brain-of-reese/tests/unit/test_git_sync.py

"""Unit tests: git clone/pull utility (phase 28; phase 107 D11/D12).

``clone_or_pull`` dispatches to ``git clone`` (full history, fresh dest)
or a shallow-probe + optional ``git fetch --unshallow`` +
``git pull --ff-only`` (existing checkout) with ``subprocess`` fully
mocked — the real git CLI is never invoked, so the tests run anywhere.
"""
from __future__ import annotations

import subprocess
from pathlib import Path

import pytest

import scripts.git_sync as git_sync
from scripts.git_sync import GitSyncError, clone_or_pull


class _FakeProc:
    def __init__(self, returncode: int = 0, stdout: str = "", stderr: str = "") -> None:
        self.returncode = returncode
        self.stdout = stdout
        self.stderr = stderr


def _fake_run(
    monkeypatch: pytest.MonkeyPatch,
    returncode: int = 0,
    stdout: str = "",
    stderr: str = "",
    missing_git: bool = False,
    responses: dict[tuple[str, ...], tuple[int, str, str]] | None = None,
) -> list[dict[str, object]]:
    """Monkeypatch scripts.git_sync.subprocess.run; record each call.

    ``responses`` dispatches by the full argv (clone / shallow-probe /
    ``fetch --unshallow`` / pull) — a per-command
    ``(returncode, stdout, stderr)``; any argv not in the map gets the
    default ``returncode``/``stdout``/``stderr``.
    """
    calls: list[dict[str, object]] = []

    def fake_run(argv: list[str], cwd: Path | None = None, **kwargs: object) -> _FakeProc:
        calls.append({"argv": list(argv), "cwd": cwd, **kwargs})
        if missing_git:
            raise FileNotFoundError("git")
        if responses is not None:
            rc, out, err = responses.get(tuple(argv), (returncode, stdout, stderr))
            return _FakeProc(rc, out, err)
        return _FakeProc(returncode, stdout, stderr)

    monkeypatch.setattr(subprocess, "run", fake_run)
    return calls


def test_clone_or_pull_clones_when_dest_has_no_git_dir(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """First run: dest absent → ``git clone`` (full history — NO
    ``--depth``, phase 107 D11) from the parent dir."""
    url = "https://github.com/user/homelab.git"
    dest = tmp_path / "homelab"
    calls = _fake_run(monkeypatch)

    result = clone_or_pull(url, dest)

    assert result == dest
    assert len(calls) == 1
    call = calls[0]
    assert call["argv"] == ["git", "clone", url, str(dest)]
    assert call["cwd"] == dest.parent
    assert call["capture_output"] is True
    assert call["text"] is True


def test_clone_or_pull_pulls_when_git_dir_exists(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Steady state: dest/.git present and the probe says NOT shallow
    (``false``) → straight to ``git pull --ff-only`` in-place (one cheap
    local probe, no network fetch)."""
    dest = tmp_path / "homelab"
    (dest / ".git").mkdir(parents=True)
    calls = _fake_run(
        monkeypatch,
        responses={("git", "rev-parse", "--is-shallow-repository"): (0, "false\n", "")},
    )

    result = clone_or_pull("https://github.com/user/homelab.git", dest)

    assert result == dest
    assert len(calls) == 2
    assert calls[0]["argv"] == ["git", "rev-parse", "--is-shallow-repository"]
    assert calls[0]["cwd"] == dest
    assert calls[1]["argv"] == ["git", "pull", "--ff-only"]
    assert calls[1]["cwd"] == dest


def test_clone_or_pull_unshallows_existing_shallow_checkout(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Existing shallow checkout (probe ``true`` — the one-time D11
    self-heal of deployed checkouts) → ``git fetch --unshallow``
    BEFORE the usual ``git pull --ff-only`` (order pinned), all in
    dest."""
    dest = tmp_path / "homelab"
    (dest / ".git").mkdir(parents=True)
    calls = _fake_run(
        monkeypatch,
        responses={
            ("git", "rev-parse", "--is-shallow-repository"): (0, "true\n", ""),
            ("git", "fetch", "--unshallow"): (0, "Fetching full history\n", ""),
        },
    )

    clone_or_pull("https://github.com/user/homelab.git", dest)

    assert len(calls) == 3
    assert calls[0]["argv"] == ["git", "rev-parse", "--is-shallow-repository"]
    assert calls[1]["argv"] == ["git", "fetch", "--unshallow"]
    assert calls[2]["argv"] == ["git", "pull", "--ff-only"]
    for call in calls:
        assert call["cwd"] == dest


def test_clone_or_pull_unshallow_failure_propagates(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """D12 fail-loud: a failed ``git fetch --unshallow`` raises
    :class:`GitSyncError` (with git's stderr) and the pull NEVER runs —
    continuing a failed self-heal would silently re-serve the uniform
    tip date (the bug D11 fixes)."""
    dest = tmp_path / "homelab"
    (dest / ".git").mkdir(parents=True)
    calls = _fake_run(
        monkeypatch,
        responses={
            ("git", "rev-parse", "--is-shallow-repository"): (0, "true\n", ""),
            ("git", "fetch", "--unshallow"): (128, "", "fatal: could not fetch\n"),
        },
    )

    with pytest.raises(
        GitSyncError, match=r"git fetch --unshallow failed \(exit 128\): fatal: could not fetch"
    ):
        clone_or_pull("https://github.com/user/homelab.git", dest)

    assert [call["argv"] for call in calls] == [
        ["git", "rev-parse", "--is-shallow-repository"],
        ["git", "fetch", "--unshallow"],
    ]  # the pull never ran


def test_clone_or_pull_creates_missing_parent_before_clone(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """The (nested) parent of the destination is mkdir'd before git runs."""
    dest = tmp_path / "nested" / "deeper" / "homelab"
    assert not dest.parent.exists()
    calls = _fake_run(monkeypatch)

    clone_or_pull("https://github.com/user/homelab.git", dest)

    assert dest.parent.is_dir()
    assert calls[0]["argv"] == [
        "git",
        "clone",
        "https://github.com/user/homelab.git",
        str(dest),
    ]


def test_existing_dir_without_git_dir_is_treated_as_fresh(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """A leftover non-repo dir at the dest still takes the clone path —
    git fails loudly (non-zero exit) if the dir is not empty."""
    dest = tmp_path / "homelab"
    dest.mkdir()
    calls = _fake_run(monkeypatch)

    clone_or_pull("https://github.com/user/homelab.git", dest)

    assert calls[0]["argv"] == [
        "git",
        "clone",
        "https://github.com/user/homelab.git",
        str(dest),
    ]


def test_failing_git_raises_error_carrying_stderr(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """Non-zero exit → GitSyncError naming the subcommand, exit code, stderr."""
    dest = tmp_path / "homelab"
    _fake_run(monkeypatch, returncode=128, stderr="fatal: repository not found\n")

    with pytest.raises(
        GitSyncError,
        match=r"git clone .* failed \(exit 128\): fatal: repository not found",
    ):
        clone_or_pull("https://example.com/nope.git", dest)

    # Same for the pull path (broken checkout, e.g. diverged history) —
    # the probe answers "false" (not shallow) so the pull runs.
    (dest / ".git").mkdir(parents=True)
    _fake_run(
        monkeypatch,
        returncode=1,
        stderr="error: cannot pull with rebase",
        responses={("git", "rev-parse", "--is-shallow-repository"): (0, "false\n", "")},
    )

    with pytest.raises(
        GitSyncError, match=r"git pull --ff-only failed \(exit 1\): error: cannot pull with rebase"
    ):
        clone_or_pull("https://example.com/homelab.git", dest)


def test_missing_git_raises_named_error(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """No git binary on PATH → GitSyncError telling the user to install it."""
    _fake_run(monkeypatch, missing_git=True)

    with pytest.raises(GitSyncError, match="git was not found on PATH"):
        clone_or_pull("https://example.com/homelab.git", tmp_path / "homelab")


def test_run_git_captures_and_returns_stdout(
    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
) -> None:
    """run_git returns the captured stdout on success (git output is not lost)."""
    calls = _fake_run(monkeypatch, stdout="From example.com\n + abc..def main")

    assert git_sync.run_git(["git", "status"], cwd=tmp_path) == "From example.com\n + abc..def main"
    assert len(calls) == 1