Index: HTMLparser.c @@ -1650,6 +1650,8 @@ if (CUR != '<') return(0); if (ctxt->name == NULL) return(1); + if (!xmlStrcmp(ctxt->name, BAD_CAST"html")) + return(1); if (!xmlStrcmp(ctxt->name, BAD_CAST"head")) return(1); if (!xmlStrcmp(ctxt->name, BAD_CAST"body")) Index: Down.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 3) @@ -36,7 +33,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: doc3.htm.sax @@ -70,11 +70,8 @@ SAX.startElement(meta, content='MSHTML 5.00.3103.1000', name='GENERATOR') SAX.endElement(meta) SAX.endElement(head) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 2) -SAX.endElement(p) SAX.startElement(body, aLink='red', bgColor='black', link='red', text='white', vLink='red') SAX.ignorableWhitespace( , 2) @@ -2923,7 +2920,6 @@ SAX.endElement(script) SAX.ignorableWhitespace( , 2) -SAX.endElement(body) SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( Index: fp40.htm.sax @@ -2,12 +2,9 @@ SAX.startDocument() SAX.internalSubset(html, -//IETF//DTD HTML//EN, ) SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 2) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -460,7 +457,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: reg1.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -33,7 +30,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: reg2.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -38,7 +35,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: reg3.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -42,7 +39,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: reg4.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 1) @@ -40,7 +37,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: test2.html.sax @@ -8,11 +8,8 @@ SAX.characters(Linux Today, 11) SAX.endElement(title) SAX.endElement(head) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 1) -SAX.endElement(p) SAX.startElement(body, bgcolor='White', link='Blue', text='Black', VLINK='Black', ALINK='Red') SAX.ignorableWhitespace( @@ -142,7 +139,6 @@ SAX.endElement(body) SAX.ignorableWhitespace( , 1) -SAX.endElement(body) SAX.endElement(html) SAX.ignorableWhitespace( , 1) Index: test3.html.sax @@ -1,11 +1,8 @@ SAX.setDocumentLocator() SAX.startDocument() SAX.startElement(html) -SAX.startElement(body) -SAX.startElement(p) -SAX.characters( +SAX.ignorableWhitespace( , 2) -SAX.endElement(p) SAX.startElement(head) SAX.ignorableWhitespace( , 2) @@ -16,6 +13,7 @@ SAX.endElement(head) SAX.ignorableWhitespace( , 2) +SAX.startElement(body) SAX.startElement(a, name='ProblemDomain.Package') SAX.startElement(h2) SAX.characters(Component Package diagram Prob, 39)