github/sql-server-samples
1
0
Fork 0
mirror of https://github.com/Microsoft/sql-server-samples.git synced 2025-12-08 14:58:54 +00:00
Code Issues Releases Wiki Activity

Added data source DDLs

Browse Source 
so script can be self-contained.
This commit is contained in:
Umachandar Jayachandran
2019-04-12 13:25:42 -07:00
parent 960f46962b
commit d2f2834644
9 changed files with 84 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/features/sql-big-data-cluster/data-virtualization/hadoop/inventory-export-hdfs-rcfile.sql
+15
View File
@@ -1,6 +1,8 @@
USE sales
GO
-- Enable option to allow INSERT against external table defined on HADOOP data source
--
DECLARE @config_option nvarchar(100) = 'allow polybase export';
IF NOT EXISTS(SELECT * FROM sys.configurations WHERE name = @config_option and value_in_use = 1)
BEGIN
@@ -9,6 +11,19 @@ BEGIN
END;
GO
-- Create data source for HDFS inside SQL big data cluster using the HADOOP type.
-- The HADOOP data source type was introduced in SQL Server 2016 to query data in
-- Hadoop clusters and relies on Java Hadoop client libraries and Map/Reduce for query
-- execution.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'HadoopData')
CREATE EXTERNAL DATA SOURCE HadoopData
WITH(
TYPE=HADOOP,
LOCATION='hdfs://mssql-master-pool-0.service-master-pool:9000/',
RESOURCE_MANAGER_LOCATION='mssql-master-pool-0.service-master-pool:8032'
);
-- Create file format for RCFILE with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'RCFILE')
samples/features/sql-big-data-cluster/data-virtualization/hadoop/product-reviews-hdfs-orc.sql
+13
View File
@@ -1,6 +1,19 @@
USE sales
GO
-- Create data source for HDFS inside SQL big data cluster using the HADOOP type.
-- The HADOOP data source type was introduced in SQL Server 2016 to query data in
-- Hadoop clusters and relies on Java Hadoop client libraries and Map/Reduce for query
-- execution.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'HadoopData')
CREATE EXTERNAL DATA SOURCE HadoopData
WITH(
TYPE=HADOOP,
LOCATION='hdfs://mssql-master-pool-0.service-master-pool:9000/',
RESOURCE_MANAGER_LOCATION='mssql-master-pool-0.service-master-pool:8032'
);
-- Create file format for orc file with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'orc_file')
samples/features/sql-big-data-cluster/data-virtualization/hadoop/web-clickstreams-hdfs-orc.sql
+13
View File
@@ -1,6 +1,19 @@
USE sales
GO
-- Create data source for HDFS inside SQL big data cluster using the HADOOP type.
-- The HADOOP data source type was introduced in SQL Server 2016 to query data in
-- Hadoop clusters and relies on Java Hadoop client libraries and Map/Reduce for query
-- execution.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'HadoopData')
CREATE EXTERNAL DATA SOURCE HadoopData
WITH(
TYPE=HADOOP,
LOCATION='hdfs://mssql-master-pool-0.service-master-pool:9000/',
RESOURCE_MANAGER_LOCATION='mssql-master-pool-0.service-master-pool:8032'
);
-- Create file format for orc file with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'orc_file')
samples/features/sql-big-data-cluster/data-virtualization/storage-pool/product-reviews-hdfs-csv.sql
+6
View File
@@ -1,6 +1,12 @@
USE sales
GO
-- Create external data source for HDFS inside SQ: big data cluster.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'SqlStoragePool')
CREATE EXTERNAL DATA SOURCE SqlStoragePool
WITH (LOCATION = 'sqlhdfs://service-master-pool:50070');
-- Create file format for CSV separated file with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'csv_file')
samples/features/sql-big-data-cluster/data-virtualization/storage-pool/product-reviews-hdfs-parquet.sql
+6
View File
@@ -1,6 +1,12 @@
USE sales
GO
-- Create external data source for HDFS inside SQ: big data cluster.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'SqlStoragePool')
CREATE EXTERNAL DATA SOURCE SqlStoragePool
WITH (LOCATION = 'sqlhdfs://service-master-pool:50070');
-- Create file format for parquet file with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'parquet_file')
samples/features/sql-big-data-cluster/data-virtualization/storage-pool/product-reviews-hdfs-tsv.sql
+6
View File
@@ -1,6 +1,12 @@
USE sales
GO
-- Create external data source for HDFS inside SQ: big data cluster.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'SqlStoragePool')
CREATE EXTERNAL DATA SOURCE SqlStoragePool
WITH (LOCATION = 'sqlhdfs://service-master-pool:50070');
-- Create file format for tab separated file with appropriate properties.
--
CREATE EXTERNAL FILE FORMAT tsv_file
samples/features/sql-big-data-cluster/data-virtualization/storage-pool/web-clickstreams-hdfs-csv.sql
+6
View File
@@ -1,6 +1,12 @@
USE sales
GO
-- Create external data source for HDFS inside SQ: big data cluster.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'SqlStoragePool')
CREATE EXTERNAL DATA SOURCE SqlStoragePool
WITH (LOCATION = 'sqlhdfs://service-master-pool:50070');
-- Create file format for CSV file with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'csv_file')
samples/features/sql-big-data-cluster/data-virtualization/storage-pool/web-clickstreams-hdfs-parquet.sql
+6
View File
@@ -1,6 +1,12 @@
USE sales
GO
-- Create external data source for HDFS inside SQ: big data cluster.
--
IF NOT EXISTS(SELECT * FROM sys.external_data_sources WHERE name = 'SqlStoragePool')
CREATE EXTERNAL DATA SOURCE SqlStoragePool
WITH (LOCATION = 'sqlhdfs://service-master-pool:50070');
-- Create file format for parquet file with appropriate properties.
--
IF NOT EXISTS(SELECT * FROM sys.external_file_formats WHERE name = 'parquet_file')