diff --git a/HTMLparser.c b/HTMLparser.c
index be6e14a2..9c9237e2 100644
--- a/HTMLparser.c
+++ b/HTMLparser.c
@@ -2441,33 +2441,36 @@ htmlSkipBogusComment(htmlParserCtxtPtr ctxt) {
*/
static const xmlChar *
-htmlParseHTMLName(htmlParserCtxtPtr ctxt) {
+htmlParseHTMLName(htmlParserCtxtPtr ctxt, int attr) {
const xmlChar *ret;
- int i = 0;
- xmlChar loc[HTML_PARSER_BUFFER_SIZE];
+ int nbchar = 0;
+ int c, l;
+ int stop = attr ? '=' : 0;
+ xmlChar buf[HTML_PARSER_BUFFER_SIZE];
- if (!IS_ASCII_LETTER(CUR) && (CUR != '_') &&
- (CUR != ':') && (CUR != '.')) return(NULL);
+ c = CUR_CHAR(l);
+ while ((c != 0) && (c != '/') && (c != '>') &&
+ ((nbchar == 0) || (c != stop)) &&
+ (!IS_BLANK_CH(c))) {
+ if (nbchar + l <= HTML_PARSER_BUFFER_SIZE) {
+ if ((c >= 'A') && (c <= 'Z')) {
+ buf[nbchar++] = c + 0x20;
+ } else {
+ COPY_BUF(buf, nbchar, c);
+ }
+ }
- while ((i < HTML_PARSER_BUFFER_SIZE) &&
- ((IS_ASCII_LETTER(CUR)) || (IS_ASCII_DIGIT(CUR)) ||
- (CUR == ':') || (CUR == '-') || (CUR == '_') ||
- (CUR == '.'))) {
- if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20;
- else loc[i] = CUR;
- i++;
-
- NEXT;
+ NEXTL(l);
+ c = CUR_CHAR(l);
}
- ret = xmlDictLookup(ctxt->dict, loc, i);
+ ret = xmlDictLookup(ctxt->dict, buf, nbchar);
if (ret == NULL)
htmlErrMemory(ctxt);
return(ret);
}
-
/**
* htmlParseHTMLName_nonInvasive:
* @ctxt: an HTML parser context
@@ -2481,22 +2484,31 @@ htmlParseHTMLName(htmlParserCtxtPtr ctxt) {
static const xmlChar *
htmlParseHTMLName_nonInvasive(htmlParserCtxtPtr ctxt) {
+ int nbchar = 0;
int i = 0;
- xmlChar loc[HTML_PARSER_BUFFER_SIZE];
+ int c, l;
+ xmlChar buf[HTML_PARSER_BUFFER_SIZE];
const xmlChar *ret;
+ size_t avail = ctxt->input->end - ctxt->input->cur;
- if (!IS_ASCII_LETTER(NXT(1)) && (NXT(1) != '_') &&
- (NXT(1) != ':')) return(NULL);
+ l = avail - i;
+ c = xmlGetUTF8Char(CUR_PTR + i, &l);
+ while ((c > 0) && (c != '/') && (c != '>') &&
+ (!IS_BLANK_CH(c))) {
+ if (nbchar + l <= HTML_PARSER_BUFFER_SIZE) {
+ if ((c >= 'A') && (c <= 'Z')) {
+ buf[nbchar++] = c + 0x20;
+ } else {
+ COPY_BUF(buf, nbchar, c);
+ }
+ }
- while ((i < HTML_PARSER_BUFFER_SIZE) &&
- ((IS_ASCII_LETTER(NXT(1+i))) || (IS_ASCII_DIGIT(NXT(1+i))) ||
- (NXT(1+i) == ':') || (NXT(1+i) == '-') || (NXT(1+i) == '_'))) {
- if ((NXT(1+i) >= 'A') && (NXT(1+i) <= 'Z')) loc[i] = NXT(1+i) + 0x20;
- else loc[i] = NXT(1+i);
- i++;
+ i += l;
+ l = avail - i;
+ c = xmlGetUTF8Char(CUR_PTR + i, &l);
}
- ret = xmlDictLookup(ctxt->dict, loc, i);
+ ret = xmlDictLookup(ctxt->dict, buf, nbchar);
if (ret == NULL)
htmlErrMemory(ctxt);
@@ -3636,7 +3648,7 @@ htmlParseAttribute(htmlParserCtxtPtr ctxt, xmlChar **value) {
xmlChar *val = NULL;
*value = NULL;
- name = htmlParseHTMLName(ctxt);
+ name = htmlParseHTMLName(ctxt, 1);
if (name == NULL) {
htmlParseErr(ctxt, XML_ERR_NAME_REQUIRED,
"error parsing attribute name\n", NULL, NULL);
@@ -3777,7 +3789,7 @@ htmlParseStartTag(htmlParserCtxtPtr ctxt) {
maxatts = ctxt->maxatts;
GROW;
- name = htmlParseHTMLName(ctxt);
+ name = htmlParseHTMLName(ctxt, 0);
if (name == NULL) {
htmlParseErr(ctxt, XML_ERR_NAME_REQUIRED,
"htmlParseStartTag: invalid element name\n",
@@ -3970,7 +3982,7 @@ htmlParseEndTag(htmlParserCtxtPtr ctxt)
}
SKIP(2);
- name = htmlParseHTMLName(ctxt);
+ name = htmlParseHTMLName(ctxt, 0);
if (name == NULL)
return (0);
/*
diff --git a/result/HTML/doc3.htm b/result/HTML/doc3.htm
index 8e45a5a4..0f3a8b79 100644
--- a/result/HTML/doc3.htm
+++ b/result/HTML/doc3.htm
@@ -97,7 +97,7 @@ eval("page" + id + " = window.open(URL, '" + id + "', 'toolbars=0, scrollbars=0,
|
- 
Gentus
+
Gentus
|
diff --git a/result/HTML/doc3.htm.err b/result/HTML/doc3.htm.err
index 5e2491da..bb9204eb 100644
--- a/result/HTML/doc3.htm.err
+++ b/result/HTML/doc3.htm.err
@@ -10,9 +10,6 @@ _top">
^
@@ -43,10 +40,10 @@ om/ad_static.asp?pid=2097&sid=1881&asid=7708">
./test/HTML/doc3.htm:795: HTML parser error : Unexpected end tag : iframe
document.write("42DF8478957377>");
^
-./test/HTML/doc3.htm:803: HTML parser error : End tag : expected '>'
- document.write("DF8478957377>'
+ document.write("RIPT>");
+ ^
+./test/HTML/doc3.htm:804: HTML parser error : Unexpected end tag : sc");
document.write("RIPT>");
^
./test/HTML/doc3.htm:811: HTML parser error : Unexpected end tag : a
diff --git a/result/HTML/doc3.htm.sax b/result/HTML/doc3.htm.sax
index 9237ad3c..f2009a95 100644
--- a/result/HTML/doc3.htm.sax
+++ b/result/HTML/doc3.htm.sax
@@ -319,8 +319,7 @@ SAX.characters(
, 26)
SAX.startElement(p, align='center')
SAX.startElement(a, href='http://www.gentus.com/')
-SAX.error: error parsing attribute name
-SAX.startElement(img, align='bottom', alt='Taking a first look at the Abit Linux release called ', border='0', height='45', src='doc3_files/gentusbox.gif', width='70', gentus)
+SAX.startElement(img, align='bottom', alt='Taking a first look at the Abit Linux release called ', border='0', height='45', src='doc3_files/gentusbox.gif', width='70', gentus?.?)
SAX.endElement(img)
SAX.endElement(a)
SAX.startElement(br)
@@ -2698,7 +2697,7 @@ SAX.error: Unexpected end tag : iframe
SAX.cdata(");
} else if ((parseI, 463)
SAX.error: End tag : expected '>'
-SAX.error: Unexpected end tag : sc
+SAX.error: Unexpected end tag : sc");
SAX.cdata(");
} else {
d, 328)
diff --git a/result/HTML/wired.html b/result/HTML/wired.html
index 916630d8..fef7a694 100644
--- a/result/HTML/wired.html
+++ b/result/HTML/wired.html
@@ -462,13 +462,13 @@ or PointCast
Making the Grade
Reading, writing, and ROM.
Sponsored by U of Phoenix
-Infostructure
An IS/IT resource
Sponsored by Sprint
+Infostructure
An IS/IT resource
Sponsored by Sprint
Y2K Watch
Tick... Tick... Tick...
More Hoo-Ha
-
+
diff --git a/result/HTML/wired.html.err b/result/HTML/wired.html.err
index 116bbd2f..6b8d8184 100644
--- a/result/HTML/wired.html.err
+++ b/result/HTML/wired.html.err
@@ -218,8 +218,14 @@ wired.com&BANNER=Sprint" style="text-decoration:none">Spri
com&BANNER=Sprint" style="text-decoration:none">Sprint
^
./test/HTML/wired.html:408: HTML parser error : End tag : expected '>'
-=Sprint" style="text-decoration:none">SprintSprintSprint
+ ^
+./test/HTML/wired.html:414: HTML parser error : Opening and ending tag mismatch: td and font
+
+ ^
./test/HTML/wired.html:414: HTML parser error : Opening and ending tag mismatch: td and font
^
diff --git a/result/HTML/wired.html.sax b/result/HTML/wired.html.sax
index bb787656..ce51ed60 100644
--- a/result/HTML/wired.html.sax
+++ b/result/HTML/wired.html.sax
@@ -1961,7 +1961,7 @@ SAX.endElement(font)
SAX.endElement(a)
SAX.endElement(i)
SAX.error: End tag : expected '>'
-SAX.endElement(font)
+SAX.error: Unexpected end tag : font<
SAX.startElement(br)
SAX.endElement(br)
SAX.startElement(br)
@@ -2024,6 +2024,8 @@ 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)