blob: 9d4860e91a5d217a26f2b36eecb74d7bdb1a3254 (
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
|
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.
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.
"""
expression = exp.maybe_parse(expression, dialect=dialect)
return expression.transform(Dialect.get_or_raise(dialect).normalize_identifier, copy=False)
|