@link-foundation/sensitive-data-sanitizer 0.19.1 → 0.19.2

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.19.2
+
+### Patch Changes
+
+- 4afc88d: Read `Mr`, `Ms` and `Dr` as person cues only when capitalized, so lowercase `ms` (milliseconds) and `dr` before a capitalized log word stay. Treat compound JSON keys ending in a personal field, such as `recruiterDisplayName`, `authorFullName` and `resumePdfOriginalFileName`, as person fields.
+
 ## 0.19.1
 
 ### Patch Changes

package/docs/COVERAGE.md

@@ -370,6 +370,11 @@ this explicit vocabulary: `firstName`, `lastName`, `middleName`, `patronymic`,
 sensitive in full, including ISO birth timestamps. Thus `first_name` and
 `firstName`, or `birth_date` and `birthDate`, follow the same policy. These are
 schema assumptions: `contact` or `company` can hold operational data too.
+Person fields also match as a word-boundary suffix of a compound key, so
+`recruiterDisplayName`, `author_full_name` and `resumePdfOriginalFileName` are
+person fields. The same suffix rule applies to `vocabulary.personalFields`.
+Other types match only the whole key (`maxAge` and `fileName` stay), and a
+bare `name` is not in the list.
 Existing native labels still apply. Unlisted URL-named fields have ordinary
 content detection; arbitrary names do not imply sensitivity. Declare them with
 [`sensitiveFields`](API.md#caller-declared-sensitive-fields) to replace complete
@@ -542,6 +547,9 @@ corpus, unbounded input, parallel builds or external analysis service.
 
 Document rules recognize a capitalized Latin name after `candidate`, `recruiter`,
 `applicant`, `Dear`, `Hi`, `Mr`/`Mr.`, `Ms`/`Ms.`, `Dr`/`Dr.`, or `message from`.
+Honorifics count only when capitalized: lowercase `ms` (milliseconds), `mr` and
+`dr` are not cues, and `Ms` right after a number is read as a unit, so
+`took 30 ms Retry scheduled` and `see dr Drive mount` stay unchanged.
 Only the name is replaced; punctuation and the cue remain. These rules work
 without enabling Latin script matching. Finite generic heading nouns such as
 `Stage` and `Status` are preserved: `Candidate Stage changed` and

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@link-foundation/sensitive-data-sanitizer",
-  "version": "0.19.1",
+  "version": "0.19.2",
   "description": "Offline sensitive-text sanitization with credential, multilingual personal-data and scanner union detection",
   "type": "module",
   "main": "src/index.js",

package/src/document-fields.js

@@ -25,7 +25,24 @@ const types = new Map(
   )
 );
 export function documentFieldType(field) {
-  return types.get(normalizeFieldName(field));
+  const type = types.get(normalizeFieldName(field));
+  if (type) {
+    return type;
+  }
+  // Compound person keys (`recruiterDisplayName`, `author_full_name`) end in
+  // a listed person field. Only PERSON entries extend this way, so generic
+  // suffixes such as `maxAge` or `homeSchool` keep their exact-match meaning,
+  // and a bare `name` is never listed.
+  return fieldSuffixes(field).some((suffix) => types.get(suffix) === 'PERSON')
+    ? 'PERSON'
+    : undefined;
+}
+// Word-boundary suffixes of a key, normalized; the whole key comes first.
+export function fieldSuffixes(field) {
+  const words = field
+    .split(/[\s_.-]+|(?<=[\p{Ll}\p{N}])(?=\p{Lu})|(?<=\p{Lu})(?=\p{Lu}\p{Ll})/u)
+    .filter(Boolean);
+  return words.map((_, i) => words.slice(i).join('').toLowerCase());
 }
 export const normalizeFieldName = (field) =>
   field.replace(/[_-]/g, '').toLowerCase();

package/src/document-person-cues.js

@@ -4,8 +4,11 @@ import { collectMatches } from './detection.js';
 // capitalized-word matching for the rest of an English log or document.
 const boundary = '[\\p{L}\\p{M}\\p{N}_]';
 const name = "[A-Z][a-z]{1,47}(?:['’-][A-Z]?[a-z]{1,47})?";
+// Honorifics count only when capitalized: lowercase `ms` is the millisecond
+// unit in logs and lowercase `dr` is usually a word or path fragment. A
+// capitalized `Ms` right after a number is still a unit (`took 30 Ms Retry`).
 const cue =
-  '(?:[Cc]andidate|[Rr]ecruiter|[Aa]pplicant|[Dd]ear|[Hh]i|[Mm]r\\.?|[Mm]s\\.?|[Dd]r\\.?|[Mm]essage[ \\t]+from)';
+  '(?:[Cc]andidate|[Rr]ecruiter|[Aa]pplicant|[Dd]ear|[Hh]i|Mr\\.?|(?<!\\d[ \\t]*)Ms\\.?|Dr\\.?|[Mm]essage[ \\t]+from)';
 const pattern = new RegExp(
   `(?<!${boundary})${cue}[ \\t]+(${name})(?!${boundary})`,
   'gu'

package/src/vocabulary.js

@@ -1,6 +1,6 @@
 import { failure, collectMatches } from './detection.js';
 import { wordPattern } from './personal-variants.js';
-import { normalizeFieldName } from './document-fields.js';
+import { fieldSuffixes, normalizeFieldName } from './document-fields.js';
 
 export const defaultVocabulary = Object.freeze(
   Object.fromEntries(
@@ -170,7 +170,8 @@ export function vocabularyField(field, options) {
   if (!vocabulary) {
     return undefined;
   }
-  return vocabulary.fields.has(normalizeFieldName(field))
+  return vocabulary.fields.has(normalizeFieldName(field)) ||
+    fieldSuffixes(field).some((suffix) => vocabulary.fields.has(suffix))
     ? true
     : options.vocabulary.personalFields?.replace
       ? false