mfer/mfer/builder.go

package mfer

import (
	"crypto/sha256"
	"errors"
	"fmt"
	"io"
	"sort"
	"strings"
	"sync"
	"time"
	"unicode/utf8"

	"github.com/multiformats/go-multihash"
)

// ValidatePath checks that a file path conforms to manifest path invariants:
//   - Must be valid UTF-8
//   - Must use forward slashes only (no backslashes)
//   - Must be relative (no leading /)
//   - Must not contain ".." segments
//   - Must not contain empty segments (no "//")
//   - Must not be empty
func ValidatePath(p string) error {
	if p == "" {
		return errors.New("path cannot be empty")
	}
	if !utf8.ValidString(p) {
		return fmt.Errorf("path %q is not valid UTF-8", p)
	}
	if strings.ContainsRune(p, '\\') {
		return fmt.Errorf("path %q contains backslash; use forward slashes only", p)
	}
	if strings.HasPrefix(p, "/") {
		return fmt.Errorf("path %q is absolute; must be relative", p)
	}
	for _, seg := range strings.Split(p, "/") {
		if seg == "" {
			return fmt.Errorf("path %q contains empty segment", p)
		}
		if seg == ".." {
			return fmt.Errorf("path %q contains '..' segment", p)
		}
	}
	return nil
}

// RelFilePath represents a relative file path within a manifest.
type RelFilePath string

// AbsFilePath represents an absolute file path on the filesystem.
type AbsFilePath string

// FileSize represents the size of a file in bytes.
type FileSize int64

// FileCount represents a count of files.
type FileCount int64

// ModTime represents a file's modification time.
type ModTime time.Time

// UnixSeconds represents seconds since Unix epoch.
type UnixSeconds int64

// UnixNanos represents the nanosecond component of a timestamp (0-999999999).
type UnixNanos int32

// Timestamp converts ModTime to a protobuf Timestamp.
func (m ModTime) Timestamp() *Timestamp {
	t := time.Time(m)
	return &Timestamp{
		Seconds: t.Unix(),
		Nanos:   int32(t.Nanosecond()),
	}
}

// Multihash represents a multihash-encoded file hash (typically SHA2-256).
type Multihash []byte

// FileHashProgress reports progress during file hashing.
type FileHashProgress struct {
	BytesRead FileSize // Total bytes read so far for the current file
}

// Builder constructs a manifest by adding files one at a time.
type Builder struct {
	mu             sync.Mutex
	files          []*MFFilePath
	createdAt      time.Time
	signingOptions *SigningOptions
}

// NewBuilder creates a new Builder.
func NewBuilder() *Builder {
	return &Builder{
		files:     make([]*MFFilePath, 0),
		createdAt: time.Now(),
	}
}

// AddFile reads file content from reader, computes hashes, and adds to manifest.
// Progress updates are sent to the progress channel (if non-nil) without blocking.
// Returns the number of bytes read.
func (b *Builder) AddFile(
	path RelFilePath,
	size FileSize,
	mtime ModTime,
	reader io.Reader,
	progress chan<- FileHashProgress,
) (FileSize, error) {
	if err := ValidatePath(string(path)); err != nil {
		return 0, err
	}

	// Create hash writer
	h := sha256.New()

	// Read file in chunks, updating hash and progress
	var totalRead FileSize
	buf := make([]byte, 64*1024) // 64KB chunks

	for {
		n, err := reader.Read(buf)
		if n > 0 {
			h.Write(buf[:n])
			totalRead += FileSize(n)
			sendFileHashProgress(progress, FileHashProgress{BytesRead: totalRead})
		}
		if err == io.EOF {
			break
		}
		if err != nil {
			return totalRead, err
		}
	}

	// Verify actual bytes read matches declared size
	if totalRead != size {
		return totalRead, fmt.Errorf("size mismatch for %q: declared %d bytes but read %d bytes", path, size, totalRead)
	}

	// Encode hash as multihash (SHA2-256)
	mh, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256)
	if err != nil {
		return totalRead, err
	}

	// Create file entry
	entry := &MFFilePath{
		Path: string(path),
		Size: int64(size),
		Hashes: []*MFFileChecksum{
			{MultiHash: mh},
		},
		Mtime: mtime.Timestamp(),
	}

	b.mu.Lock()
	b.files = append(b.files, entry)
	b.mu.Unlock()

	return totalRead, nil
}

// sendFileHashProgress sends a progress update without blocking.
func sendFileHashProgress(ch chan<- FileHashProgress, p FileHashProgress) {
	if ch == nil {
		return
	}
	select {
	case ch <- p:
	default:
	}
}

// FileCount returns the number of files added to the builder.
func (b *Builder) FileCount() int {
	b.mu.Lock()
	defer b.mu.Unlock()
	return len(b.files)
}

// AddFileWithHash adds a file entry with a pre-computed hash.
// This is useful when the hash is already known (e.g., from an existing manifest).
// Returns an error if path is empty, size is negative, or hash is nil/empty.
func (b *Builder) AddFileWithHash(path RelFilePath, size FileSize, mtime ModTime, hash Multihash) error {
	if err := ValidatePath(string(path)); err != nil {
		return err
	}
	if size < 0 {
		return errors.New("size cannot be negative")
	}
	if len(hash) == 0 {
		return errors.New("hash cannot be nil or empty")
	}

	entry := &MFFilePath{
		Path: string(path),
		Size: int64(size),
		Hashes: []*MFFileChecksum{
			{MultiHash: hash},
		},
		Mtime: mtime.Timestamp(),
	}

	b.mu.Lock()
	b.files = append(b.files, entry)
	b.mu.Unlock()
	return nil
}

// SetSigningOptions sets the GPG signing options for the manifest.
// If opts is non-nil, the manifest will be signed when Build() is called.
func (b *Builder) SetSigningOptions(opts *SigningOptions) {
	b.mu.Lock()
	defer b.mu.Unlock()
	b.signingOptions = opts
}

// Build finalizes the manifest and writes it to the writer.
func (b *Builder) Build(w io.Writer) error {
	b.mu.Lock()
	defer b.mu.Unlock()

	// Sort files by path for deterministic output (#23)
	sort.Slice(b.files, func(i, j int) bool {
		return b.files[i].Path < b.files[j].Path
	})

	// Create inner manifest
	inner := &MFFile{
		Version:   MFFile_VERSION_ONE,
		CreatedAt: newTimestampFromTime(b.createdAt),
		Files:     b.files,
	}

	// Create a temporary manifest to use existing serialization
	m := &manifest{
		pbInner:        inner,
		signingOptions: b.signingOptions,
	}

	// Generate outer wrapper
	if err := m.generateOuter(); err != nil {
		return err
	}

	// Generate final output
	if err := m.generate(); err != nil {
		return err
	}

	// Write to output
	_, err := w.Write(m.output.Bytes())
	return err
}