test: Add text families for property-based tests (#38511)

packages/nodes-base/nodes/Notion/test/GenericFunctions.test.ts

@@ -1,3 +1,4 @@
+import fc from 'fast-check';
 import type { MockProxy } from 'vitest-mock-extended';
 import { mock } from 'vitest-mock-extended';
 import type { IExecuteFunctions, INode, INodeParameterResourceLocator } from 'n8n-workflow';
@@ -23,6 +24,7 @@ import {
 } from '../shared/GenericFunctions';
 import { versionDescription as versionDescriptionV1 } from '../v1/VersionDescription';
 import { versionDescription as versionDescriptionV2 } from '../v2/VersionDescription';
+import { wordFrom } from '@test/text-families';
 import type { Mock } from 'vitest';
 
 const collectNotionUrlExpressions = (value: unknown): string[] => {
@@ -603,6 +605,15 @@ describe('Test Notion, simplifyObjects', () => {
 		},
 	});
 
+	const keyFor = (propertyName: string, nodeVersion: number, text = 'x') => {
+		const [result] = simplifyObjects(
+			[page({ [propertyName]: richText(text) })],
+			false,
+			nodeVersion,
+		);
+		return Object.keys(result).find((key) => result[key] === text);
+	};
+
 	describe('v3 keeps change-case v5 Unicode-aware keys', () => {
 		it('preserves non-ASCII characters in simplified property keys', () => {
 			const result = simplifyObjects([page({ Prénom: richText('Jean') })], false, 3);
@@ -622,6 +633,14 @@ describe('Test Notion, simplifyObjects', () => {
 
 			expect(result[0]).toHaveProperty(expectedKey, 'x');
 		});
+
+		it('keeps any accented word as its key', () => {
+			fc.assert(
+				fc.property(wordFrom('latin-accented'), (name) => {
+					expect(keyFor(name, 3)).toBe(`property_${name}`);
+				}),
+			);
+		});
 	});
 
 	describe('earlier versions fold to the pre-v5 ASCII shape', () => {
@@ -663,5 +682,13 @@ describe('Test Notion, simplifyObjects', () => {
 
 			expect(result[0]).toHaveProperty(expectedKey, 'x');
 		});
+
+		it('folds any accented word to an ASCII key', () => {
+			fc.assert(
+				fc.property(wordFrom('latin-accented'), (name) => {
+					expect(keyFor(name, 2)).toMatch(/^property_[a-z_]*$/);
+				}),
+			);
+		});
 	});
 });

packages/nodes-base/package.json

@@ -926,6 +926,9 @@
     "@types/ssh2-sftp-client": "^9.0.5",
     "@types/uuid": "catalog:",
     "@types/xml2js": "catalog:",
+    "@unicode/unicode-18.0.0": "2.0.7",
+    "confusables": "1.1.1",
+    "fast-check": "catalog:",
     "n8n-containers": "workspace:*",
     "n8n-core": "workspace:*",
     "nock": "catalog:",

packages/nodes-base/test/text-families/index.ts

@@ -0,0 +1,60 @@
+import bidiControl from '@unicode/unicode-18.0.0/Binary_Property/Bidi_Control/symbols';
+import changesWhenCasemapped from '@unicode/unicode-18.0.0/Binary_Property/Changes_When_Casemapped/symbols';
+import emojiPresentation from '@unicode/unicode-18.0.0/Binary_Property/Emoji_Presentation/symbols';
+import whiteSpace from '@unicode/unicode-18.0.0/Binary_Property/White_Space/symbols';
+import combiningDiacriticalMarks from '@unicode/unicode-18.0.0/Block/Combining_Diacritical_Marks/symbols';
+import halfwidthAndFullwidthForms from '@unicode/unicode-18.0.0/Block/Halfwidth_And_Fullwidth_Forms/symbols';
+import decimalNumber from '@unicode/unicode-18.0.0/General_Category/Decimal_Number/symbols';
+import format from '@unicode/unicode-18.0.0/General_Category/Format/symbols';
+import arabic from '@unicode/unicode-18.0.0/Script/Arabic/symbols';
+import cyrillic from '@unicode/unicode-18.0.0/Script/Cyrillic/symbols';
+import devanagari from '@unicode/unicode-18.0.0/Script/Devanagari/symbols';
+import greek from '@unicode/unicode-18.0.0/Script/Greek/symbols';
+import han from '@unicode/unicode-18.0.0/Script/Han/symbols';
+import hangul from '@unicode/unicode-18.0.0/Script/Hangul/symbols';
+import hebrew from '@unicode/unicode-18.0.0/Script/Hebrew/symbols';
+import hiragana from '@unicode/unicode-18.0.0/Script/Hiragana/symbols';
+import katakana from '@unicode/unicode-18.0.0/Script/Katakana/symbols';
+import latin from '@unicode/unicode-18.0.0/Script/Latin/symbols';
+import { alphabetMap } from 'confusables';
+import fc from 'fast-check';
+
+const isAscii = (text: string) => !/\P{ASCII}/u.test(text);
+
+const families = {
+	'latin-accented': latin.filter((c) => /^\p{Ll}$/u.test(c) && !isAscii(c)),
+	greek,
+	cyrillic,
+	hebrew,
+	arabic,
+	devanagari,
+	han,
+	hiragana,
+	katakana,
+	hangul,
+	'combining-marks': combiningDiacriticalMarks,
+	fullwidth: halfwidthAndFullwidthForms.filter((c) => /^[\p{L}\p{Nd}]$/u.test(c)),
+	/** Letters whose case mapping changes the length or does not round-trip, such as ß, fi and İ. */
+	'case-mapping': changesWhenCasemapped.filter(
+		(c) =>
+			c.toUpperCase().length !== c.length ||
+			c.toLowerCase().length !== c.length ||
+			c.toLowerCase().toUpperCase() !== c.toUpperCase() ||
+			c.toUpperCase().toLowerCase() !== c.toLowerCase(),
+	),
+	emoji: emojiPresentation,
+	digits: decimalNumber.filter((c) => !isAscii(c)),
+	whitespace: whiteSpace,
+	/** Format characters other than bidi controls: soft hyphen, zero width space and joiners, byte order mark. */
+	invisible: format.filter((c) => !bidiControl.includes(c)),
+	'bidi-controls': bidiControl,
+	/** Non-ASCII characters the `confusables` package maps to ASCII letters. */
+	confusables: [...'abcdefghijklmnopqrstuvwxyz'].flatMap((letter) =>
+		(alphabetMap.get(letter) ?? []).filter((c) => !isAscii(c)),
+	),
+} satisfies Record<string, readonly string[]>;
+
+export type FamilyName = keyof typeof families;
+
+export const wordFrom = (family: FamilyName, minLength = 1, maxLength = 8) =>
+	fc.string({ unit: fc.constantFrom(...families[family]), minLength, maxLength });

packages/nodes-base/test/text-families/unicode.d.ts

@@ -0,0 +1,5 @@
+// The Unicode data package ships no typings for its per-property modules.
+declare module '@unicode/unicode-18.0.0/*/symbols' {
+	const symbols: string[];
+	export default symbols;
+}

pnpm-lock.yaml

@@ -7284,9 +7284,18 @@ importers:
       '@types/xml2js':
         specifier: 'catalog:'
         version: 0.4.14
+      '@unicode/unicode-18.0.0':
+        specifier: 2.0.7
+        version: 2.0.7
       '@vitest/coverage-v8':
         specifier: 'catalog:'
         version: 4.1.9(@vitest/browser@4.1.10)(vitest@4.1.9)
+      confusables:
+        specifier: 1.1.1
+        version: 1.1.1
+      fast-check:
+        specifier: 'catalog:'
+        version: 3.23.2
       n8n-containers:
         specifier: workspace:*
         version: link:../testing/containers
@@ -14959,6 +14968,9 @@ packages:
     resolution: {integrity: sha512-jIXhD0eWQ1JA6ln/5Dltyx22UxWNrw0hZmhy2rlv6m6KgF7kplHx3g0fzi09lNmTJQRR91OlemYp3xFnvDK9og==}
     engines: {node: '>=20.0.0'}
 
+  '@unicode/unicode-18.0.0@2.0.7':
+    resolution: {integrity: sha512-sxWcUPwfbWVcSt+RPixHI468bs97A2+ftrC9b6wsGEkUTp2eod0qp7J59A+ngd4mFRISElQhPkYClhtXwNuLQw==}
+
   '@unrs/resolver-binding-android-arm-eabi@1.9.2':
     resolution: {integrity: sha512-tS+lqTU3N0kkthU+rYp0spAYq15DU8ld9kXkaKg9sbQqJNF+WPMuNHZQGCgdxrUOEO0j22RKMwRVhF1HTl+X8A==}
     cpu: [arm]
@@ -16634,6 +16646,10 @@ packages:
   config-chain@1.1.13:
     resolution: {integrity: sha512-qj+f8APARXHrM0hraqXYb2/bOVSV4PvJQlNZ/DVj0QrmNM2q2euizkeuVckQ57J+W0mRH6Hvi+k50M4Jul2VRQ==}
 
+  confusables@1.1.1:
+    resolution: {integrity: sha512-BzFtzUrufackm00Wb2zvrZV0ItRqPdWaUprU5FXHeZiJRrOWxGmXmQl/muGTF9EQl+MdBXz+Irk99meskGZmXw==}
+    engines: {node: '>=10', npm: '>=6'}
+
   consola@3.4.2:
     resolution: {integrity: sha512-5IKcdX0nnYavi6G7TtOhwkYzyjfJlatbjMjuLSfE2kYT5pMDOilZ4OvMhi637CcDICTmz3wARPoyhqyX1Y+XvA==}
     engines: {node: ^14.18.0 || >=16.10.0}
@@ -29026,7 +29042,7 @@ snapshots:
       mongodb: 6.21.0(@aws-sdk/credential-providers@3.808.0)(gcp-metadata@5.3.0(supports-color@8.1.1))(socks@2.8.9)
       mysql2: 3.23.1(@types/node@20.19.41)
       pdf-parse: 2.4.5
-      pg: 8.21.0
+      pg: 8.21.0(pg-native@3.8.0)
       playwright: 1.62.1
       puppeteer: 24.41.0(bufferutil@4.0.9)(supports-color@8.1.1)(typescript@7.0.2)(utf-8-validate@5.0.10)
       redis: 4.6.14
@@ -33694,6 +33710,8 @@ snapshots:
     transitivePeerDependencies:
       - supports-color
 
+  '@unicode/unicode-18.0.0@2.0.7': {}
+
   '@unrs/resolver-binding-android-arm-eabi@1.9.2':
     optional: true
 
@@ -35618,6 +35636,8 @@ snapshots:
       ini: 1.3.8
       proto-list: 1.2.4
 
+  confusables@1.1.1: {}
+
   consola@3.4.2: {}
 
   console-control-strings@1.1.0:
@@ -41480,14 +41500,9 @@ snapshots:
       libpq: 1.11.0
       pg-types: 2.2.0
 
-  pg-pool@3.14.0(pg@8.21.0(pg-native@3.8.0)):
-    dependencies:
-      pg: 8.21.0(pg-native@3.8.0)
-
   pg-pool@3.14.0(pg@8.21.0):
     dependencies:
-      pg: 8.21.0
-    optional: true
+      pg: 8.21.0(pg-native@3.8.0)
 
   pg-promise@11.9.1(pg-native@3.8.0):
     dependencies:
@@ -41513,21 +41528,10 @@ snapshots:
       postgres-date: 1.0.7
       postgres-interval: 1.2.0
 
-  pg@8.21.0:
-    dependencies:
-      pg-connection-string: 2.14.0
-      pg-pool: 3.14.0(pg@8.21.0)
-      pg-protocol: 1.15.0
-      pg-types: 2.2.0
-      pgpass: 1.0.5
-    optionalDependencies:
-      pg-cloudflare: 1.4.0
-    optional: true
-
   pg@8.21.0(pg-native@3.8.0):
     dependencies:
       pg-connection-string: 2.14.0
-      pg-pool: 3.14.0(pg@8.21.0(pg-native@3.8.0))
+      pg-pool: 3.14.0(pg@8.21.0)
       pg-protocol: 1.15.0
       pg-types: 2.2.0
       pgpass: 1.0.5