skill-tree-portfolio/src/lib/utils/search.ts

// ==========================================================================
// SEARCH — subsequence matching over the tree data. Pure, no DOM, no PixiJS.
// ==========================================================================

import { treeNodes, type TreeNode } from '$lib/data';

export interface SearchResult {
	node: TreeNode;
	score: number;
	/** Why it matched, for display ("React" vs "tech: React"). */
	context?: string;
}

/**
 * Case-insensitive subsequence match: "wbrtc" matches "WebRTC".
 *
 * Returns a score where lower is better, or null for no match. Consecutive
 * runs and an early first match are rewarded, so "react" ranks the React node
 * above a project that merely lists React in its stack.
 */
function subsequenceScore(haystack: string, needle: string): number | null {
	if (!needle) return 0;
	const h = haystack.toLowerCase();
	const n = needle.toLowerCase();

	// Exact and prefix matches short-circuit to the best scores.
	if (h === n) return -1000;
	if (h.startsWith(n)) return -500 + h.length;

	let score = 0;
	let hi = 0;
	let lastHit = -1;
	for (let ni = 0; ni < n.length; ni++) {
		const found = h.indexOf(n[ni], hi);
		if (found === -1) return null;
		// Penalise gaps; reward adjacency.
		score += found === lastHit + 1 ? 0 : found - hi + 1;
		lastHit = found;
		hi = found + 1;
	}
	// Prefer shorter haystacks — "Git" should beat "GitHub Actions" for "git".
	return score + h.length * 0.1;
}

/** Search every node by label, then category, then description/tech stack. */
export function searchNodes(query: string, nodes: TreeNode[] = treeNodes): SearchResult[] {
	const q = query.trim();
	if (!q) return [];

	const results: SearchResult[] = [];

	for (const node of nodes) {
		const labelScore = subsequenceScore(node.label, q);
		if (labelScore !== null) {
			results.push({ node, score: labelScore });
			continue;
		}

		// Tech stack is a strong signal — searching "prisma" should surface the
		// projects that use it even though no node is named Prisma.
		if (node.category === 'projects' && node.techStack) {
			const tech = node.techStack.find((t) => subsequenceScore(t, q) !== null);
			if (tech) {
				results.push({ node, score: 200, context: `tech: ${tech}` });
				continue;
			}
		}

		if (node.category === 'experience' && node.company) {
			const companyScore = subsequenceScore(node.company, q);
			if (companyScore !== null) {
				results.push({ node, score: companyScore + 100, context: node.company });
				continue;
			}
		}

		// Descriptions use plain substring matching, not subsequence. Over long
		// prose a subsequence match is almost always spurious — "Prisma" found a
		// p...r...i...s...m...a spread across an unrelated sentence.
		const haystack = node.description.toLowerCase();
		const needle = q.toLowerCase();
		const at = haystack.indexOf(needle);
		if (at !== -1) {
			results.push({
				node,
				score: 400 + at,
				context: node.description.slice(Math.max(0, at - 20), at + 45).trim()
			});
		}
	}

	return results.sort((a, b) => a.score - b.score);
}