{
  "name": "Snowplow Data Pipeline Structure",
  "description": "Hierarchical structure of Snowplow behavioral data pipeline components from event generation to data warehouse",
  "version": "1.0",
  "pipeline_stages": {
    "1_Collection": {
      "component": "Tracker",
      "description": "SDKs and libraries that generate and send events to the Snowplow Collector",
      "trackers": [
        "JavaScript Tracker (web)",
        "iOS Tracker",
        "Android Tracker",
        "Python Tracker",
        "Java Tracker",
        "Go Tracker",
        "Ruby Tracker",
        ".NET Tracker",
        "PHP Tracker",
        "Rust Tracker"
      ],
      "event_types": {
        "PageView": "Tracks user navigating to a page",
        "PagePing": "Tracks user staying on a page (engagement)",
        "StructuredEvent": "Five-field categorical event (category, action, label, property, value)",
        "SelfDescribingEvent": "Custom event with a self-describing JSON Schema",
        "Transaction": "E-commerce transaction event",
        "FormSubmit": "Form submission event"
      },
      "output": "Raw event payload (GET/POST to Collector endpoint)"
    },
    "2_Collection_Server": {
      "component": "Collector",
      "description": "Receives events from trackers, sets network cookies, forwards to enrichment",
      "fields_added": ["collector_tstamp", "network_userid", "ip_address", "useragent"],
      "output": "Raw events in Thrift format to Kinesis/Kafka/PubSub stream"
    },
    "3_Enrichment": {
      "component": "Enrich",
      "description": "Validates event schemas, applies enrichments, writes to enriched/bad streams",
      "enrichments": {
        "IP Anonymization": "Anonymize IP addresses",
        "IP Lookups": "Geolocation (country, city, ISP) from IP",
        "User Agent Parser": "Parse browser, OS, device from user agent",
        "Campaign Attribution": "Parse UTM parameters",
        "JavaScript Enrichment": "Custom JS-based enrichment logic",
        "API Request Enrichment": "Enrich with external API data",
        "SQL Query Enrichment": "Enrich with database lookup",
        "IAB Spiders and Robots": "Detect bots",
        "YAUAA (Yet Another UserAgent Analyzer)": "Advanced device detection",
        "Currency Conversion": "Convert currency values",
        "Weather Enrichment": "Add weather context from OpenWeather API"
      },
      "schema_validation": "Each self-describing event/entity is validated against its Iglu schema registry",
      "output": "Enriched events in JSON format to enriched stream; failed events to bad stream"
    },
    "4_Storage": {
      "component": "Loaders",
      "description": "Load enriched events from the stream into data warehouses",
      "destinations": [
        "Snowflake (Snowflake Streaming Loader)",
        "BigQuery (BigQuery Loader)",
        "Redshift (RDB Loader)",
        "Databricks (Databricks Loader)",
        "S3 (S3 Loader for data lake)",
        "GCS (GCS Loader for data lake)"
      ]
    },
    "5_Modeling": {
      "component": "Data Models",
      "description": "dbt-based data models transform raw event data into analytics-ready tables",
      "models": [
        "Web model (page views, sessions, users)",
        "Mobile model (screen views, sessions)",
        "E-commerce model (transactions, products)",
        "Attribution model",
        "Custom models"
      ]
    }
  },
  "governance_layer": {
    "DataStructure": {
      "description": "A JSON Schema defining the shape of a self-describing event or entity",
      "fields": {
        "hash": "string (SHA-256 of vendor+name+format)",
        "vendor": "string (reverse DNS, e.g., com.example)",
        "name": "string (snake_case event name)",
        "format": "string (jsonschema)",
        "latestVersion": "string (SchemaVer: major-minor-patch)",
        "deployedEnvironments": "array[enum: VALIDATED, DEV, PROD]"
      }
    },
    "DataProduct": {
      "description": "A tracking plan grouping related event specifications for a product feature or team",
      "fields": {
        "id": "string (UUID)",
        "name": "string",
        "description": "string",
        "status": "enum: active | draft | deprecated",
        "domain": "string",
        "eventSpecificationCount": "integer"
      },
      "children": {
        "EventSpecification": {
          "description": "A specific event type with trigger context, schema reference, and implementation notes",
          "fields": {
            "id": "string (UUID)",
            "name": "string",
            "description": "string",
            "schemaReference": "string (Iglu URI)",
            "status": "enum: active | deprecated"
          }
        }
      }
    },
    "SchemaRegistry": {
      "description": "Iglu schema registry storing and serving JSON Schema definitions for validation",
      "types": {
        "Iglu Central": "Public registry for open-source schemas",
        "Private Registry": "Customer-owned registry for custom schemas"
      }
    }
  }
}