orchestrator-agent
a3648397ee
Co-authored-by: orchestrator-agent <20+orchestrator-agent@code.cubecraftcreations.com>
59 lines
2.2 KiB
TypeScript
59 lines
2.2 KiB
TypeScript
// The PWA's copy of the server's dinner-name rules (internal/ai/harness
|
||
// Normalize and Similar), so a screen can tell beforehand that the dinners
|
||
// API would refuse a name as a duplicate. The server still decides.
|
||
// web/src/dinners/testdata/dedupe_cases.json is run against both.
|
||
|
||
import folds from './letterFolds.json'
|
||
|
||
// SIMILAR_THRESHOLD is harness.SimilarThreshold.
|
||
const SIMILAR_THRESHOLD = 0.85
|
||
|
||
// fillerWords is harness's fillerWords.
|
||
const fillerWords = new Set(['easy', 'best', 'homemade', 'quick', 'simple', 'the', 'a', 'recipe', 'classic'])
|
||
|
||
// letterFolds is harness's letterFolds: gen_folds.py writes both tables,
|
||
// and harness's TestLetterFoldsMatchPWA fails when they differ.
|
||
const letterFolds: Record<string, string> = folds
|
||
|
||
const combiningMark = /\p{Mn}/u
|
||
const wordChar = /[\p{L}\p{Nd}]/u
|
||
|
||
// normalizeName is harness.Normalize: lowercased, accents dropped, letters
|
||
// folded, apostrophes removed, other punctuation turned into spaces and
|
||
// filler words dropped. "Easy Chicken Tikka-Masala!" is
|
||
// "chicken tikka masala".
|
||
export function normalizeName(name: string): string {
|
||
let out = ''
|
||
// Lowercased letter by letter, as Go's strings.ToLower does, so no
|
||
// letter is lowered by its context (a final Σ is σ, not ς).
|
||
for (const letter of name) {
|
||
for (const ch of letter.toLowerCase()) {
|
||
if (combiningMark.test(ch) || ch === "'" || ch === '’') continue
|
||
const fold = letterFolds[ch]
|
||
if (fold !== undefined) out += fold
|
||
else if (wordChar.test(ch)) out += ch
|
||
else out += ' '
|
||
}
|
||
}
|
||
return out
|
||
.split(' ')
|
||
.filter((word) => word !== '' && !fillerWords.has(word))
|
||
.join(' ')
|
||
}
|
||
|
||
function words(name: string): Set<string> {
|
||
const normalized = normalizeName(name)
|
||
return new Set(normalized === '' ? [] : normalized.split(' '))
|
||
}
|
||
|
||
// similarNames is harness.Similar: whether a and b name the same dinner, by
|
||
// the share of the words of their normalized forms they have in common.
|
||
export function similarNames(a: string, b: string): boolean {
|
||
const left = words(a)
|
||
const right = words(b)
|
||
if (left.size === 0 || right.size === 0) return false
|
||
let shared = 0
|
||
for (const word of left) if (right.has(word)) shared++
|
||
return shared / (left.size + right.size - shared) >= SIMILAR_THRESHOLD
|
||
}
|