felhom-controller/controller/internal/backup/offbox_placement.go

package backup

import (
	"fmt"
	"io/fs"
	"os"
	"path/filepath"
	"strings"

	"gopkg.in/yaml.v3"
)

// R-351 — THE RESTORE ALREADY KNOWS WHERE THE APP LIVED. IT JUST NEVER LOOKED.
//
// Every recovery unit's manifest.json carries `drive` and `namespace_root` (recovery_unit.go:48-49),
// written at capture time from the app's own live placement. Measured on demo-hp 2026-08-21:
//
//	opengist      drive=/mnt/sys_drive             nsroot=/mnt/sys_drive/felhom-data
//	calibre-web   drive=/mnt/felhom-drives/hdd_1   nsroot=/mnt/felhom-drives/hdd_1
//
// Before this file, NO non-test code in the repository read either field back. `grep -rE
// '\.Drive\b|\.NamespaceRoot\b' --include=*.go` returned only the appbackup.NamespaceRoot FUNCTION
// and Tier2Target's unrelated field. The reconstitution opened the manifest
// (offbox_reconstitute.go:235) and took only the coherence stamp from it, then resolved its
// destination from the LIVE app instead. One side wrote the fact; the other never received it —
// the same shape as several defects closed this month.
//
// THE CONSEQUENCE THAT MADE THIS WORTH FIXING: a restore into a destination that differs from the
// one the backup recorded succeeded SILENTLY, under a green message. Nothing compared them.
//
// WHAT THIS IS NOT. It is not a lock. A domain can legitimately change and hardware can move, so a
// difference is NAMED and the customer decides — it is their own previous answer being shown back to
// them, not a rule imposed on them. What must never happen is the difference passing unremarked.

// RecordedPlacement is what a backup says about where an app's data lived when it was captured.
// Empty fields mean the manifest did not record them — an older unit, or one written before the
// field existed. That is an UNKNOWN and is never rendered as a value.
type RecordedPlacement struct {
	Drive         string // manifest.Drive — the in-guest mount (HDD_PATH), or the system data path
	NamespaceRoot string // manifest.NamespaceRoot — the resolved felhom-data namespace root
}

// Known reports whether the backup recorded a destination at all. A unit whose manifest predates the
// field, or could not be read, is NOT known — and "we cannot tell" is a different answer from "they
// match", which is why this is a method rather than a `!= ""` scattered over the callers.
func (p RecordedPlacement) Known() bool { return strings.TrimSpace(p.Drive) != "" }

// PlacementCheck is the verdict of comparing what the backup recorded against where the restore is
// actually about to write.
type PlacementCheck struct {
	// Recorded is what the backup said. Zero value when the manifest carried nothing.
	Recorded RecordedPlacement
	// LiveDrive / LiveNamespaceRoot are where this restore will write, resolved the way the
	// reconstitution resolves it today.
	LiveDrive         string
	LiveNamespaceRoot string
	// Known mirrors Recorded.Known(), carried on the verdict so a template never has to re-derive it.
	Known bool
	// Mismatch is true ONLY when the backup recorded a destination AND it differs from the live one.
	// An unknown recording is never a mismatch: refusing on an absence would block every pre-field
	// unit, and asserting a match we cannot see would be worse.
	Mismatch bool
}

// CheckPlacement compares a manifest's recorded placement against the live destination.
//
// Deliberately PURE and total: a nil manifest, an empty manifest and a manifest whose drive is blank
// all produce the same honest "not known, no mismatch" verdict. Paths are compared Cleaned, because
// `/mnt/x` and `/mnt/x/` are the same destination and a trailing slash must not manufacture a
// mismatch the customer then has to dismiss. Comparison is on the DRIVE, not the namespace root: the
// root is derived from the drive (namespaceRoot appends felhom-data only on the system-data
// fallback), so comparing both would report one difference twice.
func CheckPlacement(man *RecoveryManifest, liveDrive, liveNamespaceRoot string) PlacementCheck {
	c := PlacementCheck{
		LiveDrive:         strings.TrimSpace(liveDrive),
		LiveNamespaceRoot: strings.TrimSpace(liveNamespaceRoot),
	}
	if man != nil {
		c.Recorded = RecordedPlacement{
			Drive:         strings.TrimSpace(man.Drive),
			NamespaceRoot: strings.TrimSpace(man.NamespaceRoot),
		}
	}
	c.Known = c.Recorded.Known()
	if !c.Known || c.LiveDrive == "" {
		return c
	}
	c.Mismatch = filepath.Clean(c.Recorded.Drive) != filepath.Clean(c.LiveDrive)
	return c
}

// RecordedAddress is the web address the backup recorded for an app, read from the app.yaml the
// recovery unit captured beside its manifest.
//
// RECORDED, NEVER INFERRED. Both halves must come from the captured file. When the captured app.yaml
// carries no SUBDOMAIN, the LIVE deploy path falls back to the catalog's default
// (stacks/deploy.go:88-90) — that default is a catalog guess, not the customer's answer, and
// presenting it as "what your backup says" would be a fabricated fact. This project has ruled twice
// that a guess dressed as a fact is how these bugs are built, so an absent SUBDOMAIN is UNKNOWN here.
type RecordedAddress struct {
	Subdomain string
	Domain    string
}

// Known reports whether BOTH halves were recorded. A half-known address is not an address: showing
// „gist." or „.enkisfelhom.hu" as a prefill is worse than showing nothing.
func (a RecordedAddress) Known() bool {
	return strings.TrimSpace(a.Subdomain) != "" && strings.TrimSpace(a.Domain) != ""
}

// FQDN is the address as the customer knows it, or "" when it is not fully known.
func (a RecordedAddress) FQDN() string {
	if !a.Known() {
		return ""
	}
	return strings.TrimSpace(a.Subdomain) + "." + strings.TrimSpace(a.Domain)
}

// unitAppConfig is the slice of the captured app.yaml this package needs. Deliberately a LOCAL
// minimal struct rather than stacks.AppConfig: internal/stacks imports nothing from here today and
// reaching across for one map would couple the backup layer to the deploy layer's schema for no
// gain. Unknown keys are ignored by yaml.v3, so a richer app.yaml still parses.
type unitAppConfig struct {
	Env map[string]string `yaml:"env"`
}

// RecordedUnitForStack reads what an app's most readable recovery unit says about where it lived and
// what address it answered on. Returns ok=false when no unit can be read at all.
//
// SEARCH ORDER, and why it is not just "the app's own drive": the case this exists for is an app
// that is NOT INSTALLED on a rebuilt box, so GetStackHDDPath returns "" and there is no own drive to
// consult. It therefore checks every namespace root the box can currently see — the registered
// storage paths and the system data path — and takes the first unit it can read. That is a handful
// of stat calls on local disk: no network, no restic, no restore.
//
// A drive that is NOT attached contributes nothing, which is the honest outcome: we cannot read a
// unit that is not here, and the reconstitution's own refusal owns that case with a route.
func (m *Manager) RecordedUnitForStack(stack string) (RecordedPlacement, RecordedAddress, bool) {
	if !isSafeStackName(stack) {
		return RecordedPlacement{}, RecordedAddress{}, false
	}
	seen := map[string]bool{}
	var roots []string
	addRoot := func(drive string) {
		drive = strings.TrimSpace(drive)
		if drive == "" {
			return
		}
		r := m.namespaceRoot(drive)
		if r != "" && !seen[r] {
			seen[r] = true
			roots = append(roots, r)
		}
	}
	// The app's own drive first when it HAS one — that unit is the authoritative one for an
	// installed app, and checking it first keeps the common case to a single stat.
	if m.stackProvider != nil {
		addRoot(m.stackProvider.GetStackHDDPath(stack))
	}
	if m.settings != nil {
		for _, sp := range m.settings.GetStoragePaths() {
			addRoot(sp.Path)
		}
	}
	addRoot(m.systemDataPath)

	for _, nsRoot := range roots {
		unit := RecoveryUnitPath(nsRoot, stack)
		man := readManifest(filepath.Join(unit, "manifest.json"))
		if man == nil {
			continue
		}
		place := RecordedPlacement{
			Drive:         strings.TrimSpace(man.Drive),
			NamespaceRoot: strings.TrimSpace(man.NamespaceRoot),
		}
		addr := readRecordedAddress(filepath.Join(unit, "compose", "app.yaml"))
		if !place.Known() && !addr.Known() {
			continue // a unit that tells us nothing is not an answer
		}
		return place, addr, true
	}
	return RecordedPlacement{}, RecordedAddress{}, false
}

// readRecordedAddress parses SUBDOMAIN/DOMAIN out of a captured app.yaml. Returns the zero value on
// any failure — absent file, unreadable, malformed, or either half missing.
func readRecordedAddress(appYAMLPath string) RecordedAddress {
	raw, err := os.ReadFile(appYAMLPath)
	if err != nil {
		return RecordedAddress{}
	}
	var cfg unitAppConfig
	if yaml.Unmarshal(raw, &cfg) != nil || cfg.Env == nil {
		return RecordedAddress{}
	}
	return RecordedAddress{
		Subdomain: strings.TrimSpace(cfg.Env["SUBDOMAIN"]),
		Domain:    strings.TrimSpace(cfg.Env["DOMAIN"]),
	}
}

// scratchManifestMaxDepth bounds the walk below. The unit sits a handful of levels under the scratch
// root (the restore mirrors the snapshot's absolute path), and an unbounded walk over a scratch that
// also holds a full userdata tree would stat a customer's entire library to find one small file.
const scratchManifestMaxDepth = 8

// recordedPlacementFromScratch reads the placement out of the unit manifest inside a PREPARED
// restore scratch, without restoring anything.
//
// It exists for the not-installed refusal (scenario B), which fires BEFORE the live namespace root
// can be resolved — so it cannot use the manifest the reconstitution opens later. The scratch is
// already on local disk by then; this is a bounded walk and a file read, never a network call.
//
// Returns the zero value on ANY failure — unreadable, absent, malformed. A refusal that cannot name
// the recorded place must fall back to the plain sentence rather than print an empty path, which
// would read as "the backup says it lived nowhere".
func (m *Manager) recordedPlacementFromScratch(scratch string) RecordedPlacement {
	var found RecordedPlacement
	root := filepath.Clean(scratch)
	rootDepth := strings.Count(root, string(os.PathSeparator))
	_ = filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error {
		if err != nil {
			return nil // an unreadable subtree is not fatal: keep looking elsewhere
		}
		if d.IsDir() {
			if strings.Count(filepath.Clean(path), string(os.PathSeparator))-rootDepth >= scratchManifestMaxDepth {
				return fs.SkipDir
			}
			return nil
		}
		if d.Name() != "manifest.json" {
			return nil
		}
		if man := readManifest(path); man != nil && strings.TrimSpace(man.Drive) != "" {
			found = RecordedPlacement{
				Drive:         strings.TrimSpace(man.Drive),
				NamespaceRoot: strings.TrimSpace(man.NamespaceRoot),
			}
			return fs.SkipAll
		}
		return nil
	})
	return found
}

// PlacementMismatchMessage is the Hungarian refusal shown when the destination differs from the one
// the backup recorded. It NAMES BOTH VALUES — which is the whole point: "a destination differs" that
// does not say from what leaves the customer with a decision they cannot make.
//
// It is a refusal with a route, not a dead end: the caller re-offers the action with the
// acknowledgement field set, so the customer can proceed deliberately (scenario C).
func PlacementMismatchMessage(stack string, c PlacementCheck) string {
	return fmt.Sprintf(
		"A(z) %s mentése szerint az adatok korábban itt voltak: %s. Most viszont ide állna vissza: %s. "+
			"Ez lehet szándékos — például ha meghajtót cseréltél —, de magától nem folytatjuk. "+
			"Ha így jó, erősítsd meg alább, és a visszaállítás az új helyre fut.",
		stack, c.Recorded.Drive, c.LiveDrive)
}