Repository navigation
Expand file tree
/
Copy pathsubstrait.py
More file actions
58 lines (48 loc) · 2.33 KB
/
Copy pathsubstrait.py
File metadata and controls
58 lines (48 loc) · 2.33 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
# 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 datafusion import SessionContext
from datafusion import substrait as ss
# Create a DataFusion context
ctx = SessionContext()
# Register table with context
ctx.register_csv(
"aggregate_test_data", "./testing/data/csv/aggregate_test_100.csv"
)
substrait_plan = ss.substrait.serde.serialize_to_plan(
"SELECT * FROM aggregate_test_data", ctx
)
# type(substrait_plan) -> <class 'datafusion.substrait.plan'>
# Encode it to bytes
substrait_bytes = substrait_plan.encode()
# type(substrait_bytes) -> <class 'bytes'>, at this point the bytes can be distributed to file, network, etc safely
# where they could subsequently be deserialized on the receiving end.
# Alternative serialization approaches
# type(substrait_bytes) -> <class 'bytes'>, at this point the bytes can be distributed to file, network, etc safely
# where they could subsequently be deserialized on the receiving end.
substrait_bytes = ss.substrait.serde.serialize_bytes(
"SELECT * FROM aggregate_test_data", ctx
)
# Imagine here bytes would be read from network, file, etc ... for example brevity this is omitted and variable is simply reused
# type(substrait_plan) -> <class 'datafusion.substrait.plan'>
substrait_plan = ss.substrait.serde.deserialize_bytes(substrait_bytes)
# type(df_logical_plan) -> <class 'substrait.LogicalPlan'>
df_logical_plan = ss.substrait.consumer.from_substrait_plan(
ctx, substrait_plan
)
# Back to Substrait Plan just for demonstration purposes
# type(substrait_plan) -> <class 'datafusion.substrait.plan'>
substrait_plan = ss.substrait.producer.to_substrait_plan(df_logical_plan)