In HTML5 anchors should not be closed when encountering divs, for example, but should be closed when encountering buttons, for example. Many sites that use HTML5-style anchors end up having links displayed with zero-length link texts. The proposed patch correct this behaviour by detecting whether the document is HTML5, then suppressing the close-anchor action in CLOSE_A if it's an HTML5 document. A new macro handles the HTML5-specific cases where anchors are not already always closed.

This also fixes a bug in the tokenizing FSM in etc.c that prevented the !doctype element from being recognized; the fix is necessary because HTML5 detection depends on checking the !doctype element.

1 files changed, 22 insertions, 3 deletions

diff --git a/file.c b/file.c
index c0fc044..3d772db 100644
--- a/file.c
+++ b/file.c
@@ -1,4 +1,5 @@
 /* $Id: file.c,v 1.266 2012/05/22 09:45:56 inu Exp $ */
+/* vi: set sw=4 ts=8 ai sm noet : */
 #include "fm.h"
 #include <sys/types.h>
 #include "myctype.h"
@@ -4322,9 +4323,18 @@ process_idattr(struct readbuffer *obuf, int cmd, struct parsed_tag *tag)
       obuf->flag &= ~RB_P;\
     }
 
-#define CLOSE_A \
-    CLOSE_P; \
-    close_anchor(h_env, obuf);
+#define HTML5_CLOSE_A do { \
+	if (obuf->flag & RB_HTML5) { \
+	    close_anchor(h_env, obuf); \
+	} \
+    } while (0)
+
+#define CLOSE_A do { \
+	CLOSE_P; \
+	if (!(obuf->flag & RB_HTML5)) { \
+	    close_anchor(h_env, obuf); \
+	} \
+    } while (0)
 
 #define CLOSE_DT \
     if (obuf->flag & RB_IN_DT) { \
@@ -4930,6 +4940,8 @@ HTMLtagproc1(struct parsed_tag *tag, struct html_feed_environ *h_env)
 	close_anchor(h_env, obuf);
 	return 1;
     case HTML_IMG:
+	if (parsedtag_exists(tag, ATTR_USEMAP))
+	    HTML5_CLOSE_A;
 	tmp = process_img(tag, h_env->limit);
 	HTMLlineproc1(tmp->ptr, h_env);
 	return 1;
@@ -5125,6 +5137,7 @@ HTMLtagproc1(struct parsed_tag *tag, struct html_feed_environ *h_env)
            HTMLlineproc1(tmp->ptr, h_env);
        return 1;
     case HTML_BUTTON:
+       HTML5_CLOSE_A;
        tmp = process_button(tag);
        if (tmp)
            HTMLlineproc1(tmp->ptr, h_env);
@@ -5180,6 +5193,11 @@ HTMLtagproc1(struct parsed_tag *tag, struct html_feed_environ *h_env)
 			     NULL);
 	HTMLlineproc1(tmp->ptr, h_env);
 	return 1;
+    case HTML_DOCTYPE:
+	if (!parsedtag_exists(tag, ATTR_PUBLIC)) {
+	    obuf->flag |= RB_HTML5;
+	}
+	return 1;
     case HTML_META:
 	p = q = r = NULL;
 	parsedtag_get_value(tag, ATTR_HTTP_EQUIV, &p);
@@ -5378,6 +5396,7 @@ HTMLtagproc1(struct parsed_tag *tag, struct html_feed_environ *h_env)
 	}
 	return 1;
     case HTML_EMBED:
+	HTML5_CLOSE_A;
 	if (view_unseenobject) {
 	    if (parsedtag_get_value(tag, ATTR_SRC, &p)) {
 		Str s;