*: objectid -> object/id

4 files changed, 447 insertions, 0 deletions

diff --git a/object/id/algorithms.go b/object/id/algorithms.go
new file mode 100644
index 00000000..404d3bbf
--- /dev/null
+++ b/object/id/algorithms.go
@@ -0,0 +1,140 @@
+package objectid
+
+import (
+	"crypto/sha1" //#nosec gosec
+	"crypto/sha256"
+	"hash"
+)
+
+// maxObjectIDSize MUST be >= the largest supported algorithm size.
+const maxObjectIDSize = sha256.Size
+
+// Algorithm identifies the hash algorithm used for Git object IDs.
+type Algorithm uint8
+
+const (
+	AlgorithmUnknown Algorithm = iota
+	AlgorithmSHA1
+	AlgorithmSHA256
+)
+
+type algorithmDetails struct {
+	name       string
+	size       int
+	packHashID uint32
+	sum        func([]byte) ObjectID
+	new        func() hash.Hash
+}
+
+//nolint:gochecknoglobals
+var algorithmTable = [...]algorithmDetails{
+	AlgorithmUnknown: {},
+	AlgorithmSHA1: {
+		name:       "sha1",
+		size:       sha1.Size,
+		packHashID: 1,
+		sum: func(data []byte) ObjectID {
+			sum := sha1.Sum(data) //#nosec G401
+
+			var id ObjectID
+			copy(id.data[:], sum[:])
+			id.algo = AlgorithmSHA1
+
+			return id
+		},
+		new: sha1.New,
+	},
+	AlgorithmSHA256: {
+		name:       "sha256",
+		size:       sha256.Size,
+		packHashID: 2,
+		sum: func(data []byte) ObjectID {
+			sum := sha256.Sum256(data)
+
+			var id ObjectID
+			copy(id.data[:], sum[:])
+			id.algo = AlgorithmSHA256
+
+			return id
+		},
+		new: sha256.New,
+	},
+}
+
+var (
+	//nolint:gochecknoglobals
+	algorithmByName = map[string]Algorithm{}
+	//nolint:gochecknoglobals
+	supportedAlgorithms []Algorithm
+)
+
+func init() { //nolint:gochecknoinits
+	for algo := Algorithm(0); int(algo) < len(algorithmTable); algo++ {
+		info := algorithmTable[algo]
+		if info.name == "" {
+			continue
+		}
+
+		algorithmByName[info.name] = algo
+		supportedAlgorithms = append(supportedAlgorithms, algo)
+	}
+}
+
+// SupportedAlgorithms returns all object ID algorithms supported by furgit.
+// Do not mutate.
+func SupportedAlgorithms() []Algorithm {
+	return supportedAlgorithms
+}
+
+// ParseAlgorithm parses a canonical algorithm name (e.g. "sha1", "sha256").
+func ParseAlgorithm(s string) (Algorithm, bool) {
+	algo, ok := algorithmByName[s]
+
+	return algo, ok
+}
+
+// Size returns the hash size in bytes.
+func (algo Algorithm) Size() int {
+	return algo.info().size
+}
+
+// String returns the canonical algorithm name.
+func (algo Algorithm) String() string {
+	inf := algo.info()
+	if inf.name == "" {
+		return "unknown"
+	}
+
+	return inf.name
+}
+
+// HexLen returns the encoded hexadecimal length.
+func (algo Algorithm) HexLen() int {
+	return algo.Size() * 2
+}
+
+// PackHashID returns the Git pack/rev hash-id encoding for this algorithm.
+//
+// Unknown algorithms return 0.
+func (algo Algorithm) PackHashID() uint32 {
+	return algo.info().packHashID
+}
+
+// Sum computes an object ID from raw data using the selected algorithm.
+func (algo Algorithm) Sum(data []byte) ObjectID {
+	return algo.info().sum(data)
+}
+
+// New returns a new hash.Hash for this algorithm.
+func (algo Algorithm) New() (hash.Hash, error) {
+	newFn := algo.info().new
+	if newFn == nil {
+		return nil, ErrInvalidAlgorithm
+	}
+
+	return newFn(), nil
+}
+
+func (algo Algorithm) info() algorithmDetails {
+	return algorithmTable[algo]
+}
diff --git a/object/id/errors.go b/object/id/errors.go
new file mode 100644
index 00000000..8e604c44
--- /dev/null
+++ b/object/id/errors.go
@@ -0,0 +1,10 @@
+package objectid
+
+import "errors"
+
+var (
+	// ErrInvalidAlgorithm indicates an unsupported object ID algorithm.
+	ErrInvalidAlgorithm = errors.New("objectid: invalid algorithm")
+	// ErrInvalidObjectID indicates malformed object ID data.
+	ErrInvalidObjectID = errors.New("objectid: invalid object id")
+)
diff --git a/object/id/objectid.go b/object/id/objectid.go
new file mode 100644
index 00000000..8eb82969
--- /dev/null
+++ b/object/id/objectid.go
@@ -0,0 +1,113 @@
+// Package objectid provides utilities around object IDs and hash algorithms.
+package objectid
+
+import (
+	//#nosec G505
+
+	"bytes"
+	"encoding/hex"
+	"fmt"
+)
+
+// ObjectID represents a Git object ID.
+//
+//nolint:recvcheck
+type ObjectID struct {
+	algo Algorithm
+	data [maxObjectIDSize]byte
+}
+
+// Algorithm returns the object ID's hash algorithm.
+func (id ObjectID) Algorithm() Algorithm {
+	return id.algo
+}
+
+// Size returns the object ID size in bytes.
+func (id ObjectID) Size() int {
+	return id.algo.Size()
+}
+
+// String returns the canonical hex representation.
+func (id ObjectID) String() string {
+	size := id.Size()
+
+	return hex.EncodeToString(id.data[:size])
+}
+
+// Bytes returns a copy of the object ID bytes.
+func (id ObjectID) Bytes() []byte {
+	size := id.Size()
+
+	return append([]byte(nil), id.data[:size]...)
+}
+
+// RawBytes returns a direct byte slice view of the object ID bytes.
+//
+// The returned slice aliases the object ID's internal storage. Callers MUST
+// treat it as read-only and MUST NOT modify its contents.
+//
+// Use Bytes when an independent copy is required.
+func (id *ObjectID) RawBytes() []byte {
+	size := id.Size()
+
+	return id.data[:size:size]
+}
+
+// Compare lexicographically compares two object IDs by their canonical byte
+// representation.
+func Compare(left, right ObjectID) int {
+	return bytes.Compare(left.RawBytes(), right.RawBytes())
+}
+
+// Zero returns the all-zero object ID for the specified algorithm.
+func Zero(algo Algorithm) ObjectID {
+	id, err := FromBytes(algo, make([]byte, algo.Size()))
+	if err != nil {
+		panic(err)
+	}
+
+	return id
+}
+
+// ParseHex parses an object ID from hex for the specified algorithm.
+func ParseHex(algo Algorithm, s string) (ObjectID, error) {
+	var id ObjectID
+	if algo.Size() == 0 {
+		return id, ErrInvalidAlgorithm
+	}
+
+	if len(s)%2 != 0 {
+		return id, fmt.Errorf("%w: odd hex length %d", ErrInvalidObjectID, len(s))
+	}
+
+	if len(s) != algo.HexLen() {
+		return id, fmt.Errorf("%w: got %d chars, expected %d", ErrInvalidObjectID, len(s), algo.HexLen())
+	}
+
+	decoded, err := hex.DecodeString(s)
+	if err != nil {
+		return id, fmt.Errorf("%w: decode: %w", ErrInvalidObjectID, err)
+	}
+
+	copy(id.data[:], decoded)
+	id.algo = algo
+
+	return id, nil
+}
+
+// FromBytes builds an object ID from raw bytes for the specified algorithm.
+func FromBytes(algo Algorithm, b []byte) (ObjectID, error) {
+	var id ObjectID
+	if algo.Size() == 0 {
+		return id, ErrInvalidAlgorithm
+	}
+
+	if len(b) != algo.Size() {
+		return id, fmt.Errorf("%w: got %d bytes, expected %d", ErrInvalidObjectID, len(b), algo.Size())
+	}
+
+	copy(id.data[:], b)
+	id.algo = algo
+
+	return id, nil
+}
diff --git a/object/id/objectid_test.go b/object/id/objectid_test.go
new file mode 100644
index 00000000..2559be0a
--- /dev/null
+++ b/object/id/objectid_test.go
@@ -0,0 +1,184 @@
+package objectid_test
+
+import (
+	"bytes"
+	"strings"
+	"testing"
+
+	objectid "codeberg.org/lindenii/furgit/object/id"
+)
+
+func TestParseAlgorithm(t *testing.T) {
+	t.Parallel()
+
+	algo, ok := objectid.ParseAlgorithm("sha1")
+	if !ok || algo != objectid.AlgorithmSHA1 {
+		t.Fatalf("ParseAlgorithm(sha1) = (%v,%v)", algo, ok)
+	}
+
+	algo, ok = objectid.ParseAlgorithm("sha256")
+	if !ok || algo != objectid.AlgorithmSHA256 {
+		t.Fatalf("ParseAlgorithm(sha256) = (%v,%v)", algo, ok)
+	}
+
+	if _, ok := objectid.ParseAlgorithm("md5"); ok {
+		t.Fatalf("ParseAlgorithm(md5) should fail")
+	}
+}
+
+func TestParseHexRoundtrip(t *testing.T) {
+	t.Parallel()
+
+	for _, algo := range objectid.SupportedAlgorithms() {
+		t.Run(algo.String(), func(t *testing.T) {
+			t.Parallel()
+
+			hex := strings.Repeat("01", algo.Size())
+
+			id, err := objectid.ParseHex(algo, hex)
+			if err != nil {
+				t.Fatalf("ParseHex failed: %v", err)
+			}
+
+			if got := id.String(); got != hex {
+				t.Fatalf("String() = %q, want %q", got, hex)
+			}
+
+			if got := id.Size(); got != algo.Size() {
+				t.Fatalf("Size() = %d, want %d", got, algo.Size())
+			}
+
+			raw := id.Bytes()
+			if len(raw) != algo.Size() {
+				t.Fatalf("Bytes len = %d, want %d", len(raw), algo.Size())
+			}
+
+			id2, err := objectid.FromBytes(algo, raw)
+			if err != nil {
+				t.Fatalf("FromBytes failed: %v", err)
+			}
+
+			if id2.String() != hex {
+				t.Fatalf("FromBytes roundtrip = %q, want %q", id2.String(), hex)
+			}
+		})
+	}
+}
+
+func TestParseHexErrors(t *testing.T) {
+	t.Parallel()
+
+	t.Run("unknown algo", func(t *testing.T) {
+		t.Parallel()
+
+		_, err := objectid.ParseHex(objectid.AlgorithmUnknown, "00")
+		if err == nil {
+			t.Fatalf("expected ParseHex error")
+		}
+	})
+
+	for _, algo := range objectid.SupportedAlgorithms() {
+		t.Run(algo.String(), func(t *testing.T) {
+			t.Parallel()
+
+			_, err := objectid.ParseHex(algo, strings.Repeat("0", algo.HexLen()-1))
+			if err == nil {
+				t.Fatalf("expected ParseHex odd-len error")
+			}
+
+			_, err = objectid.ParseHex(algo, strings.Repeat("0", algo.HexLen()-2))
+			if err == nil {
+				t.Fatalf("expected ParseHex wrong-len error")
+			}
+
+			_, err = objectid.ParseHex(algo, "z"+strings.Repeat("0", algo.HexLen()-1))
+			if err == nil {
+				t.Fatalf("expected ParseHex invalid-hex error")
+			}
+		})
+	}
+}
+
+func TestFromBytesErrors(t *testing.T) {
+	t.Parallel()
+
+	_, err := objectid.FromBytes(objectid.AlgorithmUnknown, []byte{1, 2})
+	if err == nil {
+		t.Fatalf("expected FromBytes unknown algo error")
+	}
+
+	for _, algo := range objectid.SupportedAlgorithms() {
+		_, err = objectid.FromBytes(algo, []byte{1, 2})
+		if err == nil {
+			t.Fatalf("expected FromBytes wrong size error")
+		}
+	}
+}
+
+func TestBytesReturnsCopy(t *testing.T) {
+	t.Parallel()
+
+	for _, algo := range objectid.SupportedAlgorithms() {
+		id, err := objectid.ParseHex(algo, strings.Repeat("01", algo.Size()))
+		if err != nil {
+			t.Fatalf("ParseHex failed: %v", err)
+		}
+
+		b1 := id.Bytes()
+
+		b2 := id.Bytes()
+		if !bytes.Equal(b1, b2) {
+			t.Fatalf("Bytes mismatch")
+		}
+
+		b1[0] ^= 0xff
+		if bytes.Equal(b1, b2) {
+			t.Fatalf("Bytes should return independent copies")
+		}
+	}
+}
+
+func TestRawBytesAliasesStorage(t *testing.T) {
+	t.Parallel()
+
+	for _, algo := range objectid.SupportedAlgorithms() {
+		id, err := objectid.ParseHex(algo, strings.Repeat("01", algo.Size()))
+		if err != nil {
+			t.Fatalf("ParseHex failed: %v", err)
+		}
+
+		b := id.RawBytes()
+		if len(b) != id.Size() {
+			t.Fatalf("RawBytes len = %d, want %d", len(b), id.Size())
+		}
+
+		if cap(b) != len(b) {
+			t.Fatalf("RawBytes cap = %d, want %d", cap(b), len(b))
+		}
+
+		orig := id.String()
+		b[0] ^= 0xff
+
+		if id.String() == orig {
+			t.Fatalf("RawBytes should alias object ID storage")
+		}
+	}
+}
+
+func TestAlgorithmSum(t *testing.T) {
+	t.Parallel()
+
+	id1 := objectid.AlgorithmSHA1.Sum([]byte("hello"))
+	if id1.Algorithm() != objectid.AlgorithmSHA1 || id1.Size() != objectid.AlgorithmSHA1.Size() {
+		t.Fatalf("sha1 sum produced invalid object id")
+	}
+
+	id2 := objectid.AlgorithmSHA256.Sum([]byte("hello"))
+	if id2.Algorithm() != objectid.AlgorithmSHA256 || id2.Size() != objectid.AlgorithmSHA256.Size() {
+		t.Fatalf("sha256 sum produced invalid object id")
+	}
+
+	if id1.String() == id2.String() {
+		t.Fatalf("sha1 and sha256 should differ")
+	}
+}