summaryrefslogtreecommitdiffstats
path: root/extra/checks/check_hashes.sh
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2019-06-04 17:38:01 -0700
committerBryan Newbold <bnewbold@robocracy.org>2019-06-04 17:38:01 -0700
commit84c38d29fc4c7d0dd2e61a5ee9d57ee0a87a61e3 (patch)
treeb2ce9e75ed06d38216aae039ec12c76e8aaea838 /extra/checks/check_hashes.sh
parent4fdb056debb07beb36d9bfd0dd358cd398a61a6e (diff)
downloadfatcat-84c38d29fc4c7d0dd2e61a5ee9d57ee0a87a61e3.tar.gz
fatcat-84c38d29fc4c7d0dd2e61a5ee9d57ee0a87a61e3.zip
QA checks (for hash, extid duplication)
Diffstat (limited to 'extra/checks/check_hashes.sh')
-rwxr-xr-xextra/checks/check_hashes.sh16
1 files changed, 16 insertions, 0 deletions
diff --git a/extra/checks/check_hashes.sh b/extra/checks/check_hashes.sh
new file mode 100755
index 00000000..94102329
--- /dev/null
+++ b/extra/checks/check_hashes.sh
@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+set -e -u -o pipefail
+
+export LC_ALL=C
+
+HASH_FILE=$1
+
+zcat $HASH_FILE \
+ | awk '{print $3 "\t" $1}' \
+ | rg -v '^\t' \
+ | sort -S 4G \
+ | uniq -d -w 40 \
+ > sha1_ident.dupes.tsv
+
+wc -l sha1_ident.dupes.tsv >> counts.txt