feat(rag): git-based import sources — BOR_GIT_SOURCES repos cloned (first run, --depth 1) or pulled (--ff-only) into BOR_SOURCES_DIR/<repo>/ then indexed; --source still wins; a failed sync aborts before importing anything

2026-08-25 14:23:02 -04:00
parent 589e26dbe9
commit 3d044f33a1
12 changed files with 828 additions and 16 deletions
@@ -92,6 +92,53 @@ def test_import_extensions_rejects_empty(monkeypatch) -> None:
        _settings()


+def test_git_sources_default_empty_and_sources_dir_default() -> None:
+    """Phase 28: no git sources by default (backwards-compatible with the
+    ``--source`` / ``DEFAULT_SOURCES`` fallback); the clone location stays
+    a raw string (``~`` is expanded by the import script, not the setting)."""
+    s = _settings()
+    assert s.git_sources == ""
+    assert s.git_source_list == []
+    assert s.sources_dir == "~/bor-sources"
+
+
+def test_git_sources_env_override_parses_comma_separated_list(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """``BOR_GIT_SOURCES`` is a raw CSV: entries are trimmed and empty
+    entries dropped; URLs are stored untouched (no scheme parsing here)."""
+    monkeypatch.setenv(
+        "BOR_GIT_SOURCES",
+        "https://github.com/user/homelab.git, "
+        " git@github.com:user/deployments.git ,,  https://git.reeseapps.com/x/y.git ",
+    )
+    s = _settings()
+    # The raw CSV string is preserved untouched (no parsing in the setting).
+    assert s.git_sources == (
+        "https://github.com/user/homelab.git, "
+        " git@github.com:user/deployments.git ,,  https://git.reeseapps.com/x/y.git "
+    )
+    assert s.git_source_list == [
+        "https://github.com/user/homelab.git",
+        "git@github.com:user/deployments.git",
+        "https://git.reeseapps.com/x/y.git",
+    ]
+
+
+def test_git_sources_whitespace_only_yields_empty_list(monkeypatch) -> None:
+    """A configured-but-blank value behaves the same as unset: no git
+    sources, so the script falls back to its legacy local defaults."""
+    monkeypatch.setenv("BOR_GIT_SOURCES", "  , , ")
+    s = _settings()
+    assert s.git_source_list == []
+
+
+def test_sources_dir_env_override_is_raw_string(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("BOR_SOURCES_DIR", "/data/bor/sources")
+    s = _settings()
+    assert s.sources_dir == "/data/bor/sources"
+
+
 def test_suggestions_default_is_three_plus_real_questions() -> None:
    s = _settings()
    assert len(s.suggestions) >= 3
@@ -0,0 +1,153 @@
+"""Unit tests: git clone/pull utility (phase 28).
+
+``clone_or_pull`` dispatches to ``git clone --depth 1`` (fresh dest) or
+``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,
+) -> list[dict[str, object]]:
+    """Monkeypatch scripts.git_sync.subprocess.run; record each call."""
+    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")
+        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 --depth 1`` 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", "--depth", "1", 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:
+    """Subsequent run: dest/.git present → ``git pull --ff-only`` in-place."""
+    dest = tmp_path / "homelab"
+    (dest / ".git").mkdir(parents=True)
+    calls = _fake_run(monkeypatch)
+
+    result = clone_or_pull("https://github.com/user/homelab.git", dest)
+
+    assert result == dest
+    assert calls[0]["argv"] == ["git", "pull", "--ff-only"]
+    assert calls[0]["cwd"] == dest
+
+
+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()
+    _fake_run(monkeypatch)
+
+    clone_or_pull("https://github.com/user/homelab.git", dest)
+
+    assert dest.parent.is_dir()
+
+
+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",
+        "--depth",
+        "1",
+        "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 --depth 1 .* 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).
+    (dest / ".git").mkdir(parents=True)
+    _fake_run(monkeypatch, returncode=1, stderr="error: cannot pull with rebase")
+
+    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_captures_and_returns_stdout(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    """_run 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", "status"], cwd=tmp_path) == "From example.com\n + abc..def main"
+    assert len(calls) == 1