Duplicate Candidate Detection

checks for {{table_name}}:
  - invalid_percent({{column_name}}) < {{(1 - threshold) * 100}}:
      valid regex: '^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'

{% test valid_email(model, column_name) %}
select {{ column_name }}
from {{ model }}
where {{ column_name }} not regexp '^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$'
{% endtest %}

SELECT COUNT(*) as total,
  SUM(CASE WHEN {{column_name}} REGEXP
    '^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$'
    THEN 1 ELSE 0 END) as valid
FROM {{table_name}}

{
  "expectation_type": "expect_column_values_to_match_regex",
  "kwargs": {
    "column": "{{column_name}}",
    "regex": "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$",
    "mostly": {{threshold}}
  }
}

from pyspark.sql.functions import col
pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
invalid = df.filter(~col("{{column_name}}").rlike(pattern)).count()