Last active
August 23, 2022 15:26
-
-
Save marcosgz/a6414a760b65a705e494aa6f8eb41315 to your computer and use it in GitHub Desktop.
Prune orphaned documents from esse index that uses the active_record plugin
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Remove orphaned items (documents without an equivalent database record) from elasticsearch/opensearch index | |
| index = AccountsIndex # Target index | |
| index.search(query: { match_all: {} }, _source: false).scroll_hits do |hits| | |
| print(".") | |
| es_ids = hits.map { |hit| hit.fetch("_id").to_i } | |
| db_ids = index.repo.dataset.except(:includes, :preload).where(id: es_ids).pluck(:id) | |
| prune_ids = es_ids - db_ids | |
| next if prune_ids.none? | |
| puts "Pruning #{prune_ids.size} #{index} from Elasticsearch" | |
| index.cluster.client.delete_by_query( | |
| index: index.index_name, | |
| body: { | |
| query: { | |
| ids: { | |
| values: prune_ids | |
| } | |
| } | |
| } | |
| ) | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment