Merge pull request ClickHouse#71716 from rschu1ze/docs-tpch-s3

Docs: Steps to populate TPC-H tables from S3
bigo-sg · Nov 10, 2024 · 60ea77a · 60ea77a
2 parents 42a8c01 + 892d43b
commit 60ea77a
Showing 1 changed file with 28 additions and 1 deletion.
diff --git a/docs/en/getting-started/example-datasets/tpch.md b/docs/en/getting-started/example-datasets/tpch.md
@@ -166,10 +166,37 @@ clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO orders FORMAT
 clickhouse-client --format_csv_delimiter '|' --query "INSERT INTO lineitem FORMAT CSV" < lineitem.tbl
 ```
 
-The queries are generated by `./qgen -s <scaling_factor>`. Example queries for `s = 100`:
+:::note
+Instead of using tpch-kit and generating the tables by yourself, you can alternatively import the data from a public S3 bucket. Make sure
+to create empty tables first using above `CREATE` statements.
+
+```sql
+-- Scaling factor 1
+INSERT INTO nation SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/nation.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO region SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/region.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO part SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/part.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO supplier SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/supplier.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO partsupp SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/partsupp.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO customer SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/customer.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO orders SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/orders.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO lineitem SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/1/lineitem.tbl', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+
+-- Scaling factor 100
+INSERT INTO nation SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/nation.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO region SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/region.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO part SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/part.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO supplier SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/supplier.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO partsupp SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/partsupp.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO customer SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/customer.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO orders SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/orders.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+INSERT INTO lineitem SELECT * FROM s3('https://clickhouse-datasets.s3.amazonaws.com/h/100/lineitem.tbl.gz', NOSIGN, CSV) SETTINGS format_csv_delimiter = '|', input_format_defaults_for_omitted_fields = 1, input_format_csv_empty_as_default = 1;
+````
+:::
 
 ## Queries
 
+The queries are generated by `./qgen -s <scaling_factor>`. Example queries for `s = 100`:
+
 **Correctness**
 
 The result of the queries agrees with the official results unless mentioned otherwise. To verify, generate a TPC-H database with scale