// 8.2.4.35 Attribute name state
HtmlToken ReadAttributeName()
{
do {
int nc = Read ();
char c;
if (nc == -1) {
TokenizerState = HtmlTokenizerState.EndOfFile;
name.Length = 0;
tag = null;
return EmitDataToken (false);
}
c = (char) nc;
// Note: we save the data in case we hit a parse error and have to emit a data token
data.Append (c);
switch (c) {
case '\t': case '\r': case '\n': case '\f': case ' ':
TokenizerState = HtmlTokenizerState.AfterAttributeName;
break;
case '/':
TokenizerState = HtmlTokenizerState.SelfClosingStartTag;
break;
case '=':
TokenizerState = HtmlTokenizerState.BeforeAttributeValue;
break;
case '>':
EmitTagAttribute ();
return EmitTagToken ();
default:
name.Append (c == '\0' ? '\uFFFD' : c);
break;
}
} while (TokenizerState == HtmlTokenizerState.AttributeName);
EmitTagAttribute ();
return null;
}
HtmlToken EmitTagToken()
{
if (!tag.IsEndTag && !tag.IsEmptyElement) {
switch (tag.Id) {
case HtmlTagId.Style: case HtmlTagId.Xmp: case HtmlTagId.IFrame: case HtmlTagId.NoEmbed: case HtmlTagId.NoFrames:
TokenizerState = HtmlTokenizerState.RawText;
activeTagName = tag.Name;
break;
case HtmlTagId.Title: case HtmlTagId.TextArea:
TokenizerState = HtmlTokenizerState.RcData;
activeTagName = tag.Name;
break;
case HtmlTagId.PlainText:
TokenizerState = HtmlTokenizerState.PlainText;
break;
case HtmlTagId.Script:
TokenizerState = HtmlTokenizerState.ScriptData;
break;
case HtmlTagId.NoScript:
// TODO: only switch into the RawText state if scripting is enabled
TokenizerState = HtmlTokenizerState.RawText;
activeTagName = tag.Name;
break;
case HtmlTagId.Html:
TokenizerState = HtmlTokenizerState.Data;
for (int i = tag.Attributes.Count; i > 0; i--) {
var attr = tag.Attributes[i - 1];
if (attr.Id == HtmlAttributeId.XmlNS && attr.Value != null) {
HtmlNamespace = attr.Value.ToHtmlNamespace ();
break;
}
}
break;
default:
TokenizerState = HtmlTokenizerState.Data;
break;
}
} else {
TokenizerState = HtmlTokenizerState.Data;
}
var token = tag;
data.Length = 0;
tag = null;
return token;
}
// 8.2.4.27 Script data escaped end tag name state
HtmlToken ReadScriptDataEscapedEndTagName()
{
do {
int nc = Read ();
char c;
if (nc == -1) {
TokenizerState = HtmlTokenizerState.EndOfFile;
name.Length = 0;
return EmitScriptDataToken ();
}
c = (char) nc;
// Note: we save the data in case we hit a parse error and have to emit a data token
data.Append (c);
switch (c) {
case '\t': case '\r': case '\n': case '\f': case ' ':
if (NameIs ("script")) {
TokenizerState = HtmlTokenizerState.BeforeAttributeName;
break;
}
goto default;
case '/':
if (NameIs ("script")) {
TokenizerState = HtmlTokenizerState.SelfClosingStartTag;
break;
}
goto default;
case '>':
if (NameIs ("script")) {
var token = CreateTagToken (name.ToString (), true);
TokenizerState = HtmlTokenizerState.Data;
data.Length = 0;
name.Length = 0;
return token;
}
goto default;
default:
if (!IsAsciiLetter (c)) {
TokenizerState = HtmlTokenizerState.ScriptData;
return null;
}
name.Append (c);
break;
}
} while (TokenizerState == HtmlTokenizerState.ScriptDataEscapedEndTagName);
tag = CreateTagToken (name.ToString (), true);
name.Length = 0;
return null;
}
HtmlToken ReadGenericRawTextEndTagName(bool decoded, HtmlTokenizerState rawText)
{
var current = TokenizerState;
do {
int nc = Read ();
char c;
if (nc == -1) {
TokenizerState = HtmlTokenizerState.EndOfFile;
name.Length = 0;
return EmitDataToken (decoded);
}
c = (char) nc;
// Note: we save the data in case we hit a parse error and have to emit a data token
data.Append (c);
switch (c) {
case '\t': case '\r': case '\n': case '\f': case ' ':
if (NameIs (activeTagName)) {
TokenizerState = HtmlTokenizerState.BeforeAttributeName;
break;
}
goto default;
case '/':
if (NameIs (activeTagName)) {
TokenizerState = HtmlTokenizerState.SelfClosingStartTag;
break;
}
goto default;
case '>':
if (NameIs (activeTagName)) {
var token = CreateTagToken (name.ToString (), true);
TokenizerState = HtmlTokenizerState.Data;
data.Length = 0;
name.Length = 0;
return token;
}
goto default;
default:
if (!IsAsciiLetter (c)) {
TokenizerState = rawText;
return null;
}
name.Append (c == '\0' ? '\uFFFD' : c);
break;
}
} while (TokenizerState == current);
tag = CreateTagToken (name.ToString (), true);
name.Length = 0;
return null;
}
// 8.2.4.37 Before attribute value state
HtmlToken ReadBeforeAttributeValue()
{
do {
int nc = Read ();
char c;
if (nc == -1) {
TokenizerState = HtmlTokenizerState.EndOfFile;
tag = null;
return EmitDataToken (false);
}
c = (char) nc;
// Note: we save the data in case we hit a parse error and have to emit a data token
data.Append (c);
switch (c) {
case '\t': case '\r': case '\n': case '\f': case ' ':
break;
case '"': case '\'':
TokenizerState = HtmlTokenizerState.AttributeValueQuoted;
quote = c;
return null;
case '&':
TokenizerState = HtmlTokenizerState.AttributeValueUnquoted;
return null;
case '/':
TokenizerState = HtmlTokenizerState.SelfClosingStartTag;
return null;
case '>':
return EmitTagToken ();
case '<': case '=': case '`':
// parse error
goto default;
default:
TokenizerState = HtmlTokenizerState.AttributeValueUnquoted;
name.Append (c == '\0' ? '\uFFFD' : c);
return null;
}
} while (true);
}
/// <summary>
/// 8.2.4.10 Tag name state
/// </summary>
void R10_TagName()
{
do
{
int nc = Read();
char c;
if (nc == -1)
{
TokenizerState = HtmlTokenizerState.EndOfFile;
name.Length = 0;
EmitDataToken(false);
return;
}
c = (char)nc;
// Note: we save the data in case we hit a parse error and have to emit a data token
data.Append(c);
switch (c)
{
case '\t':
case '\r':
case '\n':
case '\f':
case ' ':
TokenizerState = HtmlTokenizerState.BeforeAttributeName;
break;
case '/':
TokenizerState = HtmlTokenizerState.SelfClosingStartTag;
break;
case '>':
token = CreateTagToken(name.ToString(), isEndTag);
TokenizerState = HtmlTokenizerState.Data;
data.Length = 0;
name.Length = 0;
return;
default:
name.Append(c == '\0' ? '\uFFFD' : c);
break;
}
} while (TokenizerState == HtmlTokenizerState.TagName);
tag = CreateTagToken(name.ToString(), isEndTag);
name.Length = 0;
token = null;
}
