Scrub space separated ip addresses

The issue with ReplaceAllFunc is that it's capturing the leading and
trailing spaces in the regexp, so successive ips don't match.  From the
docstring,

> If 'All' is present, the routine matches successive non-overlapping
> matches of the entire expression.

For #40306
This commit is contained in:
Arlo Breault 2024-01-03 20:20:01 -05:00 committed by Cecylia Bocovich
parent 98db63ad01
commit e4c818be76
No known key found for this signature in database
GPG key ID: 009DE379FD9B7B90
2 changed files with 18 additions and 4 deletions

View file

@ -21,7 +21,7 @@ const ipv6Full = `(` + ipv6Address + `(` + ipv4Address + `))` +
`|(` + ipv6Address + `)` + `|(` + ipv6Compressed + `)`
const optionalPort = `(:\d{1,5})?`
const addressPattern = `((` + ipv4Address + `)|(\[(` + ipv6Full + `)\])|(` + ipv6Full + `))` + optionalPort
const fullAddrPattern = `(^|\s|[^\w:])` + addressPattern + `(\s|(:\s)|[^\w:]|$)`
const fullAddrPattern = `(?:^|\s|[^\w:])(` + addressPattern + `)(?:\s|(:\s)|[^\w:]|$)`
var scrubberPatterns = []*regexp.Regexp{
regexp.MustCompile(fullAddrPattern),
@ -46,9 +46,18 @@ func Scrub(b []byte) []byte {
for _, pattern := range scrubberPatterns {
// this is a workaround since go does not yet support look ahead or look
// behind for regular expressions.
scrubbedBytes = pattern.ReplaceAllFunc(scrubbedBytes, func(b []byte) []byte {
return addressRegexp.ReplaceAll(b, []byte("[scrubbed]"))
})
var newBytes []byte
index := 0
for {
loc := pattern.FindSubmatchIndex(scrubbedBytes[index:])
if loc == nil {
break
}
newBytes = append(newBytes, scrubbedBytes[index:index+loc[2]]...)
newBytes = append(newBytes, []byte("[scrubbed]")...)
index = index + loc[3]
}
scrubbedBytes = append(newBytes, scrubbedBytes[index:]...)
}
return scrubbedBytes
}

View file

@ -107,6 +107,11 @@ func TestLogScrubberMessages(t *testing.T) {
"error dialing relay: wss://snowflake.torproject.net/?client_ip=1%3A2%3A3%3A%3Ad%3Ae%3Af = dial tcp xxx",
"error dialing relay: wss://snowflake.torproject.net/?client_ip=[scrubbed] = dial tcp xxx\n",
},
{
// multiple space-separated IP addresses
"Allowed stations: [10.0.1.1 10.0.1.2 10.0.1.3 10.0.1.4]\n",
"Allowed stations: [[scrubbed] [scrubbed] [scrubbed] [scrubbed]]\n",
},
} {
var buff bytes.Buffer
log.SetFlags(0) //remove all extra log output for test comparisons