vaultik/internal/config/config.go

// Package config loads, validates, and provides the vaultik YAML
// configuration, including snapshot definitions, encryption recipients,
// and storage settings.
package config

import (
	"errors"
	"fmt"
	"os"
	"path/filepath"
	"sort"
	"strings"

	"filippo.io/age"
	"git.eeqj.de/sneak/smartconfig"
	"github.com/adrg/xdg"
	"go.uber.org/fx"
	"gopkg.in/yaml.v3"
	"sneak.berlin/go/vaultik/internal/log"
)

const appName = "vaultik"

// Defaults and validation bounds for tunable settings.
const (
	defaultBlobSizeLimit    = Size(10 * 1024 * 1024 * 1024) // 10GB
	defaultChunkSize        = Size(10 * 1024 * 1024)        // 10MB
	defaultS3PartSize       = Size(5 * 1024 * 1024)         // 5MB
	defaultCompressionLevel = 3
	minChunkSize            = 1024 * 1024 // 1MB
	minCompressionLevel     = 1
	maxCompressionLevel     = 19
)

// Sentinel validation errors.
var (
	errNoConfigPath    = errors.New("config path not provided")
	errNoAgeRecipients = errors.New(
		"at least one age_recipient is required (generate with: age-keygen)")
	errNoSnapshots = errors.New(
		"at least one snapshot must be configured (see config.example.yml)")
	errSnapshotNoPaths   = errors.New("snapshot must have at least one path")
	errChunkSizeTooSmall = errors.New("chunk_size must be at least 1MB")
	errBlobSizeTooSmall  = errors.New("blob_size_limit must be at least chunk_size")
	errBadCompression    = errors.New("compression_level must be between 1 and 19")
	errBadStorageScheme  = errors.New(
		"storage_url must start with s3://, file://, or rclone://")
	errStorageNotConfigured = errors.New(
		"storage not configured; set storage_url or provide s3.endpoint + " +
			"s3.bucket + credentials")
	errS3BucketRequired = errors.New("s3.bucket is required (or set storage_url)")
	errS3KeyIDRequired  = errors.New("s3.access_key_id is required")
	errS3SecretRequired = errors.New("s3.secret_access_key is required")
)

// expandTilde expands ~ at the start of a path to the user's home directory.
func expandTilde(path string) string {
	if path == "~" {
		home, _ := os.UserHomeDir()

		return home
	}

	if strings.HasPrefix(path, "~/") {
		home, _ := os.UserHomeDir()

		return filepath.Join(home, path[2:])
	}

	return path
}

// expandTildeInURL expands ~ in file:// URLs.
func expandTildeInURL(url string) string {
	if strings.HasPrefix(url, "file://~/") {
		home, _ := os.UserHomeDir()

		return "file://" + filepath.Join(home, url[9:])
	}

	return url
}

// SnapshotConfig represents configuration for a named snapshot.
// Each snapshot backs up one or more paths and can have its own exclude patterns
// in addition to the global excludes.
type SnapshotConfig struct {
	Paths   []string `yaml:"paths"`
	Exclude []string `yaml:"exclude"` // Additional excludes for this snapshot
}

// GetExcludes returns the combined exclude patterns for a named snapshot.
// It merges global excludes with the snapshot-specific excludes.
func (c *Config) GetExcludes(snapshotName string) []string {
	snap, ok := c.Snapshots[snapshotName]
	if !ok {
		return c.Exclude
	}

	if len(snap.Exclude) == 0 {
		return c.Exclude
	}

	// Combine global and snapshot-specific excludes
	combined := make([]string, 0, len(c.Exclude)+len(snap.Exclude))
	combined = append(combined, c.Exclude...)
	combined = append(combined, snap.Exclude...)

	return combined
}

// SnapshotNames returns the names of all configured snapshots in sorted order.
func (c *Config) SnapshotNames() []string {
	names := make([]string, 0, len(c.Snapshots))
	for name := range c.Snapshots {
		names = append(names, name)
	}
	// Sort for deterministic order
	sort.Strings(names)

	return names
}

// Config represents the application configuration for Vaultik.
// It defines all settings for backup operations, including source directories,
// encryption recipients, storage configuration, and performance tuning parameters.
// Configuration is typically loaded from a YAML file.
//
//nolint:tagliatelle // snake_case is the established config-file format
type Config struct {
	AgeRecipients []string `yaml:"age_recipients"`
	AgeSecretKey  string   `yaml:"age_secret_key"`
	BlobSizeLimit Size     `yaml:"blob_size_limit"`
	ChunkSize     Size     `yaml:"chunk_size"`
	// Exclude holds global excludes applied to all snapshots.
	Exclude          []string                  `yaml:"exclude"`
	Hostname         string                    `yaml:"hostname"`
	IndexPath        string                    `yaml:"index_path"`
	S3               S3Config                  `yaml:"s3"`
	Snapshots        map[string]SnapshotConfig `yaml:"snapshots"`
	CompressionLevel int                       `yaml:"compression_level"`

	// StorageURL specifies the storage backend using a URL format.
	// Takes precedence over S3Config if set.
	// Supported formats:
	//   - s3://bucket/prefix?endpoint=host&region=us-east-1
	//   - file:///path/to/backup
	// For S3 URLs, credentials are still read from s3.access_key_id
	// and s3.secret_access_key.
	StorageURL string `yaml:"storage_url"`
}

// S3Config represents S3 storage configuration for backup storage.
// It supports both AWS S3 and S3-compatible storage services.
// All fields except UseSSL and PartSize are required.
//
//nolint:tagliatelle // snake_case is the established config-file format
type S3Config struct {
	Endpoint        string `yaml:"endpoint"`
	Bucket          string `yaml:"bucket"`
	Prefix          string `yaml:"prefix"`
	AccessKeyID     string `yaml:"access_key_id"`
	SecretAccessKey string `yaml:"secret_access_key"`
	Region          string `yaml:"region"`
	UseSSL          bool   `yaml:"use_ssl"`
	PartSize        Size   `yaml:"part_size"`
}

// Path wraps the config file path for fx dependency injection.
// This type allows the config file path to be injected as a distinct type
// rather than a plain string, avoiding conflicts with other string dependencies.
type Path string

// New creates a new Config instance by loading from the specified path.
// This function is used by the fx dependency injection framework.
// Returns an error if the path is empty or if loading fails.
func New(path Path) (*Config, error) {
	if path == "" {
		return nil, errNoConfigPath
	}

	cfg, err := Load(string(path))
	if err != nil {
		return nil, fmt.Errorf("failed to load config: %w", err)
	}

	return cfg, nil
}

// Load reads and parses the configuration file from the specified path.
// It applies default values for optional fields, performs environment variable
// substitution using smartconfig, and validates the configuration.
// The configuration file should be in YAML format. Returns an error if the file
// cannot be read, parsed, or if validation fails.
func Load(path string) (*Config, error) {
	// Load config using smartconfig for interpolation
	sc, err := smartconfig.NewFromConfigPath(path)
	if err != nil {
		return nil, fmt.Errorf("failed to load config file: %w", err)
	}

	cfg := &Config{
		// Set defaults
		BlobSizeLimit:    defaultBlobSizeLimit,
		ChunkSize:        defaultChunkSize,
		IndexPath:        filepath.Join(xdg.DataHome, appName, "index.sqlite"),
		CompressionLevel: defaultCompressionLevel,
	}

	// Convert smartconfig data to YAML then unmarshal
	configData := sc.Data()

	yamlBytes, err := yaml.Marshal(configData)
	if err != nil {
		return nil, fmt.Errorf("failed to marshal config data: %w", err)
	}

	err = yaml.Unmarshal(yamlBytes, cfg)
	if err != nil {
		return nil, fmt.Errorf("failed to parse config: %w", err)
	}

	// Expand tilde in all path fields
	cfg.IndexPath = expandTilde(cfg.IndexPath)
	cfg.StorageURL = expandTildeInURL(cfg.StorageURL)

	// Expand tildes in snapshot paths
	for name, snap := range cfg.Snapshots {
		for i, path := range snap.Paths {
			snap.Paths[i] = expandTilde(path)
		}

		cfg.Snapshots[name] = snap
	}

	// Check for environment variable override for IndexPath
	if envIndexPath := os.Getenv("VAULTIK_INDEX_PATH"); envIndexPath != "" {
		cfg.IndexPath = expandTilde(envIndexPath)
	}

	// Check for environment variable override for AgeSecretKey
	if envAgeSecretKey := os.Getenv("VAULTIK_AGE_SECRET_KEY"); envAgeSecretKey != "" {
		cfg.AgeSecretKey = extractAgeSecretKey(envAgeSecretKey)
	}

	// Get hostname if not set
	if cfg.Hostname == "" {
		hostname, err := os.Hostname()
		if err != nil {
			return nil, fmt.Errorf("failed to get hostname: %w", err)
		}

		cfg.Hostname = hostname
	}

	// Set default S3 settings
	if cfg.S3.Region == "" {
		cfg.S3.Region = "us-east-1"
	}

	if cfg.S3.PartSize == 0 {
		cfg.S3.PartSize = defaultS3PartSize
	}

	// Check config file permissions (warn if world or group readable)
	//nolint:gosec // G703: config path is operator-supplied by design
	info, statErr := os.Stat(path)
	if statErr == nil {
		mode := info.Mode().Perm()
		if mode&0044 != 0 { // group or world readable
			log.Warn("Config file has insecure permissions (contains S3 credentials)",
				"path", path,
				"mode", fmt.Sprintf("%04o", mode),
				"recommendation", "chmod 600 "+path)
		}
	}

	err = cfg.Validate()
	if err != nil {
		return nil, fmt.Errorf("invalid config: %w", err)
	}

	return cfg, nil
}

// Validate checks if the configuration is valid and complete.
// It ensures all required fields are present and have valid values:
// - At least one age recipient must be specified
// - At least one snapshot must be configured with at least one path
// - Storage must be configured (either storage_url or s3.* fields)
// - Chunk size must be at least 1MB
// - Blob size limit must be at least the chunk size
// - Compression level must be between 1 and 19
// Returns an error describing the first validation failure encountered.
func (c *Config) Validate() error {
	if len(c.AgeRecipients) == 0 {
		return errNoAgeRecipients
	}

	if len(c.Snapshots) == 0 {
		return errNoSnapshots
	}

	for name, snap := range c.Snapshots {
		if len(snap.Paths) == 0 {
			return fmt.Errorf("%w: %q", errSnapshotNoPaths, name)
		}
	}

	// Validate storage configuration
	err := c.validateStorage()
	if err != nil {
		return err
	}

	if c.ChunkSize.Int64() < minChunkSize {
		return errChunkSizeTooSmall
	}

	if c.BlobSizeLimit.Int64() < c.ChunkSize.Int64() {
		return errBlobSizeTooSmall
	}

	if c.CompressionLevel < minCompressionLevel ||
		c.CompressionLevel > maxCompressionLevel {
		return errBadCompression
	}

	return nil
}

// validateStorage validates storage configuration.
// If StorageURL is set, it takes precedence. S3 URLs require credentials.
// File URLs don't require any S3 configuration.
// If StorageURL is not set, legacy S3 configuration is required.
func (c *Config) validateStorage() error {
	if c.StorageURL != "" {
		return c.validateStorageURL()
	}

	// Legacy S3 configuration
	if c.S3.Endpoint == "" {
		return errStorageNotConfigured
	}

	if c.S3.Bucket == "" {
		return errS3BucketRequired
	}

	if c.S3.AccessKeyID == "" {
		return errS3KeyIDRequired
	}

	if c.S3.SecretAccessKey == "" {
		return errS3SecretRequired
	}

	return nil
}

// validateStorageURL validates URL-based storage configuration. File and
// rclone URLs need no credentials; S3 URLs require the legacy s3.*
// credential fields.
func (c *Config) validateStorageURL() error {
	switch {
	case strings.HasPrefix(c.StorageURL, "file://"):
		// File storage doesn't need S3 credentials
		return nil
	case strings.HasPrefix(c.StorageURL, "rclone://"):
		// Rclone storage uses rclone's own config
		return nil
	case strings.HasPrefix(c.StorageURL, "s3://"):
		// S3 storage needs credentials
		if c.S3.AccessKeyID == "" {
			return fmt.Errorf("%w for s3:// URLs", errS3KeyIDRequired)
		}

		if c.S3.SecretAccessKey == "" {
			return fmt.Errorf("%w for s3:// URLs", errS3SecretRequired)
		}

		return nil
	default:
		return errBadStorageScheme
	}
}

// extractAgeSecretKey extracts the AGE-SECRET-KEY from the input using
// the age library's parser, which handles comments and whitespace.
func extractAgeSecretKey(input string) string {
	identities, err := age.ParseIdentities(strings.NewReader(input))
	if err != nil || len(identities) == 0 {
		// Fall back to trimmed input if parsing fails
		return strings.TrimSpace(input)
	}
	// Return the string representation of the first identity
	if id, ok := identities[0].(*age.X25519Identity); ok {
		return id.String()
	}

	return strings.TrimSpace(input)
}

// Module exports the config module for fx dependency injection.
// It provides the Config type to other modules in the application.
//
//nolint:gochecknoglobals // fx module definitions are package globals
var Module = fx.Module("config",
	fx.Provide(New),
)