euredact 0.3.7 → 0.3.9

package/dist/cjs/types.js

@@ -36,6 +36,16 @@ var EntityType;
     EntityType["HEALTH_INSURANCE"] = "HEALTH_INSURANCE";
     EntityType["HEALTHCARE_PROVIDER"] = "HEALTHCARE_PROVIDER";
     EntityType["CHAMBER_OF_COMMERCE"] = "CHAMBER_OF_COMMERCE";
+    /**
+     * Employee, badge or customer number tied to a person.
+     *
+     * Emitted **only** when an explicit label names it — see `rules/cues.ts`.
+     * There is no pattern for an internal identifier because there is no shape
+     * for one; without the label, a digit run is not distinguishable from any
+     * other. The type exists so that a labelled employee number is filed
+     * correctly instead of being claimed by the phone pattern.
+     */
+    EntityType["INTERNAL_ID"] = "INTERNAL_ID";
     EntityType["IMEI"] = "IMEI";
     EntityType["GPS_COORDINATES"] = "GPS_COORDINATES";
     EntityType["UUID"] = "UUID";

package/dist/esm/rules/cues.d.ts

@@ -0,0 +1,121 @@
+/**
+ * Local cues: what the document calls the value sitting next to it.
+ *
+ * A label touching the left edge of a span is the strongest statement a
+ * document makes about what that value *is*. "Phone: 0705237535" is a phone
+ * number even though those digits pass the Swedish personnummer checksum, and
+ * "Αρ. Ταυτότητας: 00892341" is an identity-card number even though nothing in
+ * the engine can checksum it.
+ *
+ * This table is the single source of that knowledge. Three callers read it, and
+ * none of them may move a span:
+ *
+ * 1. `localCueBonus` — ranks a candidate above its rivals on the *same span*
+ *    when the cue names its type. The oldest use, and why the table exists.
+ * 2. `detectWithEvidence` — re-admits a candidate whose checksum failed when the
+ *    cue names that same type. A declined identifier with its own label in front
+ *    of it is still that identifier, mistyped or truncated.
+ * 3. `retypedBy` — relabels a winning generic candidate whose type the cue
+ *    contradicts, when nothing of the cued type claimed the span.
+ *
+ * Consolidated here from two places that had drifted apart: `LOCAL_CUES` in
+ * `engine.ts` (typed, but missing most of Europe) and `ID_LABEL_BEFORE` in
+ * `suppressors.ts` (broader, but untyped — it could only *delete* a phone
+ * candidate, which left the value unmasked).
+ *
+ * Kept character-for-character in step with `euredact/rules/cues.py`. Two
+ * constructs are written the way they are so that both engines agree:
+ *
+ * * Boundaries are `(?<![A-Za-z0-9_])`, not `\b`. JavaScript's `\b` is
+ *   ASCII-only, so `\bΑΦΜ` never matches — a Greek letter is not a word
+ *   character there, and a space before it is not a transition. A boundary of
+ *   some kind is required regardless: without one the short alternatives match
+ *   the *tail* of an ordinary word. "NIS" matched "tālru**nis**", the Latvian
+ *   for telephone, and suppressed 653 real phone numbers; "iva" matched
+ *   "Pr**iva**t:" and read a personal e-mail address as a VAT number.
+ * * Neither the qualifier nor the run-on may use `\w`. The qualifier is a
+ *   negated ASCII class, fixed for this in 0.3.8; `[^\W\d_]` would reject
+ *   "εταιρειας" here for the same ASCII reason. The run-on was *not* fixed then
+ *   and went on diverging for another release: Slovak "telefón 0956550012"
+ *   needs it to absorb "efón" after `tel`, and Bulgarian
+ *   "пощенски кодове 4000-4999" needs "ове" after `пощенски код`. Python's
+ *   Unicode `\w` did; this SDK's ASCII `\w` did not, so one engine said `PHONE`
+ *   and the other `NATIONAL_ID` on the same document. They were the last two
+ *   type divergences on the corpus, and only the type-aware half of
+ *   `make parity` could see them.
+ *
+ *   The run-on is spelled `(?:[A-Za-z0-9_]|[^\x00-\x7F])` — an ASCII word
+ *   character, or any non-ASCII character — rather than as a negated class of
+ *   separators. A negated class also admits `'`, `%`, `&`, `@` and the rest of
+ *   ASCII punctuation, which `\w` never did, and widening it that far was
+ *   measured at 46 extra false positives with hints and 57 blind over the
+ *   152,300-document corpus. This is `\w` plus the non-ASCII letters `\w`
+ *   should have matched all along, and nothing else.
+ *
+ * Every label ends in `(?:<run-on>|\s+<one word>)`: the label either runs on
+ * into a longer word ("telefoon" → "telefoonnummer") **or** takes one qualifier
+ * word naming whose identifier it is ("ΑΦΜ εταιρειας:", "Tel Nr:") — never both.
+ * Allowing both let "nie" grow into the surname "Nieminen" and then swallow the
+ * real label in "Matti Nieminen\nDOB: 08.05.1994", reading a date of birth as a
+ * Spanish NIE: 52 false positives across the corpus.
+ */
+import { EntityType } from "../types.js";
+/**
+ * How far back a cue may sit. Short on purpose: a cue is only evidence about
+ * the value it introduces, which is the lesson of the postal-code year defect,
+ * where a cue 150 characters away licensed every number in the window.
+ */
+export declare const CUE_WINDOW = 32;
+/**
+ * (entity type, label pattern). Ordered: the first match wins, so the narrower
+ * label comes first where two could read the same text.
+ */
+export declare const CUES: Array<[EntityType, RegExp]>;
+/**
+ * The entity type a label immediately before `start` names, or null.
+ *
+ * Reads at most `CUE_WINDOW` characters, and every pattern is anchored to the
+ * end of that window, so the cue must *touch* the span. A label further away is
+ * about some other value.
+ */
+export declare function cuedType(text: string, start: number): EntityType | null;
+/**
+ * Types a label can assert on its own.
+ *
+ * PHONE is absent on purpose: "Tel:" in front of something no phone pattern
+ * matched means the document is laid out oddly, not that the value is a phone
+ * number. So are EMAIL, DOB, VIN and the rest — those carry their own
+ * structure, and a nearby word is not entitled to overrule it.
+ */
+export declare const CUE_TARGETS: Set<string>;
+/**
+ * Which of those a label may also *rescue* — re-admit after its checksum
+ * failed. Until 0.3.9 this was the same set as CUE_TARGETS and it cannot stay
+ * that way: re-typing a span the engine already decided to mask is cheap to be
+ * wrong about, while rescuing one asserts that a value which failed its check
+ * digit is a real identifier anyway.
+ *
+ * BIC's absence is what keeps the rescue honest. Its validator is a *registry
+ * lookup*, not a checksum, so a failure means "no such bank", which no label can
+ * talk you out of. Rescuing it read 34 unlisted codes behind a "BIC:" label as
+ * real ones. The same reasoning keeps CREDIT_CARD and BANK_ACCOUNT out: Luhn and
+ * mod-97 are strong enough that a failure really does mean "not one of these".
+ * BANK_ACCOUNT joined CUE_TARGETS in 0.3.9 so "sort code 20-45-91" stops being a
+ * LICENSE_PLATE, and is kept out here for exactly the 0.3.8 reason.
+ *
+ * HEALTHCARE_PROVIDER and SECRET are absent because neither is checksummed;
+ * there is no failed validation for a label to overrule in the first place.
+ */
+export declare const RESCUE_TARGETS: Set<string>;
+/**
+ * The type a cue overrules `entityType` with, or null to leave it alone.
+ *
+ * Both gates are load-bearing. Measured over 2,000 corpus documents, re-typing
+ * without them fired 52 times and got roughly 30 of those wrong — EMAIL read as
+ * VAT, a date of birth as a phone number, a VIN as VAT — against 20 real fixes.
+ * With them: 14 re-typings, every one of them PHONE to a structured identifier.
+ *
+ * `countryScore` is the document's support for the country the winning pattern
+ * came from; see RETYPABLE_UNCORROBORATED.
+ */
+export declare function retypedBy(text: string, start: number, entityType: EntityType | string, countryScore: number): EntityType | null;

package/dist/esm/rules/cues.js

@@ -0,0 +1,235 @@
+/**
+ * Local cues: what the document calls the value sitting next to it.
+ *
+ * A label touching the left edge of a span is the strongest statement a
+ * document makes about what that value *is*. "Phone: 0705237535" is a phone
+ * number even though those digits pass the Swedish personnummer checksum, and
+ * "Αρ. Ταυτότητας: 00892341" is an identity-card number even though nothing in
+ * the engine can checksum it.
+ *
+ * This table is the single source of that knowledge. Three callers read it, and
+ * none of them may move a span:
+ *
+ * 1. `localCueBonus` — ranks a candidate above its rivals on the *same span*
+ *    when the cue names its type. The oldest use, and why the table exists.
+ * 2. `detectWithEvidence` — re-admits a candidate whose checksum failed when the
+ *    cue names that same type. A declined identifier with its own label in front
+ *    of it is still that identifier, mistyped or truncated.
+ * 3. `retypedBy` — relabels a winning generic candidate whose type the cue
+ *    contradicts, when nothing of the cued type claimed the span.
+ *
+ * Consolidated here from two places that had drifted apart: `LOCAL_CUES` in
+ * `engine.ts` (typed, but missing most of Europe) and `ID_LABEL_BEFORE` in
+ * `suppressors.ts` (broader, but untyped — it could only *delete* a phone
+ * candidate, which left the value unmasked).
+ *
+ * Kept character-for-character in step with `euredact/rules/cues.py`. Two
+ * constructs are written the way they are so that both engines agree:
+ *
+ * * Boundaries are `(?<![A-Za-z0-9_])`, not `\b`. JavaScript's `\b` is
+ *   ASCII-only, so `\bΑΦΜ` never matches — a Greek letter is not a word
+ *   character there, and a space before it is not a transition. A boundary of
+ *   some kind is required regardless: without one the short alternatives match
+ *   the *tail* of an ordinary word. "NIS" matched "tālru**nis**", the Latvian
+ *   for telephone, and suppressed 653 real phone numbers; "iva" matched
+ *   "Pr**iva**t:" and read a personal e-mail address as a VAT number.
+ * * Neither the qualifier nor the run-on may use `\w`. The qualifier is a
+ *   negated ASCII class, fixed for this in 0.3.8; `[^\W\d_]` would reject
+ *   "εταιρειας" here for the same ASCII reason. The run-on was *not* fixed then
+ *   and went on diverging for another release: Slovak "telefón 0956550012"
+ *   needs it to absorb "efón" after `tel`, and Bulgarian
+ *   "пощенски кодове 4000-4999" needs "ове" after `пощенски код`. Python's
+ *   Unicode `\w` did; this SDK's ASCII `\w` did not, so one engine said `PHONE`
+ *   and the other `NATIONAL_ID` on the same document. They were the last two
+ *   type divergences on the corpus, and only the type-aware half of
+ *   `make parity` could see them.
+ *
+ *   The run-on is spelled `(?:[A-Za-z0-9_]|[^\x00-\x7F])` — an ASCII word
+ *   character, or any non-ASCII character — rather than as a negated class of
+ *   separators. A negated class also admits `'`, `%`, `&`, `@` and the rest of
+ *   ASCII punctuation, which `\w` never did, and widening it that far was
+ *   measured at 46 extra false positives with hints and 57 blind over the
+ *   152,300-document corpus. This is `\w` plus the non-ASCII letters `\w`
+ *   should have matched all along, and nothing else.
+ *
+ * Every label ends in `(?:<run-on>|\s+<one word>)`: the label either runs on
+ * into a longer word ("telefoon" → "telefoonnummer") **or** takes one qualifier
+ * word naming whose identifier it is ("ΑΦΜ εταιρειας:", "Tel Nr:") — never both.
+ * Allowing both let "nie" grow into the surname "Nieminen" and then swallow the
+ * real label in "Matti Nieminen\nDOB: 08.05.1994", reading a date of birth as a
+ * Spanish NIE: 52 false positives across the corpus.
+ */
+import { EntityType } from "../types.js";
+/**
+ * How far back a cue may sit. Short on purpose: a cue is only evidence about
+ * the value it introduces, which is the lesson of the postal-code year defect,
+ * where a cue 150 characters away licensed every number in the window.
+ */
+export const CUE_WINDOW = 32;
+/**
+ * (entity type, label pattern). Ordered: the first match wins, so the narrower
+ * label comes first where two could read the same text.
+ */
+export const CUES = [
+    // Phone. Ranking only — nothing is ever relabelled *to* PHONE: a phone cue in
+    // front of a span that no phone pattern matched says the document is laid out
+    // unusually, not that the value is a phone number.
+    [EntityType.PHONE,
+        /(?<![A-Za-z0-9_])(?:phone|tel|telephone|téléphone|telefoon|telefon|telefono|teléfono|tlf|mobil|mobile|gsm|handy|sími|puh|móvil|cell|tālrunis|τηλέφωνο|τηλ)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // National identity number.
+    [EntityType.NATIONAL_ID,
+        /(?<![A-Za-z0-9_])(?:bsn|burgerservicenummer(?:\s*\(bsn\))?|personnummer|rijksregisternummer|nationaal\s*nummer|numéro\s*national|national\s*(?:id|number)|identiteitsnummer|henkilötunnus|kennitala|cpr(?:-?nummer)?|nif|nie|dni|rr|nn|nir|insz|niss|nis|matricule|ausweisnummer|personalausweis|osobní\s*číslo|ЕГН|EGN)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Cyprus: "ID number" in both official languages, plus the Greek abbreviation
+    // ΑΔΤ (Αστυνομική Ταυτότητα). Neither has a phone reading.
+    [EntityType.NATIONAL_ID,
+        /(?<![A-Za-z0-9_])(?:αρ\.?\s*ταυτότητας|ταυτότητας|αδτ|kimlik\s*numaras[ıi])(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Social security.
+    [EntityType.SSN,
+        /(?<![A-Za-z0-9_])(?:ssn|social\s*security|sozialversicherungsnummer|svnr|sofi)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Tax number. Greece's ΑΦΜ is issued by the tax authority; the identity-card
+    // number is the ΑΔΤ, above.
+    [EntityType.TAX_ID,
+        /(?<![A-Za-z0-9_])(?:αφμ|α\.φ\.μ\.|steuer-?id|steuernummer|st\.?-?nr|stnr|tin|finanzamt\s+ist|tax\s*(?:id|no|number)|daňové\s*číslo|numer\s*podatkowy)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Health insurance: the insured person.
+    [EntityType.HEALTH_INSURANCE,
+        /(?<![A-Za-z0-9_])(?:versichertennummer|krankenversicherung|kvnr|kv-?nr|mutualité|ziekenfonds|aansluitingsnummer|medical\s*card(?:\s*(?:no|number))?)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Healthcare provider: the clinician or practice, not the patient — the Dutch
+    // AGB-code, the German LANR, the UK GMC number.
+    [EntityType.HEALTHCARE_PROVIDER,
+        /(?<![A-Za-z0-9_])(?:agb-?code|lanr|bsnr|gmc(?:\s*(?:no|number|reg))?|big-?nummer|zorgverlener(?:snummer)?)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Company / trade register. "Companies House" and "Company Registration
+    // Number" are written out: the tail allows a run-on *or* one qualifier word,
+    // never a second word, so a three-word label needs to be spelled.
+    [EntityType.CHAMBER_OF_COMMERCE,
+        /(?<![A-Za-z0-9_])(?:siren|siret|kbo|bce|kvk|ondernemingsnummer|ondernemingen\s+onder\s+nummer|kruispuntbank|numéro\s*d'entreprise|enterprise\s*number|handelsregister|companies\s*house(?:\s*(?:registration|reg|no|number))?|company\s*registration(?:\s*(?:number|no))?|company\s*(?:no|number|reg)|organisationsnummer|orgnr|i[čc]o|identifikační\s*číslo|ЕИК|eik|bulstat|cvr(?:-?nummer)?|virksomhedsnummer)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // VAT.
+    [EntityType.VAT,
+        /(?<![A-Za-z0-9_])(?:vat|btw|tva|ust|iva|moms|alv|mwst|dič|vsk)(?:(?:[A-Za-z0-9_.\-]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Bank account. A UK sort code is NN-NN-NN, also a licence-plate shape, so
+    // "sort code 20-45-91" was typed LICENSE_PLATE with the label in front of it.
+    // Retype target only — a failed mod-97 is never rescued by a label.
+    [EntityType.BANK_ACCOUNT,
+        /(?<![A-Za-z0-9_])(?:sort\s*code|account\s*(?:no|number)|rekeningnummer|kontonummer|numéro\s*de\s*compte|sort-?code)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Passport.
+    [EntityType.PASSPORT,
+        /(?<![A-Za-z0-9_])(?:passport(?:\s*(?:no|number))?|paspoort(?:nummer)?|reisepass(?:nummer)?|passeport|passnummer)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // BIC / SWIFT.
+    [EntityType.BIC,
+        /(?<![A-Za-z0-9_])(?:bic|swift)(?:[A-Za-z0-9_\/]|[^\x00-\x7F])*\s*[:.\-]?\s*\(?\s*$/i],
+    // Postal code. A postal code loses every contested span on priority (it is
+    // the weakest evidence the engine has), so without a cue entry
+    // "Cod postal: 040171" was handed to a German phone pattern.
+    [EntityType.POSTAL_CODE,
+        /(?<![A-Za-z0-9_])(?:cod\s*po[sș]tal|postnummer|postnr|postleitzahl|plz(?:-?bereiche?)?|postcode|code\s*postal|codice\s*postale|kod\s*pocztowy|ps[čc]|τ\.?κ\.?|пощенски\s*код)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Internal / employee identifier. The canon calls these INTERNAL_ID and
+    // annotates them with an LLM, so the engine has no pattern for them — but it
+    // does have a phone pattern that was happily claiming them. The cue is the
+    // only thing that identifies one, which is why the engine emits this type
+    // from here and nowhere else.
+    [EntityType.INTERNAL_ID,
+        /(?<![A-Za-z0-9_])(?:medarbejdernummer|ansattnummer|anställningsnummer|personalnummer|personeelsnummer|matricule\s*salarié|employee\s*(?:no|number|id)|badge(?:\s*(?:no|number))?|betriebsstätten(?:nr|nummer)|grundstücks(?:nr|nummer)|dossier-?(?:nr|nummer)|aktenzeichen|osobní\s*(?:číslo\s*)?zaměstnance)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+    // Credential. Typed SECRET because that is the type this SDK has; the
+    // training pipeline's report asks for CREDENTIAL, which does not exist here.
+    [EntityType.SECRET,
+        /(?<![A-Za-z0-9_])(?:tan-?activatiecode|activatiecode|activation\s*code|verificatiecode|verification\s*code|otp|pincode)(?:(?:[A-Za-z0-9_]|[^\x00-\x7F])*|\s+[^\s:.\-\d,;()\/]{2,20})\s*\)?\s*[:.\-]*\s*$/i],
+];
+/**
+ * The entity type a label immediately before `start` names, or null.
+ *
+ * Reads at most `CUE_WINDOW` characters, and every pattern is anchored to the
+ * end of that window, so the cue must *touch* the span. A label further away is
+ * about some other value.
+ */
+export function cuedType(text, start) {
+    const before = text.slice(Math.max(0, start - CUE_WINDOW), start);
+    for (const [entityType, pattern] of CUES) {
+        if (pattern.test(before))
+            return entityType;
+    }
+    return null;
+}
+/**
+ * Shapes so generic that a label in front is better evidence than the pattern
+ * that matched. A bare digit run is not a phone number because it *could* be
+ * dialled.
+ */
+const RETYPABLE = new Set([
+    EntityType.PHONE, EntityType.POSTAL_CODE, EntityType.LICENSE_PLATE,
+]);
+/**
+ * Retypable, but only when the document gives its country no support at all.
+ *
+ * These carry a checksum, so normally the pattern outranks any label. But a
+ * checksum only says the digits fit *some* national scheme, and a weak one fits
+ * by luck — the same reasoning that demotes an uncorroborated validated
+ * candidate to priority 1 in `engine.ts`. At a country score of 0.0 the engine
+ * is already saying "this passed a Czech checksum in a document with nothing
+ * Czech about it", and an explicit "Passport No.:" is the better evidence.
+ *
+ * Restricted to zero country support on purpose: a Dutch BSN in a Dutch
+ * document scores above zero and stays a NATIONAL_ID whatever label sits near
+ * it, so this cannot relabel a domestic identifier — only the coincidental
+ * foreign ones, which is where "Passport No.: 512847603" and
+ * "Betriebsstättennr. 260326822" both landed, each reported as Czech.
+ */
+const RETYPABLE_UNCORROBORATED = new Set([EntityType.NATIONAL_ID]);
+/**
+ * Types a label can assert on its own.
+ *
+ * PHONE is absent on purpose: "Tel:" in front of something no phone pattern
+ * matched means the document is laid out oddly, not that the value is a phone
+ * number. So are EMAIL, DOB, VIN and the rest — those carry their own
+ * structure, and a nearby word is not entitled to overrule it.
+ */
+export const CUE_TARGETS = new Set([
+    EntityType.NATIONAL_ID, EntityType.SSN, EntityType.TAX_ID,
+    EntityType.HEALTH_INSURANCE, EntityType.HEALTHCARE_PROVIDER,
+    EntityType.CHAMBER_OF_COMMERCE, EntityType.VAT, EntityType.POSTAL_CODE,
+    EntityType.PASSPORT, EntityType.INTERNAL_ID, EntityType.BANK_ACCOUNT,
+    EntityType.SECRET,
+]);
+/**
+ * Which of those a label may also *rescue* — re-admit after its checksum
+ * failed. Until 0.3.9 this was the same set as CUE_TARGETS and it cannot stay
+ * that way: re-typing a span the engine already decided to mask is cheap to be
+ * wrong about, while rescuing one asserts that a value which failed its check
+ * digit is a real identifier anyway.
+ *
+ * BIC's absence is what keeps the rescue honest. Its validator is a *registry
+ * lookup*, not a checksum, so a failure means "no such bank", which no label can
+ * talk you out of. Rescuing it read 34 unlisted codes behind a "BIC:" label as
+ * real ones. The same reasoning keeps CREDIT_CARD and BANK_ACCOUNT out: Luhn and
+ * mod-97 are strong enough that a failure really does mean "not one of these".
+ * BANK_ACCOUNT joined CUE_TARGETS in 0.3.9 so "sort code 20-45-91" stops being a
+ * LICENSE_PLATE, and is kept out here for exactly the 0.3.8 reason.
+ *
+ * HEALTHCARE_PROVIDER and SECRET are absent because neither is checksummed;
+ * there is no failed validation for a label to overrule in the first place.
+ */
+export const RESCUE_TARGETS = new Set([
+    EntityType.NATIONAL_ID, EntityType.SSN, EntityType.TAX_ID,
+    EntityType.HEALTH_INSURANCE, EntityType.CHAMBER_OF_COMMERCE,
+    EntityType.VAT, EntityType.POSTAL_CODE, EntityType.PASSPORT,
+    EntityType.INTERNAL_ID,
+]);
+/**
+ * The type a cue overrules `entityType` with, or null to leave it alone.
+ *
+ * Both gates are load-bearing. Measured over 2,000 corpus documents, re-typing
+ * without them fired 52 times and got roughly 30 of those wrong — EMAIL read as
+ * VAT, a date of birth as a phone number, a VIN as VAT — against 20 real fixes.
+ * With them: 14 re-typings, every one of them PHONE to a structured identifier.
+ *
+ * `countryScore` is the document's support for the country the winning pattern
+ * came from; see RETYPABLE_UNCORROBORATED.
+ */
+export function retypedBy(text, start, entityType, countryScore) {
+    const type = String(entityType);
+    if (!RETYPABLE.has(type)
+        && !(RETYPABLE_UNCORROBORATED.has(type) && countryScore === 0))
+        return null;
+    const cued = cuedType(text, start);
+    if (cued === null || cued === entityType || !CUE_TARGETS.has(String(cued)))
+        return null;
+    return cued;
+}

package/dist/esm/rules/engine.d.ts

@@ -8,6 +8,38 @@ import { type RawMatch } from "./matchers.js";
 export declare const COUNTRY_CODE_ALIASES: Record<string, string>;
 /** Map a caller-supplied code to a registered one, or null if unknown. */
 export declare function resolveCountryCode(countryCode: string): string | null;
+/**
+ * Last-resort ordering for candidates every other field has tied on.
+ *
+ * Reaching this means the engine has no evidence left: same span, no cue, same
+ * priority, the same (usually zero) country score, and the same declared scope.
+ * Something still has to win, and before this the winner was whichever candidate
+ * happened to be generated first — which is country *registration* order, and
+ * the two SDKs do not share one. Python registers alphabetically
+ * (`AT, BE, BG, CH, CY, CZ, ...`); this SDK uses a curated order
+ * (`NL, BE, DE, AT, CH, FR, ..., PT, LU, PL, ..., CZ`). So a bare digit run that
+ * several national schemes accept was filed as a Czech `NATIONAL_ID` by Python
+ * and a Portuguese `PHONE` here — identical characters masked, contradictory
+ * labels, and `make parity` compared only characters, so it stayed green through
+ * the whole of 0.3.8.
+ *
+ * The order reproduces what Python already did rather than inventing a new one,
+ * because every accuracy figure this engine has published was measured with
+ * Python resolving these ties by its registration order. Ordering on the entity
+ * type instead was tried first and re-tuned the corpus twice over: it turned the
+ * German `Steuerß12345678911` from `TAX_ID`/DE into `NATIONAL_ID`/EL, and moved
+ * 820 further spans from `DOB` to `DATE_OF_DEATH`. So the key is deliberately
+ * not total — candidates from the same country are left to the stable sort,
+ * which preserves the order that country's pattern list was written in, and both
+ * SDKs write theirs in the same order.
+ *
+ * Taken from the **pattern**, never the finished detection: this SDK re-types a
+ * cued candidate before the sort and Python re-types after it, so keying on the
+ * final type would reintroduce the divergence in a subtler form.
+ *
+ * Kept character-for-character in step with `tie_key` in `rules/engine.py`.
+ */
+export declare function tieKey(countryCode: string): string;
 export declare class RuleEngine {
     private matcher;
     private loadedCountries;

package/dist/esm/rules/engine.js

@@ -1,6 +1,7 @@
 import { DetectionSource, EntityType } from "../types.js";
 import { MultiPatternMatcher } from "./matchers.js";
 import { shouldSuppress, SuppressionScratch } from "./suppressors.js";
+import { RESCUE_TARGETS, cuedType, retypedBy } from "./cues.js";
 import { detectStructuralDob } from "./structural.js";
 import { COUNTRY_CONFIGS } from "./countries/index.js";
 import * as evidenceMod from "./evidence.js";
@@ -43,6 +44,48 @@ export function resolveCountryCode(countryCode) {
     code = COUNTRY_CODE_ALIASES[code] ?? code;
     return code in COUNTRY_CONFIGS && code !== "SHARED" ? code : null;
 }
+/**
+ * Last-resort ordering for candidates every other field has tied on.
+ *
+ * Reaching this means the engine has no evidence left: same span, no cue, same
+ * priority, the same (usually zero) country score, and the same declared scope.
+ * Something still has to win, and before this the winner was whichever candidate
+ * happened to be generated first — which is country *registration* order, and
+ * the two SDKs do not share one. Python registers alphabetically
+ * (`AT, BE, BG, CH, CY, CZ, ...`); this SDK uses a curated order
+ * (`NL, BE, DE, AT, CH, FR, ..., PT, LU, PL, ..., CZ`). So a bare digit run that
+ * several national schemes accept was filed as a Czech `NATIONAL_ID` by Python
+ * and a Portuguese `PHONE` here — identical characters masked, contradictory
+ * labels, and `make parity` compared only characters, so it stayed green through
+ * the whole of 0.3.8.
+ *
+ * The order reproduces what Python already did rather than inventing a new one,
+ * because every accuracy figure this engine has published was measured with
+ * Python resolving these ties by its registration order. Ordering on the entity
+ * type instead was tried first and re-tuned the corpus twice over: it turned the
+ * German `Steuerß12345678911` from `TAX_ID`/DE into `NATIONAL_ID`/EL, and moved
+ * 820 further spans from `DOB` to `DATE_OF_DEATH`. So the key is deliberately
+ * not total — candidates from the same country are left to the stable sort,
+ * which preserves the order that country's pattern list was written in, and both
+ * SDKs write theirs in the same order.
+ *
+ * Taken from the **pattern**, never the finished detection: this SDK re-types a
+ * cued candidate before the sort and Python re-types after it, so keying on the
+ * final type would reintroduce the divergence in a subtler form.
+ *
+ * Kept character-for-character in step with `tie_key` in `rules/engine.py`.
+ */
+export function tieKey(countryCode) {
+    // "SHARED" and "CUSTOM" are not countries and sort as themselves under a
+    // plain alphabetical key — landing between PT and SK, rather than ahead of
+    // every country the way the registry loads them. The bucket restores that.
+    const bucket = countryCode === "SHARED" ? "0" : countryCode === "CUSTOM" ? "1" : "2";
+    // NUL separator, written as an escape so this file stays plain ASCII, and
+    // matching Python byte for byte. It must sort below every character a code
+    // or type name can contain, or a code that is a prefix of another would
+    // order differently in the two SDKs.
+    return `${bucket}\u0000${countryCode}`;
+}
 const warnedCountries = new Set();
 function warnUnknownCountry(code) {
     if (warnedCountries.has(code))
@@ -68,30 +111,13 @@ function warnUnknownCountry(code) {
 //
 // Measured: 263 phone numbers and 18 French SIREN were reported as national IDs,
 // each with an explicit cue in front of it.
-const LOCAL_CUES = [
-    [EntityType.PHONE,
-        /(?:phone|tel|telephone|téléphone|telefoon|telefon|telefono|teléfono|tlf|mobil|mobile|gsm|handy|sími|puh|móvil|cell)\w*\s*[:.\-]?\s*$/i],
-    [EntityType.CHAMBER_OF_COMMERCE,
-        /(?:siren|siret|kbo|bce|kvk|ondernemingsnummer|handelsregister|company\s*(?:no|number|reg)|organisationsnummer|orgnr)\w*\s*[:.\-]?\s*$/i],
-    [EntityType.VAT,
-        /(?:vat|btw|tva|ust|iva|moms|alv|mwst)[\w.\-]*\s*[:.\-]?\s*$/i],
-    [EntityType.BIC,
-        /(?:bic|swift)[\w/]*\s*[:.\-]?\s*\(?\s*$/i],
-    [EntityType.NATIONAL_ID,
-        /(?:bsn|personnummer|rijksregisternummer|national\s*id|identiteitsnummer|henkilötunnus|kennitala|cpr|nif|dni)\w*\s*[:.\-]?\s*$/i],
-];
-// How far back a cue may sit. Short on purpose: a cue is only evidence about the
-// value it introduces, which is the lesson of the postal-code year defect, where
-// a cue 150 characters away licensed every number in the window.
-const CUE_WINDOW = 22;
+//
+// The table itself lives in `cues.ts`, because two other steps read it: the
+// rescue of a declined identifier below, and the re-typing in deduplicate.
+// `CUE_WINDOW` is re-exported from there.
 /** 1 when a cue naming `entityType` sits immediately before the span. */
 function localCueBonus(text, start, entityType) {
-    const before = text.slice(Math.max(0, start - CUE_WINDOW), start);
-    for (const [cuedType, pattern] of LOCAL_CUES) {
-        if (cuedType === entityType && pattern.test(before))
-            return 1;
-    }
-    return 0;
+    return cuedType(text, start) === entityType ? 1 : 0;
 }
 export class RuleEngine {
     matcher = new MultiPatternMatcher();
@@ -198,7 +224,19 @@ export class RuleEngine {
         // but failed the checksum is recorded with its country and entity type;
         // what it is allowed to demote is decided below, once the document's
         // countries are known.
+        //
+        // One kind of failure is rescued rather than recorded: a span the document
+        // itself labels as the very type whose checksum just failed.
+        // "Rijksregisternummer: 85.03.19-284.73" is a Belgian national number with a
+        // bad check digit — mistyped, OCR'd, or invented — and it is still a
+        // national number. Before this, the pattern declined, the generic phone rule
+        // was denied the span as a fragment, and the value was left in the clear: a
+        // redaction library printing an identifier it had recognised and rejected.
+        //
+        // Rescued candidates are still recorded as failed spans, so the demotion
+        // zones and the fragment rule below are unchanged.
         const validated = [];
+        const rescued = [];
         const failedSpans = [];
         for (const m of rawMatches) {
             if (this.matcher.validate(m)) {
@@ -207,6 +245,9 @@ export class RuleEngine {
             else if (m.patternDef.validator !== null && !m.patternDef.requiresContext) {
                 failedSpans.push({ start: m.start, end: m.end, code: m.countryCode,
                     etype: String(m.patternDef.entityType) });
+                if (RESCUE_TARGETS.has(String(m.patternDef.entityType))
+                    && cuedType(text, m.start) === m.patternDef.entityType)
+                    rescued.push(m);
             }
         }
         // Evidence pass: work out which countries this document belongs to, from
@@ -401,8 +442,28 @@ export class RuleEngine {
                 priority = 1;
                 blindPriority = 1;
             }
-            const country = (match.countryCode !== "SHARED" && match.countryCode !== "CUSTOM")
+            let entityType = match.patternDef.entityType;
+            let country = (match.countryCode !== "SHARED" && match.countryCode !== "CUSTOM")
                 ? match.countryCode : null;
+            let outOfScope = declared !== null && country !== null && !declared.has(match.countryCode);
+            let confidence = "high";
+            // The document labels this span as something else. Relabelling, not
+            // suppression: the span is found either way, so removing the claim would
+            // decide only whether the value is masked — and the answer was "no".
+            // "Rijksregisternummer: 85.03.19-284.73" produced no detection at all.
+            //
+            // The country came from the pattern that matched, and that pattern was
+            // just overruled: a Finnish phone rule saying "Finland" is worthless once
+            // the value is filed as a Cypriot identity number. Dropping it also clears
+            // outOfScope, which would otherwise claim the detection belongs to a
+            // country the caller did not declare while naming no country at all.
+            const retyped = retypedBy(text, match.start, entityType, countryScores.get(match.countryCode) ?? 0);
+            if (retyped !== null) {
+                entityType = retyped;
+                country = null;
+                outOfScope = false;
+                confidence = "medium";
+            }
             candidates.push({
                 blindPriority,
                 cue: localCueBonus(text, match.start, match.patternDef.entityType),
@@ -410,6 +471,46 @@ export class RuleEngine {
                 length: match.end - match.start,
                 countryScore: countryScores.get(match.countryCode) ?? 0,
                 inScope: declared === null || declared.has(match.countryCode) ? 1 : 0,
+                tie: tieKey(match.countryCode),
+                tier: 0,
+                det: {
+                    entityType,
+                    start: match.start,
+                    end: match.end,
+                    text: match.text,
+                    source: DetectionSource.RULES,
+                    country,
+                    confidence,
+                    outOfScope,
+                },
+            });
+        }
+        // A declined identifier the document itself labels. Cue-backed by
+        // construction, so `cue` is 1 — that is what lets it take a span from a
+        // foreign pattern whose checksum happened to pass, which is how
+        // "ΑΦΜ: 147382965" was reported as a Czech national ID.
+        //
+        // `priority` is 0: below every regex-only claim, so it wins only what
+        // nothing better wants. `blindPriority` is 1 so that span selection — the
+        // country-blind half of the sort — treats it like any other regex-strength
+        // claim and invariant I1 is untouched.
+        //
+        // Emitted as "low", which is the honest description: the shape and the label
+        // agree, the check digit does not. A caller wanting only checksum-backed
+        // detections filters on it.
+        for (const match of rescued) {
+            if (shouldSuppress(text, match, scratch))
+                continue;
+            const country = (match.countryCode !== "SHARED" && match.countryCode !== "CUSTOM")
+                ? match.countryCode : null;
+            candidates.push({
+                blindPriority: 1,
+                cue: 1,
+                priority: 0,
+                length: match.end - match.start,
+                countryScore: countryScores.get(match.countryCode) ?? 0,
+                inScope: declared === null || declared.has(match.countryCode) ? 1 : 0,
+                tie: tieKey(match.countryCode),
                 tier: 0,
                 det: {
                     entityType: match.patternDef.entityType,
@@ -418,14 +519,15 @@ export class RuleEngine {
                     text: match.text,
                     source: DetectionSource.RULES,
                     country,
-                    confidence: "high",
+                    confidence: "low",
                     outOfScope: declared !== null && country !== null && !declared.has(match.countryCode),
                 },
             });
         }
         for (const d of detectStructuralDob(text)) {
             candidates.push({ blindPriority: 1, cue: 0, priority: 1, length: d.end - d.start,
-                countryScore: 0, inScope: 1, tier: 0, det: d });
+                countryScore: 0, inScope: 1, tier: 0, det: d,
+                tie: tieKey(d.country ?? "") });
         }
         const detections = this.deduplicate(candidates);
         detections.sort((a, b) => a.start - b.start || b.end - a.end);
@@ -493,7 +595,8 @@ export class RuleEngine {
             b.cue - a.cue || // local cue         } country-aware
             b.priority - a.priority || // country priority  } — decides the
             b.countryScore - a.countryScore || // country evidence  } LABEL only
-            b.inScope - a.inScope); // declared scope    }
+            b.inScope - a.inScope || // declared scope    }
+            (a.tie < b.tie ? -1 : a.tie > b.tie ? 1 : 0)); // total   } — see tieKey
         const result = [];
         const occupied = new Set();
         for (const { det } of sorted) {