{
  "id": "datahub",
  "name": "DataHub classification",
  "category": "catalogs",
  "doc": "DataHub can classify table columns during ingestion and attach a glossary term for each detected info type. The built-in classifier comes from the acryl-datahub-classify library: it scores a column by its name, description, data type and sample values, using regular expressions, spaCy named entities or the schwifty library. Its default configuration in reference_input.py defines 14 info types, such as Email_Address, IBAN, Swift_Code and US_Social_Security_Number. Recent acryl-datahub releases no longer include this built-in classifier.",
  "website": "https://github.com/acryldata/datahub-classify/blob/main/datahub-classify/src/datahub_classify/reference_input.py",
  "supported_types": [
    "address",
    "age",
    "bankcard",
    "bic",
    "email",
    "gender",
    "iban",
    "ipv4",
    "ipv6",
    "person_fullname",
    "phone",
    "swiftcode",
    "usdriverlic",
    "usssn",
    "vin"
  ],
  "source": {
    "path": "data/tools/catalogs/datahub.yaml",
    "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/datahub.yaml",
    "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/datahub.yaml"
  },
  "urls": {
    "html": "http://registry.apicrafter.io/tool/datahub",
    "json": "http://registry.apicrafter.io/api/v1/tools/datahub.json"
  }
}