bump logback to 1.3.16

.github/resources/github_workflow.properties

@@ -0,0 +1,35 @@
+# The script that abides by the multi-language protocol. This script will
+# be executed by the MultiLangDaemon, which will communicate with this script
+# over STDIN and STDOUT according to the multi-language protocol.
+executableName = sample_kclpy_app.py
+
+# The name of an Amazon Kinesis stream to process.
+# Important: streamArn takes precedence over streamName if both are set
+streamName = STREAM_NAME_PLACEHOLDER
+
+# Used by the KCL as the name of this application. Will be used as the name
+# of an Amazon DynamoDB table which will store the lease and checkpoint
+# information for workers with this application name
+applicationName = APP_NAME_PLACEHOLDER
+
+# Users can change the credentials provider the KCL will use to retrieve credentials.
+# Expected key name (case-sensitive):
+# AwsCredentialsProvider / AwsCredentialsProviderDynamoDB / AwsCredentialsProviderCloudWatch
+# The DefaultCredentialsProvider checks several other providers, which is
+# described here:
+# https://sdk.amazonaws.com/java/api/latest/software/amazon/awssdk/auth/credentials/DefaultCredentialsProvider.html
+AwsCredentialsProvider = DefaultCredentialsProvider
+
+# Appended to the user agent of the KCL. Does not impact the functionality of the
+# KCL in any other way.
+processingLanguage = python/3.8
+
+# Valid options at TRIM_HORIZON or LATEST.
+# See http://docs.aws.amazon.com/kinesis/latest/APIReference/API_GetShardIterator.html#API_GetShardIterator_RequestSyntax
+initialPositionInStream = TRIM_HORIZON
+
+# The KCL defaults to us-east-1
+regionName = us-east-1
+
+# Idle time between record reads in milliseconds.
+idleTimeBetweenReadsInMillis = 250

.github/scripts/clean_up_stream_table.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+# Delete stream
+if aws kinesis describe-stream --stream-name $STREAM_NAME &>/dev/null; then
+  echo "Deleting stream $STREAM_NAME"
+  for i in {1..10}; do
+    aws kinesis delete-stream --stream-name $STREAM_NAME && break ||
+    echo "Stream deletion failed, attempt $i/10. Retrying Stream deletion in $((i * 3))s" && sleep $((i * 3))
+  done
+else
+  echo "Stream $STREAM_NAME does not exist and does not need to be cleaned up"
+fi
+
+# Delete table
+delete_table() {
+  table_name=$1
+  if aws dynamodb describe-table --table-name $table_name &>/dev/null; then
+    echo "Deleting table $table_name"
+    for i in {1..10}; do
+      aws dynamodb delete-table --table-name $table_name && break ||
+      echo "Table deletion failed, attempt $i/10. Retrying DynamoDB Table deletion in $((i * 3))s" && sleep $((i * 3))
+    done
+  else
+    echo "Table $table_name does not exist and does not need to be cleaned up"
+  fi
+}
+
+# Delete all tables
+for SUFFIX in "" "-CoordinatorState" "-WorkerMetricStats"; do
+  delete_table "$APP_NAME$SUFFIX"
+done

.github/scripts/create_stream.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+set -e
+
+for i in {1..10}; do
+  if aws kinesis create-stream --stream-name $STREAM_NAME --shard-count 1; then
+    break
+  else
+    echo "Stream creation failed, attempt $i/10. Waiting $((i * 3)) seconds..."
+    sleep $((i * 3))
+  fi
+done
+aws kinesis wait stream-exists --stream-name $STREAM_NAME

.github/scripts/manipulate_properties.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+set -e
+
+# Manipulate github_workflow.properties file that the KCL application pulls properties from (ex: streamName, applicationName)
+# Depending on the OS, different properties need to be changed
+if [[ "$RUNNER_OS" == "macOS" ]]; then
+  sed -i "" "s/STREAM_NAME_PLACEHOLDER/$STREAM_NAME/g" .github/resources/github_workflow.properties
+  sed -i "" "s/APP_NAME_PLACEHOLDER/$APP_NAME/g" .github/resources/github_workflow.properties
+elif [[ "$RUNNER_OS" == "Linux" || "$RUNNER_OS" == "Windows" ]]; then
+  sed -i "s/STREAM_NAME_PLACEHOLDER/$STREAM_NAME/g" .github/resources/github_workflow.properties
+  sed -i "s/APP_NAME_PLACEHOLDER/$APP_NAME/g" .github/resources/github_workflow.properties
+
+  if [[ "$RUNNER_OS" == "Windows" ]]; then
+    echo '@echo off' > samples/run_script.bat
+    echo 'python %~dp0\sample_kclpy_app.py %*' >> samples/run_script.bat
+    sed -i 's/executableName = sample_kclpy_app.py/executableName = samples\/run_script.bat/' .github/resources/github_workflow.properties
+  fi
+else
+  echo "Unknown OS: $RUNNER_OS"
+  exit 1
+fi
+
+cat .github/resources/github_workflow.properties

.github/scripts/put_words_to_stream.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+set -e
+
+sample_kinesis_wordputter.py --stream $STREAM_NAME -w cat -w dog -w bird -w lobster -w octopus
+
+# Get records from stream to verify they exist before continuing
+SHARD_ITERATOR=$(aws kinesis get-shard-iterator --stream-name $STREAM_NAME --shard-id shardId-000000000000 --shard-iterator-type TRIM_HORIZON --query 'ShardIterator' --output text)
+INITIAL_RECORDS=$(aws kinesis get-records --shard-iterator $SHARD_ITERATOR)
+RECORD_COUNT_BEFORE=$(echo $INITIAL_RECORDS | jq '.Records | length')
+
+if [ "$RECORD_COUNT_BEFORE" -eq 0 ]; then
+  echo "No records found in stream. Test cannot proceed."
+  exit 1
+fi
+echo "Found $RECORD_COUNT_BEFORE records in stream before KCL start"

.github/scripts/start_kcl.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+set -o pipefail
+
+chmod +x .github/resources/github_workflow.properties
+chmod +x samples/sample_kclpy_app.py
+
+if [[ "$RUNNER_OS" == "macOS" ]]; then
+  brew install coreutils
+  KCL_COMMAND=$(amazon_kclpy_helper.py --print_command --java $(which java) --properties .github/resources/github_workflow.properties)
+  gtimeout $RUN_TIME_SECONDS $KCL_COMMAND 2>&1 | tee kcl_output.log  || [ $? -eq 124 ]
+elif [[ "$RUNNER_OS" == "Linux" || "$RUNNER_OS" == "Windows" ]]; then
+  KCL_COMMAND=$(amazon_kclpy_helper.py --print_command --java $(which java) --properties .github/resources/github_workflow.properties)
+  timeout $RUN_TIME_SECONDS $KCL_COMMAND 2>&1 | tee kcl_output.log || [ $? -eq 124 ]
+else
+  echo "Unknown OS: $RUNNER_OS"
+  exit 1
+fi
+
+echo "==========ERROR LOGS=========="
+grep -i error kcl_output.log || echo "No errors found in logs"

.github/scripts/verify_kcl.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+set -e
+
+NUM_LEASES_FOUND=$(aws dynamodb scan --table-name $APP_NAME --select "COUNT" --query "Count" --output text || echo "0")
+NUM_CHECKPOINTS_FOUND=$(aws dynamodb scan --table-name $APP_NAME --select "COUNT" --filter-expression "attribute_exists(checkpoint) AND checkpoint <> :trim_horizon" --expression-attribute-values '{":trim_horizon": {"S": "TRIM_HORIZON"}}' --query "Count" --output text || echo "0")
+
+echo "Found $NUM_LEASES_FOUND leases and $NUM_CHECKPOINTS_FOUND non-TRIM-HORIZON checkpoint in DynamoDB"
+
+echo "Printing checkpoint values"
+aws dynamodb scan --table-name $APP_NAME --projection-expression "leaseKey,checkpoint" --output json
+
+if [ "$NUM_LEASES_FOUND" -gt 0 ] && [ "$NUM_CHECKPOINTS_FOUND" -gt 0 ]; then
+  echo "Test passed: Found both leases and non-TRIM_HORIZON checkpoints in DDB (KCL is fully functional)"
+  exit 0
+else
+  echo "Test failed: KCL not fully functional"
+  echo "Lease(s) found: $NUM_LEASES_FOUND"
+  echo "non-TRIM_HORIZON checkpoint(s) found: $NUM_CHECKPOINTS_FOUND"
+  exit 1
+fi