util: buffer: Properly URLencode strings

According to rfc3986:

2.3.  Unreserved Characters

   Characters that are allowed in a URI but do not have a reserved
   purpose are called unreserved.  These include uppercase and lowercase
   letters, decimal digits, hyphen, period, underscore, and tilde.

      unreserved  = ALPHA / DIGIT / "-" / "." / "_" / "~"

   URIs that differ in the replacement of an unreserved character with
   its corresponding percent-encoded US-ASCII octet are equivalent: they
   identify the same resource.  However, URI comparison implementations
   do not always perform normalization prior to comparison (see Section
   6).  For consistency, percent-encoded octets in the ranges of ALPHA
   (%41-%5A and %61-%7A), DIGIT (%30-%39), hyphen (%2D), period (%2E),
   underscore (%5F), or tilde (%7E) should not be created by URI
   producers and, when found in a URI, should be decoded to their
   corresponding unreserved characters by URI normalizers.

Thus we must not include few other characters which don't match
c_isalpha to conform to the rules.

Signed-off-by: Peter Krempa <pkrempa@redhat.com>
Reviewed-by: Ján Tomko <jtomko@redhat.com>

diff --git a/src/util/virbuffer.c b/src/util/virbuffer.c
index bf703fe7a5a6528e41de303cc17f4a28b05e0ba8..bde118a248fa44d76cbc45b1e8e2a70625d37acc 100644 (file)
--- a/src/util/virbuffer.c
+++ b/src/util/virbuffer.c
@@ -638,6 +638,16 @@ virBufferEscape(virBufferPtr buf, char escape, const char *toescape,
 }
 
 
+static bool
+virBufferURIEncodeCharIsUnencoded(char c)
+{
+    if (c == '-' || c == '.' || c == '_' || c == '~')
+        return true;
+
+    return c_isalnum(c);
+}
+
+
 /**
  * virBufferURIEncodeString:
  * @buf: the buffer to append to
@@ -664,7 +674,7 @@ virBufferURIEncodeString(virBufferPtr buf, const char *str)
     virBufferAddLit(buf, ""); /* auto-indent */
 
     for (p = str; *p; ++p) {
-        if (c_isalnum(*p))
+        if (virBufferURIEncodeCharIsUnencoded(*p))
             grow_size++;
         else
             grow_size += 3; /* %ab */
@@ -674,7 +684,7 @@ virBufferURIEncodeString(virBufferPtr buf, const char *str)
         return;
 
     for (p = str; *p; ++p) {
-        if (c_isalnum(*p)) {
+        if (virBufferURIEncodeCharIsUnencoded(*p)) {
             buf->content[buf->use++] = *p;
         } else {
             uc = (unsigned char) *p;

diff --git a/tests/viruritest.c b/tests/viruritest.c
index 3255e2333a529b43b744065d59219c3cce5fe5ba..a11587e52ba40983d8194769d8032172383b954b 100644 (file)
--- a/tests/viruritest.c
+++ b/tests/viruritest.c
@@ -184,7 +184,7 @@ mymain(void)
         { NULL, NULL, false },
     };
     TEST_FULL("spice://[3ffe::104]:5900/?tlsSubject=C=XX,L=Testtown,O=Test%20Company,CN=tester.test",
-              "spice://[3ffe::104]:5900/?tlsSubject=C%3dXX%2cL%3dTesttown%2cO%3dTest%20Company%2cCN%3dtester%2etest",
+              "spice://[3ffe::104]:5900/?tlsSubject=C%3dXX%2cL%3dTesttown%2cO%3dTest%20Company%2cCN%3dtester.test",
               "spice", "3ffe::104", 5900, "/", "tlsSubject=C=XX,L=Testtown,O=Test%20Company,CN=tester.test", NULL, NULL, spiceparams);
 
     virURIParam params1[] = {