From d5d83762063b8ec7f512c20567f46c03f2e6b542 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 29 Jan 2020 21:57:32 -0800 Subject: update ES docs and proposal --- extra/elasticsearch/README.md | 2 ++ proposals/2020_elasticsearch_schemas.md | 8 ++++---- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/extra/elasticsearch/README.md b/extra/elasticsearch/README.md index 3a48a178..3e0857b4 100644 --- a/extra/elasticsearch/README.md +++ b/extra/elasticsearch/README.md @@ -40,9 +40,11 @@ Drop and rebuild the schema: http delete :9200/fatcat_release http delete :9200/fatcat_container + http delete :9200/fatcat_file http delete :9200/fatcat_changelog http put :9200/fatcat_release < release_schema.json http put :9200/fatcat_container < container_schema.json + http put :9200/fatcat_file < file_schema.json http put :9200/fatcat_changelog < changelog_schema.json Put a single object (good for debugging): diff --git a/proposals/2020_elasticsearch_schemas.md b/proposals/2020_elasticsearch_schemas.md index 83db884f..5fb28d19 100644 --- a/proposals/2020_elasticsearch_schemas.md +++ b/proposals/2020_elasticsearch_schemas.md @@ -14,8 +14,6 @@ Simple additions: - pages - `first_page` (parsed from pages) (?) - number -- `in_shadow` -- OA license slug (?) - `doi_prefix` - `doi_registrar` (based on extra) - `first_author` (surname; for matching) @@ -25,6 +23,8 @@ Simple additions: - referenced releases idents - contrib creator idents +Add affiliations, both as raw strings and ROR identifiers. + ## Preservation Summary Field @@ -128,8 +128,8 @@ hit does not}"). ## Container Fields -- `all_issns` -- `release_count` +- `issn` (all issns) +- `original_name` The `release_count` would not be indexed (left null) by default, and would be "patched" in to entities by a separate script (periodically?). -- cgit v1.2.3