Ricerca full-text con tsvector e GIN

Oltre le sottostringhe: ricerca basata sulle parole

Creare un tsvector

SELECT to_tsvector('english', 'The quick brown foxes jumped over');
-- 'brown':3 'fox':4 'jump':5 'quick':2

Creare una tsquery

SELECT to_tsquery('english', 'fox & jumping');     -- 'fox' & 'jump'
SELECT websearch_to_tsquery('english', 'fox jumping -lazy');

Corrispondenza: @@

SELECT 'fox jumping'::tsvector @@ 'fox & jump'::tsquery;     -- t

Indicizzazione per FTS

ALTER TABLE articles
  ADD COLUMN search_doc tsvector
    GENERATED ALWAYS AS (
      to_tsvector('english', coalesce(title,'') || ' ' || coalesce(body,''))
    ) STORED;

CREATE INDEX articles_search_idx ON articles USING GIN (search_doc);

Interrogazione

SELECT id, title FROM articles
WHERE search_doc @@ websearch_to_tsquery('english', 'postgres performance')
ORDER BY ts_rank(search_doc, websearch_to_tsquery('english', 'postgres performance')) DESC
LIMIT 20;

Ranking con ts_rank

SELECT id, ts_rank_cd(search_doc, q) AS rank
FROM articles, websearch_to_tsquery('english', $1) AS q
WHERE search_doc @@ q
ORDER BY rank DESC LIMIT 20;

Estratti con ts_headline

SELECT ts_headline('english', body,
  websearch_to_tsquery('english', $1),
  'StartSel=<mark>, StopSel=</mark>, MaxFragments=2')
FROM articles
WHERE search_doc @@ websearch_to_tsquery('english', $1);

Ricerca di frasi

SELECT * FROM articles
WHERE search_doc @@ phraseto_tsquery('english', 'database performance');

Ponderazioni per più campi

ALTER TABLE articles
  ADD COLUMN search_doc tsvector
    GENERATED ALWAYS AS (
      setweight(to_tsvector('english', coalesce(title,'')), 'A') ||
      setweight(to_tsvector('english', coalesce(body,'')),  'B')
    ) STORED;

Configurazione della lingua

SELECT to_tsvector('turkish', 'Veritabanı performansı');

Limiti dell'FTS integrato

Riepilogo

Verifica rapida