.meta.get("case_sensitive"):
exp.replace_children(node, _normalize)
node = dialect.normalize_identifier(node)
return node
return _normalize(expression)
|
