[FFmpeg-devel] [PATCH] avformat/http: Handle IPv6 Zone ID in hostname

[Marvin Scholz]

When using a literal IPv6 address as hostname, it can contain a Zone ID
especially in the case of link-local addresses. Sending this to the
server in the Host header is not useful to the server and in some cases
servers refuse such requests.

To prevent any such issues, strip the Zone ID from the address if it's
an IPv6 address. This also removes it for the Cookies lookup.

Based on a patch by: Daniel N Pettersson <danielnp at axis.com>
---
 libavformat/http.c | 60 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 59 insertions(+), 1 deletion(-)

diff --git a/libavformat/http.c b/libavformat/http.c
index f7b2a8a029..3bde616b43 100644
--- a/libavformat/http.c
+++ b/libavformat/http.c
@@ -24,6 +24,7 @@
 #include "config.h"
 #include "config_components.h"
 
+#include <string.h>
 #include <time.h>
 #if CONFIG_ZLIB
 #include <zlib.h>
@@ -209,6 +210,63 @@ void ff_http_init_auth_state(URLContext *dest, const URLContext *src)
            sizeof(HTTPAuthState));
 }
 
+static bool host_is_numeric_ipv6(const char *host)
+{
+    bool res = false;
+#if defined(AF_INET6)
+    struct addrinfo hints = { .ai_flags = AI_NUMERICHOST }, *ai;
+    if (getaddrinfo(host, NULL, &hints, &ai) == 0) {
+        if (ai->ai_family == AF_INET6)
+            res = true;
+        freeaddrinfo(ai);
+    }
+#else
+    // Just guess based on if the host contains a ':'
+    if (strchr(host, ':') != NULL)
+        res = true;
+#endif
+    return res;
+}
+
+/**
+ * Copy the normalized host to the given buffer
+ *
+ * If the host is a normal hostname, this just returns
+ * host:port. However in case of an IPv6 address, it
+ * ensures proper escaping with [] and removes the
+ * zone identifier, if any, making the return suitable
+ * for example for use in the HTTP Host header.
+ */
+static unsigned copy_normalized_host(char *out, unsigned size,
+                               const char *host, const int port)
+{
+    AVBPrint bp;
+    av_bprint_init_for_buffer(&bp, out, size);
+
+    if (host_is_numeric_ipv6(host)) {
+        // This is an IPv6 address, so we need to strip the Zone ID,
+        // if any.
+        // While technically we could have percent encoding even in
+        // the Zone ID, this doesn't seem to be a relevant case in
+        // the real world on any platform.
+        char *percent = strrchr(host, '%');
+        if (percent) {
+            int len = (percent - host);
+            av_bprintf(&bp, "[%.*s]", len, host);
+        } else {
+            av_bprintf(&bp, "[%s]", host);
+        }
+    } else {
+        // Host is not an IPv6 address, so just use as-is
+        av_bprintf(&bp, "%s", host);
+    }
+
+    if (port >= 0)
+        av_bprintf(&bp, ":%d", port);
+
+    return bp.len;
+}
+
 static int http_open_cnx_internal(URLContext *h, AVDictionary **options)
 {
     const char *path, *proxy_path, *lower_proto = "tcp", *local_path;
@@ -224,7 +282,7 @@ static int http_open_cnx_internal(URLContext *h, AVDictionary **options)
     av_url_split(proto, sizeof(proto), auth, sizeof(auth),
                  hostname, sizeof(hostname), &port,
                  path1, sizeof(path1), s->location);
-    ff_url_join(hoststr, sizeof(hoststr), NULL, NULL, hostname, port, NULL);
+    copy_normalized_host(hoststr, sizeof(hoststr), hostname, port);
 
     env_http_proxy = getenv_utf8("http_proxy");
     proxy_path = s->http_proxy ? s->http_proxy : env_http_proxy;
-- 
2.39.5 (Apple Git-154)