Merge pull request #916 from jfontan/improvement/memory-consumption-new-packfile-parser

Improvement/memory consumption new packfile parser

1 files changed, 37 insertions, 53 deletions

diff --git a/plumbing/format/packfile/parser.go b/plumbing/format/packfile/parser.go
index 581c334..28582b5 100644
--- a/plumbing/format/packfile/parser.go
+++ b/plumbing/format/packfile/parser.go
@@ -48,7 +48,7 @@ type Parser struct {
 	pendingRefDeltas map[plumbing.Hash][]*objectInfo
 	checksum         plumbing.Hash
 
-	cache *cache.ObjectLRU
+	cache *cache.BufferLRU
 	// delta content by offset, only used if source is not seekable
 	deltas map[int64][]byte
 
@@ -82,7 +82,7 @@ func NewParserWithStorage(
 		scanner:          scanner,
 		ob:               ob,
 		count:            0,
-		cache:            cache.NewObjectLRUDefault(),
+		cache:            cache.NewBufferLRUDefault(),
 		pendingRefDeltas: make(map[plumbing.Hash][]*objectInfo),
 		deltas:           deltas,
 	}, nil
@@ -221,21 +221,22 @@ func (p *Parser) indexObjects() error {
 			ota = newBaseObject(oh.Offset, oh.Length, t)
 		}
 
-		size, crc, err := p.scanner.NextObject(buf)
+		_, crc, err := p.scanner.NextObject(buf)
 		if err != nil {
 			return err
 		}
 
 		ota.Crc32 = crc
-		ota.PackSize = size
 		ota.Length = oh.Length
 
 		data := buf.Bytes()
 		if !delta {
-			if _, err := ota.Write(data); err != nil {
+			sha1, err := getSHA1(ota.Type, data)
+			if err != nil {
 				return err
 			}
-			ota.SHA1 = ota.Sum()
+
+			ota.SHA1 = sha1
 			p.oiByHash[ota.SHA1] = ota
 		}
 
@@ -291,41 +292,35 @@ func (p *Parser) resolveDeltas() error {
 				delete(p.deltas, obj.Offset)
 			}
 		}
-
-		obj.Content = nil
 	}
 
 	return nil
 }
 
 func (p *Parser) get(o *objectInfo) ([]byte, error) {
-	if len(o.Content) > 0 {
-		return o.Content, nil
-	}
-
-	e, ok := p.cache.Get(o.SHA1)
+	b, ok := p.cache.Get(o.Offset)
 	// If it's not on the cache and is not a delta we can try to find it in the
 	// storage, if there's one.
 	if !ok && p.storage != nil && !o.Type.IsDelta() {
 		var err error
-		e, err = p.storage.EncodedObject(plumbing.AnyObject, o.SHA1)
+		e, err := p.storage.EncodedObject(plumbing.AnyObject, o.SHA1)
 		if err != nil {
 			return nil, err
 		}
-	}
 
-	if e != nil {
 		r, err := e.Reader()
 		if err != nil {
 			return nil, err
 		}
 
-		buf := make([]byte, e.Size())
-		if _, err = r.Read(buf); err != nil {
+		b = make([]byte, e.Size())
+		if _, err = r.Read(b); err != nil {
 			return nil, err
 		}
+	}
 
-		return buf, nil
+	if b != nil {
+		return b, nil
 	}
 
 	var data []byte
@@ -348,11 +343,7 @@ func (p *Parser) get(o *objectInfo) ([]byte, error) {
 	}
 
 	if len(o.Children) > 0 {
-		m := &plumbing.MemoryObject{}
-		m.Write(data)
-		m.SetType(o.Type)
-		m.SetSize(o.Size())
-		p.cache.Put(m)
+		p.cache.Put(o.Offset, data)
 	}
 
 	return data, nil
@@ -410,8 +401,6 @@ func (p *Parser) readData(o *objectInfo) ([]byte, error) {
 		return data, nil
 	}
 
-	// TODO: skip header. Header size can be calculated with the offset of the
-	// next offset in the first pass.
 	if _, err := p.scanner.SeekFromStart(o.Offset); err != nil {
 		return nil, err
 	}
@@ -434,34 +423,40 @@ func applyPatchBase(ota *objectInfo, data, base []byte) ([]byte, error) {
 		return nil, err
 	}
 
-	ota.Type = ota.Parent.Type
-	ota.Hasher = plumbing.NewHasher(ota.Type, int64(len(patched)))
-	if _, err := ota.Write(patched); err != nil {
-		return nil, err
+	if ota.SHA1 == plumbing.ZeroHash {
+		ota.Type = ota.Parent.Type
+		sha1, err := getSHA1(ota.Type, patched)
+		if err != nil {
+			return nil, err
+		}
+
+		ota.SHA1 = sha1
+		ota.Length = int64(len(patched))
 	}
-	ota.SHA1 = ota.Sum()
-	ota.Length = int64(len(patched))
 
 	return patched, nil
 }
 
-type objectInfo struct {
-	plumbing.Hasher
+func getSHA1(t plumbing.ObjectType, data []byte) (plumbing.Hash, error) {
+	hasher := plumbing.NewHasher(t, int64(len(data)))
+	if _, err := hasher.Write(data); err != nil {
+		return plumbing.ZeroHash, err
+	}
+
+	return hasher.Sum(), nil
+}
 
-	Offset       int64
-	Length       int64
-	HeaderLength int64
-	PackSize     int64
-	Type         plumbing.ObjectType
-	DiskType     plumbing.ObjectType
+type objectInfo struct {
+	Offset   int64
+	Length   int64
+	Type     plumbing.ObjectType
+	DiskType plumbing.ObjectType
 
 	Crc32 uint32
 
 	Parent   *objectInfo
 	Children []*objectInfo
 	SHA1     plumbing.Hash
-
-	Content []byte
 }
 
 func newBaseObject(offset, length int64, t plumbing.ObjectType) *objectInfo {
@@ -473,29 +468,18 @@ func newDeltaObject(
 	t plumbing.ObjectType,
 	parent *objectInfo,
 ) *objectInfo {
-	children := make([]*objectInfo, 0)
-
 	obj := &objectInfo{
-		Hasher:   plumbing.NewHasher(t, length),
 		Offset:   offset,
 		Length:   length,
-		PackSize: 0,
 		Type:     t,
 		DiskType: t,
 		Crc32:    0,
 		Parent:   parent,
-		Children: children,
 	}
 
 	return obj
 }
 
-func (o *objectInfo) Write(b []byte) (int, error) {
-	o.Content = make([]byte, len(b))
-	copy(o.Content, b)
-	return o.Hasher.Write(b)
-}
-
 func (o *objectInfo) IsDelta() bool {
 	return o.Type.IsDelta()
 }