|
| 1 | +# Copyright 2021 Google LLC |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# https://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | + |
| 16 | +def create_table_external_hive_partitioned(table_id: str): |
| 17 | + original_table_id = table_id |
| 18 | + # [START bigquery_create_table_external_hivepartitioned] |
| 19 | + # Demonstrates creating an external table with hive partitioning. |
| 20 | + |
| 21 | + # TODO(developer): Set table_id to the ID of the table to create. |
| 22 | + table_id = "your-project.your_dataset.your_table_name" |
| 23 | + |
| 24 | + # TODO(developer): Set source uri. |
| 25 | + # Example file: |
| 26 | + # gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/dt=2020-11-15/file1.parquet |
| 27 | + uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*" |
| 28 | + |
| 29 | + # TODO(developer): Set source uri prefix. |
| 30 | + source_uri_prefix = ( |
| 31 | + "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/" |
| 32 | + ) |
| 33 | + |
| 34 | + # [END bigquery_create_table_external_hivepartitioned] |
| 35 | + table_id = original_table_id |
| 36 | + # [START bigquery_create_table_external_hivepartitioned] |
| 37 | + from google.cloud import bigquery |
| 38 | + |
| 39 | + # Construct a BigQuery client object. |
| 40 | + client = bigquery.Client() |
| 41 | + |
| 42 | + # Configure the external data source. |
| 43 | + external_config = bigquery.ExternalConfig("PARQUET") |
| 44 | + external_config.source_uris = [uri] |
| 45 | + external_config.autodetect = True |
| 46 | + |
| 47 | + # Configure partitioning options. |
| 48 | + hive_partitioning_opts = bigquery.external_config.HivePartitioningOptions() |
| 49 | + |
| 50 | + # The layout of the files in here is compatible with the layout requirements for hive partitioning, |
| 51 | + # so we can add an optional Hive partitioning configuration to leverage the object paths for deriving |
| 52 | + # partitioning column information. |
| 53 | + |
| 54 | + # For more information on how partitions are extracted, see: |
| 55 | + # https://cloud.google.com/bigquery/docs/hive-partitioned-queries-gcs |
| 56 | + |
| 57 | + # We have a "/dt=YYYY-MM-DD/" path component in our example files as documented above. |
| 58 | + # Autolayout will expose this as a column named "dt" of type DATE. |
| 59 | + hive_partitioning_opts.mode = "AUTO" |
| 60 | + hive_partitioning_opts.require_partition_filter = True |
| 61 | + hive_partitioning_opts.source_uri_prefix = source_uri_prefix |
| 62 | + |
| 63 | + external_config.hive_partitioning = hive_partitioning_opts |
| 64 | + |
| 65 | + table = bigquery.Table(table_id) |
| 66 | + table.external_data_configuration = external_config |
| 67 | + |
| 68 | + table = client.create_table(table) # Make an API request. |
| 69 | + print( |
| 70 | + "Created table {}.{}.{}".format(table.project, table.dataset_id, table.table_id) |
| 71 | + ) |
| 72 | + # [END bigquery_create_table_external_hivepartitioned] |
| 73 | + return table |
0 commit comments