From 1b472c037faaa5a1e0b0a7da340ed5f9b003429f Mon Sep 17 00:00:00 2001
From: "W. Trevor King" <wking@tremily.us>
Date: Tue, 29 Jun 2021 18:51:25 -0700
Subject: [PATCH] ci-operator/step-registry/gather/aws-console: Use LC_ALL
 instead of PYTHONIOENCODING

24b834c01d (ci-operator/step-registry/gather/aws-console: UTF-8 for
output, 2021-06-29, #19827) is not doing well in the wild.  For
example, [1]:

  INFO[2021-06-29T20:14:28Z] Gathering console logs for i-008f73fde1ef3f0dc

  'ascii' codec can't encode character '\u2026' in position 13999: ordinal not in range(128)
  {"component":"entrypoint","error":"wrapped process failed: exit status 1","file":"prow/entrypoint/run.go:80","func":"k8s.io/test-infra/prow/entrypoint.Options.Run","level":"error","msg":"Error executing test process","severity":"error","time":"2021-06-29T20:14:27Z"}
  error: failed to execute wrapped command: exit status 1

Apparently the AWS CLI is not using Python's default stream encoding
here.  But from [2,3,4] there is the suggestion that
LC_ALL=en_US.UTF-8 will help.

[1]: https://prow.ci.openshift.org/view/gs/origin-ci-test/logs/periodic-ci-openshift-release-master-ci-4.9-e2e-aws/1409949910362492928
[2]: https://awscli.amazonaws.com/v2/documentation/api/latest/topic/config-vars.html#locale
[3]: https://github.com/aws/aws-cli/blob/2.2.5/awscli/compat.py#L121-L146
[4]: https://docs.python.org/3/library/locale.html#locale.getpreferredencoding
---
 .../gather/aws-console/gather-aws-console-commands.sh           | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ci-operator/step-registry/gather/aws-console/gather-aws-console-commands.sh b/ci-operator/step-registry/gather/aws-console/gather-aws-console-commands.sh
index 1cd70da0d1ed..c9bdf67b066a 100755
--- a/ci-operator/step-registry/gather/aws-console/gather-aws-console-commands.sh
+++ b/ci-operator/step-registry/gather/aws-console/gather-aws-console-commands.sh
@@ -37,6 +37,6 @@ REGION="$(jq -r .aws.region "${SHARED_DIR}/metadata.json")"
 cat "${TMPDIR}/node-provider-IDs.txt" | sort | grep . | uniq | while read -r INSTANCE_ID
 do
 	echo "Gathering console logs for ${INSTANCE_ID}"
-	PYTHONIOENCODING=UTF-8:backslashreplace aws --region "${REGION}" ec2 get-console-output --instance-id "${INSTANCE_ID}" --output text > "${ARTIFACT_DIR}/${INSTANCE_ID}" &
+	LC_ALL=en_US.UTF-8 aws --region "${REGION}" ec2 get-console-output --instance-id "${INSTANCE_ID}" --output text > "${ARTIFACT_DIR}/${INSTANCE_ID}" &
 	wait "$!"
 done