pip3 install "sqlglot[rs]"

# Without Rust tokenizer (slower):
# pip3 install sqlglot

import sqlglot
sqlglot.transpile("SELECT EPOCH_MS(1618088028295)", read="duckdb", write="hive")[0]

'SELECT FROM_UNIXTIME(1618088028295 / POW(10, 3))'

import sqlglot
sqlglot.transpile("SELECT STRFTIME(x, '%y-%-m-%S')", read="duckdb", write="hive")[0]

"SELECT DATE_FORMAT(x, 'yy-M-ss')"

import sqlglot

# Spark SQL requires backticks (`) for delimited identifiers and uses `FLOAT` over `REAL`
sql = """WITH baz AS (SELECT a, c FROM foo WHERE a = 1) SELECT f.a, b.b, baz.c, CAST("b"."a" AS REAL) d FROM foo f JOIN bar b ON f.a = b.a LEFT JOIN baz ON f.a = baz.a"""

# Translates the query into Spark SQL, formats it, and delimits all of its identifiers
print(sqlglot.transpile(sql, write="spark", identify=True, pretty=True)[0])

WITH `baz` AS (
  SELECT
    `a`,
    `c`
  FROM `foo`
  WHERE
    `a` = 1
)
SELECT
  `f`.`a`,
  `b`.`b`,
  `baz`.`c`,
  CAST(`b`.`a` AS FLOAT) AS `d`
FROM `foo` AS `f`
JOIN `bar` AS `b`
  ON `f`.`a` = `b`.`a`
LEFT JOIN `baz`
  ON `f`.`a` = `baz`.`a`

sql = """
/* multi
   line
   comment
*/
SELECT
  tbl.cola /* comment 1 */ + tbl.colb /* comment 2 */,
  CAST(x AS SIGNED), # comment 3
  y               -- comment 4
FROM
  bar /* comment 5 */,
  tbl #          comment 6
"""

# Note: MySQL-specific comments (`#`) are converted into standard syntax
print(sqlglot.transpile(sql, read='mysql', pretty=True)[0])

/* multi
   line
   comment
*/
SELECT
  tbl.cola /* comment 1 */ + tbl.colb /* comment 2 */,
  CAST(x AS INT), /* comment 3 */
  y /* comment 4 */
FROM bar /* comment 5 */, tbl /*          comment 6 */

from sqlglot import parse_one, exp

# print all column references (a and b)
for column in parse_one("SELECT a, b + 1 AS c FROM d").find_all(exp.Column):
    print(column.alias_or_name)

# find all projections in select statements (a and c)
for select in parse_one("SELECT a, b + 1 AS c FROM d").find_all(exp.Select):
    for projection in select.expressions:
        print(projection.alias_or_name)

# find all tables (x, y, z)
for table in parse_one("SELECT * FROM x JOIN y JOIN z").find_all(exp.Table):
    print(table.name)

import sqlglot
sqlglot.transpile("SELECT foo FROM (SELECT baz FROM t")

import sqlglot
try:
    sqlglot.transpile("SELECT foo FROM (SELECT baz FROM t")
except sqlglot.errors.ParseError as e:
    print(e.errors)

[{
  'description': 'Expecting )',
  'line': 1,
  'col': 34,
  'start_context': 'SELECT foo FROM (SELECT baz FROM ',
  'highlight': 't',
  'end_context': '',
  'into_expression': None
}]

import sqlglot
sqlglot.transpile("SELECT APPROX_DISTINCT(a, 0.1) FROM foo", read="presto", write="hive")

APPROX_COUNT_DISTINCT does not support accuracy
'SELECT APPROX_COUNT_DISTINCT(a) FROM foo'

import sqlglot
sqlglot.transpile("SELECT APPROX_DISTINCT(a, 0.1) FROM foo", read="presto", write="hive", unsupported_level=sqlglot.ErrorLevel.RAISE)

from sqlglot import select, condition

where = condition("x=1").and_("y=1")
select("*").from_("y").where(where).sql()

'SELECT * FROM y WHERE x = 1 AND y = 1'

from sqlglot import parse_one
parse_one("SELECT x FROM y").from_("z").sql()

'SELECT x FROM z'

from sqlglot import exp, parse_one

expression_tree = parse_one("SELECT a FROM x")

def transformer(node):
    if isinstance(node, exp.Column) and node.name == "a":
        return parse_one("FUN(a)")
    return node

transformed_tree = expression_tree.transform(transformer)
transformed_tree.sql()

'SELECT FUN(a) FROM x'

import sqlglot
from sqlglot.optimizer import optimize

print(
    optimize(
        sqlglot.parse_one("""
            SELECT A OR (B OR (C AND D))
            FROM x
            WHERE Z = date '2021-01-01' + INTERVAL '1' month OR 1 = 0
        """),
        schema={"x": {"A": "INT", "B": "INT", "C": "INT", "D": "INT", "Z": "STRING"}}
    ).sql(pretty=True)
)

SELECT
  (
    "x"."a" <> 0 OR "x"."b" <> 0 OR "x"."c" <> 0
  )
  AND (
    "x"."a" <> 0 OR "x"."b" <> 0 OR "x"."d" <> 0
  ) AS "_col_0"
FROM "x" AS "x"
WHERE
  CAST("x"."z" AS DATE) = CAST('2021-02-01' AS DATE)

from sqlglot import parse_one
print(repr(parse_one("SELECT a + 1 AS z")))

Select(
  expressions=[
    Alias(
      this=Add(
        this=Column(
          this=Identifier(this=a, quoted=False)),
        expression=Literal(this=1, is_string=False)),
      alias=Identifier(this=z, quoted=False))])

from sqlglot import diff, parse_one
diff(parse_one("SELECT a + b, c, d"), parse_one("SELECT c, a - b, d"))

[
  Remove(expression=Add(
    this=Column(
      this=Identifier(this=a, quoted=False)),
    expression=Column(
      this=Identifier(this=b, quoted=False)))),
  Insert(expression=Sub(
    this=Column(
      this=Identifier(this=a, quoted=False)),
    expression=Column(
      this=Identifier(this=b, quoted=False)))),
  Keep(
    source=Column(this=Identifier(this=a, quoted=False)),
    target=Column(this=Identifier(this=a, quoted=False))),
  ...
]

from sqlglot import exp
from sqlglot.dialects.dialect import Dialect
from sqlglot.generator import Generator
from sqlglot.tokens import Tokenizer, TokenType


class Custom(Dialect):
    class Tokenizer(Tokenizer):
        QUOTES = ["'", '"']
        IDENTIFIERS = ["`"]

        KEYWORDS = {
            **Tokenizer.KEYWORDS,
            "INT64": TokenType.BIGINT,
            "FLOAT64": TokenType.DOUBLE,
        }

    class Generator(Generator):
        TRANSFORMS = {exp.Array: lambda self, e: f"[{self.expressions(e)}]"}

        TYPE_MAPPING = {
            exp.DataType.Type.TINYINT: "INT64",
            exp.DataType.Type.SMALLINT: "INT64",
            exp.DataType.Type.INT: "INT64",
            exp.DataType.Type.BIGINT: "INT64",
            exp.DataType.Type.DECIMAL: "NUMERIC",
            exp.DataType.Type.FLOAT: "FLOAT64",
            exp.DataType.Type.DOUBLE: "FLOAT64",
            exp.DataType.Type.BOOLEAN: "BOOL",
            exp.DataType.Type.TEXT: "STRING",
        }

print(Dialect["custom"])

from sqlglot.executor import execute

tables = {
    "sushi": [
        {"id": 1, "price": 1.0},
        {"id": 2, "price": 2.0},
        {"id": 3, "price": 3.0},
    ],
    "order_items": [
        {"sushi_id": 1, "order_id": 1},
        {"sushi_id": 1, "order_id": 1},
        {"sushi_id": 2, "order_id": 1},
        {"sushi_id": 3, "order_id": 2},
    ],
    "orders": [
        {"id": 1, "user_id": 1},
        {"id": 2, "user_id": 2},
    ],
}

execute(
    """
    SELECT
      o.user_id,
      SUM(s.price) AS price
    FROM orders o
    JOIN order_items i
      ON o.id = i.order_id
    JOIN sushi s
      ON i.sushi_id = s.id
    GROUP BY o.user_id
    """,
    tables=tables
)

user_id price
      1   4.0
      2   3.0

x + interval '1' month