[{"id": "alteryxdesignercloud", "name": "Alteryx Designer Cloud", "category": "other", "doc": "Alteryx Designer Cloud, formerly Trifacta, is a cloud service for data preparation. It infers a data type for each column from the first rows of a sample, shows the share of valid, invalid and empty values, and suggests transformations to fix the invalid ones. Besides logical types such as Integer, Boolean and Datetime it has complex types, which are strings checked by regular expressions, such as Social Security Number, Phone Number, Zip Code, State, Credit Card and HTTP Code. The types are listed in the overview of the type system in the Alteryx help.", "website": "https://help.alteryx.com/trifacta-classic/en/concepts/feature-overviews/overview-of-the-type-system.html", "supported_types": ["bankcard", "boolean", "date", "datetime", "email", "gender", "http_status_code", "ipv4", "nanpphone", "url", "usssn", "usstate", "uszipcode"], "source": {"path": "data/tools/other/alteryxdesignercloud.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/alteryxdesignercloud.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/alteryxdesignercloud.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/alteryxdesignercloud", "json": "http://registry.apicrafter.io/api/v1/tools/alteryxdesignercloud.json"}}, {"id": "amazonmacie", "name": "Amazon Macie", "category": "pii", "doc": "Amazon Macie scans objects in Amazon S3 for sensitive data with managed data identifiers. They cover credentials and private keys, financial data such as card and bank account numbers, health identifiers, and personal identifiers such as passport, driver's license and tax numbers for a list of countries. Many identifiers report a match only when a keyword is near the value.", "website": "https://docs.aws.amazon.com/macie/latest/user/mdis-reference-quick.html", "supported_types": ["aadhaar", "address", "aeiban", "ardni", "at_driver_license", "au_driver_license", "autfn", "aws_secret_access_key", "bankaccount", "bankcard", "bankcard_cvv", "bankcard_expiry", "be_driver_license", "bg_driver_license", "birthday", "br_postcode", "brcpf", "ca_bank_account", "ca_pr_card", "cadriverlic", "capassport", "casin", "chiban", "cl_rut", "cnpj", "co_nit", "cpf", "cptcode", "cuit", "curp", "cy_driver_license", "cz_driver_license", "de_passport", "dedriverlic", "depersonalausweis", "dk_driver_license", "ee_driver_license", "egiban", "es_ccc", "es_dni", "es_iban", "es_nss", "esdriverlic", "esnie", "esnif", "espassport", "fi_driver_license", "fi_ehic", "fr_driver_license", "fr_health_insurance_number", "fr_nif", "frcni", "frpassport", "gb_electoral_roll_number", "geopoint", "google_api_key", "gr_driver_license", "hr_driver_license", "http_authorization_header", "hu_driver_license", "iban", "ie_driver_license", "in_driver_license", "it_codicefiscale", "it_driver_license", "it_passport", "jwt", "lt_driver_license", "lu_driver_license", "lv_driver_license", "me_iban", "mt_driver_license", "nanpphone", "nhsnumber", "nif", "nl_driver_license", "npi", "pan", "person_fullname", "pgp_private_key_block", "phone", "pldriverlic", "pliban", "private_key", "pt_driver_license", "rfc", "rg", "ro_driver_license", "se_driver_license", "si_driver_license", "sk_driver_license", "steuerid", "stripe_api_key", "tfn", "triban", "ukdriverlic", "uknhsnum", "uknino", "ukpassport", "ukutr", "us_hicn", "us_mbi", "us_ndc", "usbankaccount", "usdeanumber", "usdriverlic", "usitin", "usnpi", "uspassport", "usssn", "vin", "x509_private_key"], "source": {"path": "data/tools/pii/amazonmacie.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/amazonmacie.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/amazonmacie.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/amazonmacie", "json": "http://registry.apicrafter.io/api/v1/tools/amazonmacie.json"}}, {"id": "ataccama", "name": "Ataccama ONE", "category": "catalogs", "doc": "Ataccama ONE classifies catalog items and attributes by assigning business glossary terms to them. Detection rules attached to a term decide when it applies: metadata rules check attribute names and descriptions, and data rules check values against masks, regular expressions, value lists or reference catalog items. The documentation says the platform ships some preconfigured terms and default detection rules for initial data discovery, but it does not list them.", "website": "https://docs.ataccama.com/one/latest/terms/terms.html", "supported_types": [], "source": {"path": "data/tools/catalogs/ataccama.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/ataccama.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/ataccama.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/ataccama", "json": "http://registry.apicrafter.io/api/v1/tools/ataccama.json"}}, {"id": "auctus", "name": "Auctus", "category": "other", "doc": "This project is a web crawler and search engine for datasets, specifically meant for data augmentation tasks in machine learning. It is able to find datasets in different repositories and index them for later retrieval.", "website": "https://gitlab.com/ViDA-NYU/auctus/auctus", "supported_types": ["datetime", "id", "latitude", "longitude", "geopoint", "address", "url", "filename", "boolean"], "source": {"path": "data/tools/other/auctus.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/auctus.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/auctus.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/auctus", "json": "http://registry.apicrafter.io/api/v1/tools/auctus.json"}}, {"id": "autotype", "name": "Auto-Type", "category": "detector", "doc": "Auto-Type is a research system from Microsoft Research, published at SIGMOD 2018, that builds type-detection functions for rich semantic types. Given a type name and a few example values, it searches open-source code on GitHub for functions that parse or validate the type and synthesizes a detector from them. Its benchmark covers 112 types in 142 test cases. The registry maps the test cases in mappings.autotype, and this list contains the records that have such a mapping.", "website": "https://github.com/congy/AutoType", "supported_types": ["abaroutingnum", "address", "asin", "bankcard", "bibcode", "ca_fsa", "casrn", "countrycode_alpha2", "cusip", "date", "datetime", "dbsnp_id", "doi", "ean", "edifact_message_type", "email", "ensembl_id", "geopoint", "gln", "gtin", "hexcolor", "hslcolor", "http_status_code", "iataairportcode", "iban", "icd10", "icd9", "idcard", "imei", "imonumber", "inchl", "ipv4", "ipv6", "isan", "isbn10", "isin", "ismn", "iso4217curcode", "isrc", "issn", "iswc", "lcc", "lei", "mac_address", "md5hash", "medication_generic_name", "mgrs", "molformula", "money", "monthday", "msisdn", "nanpphone", "orcid", "p2pkhaddr", "person_fullname", "phone", "rgbcolor", "roman_numeral", "sedol", "sha1hash", "sha256hash", "smiles", "street_address", "swiftcode", "tickersymbol", "time", "uic_wagon_number", "uknhsnum", "ukpostalcode", "uniprot_id", "unixtime", "upc", "url", "usdeanumber", "usein", "user_agent", "usnpi", "usssn", "usstate", "uszipcode", "uuid", "vin", "yearmonth"], "source": {"path": "data/tools/detectors/autotype.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/autotype.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/autotype.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/autotype", "json": "http://registry.apicrafter.io/api/v1/tools/autotype.json"}}, {"id": "awscomprehend", "name": "Amazon Comprehend", "category": "pii", "doc": "Amazon Comprehend is an AWS natural language processing service. Its PII detection (the DetectPiiEntities API and asynchronous batch jobs) finds personal data in English or Spanish text and can redact it; each finding has an entity type, character offsets and a confidence score. The entity types are universal ones such as names, addresses, card numbers, credentials and network identifiers, plus a few country-specific identifiers for Canada, India, the UK and the US. The list is in the Comprehend developer guide.", "website": "https://docs.aws.amazon.com/comprehend/latest/dg/how-pii.html", "supported_types": ["aadhaar", "aba", "abaroutingnum", "address", "age", "aws_access_key_id", "aws_secret_access_key", "bankcard", "bankcard_cvv", "bankcard_expiry", "bic", "casin", "date", "datetime", "driver_license", "email", "iban", "in_epic", "ipv4", "mac_address", "nhsnumber", "pan", "password", "person_fullname", "phone", "swiftcode", "uknhsnum", "uknino", "ukutr", "url", "usbankaccount", "username", "usitin", "uspassport", "usssn", "vehiclenumber", "vin"], "source": {"path": "data/tools/pii/awscomprehend.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/awscomprehend.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/awscomprehend.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/awscomprehend", "json": "http://registry.apicrafter.io/api/v1/tools/awscomprehend.json"}}, {"id": "awsglue", "name": "AWS Glue Sensitive Data Detection", "category": "pii", "doc": "AWS Glue Sensitive Data Detection, used through the Detect PII transform in AWS Glue Studio or from ETL scripts, finds personal and other sensitive data in datasets. It can scan every cell or a sample of rows to label whole columns, and it can redact, partially redact or hash the values it found. AWS manages a list of predefined data types: a few universal ones such as person names, email, IP and MAC addresses, US types such as SSN, ITIN and medical codes, and identity, passport, driver's license, tax and VAT numbers for about sixty other countries and territories. Users can add their own types defined by a regular expression and context words.", "website": "https://docs.aws.amazon.com/glue/latest/dg/sensitive-data-managed-data-types.html", "supported_types": ["aadhaar", "abn", "at_driver_license", "at_passport", "at_tin", "at_vat", "at_vnr", "au_driver_license", "auabn", "auacn", "aumedicarenum", "aupassport", "autfn", "bankaccount", "bankcard", "be_driver_license", "be_passport", "be_vat", "benatcardid", "bg_driver_license", "bg_egn", "bg_vat", "brcpf", "bsn", "ca_pr_card", "cadriverlic", "capassport", "casin", "chahv", "chpassport", "cl_rut", "clabe", "cnpj", "co_nit", "cpf", "cptcode", "cuit", "curp", "cy_driver_license", "cy_id_card", "cy_passport", "cy_tin", "cy_vat", "cz_dic", "cz_driver_license", "cz_rc", "de_passport", "dedriverlic", "deust", "dk_driver_license", "dkcprnum", "ee_driver_license", "ee_ik", "ee_kmkr", "ee_passport", "email", "es_ccc", "es_dni", "es_nss", "esdriverlic", "esnie", "esnif", "espassport", "esvat", "fi_alv", "fi_driver_license", "fi_hetu", "fi_passport", "fr_driver_license", "fr_health_insurance_number", "fr_nif", "frcni", "frnir", "frpassport", "frvat", "gb_electoral_roll_number", "gb_vat", "gr_amka", "gr_driver_license", "gr_passport", "gr_vat", "hk_hkid", "hr_driver_license", "hr_oib", "hr_passport", "hu_anum", "hu_driver_license", "hu_passport", "hu_taj", "hu_tin", "idcard", "idnik", "ie_driver_license", "ie_passport", "ie_pps", "ie_vat", "il_idnr", "ipaddr", "is_kennitala", "is_vsk", "it_codicefiscale", "it_driver_license", "it_iva", "it_passport", "jp_bank_account", "jp_driver_license", "jp_passport", "krpassport", "krrrn", "lt_asmens", "lt_driver_license", "lt_pvm", "lu_driver_license", "lu_matricule", "lu_passport", "lu_tva", "lv_driver_license", "lv_passport", "lv_personal_code", "lv_pvn", "mac_address", "medicare", "mt_driver_license", "mt_id_card", "mt_tin", "mt_vat", "my_nric", "mynumber", "nhsnumber", "nif", "nl_driver_license", "nl_passport", "nlbtw", "no_fodselsnummer", "no_mva", "npi", "nric", "nz_driver_license", "nz_ird", "nz_nhi", "pan", "person_fullname", "ph_passport", "phone", "pldriverlic", "plnip", "plpassport", "plregon", "pt_driver_license", "pt_nif", "pt_passport", "rfc", "ro_cf", "ro_cnp", "ro_driver_license", "ro_passport", "se_driver_license", "se_vat", "sepassport", "sepersonnummer", "sg_uen", "sgnric", "si_ddv", "si_driver_license", "si_emso", "si_passport", "si_tin", "sk_dph", "sk_driver_license", "sk_passport", "sk_rc", "steuerid", "tfn", "thidcard", "thpassport", "trpassport", "trtckimlik", "tw_national_id", "tw_passport", "ua_intpassport", "ua_passport", "ukdriverlic", "uknhsnum", "uknino", "ukpassport", "uksortcode", "ukutr", "us_hicn", "us_mbi", "us_ndc", "usatin", "usdeanumber", "usdriverlic", "usitin", "usnpi", "uspassport", "usptin", "usssn", "za_id"], "source": {"path": "data/tools/pii/awsglue.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/awsglue.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/awsglue.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/awsglue", "json": "http://registry.apicrafter.io/api/v1/tools/awsglue.json"}}, {"id": "azureailanguage", "name": "Azure AI Language PII detection", "category": "pii", "doc": "Azure AI Language (now named Azure Language in Foundry Tools) has a PII detection API that uses NLP models to find personal data in text and conversation transcripts and can redact it. Callers pick entity types with the piiCategories request parameter. The types cover people, contact and location data, dates, financial identifiers, Azure credentials and connection strings, and a long list of country-specific government identifiers, many of which share names with Microsoft Purview sensitive information types. The list is on the Learn page of recognized PII entities.", "website": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/concepts/entity-categories", "supported_types": ["aadhaar", "aba", "abaroutingnum", "abn", "address", "age", "ardni", "at_tin", "at_vat", "au_bank_account", "au_driver_license", "auabn", "auacn", "aumedicarenum", "aupassport", "autfn", "azure_storage_account_key", "bankaccount", "bankcard", "bankcard_cvv", "bankcard_expiry", "be_vat", "benatcardid", "bg_egn", "bic", "birthday", "brcpf", "bsn", "ca_bank_account", "ca_phin", "cabcphn", "cadriverlic", "capassport", "casin", "chahv", "city", "cl_rut", "cnpj", "connection_string", "cpf", "cy_id_card", "cy_tin", "cz_rc", "date", "de_passport", "dedriverlic", "depersonalausweis", "deust", "dkcprnum", "driver_license", "ee_ik", "email", "es_dni", "es_nss", "esnif", "fi_ehic", "fi_hetu", "fi_passport", "fr_driver_license", "fr_health_insurance_number", "fr_nif", "frcni", "frnir", "frpassport", "frvat", "gb_electoral_roll_number", "geopoint", "gr_id_card", "gr_vat", "hk_hkid", "hr_id_card", "hr_oib", "hu_anum", "hu_personal_id", "hu_tin", "iban", "idcard", "idnik", "ie_pps", "il_bank_account", "il_idnr", "ipaddr", "it_codicefiscale", "it_driver_license", "it_iva", "jp_bank_account", "jp_cn", "jp_driver_license", "jp_passport", "jp_pension_number", "jp_residence_card", "jp_resident_registration_number", "krdriverlic", "krpassport", "krrrn", "lt_asmens", "lu_matricule", "lu_matricule_entity", "lv_personal_code", "medicare", "mt_id_card", "mt_tin", "my_nric", "mynumber", "nhsnumber", "nif", "nlbtw", "no_fodselsnummer", "nric", "nz_bankaccount", "nz_driver_license", "nz_ird", "nz_nhi", "nz_swn", "orgname", "pan", "passport", "password", "person_fullname", "ph_umid", "phone", "pl_id_card", "plpassport", "plpesel", "plregon", "pt_cc", "pt_nif", "rg", "ro_cnp", "ruintpassport", "rupassport", "said", "sepassport", "sepersonnummer", "sgnric", "shared_access_signature", "si_emso", "si_tin", "sk_rc", "steuerid", "swiftcode", "tfn", "thidcard", "trtckimlik", "tw_arc", "tw_national_id", "tw_passport", "ua_intpassport", "ua_passport", "ukdriverlic", "uknhsnum", "uknino", "ukpassport", "uksortcode", "ukutr", "url", "us_mbi", "usbankaccount", "usdeanumber", "usdriverlic", "usitin", "uspassport", "usssn", "vehiclenumber", "vin", "za_id"], "source": {"path": "data/tools/pii/azureailanguage.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/azureailanguage.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/azureailanguage.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/azureailanguage", "json": "http://registry.apicrafter.io/api/v1/tools/azureailanguage.json"}}, {"id": "bigid", "name": "BigID", "category": "pii", "doc": "BigID is a data security and privacy platform that discovers and classifies sensitive data in structured and unstructured data sources. It uses regular-expression classifiers, NER and other machine-learning classifiers, and document classifiers, and users can add their own. The catalog of built-in classifiers is shown inside the product and is not published in public documentation.", "website": "https://bigid.com/data-classification/", "supported_types": [], "source": {"path": "data/tools/pii/bigid.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/bigid.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/bigid.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/bigid", "json": "http://registry.apicrafter.io/api/v1/tools/bigid.json"}}, {"id": "collibra", "name": "Collibra Data Classification", "category": "catalogs", "doc": "Collibra suggests data classes for catalog columns with classification rules: regular expressions on column names or values, lists of values and data type checks, applied to a sample of the column with a minimum confidence threshold. Collibra publishes a set of out-of-the-box data classes that stewards can import into their environment as a starting point and then edit. The set covers US identifiers such as SSN, EIN, ITIN and DEA numbers, card and bank numbers, securities codes, several date and time formats, Italian identifiers, and common personal attributes. The documentation lists each class with a description and an example value.", "website": "https://productresources.collibra.com/docs/collibra/latest/Content/Catalog/DataClassification/UnifiedDataClassification/co_ootb-data-classes.htm", "supported_types": ["aadhaar", "aba", "abaroutingnum", "bankcard", "bankcard_cvv", "bic", "ca_postcode", "city", "country", "cusip", "date", "datetime", "dayofweek", "email", "fqdn", "gender", "honorificprefix", "iban", "icd10", "icd9", "imei", "ipaddr", "isbn", "isbn10", "isbn13", "isin", "iso4217curcode", "it_codicefiscale", "it_id_card", "it_iva", "it_postcode", "jobtitle", "language", "latitude", "longitude", "mac_address", "marital_status", "miccode", "money", "month", "namesuffix", "nhsnumber", "npi", "pan", "passport", "password", "percentage", "person_firstname", "person_surname", "phone", "race_ethnicity", "religion", "ric", "sedol", "street_address", "swiftcode", "temperature", "tickersymbol", "time", "ukdriverlic", "uknhsnum", "ukpostalcode", "url", "us_ndc", "usatin", "usdeanumber", "usdriverlic", "usein", "usitin", "usnpi", "usptin", "usssn", "usstate", "uszipcode", "utctimezoneoffset", "uuid", "vehiclenumber", "vin"], "source": {"path": "data/tools/catalogs/collibra.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/collibra.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/collibra.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/collibra", "json": "http://registry.apicrafter.io/api/v1/tools/collibra.json"}}, {"id": "csvdetective", "name": "csv-detective", "category": "detector", "doc": "Python package by the data.gouv.fr team that detects what the columns of a tabular file (CSV, Excel, ODS, Parquet) contain. For each column it combines checks of the values (regular expressions, casting, comparison with official lists) with hints from the header. Version 0.13.0 has 55 formats: generic ones such as dates, emails, URLs, UUIDs and WGS 84 or Lambert-93 coordinates, and many French ones such as SIREN, SIRET, INSEE commune and department codes, postal codes, UAI school codes, RNA association numbers, NAF activity codes, FANTOIR street codes and RNB building identifiers; several of them use the frformat library. udata-hydra runs it on the tabular files published on data.gouv.fr. Formats without a registry datatype (int, float, json, binary, canton names, socio-professional categories and historical association numbers) are not listed. Released under the MIT license.", "website": "https://github.com/datagouv/csv-detective", "supported_types": ["address", "boolean", "country", "countrycode_alpha2", "countrycode_alpha3", "countrycode_num", "date", "datetime", "dayofweek", "easting", "email", "epcicode", "fr_commune", "fr_department", "fr_department_code", "fr_naf", "fr_region", "fr_region_code", "fr_rivoli", "fr_rna", "fr_rnb_id", "fr_uai", "frpostcode", "gender", "geojson", "geopoint", "inseecode", "latitude", "longitude", "money", "mongodbid", "month", "northing", "percentage", "phone", "siren", "siret", "url", "username", "uuid", "year"], "source": {"path": "data/tools/detectors/csvdetective.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/csvdetective.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/csvdetective.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/csvdetective", "json": "http://registry.apicrafter.io/api/v1/tools/csvdetective.json"}}, {"id": "databricks", "name": "Databricks Unity Catalog data classification", "category": "pii", "doc": "Data classification in Databricks Unity Catalog scans the tables of a catalog with an AI agent and tags columns with classes such as class.email_address, class.iban_code or class.us_ssn. Global classes apply everywhere; regional classes for national identifiers are detected only in the matching cloud regions.", "website": "https://docs.databricks.com/aws/en/data-governance/unity-catalog/data-classification-tags", "supported_types": ["aadhaar", "aeemiratesid", "age", "aumedicarenum", "autfn", "bankaccount", "bankcard", "bankcard_cvv", "bankcard_expiry", "bic", "birthday", "brcpf", "bsn", "ca_pr_card", "casin", "chahv", "cif", "cnpj", "cpf", "curp", "depersonalausweis", "dkcprnum", "driver_license", "email", "es_dni", "esnie", "fr_nif", "frcni", "frnir", "gender", "geopoint", "hk_hkid", "iban", "idcard", "il_idnr", "imei", "in_epic", "ipaddr", "it_codicefiscale", "it_id_card", "it_iva", "jp_pension_number", "krbusinessreg", "krrrn", "mac_address", "marital_status", "medicare", "mynumber", "nhsnumber", "no_fodselsnummer", "npi", "nric", "nz_ird", "nz_nhi", "nz_nzbn", "pan", "passport", "person_fullname", "phone", "race_ethnicity", "religion", "rfc", "rg", "sepersonnummer", "sgnric", "steuerid", "street_address", "swiftcode", "tfn", "uknhsnum", "uknino", "uksortcode", "ukutr", "url", "usbankaccount", "usdriverlic", "usitin", "usnpi", "uspassport", "usssn", "vehiclenumber", "vin", "za_id"], "source": {"path": "data/tools/pii/databricks.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/databricks.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/databricks.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/databricks", "json": "http://registry.apicrafter.io/api/v1/tools/databricks.json"}}, {"id": "datahub", "name": "DataHub classification", "category": "catalogs", "doc": "DataHub can classify table columns during ingestion and attach a glossary term for each detected info type. The built-in classifier comes from the acryl-datahub-classify library: it scores a column by its name, description, data type and sample values, using regular expressions, spaCy named entities or the schwifty library. Its default configuration in reference_input.py defines 14 info types, such as Email_Address, IBAN, Swift_Code and US_Social_Security_Number. Recent acryl-datahub releases no longer include this built-in classifier.", "website": "https://github.com/acryldata/datahub-classify/blob/main/datahub-classify/src/datahub_classify/reference_input.py", "supported_types": ["address", "age", "bankcard", "bic", "email", "gender", "iban", "ipv4", "ipv6", "person_fullname", "phone", "swiftcode", "usdriverlic", "usssn", "vin"], "source": {"path": "data/tools/catalogs/datahub.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/datahub.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/datahub.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/datahub", "json": "http://registry.apicrafter.io/api/v1/tools/datahub.json"}}, {"id": "dataiku", "name": "Dataiku DSS", "category": "other", "doc": "Dataiku DSS is a platform for data preparation, analytics and machine learning. Every column of a dataset has a meaning, which DSS infers from a sample of the values and uses to count invalid values and to suggest preparation steps. Built-in meanings include basic ones, such as Boolean and Date only, geospatial ones, such as Geopoint, Country and US State, and web ones, such as IP address, URL, User Agent and E-Mail address. The list is in the DSS reference documentation, and users can also define their own meanings.", "website": "https://doc.dataiku.com/dss/latest/schemas/meanings-list.html", "supported_types": ["boolean", "country", "date", "datetime", "email", "encountryname", "geopoint", "ipaddr", "ipv4", "ipv6", "latitude", "longitude", "url", "user_agent", "usstate", "wkt"], "source": {"path": "data/tools/other/dataiku.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/dataiku.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/dataiku.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/dataiku", "json": "http://registry.apicrafter.io/api/v1/tools/dataiku.json"}}, {"id": "dataprep", "name": "DataPrep", "category": "etl", "doc": "DataPrep is an open-source Python library for data preparation from the SFU Database Group. Its clean module standardises and validates the values of a DataFrame column: national identifiers, tax and VAT numbers, company registration numbers, bank account numbers and product, publication and securities codes (most of them checked with python-stdnum), as well as email addresses, phone numbers, URLs, IP addresses, dates, coordinates, countries and addresses.", "website": "https://github.com/sfu-db/dataprep", "supported_types": ["aadhaar", "ad_nrt", "address", "al_nipt", "ar_cbu", "ardni", "at_vat", "at_vnr", "auabn", "auacn", "autfn", "be_iban", "be_vat", "bg_egn", "bg_pnf", "bg_vat", "bic", "brcpf", "bsn", "by_unp", "cabn", "casin", "casrn", "ch_esr", "chahv", "chuid", "cif", "cl_rut", "cnpj", "co_nit", "country", "cr_cpf", "cr_cpj", "cr_cr", "cu_ni", "cuit", "curp", "currency", "cusip", "cy_vat", "cz_dic", "cz_rc", "date", "datetime", "de_stnr", "de_wkn", "deust", "dk_cvr", "dkcprnum", "do_cedula", "do_ncf", "do_rnc", "ean", "ec_ci", "ec_ruc", "ee_ik", "ee_kmkr", "ee_registrikood", "email", "es_ccc", "es_cups", "es_dni", "es_iban", "es_referenciacatastral", "esnie", "esnif", "eu_at_02", "eu_banknote", "eu_eic", "eu_nace", "fi_alv", "fi_associationid", "fi_hetu", "fi_veronumero", "fi_ytunnus", "figi", "fr_nif", "frnir", "frvat", "gb_upn", "gb_vat", "geopoint", "gr_amka", "gr_vat", "grid_release", "gt_nit", "handelsregisternr", "hr_oib", "hu_anum", "iban", "idcard", "idnpwp", "ie_pps", "ie_vat", "il_hp", "il_idnr", "imei", "imonumber", "imsi", "ipaddr", "ipv4", "ipv6", "is_kennitala", "is_vsk", "isan", "isbn10", "isbn13", "isil", "isin", "ismn", "issn", "it_aic", "it_codicefiscale", "it_iva", "jp_cn", "krbusinessreg", "krrrn", "lei", "li_peid", "lt_asmens", "lt_pvm", "lu_tva", "lv_pvn", "mc_tva", "md_idno", "me_iban", "meid", "mt_vat", "mu_nid", "my_nric", "nl_brin", "nl_onderwijsnummer", "nl_postcode", "nlbtw", "no_fodselsnummer", "no_iban", "no_kontonr", "no_mva", "no_orgnr", "nz_bankaccount", "nz_ird", "p2pkhaddr", "p2shaddr", "p2wpkhaddr", "p2wshaddr", "pan", "pe_cui", "pe_ruc", "phone", "plnip", "plpesel", "plregon", "pt_nif", "py_ruc", "rfc", "ro_cf", "ro_cnp", "ro_cui", "ro_onrc", "sedol", "sirencode", "siretcode", "steuerid", "swiftcode", "taxid", "uknhsnum", "ukutr", "url", "vatin"], "source": {"path": "data/tools/etl/dataprep.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/etl/dataprep.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/etl/dataprep.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/dataprep", "json": "http://registry.apicrafter.io/api/v1/tools/dataprep.json"}}, {"id": "dataprofiler", "name": "Capital One DataProfiler", "category": "detector", "doc": "DataProfiler is an open source Python library from Capital One that profiles datasets and detects sensitive data. Its data labeler is a character-level neural model that predicts an entity label for each cell of structured data, and the profiler aggregates these predictions into a label for the column. The default structured labeler has 23 labels, such as EMAIL_ADDRESS, CREDIT_CARD, SSN, IPV4 and US_STATE; the list is in the label_mapping.json resource of the structured model and on the data labeling page of the docs.", "website": "https://capitalone.github.io/DataProfiler/data_labeling.html", "supported_types": ["address", "bankaccount", "bankcard", "date", "datetime", "driver_license", "email", "ipv4", "ipv6", "mac_address", "person_fullname", "phone", "time", "url", "usssn", "usstate", "uuid"], "source": {"path": "data/tools/detectors/dataprofiler.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/dataprofiler.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/dataprofiler.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/dataprofiler", "json": "http://registry.apicrafter.io/api/v1/tools/dataprofiler.json"}}, {"id": "detectsecrets", "name": "detect-secrets", "category": "detector", "doc": "detect-secrets is an open-source (Apache-2.0) secret scanner from Yelp, built to stop new secrets from entering a code base: it records known findings in a baseline file and is usually run as a pre-commit hook. Its plugins find secrets with service-specific regular expressions, with keywords such as password in assignments and with string entropy, and some plugins can verify a secret with the service. The plugins are in detect_secrets/plugins/ of the repository; the list of supported types covers only the registry datatypes that match a plugin.", "website": "https://github.com/Yelp/detect-secrets", "supported_types": ["aws_access_key_id", "aws_secret_access_key", "azure_storage_account_key", "github_token", "gitlab_pat", "ipv4", "jfrog_api_key", "jwt", "mailchimp_api_key", "npm_access_token", "openai_api_key", "pgp_private_key_block", "pypi_token", "sendgrid_api_key", "slack_token", "slack_webhook_url", "square_oauth_secret", "stripe_api_key", "telegram_bot_token", "twilio_api_key_sid", "uri_with_password", "x509_private_key"], "source": {"path": "data/tools/detectors/detectsecrets.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/detectsecrets.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/detectsecrets.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/detectsecrets", "json": "http://registry.apicrafter.io/api/v1/tools/detectsecrets.json"}}, {"id": "doduo", "name": "Doduo", "category": "detector", "doc": "Doduo is a research model from Megagon Labs, published at SIGMOD 2022, that predicts the semantic type of every column of a table and the relation between pairs of columns. It fine-tunes a BERT language model on the whole table written out as one sequence, so the values of the other columns help to type each column. The repository ships two pretrained models: one trained on WikiTable data from TURL, with 255 Freebase column types, and one trained on VizNet data from Sato, with the same 78 semantic types as Sherlock and Sato, such as birthDate or fileSize. The registry maps the VizNet types through mappings.sherlock, so this list is the same as the one of the sherlock and sato tools. The code is released under the Apache 2.0 license.", "website": "https://github.com/megagonlabs/doduo", "supported_types": ["address", "age", "birthday", "birthplace", "brand", "category", "city", "comment", "continent", "country", "currency", "dc_creator", "dc_publisher", "description", "duration", "elevation", "filesize", "gender", "genre", "industry", "isbn", "language", "name", "nationality", "orgname", "person_fullname", "religion", "species", "weight", "year"], "source": {"path": "data/tools/detectors/doduo.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/doduo.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/doduo.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/doduo", "json": "http://registry.apicrafter.io/api/v1/tools/doduo.json"}}, {"id": "fta", "name": "FTA (Fast Text Analysis)", "category": "detector", "doc": "Java library by Tim Segall that profiles a stream of values and infers its base type, format and semantic type, for example EMAIL, IDENTITY.VAT_FR or POSTAL_CODE.ZIP5_US. It ships about 260 semantic types, many of them for specific locales. The registry records that FTA detects carry the FTA name in mappings.fta; this list is derived from them.", "website": "https://github.com/tsegall/fta", "supported_types": ["aadhaar", "abaroutingnum", "address", "address_line2", "age", "age_range", "airlinename", "at_postcode", "at_vat", "au_postcode", "au_state", "au_state_code", "au_suburb", "bg_postcode", "birth_year", "birthday", "br_municipality", "br_municipality_code", "br_postcode", "br_state", "br_state_code", "bsn", "buildingnumber", "ca_postcode", "caprovince", "caprovincecode", "cardinal_direction", "casin", "ch_canton", "ch_canton_code", "ch_postcode", "chahv", "city", "co_department", "co_municipality", "co_postcode", "color", "continent", "continentcode", "country", "countrycode_alpha2", "countrycode_alpha3", "cryptocurrency", "currency", "cusip", "dayofmonth", "dayofweek", "de_postcode", "de_state", "decountryname", "district", "dk_postcode", "duns", "ean", "easting", "ec_province", "email", "encountryname", "ennationality", "es_province", "espostcode", "esvat", "fi_postcode", "file_extension", "filename", "fips52", "fips64", "fr_department", "fr_region", "frnir", "frpostcode", "frvat", "gb_county", "gb_vat", "gender", "geojson", "geopoint", "half_year", "hexcolor", "honorificprefix", "hu_county", "ianatimezoneid", "iataairlinecode", "iataairportcode", "iban", "id", "ie_county", "ie_province", "imei", "in_postcode", "industry", "inseecode", "ipv4", "ipv6", "isbn13", "isin", "iso3166_mx3a", "iso3166code", "iso4217curcode", "iso4217curname", "iso639_1", "iso639_2", "it_comune", "it_iva", "it_postcode", "it_province", "it_province_code", "it_region", "jobtitle", "jp_postcode", "jp_prefecture_code", "jp_region", "language", "latitude", "longitude", "mac_address", "marital_status", "month", "mx_municipality", "mx_postcode", "mxstate", "mynumber", "naicscode", "namesuffix", "nationality", "nl_municipality", "nl_municipality_code", "nl_postcode", "nl_province", "nlbtw", "no_postcode", "northing", "orgname", "payment_card_brand", "pe_province", "pe_region", "person_firstname", "person_fullname", "person_midname", "person_surname", "phone", "plnip", "plpostcode", "prefecture", "pt_district", "pt_postcode", "quarter", "race_ethnicity", "ro_postcode", "ruscountryname", "ruspostalcode", "se_postcode", "sedol", "sepersonnummer", "sha1hash", "sha256hash", "state", "street", "street_address", "street_suffix", "tz_region", "uknhsnum", "uknino", "ukpostalcode", "unixtime", "upc", "url", "uscounty", "usein", "usnpi", "usssn", "usstate", "uszipcode", "uuid", "uy_postcode", "vin", "wkt", "year_range", "za_province", "za_province_code"], "source": {"path": "data/tools/detectors/fta.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/fta.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/fta.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/fta", "json": "http://registry.apicrafter.io/api/v1/tools/fta.json"}}, {"id": "gitleaks", "name": "Gitleaks", "category": "detector", "doc": "Open-source (MIT) secret scanner that finds hard-coded credentials, such as API keys, access tokens and private keys, in git history, directories and standard input. Its rules combine regular expressions with keywords and entropy checks. The list of supported types covers only the registry datatypes that match a gitleaks rule.", "website": "https://github.com/gitleaks/gitleaks", "supported_types": ["age_secret_key", "anthropic_api_key", "atlassian_api_token", "aws_access_key_id", "cloudflare_origin_ca_key", "databricks_access_token", "digitalocean_token", "doppler_token", "dynatrace_token", "facebook_app_access_token", "github_fine_grained_pat", "github_token", "gitlab_pat", "google_api_key", "grafana_service_account_token", "hashicorp_vault_token", "heroku_oauth_token", "huggingface_access_token", "jfrog_api_key", "jfrog_reference_token", "jwt", "linear_api_key", "mailchimp_api_key", "new_relic_user_api_key", "npm_access_token", "onepassword_service_account_token", "openai_api_key", "pgp_private_key_block", "planetscale_password", "planetscale_token", "postman_api_key", "pulumi_access_token", "pypi_token", "rubygems_api_key", "sendgrid_api_key", "sendinblue_api_key", "sentry_auth_token", "shopify_access_token", "shopify_shared_secret", "slack_token", "slack_webhook_url", "sonarqube_token", "square_access_token", "stripe_api_key", "telegram_bot_token", "terraform_cloud_api_token", "twilio_api_key_sid", "x509_private_key"], "source": {"path": "data/tools/detectors/gitleaks.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/gitleaks.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/gitleaks.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/gitleaks", "json": "http://registry.apicrafter.io/api/v1/tools/gitleaks.json"}}, {"id": "googledatastudio", "name": "Google Data Studio", "category": "other", "doc": "With Data Studio, you can easily report on data from a wide variety of sources, without programing. In just a few moments, you can connect to data sets such as: Databases, including BigQuery, MySQL, and PostgreSQL. Google Marketing Platform products, including Google Ads, Analytics, Display & Video 360, Search Ads 360.", "website": "https://developers.google.com/datastudio/connector/semantics#semantic-type-detection", "supported_types": ["geopoint", "country", "city", "datetime", "time", "address", "person_name", "year", "date", "month", "day", "dayofweek", "boolean", "url"], "source": {"path": "data/tools/other/googledatastudio.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/googledatastudio.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/googledatastudio.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/googledatastudio", "json": "http://registry.apicrafter.io/api/v1/tools/googledatastudio.json"}}, {"id": "googledlp", "name": "Google Cloud Sensitive Data Protection (DLP)", "category": "pii", "doc": "Google Cloud Sensitive Data Protection, formerly Cloud DLP, inspects text, files, BigQuery and Cloud Storage with built-in infoType detectors: names, contact details, credentials, financial data, medical codes and national identifiers of many countries. Findings can be masked, tokenized or redacted. Each registry record lists the matching infoType names in mappings.google_dlp.", "website": "https://cloud.google.com/sensitive-data-protection/docs/infotypes-reference", "supported_types": ["aadhaar", "aumedicarenum", "autfn", "bankcard", "be_eid", "bic", "brcpf", "bsn", "capassport", "casin", "cpf", "curp", "cz_passport", "cz_rc", "de_passport", "dedriverlic", "depersonalausweis", "dkcprnum", "email", "es_dni", "esnif", "espassport", "euvat", "fi_hetu", "fqdn", "frcni", "frnir", "frpassport", "iban", "icd10", "imei", "ipaddr", "it_codicefiscale", "jp_driver_license", "jp_passport", "mac_address", "medicare", "mynumber", "nhsnumber", "nif", "nl_passport", "no_fodselsnummer", "npi", "nric", "pan", "person_fullname", "phone", "plpesel", "sepersonnummer", "sgnric", "steuerid", "swiftcode", "uknhsnum", "uknino", "ukpassport", "ukutr", "url", "usdeanumber", "usdriverlic", "usein", "user_agent", "usitin", "usnpi", "uspassport", "usssn", "vatin"], "source": {"path": "data/tools/pii/googledlp.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/googledlp.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/googledlp.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/googledlp", "json": "http://registry.apicrafter.io/api/v1/tools/googledlp.json"}}, {"id": "greatexpectations", "name": "Great Expectations Semantic Types Expectations", "category": "other", "doc": "A contributed package of custom expectations for Great Expectations, the Python data validation framework. Each expectation asserts that the values of a column are valid for one semantic type, using a regular expression or a helper library such as python-stdnum, schwifty, phonenumbers, pycountry or geonamescache; a few call online services. The expectations live in the package's expectations folder in the Great Expectations repository and are not part of the core library.", "website": "https://github.com/fivetran/great_expectations/tree/develop/contrib/great_expectations_semantic_types_expectations", "supported_types": ["arxiv_id", "bic", "bitcoin_txid", "city", "colorhextriplet", "country", "countrycode_alpha2", "countrycode_alpha3", "countrycode_num", "cryptocurrency_ticker", "date", "doi", "ean", "email", "encountryname", "ethereum_address", "euvat", "fips10_4", "fips64", "gtin", "hexcolor", "http_status_code", "ianatimezoneid", "iban", "icd10", "imdb_id", "imei", "imsi", "ipv4", "ipv6", "isan", "isbn", "isbn10", "isbn13", "isin", "ismn", "iso4217curcode", "iso639_1", "iso639_2", "language", "mac_address", "md5hash", "meid", "miccode", "mimetype", "openlibid", "orcid", "p2pkhaddr", "p2shaddr", "p2wpkhaddr", "phone", "price", "roman_numeral", "sha1hash", "swiftcode", "temperature", "tld", "upc", "url", "uscounty", "usssn", "usstate", "uuid"], "source": {"path": "data/tools/other/greatexpectations.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/greatexpectations.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/greatexpectations.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/greatexpectations", "json": "http://registry.apicrafter.io/api/v1/tools/greatexpectations.json"}}, {"id": "ibmguardium", "name": "IBM Security Guardium Analyzer", "category": "pii", "doc": "IBM Security Guardium Analyzer is a powerful service that can help you with this data security effort. Simple to use, Guardium Analyzer allows you to set up connections to your data sources - with no need to configure classification or risk scanning.", "website": "https://www.ibm.com/docs/en/sga", "supported_types": ["email", "phone", "bankcard", "address", "person_name", "person_fullname", "person_surname", "person_firstname", "benatcardid", "ipaddr", "usssn", "uknhsnum", "esnif", "aumedicarenum", "autfn", "casin", "sepersonnummer", "es_dni", "esnie", "plpesel", "no_fodselsnummer", "bsn", "jp_passport", "mynumber", "jp_pension_number", "it_iva", "it_codicefiscale", "iban", "depersonalausweis", "frcni", "fi_hetu", "ukdriverlic", "jp_driver_license", "dkcprnum"], "source": {"path": "data/tools/pii/ibmguardium.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/ibmguardium.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/ibmguardium.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/ibmguardium", "json": "http://registry.apicrafter.io/api/v1/tools/ibmguardium.json"}}, {"id": "ibmknowledgecatalog", "name": "IBM Knowledge Catalog (IBM watsonx.data intelligence)", "category": "catalogs", "doc": "IBM Knowledge Catalog, now part of IBM watsonx.data intelligence, assigns data classes to table columns when it profiles data assets. More than 150 predefined data classes ship with the product; each one matches values or column names with a regular expression, a value list or a built-in Java classifier. They cover personal and financial identifiers, US state and Canadian province driver's licenses, codes such as ISO country and language codes, and generic classes such as Code, Identifier and Text. The table of classes and their matching criteria is published in the IBM documentation.", "website": "https://dataplatform.cloud.ibm.com/docs/content/governance/dmg_attr_classifier.html", "supported_types": ["aba", "abaroutingnum", "address_line2", "admin_area_1", "bankcard", "bankcard_cvv", "bankcard_expiry", "bic", "birthday", "boolean", "ca_postcode", "cadriverlic", "caprovince", "caprovincecode", "casin", "city", "color", "country", "countrycode_alpha2", "countrycode_alpha3", "cptcode", "date", "de_vehicle_plate", "duns", "email", "esnif", "frnir", "gender", "geopoint", "honorificprefix", "iataairportcode", "iban", "icd10", "imei", "ipv4", "ipv6", "isbn", "isbn10", "isbn13", "isicrev4", "isin", "iso3166code", "it_codicefiscale", "language", "latitude", "longitude", "mac_address", "marital_status", "money", "month", "namesuffix", "nanpphone", "nif", "orgname", "percentage", "person_firstname", "person_fullname", "person_midname", "person_surname", "race_ethnicity", "religion", "street", "street_address", "swiftcode", "temperature", "uknino", "ukpostalcode", "upc", "url", "us_hicn", "us_ndc", "uscounty", "usdriverlic", "usein", "usitin", "usssn", "usstate", "uszipcode", "vin"], "source": {"path": "data/tools/catalogs/ibmknowledgecatalog.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/ibmknowledgecatalog.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/ibmknowledgecatalog.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/ibmknowledgecatalog", "json": "http://registry.apicrafter.io/api/v1/tools/ibmknowledgecatalog.json"}}, {"id": "informatica", "name": "Informatica Cloud Data Governance and Catalog", "category": "catalogs", "doc": "Informatica Cloud Data Governance and Catalog classifies columns and fields of scanned sources with data element classifications that are configured in Metadata Command Center. A rule-based classification is a Spark SQL expression over column names, comments and profiling results such as frequent values, and it can use lookup tables and reference data. More than 200 predefined rule-based classifications can be imported as predefined content; CLAIRE can also generate classifications from asset names.", "website": "https://onlinehelp.informatica.com/IICS/prod/MCC/en/metadata-command-center-administration/Creating_a_data_element_classification.html", "supported_types": [], "source": {"path": "data/tools/catalogs/informatica.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/informatica.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/informatica.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/informatica", "json": "http://registry.apicrafter.io/api/v1/tools/informatica.json"}}, {"id": "metabase", "name": "Metabase", "category": "other", "doc": "Metabase is a simple and powerful analytics tool which lets anyone learn and make decisions from their company s data no technical knowledge required.", "website": "https://www.metabase.com/docs/latest/users-guide/field-types.html", "supported_types": ["city", "country", "latitude", "longitude", "usstate", "postindex", "birthday", "orgname", "email", "username", "datetime", "time", "date", "url"], "source": {"path": "data/tools/other/metabase.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/metabase.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/metabase.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/metabase", "json": "http://registry.apicrafter.io/api/v1/tools/metabase.json"}}, {"id": "metacrafter", "name": "metacrafter", "category": "detector", "doc": "Python command line tool and python engine to label table fields and fields in data files. It could help to find meaningful data in your tables and data files or to find Personal identifable information (PII). Its supported types are generated from the pinned metacrafter-rules release (data/coverage/metacrafter-rules.json); do not list them here.", "website": "https://github.com/apicrafter/metacrafter", "supported_types": ["aadhaar", "aba", "abaroutingnum", "abn", "acra", "address", "aebankaccount", "aecity", "aeemiratesid", "aeiban", "aepassport", "aepostcode", "aetaxnumber", "am_bank_account", "am_driver_license", "am_org_tin", "am_passport", "am_postal_code", "am_ssn", "am_tin", "am_vehicle_plate", "article_id", "asn", "atccode", "atcity", "authentihash", "awardnotice", "awbnumber", "bankaccount", "bankcard", "bic", "bik", "bip32addr", "birthday", "blake2b256hash", "blake2b512hash", "boolean", "bsb", "bsn", "budgetcode", "budgetname", "build_number", "buildingnumber", "ca_postcode", "cabizlic", "cabn", "cacharity", "cacorp", "cadastralnumber", "caextra", "cagst", "caprogramacct", "cart_id", "case_number", "casin", "category", "catransit", "ccamcode", "cfdanumber", "chahv", "chassis_number", "chbankaccount", "chiban", "chpassport", "chuid", "cif", "city", "clabe", "cnalibabaorder", "cnjdorder", "cnpj", "comment", "comment_id", "commit_hash", "compliance_status", "containernumber", "content_id", "continent", "contract_id", "country", "countrycode_alpha2", "countrycode_alpha3", "cpf", "cptcode", "cpvcode", "crc32", "crypto_address", "csrcode", "cuit", "cupscode", "curp", "cusip", "datasize", "date", "datetime", "day", "dc_contributor", "dc_coverage", "dc_creator", "dc_date", "dc_description", "dc_format", "dc_identifier", "dc_publisher", "dc_relation", "dc_rights", "dc_source", "dc_subject", "dc_type", "dclanguage", "dctitle", "de_iban", "de_rvnr", "de_vehicle_plate", "deathday", "decountryname", "description", "deust", "dhltracking", "district", "document_id", "doi", "duns", "ean", "egbankaccount", "egcity", "egiban", "egnationalid", "egpassport", "egpostcode", "egtaxnumber", "eidr", "email", "emissioninventory", "encompanyname", "encountryname", "endayofweek", "engine_number", "enmonth", "enmonthshort", "ennationality", "epcicode", "esnie", "esnif", "espassport", "espostcode", "esvat", "ethereum_address", "euid", "euvat", "fedextracking", "fedgrbs", "figi", "filename", "filesize", "fips52", "fips64", "firstname", "fqdn", "fr_vehicle_plate", "frcadastral", "frcni", "frnir", "frpassport", "frpropertynumber", "frvat", "gb_vehicle_plate", "gbpostcode", "gbuprn", "gender", "geopoint", "gln", "gmcnumber", "grid", "gridnode", "gtin", "handelsregisternr", "hash", "headline", "hidate", "iataairlinecode", "iataairportcode", "iban", "icaoairlinecode", "icaoairportcode", "iccid", "icd10code", "id", "idbankaccount", "idcard", "idcity", "iddriverlic", "idnik", "idnpwp", "idpassport", "idpostcode", "idprovince", "ifsc", "imei", "imonumber", "imphash", "imsi", "in_reply_to", "inchl", "inchlkey", "indate", "inn", "inseecode", "ipaddr", "ipsubnet", "ipv4", "ipv6", "isbn", "isbn10", "isbn13", "isin", "isni", "isrc", "issn", "kbk", "keccak256hash", "keccak512hash", "kladr", "kosgucode", "kpp", "krbankaccount", "krbusinessreg", "krcity", "krdriverlic", "krpassport", "krpostcode", "krprovince", "krrrn", "krtaxnumber", "kvk", "kvrcode", "languagetag", "lastname", "latitude", "legal_document", "lei", "license_number", "longitude", "loyalty_number", "mac_address", "magnet_link", "md5hash", "medicare", "message_id", "mimetype", "mmsi", "molformula", "mongodbid", "month", "msisdn", "mynumber", "naicscode", "name", "nationality", "ncesid", "nhsnumber", "nif", "nlbtw", "npi", "nric", "nutsregion", "ogrn", "ogrn_ogrnip", "oid", "ojreference", "okato", "okei", "okeiname", "okfs", "okogu", "okopf", "okopfname", "okpo", "oktmo", "oktmoname", "okvalpha", "okved", "okvname", "openalexid", "opscode", "orcid", "order_number", "orgname", "p2pkhaddr", "p2shaddr", "p2wpkhaddr", "p2wshaddr", "package_name", "pan", "parcelnumber", "passport", "password", "percentage", "person_firstname", "person_fullname", "person_midname", "person_name", "person_surname", "phone", "plbankaccount", "plcity", "pldriverlic", "pliban", "plnip", "plpassport", "plpesel", "plpostcode", "plregon", "postcode", "postindex", "powerplantid", "ppocode", "pponame", "prefecture", "private_key", "programminglang", "propertyid", "province", "pubchemid", "references", "researcherid", "rfc", "rg", "richpeheaderhash", "ripemd160hash", "rorid", "rsin", "ru_vehicle_plate", "rudriverlicense", "rueqsecreg", "rufias", "ruikuiko", "ruikz", "ruintpassport", "rukadastr", "rumedicineregnum", "rumedicinetradename", "rumedmnn", "rumosadmareas", "rumosdistricts", "runpa", "runpakind", "rupassport", "rupropertynumber", "rusbankaccount", "ruscity", "ruscountrycode", "ruscountryname", "rusdayofweek", "rusdegree", "rusfeddistrict", "rusfirstname", "rusfullname", "rusmidname", "rusnils", "rusregion", "rusregioncode", "russurname", "rustimerange", "rustreet", "rusworkposition", "sabankaccount", "sacity", "saiban", "said", "saiqama", "sapassport", "sapostcode", "sataxnumber", "scopusauthoirid", "sebankaccount", "semver", "seorgnumber", "sepassport", "sepersonnummer", "sha1hash", "sha256hash", "sha384hash", "sha512hash", "siren", "sirencode", "siret", "siretcode", "sku", "snomedcode", "snowflake_id", "software_license", "ssdeep", "sssc", "state", "steuerid", "street", "street_address", "studentid", "swiftcode", "taxid", "tednoticeid", "telfhash", "tfn", "thbankaccount", "thdriverlic", "thidcard", "thpassport", "thpostcode", "thprovince", "thtaxid", "time", "timerange", "timezone", "tlsh", "tnved", "tofkcode", "tofkname", "torrent_info_hash", "trackingnumber", "transaction_id", "trbankaccount", "trcity", "trdriverlic", "triban", "trpassport", "trpostcode", "trtaxnumber", "trtckimlik", "ukbnfcode", "ukboroughcode", "ukdistrictcode", "ukdriverlic", "ukestablishmentnumber", "ukgsscode", "uklacode", "ukmsoa", "uknhsnum", "uknino", "ukonscode", "ukparishcode", "ukpassport", "ukpostalcode", "ukprn", "uksloa", "uksortcode", "ukurn", "ukutr", "ukwardcode", "ukwardname", "ulid", "unixtime", "unlocode", "upc", "upin", "uprn", "upstracking", "url", "usamazonorder", "usapn", "usatin", "uscity", "usdeanumber", "usdriverlic", "usein", "userhandle", "userid", "username", "useruuid", "usfipsproperty", "usitin", "usnpi", "usorderid", "usparcelnumber", "uspassport", "uspstracking", "usptin", "usssn", "usstate", "uszipcode", "uuid", "vehiclenumber", "version", "vhash", "vimeovideoid", "vin", "vnbankaccount", "vncccd", "vncity", "vndriverlic", "vniban", "vnpassport", "vnpostcode", "vnprovince", "vntaxcode", "wbregion", "wifaddrcomp", "wifaddruncomp", "wikidataid", "winregkey", "year", "youtubevideoid"], "source": {"path": "data/tools/detectors/metacrafter.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/metacrafter.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/metacrafter.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/metacrafter", "json": "http://registry.apicrafter.io/api/v1/tools/metacrafter.json"}}, {"id": "metacrafterpro", "name": "metacrafterpro", "category": "detector", "doc": "Cloud web service based on Metacrafter open source (https://github.com/apicrafter/metacrafter) available for beta testing by request", "website": "https://apicrafter.io/metacrafterpro", "supported_types": ["birthday", "bankcard", "passport", "username", "password", "gender", "nationality", "deathday", "ruintpassport", "rusnils", "boolean", "url", "year", "datetime", "timezone", "month", "day", "timerange", "geopoint", "address", "latitude", "longitude", "country", "city", "street", "postindex", "countrycode_alpha2", "countrycode_alpha3", "languagetag", "mac_address", "ipv4", "ipv6", "ipaddr", "isbn10", "isbn13", "orgname", "person_fullname", "person_surname", "person_firstname", "person_midname", "orcid", "doi", "vehiclenumber", "sha256hash", "sha1hash", "md5hash", "uuid", "runpa", "runpakind", "rusdayofweek", "rustimerange", "rumedmnn", "rumedicinetradename", "rumedicineregnum", "atccode", "budgetcode", "budgetname", "fedgrbs", "kbk", "tofkcode", "tofkname", "ruikuiko", "kvrcode", "csrcode", "kosgucode", "ppocode", "pponame", "okpo", "inn", "ogrn", "kpp", "ogrn_ogrnip", "okopf", "rusworkposition", "rusdegree", "tnved", "okei", "okfs", "okved", "okogu", "okeiname", "okvalpha", "okvname", "okpd", "bankaccount", "bik", "swiftcode", "okato", "oktmo", "oktmoname", "kladr", "rukadastr", "ruscity", "rusregion", "rusfeddistrict", "rumosdistricts", "rusregioncode", "ruscountryname", "ruscountrycode", "rumosadmareas", "uscity", "fips52", "fips64", "encountryname", "endayofweek", "enmonth", "enmonthshort", "ukwardcode", "ukwardname", "encompanyname", "cfdanumber", "naicscode", "ukbnfcode"], "source": {"path": "data/tools/detectors/metacrafterpro.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/metacrafterpro.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/metacrafterpro.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/metacrafterpro", "json": "http://registry.apicrafter.io/api/v1/tools/metacrafterpro.json"}}, {"id": "metadata-guardian", "name": "Metadata Guardian", "category": "pii", "doc": "Metadata Guardian is a Python package that provides an easy way to protect your data sources by searching its metadata. By searching with data rules, it will detect what you are looking to protect. Using Rust, it makes blazing fast multi-regex matching.", "website": "https://github.com/fvaleye/metadata-guardian", "supported_types": ["email", "phone", "ipv4", "ipv6", "ipaddr", "postindex", "address", "person_firstname", "person_surname", "person_fullname", "birthday", "gender", "nationality", "username", "password"], "source": {"path": "data/tools/pii/metadata-guardian.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/metadata-guardian.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/metadata-guardian.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/metadata-guardian", "json": "http://registry.apicrafter.io/api/v1/tools/metadata-guardian.json"}}, {"id": "microsoftpurview", "name": "Microsoft Purview Data Loss Prevention", "category": "pii", "doc": "Microsoft Purview (formerly Microsoft 365 compliance) finds sensitive data in Microsoft 365, endpoints and connected sources with built-in sensitive information types: national identifiers, financial data, credentials, medical terms and addresses. Each registry record lists the matching type names in mappings.purview.", "website": "https://learn.microsoft.com/en-us/purview/sensitive-information-type-entity-definitions", "supported_types": ["aadhaar", "abaroutingnum", "abn", "access_token", "address", "aeemiratesid", "api_key", "ardni", "at_driver_license", "at_passport", "at_tin", "at_vat", "at_vnr", "au_bank_account", "au_driver_license", "auabn", "auacn", "aumedicarenum", "aupassport", "autfn", "aws_secret_access_key", "azure_storage_account_key", "bankcard", "be_driver_license", "be_passport", "be_vat", "benatcardid", "bg_driver_license", "bg_egn", "bg_passport", "bic", "brcpf", "bsn", "ca_bank_account", "ca_phin", "cabcphn", "cadriverlic", "capassport", "casin", "chahv", "cl_rut", "cnpj", "connection_string", "cpf", "cuit", "curp", "cy_driver_license", "cy_id_card", "cy_passport", "cy_tin", "cz_driver_license", "cz_passport", "cz_rc", "de_passport", "dedriverlic", "depersonalausweis", "deust", "dk_driver_license", "dk_passport", "dkcprnum", "ee_driver_license", "ee_ik", "ee_passport", "es_dni", "es_nss", "esdriverlic", "esnif", "espassport", "fi_driver_license", "fi_ehic", "fi_hetu", "fi_passport", "fr_driver_license", "fr_health_insurance_number", "fr_nif", "frcni", "frnir", "frpassport", "frvat", "gb_electoral_roll_number", "github_token", "google_api_key", "gr_amka", "gr_driver_license", "gr_id_card", "gr_passport", "gr_vat", "hk_hkid", "hr_driver_license", "hr_id_card", "hr_oib", "hr_passport", "http_authorization_header", "hu_anum", "hu_driver_license", "hu_passport", "hu_personal_id", "hu_taj", "hu_tin", "iban", "icd10", "idcard", "idnik", "ie_driver_license", "ie_passport", "ie_pps", "il_bank_account", "il_idnr", "in_driver_license", "in_epic", "in_gstin", "inn", "ipaddr", "ipv4", "ipv6", "it_codicefiscale", "it_driver_license", "it_iva", "it_passport", "jp_bank_account", "jp_cn", "jp_driver_license", "jp_passport", "jp_pension_number", "jp_residence_card", "jp_resident_registration_number", "krrrn", "lab_test", "lt_asmens", "lt_driver_license", "lt_passport", "lu_driver_license", "lu_matricule", "lu_matricule_entity", "lu_passport", "lv_driver_license", "lv_passport", "lv_personal_code", "medical_condition", "medical_specialty", "medicare", "medication_brand_name", "medication_class", "medication_generic_name", "mt_driver_license", "mt_id_card", "mt_passport", "mt_tin", "my_nric", "mynumber", "nhsnumber", "nl_driver_license", "nl_passport", "nlbtw", "no_fodselsnummer", "nric", "nz_bankaccount", "nz_driver_license", "nz_ird", "nz_nhi", "nz_swn", "pan", "password", "person_fullname", "ph_passport", "ph_umid", "pl_id_card", "pldriverlic", "plpassport", "plpesel", "plregon", "pt_cc", "pt_driver_license", "pt_nif", "pt_passport", "qa_qid", "rg", "ro_cnp", "ro_driver_license", "ro_passport", "ruintpassport", "rupassport", "said", "se_driver_license", "sepassport", "sepersonnummer", "sgnric", "shared_access_signature", "si_driver_license", "si_emso", "si_passport", "si_tin", "sk_driver_license", "sk_passport", "sk_rc", "slack_token", "steuerid", "surgical_procedure", "swiftcode", "symmetric_key", "tfn", "thidcard", "trtckimlik", "tw_arc", "tw_national_id", "tw_passport", "ua_intpassport", "ua_passport", "ukdriverlic", "uknhsnum", "uknino", "ukpassport", "ukutr", "us_mbi", "usbankaccount", "usdeanumber", "usdriverlic", "user_credentials", "usitin", "uspassport", "usssn", "x509_private_key", "za_id"], "source": {"path": "data/tools/pii/microsoftpurview.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/microsoftpurview.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/microsoftpurview.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/microsoftpurview", "json": "http://registry.apicrafter.io/api/v1/tools/microsoftpurview.json"}}, {"id": "nightfall", "name": "Nightfall AI", "category": "pii", "doc": "Nightfall is a cloud data loss prevention platform that scans SaaS applications, endpoints and API payloads for sensitive data. Its built-in detectors use machine learning models and pattern rules; each has a detector ID used in API requests and policies, and findings come with a confidence level. The detector glossary covers personal data, national identifiers by region, bank and card numbers, secrets and health data, plus file and image classifiers.", "website": "https://help.nightfall.ai/detection_platform/detection_glossary", "supported_types": ["aadhaar", "aba", "abaroutingnum", "access_token", "address", "api_key", "ardni", "au_bank_account", "au_driver_license", "aubsb", "aumedicarenum", "aupassport", "autfn", "bankaccount", "bankcard", "bic", "birthday", "brcpf", "bsb", "ca_bank_account", "ca_pr_card", "cabcphn", "cadriverlic", "caonohip", "capassport", "casin", "cl_rut", "cnpj", "co_nit", "connection_string", "cpf", "cuit", "curp", "date", "de_passport", "depersonalausweis", "email", "es_dni", "es_nss", "frcni", "frnir", "frpassport", "gb_electoral_roll_number", "geopoint", "github_token", "gitlab_pat", "google_api_key", "hk_hkid", "hu_passport", "iban", "idbankaccount", "iddriverlic", "idnik", "idnpwp", "idpassport", "ie_passport", "ie_pps", "imei", "ipaddr", "jwt", "krbankaccount", "krdriverlic", "krpassport", "krrrn", "mac_address", "medicare", "medication_brand_name", "medication_generic_name", "my_nric", "mynumber", "nanpphone", "nhsnumber", "npi", "nric", "pan", "passport", "password", "pe_cui", "pe_ruc", "person_fullname", "pgp_private_key_block", "ph_passport", "ph_umid", "phone", "private_key", "rfc", "rg", "sendgrid_api_key", "sepassport", "sgnric", "slack_token", "stripe_api_key", "swiftcode", "tfn", "thbankaccount", "thdriverlic", "thidcard", "thpassport", "thtaxid", "tw_arc", "tw_national_id", "tw_passport", "ukdriverlic", "uknhsnum", "uknino", "ukpassport", "ukutr", "us_hicn", "us_mbi", "us_ndc", "usdriverlic", "usein", "usitin", "usnpi", "uspassport", "usssn", "vehiclenumber", "vin", "vnbankaccount", "vncccd", "vndriverlic", "vnpassport", "vntaxcode", "x509_private_key", "za_id"], "source": {"path": "data/tools/pii/nightfall.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/nightfall.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/nightfall.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/nightfall", "json": "http://registry.apicrafter.io/api/v1/tools/nightfall.json"}}, {"id": "openmetadata", "name": "OpenMetadata auto-classification", "category": "catalogs", "doc": "OpenMetadata's auto-classification workflow samples table columns and tags them PII.Sensitive or PII.NonSensitive. It matches column names against regular expressions and checks sampled values with Microsoft Presidio recognizers and a spaCy model. Each PII tag holds a list of recognizers that administrators can change; the default list, seeded from piiTagsWithRecognizers.json, covers card numbers, IBAN, email, IP addresses, phone numbers, person names and national identifiers of the US, UK, Spain, Italy, Poland, Singapore, Australia, India and Finland.", "website": "https://docs.open-metadata.org/latest/how-to-guides/data-governance/classification/auto-classification/auto-pii-tagging", "supported_types": ["aadhaar", "aba", "abaroutingnum", "abn", "auabn", "auacn", "aumedicarenum", "autfn", "bankcard", "bankcard_cvv", "date", "email", "esnie", "esnif", "fi_hetu", "iban", "in_epic", "ipaddr", "it_codicefiscale", "it_driver_license", "it_id_card", "it_iva", "it_passport", "medicare", "nhsnumber", "nif", "nric", "p2pkhaddr", "p2shaddr", "p2wpkhaddr", "p2wshaddr", "pan", "person_fullname", "phone", "plpesel", "sg_uen", "sgnric", "tfn", "uknhsnum", "uknino", "url", "usbankaccount", "usdeanumber", "usdriverlic", "usitin", "uspassport", "usssn"], "source": {"path": "data/tools/catalogs/openmetadata.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/openmetadata.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/openmetadata.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/openmetadata", "json": "http://registry.apicrafter.io/api/v1/tools/openmetadata.json"}}, {"id": "oracleanalyticsdesktop", "name": "Oracle Analytics Desktop", "category": "other", "doc": "Oracle Analytics Desktop is a desktop application for preparing, exploring and visualizing data. When a dataset is created, it profiles each column and detects its semantic type, either from value patterns (dates, US Social Security numbers, credit card numbers, email addresses, North American phone numbers, US addresses) or from the reference data shipped with the product (names and codes of countries and states, county and city names, ZIP codes). It also recognizes first-name and last-name columns. The detected types drive its recommendations to enrich, split, concatenate, mask or delete columns. A column gets a type when at least 85% of its values match it.", "website": "https://docs.oracle.com/en/middleware/bi/analytics-desktop/bidvd/data-profiles-semantic-recommendations.html", "supported_types": ["date", "usssn", "bankcard", "email", "nanpphone", "address", "country", "usstate", "uscounty", "city", "uszipcode", "person_firstname", "person_surname"], "source": {"path": "data/tools/other/oracleanalyticsdesktop.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/oracleanalyticsdesktop.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/oracleanalyticsdesktop.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/oracleanalyticsdesktop", "json": "http://registry.apicrafter.io/api/v1/tools/oracleanalyticsdesktop.json"}}, {"id": "oracledatasafe", "name": "Oracle Data Safe", "category": "pii", "doc": "Oracle Data Safe is a security service for Oracle databases. Its Data Discovery feature finds sensitive columns with sensitive types, each defined by regular expressions over column names, comments and data, and stores the results in a sensitive data model that data masking can reuse. Oracle ships more than 180 predefined sensitive types in categories for identification, biographic, IT, financial, healthcare, employment and academic data, and users can create their own. The complete list of predefined types is shown only in the console; the documentation names some of them as examples, and only those are listed here.", "website": "https://docs.oracle.com/en-us/iaas/data-safe/doc/data-discovery-overview.html", "supported_types": ["address", "bankaccount", "bankcard", "birthday", "casin", "city", "country", "email", "income", "ipaddr", "jobtitle", "orgunit", "password", "person_firstname", "person_fullname", "person_surname", "phone", "postindex", "religion", "userid", "usssn"], "source": {"path": "data/tools/pii/oracledatasafe.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/oracledatasafe.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/oracledatasafe.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/oracledatasafe", "json": "http://registry.apicrafter.io/api/v1/tools/oracledatasafe.json"}}, {"id": "piicatcher", "name": "PII Catcher", "category": "pii", "doc": "PIICatcher is a scanner for PII and PHI information. It finds PII data in your databases and file systems and tracks critical data.", "website": "https://github.com/tokern/piicatcher", "supported_types": ["email", "birthday", "gender", "nationality", "person_fullname", "person_firstname", "lastname", "username", "password", "address", "usssn"], "source": {"path": "data/tools/pii/piicatcher.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/piicatcher.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/piicatcher.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/piicatcher", "json": "http://registry.apicrafter.io/api/v1/tools/piicatcher.json"}}, {"id": "powerbi", "name": "Microsoft Power BI", "category": "other", "doc": "Microsoft Power BI is a business intelligence service with a desktop report editor. In Power BI Desktop the author sets a data category on a column, such as City, Postal code, Latitude, Web URL or Barcode, to tell Power BI how to use its values: geographic categories are sent to Bing Maps for geocoding, Web URL and Image URL turn values into links or pictures, and Barcode lets the mobile app filter a report by a scanned code. The category is set by hand and is not inferred from the values. The categories are described in the Power BI documentation on data categorization, map tips, hyperlinks, images and barcodes.", "website": "https://learn.microsoft.com/en-us/power-bi/transform-model/desktop-data-categorization", "supported_types": ["address", "admin_area_1", "admin_area_2", "city", "continent", "country", "latitude", "longitude", "postindex", "street_address", "url"], "source": {"path": "data/tools/other/powerbi.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/powerbi.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/powerbi.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/powerbi", "json": "http://registry.apicrafter.io/api/v1/tools/powerbi.json"}}, {"id": "presidio", "name": "Microsoft Presidio", "category": "pii", "doc": "Presidio (Origin from Latin praesidium protection, garrison) helps to ensure sensitive data is properly managed and governed. It provides fast identification and anonymization modules for private entities in text such as credit card numbers, names, locations, social security numbers, bitcoin wallets, US phone numbers, financial data and more.", "website": "https://github.com/microsoft/presidio", "supported_types": ["aadhaar", "abaroutingnum", "abn", "auabn", "auacn", "aumedicarenum", "autfn", "bankcard", "casin", "date", "de_kvnr", "de_passport", "de_postcode", "de_rvnr", "de_stnr", "de_vehicle_plate", "depersonalausweis", "email", "esnie", "esnif", "espassport", "handelsregisternr", "iban", "ipaddr", "it_id_card", "krrrn", "mac_address", "medicare", "nhsnumber", "nif", "npi", "nric", "p2pkhaddr", "p2shaddr", "p2traddr", "p2wpkhaddr", "p2wshaddr", "pan", "person_fullname", "phone", "plpesel", "seorgnumber", "sepersonnummer", "sg_uen", "sgnric", "steuerid", "thidcard", "uknhsnum", "uknino", "ukpassport", "ukpostalcode", "url", "usbankaccount", "usdeanumber", "usdriverlic", "usitin", "usnpi", "uspassport", "usssn", "uuid"], "source": {"path": "data/tools/pii/presidio.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/presidio.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/presidio.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/presidio", "json": "http://registry.apicrafter.io/api/v1/tools/presidio.json"}}, {"id": "pythonstdnum", "name": "python-stdnum", "category": "other", "doc": "python-stdnum is an open source Python library with one module per standard number: national tax, VAT, company and personal identifiers, bank account and payment references, and international codes such as IBAN, ISBN, ISIN and IMEI. Each module cleans a given value and checks its length, format and check digit where one is defined; it does not scan text or guess the type of a column. The supported formats are listed in the project README and on its formats page.", "website": "https://arthurdejong.org/python-stdnum/formats", "supported_types": ["aadhaar", "aba", "abaroutingnum", "abn", "ad_nrt", "al_nipt", "ar_cbu", "ardni", "at_postcode", "at_tin", "at_vat", "at_vnr", "auabn", "auacn", "autfn", "az_voen", "bankaccount", "be_bis", "be_eid", "be_iban", "be_insz", "be_ogm_vcs", "be_vat", "benatcardid", "bg_egn", "bg_pnf", "bg_vat", "bic", "brcpf", "bsn", "by_unp", "cabcphn", "cabn", "casin", "casrn", "cficode", "ch_esr", "chahv", "chuid", "cif", "cl_rut", "cnpj", "co_nit", "containernumber", "cpf", "cr_cpf", "cr_cpj", "cr_cr", "cu_ni", "cuit", "cupscode", "curp", "cusip", "cy_vat", "cz_dic", "cz_rc", "de_stnr", "de_wkn", "deust", "dk_cvr", "dkcprnum", "do_cedula", "do_ncf", "do_rnc", "ean", "ec_ci", "ec_ruc", "ee_ik", "ee_kmkr", "ee_registrikood", "egtaxnumber", "es_ccc", "es_cups", "es_dni", "es_iban", "es_referenciacatastral", "esnie", "esnif", "espostcode", "esvat", "eu_at_02", "eu_banknote", "eu_ec_number", "eu_eic", "eu_nace", "euvat", "fi_alv", "fi_associationid", "fi_hetu", "fi_veronumero", "fi_ytunnus", "figi", "fr_nif", "frnir", "frvat", "gb_upn", "gb_vat", "gh_tin", "gr_amka", "gr_vat", "grid_release", "gt_nit", "gtin", "handelsregisternr", "hr_oib", "hu_anum", "iban", "idcard", "idnik", "idnpwp", "ie_pps", "ie_vat", "il_hp", "il_idnr", "imei", "imonumber", "imsi", "in_epic", "in_gstin", "inn", "is_kennitala", "is_vsk", "isan", "isbn", "isbn10", "isbn13", "isil", "isin", "ismn", "isni", "isrc", "issn", "it_aic", "it_codicefiscale", "it_iva", "jp_cn", "ke_kra_pin", "krbusinessreg", "krrrn", "lei", "li_peid", "lt_asmens", "lt_pvm", "lu_tva", "lv_pvn", "mac_address", "mc_tva", "md_idno", "me_iban", "me_pib", "meid", "mt_vat", "mu_nid", "my_nric", "mynumber", "nhsnumber", "nif", "nl_brin", "nl_onderwijsnummer", "nl_passport", "nl_postcode", "nlbtw", "no_fodselsnummer", "no_iban", "no_kontonr", "no_mva", "no_orgnr", "nz_bankaccount", "nz_ird", "ogrn", "ogrn_ogrnip", "p2pkhaddr", "p2shaddr", "p2wpkhaddr", "p2wshaddr", "pan", "pe_cui", "pe_ruc", "plnip", "plpesel", "plregon", "pt_cc", "pt_nif", "py_ruc", "rfc", "ro_cf", "ro_cnp", "ro_cui", "ro_onrc", "rs_pib", "se_postcode", "se_vat", "sedol", "seorgnumber", "sepersonnummer", "sg_uen", "si_ddv", "si_emso", "si_maticna_stevilka", "si_tin", "siren", "sirencode", "siret", "siretcode", "sk_dph", "sk_rc", "sn_ninea", "steuerid", "sv_nit", "swiftcode", "taxid", "tfn", "thidcard", "thtaxid", "trtaxnumber", "trtckimlik", "ua_edrpou", "uknhsnum", "ukutr", "upc", "usatin", "usein", "usitin", "usptin", "usssn", "vatin", "vntaxcode", "za_id"], "source": {"path": "data/tools/other/pythonstdnum.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/pythonstdnum.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/pythonstdnum.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/pythonstdnum", "json": "http://registry.apicrafter.io/api/v1/tools/pythonstdnum.json"}}, {"id": "qddate", "name": "qddate", "category": "detector", "doc": "Python library by Ivan Begtin that finds and parses dates written in many notations without being told the format. Version 1.1.0 has 151 date patterns, each with a key such as dt:date:date_2 - numeric dates with dots, slashes, hyphens or no separator, dates with a month name in 15 languages, and Chinese, Japanese and Korean dates with year, month and day units - plus generated variants with a time before or after the date. Metacrafter uses it to detect date columns and reports the key of the matching pattern as the format of the match. The registry records of these notations carry the pattern keys in mappings.qddate; this list is derived from them. Released under the BSD 3-Clause license.", "website": "https://github.com/ivbeg/qddate", "supported_types": ["date", "date_bulgarian", "date_cjk", "date_czech", "date_dmy", "date_dmy_compact", "date_dmy_dash", "date_dmy_dash_yy", "date_dmy_dot_yy", "date_dmy_slash", "date_dmy_slash_yy", "date_dutch", "date_english", "date_french", "date_german", "date_italian", "date_korean", "date_mdy_slash", "date_mdy_slash_yy", "date_polish", "date_portuguese", "date_romanian", "date_russian", "date_slovak", "date_spanish", "date_turkish", "date_ukrainian", "date_ymd_compact", "date_ymd_dot", "date_ymd_slash", "monthday_cjk", "monthday_dm_dot", "monthday_english", "monthday_korean", "monthday_russian"], "source": {"path": "data/tools/detectors/qddate.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/qddate.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/qddate.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/qddate", "json": "http://registry.apicrafter.io/api/v1/tools/qddate.json"}}, {"id": "sato", "name": "Sato", "category": "detector", "doc": "Sato is a research model from Megagon Labs, published at VLDB 2020, that predicts the semantic type of every column of a table. It extends the Sherlock column network with a topic model of the whole table and adds a conditional random field that predicts the types of all columns together, so the other columns of a table help to choose the type of each one. The published model predicts the same 78 semantic types as Sherlock, written in camelCase, such as birthDate or fileSize. The registry maps these types through mappings.sherlock, so this list is the same as the one of the sherlock tool. The code and the pretrained model are released under the Apache 2.0 license.", "website": "https://github.com/megagonlabs/sato", "supported_types": ["address", "age", "birthday", "birthplace", "brand", "category", "city", "comment", "continent", "country", "currency", "dc_creator", "dc_publisher", "description", "duration", "elevation", "filesize", "gender", "genre", "industry", "isbn", "language", "name", "nationality", "orgname", "person_fullname", "religion", "species", "weight", "year"], "source": {"path": "data/tools/detectors/sato.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/sato.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/sato.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/sato", "json": "http://registry.apicrafter.io/api/v1/tools/sato.json"}}, {"id": "scrubadub", "name": "scrubadub", "category": "pii", "doc": "Remove personally identifiable information from free text. Sometimes we have additional metadata about the people we wish to anonymize. Other times we dont. This package makes it easy to seamlessly scrub personal information from free text, without compromising the privacy of the people we are trying to protect.`", "website": "https://github.com/LeapBeyond/scrubadub", "supported_types": ["email", "phone", "birthday", "bankcard", "postindex", "address", "person_fullname"], "source": {"path": "data/tools/pii/scrubadub.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/scrubadub.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/scrubadub.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/scrubadub", "json": "http://registry.apicrafter.io/api/v1/tools/scrubadub.json"}}, {"id": "semgrep", "name": "Semgrep", "category": "detector", "doc": "Semgrep is a static analysis engine that runs pattern rules over source code and plain text. Its public rule registry has secret rules under generic/secrets/ (the p/secrets and p/gitleaks rulesets) that find credential formats, such as cloud keys, service tokens and private key blocks, with regular expressions and entropy checks. Semgrep Secrets, the commercial product, adds proprietary rules, data-flow analysis and live validation; its full detector list is shown only inside a customer deployment. The list of supported types covers only the registry datatypes that match a public rule.", "website": "https://github.com/semgrep/semgrep-rules/tree/develop/generic/secrets", "supported_types": ["aws_access_key_id", "aws_account_id", "aws_secret_access_key", "bcrypt_hash", "facebook_app_access_token", "github_token", "gitlab_pat", "google_api_key", "heroku_oauth_token", "jfrog_api_key", "jfrog_reference_token", "jwt", "mailchimp_api_key", "npm_access_token", "openai_api_key", "pgp_private_key_block", "sendgrid_api_key", "slack_token", "slack_webhook_url", "sonarqube_token", "square_access_token", "square_oauth_secret", "stripe_api_key", "telegram_bot_token", "twilio_api_key_sid", "unix_shadow_entry", "uri_with_password", "x509_private_key"], "source": {"path": "data/tools/detectors/semgrep.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/semgrep.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/semgrep.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/semgrep", "json": "http://registry.apicrafter.io/api/v1/tools/semgrep.json"}}, {"id": "sherlock", "name": "Sherlock", "category": "detector", "doc": "Sherlock is a deep learning model from the MIT Media Lab that predicts the semantic type of a table column from its values, without using the column header. It was trained on 686,765 columns of the VizNet corpus whose headers matched one of 78 semantic types taken from DBpedia properties, such as city, birth Date or isbn. Many of these types are header words rather than value types, such as code, type or rank. The registry records that carry a Sherlock type in mappings.sherlock are listed here. The code and the trained model are released under the MIT license.", "website": "https://sherlock.media.mit.edu", "supported_types": ["address", "age", "birthday", "birthplace", "brand", "category", "city", "comment", "continent", "country", "currency", "dc_creator", "dc_publisher", "description", "duration", "elevation", "filesize", "gender", "genre", "industry", "isbn", "language", "name", "nationality", "orgname", "person_fullname", "religion", "species", "weight", "year"], "source": {"path": "data/tools/detectors/sherlock.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/sherlock.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/sherlock.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/sherlock", "json": "http://registry.apicrafter.io/api/v1/tools/sherlock.json"}}, {"id": "snowflake", "name": "Snowflake sensitive data classification", "category": "pii", "doc": "Sensitive data classification in Snowflake samples the columns of tables and assigns each column a native semantic category, such as EMAIL, NATIONAL_IDENTIFIER or POSTAL_CODE, with a country-specific subcategory where one exists. Each category also has a privacy category: identifier, quasi-identifier or sensitive information. Results are stored as the SEMANTIC_CATEGORY and PRIVACY_CATEGORY tags.", "website": "https://docs.snowflake.com/en/user-guide/classify-native", "supported_types": ["aadhaar", "abn", "admin_area_1", "admin_area_2", "age", "at_driver_license", "at_passport", "at_tin", "at_vnr", "au_driver_license", "au_postcode", "auabn", "auacn", "aumedicarenum", "aupassport", "autfn", "bankaccount", "bankcard", "be_driver_license", "be_passport", "bg_driver_license", "bg_egn", "bg_passport", "birth_year", "birthday", "bsn", "ca_bank_account", "ca_postcode", "cadriverlic", "capassport", "caprovince", "casin", "ch_postcode", "city", "country", "cy_driver_license", "cy_id_card", "cy_passport", "cy_tin", "cz_driver_license", "cz_passport", "cz_rc", "de_passport", "dedriverlic", "depersonalausweis", "dk_driver_license", "dk_passport", "dkcprnum", "driver_license", "ee_driver_license", "ee_ik", "ee_passport", "email", "es_dni", "es_nss", "esdriverlic", "esnif", "espassport", "fi_driver_license", "fi_passport", "fiidcard", "fr_driver_license", "fr_nif", "frcni", "frnir", "frpassport", "gender", "geopoint", "gr_amka", "gr_driver_license", "gr_id_card", "gr_passport", "gr_vat", "hr_driver_license", "hr_oib", "hr_passport", "hu_driver_license", "hu_passport", "hu_personal_id", "hu_taj", "hu_tin", "iban", "icd10", "ie_driver_license", "ie_passport", "ie_pps", "imei", "in_driver_license", "in_epic", "in_gstin", "ipaddr", "it_codicefiscale", "it_driver_license", "it_passport", "jobtitle", "jp_postcode", "lab_test", "latitude", "longitude", "lt_asmens", "lt_driver_license", "lt_passport", "lu_driver_license", "lu_matricule", "lu_matricule_entity", "lu_passport", "lv_driver_license", "lv_passport", "lv_personal_code", "marital_status", "medical_condition", "medical_specialty", "medicare", "mt_driver_license", "mt_id_card", "mt_passport", "mt_tin", "nanpphone", "nl_driver_license", "nl_passport", "nric", "nz_bankaccount", "nz_driver_license", "nz_ird", "nz_nhi", "nz_nzbn", "pan", "person_fullname", "phone", "pldriverlic", "plnip", "plpassport", "postindex", "pt_cc", "pt_driver_license", "pt_nif", "pt_passport", "race_ethnicity", "ro_cnp", "ro_driver_license", "ro_passport", "se_driver_license", "sepassport", "sepersonnummer", "sg_uen", "sgnric", "si_driver_license", "si_emso", "si_passport", "si_tin", "sk_driver_license", "sk_passport", "sk_rc", "steuerid", "street_address", "tfn", "uknino", "ukpostalcode", "url", "usbankaccount", "uscity", "uscounty", "usdriverlic", "usein", "uspassport", "usssn", "usstate", "uszipcode", "vin"], "source": {"path": "data/tools/pii/snowflake.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/pii/snowflake.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/pii/snowflake.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/snowflake", "json": "http://registry.apicrafter.io/api/v1/tools/snowflake.json"}}, {"id": "soda", "name": "Soda", "category": "other", "doc": "Soda allows everyone on your data team to find, analyze, and resolve data issues. Our open-source tools and data observability platform bring everyone closer to the data, resulting in data products that you can trust.", "website": "https://docs.soda.io/soda-sql/sql_metrics.html#valid-format-values", "supported_types": ["date", "email", "ipv4", "ipv6", "ipaddr", "time", "phone", "uuid"], "source": {"path": "data/tools/other/soda.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/soda.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/soda.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/soda", "json": "http://registry.apicrafter.io/api/v1/tools/soda.json"}}, {"id": "sqldatacatalog", "name": "RedGate SQL Data catalog", "category": "catalogs", "doc": "SQL Data Catalog helps you protect your business by providing a scalable and repeatable process for managing personally-identifiable information (PII), as it moves through your SQL Server estate. Our solution lets you create a data catalog of your SQL Server estate, and monitors and controls it for protection appropriate to the sensitivity of the data, ensuring compliance during data handling.", "website": "https://documentation.red-gate.com/sql-data-catalog/data-scanning", "supported_types": ["bankaccount", "bankcard", "email", "city", "uscounty", "ipv4", "ipv6", "person_surname", "person_firstname", "person_fullname", "gender", "nationality", "ipaddr", "orgname", "usssn", "phone", "url", "usstate", "postindex", "jobtitle"], "source": {"path": "data/tools/catalogs/sqldatacatalog.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/catalogs/sqldatacatalog.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/catalogs/sqldatacatalog.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/sqldatacatalog", "json": "http://registry.apicrafter.io/api/v1/tools/sqldatacatalog.json"}}, {"id": "tableau", "name": "Tableau", "category": "other", "doc": "Tableau is a business intelligence and visual analytics platform. In Tableau Desktop a field can be given a geographic role, such as Airport, City, Country/Region or ZIP Code/Postcode, so that Tableau geocodes its values and can plot them on a map. Tableau Prep uses the same geographic roles, together with Email and URL, as data roles that validate field values and mark the ones that do not match. The roles are listed in the Tableau Desktop help on geographic roles and the Tableau Prep help on data roles.", "website": "https://help.tableau.com/current/pro/desktop/en-us/maps_geographicroles.htm", "supported_types": ["admin_area_1", "admin_area_2", "airport", "au_postcode", "city", "country", "countrycode_alpha2", "countrycode_alpha3", "de_postcode", "email", "encountryname", "eunuts", "fips10_4", "fr_department", "iataairportcode", "icaoairportcode", "latitude", "longitude", "nutsregion", "postindex", "url", "uscounty", "uszipcode"], "source": {"path": "data/tools/other/tableau.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/other/tableau.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/other/tableau.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/tableau", "json": "http://registry.apicrafter.io/api/v1/tools/tableau.json"}}, {"id": "talend", "name": "Talend (Qlik Talend Data Preparation, Data Catalog and Data Inventory)", "category": "etl", "doc": "Talend, now part of Qlik, suggests a semantic type for each column of a dataset. The types live in Talend Dictionary Service and are shared by Data Preparation, Data Inventory, Data Stewardship and Pipeline Designer. A type is either a list of values (for example ISO country and currency lists or INSEE lists of French communes), a regular expression, or a compound of other types. The predefined list covers names and titles, addresses and postal codes, phone numbers, card and bank numbers, national identifiers for France, Sweden, the UK and the US, and several kinds of URLs.", "website": "https://help.qlik.com/talend/en-US/data-preparation-user-guide/Cloud/predefined-semantic-types", "supported_types": ["aba", "abaroutingnum", "academictitle", "animal", "at_vat", "bankcard", "be_postcode", "beverage", "bg_vat", "boolean", "caprovince", "caprovincecode", "city", "civility", "colorhextriplet", "continent", "country", "countrycode_alpha2", "countrycode_alpha3", "date", "datetime", "dayofweek", "de_postcode", "email", "endayofweek", "enmonth", "enmonthshort", "formaltitle", "fqdn", "fr_commune", "fr_department", "fr_region", "frnir", "frpostcode", "frvat", "gender", "geopoint", "hexcolor", "honorificprefix", "iataairportcode", "iban", "industry", "inseecode", "ipv4", "ipv6", "isbn", "isbn10", "isbn13", "iso3166_mx3a", "iso4217curcode", "iso4217curname", "iso639_1", "iso639_2", "jobtitle", "language", "mac_address", "militarysuffix", "money", "month", "mxstate", "namesuffix", "nanpphone", "orgname", "orgunit", "person_firstname", "person_fullname", "person_surname", "phone", "sedol", "sepersonnummer", "street_address", "street_suffix", "time", "uknino", "ukpostalcode", "url", "uscounty", "usssn", "usstate", "uszipcode"], "source": {"path": "data/tools/etl/talend.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/etl/talend.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/etl/talend.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/talend", "json": "http://registry.apicrafter.io/api/v1/tools/talend.json"}}, {"id": "trufflehog", "name": "TruffleHog", "category": "detector", "doc": "TruffleHog is an open-source (AGPL-3.0) secret scanner from Truffle Security that searches git history, file systems, cloud storage and other sources for leaked credentials. Each of its several hundred detectors targets one service and combines keywords with a regular expression; many detectors then call the service's API to check whether the credential is live. The list of supported types covers only the registry datatypes that match a detector.", "website": "https://github.com/trufflesecurity/trufflehog", "supported_types": ["anthropic_api_key", "aws_access_key_id", "aws_secret_access_key", "azure_storage_account_key", "cloudflare_origin_ca_key", "connection_string", "databricks_access_token", "digitalocean_token", "doppler_token", "github_fine_grained_pat", "github_token", "gitlab_pat", "google_api_key", "grafana_service_account_token", "hashicorp_vault_token", "heroku_oauth_token", "huggingface_access_token", "jfrog_api_key", "jfrog_reference_token", "jwt", "linear_api_key", "mailchimp_api_key", "npm_access_token", "openai_api_key", "planetscale_password", "planetscale_token", "postman_api_key", "pulumi_access_token", "pypi_token", "rubygems_api_key", "sendgrid_api_key", "sendinblue_api_key", "sentry_auth_token", "shared_access_signature", "shopify_access_token", "slack_token", "slack_webhook_url", "sonarqube_token", "square_access_token", "square_oauth_secret", "stripe_api_key", "telegram_bot_token", "terraform_cloud_api_token", "twilio_api_key_sid", "uri_with_password", "x509_private_key"], "source": {"path": "data/tools/detectors/trufflehog.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/trufflehog.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/trufflehog.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/trufflehog", "json": "http://registry.apicrafter.io/api/v1/tools/trufflehog.json"}}, {"id": "woodwork", "name": "Alteryx Woodwork", "category": "detector", "doc": "Woodwork is an open source Python library from Alteryx that adds typing metadata to pandas DataFrames: a logical type and semantic tags for each column. It infers some logical types from the values, including EmailAddress, URL, PhoneNumber, PostalCode, IPAddress, Datetime and Boolean, and validates email, URL and phone values with configurable regular expressions; other types, such as Address, CountryCode or LatLong, are set by the user. Version 0.31.0 defines 26 logical types in woodwork/logical_types.py, and woodwork.list_logical_types() lists them.", "website": "https://woodwork.alteryx.com/en/stable/guides/logical_types_and_semantic_tags.html", "supported_types": ["address", "age", "boolean", "countrycode_alpha2", "datetime", "duration", "email", "geopoint", "ipaddr", "iso3166code", "iso4217curcode", "person_fullname", "phone", "postindex", "url"], "source": {"path": "data/tools/detectors/woodwork.yaml", "url": "https://github.com/apicrafter/metacrafter-registry/blob/main/data/tools/detectors/woodwork.yaml", "edit_url": "https://github.com/apicrafter/metacrafter-registry/edit/main/data/tools/detectors/woodwork.yaml"}, "urls": {"html": "http://registry.apicrafter.io/tool/woodwork", "json": "http://registry.apicrafter.io/api/v1/tools/woodwork.json"}}]