import { readFile, readdir } from 'node:fs/promises';
import { dirname, extname, join, resolve } from 'node:path';
import { fileURLToPath } from 'node:url';
import { describe, expect, it } from 'vitest';
import { parseRosterV2, validateRosterV2Semantics } from './roster-v2.js';

const packageRoot = resolve(dirname(fileURLToPath(import.meta.url)), '..', '..');
const repositoryRoot = resolve(packageRoot, '..', '..');
const fleetDocs = join(repositoryRoot, 'docs', 'fleet');
const frameworkFleet = join(packageRoot, 'framework', 'fleet');

const REQUIRED_FLEET_PAGES = [
  'README.md',
  'concepts/desired-vs-observed-state.md',
  'concepts/identity-class-runtime.md',
  'concepts/role-authority-and-leases.md',
  'concepts/generated-env-launch-chain.md',
  'reference/roster-v2.schema.json',
  'reference/roster-v2-fields.md',
  'reference/cli.md',
  'reference/role-classes.md',
  'reference/lifecycle-transitions.md',
  'reference/status-and-drift.md',
  'how-to/create-update-delete-agent.md',
  'how-to/start-stop-restart.md',
  'how-to/configure-tess-interaction.md',
  'how-to/configure-ultron-validator.md',
  'how-to/customize-roles.md',
  'operations/reconcile-and-recover.md',
  'operations/env-quarantine.md',
  'operations/systemd-tmux-troubleshooting.md',
  'operations/backup-restore.md',
  'operations/upgrade-assets.md',
  'migration/v1-to-v2.md',
  'migration/example-profile-disposition.md',
  'migration/legacy-class-aliases.md',
] as const;

async function markdownFiles(root: string): Promise<string[]> {
  const entries = await readdir(root, { withFileTypes: true });
  const paths = await Promise.all(
    entries.map(async (entry): Promise<string[]> => {
      const path = join(root, entry.name);
      if (entry.isDirectory()) return markdownFiles(path);
      return extname(entry.name) === '.md' ? [path] : [];
    }),
  );
  return paths.flat().sort();
}

function localMarkdownTargets(source: string): string[] {
  const link =
    /\[[^\]]*\]\(\s*(?:<([^>]+)>|((?:\\.|[^()\s]|\([^()]*\))+))(?:\s+(?:"[^"]*"|'[^']*'|\([^)]*\)))?\s*\)/g;
  return [...source.matchAll(link)]
    .map((match): string => match[1] ?? match[2] ?? '')
    .filter(
      (target): boolean =>
        target !== '' &&
        !target.startsWith('http://') &&
        !target.startsWith('https://') &&
        !target.startsWith('mailto:'),
    );
}

function markdownHeadingAnchors(source: string): Set<string> {
  const anchors = new Set<string>();
  let fence: { readonly marker: string; readonly length: number } | undefined;

  for (const line of source.split('\n')) {
    const fenceMatch = line.match(/^\s{0,3}(`{3,}|~{3,})(.*)$/);
    if (fence === undefined && fenceMatch !== null) {
      const run = fenceMatch[1] ?? '';
      fence = { marker: run[0] ?? '', length: run.length };
      continue;
    }
    if (fence !== undefined) {
      const closingRun = line.match(/^\s{0,3}(`{3,}|~{3,})\s*$/)?.[1];
      if (
        closingRun !== undefined &&
        closingRun[0] === fence.marker &&
        closingRun.length >= fence.length
      ) {
        fence = undefined;
      }
      continue;
    }

    const heading = line.match(/^\s{0,3}#{1,6}\s+(.+?)\s*#*\s*$/)?.[1];
    if (heading === undefined) continue;
    const base = heading
      .replace(/!?\[([^\]]*)\]\([^)]*\)/g, '$1')
      .replace(/<[^>]*>/g, '')
      .replace(/[`*_~]/g, '')
      .toLowerCase()
      .trim()
      .replace(/[^\p{L}\p{N}\s-]/gu, '')
      .replace(/\s+/g, '-');
    let anchor = base;
    let duplicate = 0;
    while (anchors.has(anchor)) {
      duplicate += 1;
      anchor = `${base}-${duplicate}`;
    }
    anchors.add(anchor);
  }
  return anchors;
}

function markdownLinkViolations(
  sourcePath: string,
  source: string,
  documents: Readonly<Record<string, string>>,
): string[] {
  const violations: string[] = [];
  for (const target of localMarkdownTargets(source)) {
    const [encodedPath = '', encodedFragment] = target.split('#', 2);
    const targetPath = decodeURIComponent(encodedPath);
    const normalizedTarget = resolve('/', dirname(sourcePath), targetPath).slice(1);
    const targetSource = documents[normalizedTarget];
    if (targetSource === undefined) {
      violations.push(`${sourcePath} -> ${target}: missing file`);
      continue;
    }
    if (encodedFragment !== undefined) {
      const fragment = decodeURIComponent(encodedFragment);
      if (fragment === '' || !markdownHeadingAnchors(targetSource).has(fragment)) {
        violations.push(`${sourcePath} -> ${target}: missing heading`);
      }
    }
  }
  return violations;
}

function commandBasename(token: string): string {
  return token.slice(token.lastIndexOf('/') + 1);
}

function shellCommandSegments(source: string): string[] {
  const segments: string[] = [];
  let segment = '';
  let quote = '';
  let escaped = false;

  const flush = (): void => {
    if (segment.trim() !== '') segments.push(segment);
    segment = '';
  };

  for (const character of source) {
    if (escaped) {
      segment += character;
      escaped = false;
      continue;
    }
    if (character === '\\' && quote !== "'") {
      segment += character;
      escaped = true;
      continue;
    }
    if (quote !== '') {
      segment += character;
      if (character === quote) quote = '';
      continue;
    }
    if (character === "'" || character === '"') {
      segment += character;
      quote = character;
      continue;
    }
    if (character === '\n' || character === ';' || character === '&' || character === '|') {
      flush();
      continue;
    }
    segment += character;
  }
  flush();
  return segments;
}

function shellCommandTokens(source: string): string[] {
  const tokens: string[] = [];
  let token = '';
  let quote = '';
  let escaped = false;

  for (const character of source) {
    if (escaped) {
      token += character;
      escaped = false;
      continue;
    }
    if (character === '\\' && quote !== "'") {
      escaped = true;
      continue;
    }
    if (quote !== '') {
      if (character === quote) quote = '';
      else token += character;
      continue;
    }
    if (character === "'" || character === '"') {
      quote = character;
      continue;
    }
    if (/\s/.test(character)) {
      if (token !== '') {
        tokens.push(token);
        token = '';
      }
      continue;
    }
    token += character;
  }
  if (escaped) token += '\\';
  if (token !== '') tokens.push(token);
  return tokens;
}

function normalizedCommandTokens(segment: string): string[] {
  const tokens = shellCommandTokens(segment.trim().replace(/^(?:[$#>]\s*)/, ''));
  let index = 0;

  while (index < tokens.length) {
    const wrapper = commandBasename(tokens[index] ?? '');
    if (wrapper === 'env') {
      index += 1;
      while (index < tokens.length) {
        const token = tokens[index] ?? '';
        if (/^[A-Za-z_][A-Za-z0-9_]*=/.test(token)) {
          index += 1;
          continue;
        }
        if (token === '--') {
          index += 1;
          break;
        }
        if (/^(?:--unset|--chdir)$/.test(token)) {
          index += 2;
          continue;
        }
        if (/^(?:--unset=|--chdir=)/.test(token)) {
          index += 1;
          continue;
        }
        if (token === '--split-string') {
          const splitTokens = shellCommandTokens(tokens[index + 1] ?? '');
          tokens.splice(index, 2, ...splitTokens);
          continue;
        }
        const longSplitString = token.match(/^--split-string=(.*)$/)?.[1];
        if (longSplitString !== undefined) {
          tokens.splice(index, 1, ...shellCommandTokens(longSplitString));
          continue;
        }
        if (/^-[^-]/.test(token)) {
          const options = token.slice(1);
          let consumed = false;
          for (let optionIndex = 0; optionIndex < options.length; optionIndex += 1) {
            const option = options[optionIndex] ?? '';
            if (option === 'u' || option === 'C') {
              index += options.slice(optionIndex + 1) === '' ? 2 : 1;
              consumed = true;
              break;
            }
            if (option === 'S') {
              const attached = options.slice(optionIndex + 1);
              const operand = attached === '' ? (tokens[index + 1] ?? '') : attached;
              tokens.splice(index, attached === '' ? 2 : 1, ...shellCommandTokens(operand));
              consumed = true;
              break;
            }
          }
          if (!consumed) index += 1;
          continue;
        }
        if (token.startsWith('-')) {
          index += 1;
          continue;
        }
        break;
      }
      continue;
    }
    if (wrapper === 'command') {
      index += 1;
      let availabilityQuery = false;
      while ((tokens[index] ?? '').startsWith('-')) {
        const option = tokens[index] ?? '';
        index += 1;
        if (option === '--') break;
        if (/^-[^-]*[vV]/.test(option)) availabilityQuery = true;
      }
      if (availabilityQuery) return [];
      continue;
    }
    break;
  }

  return tokens.slice(index);
}

function containsPrivilegedCommand(source: string): boolean {
  const privilegedCommands = new Set([
    'sudo',
    'doas',
    'pkexec',
    'systemctl',
    'service',
    'mount',
    'umount',
    'reboot',
    'shutdown',
    'poweroff',
    'halt',
    'chown',
    'chmod',
    'chroot',
    'useradd',
    'usermod',
    'groupadd',
    'visudo',
    'apt',
    'apt-get',
    'apt-cache',
    'dpkg',
    'yum',
    'dnf',
    'rpm',
    'apk',
    'pacman',
    'zypper',
    'emerge',
    'snap',
    'flatpak',
    'brew',
    'nix-env',
  ]);

  return shellCommandSegments(source).some((segment): boolean => {
    const tokens = normalizedCommandTokens(segment);
    const command = commandBasename(tokens[0] ?? '');
    if (privilegedCommands.has(command)) return true;
    if (command !== 'su') return false;

    let index = 1;
    while (index < tokens.length) {
      const token = tokens[index] ?? '';
      if (token === '--') {
        index += 1;
        break;
      }
      if (
        /^(?:--command|--session-command|--group|--supp-group|--shell|--whitelist-environment)$/.test(
          token,
        )
      ) {
        index += 2;
        continue;
      }
      if (
        /^(?:--command=|--session-command=|--group=|--supp-group=|--shell=|--whitelist-environment=)/.test(
          token,
        )
      ) {
        index += 1;
        continue;
      }
      if (/^-[^-]/.test(token)) {
        const options = token.slice(1);
        let consumed = false;
        for (let optionIndex = 0; optionIndex < options.length; optionIndex += 1) {
          const option = options[optionIndex] ?? '';
          if ('cgGsw'.includes(option)) {
            index += options.slice(optionIndex + 1) === '' ? 2 : 1;
            consumed = true;
            break;
          }
        }
        if (!consumed) index += 1;
        continue;
      }
      if (token.startsWith('-')) {
        index += 1;
        continue;
      }
      break;
    }
    const user = tokens[index];
    return user === undefined || user === 'root';
  });
}

function exampleSafetyViolationKinds(source: string): string[] {
  const kinds = new Set<string>();
  const sensitiveKey = /(?:secret|token|password|credential|MOSAIC_AGENT_COMMAND)/i;
  const credentialFormat =
    /(?:\bAKIA[0-9A-Z]{16}\b|\bAIza[0-9A-Za-z_-]{35}\b|\bgh[pousr]_[A-Za-z0-9]{20,}\b|\bgithub_pat_[A-Za-z0-9_]{20,}\b|\bglpat-[A-Za-z0-9_-]{20,}\b|\bnpm_[A-Za-z0-9]{20,}\b|\bsk-ant-(?:api\d{2}-)?[A-Za-z0-9_-]{20,}\b|\bsk-proj-[A-Za-z0-9_-]{20,}\b|\b(?:sk|rk)_(?:live|test)_[A-Za-z0-9]{16,}\b|\bxox[baprs]-[A-Za-z0-9-]{10,}\b|\bBearer\s+[A-Za-z0-9._~+/=-]{16,}\b|\beyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}\b|-----BEGIN [A-Z ]*PRIVATE KEY-----|\b[A-Za-z][A-Za-z0-9+.-]*:\/\/[^\s/:]+:[^\s/@]+@)/;

  if (sensitiveKey.test(source)) kinds.add('sensitive-key');
  if (credentialFormat.test(source)) kinds.add('credential-format');
  if (containsPrivilegedCommand(source)) kinds.add('privileged-command');
  if (/\b(?:Tess|Ultron)\b/.test(source)) kinds.add('identity');
  return [...kinds].sort();
}

function fencedCodeBlocks(source: string): string[] {
  const blocks: string[] = [];
  let fence: { readonly marker: string; readonly length: number } | undefined;
  let lines: string[] = [];

  for (const line of source.split('\n')) {
    const openingRun = line.match(/^\s{0,3}(`{3,}|~{3,})[^\n]*$/)?.[1];
    if (fence === undefined && openingRun !== undefined) {
      fence = { marker: openingRun[0] ?? '', length: openingRun.length };
      lines = [];
      continue;
    }
    if (fence === undefined) continue;

    const closingRun = line.match(/^\s{0,3}(`{3,}|~{3,})\s*$/)?.[1];
    if (
      closingRun !== undefined &&
      closingRun[0] === fence.marker &&
      closingRun.length >= fence.length
    ) {
      blocks.push(lines.join('\n'));
      fence = undefined;
      lines = [];
      continue;
    }
    lines.push(line);
  }

  if (fence !== undefined) blocks.push(lines.join('\n'));
  return blocks;
}

const UNSAFE_EXAMPLE_FIXTURES = [
  {
    expected: 'privileged-command',
    source: ['cd /srv && su', 'do systemctl restart example'].join(''),
  },
  { expected: 'privileged-command', source: '/usr/bin/sudo systemctl restart example' },
  { expected: 'privileged-command', source: '/usr/bin/apt-get install example' },
  {
    expected: 'privileged-command',
    source: '/usr/bin/env -i /usr/bin/command -- /usr/bin/apt-get install example',
  },
  {
    expected: 'privileged-command',
    source: '/usr/bin/env -u FOO /usr/bin/apt-get install example',
  },
  {
    expected: 'privileged-command',
    source: 'env -iu FOO /usr/bin/apt-get --version',
  },
  {
    expected: 'privileged-command',
    source: 'env -ivS/usr/bin/apt-get --version',
  },
  {
    expected: 'privileged-command',
    source: 'env --unset FOO /usr/bin/apt-get install example',
  },
  { expected: 'privileged-command', source: 'env -S apt-get install example' },
  { expected: 'privileged-command', source: "env -S 'apt-get update'" },
  { expected: 'privileged-command', source: "env -S'/usr/bin/apt-get --version'" },
  {
    expected: 'privileged-command',
    source: "env --split-string='apt-get update'",
  },
  {
    expected: 'privileged-command',
    source: "env --split-string='-i /usr/bin/apt-get update'",
  },
  {
    expected: 'privileged-command',
    source: "env --split-string='FOO=x /usr/bin/apt-get update'",
  },
  {
    expected: 'privileged-command',
    source: "env --split-string='-- /usr/bin/apt-get update'",
  },
  { expected: 'privileged-command', source: 'reboot' },
  { expected: 'privileged-command', source: 'su --command=/bin/sh' },
  { expected: 'privileged-command', source: 'su -lc /usr/bin/id' },
  { expected: 'privileged-command', source: 'su -l root' },
  { expected: 'privileged-command', source: 'su -l -s /bin/sh root' },
  { expected: 'privileged-command', source: '/usr/bin/su --login root' },
  { expected: 'privileged-command', source: 'su root' },
  { expected: 'privileged-command', source: '/usr/sbin/chroot /srv/example' },
  { expected: 'credential-format', source: ['ghp_', 'a'.repeat(36)].join('') },
  {
    expected: 'credential-format',
    source: ['sk-ant-api03-', 'a'.repeat(80)].join(''),
  },
  {
    expected: 'credential-format',
    source: ['sk-proj-', 'a'.repeat(80)].join(''),
  },
  {
    expected: 'credential-format',
    source: ['rk_live_', 'a'.repeat(24)].join(''),
  },
  {
    expected: 'credential-format',
    source: ['eyJ', 'a'.repeat(12), '.', 'b'.repeat(12), '.', 'c'.repeat(12)].join(''),
  },
] as const;

describe('documentation validation regressions', (): void => {
  it('rejects a local Markdown link whose heading fragment does not exist', (): void => {
    expect(
      markdownLinkViolations('docs/fleet/source.md', '[broken](target.md#missing)', {
        'docs/fleet/target.md': '# Present',
      }),
    ).toEqual(['docs/fleet/source.md -> target.md#missing: missing heading']);
  });

  it('accepts balanced-parenthesis link destinations and visible-text heading anchors', (): void => {
    expect(localMarkdownTargets('[guide](guide-(legacy).md#setup "Guide")')).toEqual([
      'guide-(legacy).md#setup',
    ]);
    expect(markdownHeadingAnchors('# [Fleet API](cli.md) behavior')).toContain(
      'fleet-api-behavior',
    );
  });

  it('keeps longer fenced blocks closed only by an equal-or-longer fence', (): void => {
    expect(markdownHeadingAnchors('````markdown\n```\n# Not a heading\n````\n# Present')).toEqual(
      new Set(['present']),
    );
  });

  it('assigns a free suffix when a prior heading already occupies the next duplicate anchor', (): void => {
    expect(markdownHeadingAnchors('# Foo\n# Foo-1\n# Foo')).toEqual(
      new Set(['foo', 'foo-1', 'foo-2']),
    );
  });

  it('allows command availability queries without classifying the queried command', (): void => {
    expect(exampleSafetyViolationKinds('command -v apt-get')).not.toContain('privileged-command');
  });

  it('keeps quoted command separators as inert argument data', (): void => {
    expect(
      exampleSafetyViolationKinds("printf '%s\\n' 'safe; /usr/bin/apt-get update'"),
    ).not.toContain('privileged-command');
  });

  it('still detects commands after unquoted command separators', (): void => {
    expect(exampleSafetyViolationKinds('printf safe; /usr/bin/apt-get update')).toContain(
      'privileged-command',
    );
  });

  it.each([
    "env --split-string='-i -- /usr/bin/printf safe'",
    "env --split-string='FOO=x /usr/bin/printf safe'",
    'env -iu FOO /usr/bin/printf safe',
    'env -ivS/usr/bin/printf safe',
    'su -lc /usr/bin/id operator',
    'su -l -s /bin/sh operator',
    'su -s /bin/sh -- operator',
    'su -c /usr/bin/id operator',
    'su --command=/usr/bin/id operator',
    'su --session-command=/usr/bin/id operator',
  ])('keeps valid non-privileged env and su forms safe', (source): void => {
    expect(exampleSafetyViolationKinds(source)).not.toContain('privileged-command');
  });

  it.each(UNSAFE_EXAMPLE_FIXTURES)(
    'classifies unsafe example fixture as $expected',
    ({ expected, source }): void => {
      expect(exampleSafetyViolationKinds(source)).toContain(expected);
    },
  );

  it('extracts tilde-fenced and unclosed examples without exposing their contents', (): void => {
    const sensitiveFixture = ['sk-ant-api03-', 'a'.repeat(80)].join('');
    const blocks = fencedCodeBlocks(
      `~~~sh\n${sensitiveFixture}\n~~~\n\n\`\`\`sh\n${sensitiveFixture}`,
    );

    expect(blocks).toHaveLength(2);
    for (const block of blocks) {
      const kinds = exampleSafetyViolationKinds(block);
      expect(kinds).toContain('credential-format');
      expect(JSON.stringify(kinds)).not.toContain(sensitiveFixture);
    }
  });
});

describe('fleet operator documentation', (): void => {
  it('ships every accepted information-architecture page', async (): Promise<void> => {
    await expect(
      Promise.all(REQUIRED_FLEET_PAGES.map((path) => readFile(join(fleetDocs, path), 'utf8'))),
    ).resolves.toHaveLength(REQUIRED_FLEET_PAGES.length);
  });

  it('resolves every local Markdown link and heading fragment in the fleet book and sitemap', async (): Promise<void> => {
    const files = [...(await markdownFiles(fleetDocs)), join(repositoryRoot, 'docs', 'SITEMAP.md')];
    const documents: Record<string, string> = {};
    for (const file of files) {
      const relative = file.slice(repositoryRoot.length + 1);
      documents[relative] = await readFile(file, 'utf8');
    }

    const violations: string[] = [];
    for (const [sourcePath, source] of Object.entries(documents)) {
      for (const target of localMarkdownTargets(source)) {
        const encodedPath = target.split('#', 1)[0] ?? '';
        const targetPath = resolve(
          dirname(join(repositoryRoot, sourcePath)),
          decodeURIComponent(encodedPath),
        );
        const relativeTarget = targetPath.slice(repositoryRoot.length + 1);
        if (documents[relativeTarget] === undefined) {
          try {
            documents[relativeTarget] = await readFile(targetPath, 'utf8');
          } catch {
            // The deterministic validator below records the missing target without exposing content.
          }
        }
      }
      violations.push(...markdownLinkViolations(sourcePath, source, documents));
    }
    expect(violations).toEqual([]);
  });

  it('validates the canonical documentation example through the production compiler and resolver', async (): Promise<void> => {
    const source = await readFile(join(fleetDocs, 'examples', 'roster-v2.yaml'), 'utf8');
    const roster = parseRosterV2(source, 'yaml');
    const validated = await validateRosterV2Semantics(roster, {
      rolesDir: join(frameworkFleet, 'roles'),
      overrideDir: join(fleetDocs, 'examples', 'roles.local'),
    });

    expect(validated.generation).toBe(1);
    expect(validated.agents.map((agent) => agent.canonicalClass)).toEqual([
      'code',
      'interaction',
      'validator',
    ]);
  });

  it('keeps every fenced fleet example free of sensitive values, privileged commands, arbitrary command overrides, and product-hardcoded identities', async (): Promise<void> => {
    const violations: string[] = [];
    for (const file of await markdownFiles(fleetDocs)) {
      const source = await readFile(file, 'utf8');
      for (const [index, block] of fencedCodeBlocks(source).entries()) {
        for (const kind of exampleSafetyViolationKinds(block)) {
          violations.push(`${file.slice(repositoryRoot.length + 1)}#block-${index + 1}: ${kind}`);
        }
      }
    }

    const rosterSource = await readFile(join(fleetDocs, 'examples', 'roster-v2.yaml'), 'utf8');
    for (const kind of exampleSafetyViolationKinds(rosterSource)) {
      violations.push(`docs/fleet/examples/roster-v2.yaml: ${kind}`);
    }
    expect(violations).toEqual([]);
  });
});