feat(classification): classify known object schema detections (#85)

* refactor: pull out shared classify functionality * refactor: clean up classify helper methods * feat: add all data classification patterns * feat: add identity regexp to db known person objects * feat: add schema classification for known objects * feat: check properties for stop words
Bearer · Oct 28, 2022 · 00a3271 · 00a3271
1 parent 0b64899
commit 00a3271
Show file tree

Hide file tree

Showing 206 changed files with 1,102 additions and 203 deletions.
diff --git a/go.mod b/go.mod
@@ -42,6 +42,7 @@ require (
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/rivo/uniseg v0.4.2 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
+	github.com/tangzero/inflector v1.0.0 // indirect
 	golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4 // indirect
 	golang.org/x/term v0.1.0 // indirect
 	gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect

diff --git a/go.sum b/go.sum
@@ -240,6 +240,8 @@ github.com/struCoder/pidusage v0.2.1 h1:dFiEgUDkubeIj0XA1NpQ6+8LQmKrLi7NiIQl86E6
 github.com/struCoder/pidusage v0.2.1/go.mod h1:bewtP2KUA1TBUyza5+/PCpSQ6sc/H6jJbIKAzqW86BA=
 github.com/subosito/gotenv v1.4.1 h1:jyEFiXpy21Wm81FBN71l9VoMMV8H8jG+qIK3GCpY6Qs=
 github.com/subosito/gotenv v1.4.1/go.mod h1:ayKnFf/c6rvx/2iiLrJUk1e6plDbT3edrFNGqEflhK0=
+github.com/tangzero/inflector v1.0.0 h1:933dvPwRUUOAl98hyeeXuzFix3HwDt5j+45lleu8oh0=
+github.com/tangzero/inflector v1.0.0/go.mod h1:OknKjAyDPCDzcWt0yOh2I7hqTukEdyyApcX3/KOhuXc=
 github.com/weppos/publicsuffix-go v0.12.0/go.mod h1:z3LCPQ38eedDQSwmsSRW4Y7t2L8Ln16JPQ02lHAdn5k=
 github.com/weppos/publicsuffix-go v0.20.0 h1:59ypvSUbW3Dunc6zVm+v+MmXf2Q6cGiNDkxgRIzEnaA=
 github.com/weppos/publicsuffix-go v0.20.0/go.mod h1:5ZC/Uv3fIEUE0eP6o9+Yg4+5+W8V0/BieMi05feGXVA=

diff --git a/pkg/classification/classification.go b/pkg/classification/classification.go
@@ -13,7 +13,7 @@ type Classifier struct {
 	config Config
 
 	Interfaces   *interfaces.Classifier
-	Schema       schema.Classifier
+	Schema       *schema.Classifier
 	Dependencies *dependencies.Classifier
 }
 
@@ -36,6 +36,14 @@ func NewClassifier(config *Config) (*Classifier, error) {
 		return nil, err
 	}
 
+	schemaClassifier := schema.New(
+		schema.Config{
+			DataTypes:                      db.Default().DataTypes,
+			DataTypeClassificationPatterns: db.Default().DataTypeClassificationPatterns,
+			KnownPersonObjectPatterns:      db.Default().KnownPersonObjectPatterns,
+		},
+	)
+
 	dependenciesClassifier := dependencies.New(
 		dependencies.Config{
 			Recipes: db.Default().Recipes,
@@ -46,5 +54,6 @@ func NewClassifier(config *Config) (*Classifier, error) {
 		config:       *config,
 		Dependencies: dependenciesClassifier,
 		Interfaces:   interfacesClassifier,
+		Schema:       schemaClassifier,
 	}, nil
 }
diff --git a/...sification_patterns/telephone_number.json → ...cation_patterns/100_telephone_number.json b/...sification_patterns/telephone_number.json → ...cation_patterns/100_telephone_number.json
diff --git a/...e_classification_patterns/geographic.json → ...assification_patterns/101_geographic.json b/...e_classification_patterns/geographic.json → ...assification_patterns/101_geographic.json
diff --git a/...classification_patterns/transactions.json → ...sification_patterns/102_transactions.json b/...classification_patterns/transactions.json → ...sification_patterns/102_transactions.json
diff --git a/...ication_patterns/browser_fingerprint.json → ...ion_patterns/103_browser_fingerprint.json b/...ication_patterns/browser_fingerprint.json → ...ion_patterns/103_browser_fingerprint.json
diff --git a/..._type_classification_patterns/emails.json → ...e_classification_patterns/104_emails.json b/..._type_classification_patterns/emails.json → ...e_classification_patterns/104_emails.json
diff --git a/...lassification_patterns/links_clicked.json → ...ification_patterns/105_links_clicked.json b/...lassification_patterns/links_clicked.json → ...ification_patterns/105_links_clicked.json
diff --git a/...ta_type_classification_patterns/race.json → ...ype_classification_patterns/106_race.json b/...ta_type_classification_patterns/race.json → ...ype_classification_patterns/106_race.json
diff --git a/...classification_patterns/conversation.json → ...sification_patterns/107_conversation.json b/...classification_patterns/conversation.json → ...sification_patterns/107_conversation.json
diff --git a/...type_classification_patterns/vaccine.json → ..._classification_patterns/108_vaccine.json b/...type_classification_patterns/vaccine.json → ..._classification_patterns/108_vaccine.json
diff --git a/...ype_classification_patterns/question.json → ...classification_patterns/109_question.json b/...ype_classification_patterns/question.json → ...classification_patterns/109_question.json
diff --git a/...type_classification_patterns/charges.json → ...e_classification_patterns/10_charges.json b/...type_classification_patterns/charges.json → ...e_classification_patterns/10_charges.json
diff --git a/..._type_classification_patterns/answer.json → ...e_classification_patterns/110_answer.json b/..._type_classification_patterns/answer.json → ...e_classification_patterns/110_answer.json
diff --git a/...a_type_classification_patterns/click.json → ...pe_classification_patterns/111_click.json b/...a_type_classification_patterns/click.json → ...pe_classification_patterns/111_click.json
diff --git a/...ype_classification_patterns/tracking.json → ...classification_patterns/112_tracking.json b/...ype_classification_patterns/tracking.json → ...classification_patterns/112_tracking.json
diff --git a/...ta_type_classification_patterns/cart.json → ...ype_classification_patterns/113_cart.json b/...ta_type_classification_patterns/cart.json → ...ype_classification_patterns/113_cart.json
diff --git a/...type_classification_patterns/payment.json → ..._classification_patterns/114_payment.json b/...type_classification_patterns/payment.json → ..._classification_patterns/114_payment.json
diff --git a/...a_type_classification_patterns/order.json → ...pe_classification_patterns/115_order.json b/...a_type_classification_patterns/order.json → ...pe_classification_patterns/115_order.json
diff --git a/...ype_classification_patterns/purchase.json → ...classification_patterns/116_purchase.json b/...ype_classification_patterns/purchase.json → ...classification_patterns/116_purchase.json
diff --git a/...a_type_classification_patterns/token.json → ...pe_classification_patterns/117_token.json b/...a_type_classification_patterns/token.json → ...pe_classification_patterns/117_token.json
diff --git a/...type_classification_patterns/invoice.json → ..._classification_patterns/118_invoice.json b/...type_classification_patterns/invoice.json → ..._classification_patterns/118_invoice.json
diff --git a/...classification_patterns/access_token.json → ...sification_patterns/119_access_token.json b/...classification_patterns/access_token.json → ...sification_patterns/119_access_token.json
diff --git a/...type_classification_patterns/pardons.json → ...e_classification_patterns/11_pardons.json b/...type_classification_patterns/pardons.json → ...e_classification_patterns/11_pardons.json
diff --git a/...type_classification_patterns/billing.json → ..._classification_patterns/120_billing.json b/...type_classification_patterns/billing.json → ..._classification_patterns/120_billing.json
diff --git a/...lassification_patterns/bank_transfer.json → ...ification_patterns/121_bank_transfer.json b/...lassification_patterns/bank_transfer.json → ...ification_patterns/121_bank_transfer.json
diff --git a/...e_classification_patterns/creditcard.json → ...assification_patterns/122_creditcard.json b/...e_classification_patterns/creditcard.json → ...assification_patterns/122_creditcard.json
diff --git a/...type_classification_patterns/paystub.json → ..._classification_patterns/123_paystub.json b/...type_classification_patterns/paystub.json → ..._classification_patterns/123_paystub.json
diff --git a/...classification_patterns/subscription.json → ...sification_patterns/124_subscription.json b/...classification_patterns/subscription.json → ...sification_patterns/124_subscription.json
diff --git a/...ta_type_classification_patterns/exam.json → ...ype_classification_patterns/125_exam.json b/...ta_type_classification_patterns/exam.json → ...ype_classification_patterns/125_exam.json
diff --git a/..._classification_patterns/appointment.json → ...ssification_patterns/126_appointment.json b/..._classification_patterns/appointment.json → ...ssification_patterns/126_appointment.json
diff --git a/...classification_patterns/consultation.json → ...sification_patterns/127_consultation.json b/...classification_patterns/consultation.json → ...sification_patterns/127_consultation.json
diff --git a/...ype_classification_patterns/document.json → ...classification_patterns/128_document.json b/...ype_classification_patterns/document.json → ...classification_patterns/128_document.json
diff --git a/...ta_type_classification_patterns/file.json → ...ype_classification_patterns/129_file.json b/...ta_type_classification_patterns/file.json → ...ype_classification_patterns/129_file.json
diff --git a/...ssification_patterns/driving_license.json → ...fication_patterns/12_driving_license.json b/...ssification_patterns/driving_license.json → ...fication_patterns/12_driving_license.json
diff --git a/...type_classification_patterns/content.json → ..._classification_patterns/130_content.json b/...type_classification_patterns/content.json → ..._classification_patterns/130_content.json
diff --git a/..._type_classification_patterns/device.json → ...e_classification_patterns/131_device.json b/..._type_classification_patterns/device.json → ...e_classification_patterns/131_device.json
diff --git a/...assification_patterns/identification.json → ...fication_patterns/132_identification.json b/...assification_patterns/identification.json → ...fication_patterns/132_identification.json
diff --git a/...type_classification_patterns/earning.json → ..._classification_patterns/133_earning.json b/...type_classification_patterns/earning.json → ..._classification_patterns/133_earning.json
diff --git a/..._classification_patterns/credentials.json → ...ssification_patterns/134_credentials.json b/..._classification_patterns/credentials.json → ...ssification_patterns/134_credentials.json
diff --git a/pkg/classification/db/data_type_classification_patterns/135_message.json b/pkg/classification/db/data_type_classification_patterns/135_message.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 135,
+  "data_type_uuid": "8358b541-500f-4321-8ee9-89ce61e9459e",
+  "exclude_regexp": "\\b.*error|status|id.*\\b",
+  "exclude_types": ["boolean"],
+  "friendly_name": "Message",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b.*message.*\\b",
+  "include_types": ["string"],
+  "match_column": false,
+  "match_object": true,
+  "object_type": ["known_data_object"]
+}
diff --git a/..._type_classification_patterns/rating.json → ...e_classification_patterns/136_rating.json b/..._type_classification_patterns/rating.json → ...e_classification_patterns/136_rating.json
diff --git a/..._type_classification_patterns/review.json → ...e_classification_patterns/137_review.json b/..._type_classification_patterns/review.json → ...e_classification_patterns/137_review.json
diff --git a/...a_type_classification_patterns/voice.json → ...pe_classification_patterns/138_voice.json b/...a_type_classification_patterns/voice.json → ...pe_classification_patterns/138_voice.json
diff --git a/..._type_classification_patterns/amount.json → ...e_classification_patterns/139_amount.json b/..._type_classification_patterns/amount.json → ...e_classification_patterns/139_amount.json
diff --git a/...ification_patterns/device_identifier.json → ...cation_patterns/13_device_identifier.json b/...ification_patterns/device_identifier.json → ...cation_patterns/13_device_identifier.json
diff --git a/pkg/classification/db/data_type_classification_patterns/140_comment.json b/pkg/classification/db/data_type_classification_patterns/140_comment.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 140,
+  "data_type_uuid": "8358b541-500f-4321-8ee9-89ce61e9459e",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Comment",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b.*comment.*\\b",
+  "include_types": ["string"],
+  "match_column": false,
+  "match_object": true,
+  "object_type": ["associated", "known_data_object"]
+}
diff --git a/...ype_classification_patterns/fullname.json → ...classification_patterns/142_fullname.json b/...ype_classification_patterns/fullname.json → ...classification_patterns/142_fullname.json
diff --git a/...ification_patterns/unique_identifier.json → ...ation_patterns/143_unique_identifier.json b/...ification_patterns/unique_identifier.json → ...ation_patterns/143_unique_identifier.json
diff --git a/...type_classification_patterns/disease.json → ..._classification_patterns/144_disease.json b/...type_classification_patterns/disease.json → ..._classification_patterns/144_disease.json
diff --git a/...type_classification_patterns/genetic.json → ..._classification_patterns/145_genetic.json b/...type_classification_patterns/genetic.json → ..._classification_patterns/145_genetic.json
diff --git a/...sification_patterns/lab_test_results.json → ...cation_patterns/146_lab_test_results.json b/...sification_patterns/lab_test_results.json → ...cation_patterns/146_lab_test_results.json
diff --git a/...ion_patterns/health_insurance_number.json → ...patterns/147_health_insurance_number.json b/...ion_patterns/health_insurance_number.json → ...patterns/147_health_insurance_number.json
diff --git a/...pe_classification_patterns/insurance.json → ...lassification_patterns/148_insurance.json b/...pe_classification_patterns/insurance.json → ...lassification_patterns/148_insurance.json
diff --git a/...ta_type_classification_patterns/test.json → ...ype_classification_patterns/149_test.json b/...ta_type_classification_patterns/test.json → ...ype_classification_patterns/149_test.json
diff --git a/...lassification_patterns/ethnic_origin.json → ...sification_patterns/14_ethnic_origin.json b/...lassification_patterns/ethnic_origin.json → ...sification_patterns/14_ethnic_origin.json
diff --git a/...fication_patterns/medical_conditions.json → ...tion_patterns/150_medical_conditions.json b/...fication_patterns/medical_conditions.json → ...tion_patterns/150_medical_conditions.json
diff --git a/...pe_classification_patterns/treatment.json → ...lassification_patterns/151_treatment.json b/...pe_classification_patterns/treatment.json → ...lassification_patterns/151_treatment.json
diff --git a/...ta_type_classification_patterns/scan.json → ...ype_classification_patterns/152_scan.json b/...ta_type_classification_patterns/scan.json → ...ype_classification_patterns/152_scan.json
diff --git a/...e_classification_patterns/medication.json → ...assification_patterns/153_medication.json b/...e_classification_patterns/medication.json → ...assification_patterns/153_medication.json
diff --git a/...pe_classification_patterns/phi_dates.json → ...lassification_patterns/154_phi_dates.json b/...pe_classification_patterns/phi_dates.json → ...lassification_patterns/154_phi_dates.json
diff --git a/...pe_classification_patterns/diagnosis.json → ...lassification_patterns/155_diagnosis.json b/...pe_classification_patterns/diagnosis.json → ...lassification_patterns/155_diagnosis.json
diff --git a/...e_classification_patterns/procedures.json → ...assification_patterns/156_procedures.json b/...e_classification_patterns/procedures.json → ...assification_patterns/156_procedures.json
diff --git a/...sification_patterns/risk_assessments.json → ...cation_patterns/157_risk_assessments.json b/...sification_patterns/risk_assessments.json → ...cation_patterns/157_risk_assessments.json
diff --git a/...pe_classification_patterns/allergies.json → ...lassification_patterns/158_allergies.json b/...pe_classification_patterns/allergies.json → ...lassification_patterns/158_allergies.json
diff --git a/...tterns/health_insurance_claim_number.json → ...ns/159_health_insurance_claim_number.json b/...tterns/health_insurance_claim_number.json → ...ns/159_health_insurance_claim_number.json
diff --git a/...ssification_patterns/national_origin.json → ...fication_patterns/15_national_origin.json b/...ssification_patterns/national_origin.json → ...fication_patterns/15_national_origin.json
diff --git a/...ssification_patterns/health_provider.json → ...ication_patterns/160_health_provider.json b/...ssification_patterns/health_provider.json → ...ication_patterns/160_health_provider.json
diff --git a/..._classification_patterns/vital_signs.json → ...ssification_patterns/161_vital_signs.json b/..._classification_patterns/vital_signs.json → ...ssification_patterns/161_vital_signs.json
diff --git a/...assification_patterns/blood_pressure.json → ...fication_patterns/162_blood_pressure.json b/...assification_patterns/blood_pressure.json → ...fication_patterns/162_blood_pressure.json
diff --git a/...ata_type_classification_patterns/bmi.json → ...type_classification_patterns/163_bmi.json b/...ata_type_classification_patterns/bmi.json → ...type_classification_patterns/163_bmi.json
diff --git a/...e_classification_patterns/tomography.json → ...assification_patterns/165_tomography.json b/...e_classification_patterns/tomography.json → ...assification_patterns/165_tomography.json
diff --git a/...ification_patterns/physical_activity.json → ...ation_patterns/166_physical_activity.json b/...ification_patterns/physical_activity.json → ...ation_patterns/166_physical_activity.json
diff --git a/...a_type_classification_patterns/x-ray.json → ...pe_classification_patterns/167_x-ray.json b/...a_type_classification_patterns/x-ray.json → ...pe_classification_patterns/167_x-ray.json
diff --git a/...ype_classification_patterns/concerns.json → ...classification_patterns/168_concerns.json b/...ype_classification_patterns/concerns.json → ...classification_patterns/168_concerns.json
diff --git a/...ion_patterns/hospital_admission_date.json → ...patterns/169_hospital_admission_date.json b/...ion_patterns/hospital_admission_date.json → ...patterns/169_hospital_admission_date.json
diff --git a/...assification_patterns/biometric_data.json → ...ification_patterns/16_biometric_data.json b/...assification_patterns/biometric_data.json → ...ification_patterns/16_biometric_data.json
diff --git a/...ion_patterns/hospital_discharge_date.json → ...patterns/170_hospital_discharge_date.json b/...ion_patterns/hospital_discharge_date.json → ...patterns/170_hospital_discharge_date.json
diff --git a/..._type_classification_patterns/cancer.json → ...e_classification_patterns/171_cancer.json b/..._type_classification_patterns/cancer.json → ...e_classification_patterns/171_cancer.json
diff --git a/..._classification_patterns/colonoscopy.json → ...ssification_patterns/172_colonoscopy.json b/..._classification_patterns/colonoscopy.json → ...ssification_patterns/172_colonoscopy.json
diff --git a/...ion_patterns/cholesterol_measurement.json → ...patterns/173_cholesterol_measurement.json b/...ion_patterns/cholesterol_measurement.json → ...patterns/173_cholesterol_measurement.json
diff --git a/...lassification_patterns/blood_glucose.json → ...ification_patterns/174_blood_glucose.json b/...lassification_patterns/blood_glucose.json → ...ification_patterns/174_blood_glucose.json
diff --git a/...tterns/high_low_density_lipoproteins.json → ...ns/175_high_low_density_lipoproteins.json b/...tterns/high_low_density_lipoproteins.json → ...ns/175_high_low_density_lipoproteins.json
diff --git a/..._type_classification_patterns/asthma.json → ...e_classification_patterns/176_asthma.json b/..._type_classification_patterns/asthma.json → ...e_classification_patterns/176_asthma.json
diff --git a/...ata_type_classification_patterns/hiv.json → ...type_classification_patterns/177_hiv.json b/...ata_type_classification_patterns/hiv.json → ...type_classification_patterns/177_hiv.json
diff --git a/...ata_type_classification_patterns/flu.json → ...type_classification_patterns/178_flu.json b/...ata_type_classification_patterns/flu.json → ...type_classification_patterns/178_flu.json
diff --git a/...e_classification_patterns/giardiasis.json → ...assification_patterns/179_giardiasis.json b/...e_classification_patterns/giardiasis.json → ...assification_patterns/179_giardiasis.json
diff --git a/...classification_patterns/bank_account.json → ...ssification_patterns/17_bank_account.json b/...classification_patterns/bank_account.json → ...ssification_patterns/17_bank_account.json
diff --git a/...e_classification_patterns/diphtheria.json → ...assification_patterns/180_diphtheria.json b/...e_classification_patterns/diphtheria.json → ...assification_patterns/180_diphtheria.json
diff --git a/...pe_classification_patterns/pneumonia.json → ...lassification_patterns/181_pneumonia.json b/...pe_classification_patterns/pneumonia.json → ...lassification_patterns/181_pneumonia.json
diff --git a/...classification_patterns/tuberculosis.json → ...sification_patterns/182_tuberculosis.json b/...classification_patterns/tuberculosis.json → ...sification_patterns/182_tuberculosis.json
diff --git a/...classification_patterns/hypertension.json → ...sification_patterns/183_hypertension.json b/...classification_patterns/hypertension.json → ...sification_patterns/183_hypertension.json
diff --git a/...type_classification_patterns/illness.json → ..._classification_patterns/184_illness.json b/...type_classification_patterns/illness.json → ..._classification_patterns/184_illness.json
diff --git a/...type_classification_patterns/therapy.json → ..._classification_patterns/185_therapy.json b/...type_classification_patterns/therapy.json → ..._classification_patterns/185_therapy.json
diff --git a/...pe_classification_patterns/procedure.json → ...lassification_patterns/186_procedure.json b/...pe_classification_patterns/procedure.json → ...lassification_patterns/186_procedure.json
diff --git a/...ype_classification_patterns/feedback.json → ...classification_patterns/187_feedback.json b/...ype_classification_patterns/feedback.json → ...classification_patterns/187_feedback.json
diff --git a/..._type_classification_patterns/agenda.json → ...e_classification_patterns/188_agenda.json b/..._type_classification_patterns/agenda.json → ...e_classification_patterns/188_agenda.json
diff --git a/...lassification_patterns/contraception.json → ...ification_patterns/189_contraception.json b/...lassification_patterns/contraception.json → ...ification_patterns/189_contraception.json
diff --git a/...cation_patterns/mother's_maiden_name.json → ...ion_patterns/18_mother's_maiden_name.json b/...cation_patterns/mother's_maiden_name.json → ...ion_patterns/18_mother's_maiden_name.json
diff --git a/...lassification_patterns/physiotherapy.json → ...ification_patterns/190_physiotherapy.json b/...lassification_patterns/physiotherapy.json → ...ification_patterns/190_physiotherapy.json
diff --git a/...pe_classification_patterns/pregnancy.json → ...lassification_patterns/191_pregnancy.json b/...pe_classification_patterns/pregnancy.json → ...lassification_patterns/191_pregnancy.json
diff --git a/...type_classification_patterns/message.json → ..._classification_patterns/192_message.json b/...type_classification_patterns/message.json → ..._classification_patterns/192_message.json
diff --git a/...type_classification_patterns/symptom.json → ..._classification_patterns/193_symptom.json b/...type_classification_patterns/symptom.json → ..._classification_patterns/193_symptom.json
diff --git a/...pe_classification_patterns/signature.json → ...lassification_patterns/194_signature.json b/...pe_classification_patterns/signature.json → ...lassification_patterns/194_signature.json
diff --git a/...type_classification_patterns/replies.json → ..._classification_patterns/195_replies.json b/...type_classification_patterns/replies.json → ..._classification_patterns/195_replies.json
diff --git a/...ta_type_classification_patterns/post.json → ...ype_classification_patterns/196_post.json b/...ta_type_classification_patterns/post.json → ...ype_classification_patterns/196_post.json
diff --git a/...pe_classification_patterns/purchases.json → ...lassification_patterns/197_purchases.json b/...pe_classification_patterns/purchases.json → ...lassification_patterns/197_purchases.json
diff --git a/...type_classification_patterns/comment.json → ..._classification_patterns/198_comment.json b/...type_classification_patterns/comment.json → ..._classification_patterns/198_comment.json
diff --git a/...ssification_patterns/passport_number.json → ...fication_patterns/19_passport_number.json b/...ssification_patterns/passport_number.json → ...fication_patterns/19_passport_number.json
diff --git a/pkg/classification/db/data_type_classification_patterns/1_email_address.json b/pkg/classification/db/data_type_classification_patterns/1_email_address.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 1,
+  "data_type_uuid": "22e24c62-82d3-4b72-827c-e261533331bd",
+  "exclude_regexp": "\\b(.*(notification|config(uration)?|template|enabled|token|reminder|subject|body|handover|sent.by|settings?|accept|label|id|voice|type).*)\\b",
+  "exclude_types": ["boolean", "date", "bool"],
+  "friendly_name": "Email Address",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\b.*email.*\b",
+  "include_types": ["object", "string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/...ta_type_classification_patterns/cars.json → ...type_classification_patterns/20_cars.json b/...ta_type_classification_patterns/cars.json → ...type_classification_patterns/20_cars.json
diff --git a/...on_patterns/national_identity_number.json → ...patterns/21_national_identity_number.json b/...on_patterns/national_identity_number.json → ...patterns/21_national_identity_number.json
diff --git a/...cation_patterns/telephone_recordings.json → ...ion_patterns/22_telephone_recordings.json b/...cation_patterns/telephone_recordings.json → ...ion_patterns/22_telephone_recordings.json
diff --git a/...e_classification_patterns/voice_mail.json → ...lassification_patterns/23_voice_mail.json b/...e_classification_patterns/voice_mail.json → ...lassification_patterns/23_voice_mail.json
diff --git a/...ion_patterns/personal_health_history.json → ..._patterns/24_personal_health_history.json b/...ion_patterns/personal_health_history.json → ..._patterns/24_personal_health_history.json
diff --git a/...ation_patterns/family_health_history.json → ...on_patterns/25_family_health_history.json b/...ation_patterns/family_health_history.json → ...on_patterns/25_family_health_history.json
diff --git a/...assification_patterns/health_records.json → ...ification_patterns/26_health_records.json b/...assification_patterns/health_records.json → ...ification_patterns/26_health_records.json
diff --git a/...classification_patterns/disabilities.json → ...ssification_patterns/27_disabilities.json b/...classification_patterns/disabilities.json → ...ssification_patterns/27_disabilities.json
diff --git a/...fication_patterns/drugs_test_results.json → ...ation_patterns/28_drugs_test_results.json b/...fication_patterns/drugs_test_results.json → ...ation_patterns/28_drugs_test_results.json
diff --git a/...e_classification_patterns/blood_type.json → ...lassification_patterns/29_blood_type.json b/...e_classification_patterns/blood_type.json → ...lassification_patterns/29_blood_type.json
diff --git a/...lassification_patterns/email_address.json → ...ssification_patterns/2_email_address.json b/...lassification_patterns/email_address.json → ...ssification_patterns/2_email_address.json
diff --git a/...ype_classification_patterns/dna_code.json → ..._classification_patterns/30_dna_code.json b/...ype_classification_patterns/dna_code.json → ..._classification_patterns/30_dna_code.json
diff --git a/...lassification_patterns/prescriptions.json → ...sification_patterns/31_prescriptions.json b/...lassification_patterns/prescriptions.json → ...sification_patterns/31_prescriptions.json
diff --git a/...assification_patterns/place_of_birth.json → ...ification_patterns/32_place_of_birth.json b/...assification_patterns/place_of_birth.json → ...ification_patterns/32_place_of_birth.json
diff --git a/...ype_classification_patterns/divorces.json → ..._classification_patterns/33_divorces.json b/...ype_classification_patterns/divorces.json → ..._classification_patterns/33_divorces.json
diff --git a/...pe_classification_patterns/marriages.json → ...classification_patterns/34_marriages.json b/...pe_classification_patterns/marriages.json → ...classification_patterns/34_marriages.json
diff --git a/...type_classification_patterns/friends.json → ...e_classification_patterns/35_friends.json b/...type_classification_patterns/friends.json → ...e_classification_patterns/35_friends.json
diff --git a/...assification_patterns/martial_status.json → ...ification_patterns/36_martial_status.json b/...assification_patterns/martial_status.json → ...ification_patterns/36_martial_status.json
diff --git a/...lassification_patterns/social_status.json → ...sification_patterns/37_social_status.json b/...lassification_patterns/social_status.json → ...sification_patterns/37_social_status.json
diff --git a/...assification_patterns/student_number.json → ...ification_patterns/38_student_number.json b/...assification_patterns/student_number.json → ...ification_patterns/38_student_number.json
diff --git a/...ssification_patterns/taxpayer_number.json → ...fication_patterns/39_taxpayer_number.json b/...ssification_patterns/taxpayer_number.json → ...fication_patterns/39_taxpayer_number.json
diff --git a/...pe_classification_patterns/age_range.json → ..._classification_patterns/3_age_range.json b/...pe_classification_patterns/age_range.json → ..._classification_patterns/3_age_range.json
diff --git a/...tion_patterns/social_security_number.json → ...n_patterns/40_social_security_number.json b/...tion_patterns/social_security_number.json → ...n_patterns/40_social_security_number.json
diff --git a/...fication_patterns/sexual_preferences.json → ...ation_patterns/41_sexual_preferences.json b/...fication_patterns/sexual_preferences.json → ...ation_patterns/41_sexual_preferences.json
diff --git a/...assification_patterns/sexual_history.json → ...ification_patterns/42_sexual_history.json b/...assification_patterns/sexual_history.json → ...ification_patterns/42_sexual_history.json
diff --git a/...cation_patterns/disciplinary_actions.json → ...ion_patterns/43_disciplinary_actions.json b/...cation_patterns/disciplinary_actions.json → ...ion_patterns/43_disciplinary_actions.json
diff --git a/...e_classification_patterns/interviews.json → ...lassification_patterns/44_interviews.json b/...e_classification_patterns/interviews.json → ...lassification_patterns/44_interviews.json
diff --git a/...e_classification_patterns/job_titles.json → ...lassification_patterns/45_job_titles.json b/...e_classification_patterns/job_titles.json → ...lassification_patterns/45_job_titles.json
diff --git a/...classification_patterns/work_history.json → ...ssification_patterns/46_work_history.json b/...classification_patterns/work_history.json → ...ssification_patterns/46_work_history.json
diff --git a/...fication_patterns/employment_history.json → ...ation_patterns/47_employment_history.json b/...fication_patterns/employment_history.json → ...ation_patterns/47_employment_history.json
diff --git a/..._type_classification_patterns/salary.json → ...pe_classification_patterns/48_salary.json b/..._type_classification_patterns/salary.json → ...pe_classification_patterns/48_salary.json
diff --git a/...assification_patterns/certifications.json → ...ification_patterns/49_certifications.json b/...assification_patterns/certifications.json → ...ification_patterns/49_certifications.json
diff --git a/pkg/classification/db/data_type_classification_patterns/4_physical_address.json b/pkg/classification/db/data_type_classification_patterns/4_physical_address.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 4,
+  "data_type_uuid": "5a80a938-6fb2-4d9a-9c47-8d377e036506",
+  "exclude_regexp": "\\b(.*email|(zip.*file)|ip|domain|cart|id|mac|submit|viewed|list|dialog|voice.*)\\b",
+  "exclude_types": ["boolean"],
+  "friendly_name": "Physical Address",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(city|street|address|region|province)|((billing|shipping).*address)|((zip\\s?postal)|(zip|postal)\\s?code)\\b",
+  "include_types": ["string", "object"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/...sification_patterns/group_membership.json → ...ication_patterns/50_group_membership.json b/...sification_patterns/group_membership.json → ...ication_patterns/50_group_membership.json
diff --git a/...lassification_patterns/acquaintances.json → ...sification_patterns/51_acquaintances.json b/...lassification_patterns/acquaintances.json → ...sification_patterns/51_acquaintances.json
diff --git a/...type_classification_patterns/opinion.json → ...e_classification_patterns/52_opinion.json b/...type_classification_patterns/opinion.json → ...e_classification_patterns/52_opinion.json
diff --git a/...assification_patterns/favorite_foods.json → ...ification_patterns/53_favorite_foods.json b/...assification_patterns/favorite_foods.json → ...ification_patterns/53_favorite_foods.json
diff --git a/...ification_patterns/religious_beliefs.json → ...cation_patterns/54_religious_beliefs.json b/...ification_patterns/religious_beliefs.json → ...cation_patterns/54_religious_beliefs.json
diff --git a/...ation_patterns/philosophical_beliefs.json → ...on_patterns/55_philosophical_beliefs.json b/...ation_patterns/philosophical_beliefs.json → ...on_patterns/55_philosophical_beliefs.json
diff --git a/...patterns/vehicle_registration_number.json → ...terns/56_vehicle_registration_number.json b/...patterns/vehicle_registration_number.json → ...terns/56_vehicle_registration_number.json
diff --git a/...ification_patterns/browsing_behavior.json → ...cation_patterns/57_browsing_behavior.json b/...ification_patterns/browsing_behavior.json → ...cation_patterns/57_browsing_behavior.json
diff --git a/...pe_classification_patterns/call_logs.json → ...classification_patterns/58_call_logs.json b/...pe_classification_patterns/call_logs.json → ...classification_patterns/58_call_logs.json
diff --git a/pkg/classification/db/data_type_classification_patterns/59_links_clicked.json b/pkg/classification/db/data_type_classification_patterns/59_links_clicked.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 59,
+  "data_type_uuid": "adfd29eb-8abb-41ea-bec6-9c0ffdfd9206",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Links clicked",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(links?|url)\\s?clicked|clicks?\\s?tracking\\b",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended", "unknown"]
+}
diff --git a/...type_classification_patterns/country.json → ...pe_classification_patterns/5_country.json b/...type_classification_patterns/country.json → ...pe_classification_patterns/5_country.json
diff --git a/pkg/classification/db/data_type_classification_patterns/60_date_of_birth.json b/pkg/classification/db/data_type_classification_patterns/60_date_of_birth.json
@@ -0,0 +1,16 @@
+{
+  "metadata": {
+    "version": "1.0"
+  },
+  "id": 60,
+  "data_type_uuid": "da48dfad-7322-411b-988d-5bde0d7bc659",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Date of birth",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(dob|bday|date\\s?of\\s?birth)|birth\\s?(date|year|day|month)\\z",
+  "include_types": ["string", "date"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/...lassification_patterns/date_of_birth.json → ...sification_patterns/61_date_of_birth.json b/...lassification_patterns/date_of_birth.json → ...sification_patterns/61_date_of_birth.json
diff --git a/pkg/classification/db/data_type_classification_patterns/62_spoken_languages.json b/pkg/classification/db/data_type_classification_patterns/62_spoken_languages.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 62,
+  "data_type_uuid": "c2f07a15-6cc1-451b-b8b4-7598bc0117e8",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Spoken Languages",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(spoken.*languages?|language)\\z",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/...sification_patterns/spoken_languages.json → ...ication_patterns/63_spoken_languages.json b/...sification_patterns/spoken_languages.json → ...ication_patterns/63_spoken_languages.json
diff --git a/...type_classification_patterns/accents.json → ...e_classification_patterns/64_accents.json b/...type_classification_patterns/accents.json → ...e_classification_patterns/64_accents.json
diff --git a/pkg/classification/db/data_type_classification_patterns/65_race.json b/pkg/classification/db/data_type_classification_patterns/65_race.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 65,
+  "data_type_uuid": "e4049ef1-da74-46dc-ac4e-f6b4aa0672ea",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Race",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(race|racial)\\b",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/..._type_classification_patterns/credit.json → ...pe_classification_patterns/66_credit.json b/..._type_classification_patterns/credit.json → ...pe_classification_patterns/66_credit.json
diff --git a/...classification_patterns/loan_records.json → ...ssification_patterns/67_loan_records.json b/...classification_patterns/loan_records.json → ...ssification_patterns/67_loan_records.json
diff --git a/...ssification_patterns/gender_identity.json → ...fication_patterns/68_gender_identity.json b/...ssification_patterns/gender_identity.json → ...fication_patterns/68_gender_identity.json
diff --git a/..._type_classification_patterns/gender.json → ...pe_classification_patterns/69_gender.json b/..._type_classification_patterns/gender.json → ...pe_classification_patterns/69_gender.json
diff --git a/...fication_patterns/credit_card_number.json → ...cation_patterns/6_credit_card_number.json b/...fication_patterns/credit_card_number.json → ...cation_patterns/6_credit_card_number.json
diff --git a/...ation_patterns/political_affiliation.json → ...on_patterns/70_political_affiliation.json b/...ation_patterns/political_affiliation.json → ...on_patterns/70_political_affiliation.json
diff --git a/...ype_classification_patterns/religion.json → ..._classification_patterns/71_religion.json b/...ype_classification_patterns/religion.json → ..._classification_patterns/71_religion.json
diff --git a/...classification_patterns/interactions.json → ...ssification_patterns/72_interactions.json b/...classification_patterns/interactions.json → ...ssification_patterns/72_interactions.json
diff --git a/...fication_patterns/general_reputation.json → ...ation_patterns/73_general_reputation.json b/...fication_patterns/general_reputation.json → ...ation_patterns/73_general_reputation.json
diff --git a/...e_classification_patterns/intentions.json → ...lassification_patterns/74_intentions.json b/...e_classification_patterns/intentions.json → ...lassification_patterns/74_intentions.json
diff --git a/...pe_classification_patterns/interests.json → ...classification_patterns/75_interests.json b/...pe_classification_patterns/interests.json → ...classification_patterns/75_interests.json
diff --git a/...a_type_classification_patterns/likes.json → ...ype_classification_patterns/76_likes.json b/...a_type_classification_patterns/likes.json → ...ype_classification_patterns/76_likes.json
diff --git a/...ype_classification_patterns/dislikes.json → ..._classification_patterns/77_dislikes.json b/...ype_classification_patterns/dislikes.json → ..._classification_patterns/77_dislikes.json
diff --git a/...ype_classification_patterns/attitude.json → ..._classification_patterns/78_attitude.json b/...ype_classification_patterns/attitude.json → ..._classification_patterns/78_attitude.json
diff --git a/...sification_patterns/physical_address.json → ...ication_patterns/79_physical_address.json b/...sification_patterns/physical_address.json → ...ication_patterns/79_physical_address.json
diff --git a/...assification_patterns/credit_records.json → ...sification_patterns/7_credit_records.json b/...assification_patterns/credit_records.json → ...sification_patterns/7_credit_records.json
diff --git a/...pe_classification_patterns/id_number.json → ...classification_patterns/80_id_number.json b/...pe_classification_patterns/id_number.json → ...classification_patterns/80_id_number.json
diff --git a/...e_classification_patterns/ip_address.json → ...lassification_patterns/82_ip_address.json b/...e_classification_patterns/ip_address.json → ...lassification_patterns/82_ip_address.json
diff --git a/pkg/classification/db/data_type_classification_patterns/83_mac_address.json b/pkg/classification/db/data_type_classification_patterns/83_mac_address.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 83,
+  "data_type_uuid": "84eb0f89-05f7-47a3-a8fb-67cc40e603c6",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Mac address",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(mac\\s?addr(ess)?)\\b",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/..._classification_patterns/mac_address.json → ...assification_patterns/84_mac_address.json b/..._classification_patterns/mac_address.json → ...assification_patterns/84_mac_address.json
diff --git a/pkg/classification/db/data_type_classification_patterns/85_firstname.json b/pkg/classification/db/data_type_classification_patterns/85_firstname.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 85,
+  "data_type_uuid": "380c8cde-ca2e-44ed-82db-2ab1e7c255c7",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean", "number"],
+  "friendly_name": "Firstname",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(first|middle|given)\\s?names?\\b",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["unknown"]
+}
diff --git a/...pe_classification_patterns/firstname.json → ...classification_patterns/86_firstname.json b/...pe_classification_patterns/firstname.json → ...classification_patterns/86_firstname.json
diff --git a/pkg/classification/db/data_type_classification_patterns/87_lastname.json b/pkg/classification/db/data_type_classification_patterns/87_lastname.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 87,
+  "data_type_uuid": "6574a267-e3bf-4ab5-832e-15b8863206df",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean", "number"],
+  "friendly_name": "Lastname",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(last|sur|family)\\s?name\\b",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["unknown"]
+}
diff --git a/...ype_classification_patterns/lastname.json → ..._classification_patterns/88_lastname.json b/...ype_classification_patterns/lastname.json → ..._classification_patterns/88_lastname.json
diff --git a/...ssification_patterns/credit_capacity.json → ...ification_patterns/8_credit_capacity.json b/...ssification_patterns/credit_capacity.json → ...ification_patterns/8_credit_capacity.json
diff --git a/pkg/classification/db/data_type_classification_patterns/90_fullname.json b/pkg/classification/db/data_type_classification_patterns/90_fullname.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 90,
+  "data_type_uuid": "1617291b-bc22-4267-ad5e-8054b2505958",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Fullname",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\A(\\S?(full|cardholder|display|person|customer|client|seller|doctor|patient|player|candidate|mentor|captain|winner|author|sender|recipient)\\s?name|name|(card\\s?holder))\\b",
+  "include_types": ["string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["known", "unknown_extended"]
+}
diff --git a/...ype_classification_patterns/username.json → ..._classification_patterns/91_username.json b/...ype_classification_patterns/username.json → ..._classification_patterns/91_username.json
diff --git a/pkg/classification/db/data_type_classification_patterns/92_physical_and_mental_health.json b/pkg/classification/db/data_type_classification_patterns/92_physical_and_mental_health.json
@@ -0,0 +1,14 @@
+{
+  "metadata": { "version": "1.0" },
+  "id": 92,
+  "data_type_uuid": "8421f13c-0b9a-422b-9080-55b78e7c07cd",
+  "exclude_regexp": null,
+  "exclude_types": ["boolean"],
+  "friendly_name": "Physical and mental health",
+  "health_context_data_type_uuid": null,
+  "include_regexp": "\\b(physical|mental)\\s?health\\b",
+  "include_types": ["object", "string"],
+  "match_column": true,
+  "match_object": false,
+  "object_type": ["unknown"]
+}
diff --git a/..._patterns/physical_and_mental_health.json → ...tterns/93_physical_and_mental_health.json b/..._patterns/physical_and_mental_health.json → ...tterns/93_physical_and_mental_health.json
diff --git a/...sification_patterns/family_structure.json → ...ication_patterns/94_family_structure.json b/...sification_patterns/family_structure.json → ...ication_patterns/94_family_structure.json
diff --git a/...ype_classification_patterns/siblings.json → ..._classification_patterns/95_siblings.json b/...ype_classification_patterns/siblings.json → ..._classification_patterns/95_siblings.json
diff --git a/...a_type_classification_patterns/image.json → ...ype_classification_patterns/96_image.json b/...a_type_classification_patterns/image.json → ...ype_classification_patterns/96_image.json
diff --git a/...ssification_patterns/income_brackets.json → ...fication_patterns/97_income_brackets.json b/...ssification_patterns/income_brackets.json → ...fication_patterns/97_income_brackets.json
diff --git a/...tterns/purchases_and_spending_habits.json → ...rns/98_purchases_and_spending_habits.json b/...tterns/purchases_and_spending_habits.json → ...rns/98_purchases_and_spending_habits.json
diff --git a/...pe_classification_patterns/passwords.json → ...classification_patterns/99_passwords.json b/...pe_classification_patterns/passwords.json → ...classification_patterns/99_passwords.json
diff --git a/..._classification_patterns/convictions.json → ...lassification_patterns/9_convictions.json b/..._classification_patterns/convictions.json → ...lassification_patterns/9_convictions.json
diff --git a/pkg/classification/db/db.go b/pkg/classification/db/db.go
@@ -5,8 +5,10 @@ import (
 	"encoding/json"
 	"log"
 	"regexp"
+	"strings"
 
 	"github.com/google/uuid"
+	"github.com/tangzero/inflector"
 )
 
 //go:embed recipes
@@ -55,7 +57,7 @@ type DataType struct {
 
 type DataTypeClassificationPattern struct {
 	Id                        int                 `json:"id"`
-	DataTypeUUID              uuid.UUID           `json:"data_type_uuid,omitempty"`
+	DataTypeUUID              *uuid.UUID          `json:"data_type_uuid,omitempty"`
 	IncludeRegexp             string              `json:"include_regexp"`
 	IncludeRegexpMatcher      *regexp.Regexp      `json:"include_regexp_matcher"`
 	ExcludeRegexp             string              `json:"exclude_regexp,omitempty"`
@@ -71,13 +73,14 @@ type DataTypeClassificationPattern struct {
 }
 
 type KnownPersonObjectPattern struct {
-	Id                   int            `json:"id"`
-	IncludeRegexp        string         `json:"include_regexp"`
-	IncludeRegexpMatcher *regexp.Regexp `json:"include_regexp_matcher"`
-	ExcludeRegexp        string         `json:"exclude_regexp,omitempty"`
-	ExcludeRegexpMatcher *regexp.Regexp `json:"exclude_regexp_matcher"`
-	Category             string         `json:"category"`
-	ActAsIdentifier      bool           `json:"act_as_identifier"`
+	Id                      int            `json:"id"`
+	IncludeRegexp           string         `json:"include_regexp"`
+	IncludeRegexpMatcher    *regexp.Regexp `json:"include_regexp_matcher"`
+	ExcludeRegexp           string         `json:"exclude_regexp,omitempty"`
+	ExcludeRegexpMatcher    *regexp.Regexp `json:"exclude_regexp_matcher"`
+	Category                string         `json:"category"`
+	ActAsIdentifier         bool           `json:"act_as_identifier"`
+	IdentifierRegexpMatcher *regexp.Regexp `json:"identifier_regexp_matcher"`
 }
 
 func Default() DefaultDB {
@@ -224,6 +227,16 @@ func defaultKnownPersonObjectPatterns() []KnownPersonObjectPattern {
 				handleError(err)
 			}
 		}
+		if knownPersonObjectPattern.ActAsIdentifier {
+			category := strings.ToLower(knownPersonObjectPattern.Category)
+			pluralCategory := inflector.Pluralize(category)
+
+			knownPersonObjectPattern.IdentifierRegexpMatcher, err = regexp.Compile("(?i)^[\\S]*(" + category + "|" + pluralCategory + ")\\s?(uu)?id")
+
+			if err != nil {
+				handleError(err)
+			}
+		}
 
 		knownPersonObjectPatterns = append(knownPersonObjectPatterns, knownPersonObjectPattern)
 	}

diff --git a/pkg/classification/interfaces/interfaces.go b/pkg/classification/interfaces/interfaces.go
@@ -8,6 +8,7 @@ import (
 	"github.com/bearer/curio/pkg/classification/db"
 	"github.com/bearer/curio/pkg/report/detections"
 	"github.com/bearer/curio/pkg/report/interfaces"
+	"github.com/bearer/curio/pkg/util/classify"
 	"github.com/bearer/curio/pkg/util/url"
 )
 
@@ -16,16 +17,11 @@ type ClassifiedInterface struct {
 	Classification *Classification `json:"classification"`
 }
 
-type ClassificationDecision struct {
-	State  url.ValidationState `json:"state"`
-	Reason string              `json:"reason"`
-}
-
 type Classification struct {
-	URL         string                 `json:"url"`
-	RecipeMatch bool                   `json:"recipe_match"`
-	RecipeName  string                 `json:"recipe_name,omitempty"`
-	Decision    ClassificationDecision `json:"decision"`
+	URL         string                          `json:"url"`
+	RecipeMatch bool                            `json:"recipe_match"`
+	RecipeName  string                          `json:"recipe_name,omitempty"`
+	Decision    classify.ClassificationDecision `json:"decision"`
 }
 
 type Classifier struct {
@@ -127,12 +123,12 @@ func (classifier *Classifier) Classify(data detections.Detection) (*ClassifiedIn
 	if err != nil {
 		return nil, err
 	}
-	if formatValidityCheck.State == url.Invalid {
+	if formatValidityCheck.State == classify.Invalid {
 		return &ClassifiedInterface{
 			Detection: &data,
 			Classification: &Classification{
 				URL: value,
-				Decision: ClassificationDecision{
+				Decision: classify.ClassificationDecision{
 					State:  formatValidityCheck.State,
 					Reason: formatValidityCheck.Reason,
 				},
@@ -159,7 +155,7 @@ func (classifier *Classifier) Classify(data detections.Detection) (*ClassifiedIn
 			Detection: &data,
 			Classification: &Classification{
 				URL: value,
-				Decision: ClassificationDecision{
+				Decision: classify.ClassificationDecision{
 					State:  internalValidityCheck.State,
 					Reason: internalValidityCheck.Reason,
 				},
@@ -182,15 +178,15 @@ func (classifier *Classifier) Classify(data detections.Detection) (*ClassifiedIn
 			},
 		}
 		if strings.Contains(recipeMatch.DetectionURLPart, "*") {
-			classifiedInterface.Classification.Decision = ClassificationDecision{
-				State:  url.Potential,
+			classifiedInterface.Classification.Decision = classify.ClassificationDecision{
+				State:  classify.Potential,
 				Reason: "recipe_match_with_wildcard",
 			}
 			return classifiedInterface, nil
 		}
 
-		classifiedInterface.Classification.Decision = ClassificationDecision{
-			State:  url.Valid,
+		classifiedInterface.Classification.Decision = classify.ClassificationDecision{
+			State:  classify.Valid,
 			Reason: "recipe_match",
 		}
 		return classifiedInterface, nil
@@ -206,7 +202,7 @@ func (classifier *Classifier) Classify(data detections.Detection) (*ClassifiedIn
 		Detection: &data,
 		Classification: &Classification{
 			URL: value,
-			Decision: ClassificationDecision{
+			Decision: classify.ClassificationDecision{
 				State:  validityCheck.State,
 				Reason: validityCheck.Reason,
 			},