public void AppendSelfClosingTagSuffix_VaryingHtmlVersion_AppendsCorrectOutput(HtmlVersion htmlVersion, string expectedOutput)
{
var template = new DummyTemplate();
string result = template.AppendSelfClosingTagSuffix(htmlVersion);
Assert.That(result, Is.EqualTo(expectedOutput));
}
public Attribute(string name, HtmlVersion versions, IAttrCheck attrCheck)
{
_name = name;
_nowrap = false;
_literal = false;
_versions = versions;
_attrCheck = attrCheck;
}
public Dict(string name, HtmlVersion versions, int model, IParser parser, ICheckAttribs checkAttribs)
{
Name = name;
Versions = versions;
Model = model;
Parser = parser;
CheckAttribs = checkAttribs;
}
public Attribute(string name, HtmlVersion versions, IAttrCheck attrCheck)
{
Name = name;
Nowrap = false;
Literal = false;
Versions = versions;
AttrCheck = attrCheck;
}
public void Render(TextWriter writer, HtmlVersion htmlVersion, IDictionary <string, object> viewData)
{
Invariant.ArgumentNotNull(writer, "textWriter");
_htmlVersion = htmlVersion;
ViewData = viewData;
HasCodeBlockRepeated = false;
CoreRender(writer);
}
public void RenderAttributeNameValuePair_BooleanAttribute_WritesCorrectAttributes(string name, string value, HtmlVersion htmlVersion, string expectedOutput)
{
var template = new DummyTemplate();
template.SetHtmlVersion(htmlVersion);
string result = template.RenderAttributeNameValuePair(name, value, '\"');
Assert.That(result, Is.EqualTo(expectedOutput));
}
public Dict(string name, HtmlVersion versions, int model, IParser parser, ICheckAttribs checkAttribs)
{
Name = name;
Versions = versions;
Model = model;
Parser = parser;
CheckAttribs = checkAttribs;
}
public Dict(string name, HtmlVersion versions, int model, IParser parser, ICheckAttribs checkAttribs)
{
_name = name;
_versions = versions;
_model = model;
_parser = parser;
_checkAttribs = checkAttribs;
}
public void Html5Support(HtmlVersion htmlVersion)
{
Document doc = new Document(MyDir + "Document.doc");
HtmlSaveOptions saveOptions = new HtmlSaveOptions();
saveOptions.HtmlVersion = htmlVersion;
}
public Attribute(string name, HtmlVersion versions, IAttrCheck attrCheck)
{
Name = name;
Nowrap = false;
Literal = false;
Versions = versions;
AttrCheck = attrCheck;
}
public Attribute(string name, HtmlVersion versions, IAttrCheck attrCheck)
{
_name = name;
_nowrap = false;
_literal = false;
_versions = versions;
_attrCheck = attrCheck;
}
public Dict(string name, HtmlVersion versions, int model, IParser parser, ICheckAttribs checkAttribs)
{
_name = name;
_versions = versions;
_model = model;
_parser = parser;
_checkAttribs = checkAttribs;
}
public void Render(TextWriter writer, HtmlVersion htmlVersion, IDictionary<string, object> viewData)
{
Invariant.ArgumentNotNull(writer, "textWriter");
_htmlVersion = htmlVersion;
ViewData = viewData;
HasCodeBlockRepeated = false;
CoreRender(writer);
}
private static string GetStrictDocType(HtmlVersion htmlVersion)
{
switch (htmlVersion)
{
case HtmlVersion.Html4:
return @"<!DOCTYPE html PUBLIC ""-//W3C//DTD HTML 4.01//EN"" ""http://www.w3.org/TR/html4/strict.dtd"">";
default:
return @"<!DOCTYPE html PUBLIC ""-//W3C//DTD XHTML 1.0 Strict//EN"" ""http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"">";
}
}
private static string GetTransitionalDocType(HtmlVersion htmlVersion)
{
switch (htmlVersion)
{
case HtmlVersion.Html4:
return @"<!DOCTYPE html PUBLIC ""-//W3C//DTD HTML 4.01 Transitional//EN"" ""http://www.w3.org/TR/html4/loose.dtd"">";
default:
return @"<!DOCTYPE html PUBLIC ""-//W3C//DTD XHTML 1.0 Transitional//EN"" ""http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"">";
}
}
private static string GetStrictDocType(HtmlVersion htmlVersion)
{
switch (htmlVersion)
{
case HtmlVersion.Html4:
return(@"<!DOCTYPE html PUBLIC ""-//W3C//DTD HTML 4.01//EN"" ""http://www.w3.org/TR/html4/strict.dtd"">");
default:
return(@"<!DOCTYPE html PUBLIC ""-//W3C//DTD XHTML 1.0 Strict//EN"" ""http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"">");
}
}
private static string GetTransitionalDocType(HtmlVersion htmlVersion)
{
switch (htmlVersion)
{
case HtmlVersion.Html4:
return(@"<!DOCTYPE html PUBLIC ""-//W3C//DTD HTML 4.01 Transitional//EN"" ""http://www.w3.org/TR/html4/loose.dtd"">");
default:
return(@"<!DOCTYPE html PUBLIC ""-//W3C//DTD XHTML 1.0 Transitional//EN"" ""http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"">");
}
}
public void Html5Support(HtmlVersion htmlVersion)
{
Document doc = new Document(MyDir + "Document.doc");
HtmlSaveOptions saveOptions = new HtmlSaveOptions
{
HtmlVersion = htmlVersion
};
doc.Save(ArtifactsDir + "HtmlSaveOptions.Html5Support.html", saveOptions);
}
public void Walk_AutoSelfClosingTag_AppendsCorrectTag(HtmlVersion htmlVersion, string expectedFormat)
{
// Arrange
var tagNode = new HamlNodeTag(new HamlLine("br"));
// Act
_hamlOptions.HtmlVersion = htmlVersion;
_tagWalker.Walk(tagNode);
// Assert
Assert.That(_classBuilderMock.Build(""), Is.StringContaining(expectedFormat));
}
private static string GetXmlDocType(IList <string> docTypeParts, HtmlVersion htmlVersion)
{
if (htmlVersion != HtmlVersion.XHtml)
{
return("");
}
string encoding = docTypeParts.Count < 2
? "utf-8"
: docTypeParts[1];
return("<?xml version='1.0' encoding='" + encoding + "' ?>");
}
public HamlOptions()
{
AutoClosingTags = new List<string> {
"area",
"base",
"br",
"col",
"hr",
"img",
"input",
"link",
"meta",
"param"
};
HtmlVersion = CodeDom.HtmlVersion.XHtml;
}
public static string GetDocType(string docType, HtmlVersion htmlVersion)
{
var docTypeParts = docType.Split(' ');
if (docTypeParts.Length == 0)
{
return(GetTransitionalDocType(htmlVersion));
}
if (htmlVersion == HtmlVersion.Html5 &&
docTypeParts[0].ToUpper() != "XML")
{
return(GetHtml5DocType());
}
switch (docTypeParts[0].ToUpper())
{
case "STRICT": return(GetStrictDocType(htmlVersion));
case "FRAMESET": return(GetFramesetDocType(htmlVersion));
case "5": return(GetHtml5DocType());
case "1.1": return(GetXHtmlDocType11());
case "BASIC": return(GetBasicDocType());
case "MOBILE": return(GetMobileDocType());
case "RDFA": return(GetRdfaDocType());
case "XML": return(GetXmlDocType(docTypeParts, htmlVersion));
default: return(GetTransitionalDocType(htmlVersion));
}
}
public static string GetDocType(string docType, HtmlVersion htmlVersion)
{
var docTypeParts = docType.Split(' ');
if (docTypeParts.Length == 0)
return GetTransitionalDocType(htmlVersion);
if (htmlVersion == HtmlVersion.Html5
&& docTypeParts[0].ToUpper() != "XML")
return GetHtml5DocType();
switch (docTypeParts[0].ToUpper())
{
case "STRICT": return GetStrictDocType(htmlVersion);
case "FRAMESET": return GetFramesetDocType(htmlVersion);
case "5": return GetHtml5DocType();
case "1.1": return GetXHtmlDocType11();
case "BASIC": return GetBasicDocType();
case "MOBILE": return GetMobileDocType();
case "RDFA": return GetRdfaDocType();
case "XML": return GetXmlDocType(docTypeParts, htmlVersion);
default: return GetTransitionalDocType(htmlVersion);
}
}
public Lexer(StreamIn input, TidyOptions options)
{
Input = input;
Lines = 1;
Columns = 1;
State = LEX_CONTENT;
BadAccess = 0;
BadLayout = 0;
BadChars = 0;
BadForm = 0;
Waswhite = false;
Pushed = false;
Insertspace = false;
Exiled = false;
Isvoyager = false;
Versions = HtmlVersion.Everything;
Doctype = HtmlVersion.Unknown;
BadDoctype = false;
Txtstart = 0;
Txtend = 0;
Token = null;
Lexbuf = null;
Lexlength = 0;
Lexsize = 0;
Inode = null;
Insert = - 1;
Istack = new Stack<InlineStack>();
Istackbase = 0;
Styles = null;
Options = options;
SeenBodyEndTag = 0;
_nodeList = new List<Node>();
}
public void AppendSelfClosingTagSuffix_VaryingHtmlVersion_AppendsCorrectOutput(HtmlVersion htmlVersion, string expectedOutput)
{
var template = new DummyTemplate();
string result = template.AppendSelfClosingTagSuffix(htmlVersion);
Assert.That(result, Is.EqualTo(expectedOutput));
}
public string AppendSelfClosingTagSuffix(HtmlVersion htmlVersion)
{
base.SetHtmlVersion(htmlVersion);
return(base.AppendSelfClosingTagSuffix());
}
public void RenderAttributeNameValuePair_BooleanAttribute_WritesCorrectAttributes(string name, string value, HtmlVersion htmlVersion, string expectedOutput)
{
var template = new DummyTemplate();
template.SetHtmlVersion(htmlVersion);
string result = template.RenderAttributeNameValuePair(name, value, '\"');
Assert.That(result, Is.EqualTo(expectedOutput));
}
public string AppendSelfClosingTagSuffix(HtmlVersion htmlVersion)
{
base.SetHtmlVersion(htmlVersion);
return base.AppendSelfClosingTagSuffix();
}
/*
modes for GetToken()
MixedContent -- for elements which don't accept PCDATA
Preformatted -- white space preserved as is
IgnoreMarkup -- for CDATA elements such as script, style
*/
public virtual Node GetToken(short mode)
{
int c;
int badcomment = 0;
var isempty = new MutableBoolean();
if (Pushed)
{
/* duplicate inlines in preference to pushed text nodes when appropriate */
if (Token.Type != Node.TEXT_NODE || (Insert == - 1 && Inode == null))
{
Pushed = false;
return Token;
}
}
/* at start of block elements, unclosed inline
elements are inserted into the token stream */
if (Insert != - 1 || Inode != null)
{
return InsertedToken();
}
Lines = Input.CursorLine;
Columns = Input.CursorColumn;
Waswhite = false;
Txtstart = Lexsize;
Txtend = Lexsize;
while (true)
{
c = Input.ReadChar();
if (c == StreamIn.END_OF_STREAM)
{
break;
}
if (Insertspace && mode != IGNORE_WHITESPACE)
{
AddCharToLexer(' ');
Waswhite = true;
Insertspace = false;
}
/* treat \r\n as \n and \r as \n */
if (c == '\r')
{
c = Input.ReadChar();
if (c != '\n')
{
Input.UngetChar(c);
}
c = '\n';
}
AddCharToLexer(c);
short map;
switch (State)
{
case LEX_CONTENT:
map = Map((char) c);
/*
Discard white space if appropriate. Its cheaper
to do this here rather than in parser methods
for elements that don't have mixed content.
*/
if (((map & WHITE) != 0) && (mode == IGNORE_WHITESPACE) && Lexsize == Txtstart + 1)
{
--Lexsize;
Waswhite = false;
Lines = Input.CursorLine;
Columns = Input.CursorColumn;
continue;
}
if (c == '<')
{
State = LEX_GT;
continue;
}
if ((map & WHITE) != 0)
{
/* was previous char white? */
if (Waswhite)
{
if (mode != PREFORMATTED && mode != IGNORE_MARKUP)
{
--Lexsize;
Lines = Input.CursorLine;
Columns = Input.CursorColumn;
}
}
/* prev char wasn't white */
else
{
Waswhite = true;
if (mode != PREFORMATTED && mode != IGNORE_MARKUP && c != ' ')
{
ChangeChar((byte) ' ');
}
}
continue;
}
if (c == '&' && mode != IGNORE_MARKUP)
{
ParseEntity(mode);
}
/* this is needed to avoid trimming trailing whitespace */
if (mode == IGNORE_WHITESPACE)
mode = MIXED_CONTENT;
Waswhite = false;
continue;
case LEX_GT:
if (c == '/')
{
c = Input.ReadChar();
if (c == StreamIn.END_OF_STREAM)
{
Input.UngetChar(c);
continue;
}
AddCharToLexer(c);
map = Map((char) c);
if ((map & LETTER) != 0)
{
Lexsize -= 3;
Txtend = Lexsize;
Input.UngetChar(c);
State = LEX_ENDTAG;
Lexbuf[Lexsize] = (byte) '\x0000'; /* debug */
Input.CursorColumn -= 2;
/* if some text before the </ return it now */
if (Txtend > Txtstart)
{
/* trim space char before end tag */
if (mode == IGNORE_WHITESPACE && Lexbuf[Lexsize - 1] == (byte) ' ')
{
Lexsize -= 1;
Txtend = Lexsize;
}
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
continue; /* no text so keep going */
}
/* otherwise treat as CDATA */
Waswhite = false;
State = LEX_CONTENT;
continue;
}
if (mode == IGNORE_MARKUP)
{
/* otherwise treat as CDATA */
Waswhite = false;
State = LEX_CONTENT;
continue;
}
/*
look out for comments, doctype or marked sections
this isn't quite right, but its getting there ...
*/
if (c == '!')
{
c = Input.ReadChar();
if (c == '-')
{
c = Input.ReadChar();
if (c == '-')
{
State = LEX_COMMENT; /* comment */
Lexsize -= 2;
Txtend = Lexsize;
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
Txtstart = Lexsize;
continue;
}
Report.Warning(this, null, null, Report.MALFORMED_COMMENT);
}
else if (c == 'd' || c == 'D')
{
State = LEX_DOCTYPE; /* doctype */
Lexsize -= 2;
Txtend = Lexsize;
mode = IGNORE_WHITESPACE;
/* skip until white space or '>' */
for (;;)
{
c = Input.ReadChar();
if (c == StreamIn.END_OF_STREAM || c == '>')
{
Input.UngetChar(c);
break;
}
map = Map((char) c);
if ((map & WHITE) == 0)
{
continue;
}
/* and skip to end of whitespace */
for (;;)
{
c = Input.ReadChar();
if (c == StreamIn.END_OF_STREAM || c == '>')
{
Input.UngetChar(c);
break;
}
map = Map((char) c);
if ((map & WHITE) != 0)
{
continue;
}
Input.UngetChar(c);
break;
}
break;
}
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
Txtstart = Lexsize;
continue;
}
else if (c == '[')
{
/* Word 2000 embeds <![if ...]> ... <![endif]> sequences */
Lexsize -= 2;
State = LEX_SECTION;
Txtend = Lexsize;
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
Txtstart = Lexsize;
continue;
}
/* otherwise swallow chars up to and including next '>' */
while (true)
{
c = Input.ReadChar();
if (c == '>')
{
break;
}
if (c == - 1)
{
Input.UngetChar(c);
break;
}
}
Lexsize -= 2;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
continue;
}
/*
processing instructions
*/
if (c == '?')
{
Lexsize -= 2;
State = LEX_PROCINSTR;
Txtend = Lexsize;
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
Txtstart = Lexsize;
continue;
}
/* Microsoft ASP's e.g. <% ... server-code ... %> */
if (c == '%')
{
Lexsize -= 2;
State = LEX_ASP;
Txtend = Lexsize;
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
Txtstart = Lexsize;
continue;
}
/* Netscapes JSTE e.g. <# ... server-code ... #> */
if (c == '#')
{
Lexsize -= 2;
State = LEX_JSTE;
Txtend = Lexsize;
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
Txtstart = Lexsize;
continue;
}
map = Map((char) c);
/* check for start tag */
if ((map & LETTER) != 0)
{
Input.UngetChar(c); /* push back letter */
Lexsize -= 2; /* discard "<" + letter */
Txtend = Lexsize;
State = LEX_STARTTAG; /* ready to read tag name */
/* if some text before < return it now */
if (Txtend > Txtstart)
{
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
continue; /* no text so keep going */
}
/* otherwise treat as CDATA */
State = LEX_CONTENT;
Waswhite = false;
continue;
case LEX_ENDTAG:
Txtstart = Lexsize - 1;
Input.CursorColumn += 2;
c = ParseTagName();
Token = NewNode(Node.END_TAG, Lexbuf, Txtstart, Txtend,
GetString(Lexbuf, Txtstart, Txtend - Txtstart));
Lexsize = Txtstart;
Txtend = Txtstart;
/* skip to '>' */
while (c != '>')
{
c = Input.ReadChar();
if (c == StreamIn.END_OF_STREAM)
{
break;
}
}
if (c == StreamIn.END_OF_STREAM)
{
Input.UngetChar(c);
continue;
}
State = LEX_CONTENT;
Waswhite = false;
return Token; /* the endtag token */
case LEX_STARTTAG:
Txtstart = Lexsize - 1; /* set txtstart to first letter */
c = ParseTagName();
isempty.Val = false;
AttVal attributes = null;
Token = NewNode((isempty.Val ? Node.START_END_TAG : Node.START_TAG), Lexbuf, Txtstart, Txtend,
GetString(Lexbuf, Txtstart, Txtend - Txtstart));
/* parse attributes, consuming closing ">" */
if (c != '>')
{
if (c == '/')
{
Input.UngetChar(c);
}
attributes = ParseAttrs(isempty);
}
if (isempty.Val)
{
Token.Type = Node.START_END_TAG;
}
Token.Attributes = attributes;
Lexsize = Txtstart;
Txtend = Txtstart;
/* swallow newline following start tag */
/* special check needed for CRLF sequence */
/* this doesn't apply to empty elements */
if (ExpectsContent(Token) || Token.Tag == Options.TagTable.TagBr)
{
c = Input.ReadChar();
if (c == '\r')
{
c = Input.ReadChar();
if (c != '\n')
{
Input.UngetChar(c);
}
}
else if (c != '\n' && c != '\f')
{
Input.UngetChar(c);
}
Waswhite = true; /* to swallow leading whitespace */
}
else
{
Waswhite = false;
}
State = LEX_CONTENT;
if (Token.Tag == null)
{
Report.Error(this, null, Token, Report.UNKNOWN_ELEMENT);
}
else if (!Options.XmlTags)
{
Versions &= Token.Tag.Versions;
if ((Token.Tag.Versions & HtmlVersion.Proprietary) != 0)
{
if (!Options.MakeClean &&
(Token.Tag == Options.TagTable.TagNobr || Token.Tag == Options.TagTable.TagWbr))
{
Report.Warning(this, null, Token, Report.PROPRIETARY_ELEMENT);
}
}
if (Token.Tag.CheckAttribs != null)
{
Token.CheckUniqueAttributes(this);
Token.Tag.CheckAttribs.Check(this, Token);
}
else
{
Token.CheckAttributes(this);
}
}
return Token; /* return start tag */
case LEX_COMMENT:
if (c != '-')
{
continue;
}
c = Input.ReadChar();
AddCharToLexer(c);
if (c != '-')
{
continue;
}
while (true)
{
c = Input.ReadChar();
if (c == '>')
{
if (badcomment != 0)
{
Report.Warning(this, null, null, Report.MALFORMED_COMMENT);
}
Txtend = Lexsize - 2; // AQ 8Jul2000
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.COMMENT_TAG, Lexbuf, Txtstart, Txtend);
/* now look for a line break */
c = Input.ReadChar();
if (c == '\r')
{
c = Input.ReadChar();
if (c != '\n')
{
Token.Linebreak = true;
}
}
if (c == '\n')
{
Token.Linebreak = true;
}
else
{
Input.UngetChar(c);
}
return Token;
}
/* note position of first such error in the comment */
if (badcomment == 0)
{
Lines = Input.CursorLine;
Columns = Input.CursorColumn - 3;
}
badcomment++;
if (Options.FixComments)
{
Lexbuf[Lexsize - 2] = (byte) '=';
}
AddCharToLexer(c);
/* if '-' then look for '>' to end the comment */
if (c != '-')
{
break;
}
}
/* otherwise continue to look for --> */
Lexbuf[Lexsize - 2] = (byte) '=';
continue;
case LEX_DOCTYPE:
map = Map((char) c);
if ((map & WHITE) != 0)
{
if (Waswhite)
{
Lexsize -= 1;
}
Waswhite = true;
}
else
{
Waswhite = false;
}
if (c != '>')
{
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.DOC_TYPE_TAG, Lexbuf, Txtstart, Txtend);
/* make a note of the version named by the doctype */
Doctype = FindGivenVersion(Token);
return Token;
case LEX_PROCINSTR:
if (Lexsize - Txtstart == 3)
{
if ((GetString(Lexbuf, Txtstart, 3)).Equals("php"))
{
State = LEX_PHP;
continue;
}
}
if (Options.XmlPIs)
{
/* insist on ?> as terminator */
if (c != '?')
{
continue;
}
/* now look for '>' */
c = Input.ReadChar();
if (c == StreamIn.END_OF_STREAM)
{
Report.Warning(this, null, null, Report.UNEXPECTED_END_OF_FILE);
Input.UngetChar(c);
continue;
}
AddCharToLexer(c);
}
if (c != '>')
{
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.PROC_INS_TAG, Lexbuf, Txtstart, Txtend);
return Token;
case LEX_ASP:
if (c != '%')
{
continue;
}
/* now look for '>' */
c = Input.ReadChar();
if (c != '>')
{
Input.UngetChar(c);
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.ASP_TAG, Lexbuf, Txtstart, Txtend);
return Token;
case LEX_JSTE:
if (c != '#')
{
continue;
}
/* now look for '>' */
c = Input.ReadChar();
if (c != '>')
{
Input.UngetChar(c);
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.JSTE_TAG, Lexbuf, Txtstart, Txtend);
return Token;
case LEX_PHP:
if (c != '?')
{
continue;
}
/* now look for '>' */
c = Input.ReadChar();
if (c != '>')
{
Input.UngetChar(c);
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.PHP_TAG, Lexbuf, Txtstart, Txtend);
return Token;
case LEX_SECTION:
if (c == '[')
{
if (Lexsize == (Txtstart + 6) && (GetString(Lexbuf, Txtstart, 6)).Equals("CDATA["))
{
State = LEX_CDATA;
Lexsize -= 6;
continue;
}
}
if (c != ']')
{
continue;
}
/* now look for '>' */
c = Input.ReadChar();
if (c != '>')
{
Input.UngetChar(c);
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.SECTION_TAG, Lexbuf, Txtstart, Txtend);
return Token;
case LEX_CDATA:
if (c != ']')
{
continue;
}
/* now look for ']' */
c = Input.ReadChar();
if (c != ']')
{
Input.UngetChar(c);
continue;
}
/* now look for '>' */
c = Input.ReadChar();
if (c != '>')
{
Input.UngetChar(c);
continue;
}
Lexsize -= 1;
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.CDATA_TAG, Lexbuf, Txtstart, Txtend);
return Token;
}
}
if (State == LEX_CONTENT)
{
/* text string */
Txtend = Lexsize;
if (Txtend > Txtstart)
{
Input.UngetChar(c);
if (Lexbuf[Lexsize - 1] == (byte) ' ')
{
Lexsize -= 1;
Txtend = Lexsize;
}
Token = NewNode(Node.TEXT_NODE, Lexbuf, Txtstart, Txtend);
return Token;
}
}
else if (State == LEX_COMMENT)
{
/* comment */
if (c == StreamIn.END_OF_STREAM)
{
Report.Warning(this, null, null, Report.MALFORMED_COMMENT);
}
Txtend = Lexsize;
Lexbuf[Lexsize] = (byte) '\x0000';
State = LEX_CONTENT;
Waswhite = false;
Token = NewNode(Node.COMMENT_TAG, Lexbuf, Txtstart, Txtend);
return Token;
}
return null;
}
/* fixup doctype if missing */
public virtual bool FixDocType(Node root)
{
Node doctype;
HtmlVersion guessed = HtmlVersion.Html40Strict;
int i;
if (this.badDoctype)
{
Report.Warning(this, null, null, Report.MALFORMED_DOCTYPE);
}
if (Options.XmlOut)
{
return true;
}
doctype = root.FindDocType();
if (Options.DocType == TidyNet.DocType.Omit)
{
if (doctype != null)
{
Node.DiscardElement(doctype);
}
return true;
}
if (Options.DocType == TidyNet.DocType.Strict)
{
Node.DiscardElement(doctype);
doctype = null;
guessed = HtmlVersion.Html40Strict;
}
else if (Options.DocType == TidyNet.DocType.Loose)
{
Node.DiscardElement(doctype);
doctype = null;
guessed = HtmlVersion.Html40Loose;
}
else if (Options.DocType == TidyNet.DocType.Auto)
{
if (doctype != null)
{
if (this.doctype == HtmlVersion.Unknown)
{
return false;
}
switch (this.doctype)
{
case HtmlVersion.Unknown:
return false;
case HtmlVersion.Html20:
if ((this.versions & HtmlVersion.Html20) != 0)
{
return true;
}
break; /* to replace old version by new */
case HtmlVersion.Html32:
if ((this.versions & HtmlVersion.Html32) != 0)
{
return true;
}
break; /* to replace old version by new */
case HtmlVersion.Html40Strict:
if ((this.versions & HtmlVersion.Html40Strict) != 0)
{
return true;
}
break; /* to replace old version by new */
case HtmlVersion.Html40Loose:
if ((this.versions & HtmlVersion.Html40Loose) != 0)
{
return true;
}
break; /* to replace old version by new */
case HtmlVersion.Frames:
if ((this.versions & HtmlVersion.Frames) != 0)
{
return true;
}
break; /* to replace old version by new */
}
/* INCONSISTENT_VERSION warning is now issued by ApparentVersion() */
}
/* choose new doctype */
guessed = GetHtmlVersion();
}
if (guessed == HtmlVersion.Unknown)
{
return false;
}
/* for XML use the Voyager system identifier */
if (this.Options.XmlOut || this.Options.XmlTags || this.isvoyager)
{
if (doctype != null)
Node.DiscardElement(doctype);
for (i = 0; i < W3CVersion.Length; ++i)
{
if (guessed == W3CVersion[i].Version)
{
FixHtmlNameSpace(root, W3CVersion[i].Profile);
break;
}
}
return true;
}
if (doctype == null)
{
doctype = NewNode(Node.DocTypeTag, this.lexbuf, 0, 0);
doctype.Next = root.Content;
doctype.Parent = root;
doctype.Prev = null;
root.Content = doctype;
}
this.txtstart = this.lexsize;
this.txtend = this.lexsize;
/* use the appropriate public identifier */
AddStringLiteral("html PUBLIC ");
if (Options.DocType == TidyNet.DocType.User && Options.DocTypeStr != null)
{
AddStringLiteral(Options.DocTypeStr);
}
else if (guessed == HtmlVersion.Html20)
{
AddStringLiteral("\"-//IETF//DTD HTML 2.0//EN\"");
}
else
{
AddStringLiteral("\"-//W3C//DTD ");
for (i = 0; i < W3CVersion.Length; ++i)
{
if (guessed == W3CVersion[i].Version)
{
AddStringLiteral(W3CVersion[i].Name);
break;
}
}
AddStringLiteral("//EN\"");
}
this.txtend = this.lexsize;
doctype.Start = this.txtstart;
doctype.End = this.txtend;
return true;
}
public virtual bool SetXhtmlDocType(Node root)
{
string fpi = " ";
string sysid = "";
string namespace_Renamed = XHTML_NAMESPACE;
Node doctype;
doctype = root.FindDocType();
if (Options.DocType == TidyNet.DocType.Omit)
{
if (doctype != null)
Node.DiscardElement(doctype);
return true;
}
if (Options.DocType == TidyNet.DocType.Auto)
{
/* see what flavor of XHTML this document matches */
if ((this.versions & HtmlVersion.Html40Strict) != 0)
{
/* use XHTML strict */
fpi = "-//W3C//DTD XHTML 1.0 Strict//EN";
sysid = voyager_strict;
}
else if ((this.versions & HtmlVersion.Loose) != 0)
{
fpi = "-//W3C//DTD XHTML 1.0 Transitional//EN";
sysid = voyager_loose;
}
else if ((this.versions & HtmlVersion.Frames) != 0)
{
/* use XHTML frames */
fpi = "-//W3C//DTD XHTML 1.0 Frameset//EN";
sysid = voyager_frameset;
}
else
{
/* lets assume XHTML transitional */
fpi = "-//W3C//DTD XHTML 1.0 Transitional//EN";
sysid = voyager_loose;
}
}
else if (Options.DocType == TidyNet.DocType.Strict)
{
fpi = "-//W3C//DTD XHTML 1.0 Strict//EN";
sysid = voyager_strict;
}
else if (Options.DocType == TidyNet.DocType.Loose)
{
fpi = "-//W3C//DTD XHTML 1.0 Transitional//EN";
sysid = voyager_loose;
}
FixHtmlNameSpace(root, namespace_Renamed);
if (doctype == null)
{
doctype = NewNode(Node.DocTypeTag, this.lexbuf, 0, 0);
doctype.Next = root.Content;
doctype.Parent = root;
doctype.Prev = null;
root.Content = doctype;
}
if (Options.DocType == TidyNet.DocType.User && Options.DocTypeStr != null)
{
fpi = Options.DocTypeStr;
sysid = "";
}
this.txtstart = this.lexsize;
this.txtend = this.lexsize;
/* add public identifier */
AddStringLiteral("html PUBLIC ");
/* check if the fpi is quoted or not */
if (fpi[0] == '"')
{
AddStringLiteral(fpi);
}
else
{
AddStringLiteral("\"");
AddStringLiteral(fpi);
AddStringLiteral("\"");
}
if (sysid.Length + 6 >= this.Options.WrapLen)
{
AddStringLiteral("\n\"");
}
else
{
AddStringLiteral("\n \"");
}
/* add system identifier */
AddStringLiteral(sysid);
AddStringLiteral("\"");
this.txtend = this.lexsize;
doctype.Start = this.txtstart;
doctype.End = this.txtend;
return false;
}
public W3CVersionInfo(string name, string voyagerName, string profile, HtmlVersion version)
{
Name = name;
VoyagerName = voyagerName;
Profile = profile;
Version = version;
}
public void SetHtmlVersion(HtmlVersion htmlVersion)
{
_htmlVersion = htmlVersion;
}
public void Walk_ReturnsCorrectDocType(string docTypeId, HtmlVersion htmlVersion, string expectedDocType)
{
var docType = DocTypeFactory.GetDocType(docTypeId, htmlVersion);
Assert.That(docType, Is.EqualTo(expectedDocType));
}
private static string GetXmlDocType(IList<string> docTypeParts, HtmlVersion htmlVersion)
{
if (htmlVersion != HtmlVersion.XHtml) return "";
string encoding = docTypeParts.Count < 2
? "utf-8"
: docTypeParts[1];
return "<?xml version='1.0' encoding='" + encoding + "' ?>";
}
public void Render(TextWriter writer, T model, HtmlVersion htmlVersion)
{
Model = model;
base.Render(writer, htmlVersion);
}
public Lexer(StreamIn input, TidyOptions options)
{
this.input = input;
this.lines = 1;
this.columns = 1;
this.state = LEX_CONTENT;
this.badAccess = 0;
this.badLayout = 0;
this.badChars = 0;
this.badForm = 0;
this.waswhite = false;
this.pushed = false;
this.insertspace = false;
this.exiled = false;
this.isvoyager = false;
this.versions = HtmlVersion.Everything;
this.doctype = HtmlVersion.Unknown;
this.badDoctype = false;
this.txtstart = 0;
this.txtend = 0;
this.token = null;
this.lexbuf = null;
this.lexlength = 0;
this.lexsize = 0;
this.inode = null;
this.insert = - 1;
this.istack = new Stack();
this.istackbase = 0;
this.styles = null;
this.Options = options;
this.seenBodyEndTag = 0;
this.nodeList = new ArrayList();
}
public void Render(TextWriter writer, HtmlVersion htmlVersion)
{
Render(writer, htmlVersion, ViewData ?? new Dictionary <string, object>());
}
public void SetHtmlVersion(HtmlVersion htmlVersion)
{
_htmlVersion = htmlVersion;
}
/*
modes for GetToken()
MixedContent -- for elements which don't accept PCDATA
Preformatted -- white space preserved as is
IgnoreMarkup -- for CDATA elements such as script, style
*/
public virtual Node GetToken(short mode)
{
short map;
int c = 0;
int lastc;
int badcomment = 0;
MutableBoolean isempty = new MutableBoolean();
AttVal attributes;
if (pushed)
{
/* duplicate inlines in preference to pushed text nodes when appropriate */
if (token.Type != Node.TextNode || (insert == - 1 && inode == null))
{
pushed = false;
return token;
}
}
/* at start of block elements, unclosed inline
elements are inserted into the token stream */
if (insert != - 1 || inode != null)
{
return InsertedToken();
}
lines = input.curline;
columns = input.curcol;
waswhite = false;
txtstart = lexsize;
txtend = lexsize;
while (true)
{
c = input.ReadChar();
if (c == StreamIn.EndOfStream)
{
break;
}
if (insertspace && mode != IgnoreWhitespace)
{
AddCharToLexer(' ');
waswhite = true;
insertspace = false;
}
/* treat \r\n as \n and \r as \n */
if (c == '\r')
{
c = input.ReadChar();
if (c != '\n')
{
input.UngetChar(c);
}
c = '\n';
}
AddCharToLexer(c);
switch (state)
{
case LEX_CONTENT:
map = MAP((char) c);
/*
Discard white space if appropriate. Its cheaper
to do this here rather than in parser methods
for elements that don't have mixed content.
*/
if (((map & WHITE) != 0) && (mode == IgnoreWhitespace) && lexsize == txtstart + 1)
{
--lexsize;
waswhite = false;
lines = input.curline;
columns = input.curcol;
continue;
}
if (c == '<')
{
state = LEX_GT;
continue;
}
if ((map & WHITE) != 0)
{
/* was previous char white? */
if (waswhite)
{
if (mode != Preformatted && mode != IgnoreMarkup)
{
--lexsize;
lines = input.curline;
columns = input.curcol;
}
}
/* prev char wasn't white */
else
{
waswhite = true;
lastc = c;
if (mode != Preformatted && mode != IgnoreMarkup && c != ' ')
{
ChangeChar((byte) ' ');
}
}
continue;
}
else if (c == '&' && mode != IgnoreMarkup)
{
ParseEntity(mode);
}
/* this is needed to avoid trimming trailing whitespace */
if (mode == IgnoreWhitespace)
mode = MixedContent;
waswhite = false;
continue;
case LEX_GT:
if (c == '/')
{
c = input.ReadChar();
if (c == StreamIn.EndOfStream)
{
input.UngetChar(c);
continue;
}
AddCharToLexer(c);
map = MAP((char) c);
if ((map & LETTER) != 0)
{
lexsize -= 3;
txtend = lexsize;
input.UngetChar(c);
state = LEX_ENDTAG;
lexbuf[lexsize] = (byte) '\x0000'; /* debug */
input.curcol -= 2;
/* if some text before the </ return it now */
if (txtend > txtstart)
{
/* trim space char before end tag */
if (mode == IgnoreWhitespace && lexbuf[lexsize - 1] == (byte) ' ')
{
lexsize -= 1;
txtend = lexsize;
}
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
continue; /* no text so keep going */
}
/* otherwise treat as CDATA */
waswhite = false;
state = LEX_CONTENT;
continue;
}
if (mode == IgnoreMarkup)
{
/* otherwise treat as CDATA */
waswhite = false;
state = LEX_CONTENT;
continue;
}
/*
look out for comments, doctype or marked sections
this isn't quite right, but its getting there ...
*/
if (c == '!')
{
c = input.ReadChar();
if (c == '-')
{
c = input.ReadChar();
if (c == '-')
{
state = LEX_COMMENT; /* comment */
lexsize -= 2;
txtend = lexsize;
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
txtstart = lexsize;
continue;
}
Report.Warning(this, null, null, Report.MALFORMED_COMMENT);
}
else if (c == 'd' || c == 'D')
{
state = LEX_DOCTYPE; /* doctype */
lexsize -= 2;
txtend = lexsize;
mode = IgnoreWhitespace;
/* skip until white space or '>' */
for (; ; )
{
c = input.ReadChar();
if (c == StreamIn.EndOfStream || c == '>')
{
input.UngetChar(c);
break;
}
map = MAP((char) c);
if ((map & WHITE) == 0)
{
continue;
}
/* and skip to end of whitespace */
for (; ; )
{
c = input.ReadChar();
if (c == StreamIn.EndOfStream || c == '>')
{
input.UngetChar(c);
break;
}
map = MAP((char) c);
if ((map & WHITE) != 0)
{
continue;
}
input.UngetChar(c);
break;
}
break;
}
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
txtstart = lexsize;
continue;
}
else if (c == '[')
{
/* Word 2000 embeds <![if ...]> ... <![endif]> sequences */
lexsize -= 2;
state = LEX_SECTION;
txtend = lexsize;
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
txtstart = lexsize;
continue;
}
/* otherwise swallow chars up to and including next '>' */
while (true)
{
c = input.ReadChar();
if (c == '>')
{
break;
}
if (c == - 1)
{
input.UngetChar(c);
break;
}
}
lexsize -= 2;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
continue;
}
/*
processing instructions
*/
if (c == '?')
{
lexsize -= 2;
state = LEX_PROCINSTR;
txtend = lexsize;
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
txtstart = lexsize;
continue;
}
/* Microsoft ASP's e.g. <% ... server-code ... %> */
if (c == '%')
{
lexsize -= 2;
state = LEX_ASP;
txtend = lexsize;
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
txtstart = lexsize;
continue;
}
/* Netscapes JSTE e.g. <# ... server-code ... #> */
if (c == '#')
{
lexsize -= 2;
state = LEX_JSTE;
txtend = lexsize;
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
txtstart = lexsize;
continue;
}
map = MAP((char) c);
/* check for start tag */
if ((map & LETTER) != 0)
{
input.UngetChar(c); /* push back letter */
lexsize -= 2; /* discard "<" + letter */
txtend = lexsize;
state = LEX_STARTTAG; /* ready to read tag name */
/* if some text before < return it now */
if (txtend > txtstart)
{
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
continue; /* no text so keep going */
}
/* otherwise treat as CDATA */
state = LEX_CONTENT;
waswhite = false;
continue;
case LEX_ENDTAG:
txtstart = lexsize - 1;
input.curcol += 2;
c = ParseTagName();
token = NewNode(Node.EndTag, lexbuf, txtstart, txtend, GetString(lexbuf, txtstart, txtend - txtstart));
lexsize = txtstart;
txtend = txtstart;
/* skip to '>' */
while (c != '>')
{
c = input.ReadChar();
if (c == StreamIn.EndOfStream)
{
break;
}
}
if (c == StreamIn.EndOfStream)
{
input.UngetChar(c);
continue;
}
state = LEX_CONTENT;
waswhite = false;
return token; /* the endtag token */
case LEX_STARTTAG:
txtstart = lexsize - 1; /* set txtstart to first letter */
c = ParseTagName();
isempty.Val = false;
attributes = null;
token = NewNode((isempty.Val ? Node.StartEndTag : Node.StartTag), lexbuf, txtstart, txtend, GetString(lexbuf, txtstart, txtend - txtstart));
/* parse attributes, consuming closing ">" */
if (c != '>')
{
if (c == '/')
{
input.UngetChar(c);
}
attributes = ParseAttrs(isempty);
}
if (isempty.Val)
{
token.Type = Node.StartEndTag;
}
token.Attributes = attributes;
lexsize = txtstart;
txtend = txtstart;
/* swallow newline following start tag */
/* special check needed for CRLF sequence */
/* this doesn't apply to empty elements */
if (ExpectsContent(token) || token.Tag == Options.tt.TagBr)
{
c = input.ReadChar();
if (c == '\r')
{
c = input.ReadChar();
if (c != '\n')
{
input.UngetChar(c);
}
}
else if (c != '\n' && c != '\f')
{
input.UngetChar(c);
}
waswhite = true; /* to swallow leading whitespace */
}
else
{
waswhite = false;
}
state = LEX_CONTENT;
if (token.Tag == null)
{
Report.Error(this, null, token, Report.UNKNOWN_ELEMENT);
}
else if (!Options.XmlTags)
{
versions &= token.Tag.Versions;
if ((token.Tag.Versions & HtmlVersion.Proprietary) != 0)
{
if (!Options.MakeClean && (token.Tag == Options.tt.TagNobr || token.Tag == Options.tt.TagWbr))
{
Report.Warning(this, null, token, Report.PROPRIETARY_ELEMENT);
}
}
if (token.Tag.CheckAttribs != null)
{
token.CheckUniqueAttributes(this);
token.Tag.CheckAttribs.Check(this, this.token);
}
else
{
token.CheckAttributes(this);
}
}
return token; /* return start tag */
case LEX_COMMENT:
if (c != '-')
{
continue;
}
c = input.ReadChar();
AddCharToLexer(c);
if (c != '-')
{
continue;
}
while (true)
{
c = input.ReadChar();
if (c == '>')
{
if (badcomment != 0)
{
Report.Warning(this, null, null, Report.MALFORMED_COMMENT);
}
txtend = lexsize - 2; // AQ 8Jul2000
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.CommentTag, lexbuf, txtstart, txtend);
/* now look for a line break */
c = input.ReadChar();
if (c == '\r')
{
c = input.ReadChar();
if (c != '\n')
{
token.Linebreak = true;
}
}
if (c == '\n')
{
token.Linebreak = true;
}
else
{
input.UngetChar(c);
}
return token;
}
/* note position of first such error in the comment */
if (badcomment == 0)
{
lines = input.curline;
columns = input.curcol - 3;
}
badcomment++;
if (Options.FixComments)
{
lexbuf[lexsize - 2] = (byte) '=';
}
AddCharToLexer(c);
/* if '-' then look for '>' to end the comment */
if (c != '-')
{
break;
}
}
/* otherwise continue to look for --> */
lexbuf[lexsize - 2] = (byte) '=';
continue;
case LEX_DOCTYPE:
map = MAP((char) c);
if ((map & WHITE) != 0)
{
if (waswhite)
{
lexsize -= 1;
}
waswhite = true;
}
else
{
waswhite = false;
}
if (c != '>')
{
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.DocTypeTag, lexbuf, txtstart, txtend);
/* make a note of the version named by the doctype */
doctype = FindGivenVersion(token);
return token;
case LEX_PROCINSTR:
if (lexsize - txtstart == 3)
{
if ((GetString(lexbuf, txtstart, 3)).Equals("php"))
{
state = LEX_PHP;
continue;
}
}
if (Options.XmlPIs)
{
/* insist on ?> as terminator */
if (c != '?')
{
continue;
}
/* now look for '>' */
c = input.ReadChar();
if (c == StreamIn.EndOfStream)
{
Report.Warning(this, null, null, Report.UNEXPECTED_END_OF_FILE);
input.UngetChar(c);
continue;
}
AddCharToLexer(c);
}
if (c != '>')
{
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.ProcInsTag, lexbuf, txtstart, txtend);
return token;
case LEX_ASP:
if (c != '%')
{
continue;
}
/* now look for '>' */
c = input.ReadChar();
if (c != '>')
{
input.UngetChar(c);
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.AspTag, lexbuf, txtstart, txtend);
return this.token;
case LEX_JSTE:
if (c != '#')
{
continue;
}
/* now look for '>' */
c = input.ReadChar();
if (c != '>')
{
input.UngetChar(c);
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.JsteTag, lexbuf, txtstart, txtend);
return token;
case LEX_PHP:
if (c != '?')
{
continue;
}
/* now look for '>' */
c = input.ReadChar();
if (c != '>')
{
input.UngetChar(c);
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.PhpTag, lexbuf, txtstart, txtend);
return token;
case LEX_SECTION:
if (c == '[')
{
if (lexsize == (txtstart + 6) && (GetString(lexbuf, txtstart, 6)).Equals("CDATA["))
{
state = LEX_CDATA;
lexsize -= 6;
continue;
}
}
if (c != ']')
{
continue;
}
/* now look for '>' */
c = input.ReadChar();
if (c != '>')
{
input.UngetChar(c);
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.SectionTag, lexbuf, txtstart, txtend);
return token;
case LEX_CDATA:
if (c != ']')
{
continue;
}
/* now look for ']' */
c = input.ReadChar();
if (c != ']')
{
input.UngetChar(c);
continue;
}
/* now look for '>' */
c = input.ReadChar();
if (c != '>')
{
input.UngetChar(c);
continue;
}
lexsize -= 1;
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.CDATATag, lexbuf, txtstart, txtend);
return token;
}
}
if (state == LEX_CONTENT)
{
/* text string */
txtend = lexsize;
if (txtend > txtstart)
{
input.UngetChar(c);
if (lexbuf[lexsize - 1] == (byte) ' ')
{
lexsize -= 1;
txtend = lexsize;
}
token = NewNode(Node.TextNode, lexbuf, txtstart, txtend);
return token;
}
}
else if (state == LEX_COMMENT)
{
/* comment */
if (c == StreamIn.EndOfStream)
{
Report.Warning(this, null, null, Report.MALFORMED_COMMENT);
}
txtend = lexsize;
lexbuf[lexsize] = (byte) '\x0000';
state = LEX_CONTENT;
waswhite = false;
token = NewNode(Node.CommentTag, lexbuf, txtstart, txtend);
return token;
}
return null;
}
public void Walk_ReturnsCorrectDocType(string docTypeId, HtmlVersion htmlVersion, string expectedDocType)
{
var docType = DocTypeFactory.GetDocType(docTypeId, htmlVersion);
Assert.That(docType, Is.EqualTo(expectedDocType));
}
public void Render(TextWriter writer, HtmlVersion htmlVersion)
{
Render(writer, htmlVersion, ViewData ?? new Dictionary<string, object>());
}
