c/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2 synced 2025-03-28 21:33:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

parsing real HTML is a nightmare.

Browse Source 
- HTMLparser.c result/HTML/*: revamped the way the HTML
  parser handles end of tags or end of input
Daniel
This commit is contained in:
Daniel Veillard 2001-04-12 15:42:58 +00:00
parent 82daa81a8b
commit a3bfca59bf
14 changed files with 393 additions and 320 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ChangeLog
View File

@ -1,3 +1,8 @@
Thu Apr 12 17:41:09 CEST 2001 Daniel Veillard <Daniel.Veillard@imag.fr>
* HTMLparser.c result/HTML/*: revamped the way the HTML
parser handles end of tags or end of input
Thu Apr 12 10:50:34 CEST 2001 Daniel Veillard <Daniel.Veillard@imag.fr>
* tree.[ch] : added xmlDocCopyNode for gdome2 support

92
HTMLparser.c
View File

@ -445,7 +445,7 @@ htmlElemDesc html40ElementTable[] = {
{ "th", 0, 1, 0, 0, 0, 0, "table header cell" },
{ "thead", 0, 1, 0, 0, 0, 0, "table header " },
{ "title", 0, 0, 0, 0, 0, 0, "document title " },
{ "tr", 0, 1, 0, 0, 0, 0, "table row " },
{ "tr", 0, 0, 0, 0, 0, 0, "table row " },
{ "tt", 0, 0, 0, 0, 0, 0, "teletype or monospaced text style" },
{ "u", 0, 0, 0, 0, 1, 1, "underlined text style" },
{ "ul", 0, 0, 0, 0, 0, 0, "unordered list " },
@ -661,6 +661,7 @@ htmlCheckAutoClose(const xmlChar *newtag, const xmlChar *oldtag) {
* htmlAutoCloseOnClose:
* @ctxt: an HTML parser context
* @newtag: The new tag name
* @force: force the tag closure
*
* The HTmL DtD allows an ending tag to implicitely close other tags.
*/
@ -688,11 +689,7 @@ htmlAutoCloseOnClose(htmlParserCtxtPtr ctxt, const xmlChar *newtag) {
xmlGenericError(xmlGenericErrorContext,"htmlAutoCloseOnClose: %s closes %s\n", newtag, ctxt->name);
#endif
} else {
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
ctxt->sax->error(ctxt->userData,
"Opening and ending tag mismatch: %s and %s\n",
newtag, ctxt->name);
ctxt->wellFormed = 0;
return;
}
if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
ctxt->sax->endElement(ctxt->userData, ctxt->name);
@ -706,6 +703,39 @@ htmlAutoCloseOnClose(htmlParserCtxtPtr ctxt, const xmlChar *newtag) {
}
}
/**
* htmlAutoCloseOnEnd:
* @ctxt: an HTML parser context
*
* Close all remaining tags at the end of the stream
*/
static void
htmlAutoCloseOnEnd(htmlParserCtxtPtr ctxt) {
xmlChar *oldname;
int i;
if (ctxt->nameNr == 0)
return;
#ifdef DEBUG
xmlGenericError(xmlGenericErrorContext,"Close of stack: %d elements\n", ctxt->nameNr);
#endif
for (i = (ctxt->nameNr - 1);i >= 0;i--) {
#ifdef DEBUG
xmlGenericError(xmlGenericErrorContext,"%d : %s\n", i, ctxt->nameTab[i]);
#endif
if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
ctxt->sax->endElement(ctxt->userData, ctxt->name);
oldname = htmlnamePop(ctxt);
if (oldname != NULL) {
#ifdef DEBUG
xmlGenericError(xmlGenericErrorContext,"htmlAutoCloseOnEnd: popped %s\n", oldname);
#endif
xmlFree(oldname);
}
}
}
/**
* htmlAutoClose:
* @ctxt: an HTML parser context
@ -737,9 +767,8 @@ htmlAutoClose(htmlParserCtxtPtr ctxt, const xmlChar *newtag) {
}
}
if (newtag == NULL) {
htmlAutoCloseOnClose(ctxt, BAD_CAST"head");
htmlAutoCloseOnClose(ctxt, BAD_CAST"body");
htmlAutoCloseOnClose(ctxt, BAD_CAST"html");
htmlAutoCloseOnEnd(ctxt);
return;
}
while ((newtag == NULL) && (ctxt->name != NULL) &&
((xmlStrEqual(ctxt->name, BAD_CAST"head")) ||
@ -3266,10 +3295,8 @@ htmlParseContent(htmlParserCtxtPtr ctxt) {
* Fourth : end of the resource
*/
else if (CUR == 0) {
int level = ctxt->nodeNr;
htmlAutoClose(ctxt, NULL);
if (level == ctxt->nodeNr)
break;
htmlAutoCloseOnEnd(ctxt);
break;
}
/*
@ -3439,29 +3466,6 @@ htmlParseElement(htmlParserCtxtPtr ctxt) {
if (ctxt->nameNr < depth) break;
}
if (!IS_CHAR(CUR)) {
/************
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
ctxt->sax->error(ctxt->userData,
"Premature end of data in tag %s\n", currentNode);
ctxt->wellFormed = 0;
*************/
/*
* end of parsing of this node.
*/
nodePop(ctxt);
oldname = htmlnamePop(ctxt);
#ifdef DEBUG
xmlGenericError(xmlGenericErrorContext,"Premature end of tag %s : popping out %s\n", name, oldname);
#endif
if (oldname != NULL)
xmlFree(oldname);
if (currentNode != NULL)
xmlFree(currentNode);
return;
}
/*
* Capture end position and add node
*/
@ -3472,6 +3476,10 @@ htmlParseElement(htmlParserCtxtPtr ctxt) {
node_info.node = ctxt->node;
xmlParserAddNodeInfo(ctxt, &node_info);
}
if (!IS_CHAR(CUR)) {
htmlAutoCloseOnEnd(ctxt);
}
if (currentNode != NULL)
xmlFree(currentNode);
}
@ -3556,7 +3564,7 @@ htmlParseDocument(htmlParserCtxtPtr ctxt) {
* autoclose
*/
if (CUR == 0)
htmlAutoClose(ctxt, NULL);
htmlAutoCloseOnEnd(ctxt);
/*
@ -3899,7 +3907,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
else
avail = in->buf->buffer->use - (in->cur - in->base);
if ((avail == 0) && (terminate)) {
htmlAutoClose(ctxt, NULL);
htmlAutoCloseOnEnd(ctxt);
if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
/*
* SAX: end of the document processing.
@ -4077,9 +4085,6 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
goto done;
} else {
ctxt->errNo = XML_ERR_DOCUMENT_END;
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
ctxt->sax->error(ctxt->userData,
"Extra content at the end of the document\n");
ctxt->wellFormed = 0;
ctxt->instate = XML_PARSER_EOF;
#ifdef DEBUG_PUSH
@ -4491,7 +4496,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
}
done:
if ((avail == 0) && (terminate)) {
htmlAutoClose(ctxt, NULL);
htmlAutoCloseOnEnd(ctxt);
if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
/*
* SAX: end of the document processing.
@ -4555,9 +4560,6 @@ htmlParseChunk(htmlParserCtxtPtr ctxt, const char *chunk, int size,
(ctxt->instate != XML_PARSER_EPILOG) &&
(ctxt->instate != XML_PARSER_MISC)) {
ctxt->errNo = XML_ERR_DOCUMENT_END;
if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
ctxt->sax->error(ctxt->userData,
"Extra content at the end of the document\n");
ctxt->wellFormed = 0;
}
if (ctxt->instate != XML_PARSER_EOF) {

3
result/HTML/autoclose3.html.err
View File

@ -1,3 +0,0 @@
./test/HTML/autoclose3.html:4: error: Opening and ending tag mismatch: body and ul
^

1
result/HTML/autoclose3.html.sax
View File

@ -13,7 +13,6 @@ SAX.startElement(li)
SAX.characters(item 2
, 7)
SAX.endElement(li)
SAX.error: Opening and ending tag mismatch: body and ul
SAX.endElement(ul)
SAX.endElement(body)
SAX.endElement(html)

27
result/HTML/doc3.htm
View File

@ -803,15 +803,15 @@ eval("page" + id + " = window.open(URL, '" + id + "', 'toolbars=0, scrollbars=0,
<!-- <input type="submit" name="npunsubscribe" value="Unsubscribe" style="font-size: xx-small; font-family: Verdana; font-weight: bold; color: #ffffff; background-color: #000000;"> -->
</font>
</form>
<font size="1"><form action="http://bp6.gamesquad.net/cgi-bin/news/viewnews.cgi?search" method="post">Search news<br>
<font size="1">
<form action="http://bp6.gamesquad.net/cgi-bin/news/viewnews.cgi?search" method="post">Search news<br>
<input name="searchstring" size="13">
<br>
<input name="submit" style="BACKGROUND-COLOR: #000000; COLOR: #ffffff; FONT-FAMILY: Verdana; FONT-SIZE: xx-small; FONT-WEIGHT: bold" type="submit" value="Submit">
<br>
<a href="http://bp6.gamesquad.net/cgi-bin/news/viewnews.cgi?newsall">News
archive</a>
</form></font>
</center></td></tr></tbody></table>
</form>
<!-- <TABLE BORDER="0" CELLPADDING="0" CELLSPACING="0" WIDTH="100%" BGCOLOR="silver">
<TR>
<TD WIDTH="100%">
@ -851,19 +851,21 @@ eval("page" + id + " = window.open(URL, '" + id + "', 'toolbars=0, scrollbars=0,
}
// -->
</script>
<b><noscript></noscript></b>
<b><noscript>
<a href="http://www.goto.com/d/search/ssn/?fromGIF=true" target="_blank"><img align="bottom" border="0" height="90" ismap src="doc3_files/100x90.gif" width="100"></a>
<b><a href="http://www.goto.com/d/search/ssn/?fromGIF=true" target="_blank"></a></b>
<b></b>
<b><!-- END GoTo.com Search Box --></b>
<!-- Pricewatch Search Box --><form action="http://www.pricewatch.com/search/search.asp" method="get" target="_Blank"><center><p>
<!-- Pricewatch Search Box --><form action="http://www.pricewatch.com/search/search.asp" method="get" target="_Blank">
<center>
<p>
<b><font color="white" face="ARIAL, HELVETICA" size="1">PC Price
Search<br>
</font></b>
<input maxlength="30" name="criteria" size="10">
<br>
<input name="submit" style="BACKGROUND-COLOR: #000000; COLOR: #ffffff; FONT-FAMILY: Verdana; FONT-SIZE: xx-small; FONT-WEIGHT: bold" type="submit" value="Search">
</p></center></form>
</p>
<!-- Pricewatch Search Box --><a href="http://www.puicorp.com/bp6specials.htm" target="_BLANK"><img src="doc3_files/puibp6.gif"></a>
<br>
<br>
@ -875,9 +877,7 @@ eval("page" + id + " = window.open(URL, '" + id + "', 'toolbars=0, scrollbars=0,
<br>BP6.COM
Special<br>Code:BP6-hd</font>
</a>
</td></tr></tbody></table>
</center></td>
</tr></tbody></table>
</center>
<table bgcolor="silver" border="0" cellpadding="0" cellspacing="0" height="100%" width="100%"><tbody><tr><td width="100%"> </td></tr></tbody></table>
<!-- </TABLE>--><center></center>
<tr><td colspan="3" valign="TOP" height="70"> </td></tr>
@ -889,7 +889,14 @@ eval("page" + id + " = window.open(URL, '" + id + "', 'toolbars=0, scrollbars=0,
</p></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>
<script> window.open=NS_ActualOpen; </script>
</form>
</noscript></b>
</td></tr></tbody></table>
</font>
</center></td></tr></tbody></table>
</center></td>
</tr></tbody></table>
</div>
</body>
</html>

76
result/HTML/doc3.htm.err
View File

@ -3,19 +3,19 @@
^
./test/HTML/doc3.htm:47: error: htmlParseEntityRef: expecting ';'
href="http://ads.gamesquad.net/addclick.exe/adclick.cgi?REGION=game|tech|ent&i
^
^
./test/HTML/doc3.htm:47: error: htmlParseEntityRef: expecting ';'
_top"><img src="http://ads.gamesquad.net/addclick.exe/adcycle.cgi?group=52&medi
^
^
./test/HTML/doc3.htm:47: error: htmlParseEntityRef: expecting ';'
><img src="http://ads.gamesquad.net/addclick.exe/adcycle.cgi?group=52&media=1&i
^
^
./test/HTML/doc3.htm:140: error: error parsing attribute name
width=70 Gentus?.?></A><BR><A
^
./test/HTML/doc3.htm:143: error: Unexpected end tag : p
</P></TD></TR></TBODY></TABLE></CENTER></TD></TR></TBODY></TABLE></CENTER></P
^
^
./test/HTML/doc3.htm:231: error: Unexpected end tag : font
Specials<BR><BR></FONT></A><BR></FONT></A><B><FONT color=yellow
^
@ -24,25 +24,37 @@ _top"><img src="http://ads.gamesquad.net/addclick.exe/adcycle.cgi?group=52&medi
^
./test/HTML/doc3.htm:742: error: htmlParseEntityRef: expecting ';'
er=0 alt="Advertisement" src="http://ads.adflight.com/ad_static.asp?pid=2097&si
^
^
./test/HTML/doc3.htm:742: error: htmlParseEntityRef: expecting ';'
Advertisement" src="http://ads.adflight.com/ad_static.asp?pid=2097&sid=1881&asi
^
^
./test/HTML/doc3.htm:742: error: Unexpected end tag : li
light.com/ad_static.asp?pid=2097&sid=1881&asid=7708"></a></IFRAME></CENTER></LI
^
^
./test/HTML/doc3.htm:742: error: Unexpected end tag : font
om/ad_static.asp?pid=2097&sid=1881&asid=7708"></a></IFRAME></CENTER></LI></FONT
^
^
./test/HTML/doc3.htm:742: error: Unexpected end tag : p
=7708"></a></IFRAME></CENTER></LI></FONT></TD></TR></TBODY></TABLE></CENTER></P
^
^
./test/HTML/doc3.htm:767: error: Opening and ending tag mismatch: font and form
archive</A></FONT> </FORM></CENTER></TD></TR></TBODY></TABLE><!--
^
./test/HTML/doc3.htm:767: error: Unexpected end tag : form
./test/HTML/doc3.htm:767: error: Opening and ending tag mismatch: center and font
archive</A></FONT> </FORM></CENTER></TD></TR></TBODY></TABLE><!--
^
^
./test/HTML/doc3.htm:767: error: Opening and ending tag mismatch: td and font
archive</A></FONT> </FORM></CENTER></TD></TR></TBODY></TABLE><!--
^
./test/HTML/doc3.htm:767: error: Opening and ending tag mismatch: tr and font
archive</A></FONT> </FORM></CENTER></TD></TR></TBODY></TABLE><!--
^
./test/HTML/doc3.htm:767: error: Opening and ending tag mismatch: tbody and font
archive</A></FONT> </FORM></CENTER></TD></TR></TBODY></TABLE><!--
^
./test/HTML/doc3.htm:767: error: Opening and ending tag mismatch: table and font
archive</A></FONT> </FORM></CENTER></TD></TR></TBODY></TABLE><!--
^
./test/HTML/doc3.htm:790: error: Unexpected end tag : iframe
document.write("42DF8478957377></IFRAME>");
^
@ -61,7 +73,7 @@ om/ad_static.asp?pid=2097&sid=1881&asid=7708"></a></IFRAME></CENTER></LI></FONT
./test/HTML/doc3.htm:815: error: Unexpected end tag : a
</A></A></B><B></NOSCRIPT></B><B><!-- END GoTo.com Search Box --></
^
./test/HTML/doc3.htm:815: error: Unexpected end tag : noscript
./test/HTML/doc3.htm:815: error: Opening and ending tag mismatch: noscript and b
</A></A></B><B></NOSCRIPT></B><B><!-- END GoTo.com Search Box --></
^
./test/HTML/doc3.htm:821: error: Opening and ending tag mismatch: form and center
@ -70,36 +82,48 @@ om/ad_static.asp?pid=2097&sid=1881&asid=7708"></a></IFRAME></CENTER></LI></FONT
./test/HTML/doc3.htm:828: error: Unexpected end tag : p
Special<BR>Code:BP6-hd</FONT></A> </P></CENTER></TD></TR></TBODY></
^
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: center and td
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: td and form
Special<BR>Code:BP6-hd</FONT></A> </P></CENTER></TD></TR></TBODY></
^
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: center and tbody
^
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: tr and form
Special<BR>Code:BP6-hd</FONT></A> </P></CENTER></TD></TR></TBODY></
^
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: center and table
^
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: tbody and form
Special<BR>Code:BP6-hd</FONT></A> </P></CENTER></TD></TR></TBODY></
^
^
./test/HTML/doc3.htm:828: error: Opening and ending tag mismatch: table and form
Special<BR>Code:BP6-hd</FONT></A> </P></CENTER></TD></TR></TBODY></TABL
^
./test/HTML/doc3.htm:834: error: Unexpected end tag : p
width="100%">&nbsp;</TD></TR></TBODY></TABLE></P></CENTER></TR></TBODY></TABLE>
^
./test/HTML/doc3.htm:834: error: Unexpected end tag : center
./test/HTML/doc3.htm:834: error: Opening and ending tag mismatch: center and form
width="100%">&nbsp;</TD></TR></TBODY></TABLE></P></CENTER></TR></TBODY></TABLE>
^
./test/HTML/doc3.htm:834: error: Unexpected end tag : tr
./test/HTML/doc3.htm:834: error: Opening and ending tag mismatch: tr and form
width="100%">&nbsp;</TD></TR></TBODY></TABLE></P></CENTER></TR></TBODY></TABLE>
^
./test/HTML/doc3.htm:834: error: Unexpected end tag : tbody
./test/HTML/doc3.htm:834: error: Opening and ending tag mismatch: tbody and form
width="100%">&nbsp;</TD></TR></TBODY></TABLE></P></CENTER></TR></TBODY></TABLE>
^
./test/HTML/doc3.htm:834: error: Unexpected end tag : table
./test/HTML/doc3.htm:834: error: Opening and ending tag mismatch: table and form
width="100%">&nbsp;</TD></TR></TBODY></TABLE></P></CENTER></TR></TBODY></TABLE>
^
./test/HTML/doc3.htm:835: error: Unexpected end tag : td
^
./test/HTML/doc3.htm:835: error: Opening and ending tag mismatch: td and form
<CENTER></CENTER></TD></TR><TR><TD COLSPAN="3" VALIGN="TOP"
^
./test/HTML/doc3.htm:835: error: Unexpected end tag : tr
./test/HTML/doc3.htm:835: error: Opening and ending tag mismatch: tr and form
<CENTER></CENTER></TD></TR><TR><TD COLSPAN="3" VALIGN="TOP"
^
./test/HTML/doc3.htm:836: error: Unexpected end tag : table
./test/HTML/doc3.htm:836: error: Opening and ending tag mismatch: table and form
HEIGHT="70">&nbsp;</TD> </TR></TABLE>
^
./test/HTML/doc3.htm:844: error: Opening and ending tag mismatch: div and form
,arial">Site design by Tim Brinkley</FONT> </TD> </TR> --></TBODY></TABLE></DI
^
./test/HTML/doc3.htm:846: error: Opening and ending tag mismatch: body and form
</BODY></HTML>
^
./test/HTML/doc3.htm:846: error: Opening and ending tag mismatch: html and form
</BODY></HTML>
^

78
result/HTML/doc3.htm.sax
View File

@ -2658,15 +2658,13 @@ SAX.characters(News
archive, 26)
SAX.endElement(a)
SAX.error: Opening and ending tag mismatch: font and form
SAX.endElement(form)
SAX.endElement(font)
SAX.characters( , 1)
SAX.error: Unexpected end tag : form
SAX.endElement(center)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(tbody)
SAX.endElement(table)
SAX.endElement(form)
SAX.error: Opening and ending tag mismatch: center and font
SAX.error: Opening and ending tag mismatch: td and font
SAX.error: Opening and ending tag mismatch: tr and font
SAX.error: Opening and ending tag mismatch: tbody and font
SAX.error: Opening and ending tag mismatch: table and font
SAX.comment( <TABLE BORDER="0" CELLPADDING="0" CELLSPACING="0" WIDTH="100%" BGCOLOR="silver">
<TR>
<TD WIDTH="100%">
@ -2712,8 +2710,6 @@ SAX.characters(
SAX.startElement(b)
SAX.startElement(noscript)
SAX.error: Opening and ending tag mismatch: b and noscript
SAX.endElement(noscript)
SAX.endElement(b)
SAX.startElement(a, href='http://www.goto.com/d/search/ssn/?fromGIF=true', target='_blank')
SAX.startElement(img, align='bottom', border='0', height='90', ismap, src='doc3_files/100x90.gif', width='100')
SAX.endElement(img)
@ -2726,7 +2722,7 @@ SAX.endElement(a)
SAX.error: Unexpected end tag : a
SAX.endElement(b)
SAX.startElement(b)
SAX.error: Unexpected end tag : noscript
SAX.error: Opening and ending tag mismatch: noscript and b
SAX.endElement(b)
SAX.startElement(b)
SAX.comment( END GoTo.com Search Box )
@ -2759,8 +2755,6 @@ SAX.characters(
, 15)
SAX.endElement(p)
SAX.error: Opening and ending tag mismatch: form and center
SAX.endElement(center)
SAX.endElement(form)
SAX.comment( Pricewatch Search Box )
SAX.startElement(a, href='http://www.puicorp.com/bp6specials.htm', target='_BLANK')
SAX.startElement(img, src='doc3_files/puibp6.gif')
@ -2789,18 +2783,11 @@ SAX.endElement(font)
SAX.endElement(a)
SAX.characters( , 1)
SAX.error: Unexpected end tag : p
SAX.error: Opening and ending tag mismatch: center and td
SAX.endElement(td)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: center and tbody
SAX.endElement(tbody)
SAX.error: Opening and ending tag mismatch: center and table
SAX.endElement(table)
SAX.endElement(center)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(tbody)
SAX.endElement(table)
SAX.error: Opening and ending tag mismatch: td and form
SAX.error: Opening and ending tag mismatch: tr and form
SAX.error: Opening and ending tag mismatch: tbody and form
SAX.error: Opening and ending tag mismatch: table and form
SAX.characters(
, 8)
SAX.startElement(table, bgcolor='silver', border='0', cellpadding='0', cellspacing='0', height='100%', width='100%')
@ -2819,24 +2806,24 @@ SAX.endElement(tr)
SAX.endElement(tbody)
SAX.endElement(table)
SAX.error: Unexpected end tag : p
SAX.error: Unexpected end tag : center
SAX.error: Unexpected end tag : tr
SAX.error: Unexpected end tag : tbody
SAX.error: Unexpected end tag : table
SAX.error: Opening and ending tag mismatch: center and form
SAX.error: Opening and ending tag mismatch: tr and form
SAX.error: Opening and ending tag mismatch: tbody and form
SAX.error: Opening and ending tag mismatch: table and form
SAX.comment( </TABLE>)
SAX.characters(
, 2)
SAX.startElement(center)
SAX.endElement(center)
SAX.error: Unexpected end tag : td
SAX.error: Unexpected end tag : tr
SAX.error: Opening and ending tag mismatch: td and form
SAX.error: Opening and ending tag mismatch: tr and form
SAX.startElement(tr)
SAX.startElement(td, colspan='3', valign='TOP', height='70')
SAX.characters(&nbsp;, 2)
SAX.endElement(td)
SAX.characters( , 1)
SAX.endElement(tr)
SAX.error: Unexpected end tag : table
SAX.error: Opening and ending tag mismatch: table and form
SAX.characters(
, 2)
SAX.startElement(table, border='0', width='780')
@ -2871,16 +2858,37 @@ SAX.endElement(tr)
SAX.comment( <TR> <TD WIDTH="780"> <P ALIGN="CENTER"><FONT SIZE="1" COLOR="#999999" FACE="Verdana,arial">Site design by Tim Brinkley</FONT> </TD> </TR> )
SAX.endElement(tbody)
SAX.endElement(table)
SAX.endElement(div)
SAX.ignorableWhitespace(
SAX.error: Opening and ending tag mismatch: div and form
SAX.characters(
, 2)
SAX.startElement(script)
SAX.cdata( window.open=NS_ActualOpen; , 28)
SAX.endElement(script)
SAX.characters(
, 2)
SAX.error: Opening and ending tag mismatch: body and form
SAX.error: Opening and ending tag mismatch: html and form
SAX.ignorableWhitespace(
, 2)
SAX.endElement(form)
SAX.endElement(noscript)
SAX.endElement(b)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(tbody)
SAX.endElement(table)
SAX.endElement(font)
SAX.endElement(center)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(tbody)
SAX.endElement(table)
SAX.endElement(center)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(tbody)
SAX.endElement(table)
SAX.endElement(div)
SAX.endElement(body)
SAX.endElement(html)
SAX.ignorableWhitespace(
, 2)
SAX.endDocument()

4
result/HTML/entities.html.err
View File

@ -1,9 +1,9 @@
./test/HTML/entities.html:1: error: htmlParseEntityRef: expecting ';'
<p tst="a&amp;b" tst2="a&b" tst3="a & b">
^
^
./test/HTML/entities.html:1: error: htmlParseEntityRef: no name
<p tst="a&amp;b" tst2="a&b" tst3="a & b">
^
^
./test/HTML/entities.html:3: error: htmlParseEntityRef: expecting ';'
a&b
^

4
result/HTML/test3.html
View File

@ -38,7 +38,8 @@
<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>
<ul><li>
<b>Link to </b>
<a href="HumanInterface.Package.html#HumanInterface.Package">HumanInterface</a>
@ -54,5 +55,6 @@
<a href="DataManagement.Package.html#DataManagement.Package">DataManagement</a>
</li></ul>
<dir></dir>
</h4>
</body>
</html>

6
result/HTML/test3.html.err
View File

@ -7,6 +7,6 @@
./test/HTML/test3.html:27: error: Opening and ending tag mismatch: h4 and b
<h4><b>Links</h4></b>
^
./test/HTML/test3.html:27: error: Unexpected end tag : b
<h4><b>Links</h4></b>
^
./test/HTML/test3.html:34: error: Opening and ending tag mismatch: html and h4
</html>
^

20
result/HTML/test3.html.sax
View File

@ -171,9 +171,7 @@ SAX.startElement(b)
SAX.characters(Links, 5)
SAX.error: Opening and ending tag mismatch: h4 and b
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 +183,11 @@ SAX.characters(HumanInterface, 14)
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 +199,11 @@ SAX.characters(DataManagement.FlatFile, 23)
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)
@ -217,14 +215,16 @@ SAX.characters(DataManagement, 14)
SAX.endElement(a)
SAX.endElement(li)
SAX.endElement(ul)
SAX.ignorableWhitespace(
SAX.characters(
, 2)
SAX.startElement(dir)
SAX.endElement(dir)
SAX.characters(
, 2)
SAX.error: Opening and ending tag mismatch: html and h4
SAX.ignorableWhitespace(
, 2)
SAX.endElement(h4)
SAX.endElement(body)
SAX.endElement(html)
SAX.ignorableWhitespace(
, 2)
SAX.endDocument()

83
result/HTML/wired.html
View File

@ -127,17 +127,17 @@
<tr><td bgcolor="#CCFFCC"><font size="1" face="Verdana, Arial, Helvetica, sans-serif" color="#000000"><a href="/news/news/reuters/sports/">Sports</a></font></td></tr>
<tr><td bgcolor="#99FF99"><font size="1" face="Verdana, Arial, Helvetica, sans-serif" color="#000000"><a href="/news/news/reuters/business/">Finance</a></font></td></tr>
<!-- End upper left nav --><!-- Begin lower Left Nav --><tr><td bgcolor="#FF0000"><font face="Verdana, Arial, Helvetica, sans-serif" color="#FFFFFF"><b><font size="1">FREE DELIVERY</font></b></font></td></tr>
<tr><td bgcolor="#99FF99"><table cellspacing="0" cellpadding="0" border="0"><tr>
<td bgcolor="#99FF99"><form action="http://r.hotwired.com/r/hw_wm_r_nav_nwsltr/http://perl.hotwired.com/massmail/cgiParser.cgi" method="get" target="_top">
<tr><td bgcolor="#99FF99"><table cellspacing="0" cellpadding="0" border="0">
<tr><td bgcolor="#99FF99"><form action="http://r.hotwired.com/r/hw_wm_r_nav_nwsltr/http://perl.hotwired.com/massmail/cgiParser.cgi" method="get" target="_top">
<input type="hidden" name="success_page" value="http://www.hotwired.com/email/signup/wirednews-ascii.html">
<input type="hidden" name="failure_page" value="http://www.hotwired.com/email/signup/wirednews-ascii.html">
<input type="hidden" name="LIST" value="wn_ascii">
<input type="hidden" name="SOURCE" value="other">
<input type="hidden" name="ACTION" value="subscribe">
<input type="TEXT" name="from" size="10" value="enter email">&nbsp;
</form></td>
<td valign="top" bgcolor="#99FF99"><input type="SUBMIT" name="SUBMIT" value="GO"></td>
</tr></table></td></tr>
<td valign="top" bgcolor="#99FF99"><input type="SUBMIT" name="SUBMIT" value="GO"></td>
</form></td></tr>
<tr><td bgcolor="#FF0000"><font face="Verdana, Arial, Helvetica, sans-serif" color="#FFFFFF"><b><font size="1">STOCKS</font></b></font></td></tr>
<tr><td bgcolor="#99FF99"><font face="Verdana, Arial, Helvetica, sans-serif" size="1">Get Quote:</font></td></tr>
<tr><td bgcolor="#99FF99" marginwidth="0" marginheight="0"><form method="get" action="http://r.wired.com/r/10020/http://stocks.wired.com/stocks_quotes.asp">
@ -206,7 +206,6 @@
</option>
</select></font>
</form></td></tr>
<tr align="left" valign="top"><td valign="top" bgcolor="#CCFFCC">
<input type="submit" value="GO">
<img src="http://barnesandnoble.bfast.com/booklink/serve?sourceid=383471&amp;is_search=Y" border="0" align="top">
@ -219,7 +218,7 @@
</font>
<br clear="all">
</p></td></tr>
</table></td></tr>
</form></td></tr>
<!-- END B&N spot --><!-- BEGIN MAGAZINE SPOT --><tr><td bgcolor="#000000"><font color="#FFFFFF" face="Verdana, Arial, Helvetica, sans-serif" size="1"><b>WIRED
MAGAZINE </b></font></td></tr>
<tr><td bgcolor="#FFFF99" align="CENTER"><font face="verdana, arial, helvetica, sans-serif" size="1">
@ -272,11 +271,7 @@ or <a href="/news/pointcast/0,1366,,00.html">PointCast</a>
</font>
<br>
<!-- TRACKING --><img src="http://www.wired.com/special/modx/news.gif" height="1" width="1" alt="">
</font>
</td></tr>
</table>
<!-- end lower left side Navigation --><!-- CONTENT TABLE --><table border="0" width="447" cellspacing="0" cellpadding="0" bordercolor="#66FF00">
<tr>
<!-- end lower left side Navigation --><!-- CONTENT TABLE --><table border="0" width="447" cellspacing="0" cellpadding="0" bordercolor="#66FF00"><tr>
<td valign="TOP" align="LEFT" rowspan="2">
<img src="http://static.wired.com/news/images/spacer.gif" height="1" width="15" alt="">
<br>
@ -316,10 +311,6 @@ or <a href="/news/pointcast/0,1366,,00.html">PointCast</a>
<font size="1" face="Arial, Geneva, sans-serif" color="#000000">Readers on Apple's G4 ... AOL's passwords ... MS vs. Linux.</font>
<br>
<br>
</font>
</font>
</td>
</tr>
<!-- Commentary Frag End --><tr>
<td align="left" bgcolor="#000000">&nbsp;</td>
<td bgcolor="#000000"><font size="1" face="Verdana, Arial, Helvetica, sans-serif" color="#FFFFFF"><b>CURRENT HOO-HA</b></font></td>
@ -390,9 +381,8 @@ or <a href="/news/pointcast/0,1366,,00.html">PointCast</a>
<font size="2" face="Arial,Helvetica, sans-serif"><b><a href="/news/exec/0,1370,,00.html">Executive Summary</a></b></font>
<br>
<font size="1" face="Arial, Helvetica, sans-serif" color="#000000">CEOs, COOs, CIOs unite. <br>
<i>Sponsored by <a href="http://r.wired.com/r/wn_exec_r_vign/http://www.vignette.com/" style="text-decoration:none"><font color="#000000">Vignette</font></a>
</i>
</font>
<i>Sponsored by <a href="http://r.wired.com/r/wn_exec_r_vign/http://www.vignette.com/" style="text-decoration:none">
<font color="#000000">Vignette</font>
<br>
<br>
<font size="2" face="Arial,Helvetica, sans-serif"><b><a href="/news/school/0,1383,,00.html">Making the Grade</a></b></font>
@ -409,10 +399,8 @@ or <a href="/news/pointcast/0,1366,,00.html">PointCast</a>
<font size="1" face="Arial, Helvetica, sans-serif" color="#000000">An IS/IT resource <br>
<i>Sponsored by <a href="http://r.wired.com/r/wn_is_r_ssec/http://ad.doubleclick.net/clk;653163;3599571;s?http://www.sprintbiz.com/s
ervlet/appservlet?from=/wired/sprint/&amp;template=/security/security.html&amp;SITE=
wired.com&amp;BANNER=Sprint" style="text-decoration:none"><font color="#000000">Sprint</font></a>
</i>
</font>
</font>
wired.com&amp;BANNER=Sprint" style="text-decoration:none">
<font color="#000000">Sprint</font>
<br>
<br>
<font size="2" face="Arial,Helvetica, sans-serif"><b><a href="/news/y2k/0,1360,,00.html">Y2K Watch</a></b></font>
@ -423,16 +411,6 @@ wired.com&amp;BANNER=Sprint" style="text-decoration:none"><font color="#000000">
<br>
<font face="Arial, Helvetica, sans-serif" size="2"><b><i><a href="/news/special_reports/1,1293,,00.html">More Hoo-Ha</a></i></b></font>
<br>&nbsp;<br>
</font>
</font>
</font>
</font>
</font>
</font>
</font>
</font>
</td>
</tr>
<!-- start of Gen News --><tr>
<td bgcolor="#000000">&nbsp;</td>
<td bgcolor="#000000"><font size="1" face="Verdana, Arial, Helvetica, sans-serif" color="#FFFFFF"><b>MEANWHILE...</b></font></td>
@ -456,9 +434,7 @@ Contruction workers in Berlin opened an old wound in the German psyche this week
<br>
</td>
</tr>
<!-- end of Gen News -->
</table>
<font size="1">&nbsp;<br>
<!-- end of Gen News --><font size="1">&nbsp;<br>
</font>
<br>
<font face="Verdana, Arial, Geneva, sans-serif" size="2"><b><i>Other Top Stories</i></b></font>
@ -586,10 +562,7 @@ Contruction workers in Berlin opened an old wound in the German psyche this week
<font face="geneva, arial" size="2">BBC News</font>
<br>
<br>
<!-- SQL above --><!-- - - - - - - - - - - - - -->
</td>
</tr>
<tr>
<!-- SQL above --><!-- - - - - - - - - - - - - --><tr>
<td valign="TOP" align="LEFT">
<img src="http://static.wired.com/news/images/spacer.gif" height="1" width="280" alt="">
<br>
@ -627,7 +600,35 @@ Contruction workers in Berlin opened an old wound in the German psyche this week
<td valign="TOP" align="LEFT"><img src="http://static.wired.com/news/images/spacer.gif" height="1" width="5" alt=""></td>
<td valign="TOP" align="LEFT"></td>
</tr>
</table>
<br>
</font>
</a>
</i>
</font>
</font>
</a>
</i>
</font>
</font>
</font>
</font>
</font>
</font>
</font>
</font>
</td>
</tr>
</font>
</font>
</td>
</tr>
</table>
</td>
</tr></table>
</font>
</td></tr>
</table></td></tr>
</table></td></tr>
</table>
</body>
</html>

197
result/HTML/wired.html.err
View File

@ -1,162 +1,162 @@
./test/HTML/wired.html:6: error: htmlParseEntityRef: expecting ';'
<FORM METHOD=GET ACTION="http://nsads.hotwired.com/event.ng/Type=click&ProfileI
^
^
./test/HTML/wired.html:6: error: htmlParseEntityRef: expecting ';'
D=GET ACTION="http://nsads.hotwired.com/event.ng/Type=click&ProfileID=9688&RunI
^
^
./test/HTML/wired.html:6: error: htmlParseEntityRef: expecting ';'
N="http://nsads.hotwired.com/event.ng/Type=click&ProfileID=9688&RunID=14074&AdI
^
^
./test/HTML/wired.html:6: error: htmlParseEntityRef: expecting ';'
s.hotwired.com/event.ng/Type=click&ProfileID=9688&RunID=14074&AdID=22584&GroupI
^
^
./test/HTML/wired.html:6: error: htmlParseEntityRef: expecting ';'
com/event.ng/Type=click&ProfileID=9688&RunID=14074&AdID=22584&GroupID=1&FamilyI
^
^
./test/HTML/wired.html:6: error: htmlParseEntityRef: expecting ';'
pe=click&ProfileID=9688&RunID=14074&AdID=22584&GroupID=1&FamilyID=2684&TagValue
^
^
./test/HTML/wired.html:52: error: htmlParseEntityRef: expecting ';'
" align="RIGHT"><a href="http://nsads.hotwired.com/event.ng/Type=click&ProfileI
^
^
./test/HTML/wired.html:52: error: htmlParseEntityRef: expecting ';'
GHT"><a href="http://nsads.hotwired.com/event.ng/Type=click&ProfileID=5597&RunI
^
^
./test/HTML/wired.html:52: error: htmlParseEntityRef: expecting ';'
f="http://nsads.hotwired.com/event.ng/Type=click&ProfileID=5597&RunID=17167&AdI
^
^
./test/HTML/wired.html:52: error: htmlParseEntityRef: expecting ';'
s.hotwired.com/event.ng/Type=click&ProfileID=5597&RunID=17167&AdID=22588&GroupI
^
^
./test/HTML/wired.html:52: error: htmlParseEntityRef: expecting ';'
com/event.ng/Type=click&ProfileID=5597&RunID=17167&AdID=22588&GroupID=1&FamilyI
^
^
./test/HTML/wired.html:52: error: htmlParseEntityRef: expecting ';'
pe=click&ProfileID=5597&RunID=17167&AdID=22588&GroupID=1&FamilyID=3228&TagValue
^
^
./test/HTML/wired.html:70: error: Tag nobr invalid
<td bgcolor="#FF0000" align="left" valign="center"><nobr><img src="http://stati
^
./test/HTML/wired.html:89: error: htmlParseEntityRef: expecting ';'
on value="http://search.hotwired.com/search97/s97.vts?Action=FilterSearch&Filte
^
^
./test/HTML/wired.html:89: error: htmlParseEntityRef: expecting ';'
d.com/search97/s97.vts?Action=FilterSearch&Filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:89: error: htmlParseEntityRef: expecting ';'
ction=FilterSearch&Filter=docs_filter.hts&ResultTemplate=vignette.hts&Collectio
^
^
./test/HTML/wired.html:89: error: htmlParseEntityRef: expecting ';'
Filter=docs_filter.hts&ResultTemplate=vignette.hts&Collection=vignette&QueryMod
^
^
./test/HTML/wired.html:89: error: htmlParseEntityRef: expecting ';'
ter.hts&ResultTemplate=vignette.hts&Collection=vignette&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:90: error: htmlParseEntityRef: expecting ';'
on value="http://search.hotwired.com/search97/s97.vts?Action=FilterSearch&Filte
^
^
./test/HTML/wired.html:90: error: htmlParseEntityRef: expecting ';'
d.com/search97/s97.vts?Action=FilterSearch&Filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:90: error: htmlParseEntityRef: expecting ';'
tion=FilterSearch&Filter=docs_filter.hts&ResultTemplate=webmonkey.hts&Collectio
^
^
./test/HTML/wired.html:90: error: htmlParseEntityRef: expecting ';'
lter=docs_filter.hts&ResultTemplate=webmonkey.hts&Collection=webmonkey&QueryMod
^
^
./test/HTML/wired.html:90: error: htmlParseEntityRef: expecting ';'
r.hts&ResultTemplate=webmonkey.hts&Collection=webmonkey&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:91: error: htmlParseEntityRef: expecting ';'
="http://search.hotwired.com/search97/s97.vts?collection=webmonkey_guides&Actio
^
^
./test/HTML/wired.html:91: error: htmlParseEntityRef: expecting ';'
ired.com/search97/s97.vts?collection=webmonkey_guides&Action=FilterSearch&filte
^
^
./test/HTML/wired.html:91: error: htmlParseEntityRef: expecting ';'
ction=webmonkey_guides&Action=FilterSearch&filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:91: error: htmlParseEntityRef: expecting ';'
ilterSearch&filter=docs_filter.hts&ResultTemplate=webmonkey_guides.hts&QueryMod
^
^
./test/HTML/wired.html:91: error: htmlParseEntityRef: expecting ';'
ter=docs_filter.hts&ResultTemplate=webmonkey_guides.hts&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:92: error: htmlParseEntityRef: expecting ';'
on value="http://search.hotwired.com/search97/s97.vts?collection=hotwired&Actio
^
^
./test/HTML/wired.html:92: error: htmlParseEntityRef: expecting ';'
rch.hotwired.com/search97/s97.vts?collection=hotwired&Action=FilterSearch&filte
^
^
./test/HTML/wired.html:92: error: htmlParseEntityRef: expecting ';'
ts?collection=hotwired&Action=FilterSearch&filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:92: error: htmlParseEntityRef: expecting ';'
ilterSearch&filter=docs_filter.hts&ResultTemplate=hotwired_archive.hts&QueryMod
^
^
./test/HTML/wired.html:92: error: htmlParseEntityRef: expecting ';'
ter=docs_filter.hts&ResultTemplate=hotwired_archive.hts&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:93: error: htmlParseEntityRef: expecting ';'
on value="http://search.hotwired.com/search97/s97.vts?Action=FilterSearch&Filte
^
^
./test/HTML/wired.html:93: error: htmlParseEntityRef: expecting ';'
d.com/search97/s97.vts?Action=FilterSearch&Filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:93: error: htmlParseEntityRef: expecting ';'
ction=FilterSearch&Filter=docs_filter.hts&ResultTemplate=magazine.hts&Collectio
^
^
./test/HTML/wired.html:93: error: htmlParseEntityRef: expecting ';'
Filter=docs_filter.hts&ResultTemplate=magazine.hts&Collection=magazine&QueryMod
^
^
./test/HTML/wired.html:93: error: htmlParseEntityRef: expecting ';'
ter.hts&ResultTemplate=magazine.hts&Collection=magazine&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:94: error: htmlParseEntityRef: expecting ';'
on value="http://search.hotwired.com/search97/s97.vts?Action=FilterSearch&Filte
^
^
./test/HTML/wired.html:94: error: htmlParseEntityRef: expecting ';'
d.com/search97/s97.vts?Action=FilterSearch&Filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:94: error: htmlParseEntityRef: expecting ';'
tion=FilterSearch&Filter=docs_filter.hts&ResultTemplate=animation.hts&Collectio
^
^
./test/HTML/wired.html:94: error: htmlParseEntityRef: expecting ';'
lter=docs_filter.hts&ResultTemplate=animation.hts&Collection=animation&QueryMod
^
^
./test/HTML/wired.html:94: error: htmlParseEntityRef: expecting ';'
r.hts&ResultTemplate=animation.hts&Collection=animation&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:95: error: htmlParseEntityRef: expecting ';'
option value="http://search.hotwired.com/search97/s97.vts?collection=suck&Actio
^
^
./test/HTML/wired.html:95: error: htmlParseEntityRef: expecting ';'
/search.hotwired.com/search97/s97.vts?collection=suck&Action=FilterSearch&filte
^
^
./test/HTML/wired.html:95: error: htmlParseEntityRef: expecting ';'
97.vts?collection=suck&Action=FilterSearch&filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:95: error: htmlParseEntityRef: expecting ';'
uck&Action=FilterSearch&filter=docs_filter.hts&ResultTemplate=suck.hts&QueryMod
^
^
./test/HTML/wired.html:95: error: htmlParseEntityRef: expecting ';'
erSearch&filter=docs_filter.hts&ResultTemplate=suck.hts&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:96: error: htmlParseEntityRef: expecting ';'
lue="http://search.hotwired.com/search97/s97.vts?collection=uber_hotwired&Actio
^
^
./test/HTML/wired.html:96: error: htmlParseEntityRef: expecting ';'
otwired.com/search97/s97.vts?collection=uber_hotwired&Action=FilterSearch&filte
^
^
./test/HTML/wired.html:96: error: htmlParseEntityRef: expecting ';'
llection=uber_hotwired&Action=FilterSearch&filter=docs_filter.hts&ResultTemplat
^
^
./test/HTML/wired.html:96: error: htmlParseEntityRef: expecting ';'
n=FilterSearch&filter=docs_filter.hts&ResultTemplate=uber_hotwired.hts&QueryMod
^
^
./test/HTML/wired.html:96: error: htmlParseEntityRef: expecting ';'
filter=docs_filter.hts&ResultTemplate=uber_hotwired.hts&QueryMode=Internet&Quer
^
^
./test/HTML/wired.html:97: error: htmlParseEntityRef: expecting ';'
<option value="http://www.hotbot.com/?SM=MC&DV=0&LG=any&RD=RG&DC=10&DE=2&_v=2&
^
@ -177,40 +177,55 @@ filter=docs_filter.hts&ResultTemplate=uber_hotwired.hts&QueryMode=Internet&Quer
^
./test/HTML/wired.html:97: error: htmlParseEntityRef: expecting ';'
option value="http://www.hotbot.com/?SM=MC&DV=0&LG=any&RD=RG&DC=10&DE=2&_v=2&OP
^
^
./test/HTML/wired.html:97: error: htmlParseEntityRef: expecting ';'
lue="http://www.hotbot.com/?SM=MC&DV=0&LG=any&RD=RG&DC=10&DE=2&_v=2&OPs=MDRTP&M
^
^
./test/HTML/wired.html:165: error: Opening and ending tag mismatch: td and form
</td>
^
./test/HTML/wired.html:170: error: Unexpected end tag : form
./test/HTML/wired.html:170: error: Opening and ending tag mismatch: tr and form
</tr> </form>
^
^
./test/HTML/wired.html:171: error: Opening and ending tag mismatch: table and td
</table></td>
^
./test/HTML/wired.html:244: error: Opening and ending tag mismatch: td and form
</select></font></td></tr>
^
./test/HTML/wired.html:244: error: Opening and ending tag mismatch: tr and form
</select></font></td></tr>
^
./test/HTML/wired.html:248: error: htmlParseEntityRef: expecting ';'
MG SRC="http://barnesandnoble.bfast.com/booklink/serve?sourceid=383471&is_searc
^
./test/HTML/wired.html:265: error: Unexpected end tag : form
</tr> </form>
^
^
./test/HTML/wired.html:266: error: Opening and ending tag mismatch: table and td
</table>
^
./test/HTML/wired.html:346: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:347: error: Opening and ending tag mismatch: tr and font
</tr>
^
./test/HTML/wired.html:349: error: Opening and ending tag mismatch: table and font
</table>
^
./test/HTML/wired.html:374: error: htmlParseEntityRef: no name
a, sans-serif"><b><a href="/news/commentarySection/0,1292,31926,00.html">Rants
^
^
./test/HTML/wired.html:374: error: Opening and ending tag mismatch: td and font
Readers on Apple's G4 ... AOL's passwords ... MS vs. Linux.</font><br><br> </t
^
./test/HTML/wired.html:374: error: Opening and ending tag mismatch: td and font
Readers on Apple's G4 ... AOL's passwords ... MS vs. Linux.</font><br><br> </t
^
^
./test/HTML/wired.html:375: error: Opening and ending tag mismatch: tr and font
</tr>
^
./test/HTML/wired.html:402: error: Opening and ending tag mismatch: a and font
w.vignette.com/" style="text-decoration:none"><font color="#000000">Vignette</a
^
^
./test/HTML/wired.html:402: error: Opening and ending tag mismatch: i and font
gnette.com/" style="text-decoration:none"><font color="#000000">Vignette</a></i
^
./test/HTML/wired.html:406: error: htmlParseEntityRef: expecting ';'
ervlet/appservlet?from=/wired/sprint/&template=/security/security.html&SITE=
^
@ -222,34 +237,40 @@ wired.com&BANNER=Sprint" style="text-decoration:none"><font color="#000000">Spr
^
./test/HTML/wired.html:406: error: Opening and ending tag mismatch: a and font
com&BANNER=Sprint" style="text-decoration:none"><font color="#000000">Sprint</a
^
^
./test/HTML/wired.html:406: error: Opening and ending tag mismatch: i and font
BANNER=Sprint" style="text-decoration:none"><font color="#000000">Sprint</a></i
^
./test/HTML/wired.html:406: error: End tag : expected '>'
=Sprint" style="text-decoration:none"><font color="#000000">Sprint</a></i></fon
^
^
./test/HTML/wired.html:406: error: Opening and ending tag mismatch: font and a
" style="text-decoration:none"><font color="#000000">Sprint</a></i></font</font
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
^
./test/HTML/wired.html:412: error: Opening and ending tag mismatch: td and font
</td>
./test/HTML/wired.html:413: error: Opening and ending tag mismatch: tr and font
</tr>
^
./test/HTML/wired.html:430: error: htmlParseEntityRef: expecting ';'
href="http://www.lycos.com/news/flash/hitlerbunker.html?v=wn1015&lpv=1">Lycos</
^
./test/HTML/wired.html:434: error: Opening and ending tag mismatch: table and font
</table>
^
./test/HTML/wired.html:461: error: Opening and ending tag mismatch: td and font
</TD>
^
./test/HTML/wired.html:462: error: Opening and ending tag mismatch: tr and font
</TR>
^
./test/HTML/wired.html:508: error: Opening and ending tag mismatch: table and font
</TABLE>
^
./test/HTML/wired.html:512: error: Opening and ending tag mismatch: body and font
</body>
^
./test/HTML/wired.html:513: error: Opening and ending tag mismatch: html and font
</html>
^

117
result/HTML/wired.html.sax
View File

@ -779,8 +779,6 @@ SAX.characters(&nbsp;, 2)
SAX.characters(
, 1)
SAX.error: Opening and ending tag mismatch: td and form
SAX.endElement(form)
SAX.endElement(td)
SAX.characters(
, 4)
SAX.startElement(td, valign='top', bgcolor='#99FF99')
@ -794,12 +792,12 @@ SAX.characters(
SAX.endElement(td)
SAX.characters(
, 2)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: tr and form
SAX.characters( , 4)
SAX.error: Unexpected end tag : form
SAX.endElement(form)
SAX.characters(
, 1)
SAX.endElement(table)
SAX.error: Opening and ending tag mismatch: table and td
SAX.endElement(td)
SAX.characters(
, 3)
@ -1077,9 +1075,7 @@ SAX.endElement(option)
SAX.endElement(select)
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and form
SAX.endElement(form)
SAX.endElement(td)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: tr and form
SAX.characters(
, 2)
SAX.startElement(tr, align='left', valign='top')
@ -1141,10 +1137,10 @@ SAX.characters(
, 9)
SAX.endElement(tr)
SAX.characters( , 2)
SAX.error: Unexpected end tag : form
SAX.endElement(form)
SAX.characters(
, 9)
SAX.endElement(table)
SAX.error: Opening and ending tag mismatch: table and td
SAX.characters(
, 2)
@ -1456,23 +1452,21 @@ SAX.endElement(img)
SAX.characters(
, 1)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.endElement(td)
SAX.characters(
, 3)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: tr and font
SAX.characters(
, 2)
SAX.endElement(table)
SAX.ignorableWhitespace(
SAX.error: Opening and ending tag mismatch: table and font
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')
@ -1632,13 +1626,9 @@ SAX.startElement(br)
SAX.endElement(br)
SAX.characters( , 2)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.endElement(td)
SAX.characters(
, 9)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: tr and font
SAX.characters(
, 1)
SAX.comment( Commentary Frag End )
@ -1894,9 +1884,7 @@ SAX.startElement(a, href='http://r.wired.com/r/wn_exec_r_vign/http://www.vignett
SAX.startElement(font, color='#000000')
SAX.characters(Vignette, 8)
SAX.error: Opening and ending tag mismatch: a and font
SAX.endElement(font)
SAX.endElement(a)
SAX.endElement(i)
SAX.error: Opening and ending tag mismatch: i and font
SAX.endElement(font)
SAX.startElement(br)
SAX.endElement(br)
@ -1959,12 +1947,10 @@ wired.com&amp;BANNER=Sprint', style='text-decoration:none')
SAX.startElement(font, color='#000000')
SAX.characters(Sprint, 6)
SAX.error: Opening and ending tag mismatch: a and font
SAX.endElement(font)
SAX.endElement(a)
SAX.endElement(i)
SAX.error: Opening and ending tag mismatch: i and font
SAX.error: End tag : expected '>'
SAX.endElement(font)
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: font and a
SAX.startElement(br)
SAX.endElement(br)
SAX.startElement(br)
@ -2010,25 +1996,9 @@ SAX.characters(
, 2)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.error: Opening and ending tag mismatch: td and font
SAX.endElement(font)
SAX.endElement(td)
SAX.characters(
, 1)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: tr and font
SAX.characters(
, 1)
SAX.comment( start of Gen News )
@ -2114,7 +2084,7 @@ SAX.characters(
SAX.comment( end of Gen News )
SAX.characters(
, 1)
SAX.endElement(table)
SAX.error: Opening and ending tag mismatch: table and font
SAX.characters(
@ -2661,10 +2631,10 @@ SAX.comment( - - - - - - - - - - - - )
SAX.characters(
, 6)
SAX.endElement(td)
SAX.error: Opening and ending tag mismatch: td and font
SAX.characters(
, 3)
SAX.endElement(tr)
SAX.error: Opening and ending tag mismatch: tr and font
SAX.characters(
, 4)
@ -2831,20 +2801,57 @@ SAX.characters(
SAX.endElement(tr)
SAX.characters(
, 1)
SAX.endElement(table)
SAX.ignorableWhitespace(
SAX.error: Opening and ending tag mismatch: table and font
SAX.characters(
, 3)
SAX.startElement(br)
SAX.endElement(br)
SAX.ignorableWhitespace(
SAX.characters(
, 1)
SAX.endElement(body)
SAX.ignorableWhitespace(
SAX.error: Opening and ending tag mismatch: body and font
SAX.characters(
, 1)
SAX.endElement(html)
SAX.error: Opening and ending tag mismatch: html and font
SAX.ignorableWhitespace(
, 2)
SAX.endElement(font)
SAX.endElement(a)
SAX.endElement(i)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(a)
SAX.endElement(i)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(font)
SAX.endElement(font)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(table)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(table)
SAX.endElement(font)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(table)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(table)
SAX.endElement(td)
SAX.endElement(tr)
SAX.endElement(table)
SAX.endElement(body)
SAX.endElement(html)
SAX.endDocument()