mirror of
https://github.com/langchain-ai/datafusion.git
synced 2026-07-16 12:04:27 -04:00
Jiayu Liu
50 lines
1.6 KiB
Python
50 lines
1.6 KiB
Python
# 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.
|
|
|
|
import pyarrow as pa
|
|
import pytest
|
|
from datafusion import ExecutionContext
|
|
from datafusion import functions as f
|
|
|
|
|
|
@pytest.fixture
|
|
def df():
|
|
ctx = ExecutionContext()
|
|
|
|
# create a RecordBatch and a new DataFrame from it
|
|
batch = pa.RecordBatch.from_arrays(
|
|
[pa.array(["Hello", "World", "!"]), pa.array([4, 5, 6])],
|
|
names=["a", "b"],
|
|
)
|
|
|
|
return ctx.create_dataframe([[batch]])
|
|
|
|
|
|
def test_string_functions(df):
|
|
df = df.select(f.md5(f.col("a")), f.lower(f.col("a")))
|
|
result = df.collect()
|
|
assert len(result) == 1
|
|
result = result[0]
|
|
assert result.column(0) == pa.array(
|
|
[
|
|
"8b1a9953c4611296a827abf8c47804d7",
|
|
"f5a7924e621e84c9280a9a27e1bcb7f6",
|
|
"9033e0e305f247c0c3c80d0c7848c8b3",
|
|
]
|
|
)
|
|
assert result.column(1) == pa.array(["hello", "world", "!"])
|