// av-surface.test.mjs — the antivirus surface of the tracked tree.
//
// Outcome this gates (operator, 2026-09-22): a Windows user can clone the
// repository and install the plugin without Defender or a similar product
// quarantining anything, and the plugin still finds what it finds today.
//
// What a documented AV quarantine in a security repository reacts to is a
// payload sitting on disk in the file type that would run it (a reverse shell
// in `.sh`, a webshell in `.php`, a SKILL.md clustering attack techniques) —
// not a regex table. So this test walks `git ls-files` — the same set a clone
// and the plugin cache put on a user's disk — and fails on four surfaces:
//
//   (a) a file whose non-comment content matches one of our OWN SIG rules in
//       the webshell / reverse_shell / cryptominer families, through the same
//       decode variants the SIG scanner tests (raw, decoded, homoglyph-folded,
//       rot13). The rules are reused from scanners/lib/malware-signatures.mjs;
//       no new regexes. Excluded from the denominator:
//         - code/data hosts (.mjs .js .cjs .json), where a payload is a quoted
//           string or a detection-table entry, not a runnable file. This keeps
//           the untouchable signature tables (commons JSON, golden
//           patterns.json, the supply-chain blocklist) out of a gate that must
//           reach zero. Literal payloads inside test .mjs files are therefore
//           NOT gated here; S1 moves them to test-time construction anyway.
//         - scanners/commons/**, the vendored pull-only subtree this
//           repository may not edit.
//   (b) a base64 blob of 24+ characters that decodes to printable text
//       containing curl, wget, bash, sh, eval or http as a WORD. Word
//       boundaries are deliberate: a bare substring `sh` matches "should" and
//       "hash", which are not shell commands.
//   (c) a Unicode Tag (U+E0000-U+E007F), zero-width (U+200B-U+200D, U+2060,
//       U+FEFF) or bidi-control (U+202A-U+202E, U+2066-U+2069) codepoint in a
//       TEXT file outside scanners/commons/conformance/**. Binary files (a NUL
//       byte in the first 8 KiB, the rule readTextFile uses) are outside the
//       denominator: decoding compressed PNG/WOFF2 bytes as UTF-8 yields these
//       codepoints by chance, and no reader ever sees them as characters.
//   (d) any tracked file under a known payload tree.
//
// This test was written RED on purpose (order S0, 2026-09-22): it is the
// failing test for sessions S1-S3 of the v8.1.0 plan. It is expected to fail
// until those sessions land.

import { describe, it } from 'node:test';
import assert from 'node:assert/strict';
import { execFileSync } from 'node:child_process';
import { readFileSync } from 'node:fs';
import { resolve, extname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { SIGNATURE_RULES } from '../scanners/lib/malware-signatures.mjs';
import { normalizeForScan, foldHomoglyphs, rot13 } from '../scanners/lib/string-utils.mjs';

const ROOT = resolve(fileURLToPath(new URL('.', import.meta.url)), '..');

const PAYLOAD_FAMILIES = new Set(['webshell', 'reverse_shell', 'cryptominer']);
const QUOTING_HOSTS = new Set(['.mjs', '.js', '.cjs', '.json']);
const VENDORED = 'scanners/commons/';
const CONFORMANCE = 'scanners/commons/conformance/';

// A line counts as a comment when it opens with a comment marker. `#!` is a
// shebang, not a comment, and stays in.
const COMMENT_LINE = /^\s*(?:\/\/|#(?!!)|\/\*|\*|<!--)/;

const BASE64_BLOB = /[A-Za-z0-9+/]{24,}={0,2}/g;
const PRINTABLE = /^[\x20-\x7e\t\r\n]+$/;
const SHELL_WORD = /\b(?:curl|wget|bash|sh|eval|http)\b/;

const CARRIER = /[\u{E0000}-\u{E007F}\u200B-\u200D\u2060\uFEFF\u202A-\u202E\u2066-\u2069]/u;

const PAYLOAD_TREES = [
  'tests/fixtures/signature-scan/poisoned/',
  'tests/fixtures/memory-scan/poisoned-project/',
  'tests/fixtures/trigger-scan/poisoned/',
  'examples/malicious-skill-demo/evil-project-health/',
  'examples/poisoned-claude-md/fixture/',
];

function trackedFiles() {
  return execFileSync('git', ['ls-files', '-z'], { cwd: ROOT, encoding: 'utf8' })
    .split('\0')
    .filter(Boolean);
}

function isBinary(buf) {
  return buf.subarray(0, 8192).includes(0);
}

/** Measure all four surfaces over the tracked tree. */
function measureAvSurface() {
  const files = trackedFiles();
  const rules = SIGNATURE_RULES.filter(r => PAYLOAD_FAMILIES.has(r.family));
  const a = [];
  const b = [];
  const c = [];
  let textFiles = 0;

  for (const rel of files) {
    const buf = readFileSync(resolve(ROOT, rel));
    if (isBinary(buf)) continue;
    textFiles++;
    const text = buf.toString('utf8');

    if (!QUOTING_HOSTS.has(extname(rel).toLowerCase()) && !rel.startsWith(VENDORED)) {
      const body = text.split('\n').filter(line => !COMMENT_LINE.test(line)).join('\n');
      const variants = [
        body,
        normalizeForScan(body, { decodeEmbedded: true }),
        normalizeForScan(body.trim(), { decodeEmbedded: true }),
        foldHomoglyphs(body),
        rot13(body),
      ];
      const hits = rules.filter(r => variants.some(v => r.re.test(v))).map(r => r.id);
      if (hits.length > 0) a.push(`${rel} [${hits.join(', ')}]`);
    }

    for (const m of text.matchAll(BASE64_BLOB)) {
      const decoded = Buffer.from(m[0], 'base64').toString('latin1');
      if (PRINTABLE.test(decoded) && SHELL_WORD.test(decoded)) {
        b.push(`${rel} :: ${decoded.slice(0, 60).replace(/\s+/g, ' ')}`);
      }
    }

    if (!rel.startsWith(CONFORMANCE) && CARRIER.test(text)) c.push(rel);
  }

  const d = PAYLOAD_TREES
    .map(tree => ({ tree, files: files.filter(f => f.startsWith(tree)) }))
    .filter(t => t.files.length > 0);

  return {
    tracked: files.length,
    textFiles,
    a,
    b,
    bFiles: new Set(b.map(x => x.split(' :: ')[0])).size,
    c,
    d,
  };
}

const report = (label, items) => `${label}: ${items.length}\n  ${items.join('\n  ')}`;

describe('av-surface: tracked tree carries no AV-triggering payloads', () => {
  const m = measureAvSurface();

  it(`(a) no SIG payload in a runnable file type (of ${m.textFiles} text files)`, (t) => {
    t.diagnostic(`a=${m.a.length}`);
    assert.deepEqual(m.a, [], report('files with a SIG payload', m.a));
  });

  it(`(b) no base64 blob decoding to a shell command (of ${m.textFiles} text files)`, (t) => {
    t.diagnostic(`b=${m.b.length} blobs in ${m.bFiles} files`);
    assert.deepEqual(m.b, [], report('base64 blobs', m.b));
  });

  it(`(c) no Tag/zero-width/bidi carrier outside the conformance corpus (of ${m.textFiles} text files)`, (t) => {
    t.diagnostic(`c=${m.c.length}`);
    assert.deepEqual(m.c, [], report('files with a carrier codepoint', m.c));
  });

  it(`(d) no known payload tree on disk (of ${PAYLOAD_TREES.length} trees)`, (t) => {
    const lines = m.d.map(x => `${x.tree} (${x.files.length} files)`);
    t.diagnostic(`d=${m.d.length}`);
    assert.deepEqual(lines, [], report('payload trees', lines));
  });
});