{
    "$schema": "http://json-schema.org/draft-07/schema#",
    "title": "GeoQuery Data Catalog Entry",
    "description": "Schema for dataset metadata in the GeoQuery platform catalog",
    "type": "object",
    "required": [
        "path",
        "columns",
        "category",
        "format"
    ],
    "properties": {
        "path": {
            "type": "string",
            "description": "Relative path to the data file from the data directory"
        },
        "description": {
            "type": "string",
            "description": "Auto-generated basic description (e.g., 'Data from hdx/health.geojson')"
        },
        "semantic_description": {
            "type": [
                "string",
                "null"
            ],
            "description": "LLM-generated rich description explaining the dataset's contents and use cases"
        },
        "tags": {
            "type": "array",
            "items": {
                "type": "string"
            },
            "description": "Searchable tags for categorization (e.g., ['health', 'facilities', 'infrastructure'])"
        },
        "data_type": {
            "type": "string",
            "enum": [
                "static",
                "semi-static",
                "realtime"
            ],
            "description": "How frequently the data changes",
            "default": "static"
        },
        "update_frequency": {
            "type": [
                "string",
                "null"
            ],
            "enum": [
                null,
                "yearly",
                "monthly",
                "weekly",
                "daily",
                "hourly",
                "realtime"
            ],
            "description": "Expected update frequency for the dataset"
        },
        "columns": {
            "type": "array",
            "items": {
                "type": "string"
            },
            "description": "List of column names in the dataset"
        },
        "row_count": {
            "type": [
                "integer",
                "null"
            ],
            "description": "Number of features/rows in the dataset"
        },
        "category": {
            "type": "string",
            "description": "Source category (base, osm, hdx, inec, custom)"
        },
        "format": {
            "type": "string",
            "enum": [
                "geojson",
                "shapefile",
                "geoparquet",
                "csv"
            ],
            "description": "File format of the source data"
        },
        "geometry_type": {
            "type": [
                "string",
                "null"
            ],
            "enum": [
                null,
                "Point",
                "MultiPoint",
                "LineString",
                "MultiLineString",
                "Polygon",
                "MultiPolygon"
            ],
            "description": "Type of geometries in the dataset"
        },
        "bbox": {
            "type": [
                "array",
                "null"
            ],
            "items": {
                "type": "number"
            },
            "minItems": 4,
            "maxItems": 4,
            "description": "Bounding box [minLon, minLat, maxLon, maxLat]"
        },
        "source": {
            "type": [
                "string",
                "null"
            ],
            "description": "Original source of the data (e.g., 'OpenStreetMap', 'INEC Census 2023')"
        },
        "license": {
            "type": [
                "string",
                "null"
            ],
            "description": "Data license (e.g., 'ODbL', 'CC-BY-4.0', 'Public Domain')"
        },
        "last_indexed": {
            "type": "string",
            "format": "date-time",
            "description": "ISO timestamp when the dataset was last indexed"
        },
        "last_enriched": {
            "type": [
                "string",
                "null"
            ],
            "format": "date-time",
            "description": "ISO timestamp when LLM enrichment was last run"
        }
    }
}