string invalid email count
string invalid email count checks
Description
Column level check that ensures that there are no more than a maximum number of invalid email in a monitored column.
profile string invalid email count
Check description
Verifies that the number of invalid emails in a column does not exceed the maximum accepted count.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| profile_string_invalid_email_count | profiling | string_invalid_email_count | max_count |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=profile_string_invalid_email_count
profiling_checks:
strings:
profile_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
profiling_checks:
strings:
profile_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
profiling_checks:
strings:
profile_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state]
ORDER BY level_1, level_2
,
daily string invalid email count
Check description
Verifies that the number of invalid emails in a column does not exceed the maximum accepted count. Stores the most recent captured value for each day when the data quality check was evaluated.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| daily_string_invalid_email_count | recurring | daily | string_invalid_email_count | max_count |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=daily_string_invalid_email_count
recurring_checks:
daily:
strings:
daily_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
recurring_checks:
daily:
strings:
daily_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
CAST(CURRENT_TIMESTAMP() AS DATE) AS time_period,
TIMESTAMP(CAST(CURRENT_TIMESTAMP() AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
CAST(SYSDATETIMEOFFSET() AS date) AS time_period,
CAST((CAST(SYSDATETIMEOFFSET() AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
recurring_checks:
daily:
strings:
daily_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
CAST(CURRENT_TIMESTAMP() AS DATE) AS time_period,
TIMESTAMP(CAST(CURRENT_TIMESTAMP() AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(LOCALTIMESTAMP AS date) AS time_period,
CAST((CAST(LOCALTIMESTAMP AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date) AS time_period,
TO_TIMESTAMP(CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
CAST(SYSDATETIMEOFFSET() AS date) AS time_period,
CAST((CAST(SYSDATETIMEOFFSET() AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state]
ORDER BY level_1, level_2
,
monthly string invalid email count
Check description
Verifies that the number of invalid emails in a column does not exceed the maximum accepted count. Stores the most recent row count for each month when the data quality check was evaluated.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| monthly_string_invalid_email_count | recurring | monthly | string_invalid_email_count | max_count |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=monthly_string_invalid_email_count
recurring_checks:
monthly:
strings:
monthly_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
recurring_checks:
monthly:
strings:
monthly_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
recurring_checks:
monthly:
strings:
monthly_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(CURRENT_TIMESTAMP() AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(LOCALTIMESTAMP, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(LOCALTIMESTAMP AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(TO_TIMESTAMP_NTZ(LOCALTIMESTAMP()) AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0) AS time_period,
CAST((DATEADD(month, DATEDIFF(month, 0, SYSDATETIMEOFFSET()), 0)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state]
ORDER BY level_1, level_2
,
daily partition string invalid email count
Check description
Verifies that the number of invalid emails in a column does not exceed the maximum accepted count. Creates a separate data quality check (and an alert) for each daily partition.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| daily_partition_string_invalid_email_count | partitioned | daily | string_invalid_email_count | max_count |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=daily_partition_string_invalid_email_count
partitioned_checks:
daily:
strings:
daily_partition_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
partitioned_checks:
daily:
strings:
daily_partition_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
CAST(analyzed_table.`` AS DATE) AS time_period,
TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
CAST(analyzed_table."" AS date) AS time_period,
TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
CAST(analyzed_table.[] AS date) AS time_period,
CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY CAST(analyzed_table.[] AS date)
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
partitioned_checks:
daily:
strings:
daily_partition_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
CAST(analyzed_table.`` AS DATE) AS time_period,
TIMESTAMP(CAST(analyzed_table.`` AS DATE)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-%d 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(analyzed_table."" AS date) AS time_period,
CAST((CAST(analyzed_table."" AS date)) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
CAST(analyzed_table."" AS date) AS time_period,
TO_TIMESTAMP(CAST(analyzed_table."" AS date)) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
CAST(analyzed_table.[] AS date) AS time_period,
CAST((CAST(analyzed_table.[] AS date)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state], CAST(analyzed_table.[] AS date), CAST(analyzed_table.[] AS date)
ORDER BY level_1, level_2CAST(analyzed_table.[] AS date)
monthly partition string invalid email count
Check description
Verifies that the number of invalid emails in a column does not exceed the maximum accepted count. Creates a separate data quality check (and an alert) for each monthly partition.
| Check name | Check type | Time scale | Sensor definition | Quality rule |
|---|---|---|---|---|
| monthly_partition_string_invalid_email_count | partitioned | monthly | string_invalid_email_count | max_count |
Enable check (Shell)
To enable this check provide connection name and check name in check enable command
To run this check provide check name in check run command It is also possible to run this check on a specific connection. In order to do this, add the connection name to the below It is additionally feasible to run this check on a specific table. In order to do this, add the table name to the below It is furthermore viable to combine run this check on a specific column. In order to do this, add the column name to the below
dqo> check run -c=connection_name -t=table_name -col=column_name -ch=monthly_partition_string_invalid_email_count
partitioned_checks:
monthly:
strings:
monthly_partition_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
columns:
target_column:
partitioned_checks:
monthly:
strings:
monthly_partition_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
BigQuery
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY time_period, time_period_utc
ORDER BY time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1) AS time_period,
CAST((DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1), DATEADD(month, DATEDIFF(month, 0, analyzed_table.[]), 0)
ORDER BY DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1)
Configuration with data grouping
Click to see more
Sample configuration (Yaml)
# yaml-language-server: $schema=https://cloud.dqo.ai/dqo-yaml-schema/TableYaml-schema.json
apiVersion: dqo/v1
kind: table
spec:
timestamp_columns:
event_timestamp_column: col_event_timestamp
ingestion_timestamp_column: col_inserted_at
incremental_time_window:
daily_partitioning_recent_days: 7
monthly_partitioning_recent_months: 1
default_grouping_name: group_by_country_and_state
groupings:
group_by_country_and_state:
level_1:
source: column_value
column: country
level_2:
source: column_value
column: state
columns:
target_column:
partitioned_checks:
monthly:
strings:
monthly_partition_string_invalid_email_count:
warning:
max_count: 0
error:
max_count: 10
fatal:
max_count: 15
labels:
- This is the column that is analyzed for data quality issues
col_event_timestamp:
labels:
- optional column that stores the timestamp when the event/transaction happened
col_inserted_at:
labels:
- optional column that stores the timestamp when row was ingested
country:
labels:
- column used as the first grouping key
state:
labels:
- column used as the second grouping key
{% import '/dialects/bigquery.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST({{ lib.render_target_column('analyzed_table') }} AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_CONTAINS(CAST(analyzed_table.`target_column` AS STRING), r"^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$")
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH) AS time_period,
TIMESTAMP(DATE_TRUNC(CAST(analyzed_table.`` AS DATE), MONTH)) AS time_period_utc
FROM `your-google-project-id`.`<target_schema>`.`<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
MySQL
{% import '/dialects/mysql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE({{ lib.render_target_column('analyzed_table') }}, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN REGEXP_LIKE(analyzed_table.`target_column`, '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$')
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.`country` AS grouping_level_1,
analyzed_table.`state` AS grouping_level_2,
DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00') AS time_period,
FROM_UNIXTIME(UNIX_TIMESTAMP(DATE_FORMAT(analyzed_table.``, '%Y-%m-01 00:00:00'))) AS time_period_utc
FROM `<target_table>` AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
PostgreSQL
{% import '/dialects/postgresql.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^[a-zA-Z0-9.!#$%&''*+/=?^_`{|}~-]+@[a-zA-Z0-9-]+(?:\.[a-zA-Z0-9-]+)*$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_postgresql_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Redshift
{% import '/dialects/redshift.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{lib.render_target_column('analyzed_table')}} !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" !~ '^([a-z0-9_\.-]+)@([\da-z\.-]+)\.([a-z]{2,6})$'
THEN 1
ELSE 0
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
CAST((DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS TIMESTAMP WITH TIME ZONE) AS time_period_utc
FROM "your_redshift_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
Snowflake
{% import '/dialects/snowflake.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table."target_column" REGEXP '^[A-Za-z]+[A-Za-z0-9.]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}$'
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table."country" AS grouping_level_1,
analyzed_table."state" AS grouping_level_2,
DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date)) AS time_period,
TO_TIMESTAMP(DATE_TRUNC('MONTH', CAST(analyzed_table."" AS date))) AS time_period_utc
FROM "your_snowflake_database"."<target_schema>"."<target_table>" AS analyzed_table
GROUP BY grouping_level_1, grouping_level_2, time_period, time_period_utc
ORDER BY grouping_level_1, grouping_level_2, time_period, time_period_utc
SQL Server
{% import '/dialects/sqlserver.sql.jinja2' as lib with context -%}
SELECT
SUM(
CASE
WHEN {{ lib.render_target_column('analyzed_table') }} LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE({{ lib.render_target_column('analyzed_table') }}, '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value
{{- lib.render_data_grouping_projections('analyzed_table') }}
{{- lib.render_time_dimension_projection('analyzed_table') }}
FROM {{ lib.render_target_table() }} AS analyzed_table
{{- lib.render_where_clause() -}}
{{- lib.render_group_by() -}}
{{- lib.render_order_by() -}}
SELECT
SUM(
CASE
WHEN analyzed_table.[target_column] LIKE '%_@__%.__%' AND PATINDEX('%[^a-z,0-9,@,.,_]%', REPLACE(analyzed_table.[target_column], '-', 'a')) = 0
THEN 0
ELSE 1
END
) AS actual_value,
analyzed_table.[country] AS grouping_level_1,
analyzed_table.[state] AS grouping_level_2,
DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1) AS time_period,
CAST((DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1)) AS DATETIME) AS time_period_utc
FROM [your_sql_server_database].[<target_schema>].[<target_table>] AS analyzed_table
GROUP BY analyzed_table.[country], analyzed_table.[state], DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1), DATEADD(month, DATEDIFF(month, 0, analyzed_table.[]), 0)
ORDER BY level_1, level_2DATEFROMPARTS(YEAR(CAST(analyzed_table.[] AS date)), MONTH(CAST(analyzed_table.[] AS date)), 1)