Merge branch 'next' into infra/unicorn/prefer-array-some

.eslintrc.js

@@ -49,14 +49,12 @@ module.exports = defineConfig({
     // Each rule should be checked whether it should be enabled/configured and the problems fixed, or stay disabled permanently.
     'unicorn/better-regex': 'off',
     'unicorn/consistent-function-scoping': 'off',
-    'unicorn/escape-case': 'off',
     'unicorn/filename-case': 'off',
     'unicorn/import-style': 'off',
     'unicorn/no-array-callback-reference': 'off',
     'unicorn/no-array-reduce': 'off',
     'unicorn/no-await-expression-member': 'off',
     'unicorn/no-for-loop': 'off',
-    'unicorn/no-instanceof-array': 'off',
     'unicorn/no-negated-condition': 'off',
     'unicorn/no-object-as-default-parameter': 'off',
     'unicorn/no-useless-switch-case': 'off',
@@ -69,7 +67,6 @@ module.exports = defineConfig({
     'unicorn/prefer-negative-index': 'off',
     'unicorn/prefer-number-properties': 'off',
     'unicorn/prefer-optional-catch-binding': 'off',
-    'unicorn/prefer-spread': 'off',
     'unicorn/prefer-string-slice': 'off',
     'unicorn/prefer-ternary': 'off',
     'unicorn/prefer-top-level-await': 'off',
@@ -112,6 +109,7 @@ module.exports = defineConfig({
       'error',
       { blankLine: 'always', prev: 'block-like', next: '*' },
     ],
+    '@typescript-eslint/prefer-regexp-exec': 'error',
     '@typescript-eslint/restrict-template-expressions': [
       'error',
       { allowNumber: true, allowBoolean: true },

scripts/generateLocales.ts

@@ -210,7 +210,7 @@ async function generateRecursiveModuleIndexes(
   submodules = removeIndexTs(submodules);
   for (const submodule of submodules) {
     const pathModule = resolve(path, submodule);
-    updateLocaleFile(pathModule);
+    await updateLocaleFile(pathModule);
     // Only process sub folders recursively
     if (lstatSync(pathModule).isDirectory()) {
       let moduleDefinition =
@@ -238,14 +238,12 @@ async function generateRecursiveModuleIndexes(
  *
  * @param filePath The full file path to the file.
  */
-function updateLocaleFile(filePath: string): void {
+async function updateLocaleFile(filePath: string): Promise<void> {
   if (lstatSync(filePath).isFile()) {
-    const pathParts = filePath
+    const [locale, moduleKey, entryKey] = filePath
       .substring(pathLocales.length + 1, filePath.length - 3)
       .split(/[\\/]/);
-    const locale = pathParts[0];
-    pathParts.splice(0, 1);
-    updateLocaleFileHook(filePath, locale, pathParts);
+    await updateLocaleFileHook(filePath, locale, moduleKey, entryKey);
   }
 }
 
@@ -255,16 +253,120 @@ function updateLocaleFile(filePath: string): void {
  *
  * @param filePath The full file path to the file.
  * @param locale The locale for that file.
- * @param localePath The locale path parts (after the locale).
+ * @param definitionKey The definition key of the current file (ex. 'location').
+ * @param entryName The entry key of the current file (ex. 'state'). Is `undefined` if `definitionKey` is `'metadata'`.
  */
-function updateLocaleFileHook(
+async function updateLocaleFileHook(
   filePath: string,
   locale: string,
-  localePath: string[]
-): void {
+  definitionKey: string,
+  entryName: string | undefined
+): Promise<void> {
+  // this needs to stay so all arguments are "used"
   if (filePath === 'never') {
-    console.log(`${filePath} <-> ${locale} @ ${localePath.join(' -> ')}`);
+    console.log(`${filePath} <-> ${locale} @ ${definitionKey} -> ${entryName}`);
   }
+
+  await normalizeLocaleFile(filePath, definitionKey);
+}
+
+/**
+ * Normalizes the data of a locale file based on a set of rules.
+ * Those include:
+ * - filter the entry list for duplicates
+ * - limiting the maximum entries of a file to 1000
+ * - sorting the entries alphabetically
+ *
+ * This function mutates the file by reading and writing to it!
+ *
+ * @param filePath The full file path to the file.
+ * @param definitionKey The definition key of the current file (ex. 'location').
+ */
+async function normalizeLocaleFile(filePath: string, definitionKey: string) {
+  function normalizeDataRecursive<T>(localeData: T): T {
+    if (typeof localeData !== 'object' || localeData === null) {
+      // we can only traverse object-like structs
+      return localeData;
+    }
+
+    if (Array.isArray(localeData)) {
+      return (
+        [...new Set(localeData)]
+          // limit entries to 1k
+          .slice(0, 1000)
+          // sort entries alphabetically
+          .sort() as T
+      );
+    }
+
+    const result = {} as T;
+    for (const key of Object.keys(localeData)) {
+      result[key] = normalizeDataRecursive(localeData[key]);
+    }
+
+    return result;
+  }
+
+  const legacyDefinitions = ['app', 'cell_phone', 'team'];
+  const definitionsToSkip = [
+    'airline',
+    'animal',
+    'color',
+    'commerce',
+    'company',
+    'database',
+    'date',
+    'finance',
+    'hacker',
+    'internet',
+    'location',
+    'lorem',
+    'metadata',
+    'music',
+    'person',
+    'phone_number',
+    'science',
+    'system',
+    'vehicle',
+    'word',
+    ...legacyDefinitions,
+  ];
+  if (definitionsToSkip.includes(definitionKey)) {
+    return;
+  }
+
+  console.log(`Running data normalization for:`, filePath);
+
+  const fileContent = readFileSync(filePath).toString();
+  const searchString = 'export default ';
+  const compareIndex = fileContent.indexOf(searchString) + searchString.length;
+  const compareString = fileContent.substring(compareIndex);
+
+  const isDynamicFile = compareString.startsWith('mergeArrays');
+  const isNonApplicable = compareString.startsWith('null');
+  const isFrozenData = compareString.startsWith('Object.freeze');
+  if (isDynamicFile || isNonApplicable || isFrozenData) {
+    return;
+  }
+
+  const validEntryListStartCharacters = ['[', '{'];
+  const staticFileOpenSyntax = validEntryListStartCharacters.find(
+    (validStart) => compareString.startsWith(validStart)
+  );
+  if (staticFileOpenSyntax === undefined) {
+    console.log('Found an unhandled dynamic file:', filePath);
+    return;
+  }
+
+  const fileContentPreData = fileContent.substring(0, compareIndex);
+  // eslint-disable-next-line @typescript-eslint/no-var-requires
+  const localeData = normalizeDataRecursive(require(filePath).default);
+
+  // We reattach the content before the actual data implementation to keep stuff like comments.
+  // In the long term we should probably define a whether we want those in the files at all.
+  const newContent = fileContentPreData + JSON.stringify(localeData);
+
+  writeFileSync(filePath, await format(newContent, prettierTsOptions));
 }
 
 // Start of actual logic

src/internal/merge.ts

@@ -8,5 +8,5 @@
  * @param args The arrays to merge.
  */
 export function mergeArrays<T>(...args: T[][]): T[] {
-  return Array.from(new Set(args.flat())).sort();
+  return [...new Set(args.flat())].sort();
 }

src/modules/color/index.ts

@@ -86,7 +86,7 @@ function toBinary(values: number[]): string {
       const buffer = new ArrayBuffer(4);
       new DataView(buffer).setFloat32(0, value);
       const bytes = new Uint8Array(buffer);
-      return toBinary(Array.from(bytes)).split(' ').join('');
+      return toBinary([...bytes]).replace(/ /g, '');
     }
 
     return (value >>> 0).toString(2).padStart(8, '0');

src/modules/company/index.ts

@@ -42,7 +42,7 @@ export class CompanyModule {
     });
     // Don't want the source array exposed to modification, so return a copy
     // eslint-disable-next-line deprecation/deprecation
-    return this.faker.definitions.company.suffix.slice(0);
+    return [...this.faker.definitions.company.suffix];
   }
 
   /**

src/modules/finance/index.ts

@@ -722,9 +722,9 @@ export class FinanceModule {
     let address = this.faker.helpers.arrayElement(['L', 'M', '3']);
 
     for (let i = 0; i < addressLength - 1; i++)
-      address += this.faker.helpers.arrayElement(
-        '123456789abcdefghijkmnopqrstuvwxyzABCDEFGHJKLMNPQRSTUVWXYZ'.split('')
-      );
+      address += this.faker.helpers.arrayElement([
+        ...'123456789abcdefghijkmnopqrstuvwxyzABCDEFGHJKLMNPQRSTUVWXYZ',
+      ]);
 
     return address;
   }

src/modules/git/index.ts

@@ -2,7 +2,7 @@ import type { Faker } from '../..';
 import { bindThisToMemberFunctions } from '../../internal/bind-this-to-member-functions';
 import { deprecated } from '../../internal/deprecated';
 
-const nbsp = '\u00a0';
+const nbsp = '\u00A0';
 
 /**
  * Module to generate git related entries.

src/modules/helpers/index.ts

@@ -190,7 +190,7 @@ export class SimpleHelpersModule {
   slugify(string: string = ''): string {
     return string
       .normalize('NFKD') //for example è decomposes to as e +  ̀
-      .replace(/[\u0300-\u036f]/g, '') // removes combining marks
+      .replace(/[\u0300-\u036F]/g, '') // removes combining marks
       .replace(/ /g, '-') // replaces spaces with hyphens
       .replace(/[^\w.-]+/g, ''); // removes all non-word characters except for dots and hyphens
   }
@@ -407,7 +407,7 @@ export class SimpleHelpersModule {
     if (pattern instanceof RegExp) {
       isCaseInsensitive = pattern.flags.includes('i');
       pattern = pattern.toString();
-      pattern = pattern.match(/\/(.+?)\//)?.[1] ?? ''; // Remove frontslash from front and back of RegExp
+      pattern = /\/(.+?)\//.exec(pattern)?.[1] ?? ''; // Remove frontslash from front and back of RegExp
     }
 
     let min: number;
@@ -417,7 +417,7 @@ export class SimpleHelpersModule {
     // Deal with single wildcards
     const SINGLE_CHAR_REG =
       /([.A-Za-z0-9])(?:\{(\d+)(?:,(\d+)|)\}|(\?|\*|\+))(?![^[]*]|[^{]*})/;
-    let token = pattern.match(SINGLE_CHAR_REG);
+    let token = SINGLE_CHAR_REG.exec(pattern);
     while (token != null) {
       const quantifierMin: string = token[2];
       const quantifierMax: string = token[3];
@@ -434,14 +434,14 @@ export class SimpleHelpersModule {
         pattern.slice(0, token.index) +
         token[1].repeat(repetitions) +
         pattern.slice(token.index + token[0].length);
-      token = pattern.match(SINGLE_CHAR_REG);
+      token = SINGLE_CHAR_REG.exec(pattern);
     }
 
     const SINGLE_RANGE_REG = /(\d-\d|\w-\w|\d|\w|[-!@#$&()`.+,/"])/;
     const RANGE_ALPHANUMEMRIC_REG =
       /\[(\^|)(-|)(.+?)\](?:\{(\d+)(?:,(\d+)|)\}|(\?|\*|\+)|)/;
     // Deal with character classes with quantifiers `[a-z0-9]{min[, max]}`
-    token = pattern.match(RANGE_ALPHANUMEMRIC_REG);
+    token = RANGE_ALPHANUMEMRIC_REG.exec(pattern);
     while (token != null) {
       const isNegated = token[1] === '^';
       const includesDash: boolean = token[2] === '-';
@@ -452,7 +452,7 @@ export class SimpleHelpersModule {
       const rangeCodes: number[] = [];
 
       let ranges = token[3];
-      let range = ranges.match(SINGLE_RANGE_REG);
+      let range = SINGLE_RANGE_REG.exec(ranges);
 
       if (includesDash) {
         // 45 is the ascii code for '-'
@@ -494,7 +494,7 @@ export class SimpleHelpersModule {
         }
 
         ranges = ranges.substring(range[0].length);
-        range = ranges.match(SINGLE_RANGE_REG);
+        range = SINGLE_RANGE_REG.exec(ranges);
       }
 
       repetitions = getRepetitionsBasedOnQuantifierParameters(
@@ -549,12 +549,12 @@ export class SimpleHelpersModule {
         pattern.slice(0, token.index) +
         generatedString +
         pattern.slice(token.index + token[0].length);
-      token = pattern.match(RANGE_ALPHANUMEMRIC_REG);
+      token = RANGE_ALPHANUMEMRIC_REG.exec(pattern);
     }
 
     const RANGE_REP_REG = /(.)\{(\d+),(\d+)\}/;
     // Deal with quantifier ranges `{min,max}`
-    token = pattern.match(RANGE_REP_REG);
+    token = RANGE_REP_REG.exec(pattern);
     while (token != null) {
       min = parseInt(token[2]);
       max = parseInt(token[3]);
@@ -568,19 +568,19 @@ export class SimpleHelpersModule {
         pattern.slice(0, token.index) +
         token[1].repeat(repetitions) +
         pattern.slice(token.index + token[0].length);
-      token = pattern.match(RANGE_REP_REG);
+      token = RANGE_REP_REG.exec(pattern);
     }
 
     const REP_REG = /(.)\{(\d+)\}/;
     // Deal with repeat `{num}`
-    token = pattern.match(REP_REG);
+    token = REP_REG.exec(pattern);
     while (token != null) {
       repetitions = parseInt(token[2]);
       pattern =
         pattern.slice(0, token.index) +
         token[1].repeat(repetitions) +
         pattern.slice(token.index + token[0].length);
-      token = pattern.match(REP_REG);
+      token = REP_REG.exec(pattern);
     }
 
     return pattern;
@@ -704,7 +704,7 @@ export class SimpleHelpersModule {
   uniqueArray<T>(source: ReadonlyArray<T> | (() => T), length: number): T[] {
     if (Array.isArray(source)) {
       const set = new Set<T>(source);
-      const array = Array.from(set);
+      const array = [...set];
       return this.shuffle(array).splice(0, length);
     }
 
@@ -722,7 +722,7 @@ export class SimpleHelpersModule {
       // Ignore
     }
 
-    return Array.from(set);
+    return [...set];
   }
 
   /**
@@ -1003,7 +1003,7 @@ export class SimpleHelpersModule {
       return [];
     }
 
-    const arrayCopy = array.slice(0);
+    const arrayCopy = [...array];
     let i = array.length;
     const min = i - numElements;
     let temp: T;

src/modules/internet/index.ts

@@ -271,8 +271,8 @@ export class InternetModule {
     // We limit to 50 chars to be more realistic
     localPart = localPart.substring(0, 50);
     if (allowSpecialCharacters) {
-      const usernameChars: string[] = '._-'.split('');
-      const specialChars: string[] = ".!#$%&'*+-/=?^_`{|}~".split('');
+      const usernameChars: string[] = [...'._-'];
+      const specialChars: string[] = [...".!#$%&'*+-/=?^_`{|}~"];
       localPart = localPart.replace(
         this.faker.helpers.arrayElement(usernameChars),
         this.faker.helpers.arrayElement(specialChars)
@@ -636,10 +636,9 @@ export class InternetModule {
     // First remove simple accents etc
     result = result
       .normalize('NFKD') //for example è decomposes to as e +  ̀
-      .replace(/[\u0300-\u036f]/g, ''); // removes combining marks
+      .replace(/[\u0300-\u036F]/g, ''); // removes combining marks
 
-    result = result
-      .split('')
+    result = [...result]
       .map((char) => {
         // If we have a mapping for this character, (for Cyrillic, Greek etc) use it
         if (charMapping[char]) {