Búsqueda de texto completo con tsvector y GIN

Más allá de las subcadenas: búsqueda orientada a palabras

Crear un tsvector

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

Crear un tsquery

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

Coincidencia: @@

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

Indexación para 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);

Consultas

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;

Clasificación 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;

Fragmentos 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);

Búsqueda de frases

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

Ponderación de varios campos

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;

Configuración del idioma

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

Limitaciones de la FTS integrada

Resumen

Comprobación rápida