Merge pull request #898 from jfontan/feature/new-packfile-parser

Feature/new packfile parser

3 files changed, 275 insertions, 2 deletions

diff --git a/plumbing/format/idxfile/idxfile.go b/plumbing/format/idxfile/idxfile.go
index b196608..f8debb1 100644
--- a/plumbing/format/idxfile/idxfile.go
+++ b/plumbing/format/idxfile/idxfile.go
@@ -28,6 +28,8 @@ type Index interface {
 	FindOffset(h plumbing.Hash) (int64, error)
 	// FindCRC32 finds the CRC32 of the object with the given hash.
 	FindCRC32(h plumbing.Hash) (uint32, error)
+	// FindHash finds the hash for the object with the given offset.
+	FindHash(o int64) (plumbing.Hash, error)
 	// Count returns the number of entries in the index.
 	Count() (int64, error)
 	// Entries returns an iterator to retrieve all index entries.
@@ -48,6 +50,8 @@ type MemoryIndex struct {
 	Offset64         []byte
 	PackfileChecksum [20]byte
 	IdxChecksum      [20]byte
+
+	offsetHash map[int64]plumbing.Hash
 }
 
 var _ Index = (*MemoryIndex)(nil)
@@ -72,7 +76,7 @@ func (idx *MemoryIndex) findHashIndex(h plumbing.Hash) int {
 	low := uint64(0)
 	for {
 		mid := (low + high) >> 1
-		offset := mid + (mid << 2)
+		offset := mid * objectIDLength
 
 		cmp := bytes.Compare(h[:], data[offset:offset+objectIDLength])
 		if cmp < 0 {
@@ -83,7 +87,7 @@ func (idx *MemoryIndex) findHashIndex(h plumbing.Hash) int {
 			low = mid + 1
 		}
 
-		if low < high {
+		if low > high {
 			break
 		}
 	}
@@ -149,6 +153,53 @@ func (idx *MemoryIndex) getCrc32(firstLevel, secondLevel int) (uint32, error) {
 	return binary.ReadUint32(buf)
 }
 
+// FindHash implements the Index interface.
+func (idx *MemoryIndex) FindHash(o int64) (plumbing.Hash, error) {
+	// Lazily generate the reverse offset/hash map if required.
+	if idx.offsetHash == nil {
+		err := idx.genOffsetHash()
+		if err != nil {
+			return plumbing.ZeroHash, nil
+		}
+	}
+
+	hash, ok := idx.offsetHash[o]
+	if !ok {
+		return plumbing.ZeroHash, plumbing.ErrObjectNotFound
+	}
+
+	return hash, nil
+}
+
+// genOffsetHash generates the offset/hash mapping for reverse search.
+func (idx *MemoryIndex) genOffsetHash() error {
+	count, err := idx.Count()
+	if err != nil {
+		return err
+	}
+
+	idx.offsetHash = make(map[int64]plumbing.Hash, count)
+
+	iter, err := idx.Entries()
+	if err != nil {
+		return err
+	}
+
+	var entry *Entry
+	for err != nil {
+		entry, err = iter.Next()
+		if err == nil {
+			idx.offsetHash[int64(entry.Offset)] = entry.Hash
+		}
+	}
+
+	if err == io.EOF {
+		return nil
+	}
+
+	return err
+}
+
 // Count implements the Index interface.
 func (idx *MemoryIndex) Count() (int64, error) {
 	return int64(idx.Fanout[fanout-1]), nil
diff --git a/plumbing/format/idxfile/writer.go b/plumbing/format/idxfile/writer.go
new file mode 100644
index 0000000..efcdcc6
--- /dev/null
+++ b/plumbing/format/idxfile/writer.go
@@ -0,0 +1,177 @@
+package idxfile
+
+import (
+	"bytes"
+	"fmt"
+	"math"
+	"sort"
+	"sync"
+
+	"gopkg.in/src-d/go-git.v4/plumbing"
+	"gopkg.in/src-d/go-git.v4/utils/binary"
+)
+
+// objects implements sort.Interface and uses hash as sorting key.
+type objects []Entry
+
+// Writer implements a packfile Observer interface and is used to generate
+// indexes.
+type Writer struct {
+	m sync.Mutex
+
+	count    uint32
+	checksum plumbing.Hash
+	objects  objects
+	offset64 uint32
+	finished bool
+	index    *MemoryIndex
+}
+
+// Index returns a previously created MemoryIndex or creates a new one if
+// needed.
+func (w *Writer) Index() (*MemoryIndex, error) {
+	w.m.Lock()
+	defer w.m.Unlock()
+
+	if w.index == nil {
+		return w.createIndex()
+	}
+
+	return w.index, nil
+}
+
+// Add appends new object data.
+func (w *Writer) Add(h plumbing.Hash, pos uint64, crc uint32) {
+	w.m.Lock()
+	defer w.m.Unlock()
+
+	w.objects = append(w.objects, Entry{h, crc, pos})
+}
+
+func (w *Writer) Finished() bool {
+	return w.finished
+}
+
+// OnHeader implements packfile.Observer interface.
+func (w *Writer) OnHeader(count uint32) error {
+	w.count = count
+	w.objects = make(objects, 0, count)
+	return nil
+}
+
+// OnInflatedObjectHeader implements packfile.Observer interface.
+func (w *Writer) OnInflatedObjectHeader(t plumbing.ObjectType, objSize int64, pos int64) error {
+	return nil
+}
+
+// OnInflatedObjectContent implements packfile.Observer interface.
+func (w *Writer) OnInflatedObjectContent(h plumbing.Hash, pos int64, crc uint32) error {
+	w.Add(h, uint64(pos), crc)
+	return nil
+}
+
+// OnFooter implements packfile.Observer interface.
+func (w *Writer) OnFooter(h plumbing.Hash) error {
+	w.checksum = h
+	w.finished = true
+	_, err := w.createIndex()
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// creatIndex returns a filled MemoryIndex with the information filled by
+// the observer callbacks.
+func (w *Writer) createIndex() (*MemoryIndex, error) {
+	if !w.finished {
+		return nil, fmt.Errorf("the index still hasn't finished building")
+	}
+
+	idx := new(MemoryIndex)
+	w.index = idx
+
+	sort.Sort(w.objects)
+
+	// unmap all fans by default
+	for i := range idx.FanoutMapping {
+		idx.FanoutMapping[i] = noMapping
+	}
+
+	buf := new(bytes.Buffer)
+
+	last := -1
+	bucket := -1
+	for i, o := range w.objects {
+		fan := o.Hash[0]
+
+		// fill the gaps between fans
+		for j := last + 1; j < int(fan); j++ {
+			idx.Fanout[j] = uint32(i)
+		}
+
+		// update the number of objects for this position
+		idx.Fanout[fan] = uint32(i + 1)
+
+		// we move from one bucket to another, update counters and allocate
+		// memory
+		if last != int(fan) {
+			bucket++
+			idx.FanoutMapping[fan] = bucket
+			last = int(fan)
+
+			idx.Names = append(idx.Names, make([]byte, 0))
+			idx.Offset32 = append(idx.Offset32, make([]byte, 0))
+			idx.Crc32 = append(idx.Crc32, make([]byte, 0))
+		}
+
+		idx.Names[bucket] = append(idx.Names[bucket], o.Hash[:]...)
+
+		offset := o.Offset
+		if offset > math.MaxInt32 {
+			offset = w.addOffset64(offset)
+		}
+
+		buf.Truncate(0)
+		binary.WriteUint32(buf, uint32(offset))
+		idx.Offset32[bucket] = append(idx.Offset32[bucket], buf.Bytes()...)
+
+		buf.Truncate(0)
+		binary.WriteUint32(buf, uint32(o.CRC32))
+		idx.Crc32[bucket] = append(idx.Crc32[bucket], buf.Bytes()...)
+	}
+
+	for j := last + 1; j < 256; j++ {
+		idx.Fanout[j] = uint32(len(w.objects))
+	}
+
+	idx.Version = VersionSupported
+	idx.PackfileChecksum = w.checksum
+
+	return idx, nil
+}
+
+func (w *Writer) addOffset64(pos uint64) uint64 {
+	buf := new(bytes.Buffer)
+	binary.WriteUint64(buf, pos)
+	w.index.Offset64 = append(w.index.Offset64, buf.Bytes()...)
+
+	index := uint64(w.offset64 | (1 << 31))
+	w.offset64++
+
+	return index
+}
+
+func (o objects) Len() int {
+	return len(o)
+}
+
+func (o objects) Less(i int, j int) bool {
+	cmp := bytes.Compare(o[i].Hash[:], o[j].Hash[:])
+	return cmp < 0
+}
+
+func (o objects) Swap(i int, j int) {
+	o[i], o[j] = o[j], o[i]
+}
diff --git a/plumbing/format/idxfile/writer_test.go b/plumbing/format/idxfile/writer_test.go
new file mode 100644
index 0000000..51273a3
--- /dev/null
+++ b/plumbing/format/idxfile/writer_test.go
@@ -0,0 +1,45 @@
+package idxfile_test
+
+import (
+	"bytes"
+	"io/ioutil"
+
+	"gopkg.in/src-d/go-git.v4/plumbing/format/idxfile"
+	"gopkg.in/src-d/go-git.v4/plumbing/format/packfile"
+
+	. "gopkg.in/check.v1"
+	"gopkg.in/src-d/go-git-fixtures.v3"
+)
+
+type IndexSuite struct {
+	fixtures.Suite
+}
+
+var _ = Suite(&IndexSuite{})
+
+func (s *IndexSuite) TestIndexWriter(c *C) {
+	f := fixtures.Basic().One()
+	scanner := packfile.NewScanner(f.Packfile())
+
+	obs := new(idxfile.Writer)
+	parser := packfile.NewParser(scanner, obs)
+
+	_, err := parser.Parse()
+	c.Assert(err, IsNil)
+
+	idx, err := obs.Index()
+	c.Assert(err, IsNil)
+
+	idxFile := f.Idx()
+	expected, err := ioutil.ReadAll(idxFile)
+	c.Assert(err, IsNil)
+	idxFile.Close()
+
+	buf := new(bytes.Buffer)
+	encoder := idxfile.NewEncoder(buf)
+	n, err := encoder.Encode(idx)
+	c.Assert(err, IsNil)
+	c.Assert(n, Equals, len(expected))
+
+	c.Assert(buf.Bytes(), DeepEquals, expected)
+}