philentropyst/src/schema/template.schema.yml

Efficient data masking tool

schema:
  version: 1.0
  # csv is the only supported format yet
  # Later we'll have support for json and other formats
  csv:
    delimiter: ,
    multiline: true
    allowQuotes: true
    hasHeader: true
    # force strings to be wrapped in double quotes
    wrapStringInQuotes: true
    # if false numbers and booleans become strings
    parseNumbers: true
    parseBooleans: true
    # removes leading and trailing whitespaces - not good for fixed sized csvs
    trim: true
    # (optional) use this to indicate that lines are grouped by a certain field
    # in that case the ref points to the column, and fields is a list of field references
    # which should receive the same data per group, i.e. firstName, lastName
#    group:
#      ref: field1
#      fields:
#        - field2
#        - firstName
    # (optional) use cache to store previous field values and reuse them.
    # A common use case is when you process multiple files, in which same data, e.g. persons,
    # appear. So, you can keep consistent names across files
#    cache:
       # the name of the cache to be used - so you can work on different caches
#      name: mycache
#      fields:
#        - field2
#        - firstName

  # masks define what fields has to be masked and how
  masks:
    - field:
        # ref means either column index (starting with 0) or name if hasHeader=true
        ref: field1
        # type can be anything supported by https://github.com/marak/Faker.js/#api-methods
        type: datatype.number
        options:
          min: 1000
          max: 10000
    - field:
        ref: field2
        type: date.past
    - field:
        ref: firstName
        type: name.firstName