void EmitOrAppendStrBuf(InterLexerState returnState)
{
//if ((returnState & DATA_AND_RCDATA_MASK) != 0)
if (((byte)returnState & DATA_AND_RCDATA_MASK) == 0)
{
AppendStrBufToLongStrBuf();
}
else
{
EmitStrBuf();
}
}
protected void SetInterLexerState(InterLexerState interLexerState)
{
}
/**
* Sets the tokenizer state and the associated element name. This should
* only ever used to put the tokenizer into one of the states that have
* a special end tag expectation.
*
* @param specialTokenizerState
* the tokenizer state to set
* @param endTagExpectation
* the expected end tag for transitioning back to normal
*/
public void SetStateAndEndTagExpectation(InterLexerState specialTokenizerState,
ElementName endTagExpectation)
{
this.stateSave = specialTokenizerState;
this.endTagExpectation = endTagExpectation;
EndTagExpectationToArray();
}
// ]NOCPP]
// For the token handler to call
/**
* Sets the tokenizer state and the associated element name. This should
* only ever used to put the tokenizer into one of the states that have
* a special end tag expectation.
*
* @param specialTokenizerState
* the tokenizer state to set
* @param endTagExpectation
* the expected end tag for transitioning back to normal
*/
public void SetStateAndEndTagExpectation(InterLexerState specialTokenizerState,
[Local] String endTagExpectation)
{
this.stateSave = specialTokenizerState;
if (specialTokenizerState == InterLexerState.s01_DATA_i)
{
return;
}
this.endTagExpectation = ElementName.ElementNameByBuffer(endTagExpectation.ToCharArray());
EndTagExpectationToArray();
}
public void ResetToDataState()
{
this.strBuffer = new StringBuilder();
this.longStrBuffer = new StringBuilder();
stateSave = InterLexerState.s01_DATA_i;
// line = 1; XXX line numbers
lastCR = false;
index = 0;
forceQuirks = false;
additional = '\u0000';
entCol = -1;
firstCharKey = -1;
lo = 0;
hi = 0; // will always be overwritten before use anyway
candidate = -1;
strBufMark = 0;
prevValue = -1;
value = 0;
seenDigits = false;
endTag = false;
// Removed J. Treworgy 12/7/2012 - this should remain true so the parser can choose to abort
//shouldSuspend = false;
InitDoctypeFields();
if (tagName != null)
{
tagName = null;
}
if (attributeName != null)
{
attributeName = null;
}
// [NOCPP[
if (newAttributesEachTime)
{
// ]NOCPP]
if (attributes != null)
{
attributes = null;
}
// [NOCPP[
}
// ]NOCPP]
}
void HandleNcrValue(InterLexerState returnState)
{
/*
* If one or more characters match the range, then take them all and
* interpret the string of characters as a number (either hexadecimal or
* decimal as appropriate).
*/
if (value <= 0xFFFF)
{
if (value >= 0x80 && value <= 0x9f)
{
/*
* If that number is one of the numbers in the first column of
* the following table, then this is a parse error.
*/
ErrNcrInC1Range();
/*
* Find the row with that number in the first column, and return
* a character token for the Unicode character given in the
* second column of that row.
*/
char[] val = NamedCharacters.WINDOWS_1252[value - 0x80];
EmitOrAppendOne(val, returnState);
// [NOCPP[
}
else if (value == 0xC
&& contentSpacePolicy != XmlViolationPolicy.Allow)
{
if (contentSpacePolicy == XmlViolationPolicy.AlterInfoset)
{
EmitOrAppendOne(SPACE, returnState);
}
else if (contentSpacePolicy == XmlViolationPolicy.Fatal)
{
Fatal("A character reference expanded to a form feed which is not legal XML 1.0 white space.");
}
// ]NOCPP]
}
else if (value == 0x0)
{
ErrNcrZero();
EmitOrAppendOne(REPLACEMENT_CHARACTER, returnState);
}
else if ((value & 0xF800) == 0xD800)
{
ErrNcrSurrogate();
EmitOrAppendOne(Tokenizer2.REPLACEMENT_CHARACTER, returnState);
}
else
{
/*
* Otherwise, return a character token for the Unicode character
* whose code point is that number.
*/
char ch = (char)value;
// [NOCPP[
if (value == 0x0D)
{
ErrNcrCr();
}
else if ((value <= 0x0008) || (value == 0x000B)
|| (value >= 0x000E && value <= 0x001F))
{
ch = ErrNcrControlChar(ch);
}
else if (value >= 0xFDD0 && value <= 0xFDEF)
{
ErrNcrUnassigned();
}
else if ((value & 0xFFFE) == 0xFFFE)
{
ch = ErrNcrNonCharacter(ch);
}
else if (value >= 0x007F && value <= 0x009F)
{
ErrNcrControlChar();
}
else
{
MaybeWarnPrivateUse(ch);
}
// ]NOCPP]
bmpChar[0] = ch;
EmitOrAppendOne(bmpChar, returnState);
}
}
else if (value <= 0x10FFFF)
{
// [NOCPP[
MaybeWarnPrivateUseAstral();
if ((value & 0xFFFE) == 0xFFFE)
{
ErrAstralNonCharacter(value);
}
// ]NOCPP]
astralChar[0] = (char)(LEAD_OFFSET + (value >> 10));
astralChar[1] = (char)(0xDC00 + (value & 0x3FF));
EmitOrAppendTwo(astralChar, returnState);
}
else
{
ErrNcrOutOfRange();
EmitOrAppendOne(REPLACEMENT_CHARACTER, returnState);
}
}
void EmitOrAppendOne(char[] val, InterLexerState returnState)
{
if (((byte)returnState & DATA_AND_RCDATA_MASK) == 0)
{
AppendLongStrBuf(val[0]);
}
else
{
TokenListener.Characters(val, 0, 1);
}
}
void EmitOrAppendTwo(char[] val, InterLexerState returnState)
{
//TODO: review here=> use != or == ?
//if ((returnState & DATA_AND_RCDATA_MASK) != 0)
if (((byte)returnState & DATA_AND_RCDATA_MASK) == 0)
{
AppendLongStrBuf(val[0]);
AppendLongStrBuf(val[1]);
}
else
{
TokenListener.Characters(val, 0, 2);
}
}
void StateLoop3(InterLexerState state, InterLexerState returnState)
{
var subLexerTagAndAttr = new SubLexerTagAndAttr();
var subLexerComment = new SubLexerComment();
var subLexerScriptData = new SubLexerScriptData();
var subLexerNCR = new SubLexerNCR();
var subLexerDocType = new SubLexerDocType();
var subLexerRawText = new SubLexerCData();
for (; ; )
{
//*************
continueStateloop:
//*************
switch (state)
{
case InterLexerState.s01_DATA_i:
/*dataloop:*/
{
char c;
while (reader.ReadNext(out c))
{
switch (c)
{
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the character
* reference in data state.
*/
FlushChars();
ClearStrBufAndAppend(c);
SetAdditionalAndRememberAmpersandLocation('\u0000');
returnState = state;
//state = Transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos);
state = InterLexerState.CONSUME_CHARACTER_REFERENCE_i;
goto continueStateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the tag
* open state.
*/
FlushChars();
//state = Transition(state, Tokenizer.TAG_OPEN, reconsume, pos);
//**************
subLexerTagAndAttr.StateLoop3_Tag(SubLexerTagState.s08_TAG_OPEN_p, SubLexerTagState.s08_TAG_OPEN_p);
state = subLexerTagAndAttr.OutputState;
//**************
break;
// stateloop;
case '\u0000':
EmitReplacementCharacter();
continue;
case '\r':
EmitCarriageReturn();
return;
case '\n':
default:
/*
* Anything else Emit the input character as a
* character token.
*
* Stay in the data state.
*/
continue;
}
}
} break;
}
}
}
