vbatts/tar-split
1
0
Fork 0
forked from mirrors/tar-split
Code Releases Activity

tar/storage: work with raw (invalid utf8) names

Browse source 
When the entry name is not UTF-8, for example ISO-8859-1, then store the
raw bytes.
To accommodate this, we will have getters and setters for the entry's
name now. Since this most heavily affects the json marshalling, we'll
double check the sanity of the name before storing it in the JSONPacker.
This commit is contained in:
Vincent Batts 2015-09-23 15:20:09 -04:00
parent 39d06b9dc4
commit 032efafc29
3 changed files with 87 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tar/storage/packer.go
View file

@ -6,6 +6,8 @@ import (
"errors"
"io"
"path/filepath"
"github.com/vbatts/tar-split/tar/common"
)
// ErrDuplicatePath occurs when a tar archive has more than one entry for the
@ -61,7 +63,7 @@ func (jup *jsonUnpacker) Next() (*Entry, error) {
// check for dup name
if e.Type == FileType {
cName := filepath.Clean(e.Name)
cName := filepath.Clean(e.GetName())
if _, ok := jup.seen[cName]; ok {
return nil, ErrDuplicatePath
}
@ -93,9 +95,17 @@ type jsonPacker struct {
type seenNames map[string]struct{}
func (jp *jsonPacker) AddEntry(e Entry) (int, error) {
// if Name is not valid utf8, switch it to raw first.
if e.Name != "" {
if !common.IsValidUtf8String(e.Name) {
e.NameRaw = []byte(e.Name)
e.Name = ""
}
}
// check early for dup name
if e.Type == FileType {
cName := filepath.Clean(e.Name)
cName := filepath.Clean(e.GetName())
if _, ok := jp.seen[cName]; ok {
return -1, ErrDuplicatePath
}