[release-branch.go1.19] html/template: handle all JS whitespace characters

Rather than just a small set. Character class as defined by \s [0].

Thanks to Juho Nurminen of Mattermost for reporting this.

For #59721
Fixes  #59813
Fixes CVE-2023-24540

[0] https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions/Character_Classes

Change-Id: I56d4fa1ef08125b417106ee7dbfb5b0923b901ba
Reviewed-on: https://team-review.git.corp.google.com/c/golang/go-private/+/1821459
Reviewed-by: Julie Qiu <julieqiu@google.com>
Run-TryBot: Roland Shoemaker <bracewell@google.com>
Reviewed-by: Damien Neil <dneil@google.com>
Reviewed-on: https://team-review.git.corp.google.com/c/golang/go-private/+/1851497
Run-TryBot: Damien Neil <dneil@google.com>
Reviewed-by: Roland Shoemaker <bracewell@google.com>
Reviewed-on: https://go-review.googlesource.com/c/go/+/491355
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: Carlos Amedee <carlos@golang.org>
TryBot-Bypass: Carlos Amedee <carlos@golang.org>
Run-TryBot: Carlos Amedee <carlos@golang.org>
This commit is contained in:
Roland Shoemaker 2023-04-11 16:27:43 +01:00 committed by Carlos Amedee
parent e49282327b
commit ce7bd33345
2 changed files with 14 additions and 5 deletions

View File

@ -13,6 +13,11 @@ import (
"unicode/utf8"
)
// jsWhitespace contains all of the JS whitespace characters, as defined
// by the \s character class.
// See https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_expressions/Character_classes.
const jsWhitespace = "\f\n\r\t\v\u0020\u00a0\u1680\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u2028\u2029\u202f\u205f\u3000\ufeff"
// nextJSCtx returns the context that determines whether a slash after the
// given run of tokens starts a regular expression instead of a division
// operator: / or /=.
@ -26,7 +31,8 @@ import (
// JavaScript 2.0 lexical grammar and requires one token of lookbehind:
// https://www.mozilla.org/js/language/js20-2000-07/rationale/syntax.html
func nextJSCtx(s []byte, preceding jsCtx) jsCtx {
s = bytes.TrimRight(s, "\t\n\f\r \u2028\u2029")
// Trim all JS whitespace characters
s = bytes.TrimRight(s, jsWhitespace)
if len(s) == 0 {
return preceding
}

View File

@ -81,14 +81,17 @@ func TestNextJsCtx(t *testing.T) {
{jsCtxDivOp, "0"},
// Dots that are part of a number are div preceders.
{jsCtxDivOp, "0."},
// Some JS interpreters treat NBSP as a normal space, so
// we must too in order to properly escape things.
{jsCtxRegexp, "=\u00A0"},
}
for _, test := range tests {
if nextJSCtx([]byte(test.s), jsCtxRegexp) != test.jsCtx {
t.Errorf("want %s got %q", test.jsCtx, test.s)
if ctx := nextJSCtx([]byte(test.s), jsCtxRegexp); ctx != test.jsCtx {
t.Errorf("%q: want %s got %s", test.s, test.jsCtx, ctx)
}
if nextJSCtx([]byte(test.s), jsCtxDivOp) != test.jsCtx {
t.Errorf("want %s got %q", test.jsCtx, test.s)
if ctx := nextJSCtx([]byte(test.s), jsCtxDivOp); ctx != test.jsCtx {
t.Errorf("%q: want %s got %s", test.s, test.jsCtx, ctx)
}
}