Add filename* for a download name past ASCII

The plain, snapshot and blob pages sent a name such as café.txt raw in
filename, which a client may read as ISO-8859-1. RFC 6266 has such a
name sent again as filename*, percent-encoded in UTF-8, for a client
that knows the form, with filename first for one that does not. The
extended form carries UTF-8 alone, so a name that is not valid UTF-8
keeps the plain filename by itself.

1 file changed, 20 insertions, 0 deletions

diff --git a/source/html.c b/source/html.cindex ce9344d..00eb7c6 100644--- a/source/html.c+++ b/source/html.c@@ -471,6 +471,26 @@ void html_header_arg_in_quotes(const char *txt) 		html(txt); } +void html_header_ext_value(const char *txt)+{+	const char *p = txt;++	while (p && *p) {+		unsigned char c = *p;++		// The attr-char set of RFC 8187, which leaves nothing that+		// could end the parameter or the header line.+		if (!isalnum(c) && !strchr("!#$&+-.^_`|~", c)) {+			html_raw(txt, p - txt);+			htmlf("%%%02X", c);+			txt = p + 1;+		}+		p++;+	}+	if (p != txt)+		html(txt);+}+ /*  * A query string goes into a header the way it arrived, already encoded by  * the client, except that a byte a header line cannot carry is percent-encoded
diff --git a/source/html.c b/source/html.c
index ce9344d..00eb7c6 100644
--- a/source/html.c
+++ b/source/html.c
@@ -471,6 +471,26 @@ void html_header_arg_in_quotes(const char *txt)
 		html(txt);
 }
 
+void html_header_ext_value(const char *txt)
+{
+	const char *p = txt;
+
+	while (p && *p) {
+		unsigned char c = *p;
+
+		// The attr-char set of RFC 8187, which leaves nothing that
+		// could end the parameter or the header line.
+		if (!isalnum(c) && !strchr("!#$&+-.^_`|~", c)) {
+			html_raw(txt, p - txt);
+			htmlf("%%%02X", c);
+			txt = p + 1;
+		}
+		p++;
+	}
+	if (p != txt)
+		html(txt);
+}
+
 /*
  * A query string goes into a header the way it arrived, already encoded by
  * the client, except that a byte a header line cannot carry is percent-encoded