Repository navigation
Expand file tree
/
Copy pathtest_io.py
More file actions
94 lines (73 loc) · 2.91 KB
/
Copy pathtest_io.py
File metadata and controls
94 lines (73 loc) · 2.91 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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
# 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.
from pathlib import Path
import pyarrow as pa
from datafusion import column
from datafusion.io import read_avro, read_csv, read_json, read_parquet
def test_read_json_global_ctx(ctx):
path = Path(__file__).parent.resolve()
# Default
test_data_path = Path(path) / "data_test_context" / "data.json"
df = read_json(test_data_path)
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].column(1) == pa.array([1, 2, 3])
# Schema
schema = pa.schema(
[
pa.field("A", pa.string(), nullable=True),
]
)
df = read_json(test_data_path, schema=schema)
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].schema == schema
# File extension
test_data_path = Path(path) / "data_test_context" / "data.json"
df = read_json(test_data_path, file_extension=".json")
result = df.collect()
assert result[0].column(0) == pa.array(["a", "b", "c"])
assert result[0].column(1) == pa.array([1, 2, 3])
def test_read_parquet_global():
parquet_df = read_parquet(path="parquet/data/alltypes_plain.parquet")
parquet_df.show()
assert parquet_df is not None
path = Path.cwd() / "parquet/data/alltypes_plain.parquet"
parquet_df = read_parquet(path=path)
assert parquet_df is not None
def test_read_csv():
csv_df = read_csv(path="testing/data/csv/aggregate_test_100.csv")
csv_df.select(column("c1")).show()
def test_read_csv_list():
csv_df = read_csv(path=["testing/data/csv/aggregate_test_100.csv"])
expected = csv_df.count() * 2
double_csv_df = read_csv(
path=[
"testing/data/csv/aggregate_test_100.csv",
"testing/data/csv/aggregate_test_100.csv",
]
)
actual = double_csv_df.count()
double_csv_df.select(column("c1")).show()
assert actual == expected
def test_read_avro():
avro_df = read_avro(path="testing/data/avro/alltypes_plain.avro")
avro_df.show()
assert avro_df is not None
path = Path.cwd() / "testing/data/avro/alltypes_plain.avro"
avro_df = read_avro(path=path)
assert avro_df is not None