Applied the last patch from Gary Coady for #304637 changing the behaviour
* HTMLparser.c: Applied the last patch from Gary Coady for #304637
changing the behaviour when text nodes are found in body
* result/HTML/*: this changes the output of some tests
Daniel
diff --git a/ChangeLog b/ChangeLog
index cf28052..be3b661 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+Thu Sep 1 11:42:39 CEST 2005 Daniel Veillard <daniel@veillard.com>
+
+ * HTMLparser.c: Applied the last patch from Gary Coady for #304637
+ changing the behaviour when text nodes are found in body
+ * result/HTML/*: this changes the output of some tests
+
Thu Sep 1 11:22:37 CEST 2005 Daniel Veillard <daniel@veillard.com>
* doc/downloads.html doc/xml.html: adding reference to Bull AIX rpms
diff --git a/HTMLparser.c b/HTMLparser.c
index 6b8b562..d11ae08 100644
--- a/HTMLparser.c
+++ b/HTMLparser.c
@@ -964,7 +964,6 @@
static const char *htmlNoContentElements[] = {
"html",
"head",
- "body",
NULL
};
@@ -2042,6 +2041,7 @@
unsigned int i;
int j;
xmlNodePtr lastChild;
+ xmlDtdPtr dtd;
for (j = 0;j < len;j++)
if (!(IS_BLANK_CH(str[j]))) return(0);
@@ -2054,8 +2054,17 @@
return(1);
if (xmlStrEqual(ctxt->name, BAD_CAST"head"))
return(1);
- if (xmlStrEqual(ctxt->name, BAD_CAST"body"))
- return(1);
+
+ /* Only strip CDATA children of the body tag for strict HTML DTDs */
+ if (xmlStrEqual(ctxt->name, BAD_CAST "body") && ctxt->myDoc != NULL) {
+ dtd = xmlGetIntSubset(ctxt->myDoc);
+ if (dtd != NULL && dtd->ExternalID != NULL) {
+ if (!xmlStrcasecmp(dtd->ExternalID, BAD_CAST "-//W3C//DTD HTML 4.01//EN") ||
+ !xmlStrcasecmp(dtd->ExternalID, BAD_CAST "-//W3C//DTD HTML 4//EN"))
+ return(1);
+ }
+ }
+
if (ctxt->node == NULL) return(0);
lastChild = xmlGetLastChild(ctxt->node);
while ((lastChild) && (lastChild->type == XML_COMMENT_NODE))
diff --git a/result/HTML/Down.html b/result/HTML/Down.html
index cd99aa1..929ed8a 100644
--- a/result/HTML/Down.html
+++ b/result/HTML/Down.html
@@ -3,10 +3,8 @@
<head><title>This service is temporary down</title></head>
<body bgcolor="#FFFFFF">
<h1 align="center">Sorry, this service is temporary down</h1>
-<p>
We are doing our best to get it back on-line,
-</p>
<p>The W3C system administrators</p>
</body>
</html>
diff --git a/result/HTML/Down.html.sax b/result/HTML/Down.html.sax
index a8c32c9..c23c332 100644
--- a/result/HTML/Down.html.sax
+++ b/result/HTML/Down.html.sax
@@ -16,19 +16,17 @@
, 2)
SAX.startElement(body, bgcolor='#FFFFFF')
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(h1, align='center')
SAX.characters(Sorry, this service is tempora, 37)
SAX.endElement(h1)
-SAX.startElement(p)
SAX.characters(
We are doing our best to get , 48)
-SAX.endElement(p)
SAX.startElement(p)
SAX.characters(The W3C system administrators, 29)
SAX.endElement(p)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/attrents.html b/result/HTML/attrents.html
index 3231d1e..0433f48 100644
--- a/result/HTML/attrents.html
+++ b/result/HTML/attrents.html
@@ -1,4 +1,4 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
-<html><body bgcolor="#FFFFFF">
-<a href="mailto:katherine@cbfanc.org,website@bis.doc.gov?subject=South%20San%20Francisco%20BIS%20Seminar%20-%20October%2016th"></a><br>
+<html><body bgcolor="#FFFFFF">
+ <a href="mailto:katherine@cbfanc.org,website@bis.doc.gov?subject=South%20San%20Francisco%20BIS%20Seminar%20-%20October%2016th"></a><br>
</body></html>
diff --git a/result/HTML/attrents.html.sax b/result/HTML/attrents.html.sax
index 976bbbe..c1cfb42 100644
--- a/result/HTML/attrents.html.sax
+++ b/result/HTML/attrents.html.sax
@@ -4,13 +4,13 @@
SAX.ignorableWhitespace(
, 2)
SAX.startElement(body, bgcolor='#FFFFFF')
-SAX.ignorableWhitespace(
+SAX.characters(
, 18)
SAX.startElement(a, href='mailto:katherine@cbfanc.org,website@bis.doc.gov?subject=South San Francisco BIS Seminar - October 16th')
SAX.endElement(a)
SAX.startElement(br)
SAX.endElement(br)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/cf_128.html b/result/HTML/cf_128.html
index 8c4f11a..b3e6b41 100644
--- a/result/HTML/cf_128.html
+++ b/result/HTML/cf_128.html
@@ -1,7 +1,9 @@
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/strict.dtd">
<html>
<head><title>gnome-xml push mode bug</title></head>
-<body><table border="4"><tr>
+<body>
+
+<table border="4"><tr>
<td bgcolor="white">
Foo1
<table border="4"><tr><td>Foo2<p></p>
@@ -9,5 +11,6 @@
</td></tr></table>
</td>
<td bgcolor="blue">Foo3</td>
- </tr></table></body>
+ </tr></table>
+</body>
</html>
diff --git a/result/HTML/cf_128.html.sax b/result/HTML/cf_128.html.sax
index 8aa82c1..8f66a42 100644
--- a/result/HTML/cf_128.html.sax
+++ b/result/HTML/cf_128.html.sax
@@ -16,7 +16,7 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(table, border='4')
@@ -58,7 +58,7 @@
SAX.characters(
, 3)
SAX.endElement(table)
-SAX.ignorableWhitespace(
+SAX.characters(
, 3)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/doc2.htm b/result/HTML/doc2.htm
index 0446695..2c7e230 100644
--- a/result/HTML/doc2.htm
+++ b/result/HTML/doc2.htm
@@ -20,7 +20,9 @@
</frameset>
<noframes>
- <body bgcolor="#FFFFFF" text="#000000" link="#000080" vlink="#000080" alink="#000080" topmargin="0" leftmargin="0" marginheight="0" marginwidth="0"><p>This page uses frames, but your browser doesn't support them.</p></body>
+ <body bgcolor="#FFFFFF" text="#000000" link="#000080" vlink="#000080" alink="#000080" topmargin="0" leftmargin="0" marginheight="0" marginwidth="0">
+ <p>This page uses frames, but your browser doesn't support them.</p>
+ </body>
</noframes>
</frameset>
</html>
diff --git a/result/HTML/doc2.htm.sax b/result/HTML/doc2.htm.sax
index 27d458a..7cbbc51 100644
--- a/result/HTML/doc2.htm.sax
+++ b/result/HTML/doc2.htm.sax
@@ -51,12 +51,12 @@
, 4)
SAX.startElement(body, bgcolor='#FFFFFF', text='#000000', link='#000080', vlink='#000080', alink='#000080', topmargin='0', leftmargin='0', marginheight='0', marginwidth='0')
-SAX.ignorableWhitespace(
+SAX.characters(
, 3)
SAX.startElement(p)
SAX.characters(This page uses frames, but you, 61)
SAX.endElement(p)
-SAX.ignorableWhitespace(
+SAX.characters(
, 3)
SAX.endElement(body)
SAX.characters(
diff --git a/result/HTML/doc3.htm b/result/HTML/doc3.htm
index ef6fddd..a53c27b 100644
--- a/result/HTML/doc3.htm
+++ b/result/HTML/doc3.htm
@@ -32,7 +32,7 @@
// End -->
</script><meta content="MSHTML 5.00.3103.1000" name="GENERATOR">
</head>
-<body alink="red" bgcolor="black" link="red" text="white" vlink="red">
+<body alink="red" bgcolor="black" link="red" text="white" vlink="red">
<p>
</p>
<div align="center">
@@ -439,7 +439,7 @@
</td></tr>
<!-- <TR> <TD WIDTH="780"> <P ALIGN="CENTER"><FONT SIZE="1" COLOR="#999999" FACE="Verdana,arial">Site design by Tim Brinkley</FONT> </TD> </TR> -->
</tbody></table>
-</div>
+</div>
<script> window.open=NS_ActualOpen; </script>
</body>
</html>
diff --git a/result/HTML/doc3.htm.sax b/result/HTML/doc3.htm.sax
index 93f5a9f..2cc38fa 100644
--- a/result/HTML/doc3.htm.sax
+++ b/result/HTML/doc3.htm.sax
Binary files differ
diff --git a/result/HTML/fp40.htm b/result/HTML/fp40.htm
index e78b8bd..a1244dd 100644
--- a/result/HTML/fp40.htm
+++ b/result/HTML/fp40.htm
@@ -44,7 +44,8 @@
configuration files (access.conf, srm.conf), add the following lines to http.conf:</p>
-</font><blockquote>
+</font>
+<blockquote>
<font face="Courier New">
ResourceConfig /dev/null <br>
AccessConfig /dev/null</font>
diff --git a/result/HTML/fp40.htm.sax b/result/HTML/fp40.htm.sax
index 3859458..6f77794 100644
--- a/result/HTML/fp40.htm.sax
+++ b/result/HTML/fp40.htm.sax
@@ -26,7 +26,7 @@
, 2)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(font, face='Verdana')
SAX.characters(
@@ -167,7 +167,7 @@
, 3)
SAX.endElement(font)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(blockquote)
SAX.characters(
@@ -184,7 +184,7 @@
SAX.characters(
, 1)
SAX.endElement(blockquote)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(font, face='Verdana')
SAX.characters(
@@ -452,7 +452,7 @@
, 4)
SAX.endElement(font)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/liclose.html b/result/HTML/liclose.html
index b8a464e..f4e4edb 100644
--- a/result/HTML/liclose.html
+++ b/result/HTML/liclose.html
@@ -1,10 +1,12 @@
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
<html>
<head><title></title></head>
-<body><ul>
+<body>
+<ul>
<li>First item
</li>
<li>Second item, closes the first one
</li>
-</ul></body>
+</ul>
+</body>
</html>
diff --git a/result/HTML/liclose.html.sax b/result/HTML/liclose.html.sax
index 30f26c0..eabcdf6 100644
--- a/result/HTML/liclose.html.sax
+++ b/result/HTML/liclose.html.sax
@@ -15,7 +15,7 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(ul)
SAX.characters(
@@ -28,7 +28,7 @@
SAX.characters(Second item, closes the first , 34)
SAX.endElement(li)
SAX.endElement(ul)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.endElement(body)
diff --git a/result/HTML/pre.html b/result/HTML/pre.html
index 17f5b3f..5308b6d 100644
--- a/result/HTML/pre.html
+++ b/result/HTML/pre.html
@@ -1,2 +1,4 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
-<html><body><pre><a href="toto"></a><img src="titi"></pre></body></html>
+<html><body>
+<pre><a href="toto"></a><img src="titi"></pre>
+</body></html>
diff --git a/result/HTML/pre.html.sax b/result/HTML/pre.html.sax
index 4f567ae..f8782b7 100644
--- a/result/HTML/pre.html.sax
+++ b/result/HTML/pre.html.sax
@@ -4,7 +4,7 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(pre)
SAX.startElement(a, href='toto')
@@ -12,7 +12,7 @@
SAX.startElement(img, src='titi')
SAX.endElement(img)
SAX.endElement(pre)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/python.html b/result/HTML/python.html
index e5f9d56..5fdc6a2 100644
--- a/result/HTML/python.html
+++ b/result/HTML/python.html
@@ -1,5 +1,6 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<?xml-stylesheet href="./css/ht2html.css" type="text/css"?><html>
<!-- THIS PAGE IS AUTOMATICALLY GENERATED. DO NOT EDIT. --><head><title>Python Programming Language</title></head>
-<body></body>
+<body>
+</body>
</html>
diff --git a/result/HTML/python.html.sax b/result/HTML/python.html.sax
index 4f96e8a..665539c 100644
--- a/result/HTML/python.html.sax
+++ b/result/HTML/python.html.sax
@@ -20,7 +20,7 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.endElement(html)
diff --git a/result/HTML/reg1.html.sax b/result/HTML/reg1.html.sax
index 1ca0271..c8ee3ac 100644
--- a/result/HTML/reg1.html.sax
+++ b/result/HTML/reg1.html.sax
@@ -15,12 +15,12 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(h1)
SAX.characters(Regression test 1, 17)
SAX.endElement(h1)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(p)
SAX.characters(
diff --git a/result/HTML/reg2.html.sax b/result/HTML/reg2.html.sax
index 63acfd4..f85691e 100644
--- a/result/HTML/reg2.html.sax
+++ b/result/HTML/reg2.html.sax
@@ -15,12 +15,12 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(h1)
SAX.characters(Regression test 2, 17)
SAX.endElement(h1)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(p)
SAX.characters(
diff --git a/result/HTML/reg3.html.sax b/result/HTML/reg3.html.sax
index 5d498b2..ec0f039 100644
--- a/result/HTML/reg3.html.sax
+++ b/result/HTML/reg3.html.sax
@@ -15,12 +15,12 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(h1)
SAX.characters(Regression test 3, 17)
SAX.endElement(h1)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(p)
SAX.characters(
@@ -29,7 +29,7 @@
SAX.endElement(p)
SAX.startElement(hr)
SAX.endElement(hr)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(p)
SAX.characters(
diff --git a/result/HTML/reg4.html.sax b/result/HTML/reg4.html.sax
index 5a4eacf..4c5147c 100644
--- a/result/HTML/reg4.html.sax
+++ b/result/HTML/reg4.html.sax
@@ -15,12 +15,12 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(h1)
SAX.characters(Regression test 4, 17)
SAX.endElement(h1)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(p)
SAX.characters(
@@ -29,10 +29,10 @@
SAX.endElement(p)
SAX.startElement(hr)
SAX.endElement(hr)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.error: Unexpected end tag : p
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/script.html.sax b/result/HTML/script.html.sax
index 3a47061..b259f7f 100644
--- a/result/HTML/script.html.sax
+++ b/result/HTML/script.html.sax
@@ -11,17 +11,17 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(script, language='javascript')
SAX.cdata(
if (window.open<max) ;, 28)
SAX.endElement(script)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(input, onclick='if(window.open<max);')
SAX.endElement(input)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/script2.html b/result/HTML/script2.html
index bf9318e..2be4f93 100644
--- a/result/HTML/script2.html
+++ b/result/HTML/script2.html
@@ -4,11 +4,13 @@
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>Test Page</title>
</head>
-<body><div id="portal">
+<body>
+<div id="portal">
<script type="text/javascript">
documen.write("Příliš žluťoučký kůň úpěl ďábelksé ódy");
</script><p>
Příliš žluťoučký kůň úpěl ďábelksé ódy;
</p>
-</div></body>
+</div>
+</body>
</html>
diff --git a/result/HTML/script2.html.sax b/result/HTML/script2.html.sax
index 1607ccb..1971991 100644
--- a/result/HTML/script2.html.sax
+++ b/result/HTML/script2.html.sax
@@ -20,7 +20,7 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(div, id='portal')
SAX.characters(
@@ -38,7 +38,7 @@
SAX.characters(
, 1)
SAX.endElement(div)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
diff --git a/result/HTML/test2.html b/result/HTML/test2.html
index ef62dc6..98a2716 100644
--- a/result/HTML/test2.html
+++ b/result/HTML/test2.html
@@ -2,6 +2,7 @@
<html>
<head><title>Linux Today</title></head>
<body bgcolor="White" link="Blue" text="Black" vlink="Black" alink="Red">
+
<center>
<table border="0" width="100%" cellspacing="0" cellpadding="0"><tr bgcolor="#FFFFFF">
<td height="90">
diff --git a/result/HTML/test2.html.sax b/result/HTML/test2.html.sax
index 03f7285..78bb090 100644
--- a/result/HTML/test2.html.sax
+++ b/result/HTML/test2.html.sax
@@ -11,7 +11,7 @@
SAX.ignorableWhitespace(
, 1)
SAX.startElement(body, bgcolor='White', link='Blue', text='Black', vlink='Black', alink='Red')
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(center)
@@ -130,7 +130,7 @@
SAX.characters(
, 1)
SAX.endElement(center)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(p)
SAX.characters(
diff --git a/result/HTML/test3.html b/result/HTML/test3.html
index 4437f4d..903723c 100644
--- a/result/HTML/test3.html
+++ b/result/HTML/test3.html
@@ -38,7 +38,7 @@
<dt><h4>Class <a href="ProblemDomain.Note.html#ProblemDomain.Note">ProblemDomain.Note</a>
</h4></dt>
</dl>
-<h4><b>Links</b></h4>
+<h4><b>Links</b></h4>
<ul><li>
<b>Link to </b><a href="HumanInterface.Package.html#HumanInterface.Package">HumanInterface</a>
</li></ul>
diff --git a/result/HTML/test3.html.sax b/result/HTML/test3.html.sax
index 1f76e50..c9f6638 100644
--- a/result/HTML/test3.html.sax
+++ b/result/HTML/test3.html.sax
@@ -26,7 +26,7 @@
SAX.startElement(hr)
SAX.endElement(hr)
SAX.error: Unexpected end tag : p
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(dl)
SAX.characters(
@@ -59,14 +59,14 @@
SAX.endElement(dd)
SAX.endElement(dd)
SAX.endElement(dl)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(p)
SAX.endElement(p)
SAX.startElement(hr)
SAX.endElement(hr)
SAX.error: Unexpected end tag : p
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(dl)
SAX.characters(
@@ -163,7 +163,7 @@
SAX.characters(
, 2)
SAX.endElement(dl)
-SAX.ignorableWhitespace(
+SAX.characters(
, 4)
SAX.startElement(h4)
@@ -173,7 +173,7 @@
SAX.endElement(b)
SAX.endElement(h4)
SAX.error: Unexpected end tag : b
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(ul)
SAX.startElement(li)
@@ -185,11 +185,11 @@
SAX.endElement(a)
SAX.endElement(li)
SAX.endElement(ul)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(dir)
SAX.endElement(dir)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(ul)
SAX.startElement(li)
@@ -201,11 +201,11 @@
SAX.endElement(a)
SAX.endElement(li)
SAX.endElement(ul)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(dir)
SAX.endElement(dir)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(ul)
SAX.startElement(li)
@@ -217,11 +217,11 @@
SAX.endElement(a)
SAX.endElement(li)
SAX.endElement(ul)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(dir)
SAX.endElement(dir)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.endElement(body)
SAX.endElement(html)
diff --git a/result/HTML/wired.html b/result/HTML/wired.html
index 674623f..f7123e8 100644
--- a/result/HTML/wired.html
+++ b/result/HTML/wired.html
@@ -2,6 +2,7 @@
<!-- Vignette StoryServer 4 Fri Oct 15 11:37:12 1999 --><html>
<head><title>Top Stories News from Wired News</title></head>
<body bgcolor="#FFFFFF" text="#000000" link="#333399" vlink="#660066" alink="#666699">
+
<table border="0" width="600" cellspacing="0" cellpadding="0"><tr>
<td valign="top" align="LEFT"><table border="0" cellpadding="0" cellspacing="0" width="468" height="60" bgcolor="#FFFFFF">
<form method="GET" action="http://nsads.hotwired.com/event.ng/Type=click&ProfileID=9688&RunID=14074&AdID=22584&GroupID=1&FamilyID=2684&TagValues=8.25.156.159.166.171.172.174.179.180.181.182.183.196.197.199.208.389.412.436.2041.6750.78456.79630.81880&Redirect=http://www.springstreet.com/aa/citysearch.htm" id="form1" name="form1">
@@ -69,7 +70,8 @@
</table></td>
<td valign="top" align="RIGHT"><a href="http://nsads.hotwired.com/event.ng/Type=click&ProfileID=5597&RunID=17167&AdID=22588&GroupID=1&FamilyID=3228&TagValues=8.25.159.171.172.174.179.180.181.182.183.196.197.199.208.241.389.412.436.2035.6749.6750.70367.78456.79630.81880&Redirect=http:%2F%2Fwww.hp.com%2Fgo%2Foriginal%20" target="_top"><img src="http://static.wired.com/advertising/blipverts/hp_colorinkjet/hp_970c_120x60_6.gif" border="1" height="60" width="120" alt="True to the Original"></a></td>
</tr></table>
-<!-- WIRED NEWS header --><!-- CMD_HOST = scoop.hotwired.com --><a name="#"></a><table border="0" width="600" cellspacing="0" cellpadding="0">
+<!-- WIRED NEWS header --><!-- CMD_HOST = scoop.hotwired.com --><a name="#"></a>
+<table border="0" width="600" cellspacing="0" cellpadding="0">
<tr>
<td></td>
<td colspan="2"><img src="http://static.wired.com/news/images/spacer.gif" height="5" width="447" alt=""></td>
diff --git a/result/HTML/wired.html.sax b/result/HTML/wired.html.sax
index 0edd57e..3860c76 100644
--- a/result/HTML/wired.html.sax
+++ b/result/HTML/wired.html.sax
@@ -8,7 +8,7 @@
SAX.endElement(title)
SAX.endElement(head)
SAX.startElement(body, bgcolor='#FFFFFF', text='#000000', link='#333399', vlink='#660066', alink='#666699')
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(table, border='0', width='600', cellspacing='0', cellpadding='0')
@@ -315,19 +315,19 @@
SAX.characters(
, 1)
SAX.endElement(table)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.comment( WIRED NEWS header )
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.comment( CMD_HOST = scoop.hotwired.com )
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(a, name='#')
SAX.endElement(a)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.startElement(table, border='0', width='600', cellspacing='0', cellpadding='0')
SAX.characters(
@@ -574,14 +574,14 @@
SAX.characters(
, 1)
SAX.endElement(table)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.comment( end WIRED NEWS header )
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.comment( begin upper left side Navigation )
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(table, border='0', cellpadding='3', cellspacing='0', align='LEFT', bgcolor='#FFFFFF')
@@ -1463,14 +1463,14 @@
, 2)
SAX.endElement(table)
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.comment( end lower left side Navigation )
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.comment( CONTENT TABLE )
-SAX.ignorableWhitespace(
+SAX.characters(
, 2)
SAX.startElement(table, border='0', width='447', cellspacing='0', cellpadding='0', bordercolor='#66FF00')
@@ -2830,13 +2830,13 @@
SAX.characters(
, 1)
SAX.endElement(table)
-SAX.ignorableWhitespace(
+SAX.characters(
, 3)
SAX.startElement(br)
SAX.endElement(br)
-SAX.ignorableWhitespace(
+SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(