Files
orca/src/shared/emoji-shortcode-catalog.ts

97 lines
3.4 KiB
TypeScript
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
export type StandardEmojiShortcodeEntry = {
emoji: string
shortcode: string
}
/** Shape of `emojibase-data/en/shortcodes/emojibase.json`: hexcode -> shortcode or aliases. */
export type EmojiShortcodeDataset = Readonly<Record<string, string | readonly string[]>>
let loadDataset: (() => EmojiShortcodeDataset) | null = null
/** Renderer needs eager synchronous data or it persists literal :wink: during load. Inject main’s lazy require to avoid bundling/parsing 166KB at launch. */
export function setEmojiShortcodeDatasetLoader(load: () => EmojiShortcodeDataset): void {
loadDataset = load
}
// Skin-tone aliases (`wave_tone3`) are ~40% of the dataset and would drown the suggestion list.
const SKIN_TONE_SHORTCODE = /_tone\d(?:-\d)?$/
type EmojiShortcodeCatalog = {
entries: readonly StandardEmojiShortcodeEntry[]
primaryShortcodeByEmoji: ReadonlyMap<string, string>
segmenter: Intl.Segmenter
}
let catalog: EmojiShortcodeCatalog | null = null
// Defer ~3,900-shortcode traversal until first colon/name sanitization, memoizing once instead of charging every launch.
function loadCatalog(): EmojiShortcodeCatalog {
if (catalog) {
return catalog
}
if (!loadDataset) {
throw new Error('Emoji shortcode dataset loader was never registered')
}
const grouped = Object.entries(loadDataset()).flatMap(([hexcode, value]) => {
const shortcodes = (typeof value === 'string' ? [value] : value).filter(
(shortcode) => !SKIN_TONE_SHORTCODE.test(shortcode)
)
return shortcodes.length > 0 ? [{ emoji: hexcodeToEmoji(hexcode), shortcodes }] : []
})
catalog = {
entries: grouped.flatMap(({ emoji, shortcodes }) =>
shortcodes.map((shortcode) => ({ emoji, shortcode }))
),
primaryShortcodeByEmoji: new Map(
grouped.map(({ emoji, shortcodes }) => [
normalizeEmojiLookup(emoji),
primaryShortcode(shortcodes)
])
),
segmenter: new Intl.Segmenter('en', { granularity: 'grapheme' })
}
return catalog
}
export function getStandardEmojiShortcodeEntries(): readonly StandardEmojiShortcodeEntry[] {
return loadCatalog().entries
}
/** Prefer spelled-out names over symbolic +1/-1, cryptic no/v and flag_xx namespaces for branch/directory labels. */
function primaryShortcode(shortcodes: readonly string[]): string {
const named = shortcodes.filter((candidate) => /^[a-z]/i.test(candidate))
return (
named.find((candidate) => candidate.length >= 3 && !candidate.startsWith('flag_')) ??
named.find((candidate) => candidate.length >= 3) ??
named[0] ??
shortcodes[0]
)
}
export function replaceKnownEmojiWithShortcodes(input: string): string {
const { primaryShortcodeByEmoji, segmenter } = loadCatalog()
return Array.from(segmenter.segment(input), ({ segment }) => {
const shortcode = primaryShortcodeByEmoji.get(normalizeEmojiLookup(segment))
return shortcode ? ` ${shortcode.replaceAll('_', '-')} ` : segment
}).join('')
}
function normalizeEmojiLookup(emoji: string): string {
return Array.from(emoji)
.filter((character) => {
const codepoint = character.codePointAt(0)
return (
character !== '\ufe0f' &&
(codepoint === undefined || codepoint < 0x1f3fb || codepoint > 0x1f3ff)
)
})
.join('')
}
function hexcodeToEmoji(hexcode: string): string {
return hexcode
.split('-')
.map((codepoint) => String.fromCodePoint(Number.parseInt(codepoint, 16)))
.join('')
}