.env.example

# Google Cloud Configuration for Dataproc Spark Connect Integration Tests
# Copy this file to .env and fill in your actual values

# ============================================================================
# REQUIRED CONFIGURATION
# ============================================================================

# Your Google Cloud Project ID
GOOGLE_CLOUD_PROJECT="your-project-id"

# Google Cloud Region where Dataproc sessions will be created
GOOGLE_CLOUD_REGION="us-central1"

# Path to service account key file (if using SERVICE_ACCOUNT auth)
GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/service-account-key.json"

# ============================================================================
# AUTHENTICATION CONFIGURATION
# ============================================================================

# Authentication type (SERVICE_ACCOUNT or END_USER_CREDENTIALS). If not set, API default is used.
# DATAPROC_SPARK_CONNECT_AUTH_TYPE="SERVICE_ACCOUNT"
# DATAPROC_SPARK_CONNECT_AUTH_TYPE="END_USER_CREDENTIALS"

# Service account email for workload authentication (optional)
# DATAPROC_SPARK_CONNECT_SERVICE_ACCOUNT="your-service-account@your-project.iam.gserviceaccount.com"

# ============================================================================
# SESSION CONFIGURATION
# ============================================================================

# Session timeout in seconds (how long session stays active)
# DATAPROC_SPARK_CONNECT_TTL_SECONDS="3600"

# Session idle timeout in seconds (how long session stays active when idle)
# DATAPROC_SPARK_CONNECT_IDLE_TTL_SECONDS="900"

# Automatically terminate session when Python process exits (true/false)
# DATAPROC_SPARK_CONNECT_SESSION_TERMINATE_AT_EXIT="false"

# Custom file path for storing active session information
# DATAPROC_SPARK_CONNECT_ACTIVE_SESSION_FILE_PATH="/tmp/dataproc_spark_connect_session"

# ============================================================================
# DATA SOURCE CONFIGURATION
# ============================================================================

# Default data source for Spark SQL (currently only supports "bigquery")
# Only available for Dataproc runtime version 2.3
# DATAPROC_SPARK_CONNECT_DEFAULT_DATASOURCE="bigquery"

# ============================================================================
# ADVANCED CONFIGURATION
# ============================================================================

# Custom Dataproc API endpoint (uncomment if needed)
# GOOGLE_CLOUD_DATAPROC_API_ENDPOINT="your-region-dataproc.googleapis.com"

# Subnet URI for Dataproc Spark Connect (full resource name format)
# Example: projects/your-project-id/regions/us-central1/subnetworks/your-subnet-name
# DATAPROC_SPARK_CONNECT_SUBNET="projects/your-project-id/regions/us-central1/subnetworks/your-subnet-name"