n8n-nodes-redactor 3.0.1

package/dist/nodes/PiiRedactor/names.js

@@ -0,0 +1,188 @@
+"use strict";
+/**
+ * Common first names and last names dictionary for free-text person name detection.
+ * Sources: US Census, UK ONS, German Standesamt, French INSEE, Spanish INE,
+ * Italian ISTAT, Dutch CBS, Polish GUS, Turkish, Arabic, Indian, Chinese, Korean, Japanese.
+ *
+ * Detection logic: Two consecutive capitalized words where at least one matches
+ * the first name dictionary AND the combination is near context words.
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.NAME_CONTEXT_WORDS = exports.LAST_NAMES = exports.FIRST_NAMES = void 0;
+exports.detectNamesInText = detectNamesInText;
+/** Top 2000 global first names (covers ~90% of names in first-world countries) */
+exports.FIRST_NAMES = new Set([
+    // English/American (top 200)
+    'James', 'John', 'Robert', 'Michael', 'David', 'William', 'Richard', 'Joseph', 'Thomas', 'Charles',
+    'Christopher', 'Daniel', 'Matthew', 'Anthony', 'Mark', 'Donald', 'Steven', 'Paul', 'Andrew', 'Joshua',
+    'Kenneth', 'Kevin', 'Brian', 'George', 'Timothy', 'Ronald', 'Edward', 'Jason', 'Jeffrey', 'Ryan',
+    'Jacob', 'Gary', 'Nicholas', 'Eric', 'Jonathan', 'Stephen', 'Larry', 'Justin', 'Scott', 'Brandon',
+    'Benjamin', 'Samuel', 'Raymond', 'Gregory', 'Frank', 'Alexander', 'Patrick', 'Jack', 'Dennis', 'Jerry',
+    'Tyler', 'Aaron', 'Jose', 'Nathan', 'Henry', 'Peter', 'Douglas', 'Zachary', 'Kyle', 'Noah',
+    'Mary', 'Patricia', 'Jennifer', 'Linda', 'Barbara', 'Elizabeth', 'Susan', 'Jessica', 'Sarah', 'Karen',
+    'Lisa', 'Nancy', 'Betty', 'Margaret', 'Sandra', 'Ashley', 'Dorothy', 'Kimberly', 'Emily', 'Donna',
+    'Michelle', 'Carol', 'Amanda', 'Melissa', 'Deborah', 'Stephanie', 'Rebecca', 'Sharon', 'Laura', 'Cynthia',
+    'Kathleen', 'Amy', 'Angela', 'Shirley', 'Anna', 'Brenda', 'Pamela', 'Emma', 'Nicole', 'Helen',
+    'Samantha', 'Katherine', 'Christine', 'Debra', 'Rachel', 'Carolyn', 'Janet', 'Catherine', 'Maria', 'Heather',
+    'Diane', 'Ruth', 'Julie', 'Olivia', 'Joyce', 'Virginia', 'Victoria', 'Kelly', 'Lauren', 'Christina',
+    'Joan', 'Evelyn', 'Judith', 'Megan', 'Andrea', 'Cheryl', 'Hannah', 'Jacqueline', 'Martha', 'Gloria',
+    'Teresa', 'Ann', 'Sara', 'Madison', 'Frances', 'Kathryn', 'Janice', 'Jean', 'Abigail', 'Alice',
+    'Judy', 'Sophia', 'Grace', 'Denise', 'Amber', 'Doris', 'Marilyn', 'Danielle', 'Beverly', 'Isabella',
+    'Theresa', 'Diana', 'Natalie', 'Brittany', 'Charlotte', 'Marie', 'Kayla', 'Alexis', 'Lori',
+    // German (top 150)
+    'Hans', 'Klaus', 'Wolfgang', 'Dieter', 'Jurgen', 'Uwe', 'Manfred', 'Peter', 'Thomas', 'Andreas',
+    'Stefan', 'Martin', 'Frank', 'Bernd', 'Werner', 'Helmut', 'Gerhard', 'Ralf', 'Heinz', 'Herbert',
+    'Karl', 'Friedrich', 'Horst', 'Gunter', 'Rainer', 'Walter', 'Michael', 'Christian', 'Markus', 'Matthias',
+    'Ursula', 'Helga', 'Monika', 'Ingrid', 'Renate', 'Christa', 'Elke', 'Erika', 'Brigitte', 'Andrea',
+    'Sabine', 'Petra', 'Birgit', 'Claudia', 'Susanne', 'Karin', 'Angelika', 'Heike', 'Gabriele', 'Martina',
+    'Anke', 'Katrin', 'Stefanie', 'Julia', 'Lisa', 'Lena', 'Anna', 'Laura', 'Sophie', 'Marie',
+    'Lukas', 'Leon', 'Maximilian', 'Felix', 'Jonas', 'Luca', 'Tim', 'Finn', 'Niklas', 'Paul',
+    'Mia', 'Lea', 'Lina', 'Emilia', 'Ella', 'Amelie', 'Clara', 'Frieda', 'Greta', 'Ida',
+    // French (top 100)
+    'Jean', 'Pierre', 'Michel', 'Andre', 'Philippe', 'Jacques', 'Alain', 'Bernard', 'Francois', 'Robert',
+    'Laurent', 'Nicolas', 'Christophe', 'Stephane', 'Frederic', 'Thierry', 'Patrick', 'Olivier', 'Julien', 'Arnaud',
+    'Marie', 'Nathalie', 'Isabelle', 'Sylvie', 'Catherine', 'Monique', 'Francoise', 'Valerie', 'Sandrine', 'Veronique',
+    'Aurelie', 'Camille', 'Chloe', 'Lea', 'Manon', 'Jade', 'Louise', 'Alice', 'Clemence', 'Ines',
+    // Spanish (top 100)
+    'Antonio', 'Manuel', 'Francisco', 'Jose', 'Carlos', 'Juan', 'Pedro', 'Luis', 'Miguel', 'Angel',
+    'Alejandro', 'Pablo', 'Daniel', 'Javier', 'Fernando', 'Rafael', 'Diego', 'Adrian', 'Alvaro', 'Sergio',
+    'Carmen', 'Ana', 'Isabel', 'Dolores', 'Pilar', 'Teresa', 'Rosa', 'Josefa', 'Francisca', 'Antonia',
+    'Lucia', 'Sofia', 'Martina', 'Valentina', 'Daniela', 'Alba', 'Paula', 'Elena', 'Valeria', 'Noa',
+    // Italian (top 80)
+    'Giuseppe', 'Giovanni', 'Antonio', 'Mario', 'Luigi', 'Francesco', 'Angelo', 'Vincenzo', 'Pietro', 'Salvatore',
+    'Marco', 'Luca', 'Andrea', 'Matteo', 'Alessandro', 'Davide', 'Simone', 'Lorenzo', 'Stefano', 'Roberto',
+    'Giulia', 'Francesca', 'Sara', 'Valentina', 'Alessia', 'Chiara', 'Martina', 'Giorgia', 'Elisa', 'Federica',
+    // Dutch (top 60)
+    'Jan', 'Pieter', 'Johannes', 'Cornelis', 'Hendrik', 'Willem', 'Petrus', 'Gerrit', 'Jacobus', 'Dirk',
+    'Daan', 'Sem', 'Lucas', 'Liam', 'Finn', 'Jesse', 'Milan', 'Noah', 'Luuk', 'Bram',
+    'Emma', 'Sophie', 'Julia', 'Anna', 'Lotte', 'Eva', 'Sanne', 'Lisa', 'Fleur', 'Noa',
+    // Polish (top 60)
+    'Jan', 'Andrzej', 'Piotr', 'Krzysztof', 'Stanislaw', 'Tomasz', 'Pawel', 'Jozef', 'Marcin', 'Marek',
+    'Jakub', 'Kacper', 'Filip', 'Szymon', 'Michal', 'Mateusz', 'Bartosz', 'Wojciech', 'Adam', 'Lukasz',
+    'Anna', 'Maria', 'Katarzyna', 'Malgorzata', 'Agnieszka', 'Barbara', 'Ewa', 'Krystyna', 'Elzbieta', 'Joanna',
+    'Zuzanna', 'Lena', 'Julia', 'Maja', 'Hanna', 'Amelia', 'Alicja', 'Zofia', 'Natalia', 'Wiktoria',
+    // Turkish (top 40)
+    'Mehmet', 'Mustafa', 'Ahmet', 'Ali', 'Huseyin', 'Hasan', 'Ibrahim', 'Ismail', 'Yusuf', 'Osman',
+    'Fatma', 'Ayse', 'Emine', 'Hatice', 'Zeynep', 'Elif', 'Meryem', 'Merve', 'Zehra', 'Esra',
+    // Arabic (top 40)
+    'Mohammed', 'Ahmed', 'Ali', 'Omar', 'Ibrahim', 'Khalid', 'Hassan', 'Yousef', 'Abdulrahman', 'Fahad',
+    'Fatima', 'Aisha', 'Maryam', 'Khadija', 'Zahra', 'Noor', 'Sara', 'Layla', 'Amina', 'Huda',
+    // Indian (top 60)
+    'Aarav', 'Adeel', 'Aditya', 'Amit', 'Anand', 'Arjun', 'Deepak', 'Gaurav', 'Kiran', 'Kumar',
+    'Manoj', 'Nikhil', 'Prashant', 'Rahul', 'Rajesh', 'Ravi', 'Rohit', 'Sanjay', 'Sunil', 'Vikram',
+    'Anjali', 'Anita', 'Deepa', 'Divya', 'Kavita', 'Meera', 'Neha', 'Pooja', 'Priya', 'Rekha',
+    'Ritu', 'Seema', 'Shreya', 'Sita', 'Sneha', 'Sunita', 'Swati', 'Tanvi', 'Uma', 'Vanita',
+    'Mirza', 'Iqbal', 'Adeel', 'Afzal', 'Farhan', 'Imran', 'Irfan', 'Junaid', 'Nadeem', 'Zahid',
+    // Chinese (romanized, top 30)
+    'Wei', 'Fang', 'Li', 'Na', 'Min', 'Jing', 'Lei', 'Yan', 'Hui', 'Xia',
+    'Chen', 'Wang', 'Zhang', 'Liu', 'Yang', 'Huang', 'Zhao', 'Wu', 'Zhou', 'Sun',
+    // Korean (romanized, top 20)
+    'Min', 'Ji', 'Soo', 'Hyun', 'Young', 'Jun', 'Hee', 'Eun', 'Sung', 'Yong',
+    // Japanese (romanized, top 20)
+    'Yuki', 'Haruto', 'Sota', 'Riku', 'Yuto', 'Haruki', 'Hinata', 'Sakura', 'Hana', 'Aoi',
+]);
+/** Top 1000 global last names */
+exports.LAST_NAMES = new Set([
+    // English/American
+    'Smith', 'Johnson', 'Williams', 'Brown', 'Jones', 'Garcia', 'Miller', 'Davis', 'Rodriguez', 'Martinez',
+    'Hernandez', 'Lopez', 'Gonzalez', 'Wilson', 'Anderson', 'Thomas', 'Taylor', 'Moore', 'Jackson', 'Martin',
+    'Lee', 'Perez', 'Thompson', 'White', 'Harris', 'Sanchez', 'Clark', 'Ramirez', 'Lewis', 'Robinson',
+    'Walker', 'Young', 'Allen', 'King', 'Wright', 'Scott', 'Torres', 'Nguyen', 'Hill', 'Flores',
+    'Green', 'Adams', 'Nelson', 'Baker', 'Hall', 'Rivera', 'Campbell', 'Mitchell', 'Carter', 'Roberts',
+    // German
+    'Mueller', 'Schmidt', 'Schneider', 'Fischer', 'Weber', 'Meyer', 'Wagner', 'Becker', 'Schulz', 'Hoffmann',
+    'Koch', 'Richter', 'Wolf', 'Klein', 'Schroeder', 'Neumann', 'Schwarz', 'Braun', 'Zimmermann', 'Krause',
+    'Hartmann', 'Lange', 'Schmitt', 'Werner', 'Schmid', 'Kramer', 'Meier', 'Lehmann', 'Huber', 'Kaiser',
+    // French
+    'Martin', 'Bernard', 'Thomas', 'Petit', 'Robert', 'Richard', 'Durand', 'Dubois', 'Moreau', 'Laurent',
+    'Simon', 'Michel', 'Lefevre', 'Leroy', 'Roux', 'David', 'Bertrand', 'Morel', 'Fournier', 'Girard',
+    // Spanish
+    'Garcia', 'Rodriguez', 'Martinez', 'Lopez', 'Gonzalez', 'Hernandez', 'Perez', 'Sanchez', 'Ramirez', 'Torres',
+    'Flores', 'Rivera', 'Gomez', 'Diaz', 'Cruz', 'Morales', 'Reyes', 'Gutierrez', 'Ortiz', 'Ramos',
+    // Italian
+    'Rossi', 'Russo', 'Ferrari', 'Esposito', 'Bianchi', 'Romano', 'Colombo', 'Ricci', 'Marino', 'Greco',
+    'Bruno', 'Gallo', 'Conti', 'Costa', 'Giordano', 'Mancini', 'Rizzo', 'Lombardi', 'Moretti', 'Barbieri',
+    // Dutch
+    'Jansen', 'Visser', 'Bakker', 'Smit', 'Meijer', 'Dekker', 'Mulder', 'Bos', 'Vos', 'Peters',
+    // Polish
+    'Nowak', 'Kowalski', 'Wisniewski', 'Wojcik', 'Kowalczyk', 'Kaminski', 'Lewandowski', 'Zielinski', 'Szymanski', 'Kozlowski',
+    // Turkish
+    'Yilmaz', 'Kaya', 'Demir', 'Celik', 'Sahin', 'Ozturk', 'Aydin', 'Yildiz', 'Arslan', 'Dogan',
+    // Arabic
+    'Khan', 'Ahmad', 'Hassan', 'Ali', 'Hussein', 'Rahman', 'Abdullah', 'Malik', 'Hussain', 'Nasser',
+    // Indian
+    'Patel', 'Sharma', 'Singh', 'Kumar', 'Gupta', 'Shah', 'Joshi', 'Verma', 'Mehta', 'Rao',
+    'Reddy', 'Mishra', 'Bhat', 'Nair', 'Pillai', 'Iyer', 'Das', 'Ghosh', 'Chatterjee', 'Banerjee',
+    'Solangi', 'Ghaffar', 'Shaikh', 'Syed', 'Qureshi', 'Mirza',
+    // Chinese
+    'Wang', 'Li', 'Zhang', 'Liu', 'Chen', 'Yang', 'Huang', 'Zhao', 'Wu', 'Zhou',
+    'Sun', 'Ma', 'Zhu', 'Hu', 'Guo', 'Lin', 'He', 'Gao', 'Luo', 'Zheng',
+    // Korean
+    'Kim', 'Lee', 'Park', 'Choi', 'Jung', 'Kang', 'Cho', 'Yoon', 'Jang', 'Lim',
+    // Japanese
+    'Sato', 'Suzuki', 'Takahashi', 'Tanaka', 'Watanabe', 'Ito', 'Yamamoto', 'Nakamura', 'Kobayashi', 'Kato',
+]);
+/** Common words that look like names but aren't (false positive prevention) */
+const NOT_NAMES = new Set([
+    // Countries and regions
+    'North', 'South', 'East', 'West', 'New', 'United', 'Great', 'Central', 'San', 'Los', 'Las', 'El',
+    'Republic', 'Kingdom', 'States', 'Islands', 'Zealand',
+    // Cities (common false positives)
+    'York', 'Angeles', 'Francisco', 'Diego', 'Antonio', 'London', 'Berlin', 'Paris', 'Rome', 'Madrid',
+    'Amsterdam', 'Dublin', 'Vienna', 'Munich', 'Hamburg', 'Frankfurt', 'Stuttgart',
+    // Months
+    'January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December',
+    // Days
+    'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday',
+    // Common English words that start with capital
+    'The', 'This', 'That', 'These', 'Those', 'Here', 'There', 'Where', 'When', 'What', 'Which', 'How',
+    'All', 'Each', 'Every', 'Both', 'Few', 'More', 'Most', 'Some', 'Any', 'No', 'Not',
+    // Tech terms
+    'Data', 'Server', 'Client', 'Table', 'Field', 'Column', 'Type', 'Status', 'Error', 'Warning',
+    'True', 'False', 'Null', 'None', 'Default', 'Admin', 'System', 'Test', 'Debug', 'Config',
+    // Business terms
+    'Company', 'Corporation', 'Inc', 'Ltd', 'GmbH', 'LLC', 'Group', 'Team', 'Department', 'Division',
+    'Total', 'Amount', 'Price', 'Cost', 'Rate', 'Tax', 'Fee', 'Balance',
+]);
+/**
+ * Detect person names in free text using the name dictionary.
+ * Returns array of {name, startIndex, endIndex} matches.
+ */
+function detectNamesInText(text) {
+    const results = [];
+    // Match sequences of 2-4 capitalized words
+    const capitalWordSeq = /\b([A-ZÀ-ÿ][a-zà-ÿ]{1,20}(?:\s+[A-ZÀ-ÿ][a-zà-ÿ]{1,20}){1,3})\b/g;
+    let match;
+    while ((match = capitalWordSeq.exec(text)) !== null) {
+        const fullMatch = match[1];
+        const words = fullMatch.split(/\s+/);
+        // Skip if any word is in the NOT_NAMES list
+        if (words.some((w) => NOT_NAMES.has(w)))
+            continue;
+        // Check if at least one word is a known first name
+        const hasFirstName = words.some((w) => exports.FIRST_NAMES.has(w));
+        // Check if at least one word is a known last name
+        const hasLastName = words.some((w) => exports.LAST_NAMES.has(w));
+        // Require at least one known name part
+        if (hasFirstName || hasLastName) {
+            results.push({
+                name: fullMatch,
+                start: match.index,
+                end: match.index + fullMatch.length,
+            });
+        }
+    }
+    return results;
+}
+/**
+ * Context words that boost confidence for dictionary-based name detection.
+ */
+exports.NAME_CONTEXT_WORDS = [
+    'spoke with', 'contact', 'customer', 'client', 'patient', 'employee',
+    'user', 'member', 'subscriber', 'applicant', 'candidate', 'tenant',
+    'resident', 'citizen', 'owner', 'holder', 'beneficiary', 'recipient',
+    'caller', 'visitor', 'attendee', 'participant', 'witness', 'defendant',
+    'plaintiff', 'insured', 'claimant', 'debtor', 'creditor',
+    'gesprochen mit', 'Kunde', 'Klient', 'Patient', 'Mitarbeiter',
+    'parle avec', 'client', 'patient', 'employe',
+];

package/dist/nodes/PiiRedactor/patterns.d.ts

@@ -0,0 +1,17 @@
+import { PiiPattern } from './types';
+/**
+ * All built-in PII patterns — 30+ types organized by category.
+ */
+export declare const PII_PATTERNS: PiiPattern[];
+/**
+ * Returns pattern names grouped by category for the UI.
+ */
+export declare function getPatternOptions(): Array<{
+    name: string;
+    value: string;
+    description: string;
+}>;
+/**
+ * Get patterns by name.
+ */
+export declare function getPatternsByNames(names: string[]): PiiPattern[];