plumbing/packfile: PACK encoder (#131)

* plumbing/packfile: PACK encoder

- Added simple PACK encoder, deltas not supported by now

* Requested changes

* Requested changes

* Requested changes

4 files changed, 272 insertions, 15 deletions

diff --git a/plumbing/format/packfile/common.go b/plumbing/format/packfile/common.go
new file mode 100644
index 0000000..1656551
--- /dev/null
+++ b/plumbing/format/packfile/common.go
@@ -0,0 +1,15 @@
+package packfile
+
+var signature = []byte{'P', 'A', 'C', 'K'}
+
+const (
+	// VersionSupported is the packfile version supported by this package
+	VersionSupported uint32 = 2
+
+	firstLengthBits = uint8(4)   // the first byte into object header has 4 bits to store the length
+	lengthBits      = uint8(7)   // subsequent bytes has 7 bits to store the length
+	maskFirstLength = 15         // 0000 1111
+	maskContinue    = 0x80       // 1000 0000
+	maskLength      = uint8(127) // 0111 1111
+	maskType        = uint8(112) // 0111 0000
+)
diff --git a/plumbing/format/packfile/encoder.go b/plumbing/format/packfile/encoder.go
new file mode 100644
index 0000000..1404dbe
--- /dev/null
+++ b/plumbing/format/packfile/encoder.go
@@ -0,0 +1,116 @@
+package packfile
+
+import (
+	"compress/zlib"
+	"crypto/sha1"
+	"fmt"
+	"io"
+
+	"gopkg.in/src-d/go-git.v4/plumbing"
+	"gopkg.in/src-d/go-git.v4/plumbing/storer"
+	"gopkg.in/src-d/go-git.v4/utils/binary"
+)
+
+// Encoder gets the data from the storage and write it into the writer in PACK
+// format
+type Encoder struct {
+	storage storer.ObjectStorer
+	w       io.Writer
+	zw      *zlib.Writer
+	hasher  plumbing.Hasher
+}
+
+// NewEncoder creates a new packfile encoder using a specific Writer and
+// ObjectStorer
+func NewEncoder(w io.Writer, s storer.ObjectStorer) *Encoder {
+	h := plumbing.Hasher{
+		Hash: sha1.New(),
+	}
+	mw := io.MultiWriter(w, h)
+	zw := zlib.NewWriter(mw)
+	return &Encoder{
+		storage: s,
+		w:       mw,
+		zw:      zw,
+		hasher:  h,
+	}
+}
+
+// Encode creates a packfile containing all the objects referenced in hashes
+// and writes it to the writer in the Encoder.
+func (e *Encoder) Encode(hashes []plumbing.Hash) (plumbing.Hash, error) {
+	if err := e.head(len(hashes)); err != nil {
+		return plumbing.ZeroHash, err
+	}
+
+	for _, h := range hashes {
+		o, err := e.storage.Object(plumbing.AnyObject, h)
+		if err != nil {
+			return plumbing.ZeroHash, err
+		}
+
+		if err := e.entry(o); err != nil {
+			return plumbing.ZeroHash, err
+		}
+	}
+
+	return e.footer()
+}
+
+func (e *Encoder) head(numEntries int) error {
+	return binary.Write(
+		e.w,
+		signature,
+		int32(VersionSupported),
+		int32(numEntries),
+	)
+}
+
+func (e *Encoder) entry(o plumbing.Object) error {
+	t := o.Type()
+	if t == plumbing.OFSDeltaObject || t == plumbing.REFDeltaObject {
+		// TODO implements delta objects
+		return fmt.Errorf("delta object not supported: %v", t)
+	}
+
+	if err := e.entryHead(t, o.Size()); err != nil {
+		return err
+	}
+
+	e.zw.Reset(e.w)
+	or, err := o.Reader()
+	if err != nil {
+		return err
+	}
+	_, err = io.Copy(e.zw, or)
+	if err != nil {
+		return err
+	}
+
+	return e.zw.Close()
+}
+
+func (e *Encoder) entryHead(typeNum plumbing.ObjectType, size int64) error {
+	t := int64(typeNum)
+	header := []byte{}
+	c := (t << firstLengthBits) | (size & maskFirstLength)
+	size >>= firstLengthBits
+	for {
+		if size == 0 {
+			break
+		}
+		header = append(header, byte(c|maskContinue))
+		c = size & int64(maskLength)
+		size >>= lengthBits
+	}
+
+	header = append(header, byte(c))
+	_, err := e.w.Write(header)
+
+	return err
+}
+
+func (e *Encoder) footer() (plumbing.Hash, error) {
+	h := e.hasher.Sum()
+	return h, binary.Write(e.w, h)
+}
diff --git a/plumbing/format/packfile/encoder_test.go b/plumbing/format/packfile/encoder_test.go
new file mode 100644
index 0000000..729843d
--- /dev/null
+++ b/plumbing/format/packfile/encoder_test.go
@@ -0,0 +1,140 @@
+package packfile
+
+import (
+	"bytes"
+
+	"gopkg.in/src-d/go-git.v4/fixtures"
+	"gopkg.in/src-d/go-git.v4/plumbing"
+	"gopkg.in/src-d/go-git.v4/storage/memory"
+
+	. "gopkg.in/check.v1"
+)
+
+type EncoderSuite struct {
+	fixtures.Suite
+	buf   *bytes.Buffer
+	store *memory.Storage
+	enc   *Encoder
+}
+
+var _ = Suite(&EncoderSuite{})
+
+func (s *EncoderSuite) SetUpTest(c *C) {
+	s.buf = bytes.NewBuffer(nil)
+	s.store = memory.NewStorage()
+	s.enc = NewEncoder(s.buf, s.store)
+}
+
+func (s *EncoderSuite) TestCorrectPackHeader(c *C) {
+	hash, err := s.enc.Encode([]plumbing.Hash{})
+	c.Assert(err, IsNil)
+
+	hb := [20]byte(hash)
+
+	// PACK + VERSION + OBJECTS + HASH
+	expectedResult := []byte{'P', 'A', 'C', 'K', 0, 0, 0, 2, 0, 0, 0, 0}
+	expectedResult = append(expectedResult, hb[:]...)
+
+	result := s.buf.Bytes()
+
+	c.Assert(result, DeepEquals, expectedResult)
+}
+
+func (s *EncoderSuite) TestCorrectPackWithOneEmptyObject(c *C) {
+	o := &plumbing.MemoryObject{}
+	o.SetType(plumbing.CommitObject)
+	o.SetSize(0)
+	_, err := s.store.SetObject(o)
+	c.Assert(err, IsNil)
+
+	hash, err := s.enc.Encode([]plumbing.Hash{o.Hash()})
+	c.Assert(err, IsNil)
+
+	// PACK + VERSION(2) + OBJECT NUMBER(1)
+	expectedResult := []byte{'P', 'A', 'C', 'K', 0, 0, 0, 2, 0, 0, 0, 1}
+	// OBJECT HEADER(TYPE + SIZE)= 0001 0000
+	expectedResult = append(expectedResult, []byte{16}...)
+
+	// Zlib header
+	expectedResult = append(expectedResult,
+		[]byte{120, 156, 1, 0, 0, 255, 255, 0, 0, 0, 1}...)
+
+	// + HASH
+	hb := [20]byte(hash)
+	expectedResult = append(expectedResult, hb[:]...)
+
+	result := s.buf.Bytes()
+
+	c.Assert(result, DeepEquals, expectedResult)
+}
+
+func (s *EncoderSuite) TestMaxObjectSize(c *C) {
+	o := s.store.NewObject()
+	o.SetSize(9223372036854775807)
+	o.SetType(plumbing.CommitObject)
+	_, err := s.store.SetObject(o)
+	c.Assert(err, IsNil)
+	hash, err := s.enc.Encode([]plumbing.Hash{o.Hash()})
+	c.Assert(err, IsNil)
+	c.Assert(hash.IsZero(), Not(Equals), true)
+}
+
+func (s *EncoderSuite) TestDecodeEncodeDecode(c *C) {
+	fixtures.Basic().ByTag("packfile").Test(c, func(f *fixtures.Fixture) {
+		scanner := NewScanner(f.Packfile())
+		storage := memory.NewStorage()
+
+		d, err := NewDecoder(scanner, storage)
+		c.Assert(err, IsNil)
+
+		ch, err := d.Decode()
+		c.Assert(err, IsNil)
+		c.Assert(ch, Equals, f.PackfileHash)
+
+		commitIter, err := d.o.IterObjects(plumbing.AnyObject)
+		c.Assert(err, IsNil)
+
+		objects := []plumbing.Object{}
+		hashes := []plumbing.Hash{}
+		err = commitIter.ForEach(func(o plumbing.Object) error {
+			objects = append(objects, o)
+			hash, err := s.store.SetObject(o)
+			hashes = append(hashes, hash)
+
+			return err
+
+		})
+		c.Assert(err, IsNil)
+		_, err = s.enc.Encode(hashes)
+		c.Assert(err, IsNil)
+
+		scanner = NewScanner(s.buf)
+		storage = memory.NewStorage()
+		d, err = NewDecoder(scanner, storage)
+		c.Assert(err, IsNil)
+		_, err = d.Decode()
+		c.Assert(err, IsNil)
+
+		commitIter, err = d.o.IterObjects(plumbing.AnyObject)
+		c.Assert(err, IsNil)
+		obtainedObjects := []plumbing.Object{}
+		err = commitIter.ForEach(func(o plumbing.Object) error {
+			obtainedObjects = append(obtainedObjects, o)
+
+			return nil
+		})
+		c.Assert(err, IsNil)
+		c.Assert(len(obtainedObjects), Equals, len(objects))
+
+		equals := 0
+		for _, oo := range obtainedObjects {
+			for _, o := range objects {
+				if o.Hash() == oo.Hash() {
+					equals++
+				}
+			}
+		}
+
+		c.Assert(len(obtainedObjects), Equals, equals)
+	})
+}
diff --git a/plumbing/format/packfile/scanner.go b/plumbing/format/packfile/scanner.go
index 130bb94..3adc26a 100644
--- a/plumbing/format/packfile/scanner.go
+++ b/plumbing/format/packfile/scanner.go
@@ -26,11 +26,6 @@ var (
 	ErrSeekNotSupported = NewError("not seek support")
 )
 
-const (
-	// VersionSupported is the packfile version supported by this parser.
-	VersionSupported uint32 = 2
-)
-
 // ObjectHeader contains the information related to the object, this information
 // is collected from the previous bytes to the content of the object.
 type ObjectHeader struct {
@@ -124,7 +119,7 @@ func (s *Scanner) readSignature() ([]byte, error) {
 
 // isValidSignature returns if sig is a valid packfile signature.
 func (s *Scanner) isValidSignature(sig []byte) bool {
-	return bytes.Equal(sig, []byte{'P', 'A', 'C', 'K'})
+	return bytes.Equal(sig, signature)
 }
 
 // readVersion reads and returns the version field of a packfile.
@@ -230,15 +225,6 @@ func (s *Scanner) readObjectTypeAndLength() (plumbing.ObjectType, int64, error)
 	return t, l, err
 }
 
-const (
-	maskType        = uint8(112) // 0111 0000
-	maskFirstLength = uint8(15)  // 0000 1111
-	maskContinue    = uint8(128) // 1000 000
-	firstLengthBits = uint8(4)   // the first byte has 4 bits to store the length
-	maskLength      = uint8(127) // 0111 1111
-	lengthBits      = uint8(7)   // subsequent bytes has 7 bits to store the length
-)
-
 func (s *Scanner) readType() (plumbing.ObjectType, byte, error) {
 	var c byte
 	var err error