From 9302b8e0daf4c62efbb38553a2b823960b2944cd Mon Sep 17 00:00:00 2001 From: ShareVB Date: Thu, 9 Jul 2026 22:57:39 +0200 Subject: [PATCH] feat(Case Converter): add Language specific Title Case Fix #1831 --- locales/en.yml | 3 + package.json | 2 + pnpm-lock.yaml | 16 +++ .../case-converter.service.test.ts | 120 ++++++++++++++++++ .../case-converter/case-converter.service.ts | 68 ++++++++++ src/tools/case-converter/case-converter.vue | 15 +++ src/tools/iso-639-searcher/langs.d.ts | 34 +++-- 7 files changed, 248 insertions(+), 10 deletions(-) create mode 100644 src/tools/case-converter/case-converter.service.test.ts create mode 100644 src/tools/case-converter/case-converter.service.ts diff --git a/locales/en.yml b/locales/en.yml index ea6cf1a5..f36e2af0 100644 --- a/locales/en.yml +++ b/locales/en.yml @@ -680,6 +680,9 @@ tools: label-titlecase: 'Titlecase:' label-spongecase: 'Spongecase:' label-swapcase: 'Swapcase:' + label-lang-title-case: 'Language TitleCase:' + label-language: 'Language:' + placeholder-your-language: Language Title casing language... html-entities: title: Escape HTML entities description: >- diff --git a/package.json b/package.json index 9813635b..a9e18f42 100644 --- a/package.json +++ b/package.json @@ -353,6 +353,7 @@ "sql-formatter": "^15.6.12", "sshpk": "^1.18.0", "staveless-futhark": "^0.6.1", + "stopword": "^3.1.5", "stringify-object": "^6.0.0", "svg2png-wasm": "^1.4.1", "svgo": "^3.3.3", @@ -437,6 +438,7 @@ "@types/sanitize-html": "^2.13.0", "@types/spdx-satisfies": "^6.0.0", "@types/sshpk": "^1.17.4", + "@types/stopword": "^2.0.3", "@types/stringify-object": "^4.0.5", "@types/text-encoding-utf-8": "^1.0.5", "@types/turndown": "^5.0.6", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 94e5b9f4..44b2e7c3 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -944,6 +944,9 @@ importers: staveless-futhark: specifier: ^0.6.1 version: 0.6.1 + stopword: + specifier: ^3.1.5 + version: 3.1.5 stringify-object: specifier: ^6.0.0 version: 6.0.0 @@ -1191,6 +1194,9 @@ importers: '@types/sshpk': specifier: ^1.17.4 version: 1.17.5 + '@types/stopword': + specifier: ^2.0.3 + version: 2.0.3 '@types/stringify-object': specifier: ^4.0.5 version: 4.0.5 @@ -4623,6 +4629,9 @@ packages: '@types/sshpk@1.17.5': resolution: {integrity: sha512-khJbOFAOnyLaqOoGIlDCF2ZghIb0jM1K1N0rRoKL0ObqUMwfkicu5zlJ5Wsp+Xn2EUduVwONXwsgbGk+COaCug==} + '@types/stopword@2.0.3': + resolution: {integrity: sha512-hioMj0lOvISM+EDevf7ijG8EMbU+J3pj4SstCyfQC1t39uPYpAe7beSfBdU6c1d9jeECTQQtR3UJWtVoUO8Weg==} + '@types/stringify-object@4.0.5': resolution: {integrity: sha512-TzX5V+njkbJ8iJ0mrj+Vqveep/1JBH4SSA3J2wYrE1eUrOhdsjTBCb0kao4EquSQ8KgPpqY4zSVP2vCPWKBElg==} @@ -10053,6 +10062,9 @@ packages: resolution: {integrity: sha512-eLoXW/DHyl62zxY4SCaIgnRhuMr6ri4juEYARS8E6sCEqzKpOiE521Ucofdx+KnDZl5xmvGYaaKCk5FEOxJCoQ==} engines: {node: '>= 0.4'} + stopword@3.1.5: + resolution: {integrity: sha512-OgLYGVFCNa430WOrj9tYZhQge5yg6vd6JsKredveAqEhdLVQkfrpnQIGjx0L9lLqzL4Kq4J8yNTcfQR/MpBwhg==} + stream-browserify@3.0.0: resolution: {integrity: sha512-H73RAHsVBapbim0tU2JwwOiXUj+fikfiaoYAKHF3VJfA0pe2BCzkhAHBlLG6REzE+2WNZcxOXjK7lkso+9euLA==} @@ -14913,6 +14925,8 @@ snapshots: '@types/asn1': 0.2.4 '@types/node': 24.13.2 + '@types/stopword@2.0.3': {} + '@types/stringify-object@4.0.5': {} '@types/swagger-ui-dist@3.30.6': {} @@ -21000,6 +21014,8 @@ snapshots: es-errors: 1.3.0 internal-slot: 1.1.0 + stopword@3.1.5: {} + stream-browserify@3.0.0: dependencies: inherits: 2.0.4 diff --git a/src/tools/case-converter/case-converter.service.test.ts b/src/tools/case-converter/case-converter.service.test.ts new file mode 100644 index 00000000..ed8784a8 --- /dev/null +++ b/src/tools/case-converter/case-converter.service.test.ts @@ -0,0 +1,120 @@ +import { describe, it, expect } from 'vitest'; +import { toLanguageTitleCase, getSupportedLanguages } from './case-converter.service'; + +describe('toLanguageTitleCase – core behavior', () => { + it('capitalizes normal words', () => { + expect(toLanguageTitleCase('the quick brown fox', 'eng')).toBe('The Quick Brown Fox'); + }); + + it('keeps stopwords lowercase except boundaries', () => { + expect(toLanguageTitleCase('the lord of the rings', 'eng')).toBe('The Lord of the Rings'); + }); + + it('handles empty input', () => { + expect(toLanguageTitleCase('', 'eng')).toBe(''); + }); + + it('handles single word', () => { + expect(toLanguageTitleCase('hello', 'eng')).toBe('Hello'); + }); +}); + +describe('toLanguageTitleCase – punctuation handling', () => { + it('handles trailing punctuation', () => { + expect(toLanguageTitleCase('hello, world!', 'eng')).toBe('Hello, World!'); + }); + + it('handles starting punctuation', () => { + expect(toLanguageTitleCase('(the lord of the rings)', 'eng')).toBe('(The Lord of the Rings)'); + }); + + it('handles nested punctuation', () => { + expect(toLanguageTitleCase('((the lord of the rings))', 'eng')).toBe('((The Lord of the Rings))'); + }); + + it('handles unicode punctuation', () => { + expect(toLanguageTitleCase('“the lord of the rings”', 'eng')).toBe('“The Lord of the Rings”'); + }); + + it('handles mixed punctuation', () => { + expect(toLanguageTitleCase('...the lord of the rings?!', 'eng')).toBe('...the Lord of the Rings?!'); + expect(toLanguageTitleCase('... the lord of the rings?!', 'eng')).toBe('... The Lord of the Rings?!'); + }); + + it('handles punctuation inside sentence', () => { + expect(toLanguageTitleCase('hello: the lord of the rings', 'eng')).toBe('Hello: the Lord of the Rings'); + }); +}); + +describe('toLanguageTitleCase – French elisions', () => { + it('handles basic elision', () => { + expect(toLanguageTitleCase("l'homme et la mer", 'fra')).toBe('L’Homme et la Mer'); + }); + + it('handles elision with punctuation', () => { + expect(toLanguageTitleCase("“l'homme”", 'fra')).toBe('“L’Homme”'); + }); + + it('handles multiple elisions', () => { + expect(toLanguageTitleCase("d'amour et d'etoiles", 'fra')).toBe('D’Amour et d’Etoiles'); + }); + + it('handles elisions with starting punctuation', () => { + expect(toLanguageTitleCase("(l'amour", 'fra')).toBe('(L’Amour'); + }); + + it('handles elisions with trailing punctuation', () => { + expect(toLanguageTitleCase("l'homme!", 'fra')).toBe('L’Homme!'); + }); + + it('handles elisions with unicode apostrophes', () => { + expect(toLanguageTitleCase('l’homme et l’amour', 'fra')).toBe('L’Homme et l’Amour'); + }); +}); + +describe('toLanguageTitleCase – advanced cases', () => { + it('handles numbers', () => { + expect(toLanguageTitleCase('the 7 wonders of the world', 'eng')).toBe('The 7 Wonders of the World'); + }); + + it('handles acronyms', () => { + expect(toLanguageTitleCase('the nasa launch', 'eng')).toBe('The Nasa Launch'); + }); + + it('handles hyphenated words', () => { + expect(toLanguageTitleCase('the state-of-the-art system', 'eng')).toBe('The State-of-the-art System'); + }); + + it('handles mixed languages', () => { + expect(toLanguageTitleCase("l'homme et l'homme and the sea", 'fra')).toBe('L’Homme et l’Homme And The Sea'); + }); + + it('handles multiple spaces', () => { + expect(toLanguageTitleCase('the lord of the rings', 'eng')).toBe('The Lord of the Rings'); + }); + + it('handles tabs and newlines', () => { + expect(toLanguageTitleCase('the\tlord\nof the rings', 'eng')).toBe('The Lord of the Rings'); + }); + + it('handles uppercase input', () => { + expect(toLanguageTitleCase('THE LORD OF THE RINGS', 'eng')).toBe('The Lord of the Rings'); + }); + + it('handles mixed case input', () => { + expect(toLanguageTitleCase('tHe LoRd oF tHe RiNgS', 'eng')).toBe('The Lord of the Rings'); + }); + + it('handles sentences input', () => { + expect(toLanguageTitleCase('tHe LoRd. oF tHe RiNgS', 'eng')).toBe('The Lord. Of the Rings'); + }); +}); + +describe('getSupportedLanguages', () => { + it('includes english stopwords', () => { + const langs = getSupportedLanguages(); + const en = langs.find((l) => l.value === 'eng'); + expect(en).toBeDefined(); + expect(en!.label).toBe('English'); + }); +}); diff --git a/src/tools/case-converter/case-converter.service.ts b/src/tools/case-converter/case-converter.service.ts new file mode 100644 index 00000000..2d4d346c --- /dev/null +++ b/src/tools/case-converter/case-converter.service.ts @@ -0,0 +1,68 @@ +import { type LanguageCode } from 'stopword'; +import * as stopwords from 'stopword'; +import langs from 'langs'; + +const STARTING_PUNCT = /^[({[\“"']+/; +const TRAILING_PUNCT = /[.,;:!?'"”’)\]}]+$/; +const FRENCH_ELISION = /^(l|d|j|t|m|n|s|c|qu)['’](.+)$/iu; + +/** + * Returns an array of { code, words } for all supported languages. + */ +export function getSupportedLanguages(): Array<{ value: string; label: string }> { + return Object.entries(stopwords).map(([code]) => ({ + label: langs.where('3', code)?.name ?? code, + value: code, + })); +} + +/** + * Title Case with stopwords, punctuation handling (start & end), + * and French elisions. + */ +export function toLanguageTitleCase(input: string, lang: string = 'eng'): string { + const stop = new Set(stopwords[lang as LanguageCode] ?? []); + + const words = input + .trim() + .split(/\s+/) + .map((w) => w.toLowerCase()); + + let wasBoundary = true; // Start of string is a boundary + return words + .map((rawWord) => { + // Extract starting punctuation + const startMatch = rawWord.match(STARTING_PUNCT); + const startPunct = startMatch ? startMatch[0] : ''; + const withoutStart = startPunct ? rawWord.slice(startPunct.length) : rawWord; + + // Extract trailing punctuation + const endMatch = withoutStart.match(TRAILING_PUNCT); + const endPunct = endMatch ? endMatch[0] : ''; + const core = endPunct ? withoutStart.slice(0, -endPunct.length) : withoutStart; + + const isBoundary = wasBoundary; + const isStopword = stop.has(core); + + wasBoundary = withoutStart.match(/[.!?]['"”’)\]}]*$/) !== null; + + if (lang === 'fra') { + const elision = core.match(FRENCH_ELISION); + if (elision) { + const [, prefix, rest] = elision; + const capPrefix = isBoundary ? prefix.charAt(0).toUpperCase() + prefix.slice(1) : prefix; + const capRest = rest.charAt(0).toUpperCase() + rest.slice(1); + return `${startPunct}${capPrefix}’${capRest}${endPunct}`; + } + } + + if (isStopword && !isBoundary) { + return `${startPunct}${core}${endPunct}`; + } + + // Default capitalization + const cap = core.charAt(0).toUpperCase() + core.slice(1); + return `${startPunct}${cap}${endPunct}`; + }) + .join(' '); +} diff --git a/src/tools/case-converter/case-converter.vue b/src/tools/case-converter/case-converter.vue index 3ef94c01..b1f10f38 100644 --- a/src/tools/case-converter/case-converter.vue +++ b/src/tools/case-converter/case-converter.vue @@ -20,6 +20,7 @@ import { titleCase } from 'title-case'; import InputCopyable from '../../components/InputCopyable.vue'; import { useQueryParam, useQueryParamOrStorage } from '@/composable/queryParams'; import { useValidation } from '@/composable/validation'; +import { getSupportedLanguages, toLanguageTitleCase } from './case-converter.service.ts'; const { t } = useI18n(); @@ -43,6 +44,7 @@ const cleaningRegexValidation = useValidation({ }); const input = useQueryParam({ tool: 'case-conv', name: 'text', defaultValue: 'lorem ipsum dolor sit amet' }); +const language = useQueryParam({ tool: 'case-conv', name: 'lang', defaultValue: 'eng' }); const inputCleaned = computed(() => { if (!cleaningRegexValidation.isValid) { return input.value.split('\n'); @@ -51,6 +53,10 @@ const inputCleaned = computed(() => { }); const formats = computed(() => [ + { + label: t('tools.case-converter.texts.label-lang-title-case'), + value: inputCleaned.value.map((s) => toLanguageTitleCase(s, language.value)), + }, { label: t('tools.case-converter.texts.label-lowercase'), value: inputCleaned.value.map((s) => s.toLocaleLowerCase()), @@ -154,6 +160,15 @@ const inputLabelAlignmentConfig = { mb-1 /> + +
-} \ No newline at end of file + export function all(): Array<{ + name: string; + local: string; + '1': string; + '2': string; + '2T': string; + '2B': string; + '3': string; + }>; + export function where( + type: string, + value: string, + ): + | { + name: string; + local: string; + '1': string; + '2': string; + '2T': string; + '2B': string; + '3': string; + } + | undefined; +}