pixa/internal/imgcache/storage.go

package imgcache

import (
	"crypto/sha256"
	"encoding/hex"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"os"
	"path/filepath"
)

// Storage constants.
const (
	// StorageDirPerm is the permission mode for storage directories.
	StorageDirPerm = 0750
	// MinHashLength is the minimum hash length for path splitting.
	MinHashLength = 4
)

// Storage errors.
var (
	ErrNotFound = errors.New("content not found")
)

// ContentStorage handles content-addressable file storage.
// Files are stored at: <basedir>/<ab>/<cd>/<abcdef...sha256>
type ContentStorage struct {
	baseDir string
}

// NewContentStorage creates a new content storage at the given base directory.
func NewContentStorage(baseDir string) (*ContentStorage, error) {
	if err := os.MkdirAll(baseDir, StorageDirPerm); err != nil {
		return nil, fmt.Errorf("failed to create storage directory: %w", err)
	}

	return &ContentStorage{baseDir: baseDir}, nil
}

// Store writes content to storage and returns its SHA256 hash.
// The content is read fully into memory to compute the hash before writing.
func (s *ContentStorage) Store(r io.Reader) (hash string, size int64, err error) {
	// Read all content to compute hash
	data, err := io.ReadAll(r)
	if err != nil {
		return "", 0, fmt.Errorf("failed to read content: %w", err)
	}

	// Compute hash
	h := sha256.Sum256(data)
	hash = hex.EncodeToString(h[:])
	size = int64(len(data))

	// Build path: <basedir>/<ab>/<cd>/<hash>
	path := s.hashToPath(hash)

	// Check if already exists
	if _, err := os.Stat(path); err == nil {
		return hash, size, nil
	}

	// Create directory structure
	dir := filepath.Dir(path)
	if err := os.MkdirAll(dir, StorageDirPerm); err != nil {
		return "", 0, fmt.Errorf("failed to create directory: %w", err)
	}

	// Write to temp file first, then rename for atomicity
	tmpFile, err := os.CreateTemp(dir, ".tmp-*")
	if err != nil {
		return "", 0, fmt.Errorf("failed to create temp file: %w", err)
	}
	tmpPath := tmpFile.Name()

	defer func() {
		if err != nil {
			_ = os.Remove(tmpPath)
		}
	}()

	if _, err := tmpFile.Write(data); err != nil {
		_ = tmpFile.Close()

		return "", 0, fmt.Errorf("failed to write content: %w", err)
	}

	if err := tmpFile.Close(); err != nil {
		return "", 0, fmt.Errorf("failed to close temp file: %w", err)
	}

	// Atomic rename
	if err := os.Rename(tmpPath, path); err != nil {
		return "", 0, fmt.Errorf("failed to rename temp file: %w", err)
	}

	return hash, size, nil
}

// Load returns a reader for the content with the given hash.
func (s *ContentStorage) Load(hash string) (io.ReadCloser, error) {
	path := s.hashToPath(hash)

	f, err := os.Open(path) //nolint:gosec // content-addressable path from hash
	if err != nil {
		if os.IsNotExist(err) {
			return nil, ErrNotFound
		}

		return nil, fmt.Errorf("failed to open content: %w", err)
	}

	return f, nil
}

// LoadWithSize returns a reader and file size for the content with the given hash.
func (s *ContentStorage) LoadWithSize(hash string) (io.ReadCloser, int64, error) {
	path := s.hashToPath(hash)

	f, err := os.Open(path) //nolint:gosec // content-addressable path from hash
	if err != nil {
		if os.IsNotExist(err) {
			return nil, 0, ErrNotFound
		}

		return nil, 0, fmt.Errorf("failed to open content: %w", err)
	}

	stat, err := f.Stat()
	if err != nil {
		_ = f.Close()

		return nil, 0, fmt.Errorf("failed to stat content: %w", err)
	}

	return f, stat.Size(), nil
}

// Delete removes content with the given hash.
func (s *ContentStorage) Delete(hash string) error {
	path := s.hashToPath(hash)

	err := os.Remove(path)
	if err != nil && !os.IsNotExist(err) {
		return fmt.Errorf("failed to delete content: %w", err)
	}

	return nil
}

// Exists checks if content with the given hash exists.
func (s *ContentStorage) Exists(hash string) bool {
	path := s.hashToPath(hash)
	_, err := os.Stat(path)

	return err == nil
}

// Path returns the file path for a given hash.
func (s *ContentStorage) Path(hash string) string {
	return s.hashToPath(hash)
}

// hashToPath converts a hash to a file path: <basedir>/<ab>/<cd>/<hash>
func (s *ContentStorage) hashToPath(hash string) string {
	if len(hash) < MinHashLength {
		return filepath.Join(s.baseDir, hash)
	}

	return filepath.Join(s.baseDir, hash[0:2], hash[2:4], hash)
}

// MetadataStorage handles JSON metadata file storage.
// Files are stored at: <basedir>/<hostname>/<path_hash>.json
type MetadataStorage struct {
	baseDir string
}

// NewMetadataStorage creates a new metadata storage at the given base directory.
func NewMetadataStorage(baseDir string) (*MetadataStorage, error) {
	if err := os.MkdirAll(baseDir, StorageDirPerm); err != nil {
		return nil, fmt.Errorf("failed to create metadata directory: %w", err)
	}

	return &MetadataStorage{baseDir: baseDir}, nil
}

// SourceMetadata represents cached metadata about a source URL.
type SourceMetadata struct {
	Host            string              `json:"host"`
	Path            string              `json:"path"`
	Query           string              `json:"query,omitempty"`
	ContentHash     string              `json:"content_hash,omitempty"`
	StatusCode      int                 `json:"status_code"`
	ContentType     string              `json:"content_type,omitempty"`
	ResponseHeaders map[string][]string `json:"response_headers,omitempty"`
	FetchedAt       int64               `json:"fetched_at"`
	ExpiresAt       int64               `json:"expires_at,omitempty"`
	ETag            string              `json:"etag,omitempty"`
	LastModified    string              `json:"last_modified,omitempty"`
}

// Store writes metadata to storage.
func (s *MetadataStorage) Store(host, pathHash string, meta *SourceMetadata) error {
	path := s.metaPath(host, pathHash)

	// Create directory structure
	dir := filepath.Dir(path)
	if err := os.MkdirAll(dir, StorageDirPerm); err != nil {
		return fmt.Errorf("failed to create directory: %w", err)
	}

	// Marshal to JSON
	data, err := json.MarshalIndent(meta, "", "  ")
	if err != nil {
		return fmt.Errorf("failed to marshal metadata: %w", err)
	}

	// Write to temp file first, then rename for atomicity
	tmpFile, err := os.CreateTemp(dir, ".tmp-*.json")
	if err != nil {
		return fmt.Errorf("failed to create temp file: %w", err)
	}
	tmpPath := tmpFile.Name()

	defer func() {
		if err != nil {
			_ = os.Remove(tmpPath)
		}
	}()

	if _, err := tmpFile.Write(data); err != nil {
		_ = tmpFile.Close()

		return fmt.Errorf("failed to write metadata: %w", err)
	}

	if err := tmpFile.Close(); err != nil {
		return fmt.Errorf("failed to close temp file: %w", err)
	}

	// Atomic rename
	if err := os.Rename(tmpPath, path); err != nil {
		return fmt.Errorf("failed to rename temp file: %w", err)
	}

	return nil
}

// Load reads metadata from storage.
func (s *MetadataStorage) Load(host, pathHash string) (*SourceMetadata, error) {
	path := s.metaPath(host, pathHash)

	data, err := os.ReadFile(path) //nolint:gosec // path derived from host+hash
	if err != nil {
		if os.IsNotExist(err) {
			return nil, ErrNotFound
		}

		return nil, fmt.Errorf("failed to read metadata: %w", err)
	}

	var meta SourceMetadata
	if err := json.Unmarshal(data, &meta); err != nil {
		return nil, fmt.Errorf("failed to unmarshal metadata: %w", err)
	}

	return &meta, nil
}

// Delete removes metadata for the given host and path hash.
func (s *MetadataStorage) Delete(host, pathHash string) error {
	path := s.metaPath(host, pathHash)

	err := os.Remove(path)
	if err != nil && !os.IsNotExist(err) {
		return fmt.Errorf("failed to delete metadata: %w", err)
	}

	return nil
}

// Exists checks if metadata exists for the given host and path hash.
func (s *MetadataStorage) Exists(host, pathHash string) bool {
	path := s.metaPath(host, pathHash)
	_, err := os.Stat(path)

	return err == nil
}

// metaPath returns the file path for metadata: <basedir>/<host>/<path_hash>.json
func (s *MetadataStorage) metaPath(host, pathHash string) string {
	return filepath.Join(s.baseDir, host, pathHash+".json")
}

// HashPath computes the SHA256 hash of a path string.
func HashPath(path string) string {
	h := sha256.Sum256([]byte(path))

	return hex.EncodeToString(h[:])
}

// CacheKey generates a unique cache key for a request.
// Format: sha256(host:path:query:width:height:format:quality:fit_mode)
func CacheKey(req *ImageRequest) string {
	data := fmt.Sprintf("%s:%s:%s:%d:%d:%s:%d:%s",
		req.SourceHost,
		req.SourcePath,
		req.SourceQuery,
		req.Size.Width,
		req.Size.Height,
		req.Format,
		req.Quality,
		req.FitMode,
	)
	h := sha256.Sum256([]byte(data))

	return hex.EncodeToString(h[:])
}