Smertefuldt langsom Postgres-forespørgsel ved hjælp af WHERE på mange tilstødende rækker

Trin 1:Brug en vinduesfunktion til at få tilstødende poster, undgå den smertefulde selv-join (12 tabeller er meget tæt på grænsen, hvor geqo overtager):

copy(
WITH stuff AS (
    SELECT   c1.id , c1.source, c1.word
    , LEAD ( c1.word, 1) OVER (www) AS c2w
    , LEAD (c1.word, 2) OVER (www) AS c3w
    , LEAD ( c1.word, 3) OVER (www) AS c4w
    , LEAD (c1.lemma, 3) OVER (www) AS c4l
    , LEAD (c1.pos, 3) OVER (www) AS c4p
    , LEAD (c1.pos, 4) OVER (www) AS c5p
    , LEAD (c1.word, 4) OVER (www) AS c5w
    , LEAD (c1.word, 5) OVER (www) AS c6w
    , LEAD (c1.lemma, 5) OVER (www) AS c6l
    , LEAD (c1.word, 6) OVER (www) AS c7w
    , LEAD (c1.pos, 6) OVER (www) AS c7p
    , LEAD (c1.word, 7) OVER (www) AS c8w
    , LEAD (c1.word, 8) OVER (www) AS c9w
    , LEAD (c1.lemma, 8) OVER (www) AS c9l
    , LEAD (c1.pos, 8) OVER (www) AS c9p
    , LEAD (c1.word, 9) OVER (www) AS c10w
    , LEAD (c1.word, 10) OVER (www) AS c11w
    FROM orderedflatcorpus AS c1
    WINDOW www AS (ORDER BY id)
    )
SELECT id ,  source, word
    , c2w
    , c3w
    , c4w
    , c4l
    , c4p
    , c5w
    , c6w
    , c7w
    , c8w
    , c9w
    , c9l
    , c9p
    , c10w
    , c11w
FROM stuff
WHERE 1=1
AND c4p LIKE 'v%'
AND c5p = 'appge'
AND c6l = 'way'
AND c7p LIKE 'i%'
AND c8w = 'the'
AND c9p LIKE 'n%'
ORDER BY id
)
-- TO '/home/postgres/Results/OUTPUT.csv' DELIMITER E'\t' csv header;
TO '/tmp/OUTPUT2.csv' DELIMITER E'\t' csv header;
 

Trin 2:[datamodel] {word,lemma, pos}-kolonnerne ser ud til at være en gruppe med lav kardinalitet, du kan presse dem ud i et separat token/lemma/pos-table:

    -- An index to speedup the unique extraction and final update
    -- (the index will be dropped automatically
    -- once the columns are dropped)
    CREATE INDEX ON tmp.orderedflatcorpus (word, lemma, pos );

    ANALYZE tmp.orderedflatcorpus;
    -- table containing the "squeezed out" domain
    CREATE TABLE tmp.words AS
     SELECT DISTINCT  word, lemma, pos
     FROM tmp.orderedflatcorpus
            ;
    ALTER TABLE tmp.words
     ADD COLUMN id SERIAL NOT NULL PRIMARY KEY;

    ALTER TABLE tmp.words
     ADD UNIQUE (word , lemma, pos );

    -- The original table needs an FK "link" to the new table
    ALTER TABLE tmp.orderedflatcorpus
      ADD column words_id INTEGER -- NOT NULL
      REFERENCES tmp.words(id)
      ;
    -- FK constraints are helped a lot by a supportive index.
    CREATE INDEX orderedflatcorpus_words_id_fk ON tmp.orderedflatcorpus (words_id)
     ;
    ANALYZE tmp.orderedflatcorpus;
    ANALYZE tmp.words;
    -- Initialize the FK column in the original table.
    --  we need NOT DISTINCT FROM here, since the joined
    --  columns could contain NULLs , which MUST compare equal.
    -- ------------------------------------------------------
    UPDATE tmp.orderedflatcorpus dst
       SET  words_id = src.id
      FROM tmp.words src
     WHERE src.word IS NOT DISTINCT FROM dst.word
       AND dst.lemma IS NOT DISTINCT FROM src.lemma
       AND dst.pos IS NOT DISTINCT FROM src.pos
            ;
    ALTER TABLE tmp.orderedflatcorpus
     DROP column word
     , DROP column lemma
     , DROP column pos
            ;
 

Og den nye forespørgsel med et JOIN til ord-tabellen:

copy(
WITH stuff AS (
    SELECT   c1.id , c1.source, w.word
    , LEAD ( w.word, 1) OVER (www) AS c2w
    , LEAD (w.word, 2) OVER (www) AS c3w
    , LEAD ( w.word, 3) OVER (www) AS c4w
    , LEAD (w.lemma, 3) OVER (www) AS c4l
    , LEAD (w.pos, 3) OVER (www) AS c4p
    , LEAD (w.pos, 4) OVER (www) AS c5p
    , LEAD (w.word, 4) OVER (www) AS c5w
    , LEAD (w.word, 5) OVER (www) AS c6w
    , LEAD (w.lemma, 5) OVER (www) AS c6l
    , LEAD (w.word, 6) OVER (www) AS c7w
    , LEAD (w.pos, 6) OVER (www) AS c7p
    , LEAD (w.word, 7) OVER (www) AS c8w
    , LEAD (w.word, 8) OVER (www) AS c9w
    , LEAD (w.lemma, 8) OVER (www) AS c9l
    , LEAD (w.pos, 8) OVER (www) AS c9p
    , LEAD (w.word, 9) OVER (www) AS c10w
    , LEAD (w.word, 10) OVER (www) AS c11w
    FROM orderedflatcorpus AS c1
    JOIN words w ON w.id=c1.words_id
    WINDOW www AS (ORDER BY c1.id)
    )
SELECT id ,  source, word
    , c2w , c3w
    , c4w , c4l , c4p
    , c5w
    , c6w
    , c7w
    , c8w
    , c9w , c9l , c9p
    , c10w
    , c11w
FROM stuff
WHERE 1=1
AND c4p LIKE 'v%'
AND c5p = 'appge'
AND c6l = 'way'
AND c7p LIKE 'i%'
AND c8w = 'the'
AND c9p LIKE 'n%'
ORDER BY id
)
-- TO '/home/postgres/Results/OUTPUT.csv' DELIMITER E'\t' csv header;
TO '/tmp/OUTPUT3.csv' DELIMITER E'\t' csv header;
 

Bemærk:Jeg får to linjer i outputtet, fordi jeg lempede betingelserne lidt for meget ...

Opdater :den første forespørgsel, undgå CTE