#!/usr/bin/env bun
/**
 * Strips truncated/orphan `<!-- en…` (or `<!-- en` followed by ellipsis)
 * fragments from .md files. These were produced by a display-truncated
 * comment that got round-tripped back into the source.
 */

import { readdirSync, readFileSync, statSync, writeFileSync } from "node:fs";
import { join } from "node:path";

function walkMd(dir: string): string[] {
    const out: string[] = [];
    for (const name of readdirSync(dir)) {
        const full = join(dir, name);
        const s = statSync(full);
        if (s.isDirectory()) {
            if (name === "node_modules" || name === "dist" || name === ".turbo")
                continue;
            out.push(...walkMd(full));
        } else if (name.endsWith(".md")) {
            out.push(full);
        }
    }
    return out;
}

function clean(src: string): string {
    let next = src;
    // Strip `<!-- en…` (Unicode ellipsis) on its own line or inline.
    next = next.replace(/[ \t]*<!--\s*en…[ \t]*\n?/g, "");
    // Also strip any unterminated `<!-- end:auto-docs -->` (missing closing -->).
    next = next.replace(/[ \t]*<!-- end:auto-docs[^>]*?\n/g, (m) => {
        if (m.includes("-->")) return m;
        return "";
    });
    return next;
}

function main(): void {
    const files = walkMd("packages");
    let changed = 0;
    for (const file of files) {
        const src = readFileSync(file, "utf8");
        const next = clean(src);
        if (next !== src) {
            writeFileSync(file, next);
            changed++;
        }
    }
    console.log(`Cleaned ${changed} .md files.`);
}

main();