From 91f5f53c90742c80890e3bd44fdc9044555b8209 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 11 Dec 2019 18:20:13 -0800
Subject: add some GROBID metadata schema docs to SQL schema

---
 sql/sandcrawler_schema.sql | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'sql')

diff --git a/sql/sandcrawler_schema.sql b/sql/sandcrawler_schema.sql
index fd921ed..b6bc201 100644
--- a/sql/sandcrawler_schema.sql
+++ b/sql/sandcrawler_schema.sql
@@ -43,6 +43,17 @@ CREATE TABLE IF NOT EXISTS grobid (
     status_code         INT NOT NULL,
     status              TEXT CHECK (octet_length(status) >= 1),
     fatcat_release      TEXT CHECK (octet_length(fatcat_release) = 26),
+    -- extracted basic biblio metadata:
+    --  title
+    --  authors[]
+    --    full/display
+    --    given_name
+    --    surname
+    --    affiliation
+    --  year
+    --  journal_issn
+    --  journal_name
+    --  refs_count
     metadata            JSONB
 );
 -- CREATE INDEX grobid_fatcat_release_idx ON grobid(fatcat_release);
-- 
cgit v1.2.3