rebase: ParseAcceptLanguage takes a long time to parse complex tags

A vulnerability was found in golang.org/x/text/language package which
could cause a denial of service. An attacker can craft an
Accept-Language header which ParseAcceptLanguage will take significant
time to parse.
Version v0.3.8 of golang.org/x/text fixes a vulnerability.

See-also: https://go.dev/issue/56152
See-also: https://bugzilla.redhat.com/CVE-2022-32149
Signed-off-by: Niels de Vos <ndevos@redhat.com>
This commit is contained in:
Niels de Vos
2022-10-17 08:49:59 +02:00
committed by mergify[bot]
parent b3837d44ce
commit e08005f402
27 changed files with 667 additions and 583 deletions

View File

@ -10,18 +10,17 @@
// and provides the user with the best experience
// (see https://blog.golang.org/matchlang).
//
//
// Matching preferred against supported languages
// # Matching preferred against supported languages
//
// A Matcher for an application that supports English, Australian English,
// Danish, and standard Mandarin can be created as follows:
//
// var matcher = language.NewMatcher([]language.Tag{
// language.English, // The first language is used as fallback.
// language.MustParse("en-AU"),
// language.Danish,
// language.Chinese,
// })
// var matcher = language.NewMatcher([]language.Tag{
// language.English, // The first language is used as fallback.
// language.MustParse("en-AU"),
// language.Danish,
// language.Chinese,
// })
//
// This list of supported languages is typically implied by the languages for
// which there exists translations of the user interface.
@ -30,14 +29,14 @@
// language tags.
// The MatchString finds best matches for such strings:
//
// handler(w http.ResponseWriter, r *http.Request) {
// lang, _ := r.Cookie("lang")
// accept := r.Header.Get("Accept-Language")
// tag, _ := language.MatchStrings(matcher, lang.String(), accept)
// handler(w http.ResponseWriter, r *http.Request) {
// lang, _ := r.Cookie("lang")
// accept := r.Header.Get("Accept-Language")
// tag, _ := language.MatchStrings(matcher, lang.String(), accept)
//
// // tag should now be used for the initialization of any
// // locale-specific service.
// }
// // tag should now be used for the initialization of any
// // locale-specific service.
// }
//
// The Matcher's Match method can be used to match Tags directly.
//
@ -48,8 +47,7 @@
// For instance, it will know that a reader of Bokmål Danish can read Norwegian
// and will know that Cantonese ("yue") is a good match for "zh-HK".
//
//
// Using match results
// # Using match results
//
// To guarantee a consistent user experience to the user it is important to
// use the same language tag for the selection of any locale-specific services.
@ -58,9 +56,9 @@
// More subtly confusing is using the wrong sorting order or casing
// algorithm for a certain language.
//
// All the packages in x/text that provide locale-specific services
// (e.g. collate, cases) should be initialized with the tag that was
// obtained at the start of an interaction with the user.
// All the packages in x/text that provide locale-specific services
// (e.g. collate, cases) should be initialized with the tag that was
// obtained at the start of an interaction with the user.
//
// Note that Tag that is returned by Match and MatchString may differ from any
// of the supported languages, as it may contain carried over settings from
@ -70,8 +68,7 @@
// Match and MatchString both return the index of the matched supported tag
// to simplify associating such data with the matched tag.
//
//
// Canonicalization
// # Canonicalization
//
// If one uses the Matcher to compare languages one does not need to
// worry about canonicalization.
@ -92,10 +89,9 @@
// equivalence relations. The CanonType type can be used to alter the
// canonicalization form.
//
// References
// # References
//
// BCP 47 - Tags for Identifying Languages http://tools.ietf.org/html/bcp47
//
package language // import "golang.org/x/text/language"
// TODO: explanation on how to match languages for your own locale-specific

View File

@ -545,7 +545,7 @@ type bestMatch struct {
// match as the preferred match.
//
// If pin is true and have and tag are a strong match, it will henceforth only
// consider matches for this language. This corresponds to the nothing that most
// consider matches for this language. This corresponds to the idea that most
// users have a strong preference for the first defined language. A user can
// still prefer a second language over a dialect of the preferred language by
// explicitly specifying dialects, e.g. "en, nl, en-GB". In this case pin should

View File

@ -147,6 +147,7 @@ func update(b *language.Builder, part ...interface{}) (err error) {
}
var errInvalidWeight = errors.New("ParseAcceptLanguage: invalid weight")
var errTagListTooLarge = errors.New("tag list exceeds max length")
// ParseAcceptLanguage parses the contents of an Accept-Language header as
// defined in http://www.ietf.org/rfc/rfc2616.txt and returns a list of Tags and
@ -164,6 +165,10 @@ func ParseAcceptLanguage(s string) (tag []Tag, q []float32, err error) {
}
}()
if strings.Count(s, "-") > 1000 {
return nil, nil, errTagListTooLarge
}
var entry string
for s != "" {
if entry, s = split(s, ','); entry == "" {

View File

@ -39,12 +39,12 @@ const (
_Hani = 57
_Hans = 59
_Hant = 60
_Qaaa = 143
_Qaai = 151
_Qabx = 192
_Zinh = 245
_Zyyy = 250
_Zzzz = 251
_Qaaa = 147
_Qaai = 155
_Qabx = 196
_Zinh = 252
_Zyyy = 257
_Zzzz = 258
)
var regionToGroups = []uint8{ // 358 elements
@ -265,9 +265,9 @@ var matchScript = []scriptIntelligibility{ // 26 elements
13: {wantLang: 0x39d, haveLang: 0x139, wantScript: 0x36, haveScript: 0x5a, distance: 0xa},
14: {wantLang: 0x3be, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5a, distance: 0xa},
15: {wantLang: 0x3fa, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5a, distance: 0xa},
16: {wantLang: 0x40c, haveLang: 0x139, wantScript: 0xcf, haveScript: 0x5a, distance: 0xa},
17: {wantLang: 0x450, haveLang: 0x139, wantScript: 0xde, haveScript: 0x5a, distance: 0xa},
18: {wantLang: 0x461, haveLang: 0x139, wantScript: 0xe1, haveScript: 0x5a, distance: 0xa},
16: {wantLang: 0x40c, haveLang: 0x139, wantScript: 0xd4, haveScript: 0x5a, distance: 0xa},
17: {wantLang: 0x450, haveLang: 0x139, wantScript: 0xe3, haveScript: 0x5a, distance: 0xa},
18: {wantLang: 0x461, haveLang: 0x139, wantScript: 0xe6, haveScript: 0x5a, distance: 0xa},
19: {wantLang: 0x46f, haveLang: 0x139, wantScript: 0x2c, haveScript: 0x5a, distance: 0xa},
20: {wantLang: 0x476, haveLang: 0x3e2, wantScript: 0x5a, haveScript: 0x20, distance: 0xa},
21: {wantLang: 0x4b4, haveLang: 0x139, wantScript: 0x5, haveScript: 0x5a, distance: 0xa},