add a Unique function (#203)

* add a Deduplicate function

* rename Deduplicate to Unique

Author: marten-seemann

go.mod

@@ -8,6 +8,7 @@ require (
 	github.com/multiformats/go-multihash v0.0.14
 	github.com/multiformats/go-varint v0.0.6
 	github.com/stretchr/testify v1.7.0
+	golang.org/x/exp v0.0.0-20230626212559-97b1e661b5df
 )
 
 require (

go.sum

@@ -32,6 +32,8 @@ golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACk
 golang.org/x/crypto v0.0.0-20190611184440-5c40567a22f8/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.1.0 h1:MDRAIl0xIo9Io2xV565hzXHw3zVseKrJKodhohM5CjU=
 golang.org/x/crypto v0.1.0/go.mod h1:RecgLatLF4+eUMCP1PoPZQb+cVrJcOPbHkTkbkB9sbw=
+golang.org/x/exp v0.0.0-20230626212559-97b1e661b5df h1:UA2aFVmmsIlefxMk29Dp2juaUSth8Pyn3Tq5Y5mJGME=
+golang.org/x/exp v0.0.0-20230626212559-97b1e661b5df/go.mod h1:FXUEEKJgO7OQYeo8N01OfiKP8RXMtf6e8aTskBGqWdc=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=

multiaddr.go

@@ -6,6 +6,8 @@ import (
 	"fmt"
 	"log"
 	"strings"
+
+	"golang.org/x/exp/slices"
 )
 
 // multiaddr is the data structure representing a Multiaddr
@@ -210,3 +212,24 @@ func Contains(addrs []Multiaddr, addr Multiaddr) bool {
 	}
 	return false
 }
+
+// Unique deduplicates addresses in place, leave only unique addresses.
+// It doesn't allocate.
+func Unique(addrs []Multiaddr) []Multiaddr {
+	if len(addrs) == 0 {
+		return addrs
+	}
+	// Use the new slices package here, as the sort function doesn't allocate (sort.Slice does).
+	slices.SortFunc(addrs, func(a, b Multiaddr) bool { return bytes.Compare(a.Bytes(), b.Bytes()) < 0 })
+	idx := 1
+	for i := 1; i < len(addrs); i++ {
+		if !addrs[i-1].Equal(addrs[i]) {
+			addrs[idx] = addrs[i]
+			idx++
+		}
+	}
+	for i := idx; i < len(addrs); i++ {
+		addrs[i] = nil
+	}
+	return addrs[:idx]
+}

multiaddr_test.go

@@ -3,6 +3,9 @@ package multiaddr
 import (
 	"bytes"
 	"encoding/hex"
+	"fmt"
+	"math"
+	"math/rand"
 	"testing"
 
 	"github.com/ipfs/go-cid"
@@ -785,3 +788,50 @@ func TestContains(t *testing.T) {
 	require.False(t, Contains(addrs, newMultiaddr(t, "/ip4/4.3.2.1/udp/1234/utp")))
 	require.False(t, Contains(nil, a1))
 }
+
+func TestUniqueAddrs(t *testing.T) {
+	tcpAddr := StringCast("/ip4/127.0.0.1/tcp/1234")
+	quicAddr := StringCast("/ip4/127.0.0.1/udp/1234/quic-v1")
+	wsAddr := StringCast("/ip4/127.0.0.1/tcp/1234/ws")
+
+	type testcase struct {
+		in, out []Multiaddr
+	}
+
+	for i, tc := range []testcase{
+		{in: nil, out: nil},
+		{in: []Multiaddr{tcpAddr}, out: []Multiaddr{tcpAddr}},
+		{in: []Multiaddr{tcpAddr, tcpAddr, tcpAddr}, out: []Multiaddr{tcpAddr}},
+		{in: []Multiaddr{tcpAddr, quicAddr, tcpAddr}, out: []Multiaddr{tcpAddr, quicAddr}},
+		{in: []Multiaddr{tcpAddr, quicAddr, wsAddr}, out: []Multiaddr{tcpAddr, quicAddr, wsAddr}},
+	} {
+		tc := tc
+		t.Run(fmt.Sprintf("test %d", i), func(t *testing.T) {
+			deduped := Unique(tc.in)
+			for _, a := range tc.out {
+				require.Contains(t, deduped, a)
+			}
+		})
+	}
+}
+
+func BenchmarkUniqueAddrs(b *testing.B) {
+	b.ReportAllocs()
+	var addrs []Multiaddr
+	r := rand.New(rand.NewSource(1234))
+	for i := 0; i < 100; i++ {
+		tcpAddr := StringCast(fmt.Sprintf("/ip4/127.0.0.1/tcp/%d", r.Intn(math.MaxUint16)))
+		quicAddr := StringCast(fmt.Sprintf("/ip4/127.0.0.1/udp/%d/quic-v1", r.Intn(math.MaxUint16)))
+		wsAddr := StringCast(fmt.Sprintf("/ip4/127.0.0.1/tcp/%d/ws", r.Intn(math.MaxUint16)))
+		addrs = append(addrs, tcpAddr, tcpAddr, quicAddr, quicAddr, wsAddr)
+	}
+	for _, sz := range []int{10, 20, 30, 50, 100} {
+		b.Run(fmt.Sprintf("%d", sz), func(b *testing.B) {
+			items := make([]Multiaddr, sz)
+			for i := 0; i < b.N; i++ {
+				copy(items, addrs[:sz])
+				Unique(items)
+			}
+		})
+	}
+}