Read the published research corpus and avoid expensive paging plans [skip ci]

2026-11-07 15:51:17 +08:00
parent 913bf4292b
commit 1363792bb0
10 changed files with 355 additions and 37 deletions
@@ -0,0 +1,14 @@
+-- Manual operator step against the published Paper Atlas schema, outside a
+-- transaction. Core's SELECT-only runtime role must never execute this file.
+-- These indexes support the actual author search and exact category filter;
+-- the migration already owns the title/abstract English GIN index.
+SET lock_timeout = '2s';
+SET statement_timeout = '20min';
+SET maintenance_work_mem = '32MB';
+SET max_parallel_maintenance_workers = 0;
+CREATE INDEX CONCURRENTLY IF NOT EXISTS paper_tags_tag_paper
+ ON research.paper_tags(tag_id,paper_id);
+CREATE INDEX CONCURRENTLY IF NOT EXISTS papers_authors_search_gin
+ ON research.papers USING gin(to_tsvector('simple'::regconfig,authors_json));
+-- After an interrupted concurrent build, inspect pg_index.indisvalid before
+-- reuse. IF NOT EXISTS alone does not repair an invalid index.