mirror of
https://github.com/Microsoft/sql-server-samples.git
synced 2025-12-08 14:58:54 +00:00
42 lines
1.1 KiB
Transact-SQL
42 lines
1.1 KiB
Transact-SQL
USE sales
|
|
GO
|
|
|
|
-- Create file format for CSV separated file with appropriate properties.
|
|
--
|
|
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'csv_file')
|
|
CREATE EXTERNAL FILE FORMAT csv_file
|
|
WITH (
|
|
FORMAT_TYPE = DELIMITEDTEXT,
|
|
FORMAT_OPTIONS(
|
|
FIELD_TERMINATOR = ',',
|
|
STRING_DELIMITER = '"',
|
|
USE_TYPE_DEFAULT = TRUE)
|
|
);
|
|
|
|
|
|
-- Create external table over HDFS data source (SqlStoragePool) in
|
|
-- SQL Server 2019 big data cluster. The SqlStoragePool data source
|
|
-- is a special data source that is available in any new database in
|
|
-- SQL Master instance.
|
|
--
|
|
CREATE EXTERNAL TABLE [product_reviews_hdfs_csv]
|
|
("pr_review_sk" BIGINT , "pr_review_content" varchar(8000))
|
|
WITH
|
|
(
|
|
DATA_SOURCE = SqlStoragePool,
|
|
LOCATION = '/product_review_data',
|
|
FILE_FORMAT = csv_file
|
|
);
|
|
GO
|
|
|
|
-- Join external table with local tables
|
|
--
|
|
SELECT
|
|
p.pr_review_sk, pc.pr_review_content
|
|
FROM product_reviews as p
|
|
JOIN (SELECT TOP(10) * FROM product_reviews_hdfs_csv) AS pc
|
|
ON pc.pr_review_sk = p.pr_review_sk;
|
|
GO
|
|
|
|
DROP EXTERNAL TABLE [dbo].[product_reviews_hdfs_csv];
|
|
GO |