From 0ce7b6bffc311d83871c75bfc52330354ff84615 Mon Sep 17 00:00:00 2001
From: hniksic <devnull@localhost>
Date: Fri, 16 Nov 2001 08:44:34 -0800
Subject: [PATCH] [svn] Support XML-style empty tags.

---
 src/ChangeLog    |  4 ++++
 src/html-parse.c | 17 +++++++++++++++--
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/src/ChangeLog b/src/ChangeLog
index de743a8f..29edda04 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,7 @@
+2001-11-16  Hrvoje Niksic  <hniksic@arsdigita.com>
+
+	* html-parse.c (map_html_tags): Support XML-style empty tags.
+
 2001-06-26  Hrvoje Niksic  <hniksic@arsdigita.com>
 
 	* wget.h (DO_REALLOC_FROM_ALLOCA): Check for do_realloc_newsize in
diff --git a/src/html-parse.c b/src/html-parse.c
index f9a5b0f5..4ae7afe7 100644
--- a/src/html-parse.c
+++ b/src/html-parse.c
@@ -638,6 +638,19 @@ map_html_tags (const char *text, int size,
 
 	SKIP_WS (p);
 
+	if (*p == '/')
+	  {
+	    /* A slash at this point means the tag is about to be
+	       closed.  This is legal in XML and has been popularized
+	       in HTML via XHTML.  */
+	    /* <foo a=b c=d /> */
+	    /*              ^  */
+	    ADVANCE (p);
+	    SKIP_WS (p);
+	    if (*p != '>')
+	      goto backout_tag;
+	  }
+
 	/* Check for end of tag definition. */
 	if (*p == '>')
 	  break;
@@ -654,7 +667,7 @@ map_html_tags (const char *text, int size,
 
 	/* Establish bounds of attribute value. */
 	SKIP_WS (p);
-	if (NAME_CHAR_P (*p) || *p == '>')
+	if (NAME_CHAR_P (*p) || *p == '/' || *p == '>')
 	  {
 	    /* Minimized attribute syntax allows `=' to be omitted.
                For example, <UL COMPACT> is a valid shorthand for <UL
@@ -735,7 +748,7 @@ map_html_tags (const char *text, int size,
 	    /* We skipped the whitespace and found something that is
 	       neither `=' nor the beginning of the next attribute's
 	       name.  Back out.  */
-	    goto backout_tag;	/* <foo bar /... */
+	    goto backout_tag;	/* <foo bar [... */
 				/*          ^    */
 	  }
 
-- 
2.39.2