From 554576b6cfe79a91d37e14d3617ca417562085db Mon Sep 17 00:00:00 2001 From: Marton Balint Date: Mon, 3 Feb 2020 01:32:00 +0100 Subject: avformat/utils: make av_url_split search for hashmark as well to separate hostname RFC 3986 states that the generic syntax uses the slash ("/"), question mark ("?"), and number sign ("#") characters to delimit components that are significant to the generic parser's hierarchical interpretation of an identifier. Signed-off-by: Marton Balint --- libavformat/tests/url.c | 1 + libavformat/utils.c | 14 +++----------- 2 files changed, 4 insertions(+), 11 deletions(-) (limited to 'libavformat') diff --git a/libavformat/tests/url.c b/libavformat/tests/url.c index d99876f02c..5e484fd428 100644 --- a/libavformat/tests/url.c +++ b/libavformat/tests/url.c @@ -75,6 +75,7 @@ int main(void) test2("https://1l-lh.a.net/i/1LIVE_HDS@179577/master.m3u8"); test2("ftp://u:p%2B%2F2@ftp.pbt.com/ExportHD.mpg"); test2("https://key.dns.com?key_id=2&model_id=12345&&access_key="); + test2("http://example.com#tag"); return 0; } diff --git a/libavformat/utils.c b/libavformat/utils.c index b3fbbd1942..7ff5ea9702 100644 --- a/libavformat/utils.c +++ b/libavformat/utils.c @@ -4786,7 +4786,7 @@ void av_url_split(char *proto, int proto_size, char *hostname, int hostname_size, int *port_ptr, char *path, int path_size, const char *url) { - const char *p, *ls, *ls2, *at, *at2, *col, *brk; + const char *p, *ls, *at, *at2, *col, *brk; if (port_ptr) *port_ptr = -1; @@ -4814,16 +4814,8 @@ void av_url_split(char *proto, int proto_size, } /* separate path from hostname */ - ls = strchr(p, '/'); - ls2 = strchr(p, '?'); - if (!ls) - ls = ls2; - else if (ls && ls2) - ls = FFMIN(ls, ls2); - if (ls) - av_strlcpy(path, ls, path_size); - else - ls = &p[strlen(p)]; // XXX + ls = p + strcspn(p, "/?#"); + av_strlcpy(path, ls, path_size); /* the rest is hostname, use that to parse auth/port */ if (ls != p) { -- cgit v1.2.3