mfer/internal/checker/checker.go

package checker

import (
	"bytes"
	"context"
	"crypto/sha256"
	"errors"
	"io"
	"os"
	"path/filepath"
	"time"

	"github.com/multiformats/go-multihash"
	"github.com/spf13/afero"
	"sneak.berlin/go/mfer/mfer"
)

// Result represents the outcome of checking a single file.
type Result struct {
	Path    mfer.RelFilePath // Relative path from manifest
	Status  Status           // Verification result status
	Message string           // Human-readable description of the result
}

// Status represents the verification status of a file.
type Status int

const (
	StatusOK           Status = iota // File matches manifest (size and hash verified)
	StatusMissing                    // File not found on disk
	StatusSizeMismatch               // File size differs from manifest
	StatusHashMismatch               // File hash differs from manifest
	StatusExtra                      // File exists on disk but not in manifest
	StatusError                      // Error occurred during verification
)

func (s Status) String() string {
	switch s {
	case StatusOK:
		return "OK"
	case StatusMissing:
		return "MISSING"
	case StatusSizeMismatch:
		return "SIZE_MISMATCH"
	case StatusHashMismatch:
		return "HASH_MISMATCH"
	case StatusExtra:
		return "EXTRA"
	case StatusError:
		return "ERROR"
	default:
		return "UNKNOWN"
	}
}

// CheckStatus contains progress information for the check operation.
type CheckStatus struct {
	TotalFiles   mfer.FileCount // Total number of files in manifest
	CheckedFiles mfer.FileCount // Number of files checked so far
	TotalBytes   mfer.FileSize  // Total bytes to verify (sum of all file sizes)
	CheckedBytes mfer.FileSize  // Bytes verified so far
	BytesPerSec  float64        // Current throughput rate
	ETA          time.Duration  // Estimated time to completion
	Failures     mfer.FileCount // Number of verification failures encountered
}

// Checker verifies files against a manifest.
type Checker struct {
	basePath mfer.AbsFilePath
	files    []*mfer.MFFilePath
	fs       afero.Fs
	// manifestPaths is a set of paths in the manifest for quick lookup
	manifestPaths map[mfer.RelFilePath]struct{}
}

// NewChecker creates a new Checker for the given manifest, base path, and filesystem.
// The basePath is the directory relative to which manifest paths are resolved.
// If fs is nil, the real filesystem (OsFs) is used.
func NewChecker(manifestPath string, basePath string, fs afero.Fs) (*Checker, error) {
	if fs == nil {
		fs = afero.NewOsFs()
	}

	m, err := mfer.NewManifestFromFile(fs, manifestPath)
	if err != nil {
		return nil, err
	}

	abs, err := filepath.Abs(basePath)
	if err != nil {
		return nil, err
	}

	files := m.Files()
	manifestPaths := make(map[mfer.RelFilePath]struct{}, len(files))
	for _, f := range files {
		manifestPaths[mfer.RelFilePath(f.Path)] = struct{}{}
	}

	return &Checker{
		basePath:      mfer.AbsFilePath(abs),
		files:         files,
		fs:            fs,
		manifestPaths: manifestPaths,
	}, nil
}

// FileCount returns the number of files in the manifest.
func (c *Checker) FileCount() mfer.FileCount {
	return mfer.FileCount(len(c.files))
}

// TotalBytes returns the total size of all files in the manifest.
func (c *Checker) TotalBytes() mfer.FileSize {
	var total mfer.FileSize
	for _, f := range c.files {
		total += mfer.FileSize(f.Size)
	}
	return total
}

// Check verifies all files against the manifest.
// Results are sent to the results channel as files are checked.
// Progress updates are sent to the progress channel approximately once per second.
// Both channels are closed when the method returns.
func (c *Checker) Check(ctx context.Context, results chan<- Result, progress chan<- CheckStatus) error {
	if results != nil {
		defer close(results)
	}
	if progress != nil {
		defer close(progress)
	}

	totalFiles := mfer.FileCount(len(c.files))
	totalBytes := c.TotalBytes()

	var checkedFiles mfer.FileCount
	var checkedBytes mfer.FileSize
	var failures mfer.FileCount

	startTime := time.Now()

	for _, entry := range c.files {
		select {
		case <-ctx.Done():
			return ctx.Err()
		default:
		}

		result := c.checkFile(entry, &checkedBytes)
		if result.Status != StatusOK {
			failures++
		}
		checkedFiles++

		if results != nil {
			results <- result
		}

		// Send progress with rate and ETA calculation
		if progress != nil {
			elapsed := time.Since(startTime)
			var bytesPerSec float64
			var eta time.Duration

			if elapsed > 0 && checkedBytes > 0 {
				bytesPerSec = float64(checkedBytes) / elapsed.Seconds()
				remainingBytes := totalBytes - checkedBytes
				if bytesPerSec > 0 {
					eta = time.Duration(float64(remainingBytes)/bytesPerSec) * time.Second
				}
			}

			sendCheckStatus(progress, CheckStatus{
				TotalFiles:   totalFiles,
				CheckedFiles: checkedFiles,
				TotalBytes:   totalBytes,
				CheckedBytes: checkedBytes,
				BytesPerSec:  bytesPerSec,
				ETA:          eta,
				Failures:     failures,
			})
		}
	}

	return nil
}

func (c *Checker) checkFile(entry *mfer.MFFilePath, checkedBytes *mfer.FileSize) Result {
	absPath := filepath.Join(string(c.basePath), entry.Path)
	relPath := mfer.RelFilePath(entry.Path)

	// Check if file exists
	info, err := c.fs.Stat(absPath)
	if err != nil {
		if errors.Is(err, afero.ErrFileNotFound) || errors.Is(err, errors.New("file does not exist")) {
			return Result{Path: relPath, Status: StatusMissing, Message: "file not found"}
		}
		// Check for "file does not exist" style errors
		exists, _ := afero.Exists(c.fs, absPath)
		if !exists {
			return Result{Path: relPath, Status: StatusMissing, Message: "file not found"}
		}
		return Result{Path: relPath, Status: StatusError, Message: err.Error()}
	}

	// Check size
	if info.Size() != entry.Size {
		*checkedBytes += mfer.FileSize(info.Size())
		return Result{
			Path:    relPath,
			Status:  StatusSizeMismatch,
			Message: "size mismatch",
		}
	}

	// Open and hash file
	f, err := c.fs.Open(absPath)
	if err != nil {
		return Result{Path: relPath, Status: StatusError, Message: err.Error()}
	}
	defer func() { _ = f.Close() }()

	h := sha256.New()
	n, err := io.Copy(h, f)
	if err != nil {
		return Result{Path: relPath, Status: StatusError, Message: err.Error()}
	}
	*checkedBytes += mfer.FileSize(n)

	// Encode as multihash and compare
	computed, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256)
	if err != nil {
		return Result{Path: relPath, Status: StatusError, Message: err.Error()}
	}

	// Check against all hashes in manifest (at least one must match)
	for _, hash := range entry.Hashes {
		if bytes.Equal(computed, hash.MultiHash) {
			return Result{Path: relPath, Status: StatusOK}
		}
	}

	return Result{Path: relPath, Status: StatusHashMismatch, Message: "hash mismatch"}
}

// FindExtraFiles walks the filesystem and reports files not in the manifest.
// Results are sent to the results channel. The channel is closed when done.
func (c *Checker) FindExtraFiles(ctx context.Context, results chan<- Result) error {
	if results != nil {
		defer close(results)
	}

	return afero.Walk(c.fs, string(c.basePath), func(path string, info os.FileInfo, err error) error {
		if err != nil {
			return err
		}

		select {
		case <-ctx.Done():
			return ctx.Err()
		default:
		}

		// Skip directories
		if info.IsDir() {
			return nil
		}

		// Get relative path
		rel, err := filepath.Rel(string(c.basePath), path)
		if err != nil {
			return err
		}
		relPath := mfer.RelFilePath(rel)

		// Check if path is in manifest
		if _, exists := c.manifestPaths[relPath]; !exists {
			if results != nil {
				results <- Result{
					Path:    relPath,
					Status:  StatusExtra,
					Message: "not in manifest",
				}
			}
		}

		return nil
	})
}

// sendCheckStatus sends a status update without blocking.
func sendCheckStatus(ch chan<- CheckStatus, status CheckStatus) {
	if ch == nil {
		return
	}
	select {
	case ch <- status:
	default:
	}
}