Repository navigation
Expand file tree
/
Copy pathutils.py
More file actions
62 lines (51 loc) · 2.21 KB
/
Copy pathutils.py
File metadata and controls
62 lines (51 loc) · 2.21 KB
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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
"""Testing-only helpers for datafusion-python.
This module contains utilities used by the test-suite that should not be
exposed as part of the public API. Keep the implementation minimal and
documented so reviewers can easily see it's test-only.
"""
from __future__ import annotations
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from datafusion import DataFrame
from datafusion.context import SessionContext
def range_table(
ctx: SessionContext,
start: int,
stop: int | None = None,
step: int = 1,
partitions: int | None = None,
) -> DataFrame:
"""Create a DataFrame containing a sequence of numbers using SQL RANGE.
This mirrors the previous ``SessionContext.range`` convenience method but
lives in a testing-only module so it doesn't expand the public surface.
Args:
ctx: SessionContext instance to run the SQL against.
start: Starting value for the sequence or exclusive stop when ``stop``
is ``None``.
stop: Exclusive upper bound of the sequence.
step: Increment between successive values.
partitions: Optional number of partitions for the generated data.
Returns:
DataFrame produced by the range table function.
"""
if stop is None:
start, stop = 0, start
parts = f", {int(partitions)}" if partitions is not None else ""
sql = f"SELECT * FROM range({int(start)}, {int(stop)}, {int(step)}{parts})"
return ctx.sql(sql)