cargo: don't fail unpacking on duplicate files (#38557)

Turns out that crates.io sometimes has duplicate files in their `tar.gz`
archives.

    $ wget 'https://crates.io/api/v1/crates/proc/0.1.4/download' -O proc-0.1.4.tar.gz
    $ tar -ztvf  proc-0.1.4.tar.gz
    -rw-r--r--  0 1000   1000       18 Aug 14  2015 proc-0.1.4/.gitignore
    -rw-r--r--  0 1000   1000     1107 Aug 21  2015 proc-0.1.4/.travis.yml
    -rw-r--r--  0 1000   1000      304 Aug 29  2015 proc-0.1.4/Cargo.toml
    -rw-r--r--  0 1000   1000    10847 Aug 21  2015 proc-0.1.4/LICENSE-APACHE
    -rw-r--r--  0 1000   1000     1071 Aug 21  2015 proc-0.1.4/LICENSE-MIT
    -rw-r--r--  0 1000   1000     1149 Aug 29  2015 proc-0.1.4/README.md
    -rw-r--r--  0 1000   1000       22 Aug 29  2015 proc-0.1.4/src/lib.rs
    -rw-r--r--  0 1000   1000      304 Aug 29  2015 proc-0.1.4/Cargo.toml

There are two `Cargo.toml` in there.

cmd/gitserver/server/vcs_syncer_rust_packages.go

@@ -91,7 +91,8 @@ func (s *rustDependencySource) Download(ctx context.Context, dir string, dep rep
 func unpackRustPackage(pkg []byte, workDir string) error {
 	r := bytes.NewReader(pkg)
 	opts := unpack.Opts{
-		SkipInvalid: true,
+		SkipInvalid:    true,
+		SkipDuplicates: true,
 		Filter: func(path string, file fs.FileInfo) bool {
 			size := file.Size()
 

internal/unpack/unpack.go

@@ -34,6 +34,11 @@ type Opts struct {
 	// the whole unpack.
 	SkipInvalid bool
 
+	// SkipDuplicates makes unpacking skip any files that couldn't be extracted
+	// because of os.FileExist errors. In practice, this means the first file
+	// wins if the tar contains two or more entries with the same filename.
+	SkipDuplicates bool
+
 	// Filter filters out files that do not match the given predicate.
 	Filter func(path string, file fs.FileInfo) bool
 }
@@ -62,6 +67,9 @@ func Zip(r io.ReaderAt, size int64, dir string, opt Opts) error {
 
 		err = extractZipFile(f, dir)
 		if err != nil {
+			if opt.SkipDuplicates && errors.Is(err, os.ErrExist) {
+				continue
+			}
 			return err
 		}
 	}
@@ -135,6 +143,9 @@ func Tar(r io.Reader, dir string, opt Opts) error {
 
 		err = extractTarFile(tr, header, dir)
 		if err != nil {
+			if opt.SkipDuplicates && errors.Is(err, os.ErrExist) {
+				continue
+			}
 			return err
 		}
 	}

internal/unpack/unpack_test.go

@@ -11,6 +11,7 @@ import (
 	"os"
 	"path"
 	"path/filepath"
+	"strings"
 	"testing"
 	"time"
 
@@ -46,11 +47,12 @@ func TestUnpack(t *testing.T) {
 
 	type testCase struct {
 		packer
-		name string
-		opts Opts
-		in   []*fileInfo
-		out  []*fileInfo
-		err  string
+		name        string
+		opts        Opts
+		in          []*fileInfo
+		out         []*fileInfo
+		err         string
+		errContains string
 	}
 
 	var testCases []testCase
@@ -161,6 +163,30 @@ func TestUnpack(t *testing.T) {
 					{path: "dir/file4", contents: "x", mode: 0600, size: 1},
 				},
 			},
+			{
+				packer: p,
+				name:   "duplicates",
+				in: []*fileInfo{
+					{path: "bar", contents: "bar", mode: 0655},
+					{path: "bar", contents: "bar", mode: 0655},
+				},
+				errContains: "/bar: file exists",
+				out: []*fileInfo{
+					{path: "bar", contents: "bar", mode: 0655, size: 3},
+				},
+			},
+			{
+				packer: p,
+				name:   "skip-duplicates",
+				opts:   Opts{SkipDuplicates: true},
+				in: []*fileInfo{
+					{path: "bar", contents: "bar", mode: 0655},
+					{path: "bar", contents: "bar", mode: 0655},
+				},
+				out: []*fileInfo{
+					{path: "bar", contents: "bar", mode: 0655, size: 3},
+				},
+			},
 		}...)
 	}
 
@@ -174,7 +200,7 @@ func TestUnpack(t *testing.T) {
 				tc.opts,
 			)
 
-			assertError(t, err, tc.err)
+			assertError(t, err, tc.err, tc.errContains)
 			assertUnpack(t, dir, tc.out)
 		})
 	}
@@ -249,7 +275,15 @@ func makeTar(t testing.TB, files ...*fileInfo) []byte {
 	return buf.Bytes()
 }
 
-func assertError(t testing.TB, have error, want string) {
+func assertError(t testing.TB, have error, want string, wantContains string) {
+	if want == "" && wantContains != "" {
+		haveMessage := fmt.Sprint(have)
+		if !strings.Contains(haveMessage, wantContains) {
+			t.Fatalf("error should contain %q, but doesn't: %q", wantContains, haveMessage)
+		}
+		return
+	}
+
 	if want == "" {
 		want = "<nil>"
 	}