Skip to content
Open
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
332 changes: 332 additions & 0 deletions .github/workflows/container_integration_tests.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,332 @@
name: Container Integration Tests Workflow

on:
workflow_dispatch:
inputs:
force_run:
description: 'Force run even if ENABLE_DOCKER_TESTS is false'
required: false
type: boolean
default: false
Comment thread
srmanda-cs marked this conversation as resolved.
Outdated
push:
branches:
- develop
paths-ignore:
- "doc/**"
- "**/*.md"
- "**/*.txt"
- ".github/ISSUE_TEMPLATE/**"
- ".github/*.md"
Comment on lines +6 to +13
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we need "push" at all? We have branch protection turned on for both "develop" and "master".

pull_request:
branches:
- develop
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we add "master" here? That way the tests will run when we release, I would think, after this step: https://guides.dataverse.org/en/6.10.1/developers/making-releases.html#merge-develop-into-master-non-hotfix-only

Here's an example of where we merged develop into master:

paths-ignore:
- "doc/**"
- "**/*.md"
- "**/*.txt"
- ".github/ISSUE_TEMPLATE/**"
- ".github/*.md"
Comment thread
srmanda-cs marked this conversation as resolved.

concurrency:
group: "container-integration-tests-group"
Comment thread
srmanda-cs marked this conversation as resolved.
Outdated
cancel-in-progress: true

jobs:
main-integration-tests-workflow:
runs-on: ubuntu-latest
timeout-minutes: 120

defaults:
run:
shell: bash

permissions:
Comment thread
srmanda-cs marked this conversation as resolved.
checks: write
pull-requests: write

steps:

# ---------------------------
# CHECKOUT
# ---------------------------
- name: Checkout repository
uses: actions/checkout@v6

# ---------------------------
# VERIFY DOCKER
# ---------------------------
- name: Verify Docker
run: |
set -euo pipefail
docker version

# ---------------------------
# SETUP JAVA + MAVEN
# ---------------------------
- name: Setup Java
uses: actions/setup-java@v5
with:
distribution: "temurin"
java-version: "21"
cache: "maven"

- name: Verify Maven
run: |
set -euo pipefail
mvn -version

# ---------------------------
# CLEAN PREVIOUS VOLUMES
# ---------------------------
- name: Clean docker-dev-volumes
run: |
set -euo pipefail
rm -rf docker-dev-volumes || true

# ---------------------------
# BUILD IMAGES (Dataverse-native)
# ---------------------------
- name: Build Dataverse containers via Maven
run: |
set -euo pipefail
# Force unit tests to run, generate coverage, and ignore failures so the build continues
mvn clean package -Pct -P all-unit-tests \
-DskipUnitTests=false \
-Djacoco.skip=false \
-Dmaven.test.failure.ignore=true

# ---------------------------
# START CONTAINERS (BACKGROUND)
# ---------------------------
- name: Start Dataverse stack
run: |
set -euo pipefail
mvn -Pct docker:start \
-Ddataverse.cors.origin=* \
-Ddataverse.cors.methods=GET,POST,PUT,DELETE,OPTIONS \
-Ddataverse.cors.headers.allow=range,content-type,x-dataverse-key,accept \
-Ddataverse.cors.headers.expose=content-encoding,content-range,accept-ranges \
-Ddataverse.feature.index-harvested-metadata-source=true \
-Ddataverse.oai.server.maxidentifiers=2 \
-Ddataverse.oai.server.maxrecords=2 \

# ---------------------------
# WAIT FOR API READINESS
# ---------------------------
- name: Wait for Dataverse API readiness
run: |
set -euo pipefail
URL="http://localhost:8080/api/info/version"
MAX_ATTEMPTS=10
SLEEP_TIME=15
echo "Waiting for Dataverse readiness..."
for attempt in $(seq 1 $MAX_ATTEMPTS); do
echo "Attempt $attempt..."
RESPONSE=$(curl -s --max-time 15 "$URL" || true)
STATUS=$(echo "$RESPONSE" | jq -r '.status' 2>/dev/null || echo "NOT_READY")
if [ "$STATUS" = "OK" ]; then
echo "Dataverse endpoint is READY."
echo "Dataverse waiting for full readiness. Waiting 30 more seconds."
sleep 30
echo "Response: $RESPONSE"
exit 0
fi
echo "Not ready. Sleeping ${SLEEP_TIME}s..."
sleep $SLEEP_TIME
if [ $SLEEP_TIME -lt 60 ]; then
SLEEP_TIME=$((SLEEP_TIME * 2))
if [ $SLEEP_TIME -gt 60 ]; then
SLEEP_TIME=60
fi
fi
done
echo "Dataverse failed to become ready."
docker ps
CONTAINERS="$(docker ps -aq)"
if [ -n "$CONTAINERS" ]; then
for cid in $CONTAINERS; do
echo "===== Logs for container $cid ====="
docker logs "$cid" || true
done
else
echo "No running containers to show logs for."
fi
exit 1

# ---------------------------
# MAP LOCALSTACK TO LOCALHOST
# ---------------------------
- name: Map localstack to localhost for Maven tests
run: echo "127.0.0.1 localstack" | sudo tee -a /etc/hosts

# ---------------------------
# CONFIGURE DATAVERSE FOR TESTS
# ---------------------------
- name: Configure Dataverse API Settings
run: |
set -euo pipefail

echo "Setting API Database Settings via internal container curl..."

# We define the settings in an array
declare -A settings=(
[":BuiltinUsersKey"]="burrito"
[":ProvCollectionEnabled"]="true"
[":AllowApiTokenLookupViaApi"]="true"
[":AllowSignUp"]="true"
)
# We run curl INSIDE the container so the source IP is 127.0.0.1
for key in "${!settings[@]}"; do
echo "Setting $key..."
docker exec dev_dataverse curl -s -X PUT -d "${settings[$key]}" "http://localhost:8080/api/admin/settings/$key"
Comment thread
srmanda-cs marked this conversation as resolved.
Outdated
echo ""
done

# ---------------------------
# PRE-TEST INJECTIONS (FROM YOUR ALTERNATE WORKFLOWS)
# ---------------------------
- name: Put SUSHI config file in place
run: |
set -euo pipefail
# Fixes MakeDataCountApiIT
docker exec dev_dataverse sh -c 'curl https://raw.githubusercontent.com/IQSS/dataverse/develop/src/test/java/edu/harvard/iq/dataverse/makedatacount/sushi_sample_logs.json > /tmp/sushi_sample_logs.json && head /tmp/sushi_sample_logs.json'
Comment thread
srmanda-cs marked this conversation as resolved.
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess this will work but would it make more sense to copy the sushi_sample_logs.json file locally rather than downloading it from GitHub?


# ---------------------------
# RUN MAVEN TESTS
# ---------------------------
- name: Run Maven Integration Tests
env:
DVAPIKEY: "burrito"
DV_APIKEY: "burrito"
DV_API_KEY: "burrito"
Comment on lines +193 to +195
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we need all three of these? 🌯 🌯 🌯

run: |
set -euo pipefail
TEST_SUITE=$(cat tests/integration-tests.txt)

echo "Running suite: $TEST_SUITE"

# -Dmaven.test.failure.ignore=true forces the JVM to shut down cleanly
# and write the jacoco.exec file, even when tests fail.
mvn test \
-Dtest="$TEST_SUITE" \
-Dmaven.test.failure.ignore=true \
-Ddataverse.test.baseurl=http://localhost:8080 \
-DcompilerArgument=-Xlint:unchecked

# ---------------------------
# GENERATE REPORTS & DEPOSIT TO COVERALLS
# ---------------------------
- name: Deposit to Coveralls
if: always()
env:
COVERALLS_REPO_TOKEN: ${{ secrets.COVERALLS_REPO_TOKEN }}
continue-on-error: true
run: |
set -euo pipefail

# The pom.xml automatically merged the files and put them here:
mvn coveralls:report \
-P all-unit-tests \
-DrepoToken=$COVERALLS_REPO_TOKEN \
-DjacocoReports=target/site/jacoco-merged-test-coverage-report/jacoco.xml
Comment on lines +221 to +225
Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is probably wrong, but let me verify just in case.

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is right, JaCoCo reporting is failing

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this related to why I don't see this branch over at https://coveralls.io/github/IQSS/dataverse ? Check this out:

Image


# ---------------------------
# UPLOAD SUREFIRE/FAILSAFE REPORTS
# ---------------------------
- name: Upload Test Failure Reports
if: always()
uses: actions/upload-artifact@v4
with:
name: maven-test-reports
path: |
target/surefire-reports/
target/failsafe-reports/
target/site/jacoco/
retention-days: 14

# ---------------------------
# 2. PUBLISH TEST DASHBOARD IN GITHUB PR (Optional but highly recommended)
# ---------------------------
- name: Publish Test Results Dashboard
uses: EnricoMi/publish-unit-test-result-action@v2
if: always()
with:
files: |
target/failsafe-reports/TEST-*.xml
target/surefire-reports/TEST-*.xml

# ---------------------------
# FAIL WORKFLOW IF TESTS FAILED
# ---------------------------
- name: Check for Test Failures
if: always()
run: |
echo "Checking Surefire/Failsafe reports for failures..."
if grep -q "<failure" target/surefire-reports/*.xml target/failsafe-reports/*.xml 2>/dev/null; then
echo "Tests failed! Failing the workflow."
exit 1
fi
echo "All tests passed."

# ---------------------------
# COLLECT DOCKER LOGS (ALWAYS, WITH MAPPING)
# ---------------------------
- name: Collect Docker logs (mapped)
if: always()
run: |
mkdir -p docker-logs
echo "Gathering container metadata..."
docker ps -a --format '{{.Names}}|{{.Image}}|{{.Status}}' > docker-logs/container-summary.txt
while IFS='|' read -r name image status; do
# Create a readable label
label="$name"
case "$name" in
*dataverse*)
label="dataverse-app"
;;
*postgres*)
label="postgres-db"
;;
*solr*)
label="solr-index"
;;
*localstack*)
label="localstack-s3"
;;
esac
echo "Collecting logs for $name ($label)"
{
echo "===== CONTAINER: $name ====="
echo "Label: $label"
echo "Image: $image"
echo "Status: $status"
echo ""
echo "===== LOGS ====="
docker logs --timestamps "$name" 2>&1 || true
} > "docker-logs/${label}__${name}.log"
done < docker-logs/container-summary.txt

# ---------------------------
# UPLOAD DOCKER LOGS (ALWAYS)
# ---------------------------
- name: Upload Docker logs
if: always()
uses: actions/upload-artifact@v4
with:
name: docker-logs
path: docker-logs/
retention-days: 7

# ---------------------------
# SHUTDOWN STACK
# ---------------------------
- name: Stop Dataverse stack
if: always()
run: |
set -euo pipefail
mvn -Pct docker:stop || true

- name: Final Docker cleanup
if: always()
run: |
docker system prune -af || true
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
import static org.hamcrest.CoreMatchers.equalTo;
import static org.hamcrest.CoreMatchers.startsWith;
import static org.junit.jupiter.api.Assertions.*;
import org.junit.jupiter.api.Disabled;

public class DataRetrieverApiIT {

Expand Down Expand Up @@ -111,6 +112,7 @@ public void testRetrieveMyDataAsJsonString() throws InterruptedException {
}

// Test getting a list of collections that the user can add datasets to
@Disabled
Comment thread
srmanda-cs marked this conversation as resolved.
Outdated
@Test
public void testRetrieveMyDataCollections() throws InterruptedException {
int rootCount = 1; // everyone has access to this dataverse
Expand Down
2 changes: 1 addition & 1 deletion src/test/java/edu/harvard/iq/dataverse/api/SearchIT.java
Original file line number Diff line number Diff line change
Expand Up @@ -2024,7 +2024,7 @@ public void testSearchFilesAndUrlImages() throws InterruptedException {
.body("data.items[0].url", CoreMatchers.containsString("/dataverse/"))
.body("data.items[0]", CoreMatchers.not(CoreMatchers.hasItem("image_url")));

searchResp = UtilIT.search(datasetPid, apiToken);
searchResp = UtilIT.search("id:dataset_" + datasetId, apiToken);
searchResp.prettyPrint();
searchResp.then().assertThat()
.statusCode(OK.getStatusCode())
Expand Down
Loading