minimal_spec.json

{
  "_comment": "Copy-paste this object into the `datasets` array in sources.json and edit the placeholder values. Validates against sources.schema.json. Use the Python load-edit-dump pattern from AGENTS.md to insert it — never `sed`.",
  "slug": "my-dataset",
  "short_name": "My Dataset",
  "full_name": "My Dataset (Publisher Attribution, Year)",
  "description": "One-line summary describing what this dataset contains.",
  "license": {
    "spdx": "CC0-1.0",
    "source_url": "https://example.com/LICENSE",
    "redistribution_permitted": true,
    "attribution_required": false,
    "notes": null,
    "scrape_advisory": null
  },
  "fetch": {
    "type": "http",
    "urls": ["https://example.com/data.csv"],
    "auth": null,
    "expected_bytes": null,
    "expected_sha256": null
  },
  "extract": {
    "type": "passthrough",
    "include": null,
    "exclude": null,
    "post": null
  },
  "parse": {
    "reader": "csv",
    "options": {
      "delimiter": ",",
      "has_header": true,
      "encoding": "utf-8"
    }
  },
  "transform": {
    "handler": "tighten_types",
    "params": {}
  },
  "write": {
    "output": "my-dataset.parquet",
    "compression": "zstd",
    "row_group_size_rows": 1048576,
    "statistics": true,
    "page_index": false
  },
  "expect": {
    "rows": null,
    "schema_hash": null,
    "notes": "Populate `rows` after the first successful build."
  },
  "convert": {
    "vortex": true,
    "vortex_skip_reason": null
  }
}