required Ensures that mandatory fields are present in all records | required | Error | Field is required |
unique Ensures that field content is unique in all records | uniqueness | Error | Field content must be unique |
capitalization Ensures that field starts with proper capitalization | capitalization | Warning | Field content must start with a Capital Show config{
"check_first_letter": true
} |
not_empty Ensures fields contain meaningful content rather than empty values | notEmpty | Info | Field should not be empty when present |
length_check Validates that field content is within acceptable length limits | length | Warning | Field length should be within acceptable range Show config{
"max": 1000,
"min": 1
} |
word_check Validates that field content is within acceptable word length limits | length | Warning | Field length in words should be within acceptable range Show config{
"count_words": true,
"max": 1000,
"min": 1
} |
identifier_pattern Validates identifier format for consistency and system compatibility | regex | Warning | Identifier should contain only alphanumeric characters and common separators Show config{
"pattern": "^[A-Za-z0-9._,-/]+$"
} |
iso_date_format Validates dates conform to ISO standards for interoperability | iso_date | Warning | Date should be in ISO format Show config{
"allow_ranges": true,
"formats": [
"YYYY",
"YYYY-MM",
"YYYY-MM-DD"
]
} |
date_range_format Validates date ranges use consistent formatting | regex | Info | Date range should use YYYY/YYYY or YYYY-YYYY format Show config{
"pattern": "^\\d{4}/\\d{4}$|^\\d{4}-\\d{4}$"
} |
language_code Validates language codes conform to ISO 639 standards | regex | Info | Language should be a valid ISO 639 code Show config{
"pattern": "^[a-z]{2,3}$"
} |
valid_url Validates URLs are properly formatted and accessible using Go's url.Parse | validUrl | Error | Must be a valid, well-formed URL Show config{
"require_host": true,
"schemes": [
"http",
"https"
]
} |
https_required Ensures URLs use secure HTTPS protocol for data protection | validUrl | Warning | Should use secure HTTPS URL for better security Show config{
"require_host": true,
"schemes": [
"https"
]
} |
http_security_warning Flags insecure HTTP URLs to encourage HTTPS adoption | validUrl | Warning | Insecure HTTP URL detected - upgrade to HTTPS recommended Show config{
"flag_insecure": true,
"require_host": true,
"schemes": [
"http",
"https"
]
} |
edm_type_vocabulary Validates resource type against Europeana Data Model standards | enum | Error | Must be valid EDM type Show config{
"case_sensitive": true,
"values": [
"IMAGE",
"TEXT",
"VIDEO",
"SOUND",
"3D"
]
} |
terminology_link_required Must a uri to known vocabulary | content | Error | An URI must point to a known vocabulary |
rights_vocabulary Validates rights statements against accepted standards for legal clarity | enum | Error | Must be valid rights statement URL Show config{
"case_sensitive": true,
"values": [
"http://rightsstatements.org/vocab/InC/1.0/",
"http://rightsstatements.org/vocab/InC-OW-EU/1.0/",
"http://rightsstatements.org/vocab/NoC-NC/1.0/",
"http://rightsstatements.org/vocab/NoC-OKLR/1.0/",
"http://creativecommons.org/publicdomain/zero/1.0/",
"http://creativecommons.org/licenses/by/4.0/",
"http://creativecommons.org/licenses/by-sa/4.0/",
"http://creativecommons.org/licenses/by-nc/4.0/"
]
} |
no_whitespace_only Ensures fields contain content beyond just whitespace characters | regex | Warning | Field should contain meaningful content, not just whitespace Show config{
"pattern": ".*\\S.*"
} |
no_unknown_terms Prevents use of unknown or placeholder terms | blacklist | Warning | Avoid using unknown or placeholder terms Show config{
"case_sensitive": false,
"terms": [
"onbekend",
"Onbekend",
"unknown",
"?",
" ",
"|",
" /",
"Unknown",
"ONBEKEND"
]
} |
no_words_matter_terms Prevents use of problematic terminology from Words Matter list | blacklist | Error | Content contains problematic terminology from Words Matter - please use respectful alternative language Show config{
"case_sensitive": false,
"terms": [
"Aboriginal",
"Afkomst",
"Allochtoon",
"Barbaar",
"Bediende",
"Berber",
"Blank",
"Bombay",
"Bosneger",
"Derde Wereld",
"Dwerg",
"Eskimo",
"Etniciteit",
"Exotisch",
"Gay",
"Gekleurd",
"Halfbloed",
"Handicap",
"Hermafrodiet",
"Homo",
"Hottentot",
"Inboorling",
"Indiaan",
"Indisch",
"Indo",
"Inheems",
"Inlander",
"Islamiet",
"Jappenkamp",
"Kaffer",
"Kaukasisch",
"Koelie",
"Koppensneller",
"Marron",
"Medicijnman",
"Mohammedaan",
"Mongool",
"Moor",
"Mulat",
"Neger",
"Ontdekken",
"Oriëntaals",
"Politionele actie",
"Primitief",
"Pygmee",
"Queer",
"Ras",
"Roots",
"Slaaf",
"Stam",
"Traditioneel",
"Trans",
"Westers",
"Wit",
"Zigeuners",
"Zwart"
]
} |
no_punctuation Validates field contains no punctuation marks | regex | Warning | Field should not contain punctuation marks Show config{
"pattern": "^[^.,;:!?()\"\\[\\]{}]+$"
} |
limited_punctuation Allows only comma and period punctuation | regex | Warning | Only comma and period are allowed as punctuation Show config{
"pattern": "^[^;:!?()\"\\[\\]{}]*$"
} |
no_empty_brackets Detects and flags empty brackets | regex | Warning | Remove empty brackets from field Show config{
"pattern": "^(?!.*\\(\\s*\\)).*$"
} |
no_approximation_terms Prevents use of approximation terms in dimensions | blacklist | Warning | Avoid approximation terms in dimensions Show config{
"case_sensitive": false,
"terms": [
"circa",
"ca.",
"ca",
"ongeveer"
]
} |
lowercase_units Validates units are in lowercase | regex | Warning | Use lowercase letters for dimension units Show config{
"pattern": "^[^A-Z]*$"
} |