romenskiy2012/curl
1
0
Fork 0
mirror of https://github.com/curl/curl.git synced 2026-08-25 22:03:47 +03:00
Code Issues Projects Releases Packages Wiki Activity

URL parser: allow URLs to use one, two or three slashes

Browse source 
Mostly in order to support broken web sites that redirect to broken URLs
that are accepted by browsers.

Browsers are typically even more leniant than this as the WHATWG URL
spec they should allow an _infinite_ amount. I tested 8000 slashes with
Firefox and it just worked.

Added test case 1141, 1142 and 1143 to verify the new parser.

Closes #791
This commit is contained in:
Daniel Stenberg 2016-05-08 15:11:10 +02:00
parent ed8b8f2456
commit 5409e1d793
5 changed files with 200 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

30
lib/url.c
View file

@ -4141,12 +4141,17 @@ static CURLcode parseurlandfillconn(struct SessionHandle *data,
}
else {
/* clear path */
char slashbuf[4];
path[0]=0;
if(2 > sscanf(data->change.url,
"%15[^\n:]://%[^\n/?]%[^\n]",
protobuf,
conn->host.name, path)) {
rc = sscanf(data->change.url,
"%15[^\n:]:%3[/]%[^\n/?]%[^\n]",
protobuf, slashbuf, conn->host.name, path);
if(2 == rc) {
failf(data, "Bad URL");
return CURLE_URL_MALFORMAT;
}
if(3 > rc) {
/*
* The URL was badly formatted, let's try the browser-style _without_
@ -4197,8 +4202,23 @@ static CURLcode parseurlandfillconn(struct SessionHandle *data,
*prot_missing = TRUE; /* not given in URL */
}
else
else {
size_t s = strlen(slashbuf);
protop = protobuf;
if(s != 2) {
infof(data, "Unwillingly accepted illegal URL using %d slash%s!\n",
s, s>1?"es":"");
if(data->change.url_alloc)
free(data->change.url);
/* repair the URL to use two slashes */
data->change.url = aprintf("%s://%s%s",
protobuf, conn->host.name, path);
if(!data->change.url)
return CURLE_OUT_OF_MEMORY;
data->change.url_alloc = TRUE;
}
}
}
/* We search for '?' in the host name (but only on the right side of a