PostgreSQL Antipatterns: ¿qué tan profundo es el agujero del conejo? pasar por la jerarquía

CREATE TABLE hier(
  id
    integer
      PRIMARY KEY
, pid
    integer
      REFERENCES hier
, data
    json
);

CREATE INDEX ON hier(pid); --  ,  FK    ,    PK

# 1 ¿Qué tan profundo es la madriguera del conejo?

INSERT INTO hier
WITH RECURSIVE T AS (
  SELECT
    1::integer id
  , '{1}'::integer[] pids
UNION ALL
  SELECT
    id + 1
  , pids[1:(random() * array_length(pids, 1))::integer] || (id + 1)
  FROM
    T
  WHERE
    id < 10000
)
SELECT
  pids[array_length(pids, 1)] id
, pids[array_length(pids, 1) - 1] pid
FROM
  T;

WITH RECURSIVE T AS (
  SELECT
    id
  , pid
  , ARRAY[id] path
  FROM
    hier
  WHERE
    pid IS NULL
UNION ALL
  SELECT
    hier.id
  , hier.pid
  , T.path || hier.id
  FROM
    T
  JOIN
    hier
      ON hier.pid = T.id
)
TABLE T ORDER BY array_length(path, 1) DESC;

 id  | pid  | path
---------------------------------------------
7624 | 7623 | {7615,7620,7621,7622,7623,7624}
4995 | 4994 | {4983,4985,4988,4993,4994,4995}
4991 | 4990 | {4983,4985,4988,4989,4990,4991}
...

...
SELECT
  path[1] id
, count(*)
FROM
  T
GROUP BY
  1
ORDER BY
  2 DESC;

id   | count
------------
5300 |   30
 450 |   28
1239 |   27
1573 |   25

WITH RECURSIVE T AS (
  SELECT
    id
  FROM
    hier
  WHERE
    id = 5300
UNION ALL
  SELECT
    hier.id
  FROM
    T
  JOIN
    hier
      ON hier.pid = T.id
)
TABLE T;

Revisión masiva por índice

WITH RECURSIVE T AS (
  SELECT
    ARRAY[id] id$
  FROM
    hier
  WHERE
    id = 5300
UNION ALL
  SELECT
    ARRAY(
      SELECT
        id
      FROM
        hier
      WHERE
        pid = ANY(T.id$)
    ) id$
  FROM
    T
  WHERE
    coalesce(id$, '{}') <> '{}' --     -  
)
SELECT
  unnest(id$) id
FROM
  T;

Etiqueta de nodo

ALTER TABLE hier
  ADD COLUMN branch boolean;

UPDATE
  hier T
SET
  branch = TRUE
WHERE
  EXISTS(
    SELECT
      NULL
    FROM
      hier
    WHERE
      pid = T.id
    LIMIT 1
);
--   : 3033    42 .

WITH RECURSIVE T AS (
  SELECT
    array_agg(id) id$
  , array_agg(id) FILTER(WHERE branch) ns$
  FROM
    hier
  WHERE
    id = 5300
UNION ALL
  SELECT
    X.*
  FROM
    T
  JOIN LATERAL (
    SELECT
      array_agg(id) id$
    , array_agg(id) FILTER(WHERE branch) ns$
    FROM
      hier
    WHERE
      pid = ANY(T.ns$)
  ) X
    ON coalesce(T.ns$, '{}') <> '{}'
)
SELECT
  unnest(id$) id
FROM
  T;

# 2 De vuelta a las raíces

• Es mejor leer el mismo registro de la base de datos solo una vez .
• Las entradas de la base de datos se leen más eficientemente en un "paquete" que individualmente.

Paso 1

WITH RECURSIVE tree AS (
  SELECT
    rec --    
  , id::text chld --  ""    
  FROM
    hier rec
  WHERE
    id = ANY('{1,2,4,8,16,32,64,128,256,512,1024,2048,4096,8192}'::integer[])
UNION ALL
  ...

Paso 2

1. La parte "sub-recursiva" de una consulta no puede contener funciones agregadas c GROUP BY.
2. Una llamada a una "tabla" recursiva no puede estar en una subconsulta anidada.
3. Una consulta en la parte recursiva no puede contener un CTE.

CTE en la parte recursiva

WITH RECURSIVE tree AS (
  ...
UNION ALL
  WITH T (...)
  SELECT ...
)

WITH RECURSIVE tree AS (
  ...
UNION ALL
  (
    WITH T (...)
    SELECT ...
  )
)

Consulta anidada para "tabla" recursiva

GROUP BY dentro de recursión

SELECT
  (rec).pid id
, string_agg(chld::text, ',') chld
FROM
  tree
WHERE
  (rec).pid IS NOT NULL
GROUP BY 1 --  !

SELECT DISTINCT ON((rec).pid)
  (rec).pid id
, string_agg(chld::text, ',') OVER(PARTITION BY (rec).pid) chld
FROM
  tree
WHERE
  (rec).pid IS NOT NULL

Paso 3

• leemos registros de "secciones" en un conjunto de ID agrupadas
• unir las secciones restadas con los "conjuntos" de hojas de origen
• "Expanda" la cadena establecida usando unnest(string_to_array(chld, ',')::integer[])

WITH RECURSIVE tree AS (
  SELECT
    rec
  , id::text chld
  FROM
    hier rec
  WHERE
    id = ANY('{1,2,4,8,16,32,64,128,256,512,1024,2048,4096,8192}'::integer[])
UNION ALL
  (
    WITH prnt AS (
      SELECT DISTINCT ON((rec).pid)
        (rec).pid id
      , string_agg(chld::text, ',') OVER(PARTITION BY (rec).pid) chld
      FROM
        tree
      WHERE
        (rec).pid IS NOT NULL
    )
    , nodes AS (
      SELECT
        rec
      FROM
        hier rec
      WHERE
        id = ANY(ARRAY(
          SELECT
            id
          FROM
            prnt
        ))
    )
    SELECT
      nodes.rec
    , prnt.chld
    FROM
      prnt
    JOIN
      nodes
        ON (nodes.rec).id = prnt.id
  )
)
SELECT
  unnest(string_to_array(chld, ',')::integer[]) leaf
, (rec).*
FROM
  tree;