/**
 * @copyright Sister Software
 * @license AGPL-3.0
 * @author Teffen Ellis, et al.
 *
 * Decompose a US street name into Stage 3 components (street_prefix, street, street_suffix) from the
 * curated libpostal/en directionals and street_types dictionaries — the same ones the runtime
 * StreetPrefixClassifier and StreetSuffixClassifier use, so corpus labels and runtime classifications
 * agree on the vocabulary.
 */

import { loadLibpostalDictionary } from "#adapters/libpostal-dictionary"

const [DIRECTIONALS, STREET_TYPES] = await Promise.all([
	loadLibpostalDictionary("en", "directionals.txt"),
	loadLibpostalDictionary("en", "street_types.txt"),
])

export interface DecomposedStreet {
	prefix: string | null
	street: string
	suffix: string | null
}

/**
 * Decompose a US street name into prefix/name/suffix components.
 *
 * Conservative, emitting a prefix or suffix only for a clear directional or street-type keyword.
 * It returns the original as `street` when no pattern matches.
 */
export function decomposeStreet(fullname: string): DecomposedStreet {
	const trimmed = fullname.trim()

	if (!trimmed) return { prefix: null, street: "", suffix: null }

	const tokens = trimmed.split(/\s+/)

	if (tokens.length === 1) return { prefix: null, street: trimmed, suffix: null }

	const norm = (s: string) => s.toLowerCase().replace(/\.$/, "")

	let prefix: string | null = null
	let suffix: string | null = null
	let startIdx = 0
	let endIdx = tokens.length

	if (DIRECTIONALS.has(norm(tokens[0]!)) && tokens.length >= 2) {
		prefix = tokens[0]!
		startIdx = 1
	}

	const last = norm(tokens[endIdx - 1]!)
	const secondLast = endIdx >= 2 ? norm(tokens[endIdx - 2]!) : ""

	if (DIRECTIONALS.has(last) && STREET_TYPES.has(secondLast)) {
		suffix = tokens.slice(endIdx - 2, endIdx).join(" ")
		endIdx -= 2
	} else if (STREET_TYPES.has(last) && endIdx - startIdx >= 2) {
		suffix = tokens[endIdx - 1]!
		endIdx -= 1
	} else if (DIRECTIONALS.has(last) && endIdx - startIdx >= 2) {
		suffix = tokens[endIdx - 1]!
		endIdx -= 1
	}

	const street = tokens.slice(startIdx, endIdx).join(" ").trim()

	if (!street) {
		return { prefix: null, street: trimmed, suffix: null }
	}

	return { prefix, street, suffix }
}