@stll/anonymize-wasm 1.4.6 → 1.4.8

package/dist/triggers.global.mjs

@@ -1,33 +1,78 @@
 //#region src/data/triggers.global.json
-var triggers_global_default = [{
-	"id": "swift-bic",
-	"triggers": ["SWIFT", "BIC"],
-	"label": "bank account number",
-	"strategy": {
-		"type": "n-words",
-		"count": 1
+var triggers_global_default = [
+	{
+		"id": "swift-bic",
+		"triggers": ["SWIFT", "BIC"],
+		"label": "bank account number",
+		"strategy": {
+			"type": "n-words",
+			"count": 1
+		},
+		"extensions": ["add-colon"],
+		"validations": [{
+			"type": "matches-pattern",
+			"pattern": "^[A-Za-z]{4}[A-Za-z]{2}[A-Za-z0-9]{2}(?:[A-Za-z0-9]{3})?$"
+		}]
 	},
-	"extensions": ["add-colon"],
-	"validations": [{
-		"type": "matches-pattern",
-		"pattern": "^[A-Za-z]{4}[A-Za-z]{2}[A-Za-z0-9]{2}(?:[A-Za-z0-9]{3})?$"
-	}]
-}, {
-	"id": "amount-prefix",
-	"triggers": [
-		"ve výši",
-		"in the amount of",
-		"in Höhe von",
-		"d'un montant de",
-		"w wysokości",
-		"nell'importo di",
-		"por un importe de"
-	],
-	"label": "monetary amount",
-	"strategy": { "type": "to-next-comma" },
-	"extensions": ["add-colon"],
-	"validations": [{ "type": "has-digits" }]
-}];
+	{
+		"id": "us-aba-routing",
+		"triggers": [
+			"ABA",
+			"ABA Number",
+			"RTN",
+			"Routing Number",
+			"Routing No.",
+			"Routing Transit Number"
+		],
+		"label": "bank account number",
+		"strategy": {
+			"type": "n-words",
+			"count": 1
+		},
+		"extensions": ["add-colon"],
+		"validations": [{ "type": "has-digits" }, {
+			"type": "valid-id",
+			"validator": "us.rtn"
+		}]
+	},
+	{
+		"id": "intl-labeled-phone",
+		"triggers": [
+			"fax",
+			"telecopy",
+			"telecopier",
+			"facsimile",
+			"telephone",
+			"phone number",
+			"contact phone number"
+		],
+		"label": "phone number",
+		"strategy": {
+			"type": "match-pattern",
+			"pattern": "(?:\\+\\d{1,3}[\\s.\\-]?)?\\(?\\d{1,4}\\)?(?:[\\s.\\-]\\d{1,4}){2,4}"
+		},
+		"validations": [{
+			"type": "matches-pattern",
+			"pattern": "(?:\\d[^\\d]*){6,}"
+		}]
+	},
+	{
+		"id": "amount-prefix",
+		"triggers": [
+			"ve výši",
+			"in the amount of",
+			"in Höhe von",
+			"d'un montant de",
+			"w wysokości",
+			"nell'importo di",
+			"por un importe de"
+		],
+		"label": "monetary amount",
+		"strategy": { "type": "to-next-comma" },
+		"extensions": ["add-colon"],
+		"validations": [{ "type": "has-digits" }]
+	}
+];
 //#endregion
 export { triggers_global_default as default };
 

package/dist/wasm.d.mts

@@ -117,7 +117,7 @@ type TriggerValidation = {
 };
 /** Built-in stdnum validators that can be referenced
  *  by `valid-id` validations. */
-type ValidIdValidator = "br.cpf" | "br.cnpj";
+type ValidIdValidator = "br.cpf" | "br.cnpj" | "us.rtn";
 /** Auto-generated trigger variants — closed set. */
 type TriggerExtension = "add-colon" | "add-trailing-space" | "add-colon-space" | "normalize-spaces";
 /** V2 trigger config entry (JSON shape). */

package/dist/wasm.mjs

@@ -8592,6 +8592,35 @@ const HONORIFIC_BOUNDARY = new Set([
 	"Señora"
 ]);
 /**
+* Honorifics that are abbreviations: a dot after them is an
+* abbreviation dot (same sentence), so the detector keeps an
+* optional `.` between the title and the name ("Mr. Smith").
+* Every other honorific is a full word — a trailing dot ends a
+* sentence, so the detector must NOT consume it (otherwise a span
+* like "President. The Employee" crosses the sentence boundary).
+*
+* Maintained explicitly, NOT derived from "ends in a dot": "Mr" is
+* an abbreviation written without a dot, and "Lord" is a full word.
+*/
+const HONORIFIC_ABBREVIATION = new Set([
+	"Avv.",
+	"Dott.",
+	"M.",
+	"Me",
+	"Messrs",
+	"Mlle",
+	"Mme",
+	"Mr",
+	"Mrs",
+	"Ms",
+	"Pr",
+	"Pr.",
+	"Sig.",
+	"Sig.ra",
+	"Sr.",
+	"Sra."
+]);
+/**
 * Post-nominal degrees (comma or space separated after name).
 * Plain text; the detector auto-escapes for regex.
 */
@@ -9118,11 +9147,14 @@ const POST_NOMINAL = POST_NOMINALS.toSorted((a, b) => b.length - a.length).map(e
 const NAME_WORD = `\\p{Lu}\\p{Ll}+`;
 const PARTICLE = "(?:van der|van den|de la|della|von|van|dos|ibn|ben|bin|del|zum|zur|ten|ter|da|de|di|al|el|le|la|zu|af|av)";
 const SP = "[^\\S\\n]";
-/** Honorific alternation built from titles.ts config. */
-const HONORIFIC_ALT = [...HONORIFICS].toSorted((a, b) => b.length - a.length).map((h) => {
+/** Honorific alternation built from titles.ts config. Sorted
+* longest-first so e.g. "Sig.ra" wins over "Sig.". */
+const buildHonorificAlt = (entries) => [...entries].toSorted((a, b) => b.length - a.length).map((h) => {
 	const escaped = escapeRegex$2(h);
 	return HONORIFIC_BOUNDARY.has(h) ? `\\b${escaped}` : escaped;
 }).join("|");
+const HONORIFIC_ABBREV_ALT = buildHonorificAlt(HONORIFICS.filter((h) => HONORIFIC_ABBREVIATION.has(h)));
+const HONORIFIC_FULLWORD_ALT = buildHonorificAlt(HONORIFICS.filter((h) => !HONORIFIC_ABBREVIATION.has(h)));
 const AMOUNT_WORDS = amount_words_default;
 const toEntry = (validator, label, score) => {
 	const pattern = toRegex(validator).source;
@@ -9214,7 +9246,7 @@ const TITLED_PERSON = {
 	score: .95
 };
 const HONORIFIC_PERSON = {
-	pattern: `(?:${HONORIFIC_ALT})\\.?${SP}+${NAME_WORD}(?:(?:${SP}|-){1,2}(?:${PARTICLE}${SP}+)?${NAME_WORD}){0,3}(?:${SP}+(?:QC|KC|SC|LJ|AG))?`,
+	pattern: `(?:(?:${HONORIFIC_ABBREV_ALT})\\.?|(?:${HONORIFIC_FULLWORD_ALT}))${SP}+${NAME_WORD}(?:(?:${SP}|-){1,2}(?:${PARTICLE}${SP}+)?${NAME_WORD}){0,3}(?:${SP}+(?:QC|KC|SC|LJ|AG))?`,
 	label: "person",
 	score: .95
 };
@@ -10089,7 +10121,8 @@ const dropOverlapping = (candidates) => {
 //#region src/detectors/triggers.ts
 const VALID_ID_VALIDATORS = {
 	"br.cpf": br.cpf,
-	"br.cnpj": br.cnpj
+	"br.cnpj": br.cnpj,
+	"us.rtn": us.rtn
 };
 const TRIGGER_SCORE = .95;
 const WHITESPACE_RE$1 = /\s+/;