Package: libxml2-dev
Version: 2.7.8.dfsg-2
[While filing a bug against an older version of the package, I
don't seem to find anything in the Debian changelog of
2.7.8.dfsg-2+squeeze1 that'd suggest that any change was made to
the behavior described below.]
The xmlSaveUri () function appears to format the URI's with
:-delimited paths incorrectly, by adding a superfluous // (which
is simple to resolve, see below), and %-encoding the :'s
themselves (much harder, I guess), effectively preventing
urn:-scheme URN's from being used. (As in: catalogs.)
Consider the output of the example program (MIME'd):
URI urn:example:animal:ferret:nose
scheme urn
opaque (null)
authority (null)
server (null)
user (null)
port 0
path example:animal:ferret:nose
query (null)
fragment (null)
cleanup 0
query_raw (null)
xmlSaveUri urn://example%3Aanimal%3Aferret%3Anose
Cf. the example in RFC 3986, section 3 [1]:
--cut--
foo://example.com:8042/over/there?name=ferret#nose
\_/ \______________/\_________/ \_________/ \__/
| | | | |
scheme authority path query fragment
| _____________________|__
/ \ / \
urn:example:animal:ferret:nose
--cut--
As the example URN has no authority part, it shouldn't have the
// separator either.
[1] http://tools.ietf.org/html/rfc3986#section-3
The relevant parts of the code (as of 2ee91eb6) seem to be:
999 xmlChar *
1000 xmlSaveUri(xmlURIPtr uri) {
×
1019 if (uri->scheme != NULL) {
× formatting the scheme×
1047 }
1048 if (uri->opaque != NULL) {
×
1072 } else {
1073 if (uri->server != NULL) {
× adding //[USER@]SERVER[:PORT]
1161 } else if (uri->authority != NULL) {
× adding //AUTHORITY
1203 } else if (uri->scheme != NULL) {
×
1216 ret[len++] = '/';
1217 ret[len++] = '/';
Here, we've added the superfluous // part. Arguably, it should
only be done for the file: scheme, and even then, it may worth
using an explicit empty string for uri->server instead.
1218 }
1219 if (uri->path != NULL) {
×
1245 while (*p != 0) {
×
1258 if ((IS_UNRESERVED(*(p))) || ((*(p) == '/')) ||
1259 ((*(p) == ';')) || ((*(p) == '@')) || ((*(p) ==
'&')) ||
1260 ((*(p) == '=')) || ((*(p) == '+')) || ((*(p) ==
'$')) ||
1261 ((*(p) == ',')))
Note that the :'s aren't in the list above.
1262 ret[len++] = *p++;
1263 else {
1264 int val = *(unsigned char *)p++;
1265 int hi = val / 0x10, lo = val % 0x10;
1266 ret[len++] = '%';
1267 ret[len++] = hi + (hi > 9? 'A'-10 : '0');
1268 ret[len++] = lo + (lo > 9? 'A'-10 : '0');
And here, we're %-encoding the :'s.
This issue is, however, harder to overcome, unless
uri->cleanup |= 2 is done before parsing, as
xmlURIUnescapeString () will be called on the path part of the
URI, thus effectively making %-encoded :'s indistinguishable
from the :'s used as URN path delimiters.
1269 }
1270 }
1271 }
--
FSF associate member #7257
/*** b87fb7f6-2b9c-11e1-aa29-001966aaa0b6.c -*- C -*- */
/*** Code: */
#include <assert.h> /* for assert () */
#include <stdio.h> /* for printf () */
#include <libxml/uri.h>
#include <libxml/xmlstring.h> /* for xmlChar */
int
main ()
{
/* NB: as per the example from RFC 3986, section 3;
http://tools.ietf.org/html/rfc3986#section-3 */
const char *uri_s
= "urn:example:animal:ferret:nose";
xmlURIPtr uri
= xmlParseURI (uri_s);
assert (uri != 0);
char *uri_saved_s
= xmlSaveUri (uri);
assert (uri_saved_s != 0);
/* NB: assume that printf () is able to %s-format NULL */
printf (("%-15s %s\n"
"%-15s %s\n" "%-15s %s\n" "%-15s %s\n" "%-15s %s\n"
"%-15s %s\n" "%-15s %d\n" "%-15s %s\n" "%-15s %s\n"
"%-15s %s\n" "%-15s %d\n" "%-15s %s\n"
"%-15s %s\n"),
"URI", uri_s, /* -1 */
"scheme", uri->scheme, /* 0 */
"opaque", uri->opaque,
"authority", uri->authority,
"server", uri->server,
"user", uri->user, /* 4 */
"port", uri->port, /* NB: %d */
"path", uri->path,
"query", uri->query,
"fragment", uri->fragment, /* 8 */
"cleanup", uri->cleanup, /* NB: %d */
"query_raw", uri->query_raw,
"xmlSaveUri", uri_saved_s);
/* . */
return 0;
}
/*** b87fb7f6-2b9c-11e1-aa29-001966aaa0b6.c ends here */
