From fbb056e56459be523a75e2bd799b7dd233a09fce Mon Sep 17 00:00:00 2001 From: Yingfan Chen Date: Tue, 24 Aug 2021 08:55:27 +0800 Subject: [PATCH 1/2] fix star schema zh sql --- .../example-datasets/star-schema.md | 52 ++++++++++++++++--- 1 file changed, 44 insertions(+), 8 deletions(-) diff --git a/docs/zh/getting-started/example-datasets/star-schema.md b/docs/zh/getting-started/example-datasets/star-schema.md index fcb6e90c694..4f3d8f51f07 100644 --- a/docs/zh/getting-started/example-datasets/star-schema.md +++ b/docs/zh/getting-started/example-datasets/star-schema.md @@ -103,19 +103,55 @@ $ clickhouse-client --query "INSERT INTO lineorder FORMAT CSV" < lineorder.tbl 将`star schema`转换为`flat schema`: ``` sql -SET max_memory_usage = 20000000000, allow_experimental_multiple_joins_emulation = 1; +SET max_memory_usage = 20000000000; CREATE TABLE lineorder_flat ENGINE = MergeTree PARTITION BY toYear(LO_ORDERDATE) ORDER BY (LO_ORDERDATE, LO_ORDERKEY) AS -SELECT l.*, c.*, s.*, p.* -FROM lineorder l - ANY INNER JOIN customer c ON (c.C_CUSTKEY = l.LO_CUSTKEY) - ANY INNER JOIN supplier s ON (s.S_SUPPKEY = l.LO_SUPPKEY) - ANY INNER JOIN part p ON (p.P_PARTKEY = l.LO_PARTKEY); - -ALTER TABLE lineorder_flat DROP COLUMN C_CUSTKEY, DROP COLUMN S_SUPPKEY, DROP COLUMN P_PARTKEY; +SELECT + l.LO_ORDERKEY AS LO_ORDERKEY, + l.LO_LINENUMBER AS LO_LINENUMBER, + l.LO_CUSTKEY AS LO_CUSTKEY, + l.LO_PARTKEY AS LO_PARTKEY, + l.LO_SUPPKEY AS LO_SUPPKEY, + l.LO_ORDERDATE AS LO_ORDERDATE, + l.LO_ORDERPRIORITY AS LO_ORDERPRIORITY, + l.LO_SHIPPRIORITY AS LO_SHIPPRIORITY, + l.LO_QUANTITY AS LO_QUANTITY, + l.LO_EXTENDEDPRICE AS LO_EXTENDEDPRICE, + l.LO_ORDTOTALPRICE AS LO_ORDTOTALPRICE, + l.LO_DISCOUNT AS LO_DISCOUNT, + l.LO_REVENUE AS LO_REVENUE, + l.LO_SUPPLYCOST AS LO_SUPPLYCOST, + l.LO_TAX AS LO_TAX, + l.LO_COMMITDATE AS LO_COMMITDATE, + l.LO_SHIPMODE AS LO_SHIPMODE, + c.C_NAME AS C_NAME, + c.C_ADDRESS AS C_ADDRESS, + c.C_CITY AS C_CITY, + c.C_NATION AS C_NATION, + c.C_REGION AS C_REGION, + c.C_PHONE AS C_PHONE, + c.C_MKTSEGMENT AS C_MKTSEGMENT, + s.S_NAME AS S_NAME, + s.S_ADDRESS AS S_ADDRESS, + s.S_CITY AS S_CITY, + s.S_NATION AS S_NATION, + s.S_REGION AS S_REGION, + s.S_PHONE AS S_PHONE, + p.P_NAME AS P_NAME, + p.P_MFGR AS P_MFGR, + p.P_CATEGORY AS P_CATEGORY, + p.P_BRAND AS P_BRAND, + p.P_COLOR AS P_COLOR, + p.P_TYPE AS P_TYPE, + p.P_SIZE AS P_SIZE, + p.P_CONTAINER AS P_CONTAINER +FROM lineorder AS l +INNER JOIN customer AS c ON c.C_CUSTKEY = l.LO_CUSTKEY +INNER JOIN supplier AS s ON s.S_SUPPKEY = l.LO_SUPPKEY +INNER JOIN part AS p ON p.P_PARTKEY = l.LO_PARTKEY; ``` 运行查询: From e83675264bb6dd6bf85c123d769a4f2744980a95 Mon Sep 17 00:00:00 2001 From: Yingfan Chen Date: Tue, 24 Aug 2021 22:38:33 +0800 Subject: [PATCH 2/2] fix sql query 1-4.3 to be multilines --- .../example-datasets/star-schema.md | 197 +++++++++++++++--- 1 file changed, 164 insertions(+), 33 deletions(-) diff --git a/docs/zh/getting-started/example-datasets/star-schema.md b/docs/zh/getting-started/example-datasets/star-schema.md index 4f3d8f51f07..563b7922238 100644 --- a/docs/zh/getting-started/example-datasets/star-schema.md +++ b/docs/zh/getting-started/example-datasets/star-schema.md @@ -7,7 +7,7 @@ toc_title: Star Schema Benchmark 编译 dbgen: -``` bash +```bash $ git clone git@github.com:vadimtk/ssb-dbgen.git $ cd ssb-dbgen $ make @@ -16,9 +16,9 @@ $ make 开始生成数据: !!! warning "注意" - 使用`-s 100`dbgen将生成6亿行数据(67GB), 如果使用`-s 1000`它会生成60亿行数据(这需要很多时间)) +使用`-s 100`dbgen 将生成 6 亿行数据(67GB), 如果使用`-s 1000`它会生成 60 亿行数据(这需要很多时间)) -``` bash +```bash $ ./dbgen -s 1000 -T c $ ./dbgen -s 1000 -T l $ ./dbgen -s 1000 -T p @@ -26,9 +26,9 @@ $ ./dbgen -s 1000 -T s $ ./dbgen -s 1000 -T d ``` -在ClickHouse中创建数据表: +在 ClickHouse 中创建数据表: -``` sql +```sql CREATE TABLE customer ( C_CUSTKEY UInt32, @@ -93,7 +93,7 @@ ENGINE = MergeTree ORDER BY S_SUPPKEY; 写入数据: -``` bash +```bash $ clickhouse-client --query "INSERT INTO customer FORMAT CSV" < customer.tbl $ clickhouse-client --query "INSERT INTO part FORMAT CSV" < part.tbl $ clickhouse-client --query "INSERT INTO supplier FORMAT CSV" < supplier.tbl @@ -102,7 +102,7 @@ $ clickhouse-client --query "INSERT INTO lineorder FORMAT CSV" < lineorder.tbl 将`star schema`转换为`flat schema`: -``` sql +```sql SET max_memory_usage = 20000000000; CREATE TABLE lineorder_flat @@ -158,80 +158,211 @@ INNER JOIN part AS p ON p.P_PARTKEY = l.LO_PARTKEY; Q1.1 -``` sql -SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue FROM lineorder_flat WHERE toYear(LO_ORDERDATE) = 1993 AND LO_DISCOUNT BETWEEN 1 AND 3 AND LO_QUANTITY < 25; +```sql +SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue +FROM lineorder_flat +WHERE toYear(LO_ORDERDATE) = 1993 AND LO_DISCOUNT BETWEEN 1 AND 3 AND LO_QUANTITY < 25; ``` Q1.2 -``` sql -SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue FROM lineorder_flat WHERE toYYYYMM(LO_ORDERDATE) = 199401 AND LO_DISCOUNT BETWEEN 4 AND 6 AND LO_QUANTITY BETWEEN 26 AND 35; +```sql +SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue +FROM lineorder_flat +WHERE toYYYYMM(LO_ORDERDATE) = 199401 AND LO_DISCOUNT BETWEEN 4 AND 6 AND LO_QUANTITY BETWEEN 26 AND 35; ``` Q1.3 -``` sql -SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue FROM lineorder_flat WHERE toISOWeek(LO_ORDERDATE) = 6 AND toYear(LO_ORDERDATE) = 1994 AND LO_DISCOUNT BETWEEN 5 AND 7 AND LO_QUANTITY BETWEEN 26 AND 35; +```sql +SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue +FROM lineorder_flat +WHERE toISOWeek(LO_ORDERDATE) = 6 AND toYear(LO_ORDERDATE) = 1994 + AND LO_DISCOUNT BETWEEN 5 AND 7 AND LO_QUANTITY BETWEEN 26 AND 35; ``` Q2.1 -``` sql -SELECT sum(LO_REVENUE), toYear(LO_ORDERDATE) AS year, P_BRAND FROM lineorder_flat WHERE P_CATEGORY = 'MFGR#12' AND S_REGION = 'AMERICA' GROUP BY year, P_BRAND ORDER BY year, P_BRAND; +```sql +SELECT + sum(LO_REVENUE), + toYear(LO_ORDERDATE) AS year, + P_BRAND +FROM lineorder_flat +WHERE P_CATEGORY = 'MFGR#12' AND S_REGION = 'AMERICA' +GROUP BY + year, + P_BRAND +ORDER BY + year, + P_BRAND; ``` Q2.2 -``` sql -SELECT sum(LO_REVENUE), toYear(LO_ORDERDATE) AS year, P_BRAND FROM lineorder_flat WHERE P_BRAND BETWEEN 'MFGR#2221' AND 'MFGR#2228' AND S_REGION = 'ASIA' GROUP BY year, P_BRAND ORDER BY year, P_BRAND; +```sql +SELECT + sum(LO_REVENUE), + toYear(LO_ORDERDATE) AS year, + P_BRAND +FROM lineorder_flat +WHERE P_BRAND >= 'MFGR#2221' AND P_BRAND <= 'MFGR#2228' AND S_REGION = 'ASIA' +GROUP BY + year, + P_BRAND +ORDER BY + year, + P_BRAND; ``` Q2.3 -``` sql -SELECT sum(LO_REVENUE), toYear(LO_ORDERDATE) AS year, P_BRAND FROM lineorder_flat WHERE P_BRAND = 'MFGR#2239' AND S_REGION = 'EUROPE' GROUP BY year, P_BRAND ORDER BY year, P_BRAND; +```sql +SELECT + sum(LO_REVENUE), + toYear(LO_ORDERDATE) AS year, + P_BRAND +FROM lineorder_flat +WHERE P_BRAND = 'MFGR#2239' AND S_REGION = 'EUROPE' +GROUP BY + year, + P_BRAND +ORDER BY + year, + P_BRAND; ``` Q3.1 -``` sql -SELECT C_NATION, S_NATION, toYear(LO_ORDERDATE) AS year, sum(LO_REVENUE) AS revenue FROM lineorder_flat WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND year >= 1992 AND year <= 1997 GROUP BY C_NATION, S_NATION, year ORDER BY year asc, revenue desc; +```sql +SELECT + C_NATION, + S_NATION, + toYear(LO_ORDERDATE) AS year, + sum(LO_REVENUE) AS revenue +FROM lineorder_flat +WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND year >= 1992 AND year <= 1997 +GROUP BY + C_NATION, + S_NATION, + year +ORDER BY + year ASC, + revenue DESC; ``` Q3.2 -``` sql -SELECT C_CITY, S_CITY, toYear(LO_ORDERDATE) AS year, sum(LO_REVENUE) AS revenue FROM lineorder_flat WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND year >= 1992 AND year <= 1997 GROUP BY C_CITY, S_CITY, year ORDER BY year asc, revenue desc; +```sql +SELECT + C_CITY, + S_CITY, + toYear(LO_ORDERDATE) AS year, + sum(LO_REVENUE) AS revenue +FROM lineorder_flat +WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND year >= 1992 AND year <= 1997 +GROUP BY + C_CITY, + S_CITY, + year +ORDER BY + year ASC, + revenue DESC; ``` Q3.3 -``` sql -SELECT C_CITY, S_CITY, toYear(LO_ORDERDATE) AS year, sum(LO_REVENUE) AS revenue FROM lineorder_flat WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND year >= 1992 AND year <= 1997 GROUP BY C_CITY, S_CITY, year ORDER BY year asc, revenue desc; +```sql +SELECT + C_CITY, + S_CITY, + toYear(LO_ORDERDATE) AS year, + sum(LO_REVENUE) AS revenue +FROM lineorder_flat +WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND year >= 1992 AND year <= 1997 +GROUP BY + C_CITY, + S_CITY, + year +ORDER BY + year ASC, + revenue DESC; ``` Q3.4 -``` sql -SELECT C_CITY, S_CITY, toYear(LO_ORDERDATE) AS year, sum(LO_REVENUE) AS revenue FROM lineorder_flat WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND toYYYYMM(LO_ORDERDATE) = '199712' GROUP BY C_CITY, S_CITY, year ORDER BY year asc, revenue desc; +```sql +SELECT + C_CITY, + S_CITY, + toYear(LO_ORDERDATE) AS year, + sum(LO_REVENUE) AS revenue +FROM lineorder_flat +WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND toYYYYMM(LO_ORDERDATE) = 199712 +GROUP BY + C_CITY, + S_CITY, + year +ORDER BY + year ASC, + revenue DESC; ``` Q4.1 -``` sql -SELECT toYear(LO_ORDERDATE) AS year, C_NATION, sum(LO_REVENUE - LO_SUPPLYCOST) AS profit FROM lineorder_flat WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2') GROUP BY year, C_NATION ORDER BY year, C_NATION; +```sql +SELECT + toYear(LO_ORDERDATE) AS year, + C_NATION, + sum(LO_REVENUE - LO_SUPPLYCOST) AS profit +FROM lineorder_flat +WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2') +GROUP BY + year, + C_NATION +ORDER BY + year ASC, + C_NATION ASC; ``` Q4.2 -``` sql -SELECT toYear(LO_ORDERDATE) AS year, S_NATION, P_CATEGORY, sum(LO_REVENUE - LO_SUPPLYCOST) AS profit FROM lineorder_flat WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (year = 1997 OR year = 1998) AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2') GROUP BY year, S_NATION, P_CATEGORY ORDER BY year, S_NATION, P_CATEGORY; +```sql +SELECT + toYear(LO_ORDERDATE) AS year, + S_NATION, + P_CATEGORY, + sum(LO_REVENUE - LO_SUPPLYCOST) AS profit +FROM lineorder_flat +WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (year = 1997 OR year = 1998) AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2') +GROUP BY + year, + S_NATION, + P_CATEGORY +ORDER BY + year ASC, + S_NATION ASC, + P_CATEGORY ASC; ``` Q4.3 -``` sql -SELECT toYear(LO_ORDERDATE) AS year, S_CITY, P_BRAND, sum(LO_REVENUE - LO_SUPPLYCOST) AS profit FROM lineorder_flat WHERE S_NATION = 'UNITED STATES' AND (year = 1997 OR year = 1998) AND P_CATEGORY = 'MFGR#14' GROUP BY year, S_CITY, P_BRAND ORDER BY year, S_CITY, P_BRAND; +```sql +SELECT + toYear(LO_ORDERDATE) AS year, + S_CITY, + P_BRAND, + sum(LO_REVENUE - LO_SUPPLYCOST) AS profit +FROM lineorder_flat +WHERE S_NATION = 'UNITED STATES' AND (year = 1997 OR year = 1998) AND P_CATEGORY = 'MFGR#14' +GROUP BY + year, + S_CITY, + P_BRAND +ORDER BY + year ASC, + S_CITY ASC, + P_BRAND ASC; ``` [原始文章](https://clickhouse.tech/docs/en/getting_started/example_datasets/star_schema/)