Make atomic field limits configurable

[pondzix]

This PR adds new configuration section which allows us to set custom length limits for atomic fields. Previously those limits were hardcoded in enrich code with values equal to the ones in the atomic schema.

New configuration looks like this:

{
  ...
  
  # Optional. Configuration section for various validation-oriented settings.
  "validation": {
   
    # Optional. Configuration for custom maximum atomic fields (strings) length.
    # Map-like structure with keys being field names and values being their max allowed length

    "atomicFieldsLimits": {
        "app_id": 5
        "mkt_clickid": 100000
        # ...and any other 'atomic' field with custom limit
    }
  }
}

with defaults set in application.conf:

Note: page_url, page_referrer and mkt_clickid have now increased limit by default!

{
  ...
  "validation": {
    "atomicFieldsLimits": { 
       "app_id": 255
       "platform": 255
       "event": 128
       "event_id": 36
       "name_tracker": 128
       "v_tracker": 100
       "v_collector": 100
       "v_etl": 100
       "user_id": 255
       "user_ipaddress": 128
       "user_fingerprint": 128
       "domain_userid": 128
       "network_userid": 128
       "geo_country": 2
       "geo_region": 3
       "geo_city": 75
       "geo_zipcode": 15
       "geo_region_name": 100
       "ip_isp": 100
       "ip_organization": 128
       "ip_domain": 128
       "ip_netspeed": 100
       "page_url": 10000 # Different than the one in atomic schema (4096)
       "page_title": 2000
       "page_referrer": 10000 # Different than the one in atomic schema (4096)
       "page_urlscheme": 16
       "page_urlhost": 255
       "page_urlpath": 3000
       "page_urlquery": 6000
       "page_urlfragment": 3000
       "refr_urlscheme": 16
       "refr_urlhost": 255
       "refr_urlpath": 6000
       "refr_urlquery": 6000
       "refr_urlfragment": 3000
       "refr_medium": 25
       "refr_source": 50
       "refr_term": 255
       "mkt_clickid": 1000 # Different than the one in atomic schema (128)
       "mkt_network": 64
       "mkt_medium": 255
       "mkt_source": 255
       "mkt_term": 255
       "mkt_content": 500
       "mkt_campaign": 255
       "se_category": 1000
       "se_action": 1000
       "se_label": 4096
       "se_property": 1000
       "tr_orderid": 255
       "tr_affiliation": 255
       "tr_city": 255
       "tr_state": 255
       "tr_country": 255
       "ti_orderid": 255
       "ti_sku": 255
       "ti_name": 255
       "ti_category": 255
       "useragent": 1000
       "br_name": 50
       "br_family": 50
       "br_version": 50
       "br_type": 50
       "br_renderengine": 50
       "br_lang": 255
       "br_colordepth": 12
       "os_name": 50
       "os_family": 50
       "os_manufacturer": 50
       "os_timezone": 255
       "dvce_type": 50
       "doc_charset": 128
       "tr_currency": 3
       "ti_currency": 3
       "base_currency": 3
       "geo_timezone": 64
       "etl_tags": 500
       "refr_domain_userid": 128
       "domain_sessionid": 128
       "event_vendor": 1000
       "event_name": 1000
       "event_format": 128
       "event_version": 128
       "event_fingerprint": 128
    }
  }
}

[istreeter]

Looks great

[benjben]

👍