// unicode-bom.test.mjs — Regression tests for the leading-BOM exception in
// unicode-scanner (v7.8.3, #42).
//
// A legitimate UTF-8 BOM (U+FEFF at file position 0) was flagged as a HIGH
// zero-width finding — a finding the tool's own auto-cleaner refuses to strip
// (auto-cleaner.mjs preserves cp === 0xFEFF at line 0, pos 0). The scanner
// must apply the same file-start exception. A BOM anywhere else in the file
// is still a zero-width smuggling vector and must be flagged.

import { describe, it, beforeEach, after } from 'node:test';
import assert from 'node:assert/strict';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
import { mkdtemp, writeFile, rm } from 'node:fs/promises';
import { resetCounter } from '../../scanners/lib/output.mjs';
import { discoverFiles } from '../../scanners/lib/file-discovery.mjs';
import { scan } from '../../scanners/unicode-scanner.mjs';

const created = [];

/** Make a scan root containing a single file with the given content. */
async function makeRepo(content, fileName = 'app.mjs') {
  const root = await mkdtemp(join(tmpdir(), 'llmsec-bom-'));
  created.push(root);
  await writeFile(join(root, fileName), content, 'utf8');
  return root;
}

async function scanRepo(root) {
  resetCounter();
  const discovery = await discoverFiles(root);
  return scan(root, discovery);
}

function zeroWidthFindings(result) {
  return result.findings.filter(f =>
    f.title.toLowerCase().includes('zero-width') ||
    (f.evidence && f.evidence.toUpperCase().includes('U+FEFF'))
  );
}

after(async () => {
  for (const dir of created) await rm(dir, { recursive: true, force: true });
});

describe('unicode-scanner — leading UTF-8 BOM exception (v7.8.3, #42)', () => {
  beforeEach(() => {
    resetCounter();
  });

  it('does not flag a legitimate BOM at file position 0', async () => {
    const root = await makeRepo('\uFEFFconst x = 1;\nexport default x;\n');
    const result = await scanRepo(root);
    assert.equal(result.status, 'ok');
    const hits = zeroWidthFindings(result);
    assert.equal(
      hits.length, 0,
      `leading BOM must not be flagged, got: ${hits.map(f => f.title).join('; ')}`
    );
  });

  it('still flags a BOM at the start of a later line', async () => {
    const root = await makeRepo('const x = 1;\n\uFEFFconst y = 2;\n');
    const result = await scanRepo(root);
    assert.equal(result.status, 'ok');
    const hits = zeroWidthFindings(result);
    assert.ok(
      hits.length >= 1,
      `mid-file BOM must be flagged, got ${hits.length} findings`
    );
    assert.equal(hits[0].line, 2);
  });

  it('still flags a BOM mid-line on the first line', async () => {
    const root = await makeRepo('const x\uFEFF = 1;\n');
    const result = await scanRepo(root);
    assert.equal(result.status, 'ok');
    const hits = zeroWidthFindings(result);
    assert.ok(
      hits.length >= 1,
      `first-line non-leading BOM must be flagged, got ${hits.length} findings`
    );
  });

  it('still flags other zero-width chars on the first line after a BOM', async () => {
    const root = await makeRepo('\uFEFFconst x\u200B = 1;\n');
    const result = await scanRepo(root);
    assert.equal(result.status, 'ok');
    const hits = result.findings.filter(f =>
      f.evidence && f.evidence.toUpperCase().includes('U+200B')
    );
    assert.ok(
      hits.length >= 1,
      `U+200B after a leading BOM must still be flagged, got ${hits.length} findings`
    );
  });
});