git: 9front

Info  •  Files  •  Log  •  Branches

uhtml: dont trust charset=utf-8 attribute, verify.

when the charset is explicitely specified as utf-8, ignore it
for now. we'll assume utf-8 when all bytes have been properly
utf-8 encoded.

--- a/sys/src/cmd/uhtml.c

+++ b/sys/src/cmd/uhtml.c

@@ -122,7 +122,8 @@

 		}

 		t = *e;

 		*e = 0;

-		if((a = attr(g, "encoding")) != nil || (a = attr(g, "charset")) != nil){

+		if((a = attr(g, "encoding")) != nil || (a = attr(g, "charset")) != nil)

+		if(cistrcmp(a, "utf") != 0 && cistrcmp(a, "utf-8") != 0){

 			cset = a;

 			*e = t;

 			break;

-- 

⑨