测试DuckDB 2.1的match_recognize模式匹配语句

1. 下载DuckDB 2.1 alpha版本

   C:\d>wget https://artifacts.duckdb.org/latest/duckdb-cli-windows-amd64.tar.gz -O duckdb-cli-windows-amd64-260918a.tar.gz

   duckdb-cli-windows-amd64-2609 100%[=================================================>] 18.39M 33.3KB/s in 7m 57s

   2026-09-18 17:29:40 (39.5 KB/s) - 'duckdb-cli-windows-amd64-260918a.tar.gz' saved [19288695/19288695]

2. 解压执行

   C:\d>duckdb0918a
   DuckDB v2.1.0-alpha42457 (Unknown Version)
   Enter ".help" for usage hints.

3. 用https://www.modb.pro/db/192919 中的例子测试，为了使用oracle的语法，先创建一个dual表。
   memory D create table dual as select 1 a;

with d (type,dt,status)as
(         select 'X' ,date '2021-7-1','1'  from dual
union all select 'X' ,date '2021-7-2','1'  from dual
union all select 'X' ,date '2021-7-3','0'  from dual
union all select 'X' ,date '2021-7-4','0'  from dual
union all select 'X' ,date '2021-7-5','1'  from dual
union all select 'X' ,date '2021-7-6','0'  from dual
union all select 'X' ,date '2021-7-7','0'  from dual
union all select 'X' ,date '2021-7-8','0'  from dual
union all select 'X' ,date '2021-7-9','1'  from dual
union all select 'X' ,date '2021-7-10','1'  from dual
union all select 'X' ,date '2021-7-11','1'  from dual
)
SELECT *
FROM d
MATCH_RECOGNIZE (
     PARTITION BY type
     ORDER BY dt
      measures
             dt as dt,
             status as status
      one ROW PER MATCH
     PATTERN (  A  )   
     DEFINE
           A as status<>prev(status)  or prev(status) is null
);

输出

memory D .read match-rec3.txt
┌─────────┬────────────┬─────────┐
│  type   │     dt     │ status  │
│ varchar │    date    │ varchar │
├─────────┼────────────┼─────────┤
│ X       │ 2021-07-01 │ 1       │
│ X       │ 2021-07-03 │ 0       │
│ X       │ 2021-07-05 │ 1       │
│ X       │ 2021-07-06 │ 0       │
│ X       │ 2021-07-09 │ 1       │
└─────────┴────────────┴─────────┘

with d (type,dt,status)as
(         select 'X' ,date '2021-7-1','1'  from dual
union all select 'X' ,date '2021-7-2','1'  from dual
union all select 'X' ,date '2021-7-3','0'  from dual
union all select 'X' ,date '2021-7-4','0'  from dual
union all select 'X' ,date '2021-7-5','1'  from dual
union all select 'X' ,date '2021-7-6','0'  from dual
union all select 'X' ,date '2021-7-7','0'  from dual
union all select 'X' ,date '2021-7-8','0'  from dual
union all select 'X' ,date '2021-7-9','1'  from dual
union all select 'X' ,date '2021-7-10','1'  from dual
union all select 'X' ,date '2021-7-11','1'  from dual
)
SELECT *
FROM d
MATCH_RECOGNIZE (
     PARTITION BY type
     ORDER BY dt
     ALL ROWS PER MATCH
     PATTERN (    (A|{-B-})+   )   
     DEFINE
        A as status<>last(status,1) or prev(status) is null
);

输出

memory D .read match-rec4.txt
┌─────────┬────────────┬─────────┐
│  type   │     dt     │ status  │
│ varchar │    date    │ varchar │
├─────────┼────────────┼─────────┤
│ X       │ 2021-07-01 │ 1       │
│ X       │ 2021-07-03 │ 0       │
│ X       │ 2021-07-05 │ 1       │
│ X       │ 2021-07-06 │ 0       │
│ X       │ 2021-07-09 │ 1       │
└─────────┴────────────┴─────────┘

with tmp(id ,page) as
(select 1,3 from dual union all select 2,4 from dual union all
 select 4,8 from dual union all select 3,5 from dual union all
 select 5,9 from dual union all select 6,16 from dual union all
 select 7,15 from dual union all select 8,18 from dual
) 
SELECT *
FROM tmp
MATCH_RECOGNIZE 
(
ORDER BY page
MEASURES
  A.page as firstpage,
  LAST(page) as lastpage,
  COUNT(*) as cnt
 ONE ROW PER MATCH
 AFTER MATCH SKIP PAST LAST ROW
 PATTERN (A B*)
 DEFINE B AS page = PREV(page)+1
);

输出，注意别名前的as不可省略。

memory D .read match-rec5.txt
Parser Error:
syntax error at or near "cnt"

LINE 29:   COUNT(*) cnt
                    ^^^
memory D .read match-rec5.txt
┌───────────┬──────────┬───────┐
│ firstpage │ lastpage │  cnt  │
│   int32   │  int32   │ int64 │
├───────────┼──────────┼───────┤
│        15 │       16 │     2 │
│        18 │       18 │     1 │
│         8 │        9 │     2 │
│         3 │        5 │     3 │
└───────────┴──────────┴───────┘

with gen (id, val) as 
(select 1, 3 from dual union all select 2, 2 from dual union all select 3,5 from dual union all
 select 5, 3 from dual union all select 8, 2 from dual union all select 9,5 from dual union all
 select 10, 3 from dual union all select 12, 2 from dual union all select 13,5 from dual union all
 select 14, 3 from dual union all select 15, 2 from dual union all select 16,5 from dual union all
 select 20, 3 from dual union all select 21, 2 from dual union all select 23,5 from dual 
)
select bid,bid+2 as eid,sum3 from gen
match_recognize(
order by id
measures 
   first (a.id) as bid,
   sum(val) as sum3
one row per match
after match skip to next row
pattern (A B*)
define
      B as b.id<=a.id+2
);

输出

memory D .read match-rec6.txt
┌───────┬───────┬────────┐
│  bid  │  eid  │  sum3  │
│ int32 │ int32 │ int128 │
├───────┼───────┼────────┤
│     1 │     3 │     10 │
│    10 │    12 │      5 │
│    15 │    17 │      7 │
│     5 │     7 │      3 │
│    14 │    16 │     10 │
│    12 │    14 │     10 │
│    20 │    22 │      5 │
│    16 │    18 │      5 │
│    23 │    25 │      5 │
│     2 │     4 │      7 │
│     3 │     5 │      8 │
│     9 │    11 │      8 │
│     8 │    10 │     10 │
│    13 │    15 │     10 │
│    21 │    23 │      7 │
└───────┴───────┴────────┘
  15 rows      3 columns
memory D