sow-tools/internal/depot/manifest.go

package depot

import (
	"fmt"
	"os"
	"path/filepath"
	"regexp"

	"gopkg.in/yaml.v3"
)

type manifestFile struct {
	Assets []struct {
		Path   string `yaml:"path"`
		SHA256 string `yaml:"sha256"`
		Size   int64  `yaml:"size"`
	} `yaml:"assets"`
}

var sha256Pattern = regexp.MustCompile(`^[0-9a-f]{64}$`)

func ValidSHA(s string) bool {
	return sha256Pattern.MatchString(s)
}

func BlobKey(sha string) string {
	return fmt.Sprintf("sha256/%s/%s/%s", sha[0:2], sha[2:4], sha)
}

func ReferencedSHAs(dir string) (map[string]int64, error) {
	entries, err := os.ReadDir(dir)
	if err != nil {
		return nil, err
	}

	result := make(map[string]int64)
	foundAny := false

	for _, entry := range entries {
		if entry.IsDir() {
			continue
		}
		if filepath.Ext(entry.Name()) != ".yml" {
			continue
		}

		foundAny = true
		path := filepath.Join(dir, entry.Name())
		data, err := os.ReadFile(path)
		if err != nil {
			return nil, err
		}

		var manifest manifestFile
		if err := yaml.Unmarshal(data, &manifest); err != nil {
			return nil, err
		}

		for _, asset := range manifest.Assets {
			if !ValidSHA(asset.SHA256) {
				return nil, fmt.Errorf("%s: asset %q: invalid sha256 %q", entry.Name(), asset.Path, asset.SHA256)
			}

			// Keep the largest size for each sha
			if asset.Size > result[asset.SHA256] {
				result[asset.SHA256] = asset.Size
			}
		}
	}

	if !foundAny {
		return nil, fmt.Errorf("no *.yml files found in %s", dir)
	}

	return result, nil
}