aboutsummaryrefslogtreecommitdiffstats
path: root/sql/reingest_bulk.sh
diff options
context:
space:
mode:
Diffstat (limited to 'sql/reingest_bulk.sh')
-rwxr-xr-xsql/reingest_bulk.sh19
1 files changed, 19 insertions, 0 deletions
diff --git a/sql/reingest_bulk.sh b/sql/reingest_bulk.sh
new file mode 100755
index 0000000..d39a171
--- /dev/null
+++ b/sql/reingest_bulk.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+set -e # fail on error
+set -u # fail if variable not set in substitution
+set -o pipefail # fail if part of a '|' command fails
+
+sudo -u postgres psql sandcrawler < dump_reingest_bulk.sql
+
+cd ../python
+sudo -u sandcrawler pipenv run \
+ ./scripts/ingestrequest_row2json.py /srv/sandcrawler/tasks/reingest_bulk_current.rows.json \
+ > /srv/sandcrawler/tasks/reingest_bulk_current.json
+
+cat /srv/sandcrawler/tasks/reingest_bulk_current.json \
+ | shuf \
+ | head -n1000000 \
+ | jq . -c \
+ | kafkacat -P -b wbgrp-svc350.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1
+