From 1e19371d6f47dc89744271c4791f3888a246dc4a Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Fri, 12 Apr 2019 13:51:10 -0700
Subject: schema notes on deeper file metadata

---
 hbase/schema_design.md | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'hbase')

diff --git a/hbase/schema_design.md b/hbase/schema_design.md
index 67a940f..2db8998 100644
--- a/hbase/schema_design.md
+++ b/hbase/schema_design.md
@@ -40,6 +40,14 @@ Column families:
         - `warc` (item and file name)
         - `offset`
         - `c_size` (compressed size)
+    - `meta` (json string)
+        - `size` (int)
+        - `mime` (str)
+        - `magic` (str)
+        - `magic_mime` (str)
+        - `sha1` (hex str)
+        - `md5` (hex str)
+        - `sha256` (hex str)
 - `grobid0`: processing status, version, XML and JSON fulltext, JSON metadata. timestamp. Should be compressed! `COMPRESSION => SNAPPY`
     - `status_code` (signed int; HTTP status from grobid)
     - `quality` (int or string; we define the meaning ("good"/"marginal"/"bad")
-- 
cgit v1.2.3