US09-02: Write the Installation and Operations Manual (#108)

tests/integration/test_installation_manual.py

@@ -0,0 +1,178 @@
+"""US09-02: the installation manual, checked against the thing it describes.
+
+Documentation rots quietly. A setting is renamed, a command grows a flag, an exit
+code changes meaning — and the manual keeps confidently saying the old thing until
+somebody follows it into a bad afternoon. So every fact in it that the code also
+knows is compared with the code, in both directions where both directions are
+meaningful: a setting the manual invents fails, and a setting the manual forgot
+fails too.
+"""
+
+from __future__ import annotations
+
+import re
+import subprocess
+import sys
+from functools import lru_cache
+from pathlib import Path
+
+from photo_pipeline.config import ENV_PREFIX, LEGACY_ALIASES, Config
+
+REPO = Path(__file__).resolve().parents[2]
+MANUAL = REPO / "docs" / "installation.md"
+MAIN = REPO / "photo_pipeline" / "__main__.py"
+
+TEXT = MANUAL.read_text()
+ENV_NAMES = re.compile(rf"{ENV_PREFIX}[A-Z0-9_]+")
+
+# Read by docker-compose.yml, not by Config. They are configuration an installer sets,
+# so the manual documents them; they are simply not application settings.
+COMPOSITION_ONLY = {
+    f"{ENV_PREFIX}IMAGE",
+    f"{ENV_PREFIX}LIBRARY_HOST_PATH",
+    f"{ENV_PREFIX}PUBLISH_ADDRESS",
+    f"{ENV_PREFIX}UID",
+    f"{ENV_PREFIX}GID",
+    f"{ENV_PREFIX}ENV_FILE",  # read before Config exists, so it is not a field
+}
+
+
+def documented_env_names() -> set[str]:
+    return set(ENV_NAMES.findall(TEXT))
+
+
+@lru_cache
+def cli_help(*args: str) -> str:
+    """What the CLI says about itself, asked the way an operator asks."""
+    result = subprocess.run(
+        [sys.executable, "-m", "photo_pipeline", *args, "--help"],
+        cwd=REPO,
+        capture_output=True,
+        text=True,
+        timeout=120,
+        check=False,
+    )
+    assert result.returncode == 0, result.stderr
+    return result.stdout
+
+
+@lru_cache
+def cli_commands() -> frozenset[str]:
+    listed = re.search(r"\{([a-z0-9,\-]+)\}", cli_help())
+    assert listed, f"the CLI listed no subcommands:\n{cli_help()}"
+    return frozenset(listed.group(1).split(","))
+
+
+def cli_flags(command: str) -> frozenset[str]:
+    return frozenset(re.findall(r"--[a-z][a-z-]+", cli_help(command)))
+
+
+# ── settings ─────────────────────────────────────────────────────────────────
+
+
+def test_every_setting_is_documented():
+    """A setting nobody documents is a setting nobody configures deliberately."""
+    expected = {f"{ENV_PREFIX}{field.upper()}" for field in Config.model_fields}
+    missing = sorted(expected - documented_env_names())
+    assert missing == [], f"undocumented settings: {missing}"
+
+
+def test_the_manual_invents_no_settings():
+    unknown = sorted(
+        name
+        for name in documented_env_names()
+        if name.removeprefix(ENV_PREFIX).lower() not in Config.model_fields
+        and name not in COMPOSITION_ONLY
+    )
+    assert unknown == [], f"documented but not a real setting: {unknown}"
+
+
+def test_the_documented_defaults_are_the_real_defaults():
+    """Spot-checked where a wrong default is actively dangerous: the bind address,
+    the trust boundary, and the gate that protects an irreplaceable library."""
+    assert Config.model_fields["host"].default == "127.0.0.1"
+    assert "`PHOTO_PIPELINE_HOST` | `127.0.0.1`" in TEXT
+    assert Config.model_fields["allowed_hosts"].default == ()
+    assert Config.model_fields["require_dry_run_approval"].default is False
+    assert "`PHOTO_PIPELINE_REQUIRE_DRY_RUN_APPROVAL` | `false`" in TEXT
+
+
+def test_every_secret_is_marked_as_one():
+    for field in ("access_secret", "vision_api_key", "immich_api_key"):
+        name = f"{ENV_PREFIX}{field.upper()}"
+        row = next(line for line in TEXT.splitlines() if line.startswith(f"| `{name}`"))
+        assert "secret" in row.lower(), f"{name} is not marked as a secret"
+
+
+def test_the_legacy_aliases_are_documented():
+    """An operator with an existing photo_analyzer.env needs to know it still works."""
+    for alias in LEGACY_ALIASES:
+        assert alias in TEXT, f"legacy alias {alias} is undocumented"
+
+
+# ── commands ─────────────────────────────────────────────────────────────────
+
+
+# The manual is an installation and operations manual, not a command reference: these
+# are the commands an installer actually runs, and every one of them must exist.
+OPERATIONAL = ("migrate", "serve", "worker", "backup", "verify-backup", "restore", "diagnostics")
+
+
+def test_every_command_the_manual_tells_you_to_run_exists():
+    missing = [name for name in OPERATIONAL if name not in cli_commands()]
+    assert missing == [], f"the manual names commands the CLI does not have: {missing}"
+    undocumented = [name for name in OPERATIONAL if not re.search(rf"\b{re.escape(name)}\b", TEXT)]
+    assert undocumented == [], f"operational commands the manual omits: {undocumented}"
+
+
+def test_every_documented_flag_exists_on_the_command_it_is_shown_with():
+    for command, flag in (
+        ("backup", "--reason"),
+        ("backup", "--keep"),
+        ("restore", "--into"),
+        ("worker", "--allow-legacy"),
+        ("serve", "--allow-legacy"),
+    ):
+        assert flag in cli_flags(command), f"{command} has no {flag}"
+        assert flag in TEXT, f"{flag} is undocumented"
+
+
+# ── exit codes ───────────────────────────────────────────────────────────────
+
+
+def test_every_documented_exit_code_is_one_the_cli_can_return():
+    documented = {int(code) for code in re.findall(r"^\| `(\d)` \|", TEXT, re.MULTILINE)}
+    returned = {int(code) for code in re.findall(r"^\s+return (\d)$", MAIN.read_text(), re.MULTILINE)}
+    assert documented, "no exit codes are documented"
+    assert documented <= returned | {0}, f"documented but unreachable: {sorted(documented - returned)}"
+
+
+def test_every_refusal_exit_code_is_documented():
+    """0 is success and 1 is 'it said why'; every other code is a specific refusal an
+    operator will meet at startup, and meeting an undocumented one is the worst case."""
+    returned = {int(code) for code in re.findall(r"^\s+return (\d)$", MAIN.read_text(), re.MULTILINE)}
+    documented = {int(code) for code in re.findall(r"^\| `(\d)` \|", TEXT, re.MULTILINE)}
+    missing = sorted(code for code in returned if code not in documented and code != 0)
+    assert missing == [], f"undocumented exit codes: {missing}"
+
+
+# ── the promises the manual makes ────────────────────────────────────────────
+
+
+def test_the_manual_carries_no_credential_shaped_example():
+    """The repository's own scanner refuses these in a commit; a manual is exactly
+    where a real-looking one gets copied from."""
+    suspicious = re.findall(
+        r"(?i)(api[_-]?key|secret|token|password)\s*[=:]\s*[\"']?([A-Za-z0-9_\-]{12,})",
+        TEXT,
+    )
+    assert suspicious == [], f"credential-shaped example: {suspicious}"
+
+
+def test_the_manual_states_the_invariants_an_installer_must_not_break():
+    for invariant in ("_IGNORE/", "One writer", "EXIF is verified before upload"):
+        assert invariant in TEXT, f"the manual does not state: {invariant}"
+
+
+def test_the_manual_is_reachable_from_the_index():
+    assert "installation.md" in (REPO / "docs" / "index.md").read_text()