pi-map/src/routing-metadata.ts

import type {
	DirectoryArtifactModel,
	FileEntry,
	RoutingMetadataOptions,
	WorkflowHint,
} from "./directory-model.js";

const DEFAULT_TAG_CAP = 8;
const DEFAULT_WORKFLOW_HINT_CAP = 5;

const STOP_WORDS = new Set([
	"the",
	"and",
	"for",
	"with",
	"from",
	"into",
	"onto",
	"this",
	"that",
	"then",
	"than",
	"when",
	"where",
	"what",
	"how",
	"why",
	"who",
	"which",
	"while",
	"during",
	"before",
	"after",
	"above",
	"below",
	"between",
	"among",
	"through",
	"over",
	"under",
	"again",
	"further",
	"once",
	"here",
	"there",
	"all",
	"any",
	"both",
	"each",
	"few",
	"more",
	"most",
	"other",
	"some",
	"such",
	"only",
	"own",
	"same",
	"so",
	"too",
	"very",
	"can",
	"will",
	"just",
	"should",
	"now",
	"use",
	"using",
	"used",
	"via",
	"based",
	"build",
	"built",
	"used",
	"file",
	"files",
	"module",
	"modules",
	"function",
	"functions",
	"class",
	"classes",
	"export",
	"exports",
	"import",
	"imports",
]);

export function populateRoutingMetadata(
	model: DirectoryArtifactModel,
	opts: RoutingMetadataOptions = {},
): void {
	const tagCap = opts.tagCap ?? DEFAULT_TAG_CAP;
	const workflowHintCap = opts.workflowHintCap ?? DEFAULT_WORKFLOW_HINT_CAP;

	model.tags = generateTags(model.files, tagCap);
	model.symbols = generateSymbols(model.files, tagCap);
	model.workflows = generateWorkflows(model, workflowHintCap);
}

function generateTags(files: FileEntry[], cap: number): string[] {
	const scores = new Map<string, number>();

	for (const file of files) {
		// Score words from file purpose
		for (const word of extractWords(file.purpose)) {
			scores.set(word, (scores.get(word) ?? 0) + 1);
		}

		// Score words from export names (camelCase split)
		for (const exp of file.exports) {
			const cleanExp = exp.replace(/^(class|func|method):/, "").split("(")[0];
			for (const word of splitCamelCase(cleanExp)) {
				if (word.length > 1) {
					scores.set(word, (scores.get(word) ?? 0) + 2);
				}
			}
		}

		// Score dep path segments
		for (const dep of file.deps) {
			for (const segment of dep.split(/[/\-.]/)) {
				const word = segment.toLowerCase();
				if (word.length > 1 && !STOP_WORDS.has(word)) {
					scores.set(word, (scores.get(word) ?? 0) + 1);
				}
			}
		}

		// Score from file name (stem, no extension)
		const stem = file.name.replace(/\.[^.]+$/, "");
		for (const word of splitCamelCase(stem)) {
			if (word.length > 1) {
				scores.set(word, (scores.get(word) ?? 0) + 2);
			}
		}
	}

	return Array.from(scores.entries())
		.sort((a, b) => b[1] - a[1])
		.map(([word]) => word)
		.slice(0, cap);
}

function generateSymbols(files: FileEntry[], cap: number): string[] {
	const scores = new Map<string, number>();
	const seen = new Set<string>();

	for (const file of files) {
		for (const exp of file.exports) {
			// Prefer clean identifiers over encoded DSL entries when possible
			let symbol = exp;
			let score = 1;

			if (exp.startsWith("class:")) {
				symbol = exp.slice(6).split(" ")[0];
				score = 3;
			} else if (exp.startsWith("func:")) {
				symbol = exp.slice(5).split("(")[0];
				score = 2;
			} else if (exp.startsWith("method:")) {
				symbol = exp.slice(7).split("(")[0];
				score = 2;
			}

			if (!seen.has(symbol)) {
				seen.add(symbol);
				scores.set(symbol, (scores.get(symbol) ?? 0) + score);
			}
		}
	}

	return Array.from(scores.entries())
		.sort((a, b) => b[1] - a[1])
		.map(([name]) => name)
		.slice(0, cap);
}

function generateWorkflows(
	model: DirectoryArtifactModel,
	cap: number,
): WorkflowHint[] {
	const workflows: WorkflowHint[] = [];
	const dirName = model.dir.split("/").pop() || model.dir;
	const baseName = dirName === "." ? "project" : dirName;

	// Only generate workflows when we have reasonable structural confidence
	const hasSourceFiles = model.files.some((f) =>
		/\.(ts|tsx|js|jsx|py|go|rs|java)$/.test(f.name),
	);
	if (!hasSourceFiles || model.files.length === 0) {
		return workflows;
	}

	const sourceFiles = model.files.filter(
		(f) =>
			!/\.(test|spec)\./.test(f.name) && !/\.(md|json|yaml|yml)$/.test(f.name),
	);
	const testFiles = model.files.filter((f) => /\.(test|spec)\./.test(f.name));
	const configFiles = model.files.filter(
		(f) =>
			f.name.includes("config") ||
			/\.(json|yaml|yml|toml)$/.test(f.name) ||
			f.name === ".env",
	);
	const cliFiles = model.files.filter(
		(f) => f.name.includes("cli") || f.name.includes("command"),
	);

	if (sourceFiles.length > 0) {
		workflows.push({
			task: `change ${baseName} behavior`,
			read: sourceFiles.slice(0, 3).map((f) => f.name),
		});
	}

	if (testFiles.length > 0) {
		workflows.push({
			task: `update ${baseName} tests`,
			read: testFiles.slice(0, 3).map((f) => f.name),
		});
	}

	if (cliFiles.length > 0) {
		workflows.push({
			task: `change ${baseName} CLI`,
			read: cliFiles.slice(0, 3).map((f) => f.name),
		});
	}

	if (configFiles.length > 0) {
		workflows.push({
			task: `change ${baseName} config`,
			read: configFiles.slice(0, 3).map((f) => f.name),
		});
	}

	// Add a directory-navigation workflow for non-leaf directories
	if (model.children.length > 0) {
		workflows.push({
			task: `explore ${baseName} subdirectories`,
			index: model.children
				.slice(0, 3)
				.map((child) => `${child}/.pi-map.index.md`),
		});
	}

	return workflows.slice(0, cap);
}

function extractWords(text: string): string[] {
	return text
		.toLowerCase()
		.split(/[^a-z0-9]+/)
		.filter((w) => w.length > 2 && !STOP_WORDS.has(w));
}

function splitCamelCase(str: string): string[] {
	return str
		.replace(/([a-z0-9])([A-Z])/g, "$1 $2")
		.replace(/[_-]+/g, " ")
		.toLowerCase()
		.split(/\s+/)
		.filter((w) => w.length > 1 && !STOP_WORDS.has(w));
}