docmost-sync/test/git.test.ts

import { execFile } from 'node:child_process';
import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { promisify } from 'node:util';
import { afterEach, beforeAll, describe, expect, it } from 'vitest';
import {
  VaultGit,
  BOT_AUTHOR_NAME,
  BOT_AUTHOR_EMAIL,
  buildCommitMessage,
} from '../src/git.js';

const execFileAsync = promisify(execFile);

/** True if a usable `git` binary is on PATH (skip the suite otherwise). */
async function gitAvailable(): Promise<boolean> {
  try {
    await execFileAsync('git', ['--version']);
    return true;
  } catch {
    return false;
  }
}

/** Read the full commit message of HEAD (subject + body) in a repo dir. */
async function headMessage(dir: string): Promise<string> {
  const { stdout } = await execFileAsync(
    'git',
    ['--no-pager', 'log', '-1', '--pretty=%B'],
    { cwd: dir },
  );
  return stdout.trim();
}

/** Read the author "Name <email>" of HEAD in a repo dir. */
async function headAuthor(dir: string): Promise<string> {
  const { stdout } = await execFileAsync(
    'git',
    ['--no-pager', 'log', '-1', '--pretty=%an <%ae>'],
    { cwd: dir },
  );
  return stdout.trim();
}

describe('buildCommitMessage (pure)', () => {
  it('returns the bare subject when there are no trailers', () => {
    expect(buildCommitMessage('subject')).toBe('subject');
    expect(buildCommitMessage('subject', [])).toBe('subject');
  });

  it('appends trailers separated from the subject by a blank line', () => {
    expect(buildCommitMessage('subject', ['Docmost-Sync-Source: docmost'])).toBe(
      'subject\n\nDocmost-Sync-Source: docmost',
    );
  });
});

describe('VaultGit (integration; temp repo)', () => {
  let available = false;
  let dir: string;

  beforeAll(async () => {
    available = await gitAvailable();
  });

  afterEach(async () => {
    if (dir) {
      await rm(dir, { recursive: true, force: true });
    }
  });

  /** Make a fresh temp dir for one test (under the OS tmpdir, NOT the repo). */
  async function freshDir(): Promise<string> {
    dir = await mkdtemp(join(tmpdir(), 'docmost-vault-'));
    return dir;
  }

  it('ensureRepo creates .git + main + an initial commit', async () => {
    if (!available) return; // skip gracefully when git is unavailable
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    // It is a git work-tree now.
    const { stdout: insideWt } = await execFileAsync(
      'git',
      ['rev-parse', '--is-inside-work-tree'],
      { cwd: vault },
    );
    expect(insideWt.trim()).toBe('true');

    // On `main`.
    expect(await git.currentBranch()).toBe('main');

    // Has the initial commit.
    expect(await headMessage(vault)).toBe('init vault');

    // Idempotent: calling again does not create a second commit.
    await git.ensureRepo();
    const { stdout: count } = await execFileAsync(
      'git',
      ['rev-list', '--count', 'HEAD'],
      { cwd: vault },
    );
    expect(count.trim()).toBe('1');
  });

  it('ensureRepo neutralizes correctness-affecting LOCAL config', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    // These LOCAL values neutralize a hostile GLOBAL/system config that would
    // otherwise change porcelain BEHAVIOR and corrupt the vault (SPEC §11 for
    // core.autocrlf; gpgsign/safecrlf for the headless daemon).
    const localConfig = async (key: string): Promise<string> => {
      const { stdout } = await execFileAsync(
        'git',
        ['config', '--local', '--get', key],
        { cwd: vault },
      );
      return stdout.trim();
    };
    expect(await localConfig('core.autocrlf')).toBe('false');
    expect(await localConfig('commit.gpgsign')).toBe('false');
    expect(await localConfig('core.safecrlf')).toBe('false');
    expect(await localConfig('core.attributesFile')).toBe('/dev/null');

    // Idempotent: a second run leaves the same single values (no duplicates).
    await git.ensureRepo();
    expect(await localConfig('core.autocrlf')).toBe('false');
    expect(await localConfig('commit.gpgsign')).toBe('false');
    expect(await localConfig('core.safecrlf')).toBe('false');
  });

  it('preserves LF bytes verbatim on commit (SPEC §11: autocrlf=false)', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    // Write content with explicit LF line endings. With a hostile
    // core.autocrlf=true git would translate these to CRLF in the stored blob,
    // breaking the byte-stable round-trip invariant. ensureRepo pins
    // core.autocrlf=false locally, so the stored bytes must round-trip exactly.
    const fileName = 'lf.md';
    const content = 'line1\nline2\nline3\n';
    await writeFile(join(vault, fileName), content, 'utf8');
    await git.stageAll();
    const made = await git.commit('add LF file', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
    });
    expect(made).toBe(true);

    // Read the STORED blob (not the worktree file) and assert verbatim bytes:
    // still LF-only, no CRLF translation.
    const { stdout: stored } = await execFileAsync(
      'git',
      ['--no-pager', 'show', `HEAD:${fileName}`],
      { cwd: vault, encoding: 'buffer' },
    );
    const storedBuf = stored as unknown as Buffer;
    expect(storedBuf.includes(Buffer.from('\r\n'))).toBe(false);
    expect(storedBuf.toString('utf8')).toBe(content);
  });

  it('ensureBranch creates the docmost branch from main', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    expect(await git.branchExists('docmost')).toBe(false);
    await git.ensureBranch('docmost', 'main');
    expect(await git.branchExists('docmost')).toBe(true);

    // Idempotent.
    await git.ensureBranch('docmost', 'main');
    expect(await git.branchExists('docmost')).toBe(true);
  });

  it('commit writes a commit with the provenance trailer and the bot identity', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    await writeFile(join(vault, 'page.md'), 'hello\n', 'utf8');
    await git.stageAll();
    const made = await git.commit('docmost: sync 1 page(s)', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
      trailers: ['Docmost-Sync-Source: docmost'],
    });
    expect(made).toBe(true);

    const msg = await headMessage(vault);
    expect(msg).toContain('docmost: sync 1 page(s)');
    expect(msg).toContain('Docmost-Sync-Source: docmost');

    const author = await headAuthor(vault);
    expect(author).toBe(`${BOT_AUTHOR_NAME} <${BOT_AUTHOR_EMAIL}>`);

    // The trailer is parseable by git itself.
    const { stdout: trailers } = await execFileAsync(
      'git',
      ['--no-pager', 'log', '-1', '--pretty=%(trailers:key=Docmost-Sync-Source,valueonly)'],
      { cwd: vault },
    );
    expect(trailers.trim()).toBe('docmost');
  });

  it('commit is a no-op when there is nothing to commit', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    await git.stageAll(); // nothing changed since the init commit
    const made = await git.commit('docmost: sync 0 page(s)', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
      trailers: ['Docmost-Sync-Source: docmost'],
    });
    expect(made).toBe(false);

    // Still exactly one commit (the init one).
    const { stdout: count } = await execFileAsync(
      'git',
      ['rev-list', '--count', 'HEAD'],
      { cwd: vault },
    );
    expect(count.trim()).toBe('1');
  });

  it('merge fast-forwards main to docmost', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();
    await git.ensureBranch('docmost', 'main');

    // Commit a file on docmost.
    await git.checkout('docmost');
    await writeFile(join(vault, 'a.md'), 'a\n', 'utf8');
    await git.stageAll();
    await git.commit('docmost: sync 1 page(s)', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
      trailers: ['Docmost-Sync-Source: docmost'],
    });

    // main has not diverged, so the merge is a clean fast-forward.
    await git.checkout('main');
    const res = await git.merge('docmost');
    expect(res.ok).toBe(true);
    expect(res.conflict).toBe(false);

    // main now contains the file and the docmost commit.
    const tracked = await git.listTrackedFiles();
    expect(tracked).toContain('a.md');
    expect(await headMessage(vault)).toContain('docmost: sync 1 page(s)');
  });

  it('merge surfaces a conflict distinctly (no auto-resolve)', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();
    await git.ensureBranch('docmost', 'main');

    // Divergent edits to the SAME file on both branches -> real conflict.
    await git.checkout('docmost');
    await writeFile(join(vault, 'c.md'), 'from docmost\n', 'utf8');
    await git.stageAll();
    await git.commit('docmost edit', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
    });

    await git.checkout('main');
    await writeFile(join(vault, 'c.md'), 'from main\n', 'utf8');
    await git.stageAll();
    await git.commit('main edit', {
      authorName: 'Human',
      authorEmail: 'human@local',
    });

    const res = await git.merge('docmost');
    expect(res.ok).toBe(false);
    expect(res.conflict).toBe(true);
  });

  it('isMergeInProgress is false on a clean repo and true mid-merge', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();
    await git.ensureBranch('docmost', 'main');

    // Clean repo, no merge in progress.
    expect(await git.isMergeInProgress()).toBe(false);

    // Create a REAL conflict: divergent edits to the same file on both branches.
    await git.checkout('docmost');
    await writeFile(join(vault, 'c.md'), 'from docmost\n', 'utf8');
    await git.stageAll();
    await git.commit('docmost edit', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
    });

    await git.checkout('main');
    await writeFile(join(vault, 'c.md'), 'from main\n', 'utf8');
    await git.stageAll();
    await git.commit('main edit', {
      authorName: 'Human',
      authorEmail: 'human@local',
    });

    // Merge conflicts -> the repo is now left mid-merge.
    const res = await git.merge('docmost');
    expect(res.conflict).toBe(true);
    expect(await git.isMergeInProgress()).toBe(true);

    // Aborting the merge clears the in-progress state again.
    await execFileAsync('git', ['--no-pager', 'merge', '--abort'], { cwd: vault });
    expect(await git.isMergeInProgress()).toBe(false);
  });

  it('listTrackedFiles supports a glob and returns forward-slash paths', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    await writeFile(join(vault, 'keep.md'), 'k\n', 'utf8');
    await writeFile(join(vault, 'note.txt'), 't\n', 'utf8');
    await git.stageAll();
    await git.commit('add files', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
    });

    const md = await git.listTrackedFiles('*.md');
    expect(md).toEqual(['keep.md']);
    const all = await git.listTrackedFiles();
    expect(new Set(all)).toEqual(new Set(['keep.md', 'note.txt']));
  });

  it('listTrackedFiles returns RAW UTF-8 Cyrillic paths (not octal-escaped/quoted)', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    await git.ensureRepo();

    // The target wiki is Russian, so file names contain Cyrillic. With git's
    // DEFAULT core.quotepath=true these come back as `"\320\232..."` from
    // ls-files; `listTrackedFiles` must return them verbatim as UTF-8.
    const topName = 'Колонка.md';
    const nestedDir = 'Раздел';
    const nestedName = 'Подстраница.md';
    await writeFile(join(vault, topName), 'top\n', 'utf8');
    await mkdir(join(vault, nestedDir), { recursive: true });
    await writeFile(join(vault, nestedDir, nestedName), 'nested\n', 'utf8');
    await git.stageAll();
    await git.commit('add cyrillic files', {
      authorName: BOT_AUTHOR_NAME,
      authorEmail: BOT_AUTHOR_EMAIL,
    });

    const md = await git.listTrackedFiles('*.md');
    // Exact UTF-8 names, forward-slash separated for the nested one — NOT an
    // escaped/quoted form like `"\320\232..."`.
    expect(new Set(md)).toEqual(
      new Set([topName, `${nestedDir}/${nestedName}`]),
    );
    // Guard explicitly against the quotepath regression: no entry is quoted or
    // contains a backslash escape sequence.
    for (const p of md) {
      expect(p.startsWith('"')).toBe(false);
      expect(p.includes('\\')).toBe(false);
    }

    // No-glob listing also returns the raw Cyrillic names.
    const all = await git.listTrackedFiles();
    expect(all).toContain(topName);
    expect(all).toContain(`${nestedDir}/${nestedName}`);
  });

  it('assertGitAvailable resolves when git is present', async () => {
    if (!available) return;
    const vault = await freshDir();
    const git = new VaultGit(vault);
    // No repo needed: it only probes `git --version` (and the vault dir need
    // not even exist yet).
    await expect(git.assertGitAvailable()).resolves.toBeUndefined();
  });
});