From 835c5b29a746756a5e63b08a66716092f5534c28 Mon Sep 17 00:00:00 2001 From: Geoffrey Yu Date: Mon, 15 Apr 2024 10:50:44 -0400 Subject: [PATCH] Add manifest for smaller CH-BenCHmark dataset for debugging --- .../manifests/manifest_chbenchmark_small.yml | 88 +++++++++++++++++++ 1 file changed, 88 insertions(+) create mode 100644 config/manifests/manifest_chbenchmark_small.yml diff --git a/config/manifests/manifest_chbenchmark_small.yml b/config/manifests/manifest_chbenchmark_small.yml new file mode 100644 index 00000000..dd752874 --- /dev/null +++ b/config/manifests/manifest_chbenchmark_small.yml @@ -0,0 +1,88 @@ +s3_bucket: geoffxy-research +s3_bucket_region: us-east-1 +schema_name: chbenchmark_small + +tables: + - table_name: warehouse + s3_path: chbenchmark_small/warehouse/warehouse.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: item + s3_path: chbenchmark_small/item/item.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: stock + s3_path: chbenchmark_small/stock/stock.tbl + aurora_options: FORMAT CSV, HEADER, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: district + s3_path: chbenchmark_small/district/district.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: customer + s3_path: chbenchmark_small/customer/customer.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: history + s3_path: chbenchmark_small/history/history.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: orders + s3_path: chbenchmark_small/orders/orders.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: new_order + s3_path: chbenchmark_small/new_order/new_order.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: order_line + s3_path: chbenchmark_small/order_line/order_line.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: supplier + s3_path: chbenchmark_small/supplier/supplier.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: nation + s3_path: chbenchmark_small/nation/nation.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1') + + - table_name: region + s3_path: chbenchmark_small/region/region.tbl + aurora_options: FORMAT CSV, HEADER true, ESCAPE ''\'', DELIMITER ''|'' + redshift_options: CSV IGNOREHEADER 1 DELIMITER '|' BLANKSASNULL + athena_options1: ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' NULL DEFINED AS '' STORED AS TEXTFILE + athena_options2: TBLPROPERTIES ('skip.header.line.count' = '1')