.env.example

# ===============================================
# Neo4j Export Tool Configuration
# ===============================================
# This file contains all available configuration options for the Neo4j export tool.
# Copy this file to .env and modify the values as needed.
# All values shown are the defaults unless otherwise noted.

# ===============================================
# Neo4j Connection Settings
# ===============================================

# Neo4j connection URI
# Supported schemes: bolt, neo4j, bolt+s, neo4j+s
# Default: bolt://localhost:7687
N4JET_NEO4J_URI=bolt://localhost:7687

# Neo4j username
# Default: neo4j
N4JET_NEO4J_USER=neo4j

# Neo4j password
# Default: (empty string)
# For production, use a secure password
N4JET_NEO4J_PASSWORD=your-secure-password

# ===============================================
# Output Configuration
# ===============================================

# Output directory for the export file
# The export will create a timestamped JSONL file in this directory
# Path should be inside the container (mapped by docker-compose)
# Default: . (current directory)
N4JET_OUTPUT_DIRECTORY=/data/export

# ===============================================
# Resource Management
# ===============================================

# Minimum free disk space in GB required on the export volume
# Export will stop if available space falls below this threshold
# Default: 10
N4JET_MIN_DISK_GB=10

# Maximum memory usage in MB before triggering garbage collection
# Default: 1024
N4JET_MAX_MEMORY_MB=1024

# ===============================================
# Export Behavior
# ===============================================

# Skip schema collection phase to speed up export
# Set to true for faster exports when schema information is not needed
# Default: false
N4JET_SKIP_SCHEMA_COLLECTION=false

# Number of records to process in each batch
# Larger values may improve performance but use more memory
# Default: 10000
N4JET_BATCH_SIZE=10000

# Enable generation of content-based hash IDs
# Set to false to skip hash computation for better performance
# Default: true
N4JET_ENABLE_HASHED_IDS=true

# ===============================================
# Error Handling and Resilience
# ===============================================

# Maximum number of retry attempts for transient failures
# Default: 5
N4JET_MAX_RETRIES=5

# Initial delay in milliseconds between retry attempts
# Uses exponential backoff for subsequent retries
# Default: 1000
N4JET_RETRY_DELAY_MS=1000

# Maximum delay in milliseconds between retry attempts
# Caps the exponential backoff to prevent excessive wait times
# Default: 30000 (30 seconds)
N4JET_MAX_RETRY_DELAY_MS=30000

# Query timeout in seconds for individual Cypher queries
# Default: 300
N4JET_QUERY_TIMEOUT_SECONDS=300

# ===============================================
# Debugging and Validation
# ===============================================

# Enable debug logging for troubleshooting
# Set to true for verbose output
# Default: false
N4JET_DEBUG=false

# Validate JSON output during export
# Set to false for slightly better performance
# Default: true
N4JET_VALIDATE_JSON=true

# ===============================================
# Test Configuration
# ===============================================

# Minimum log level for test output
# Controls verbosity of test execution logs
# Values: Debug, Info, Warn, Error, Fatal (case-insensitive)
# Default: Info
N4JET_TEST_LOG_LEVEL=Info

# ===============================================
# Security Settings
# ===============================================

# Allow insecure TLS connections (e.g., self-signed certificates)
# WARNING: Use with caution in production environments
# Default: false
N4JET_ALLOW_INSECURE=false

# ===============================================
# Memory Estimation Configuration
# ===============================================

# Average size per record in bytes for memory estimation
# Adjust based on your graph's typical property sizes
# Default: 1024 (1KB)
N4JET_NEO4J_EXPORT_AVG_RECORD_SIZE=1024

# Processing overhead multiplier for memory estimation
# Higher values reserve more memory for serialization buffers
# Default: 2.0
N4JET_NEO4J_EXPORT_OVERHEAD_MULTIPLIER=2.0

# Minimum memory to reserve in bytes
# Ensures a baseline memory reservation regardless of batch size
# Default: 104857600 (100MB)
N4JET_NEO4J_EXPORT_MIN_MEMORY_RESERVATION=104857600

# ===============================================
# JSON Serialization Configuration
# ===============================================

# JSON Serialization Buffer Size (KB)
# Initial buffer size for JSON serialization. Buffer grows as needed.
# Default: 16KB. Increase for databases with large properties.
N4JET_JSON_BUFFER_SIZE_KB=16

# ===============================================
# Path Serialization Safety Thresholds
# ===============================================
# These thresholds control automatic behavior for path serialization.
# The tool always attempts maximum extraction and degrades automatically.

# Absolute maximum path length allowed
# Paths longer than this will be truncated with an error
# Default: 100000
N4JET_MAX_PATH_LENGTH=100000

# Threshold for switching from Full to Compact mode
# When path has more nodes than this, properties are omitted
# Default: 1000
N4JET_PATH_FULL_MODE_LIMIT=1000

# Threshold for switching from Compact to IdsOnly mode
# When path has more nodes than this, only IDs are exported
# Default: 10000
N4JET_PATH_COMPACT_MODE_LIMIT=10000

# Maximum depth for serializing properties in path elements
# Default: 5
N4JET_PATH_PROPERTY_DEPTH=5

# ===============================================
# Nested Graph Element Safety Thresholds
# ===============================================
# These thresholds control automatic behavior for nested elements.
# The tool always serializes nested elements, never returns errors.

# Absolute maximum nesting depth allowed
# Default: 10
N4JET_MAX_NESTED_DEPTH=10

# Depth at which to switch from Deep to Shallow mode
# Shallow mode omits properties but includes labels/types
# Default: 5
N4JET_NESTED_SHALLOW_MODE_DEPTH=5

# Depth at which to switch from Shallow to Reference mode
# Reference mode only includes IDs and basic type info
# Default: 8
N4JET_NESTED_REFERENCE_MODE_DEPTH=8

# ===============================================
# Label Truncation Limits
# ===============================================
# These limits control how many labels are serialized for nodes
# in different contexts to prevent excessive JSON size.

# Maximum number of labels per node in full serialization mode
# When a node has more labels than this, they are truncated
# Default: 100
N4JET_MAX_LABELS_PER_NODE=100

# Maximum number of labels in reference mode (minimal serialization)
# Used when nodes appear as references in paths or nested structures
# Default: 10
N4JET_MAX_LABELS_IN_REFERENCE_MODE=10

# Maximum number of labels in path compact mode
# Used when serializing nodes within paths in compact mode
# Default: 5
N4JET_MAX_LABELS_IN_PATH_COMPACT=5

# ===============================================
# Collection Limits
# ===============================================

# Maximum number of items to include in collections (lists, maps)
# Collections larger than this are truncated with a warning
# Default: 10000
N4JET_MAX_COLLECTION_ITEMS=10000