public void LoadState(Tokenizer other)
{
strBufLen = other.strBufLen;
if (strBufLen > strBuf.Length)
{
strBuf = new char[strBufLen];
}
Array.Copy(other.strBuf, strBuf, strBufLen);
longStrBufLen = other.longStrBufLen;
if (longStrBufLen > longStrBuf.Length)
{
longStrBuf = new char[longStrBufLen];
}
Array.Copy(other.longStrBuf, longStrBuf, longStrBufLen);
stateSave = other.stateSave;
returnStateSave = other.returnStateSave;
endTagExpectation = other.endTagExpectation;
endTagExpectationAsArray = other.endTagExpectationAsArray;
// line = 1; XXX line numbers
lastCR = other.lastCR;
index = other.index;
forceQuirks = other.forceQuirks;
additional = other.additional;
entCol = other.entCol;
firstCharKey = other.firstCharKey;
lo = other.lo;
hi = other.hi;
candidate = other.candidate;
strBufMark = other.strBufMark;
prevValue = other.prevValue;
value = other.value;
seenDigits = other.seenDigits;
endTag = other.endTag;
shouldSuspend = false;
if (other.doctypeName == null)
{
doctypeName = null;
}
else
{
doctypeName = other.doctypeName;
}
if (other.systemIdentifier == null)
{
systemIdentifier = null;
}
else
{
systemIdentifier = other.systemIdentifier;
}
if (other.publicIdentifier == null)
{
publicIdentifier = null;
}
else
{
publicIdentifier = other.publicIdentifier;
}
if (other.tagName == null)
{
tagName = null;
}
else
{
tagName = other.tagName.CloneElementName();
}
if (other.attributeName == null)
{
attributeName = null;
}
else
{
attributeName = other.attributeName.CloneAttributeName();
}
if (other.attributes == null)
{
attributes = null;
}
else
{
attributes = other.attributes.CloneAttributes();
}
}
public void End()
{
strBuf = null;
longStrBuf = null;
doctypeName = null;
systemIdentifier = null;
publicIdentifier = null;
tagName = null;
attributeName = null;
TokenHandler.EndTokenization();
if (attributes != null)
{
attributes.Clear(mappingLangToXmlLang);
attributes = null;
}
}
private void StrBufToElementNameString()
{
tagName = ElementName.ElementNameByBuffer(strBuf, 0, strBufLen);
}
private int StateLoop(int state, char c, int pos, char[] buf, bool reconsume, int returnState, int endPos)
{
/*
* Idioms used in this code:
*
*
* Consuming the next input character
*
* To consume the next input character, the code does this: if (++pos ==
* endPos) { goto breakStateloop; } c = checkChar(buf, pos);
*
*
* Staying in a state
*
* When there's a state that the tokenizer may stay in over multiple
* input characters, the state has a wrapper |for(;;)| loop and staying
* in the state continues the loop.
*
*
* Switching to another state
*
* To switch to another state, the code sets the state variable to the
* magic number of the new state. Then it either continues stateloop or
* breaks out of the state's own wrapper loop if the target state is
* right after the current state in source order. (This is a partial
* workaround for Java's lack of goto.)
*
*
* Reconsume support
*
* The spec sometimes says that an input character is reconsumed in
* another state. If a state can ever be entered so that an input
* character can be reconsumed in it, the state's code starts with an
* |if (reconsume)| that sets reconsume to false and skips over the
* normal code for consuming a new character.
*
* To reconsume the current character in another state, the code sets
* |reconsume| to true and then switches to the other state.
*
*
* Emitting character tokens
*
* This method emits character tokens lazily. Whenever a new range of
* character tokens starts, the field cstart must be set to the start
* index of the range. The flushChars() method must be called at the end
* of a range to flush it.
*
*
* U+0000 handling
*
* The various states have to handle the replacement of U+0000 with
* U+FFFD. However, if U+0000 would be reconsumed in another state, the
* replacement doesn't need to happen, because it's handled by the
* reconsuming state.
*
*
* LF handling
*
* Every state needs to increment the line number upon LF unless the LF
* gets reconsumed by another state which increments the line number.
*
*
* CR handling
*
* Every state needs to handle CR unless the CR gets reconsumed and is
* handled by the reconsuming state. The CR needs to be handled as if it
* were and LF, the lastCR field must be set to true and then this
* method must return. The IO driver will then swallow the next
* character if it is an LF to coalesce CRLF.
*/
/*
* As there is no support for labeled loops in C#, instead of break <loop>;
* the port uses goto break<loop>; and a label after the loop.
* Instead of continue <loop>; it uses goto continue<loop>; and a label
* at the beginning or end of the loop (which doesn't matter in for(;;) loops)
*/
/*stateloop:*/
for (; ; )
{
continueStateloop:
switch (state)
{
case DATA:
/*dataloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
switch (c)
{
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the character
* reference in data state.
*/
FlushChars(buf, pos);
ClearStrBufAndAppend(c);
SetAdditionalAndRememberAmpersandLocation('\u0000');
returnState = state;
goto continueStateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the tag
* open state.
*/
FlushChars(buf, pos);
goto breakDataloop; // FALL THROUGH continue
// stateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the input character as a
* character token.
*
* Stay in the data state.
*/
continue;
}
}
breakDataloop:
goto case TAG_OPEN;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case TAG_OPEN:
/*tagopenloop:*/
for (; ; )
{
/*
* The behavior of this state depends on the content
* model flag.
*/
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* If the content model flag is set to the PCDATA state
* Consume the next input character:
*/
if (c >= 'A' && c <= 'Z')
{
/*
* U+0041 LATIN CAPITAL LETTER A through to U+005A
* LATIN CAPITAL LETTER Z Create a new start tag
* token,
*/
endTag = false;
/*
* set its tag name to the lowercase version of the
* input character (add 0x0020 to the character's
* code point),
*/
ClearStrBufAndAppend((char)(c + 0x20));
/* then switch to the tag name state. */
/*
* (Don't emit the token yet; further details will
* be filled in before it is emitted.)
*/
goto breakTagopenloop;
// goto continueStateloop;
}
else if (c >= 'a' && c <= 'z')
{
/*
* U+0061 LATIN SMALL LETTER A through to U+007A
* LATIN SMALL LETTER Z Create a new start tag
* token,
*/
endTag = false;
/*
* set its tag name to the input character,
*/
ClearStrBufAndAppend(c);
/* then switch to the tag name state. */
/*
* (Don't emit the token yet; further details will
* be filled in before it is emitted.)
*/
goto breakTagopenloop;
// goto continueStateloop;
}
switch (c)
{
case '!':
/*
* U+0021 EXCLAMATION MARK (!) Switch to the
* markup declaration open state.
*/
goto continueStateloop;
case '/':
/*
* U+002F SOLIDUS (/) Switch to the close tag
* open state.
*/
goto continueStateloop;
case '?':
/*
* U+003F QUESTION MARK () Parse error.
*/
ErrProcessingInstruction();
/*
* Switch to the bogus comment state.
*/
ClearLongStrBufAndAppend(c);
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Parse error.
*/
ErrLtGt();
/*
* Emit a U+003C LESS-THAN SIGN character token
* and a U+003E GREATER-THAN SIGN character
* token.
*/
TokenHandler.Characters(Tokenizer.LT_GT, 0, 2);
/* Switch to the data state. */
cstart = pos + 1;
goto continueStateloop;
default:
/*
* Anything else Parse error.
*/
ErrBadCharAfterLt(c);
/*
* Emit a U+003C LESS-THAN SIGN character token
*/
TokenHandler.Characters(Tokenizer.LT_GT, 0, 1);
/*
* and reconsume the current input character in
* the data state.
*/
cstart = pos;
reconsume = true;
goto continueStateloop;
}
}
breakTagopenloop:
goto case TAG_NAME;
// FALL THROUGH DON'T REORDER
case TAG_NAME:
/*tagnameloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
StrBufToElementNameString();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the before attribute name state.
*/
StrBufToElementNameString();
goto breakTagnameloop;
// goto continueStateloop;
case '/':
/*
* U+002F SOLIDUS (/) Switch to the self-closing
* start tag state.
*/
StrBufToElementNameString();
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* tag token.
*/
StrBufToElementNameString();
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
goto default;
// fall thru
default:
if (c >= 'A' && c <= 'Z')
{
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Append the
* lowercase version of the current input
* character (add 0x0020 to the character's
* code point) to the current tag token's
* tag name.
*/
c += (char)0x20;
}
/*
* Anything else Append the current input
* character to the current tag token's tag
* name.
*/
AppendStrBuf(c);
/*
* Stay in the tag name state.
*/
continue;
}
}
breakTagnameloop:
goto case BEFORE_ATTRIBUTE_NAME;
// FALLTHRU DON'T REORDER
case BEFORE_ATTRIBUTE_NAME:
/*beforeattributenameloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the before attribute name state.
*/
continue;
case '/':
/*
* U+002F SOLIDUS (/) Switch to the self-closing
* start tag state.
*/
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* tag token.
*/
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto case '\"';
case '\"':
case '\'':
case '<':
case '=':
/*
* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE
* (') U+003C LESS-THAN SIGN (<) U+003D EQUALS
* SIGN (=) Parse error.
*/
ErrBadCharBeforeAttributeNameOrNull(c);
/*
* Treat it as per the "anything else" entry
* below.
*/
goto default;
default:
/*
* Anything else Start a new attribute in the
* current tag token.
*/
if (c >= 'A' && c <= 'Z')
{
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Set that
* attribute's name to the lowercase version
* of the current input character (add
* 0x0020 to the character's code point)
*/
c += (char)0x20;
}
/*
* Set that attribute's name to the current
* input character,
*/
ClearStrBufAndAppend(c);
/*
* and its value to the empty string.
*/
// Will do later.
/*
* Switch to the attribute name state.
*/
goto breakBeforeattributenameloop;
// goto continueStateloop;
}
}
breakBeforeattributenameloop:
goto case ATTRIBUTE_NAME;
// FALLTHRU DON'T REORDER
case ATTRIBUTE_NAME:
/*attributenameloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
AttributeNameComplete();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
// fall thru
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the after attribute name state.
*/
AttributeNameComplete();
goto continueStateloop;
case '/':
/*
* U+002F SOLIDUS (/) Switch to the self-closing
* start tag state.
*/
AttributeNameComplete();
AddAttributeWithoutValue();
goto continueStateloop;
case '=':
/*
* U+003D EQUALS SIGN (=) Switch to the before
* attribute value state.
*/
AttributeNameComplete();
goto breakAttributenameloop;
// goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* tag token.
*/
AttributeNameComplete();
AddAttributeWithoutValue();
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto case '\"';
case '\"':
case '\'':
case '<':
/*
* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE
* (') U+003C LESS-THAN SIGN (<) Parse error.
*/
ErrQuoteOrLtInAttributeNameOrNull(c);
/*
* Treat it as per the "anything else" entry
* below.
*/
goto default;
default:
if (c >= 'A' && c <= 'Z')
{
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Append the
* lowercase version of the current input
* character (add 0x0020 to the character's
* code point) to the current attribute's
* name.
*/
c += (char)0x20;
}
/*
* Anything else Append the current input
* character to the current attribute's name.
*/
AppendStrBuf(c);
/*
* Stay in the attribute name state.
*/
continue;
}
}
breakAttributenameloop:
goto case BEFORE_ATTRIBUTE_VALUE;
// FALLTHRU DON'T REORDER
case BEFORE_ATTRIBUTE_VALUE:
/*beforeattributevalueloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
// fall thru
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the before attribute value state.
*/
continue;
case '"':
/*
* U+0022 QUOTATION MARK (") Switch to the
* attribute value (double-quoted) state.
*/
ClearLongStrBuf();
goto breakBeforeattributevalueloop;
// goto continueStateloop;
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the attribute
* value (unquoted) state and reconsume this
* input character.
*/
ClearLongStrBuf();
NoteUnquotedAttributeValue();
reconsume = true;
goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Switch to the attribute
* value (single-quoted) state.
*/
ClearLongStrBuf();
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Parse error.
*/
ErrAttributeValueMissing();
/*
* Emit the current tag token.
*/
AddAttributeWithoutValue();
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto case '<';
case '<':
case '=':
case '`':
/*
* U+003C LESS-THAN SIGN (<) U+003D EQUALS SIGN
* (=) U+0060 GRAVE ACCENT (`)
*/
ErrLtOrEqualsOrGraveInUnquotedAttributeOrNull(c);
/*
* Treat it as per the "anything else" entry
* below.
*/
goto default;
default:
/*
* Anything else Append the current input
* character to the current attribute's value.
*/
ClearLongStrBufAndAppend(c);
/*
* Switch to the attribute value (unquoted)
* state.
*/
NoteUnquotedAttributeValue();
goto continueStateloop;
}
}
breakBeforeattributevalueloop:
goto case ATTRIBUTE_VALUE_DOUBLE_QUOTED;
// FALLTHRU DON'T REORDER
case ATTRIBUTE_VALUE_DOUBLE_QUOTED:
/*attributevaluedoublequotedloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '"':
/*
* U+0022 QUOTATION MARK (") Switch to the after
* attribute value (quoted) state.
*/
AddAttributeWithValue();
goto breakAttributevaluedoublequotedloop;
// goto continueStateloop;
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the character
* reference in attribute value state, with the
* additional allowed character being U+0022
* QUOTATION MARK (").
*/
ClearStrBufAndAppend(c);
SetAdditionalAndRememberAmpersandLocation('\"');
returnState = state;
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the current input
* character to the current attribute's value.
*/
AppendLongStrBuf(c);
/*
* Stay in the attribute value (double-quoted)
* state.
*/
continue;
}
}
breakAttributevaluedoublequotedloop:
goto case AFTER_ATTRIBUTE_VALUE_QUOTED;
// FALLTHRU DON'T REORDER
case AFTER_ATTRIBUTE_VALUE_QUOTED:
/*afterattributevaluequotedloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the before attribute name state.
*/
goto continueStateloop;
case '/':
/*
* U+002F SOLIDUS (/) Switch to the self-closing
* start tag state.
*/
goto breakAfterattributevaluequotedloop;
// goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* tag token.
*/
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
/*
* Anything else Parse error.
*/
ErrNoSpaceBetweenAttributes();
/*
* Reconsume the character in the before
* attribute name state.
*/
reconsume = true;
goto continueStateloop;
}
}
breakAfterattributevaluequotedloop:
goto case SELF_CLOSING_START_TAG;
// FALLTHRU DON'T REORDER
case SELF_CLOSING_START_TAG:
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Set the self-closing
* flag of the current tag token. Emit the current
* tag token.
*/
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
/* Anything else Parse error. */
ErrSlashNotFollowedByGt();
/*
* Reconsume the character in the before attribute
* name state.
*/
reconsume = true;
goto continueStateloop;
}
// XXX reorder point
case ATTRIBUTE_VALUE_UNQUOTED:
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
AddAttributeWithValue();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the before attribute name state.
*/
AddAttributeWithValue();
goto continueStateloop;
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the character
* reference in attribute value state, with the
* additional allowed character being U+003E
* GREATER-THAN SIGN (>)
*/
ClearStrBufAndAppend(c);
SetAdditionalAndRememberAmpersandLocation('>');
returnState = state;
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* tag token.
*/
AddAttributeWithValue();
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
goto case '<';
// fall thru
case '<':
case '\"':
case '\'':
case '=':
case '`':
/*
* U+0022 QUOTATION MARK (") U+0027 APOSTROPHE
* (') U+003C LESS-THAN SIGN (<) U+003D EQUALS
* SIGN (=) U+0060 GRAVE ACCENT (`) Parse error.
*/
ErrUnquotedAttributeValOrNull(c);
/*
* Treat it as per the "anything else" entry
* below.
*/
// fall through
goto default;
default:
// [NOCPP]
ErrHtml4NonNameInUnquotedAttribute(c);
// ]NOCPP]
/*
* Anything else Append the current input
* character to the current attribute's value.
*/
AppendLongStrBuf(c);
/*
* Stay in the attribute value (unquoted) state.
*/
continue;
}
}
// XXX reorder point
case AFTER_ATTRIBUTE_NAME:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the after attribute name state.
*/
continue;
case '/':
/*
* U+002F SOLIDUS (/) Switch to the self-closing
* start tag state.
*/
AddAttributeWithoutValue();
goto continueStateloop;
case '=':
/*
* U+003D EQUALS SIGN (=) Switch to the before
* attribute value state.
*/
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* tag token.
*/
AddAttributeWithoutValue();
if (shouldSuspend)
{
goto breakStateloop;
}
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
goto case '\"';
// fall thru
case '\"':
case '\'':
case '<':
ErrQuoteOrLtInAttributeNameOrNull(c);
/*
* Treat it as per the "anything else" entry
* below.
*/
goto default;
default:
AddAttributeWithoutValue();
/*
* Anything else Start a new attribute in the
* current tag token.
*/
if (c >= 'A' && c <= 'Z')
{
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Set that
* attribute's name to the lowercase version
* of the current input character (add
* 0x0020 to the character's code point)
*/
c += (char)0x20;
}
/*
* Set that attribute's name to the current
* input character,
*/
ClearStrBufAndAppend(c);
/*
* and its value to the empty string.
*/
// Will do later.
/*
* Switch to the attribute name state.
*/
goto continueStateloop;
}
}
// XXX reorder point
case MARKUP_DECLARATION_OPEN:
/*markupdeclarationopenloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* If the next two characters are both U+002D
* HYPHEN-MINUS characters (-), consume those two
* characters, create a comment token whose data is the
* empty string, and switch to the comment start state.
*
* Otherwise, if the next seven characters are an ASCII
* case-insensitive match for the word "DOCTYPE", then
* consume those characters and switch to the DOCTYPE
* state.
*
* Otherwise, if the insertion mode is
* "in foreign content" and the current node is not an
* element in the HTML namespace and the next seven
* characters are an case-sensitive match for the string
* "[CDATA[" (the five uppercase letters "CDATA" with a
* U+005B LEFT SQUARE BRACKET character before and
* after), then consume those characters and switch to
* the CDATA section state.
*
* Otherwise, is is a parse error. Switch to the bogus
* comment state. The next character that is consumed,
* if any, is the first character that will be in the
* comment.
*/
switch (c)
{
case '-':
ClearLongStrBufAndAppend(c);
goto breakMarkupdeclarationopenloop;
// goto continueStateloop;
case 'd':
case 'D':
ClearLongStrBufAndAppend(c);
index = 0;
goto continueStateloop;
case '[':
if (TokenHandler.IsCDataSectionAllowed)
{
ClearLongStrBufAndAppend(c);
index = 0;
goto continueStateloop;
}
else
{
// else fall through
goto default;
}
default:
ErrBogusComment();
ClearLongStrBuf();
reconsume = true;
goto continueStateloop;
}
}
breakMarkupdeclarationopenloop:
goto case MARKUP_DECLARATION_HYPHEN;
// FALLTHRU DON'T REORDER
case MARKUP_DECLARATION_HYPHEN:
/*markupdeclarationhyphenloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
switch (c)
{
case '\u0000':
goto breakStateloop;
case '-':
ClearLongStrBuf();
goto breakMarkupdeclarationhyphenloop;
// goto continueStateloop;
default:
ErrBogusComment();
reconsume = true;
goto continueStateloop;
}
}
breakMarkupdeclarationhyphenloop:
goto case COMMENT_START;
// FALLTHRU DON'T REORDER
case COMMENT_START:
/*commentstartloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Comment start state
*
*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Switch to the comment
* start dash state.
*/
AppendLongStrBuf(c);
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Parse error.
*/
ErrPrematureEndOfComment();
/* Emit the comment token. */
EmitComment(0, pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
goto breakCommentstartloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the input character to
* the comment token's data.
*/
AppendLongStrBuf(c);
/*
* Switch to the comment state.
*/
goto breakCommentstartloop;
// goto continueStateloop;
}
}
breakCommentstartloop:
goto case COMMENT;
// FALLTHRU DON'T REORDER
case COMMENT:
/*commentloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Comment state Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Switch to the comment
* end dash state
*/
AppendLongStrBuf(c);
goto breakCommentloop;
// goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the input character to
* the comment token's data.
*/
AppendLongStrBuf(c);
/*
* Stay in the comment state.
*/
continue;
}
}
breakCommentloop:
goto case COMMENT_END_DASH;
// FALLTHRU DON'T REORDER
case COMMENT_END_DASH:
/*commentenddashloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Comment end dash state Consume the next input
* character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Switch to the comment
* end state
*/
AppendLongStrBuf(c);
goto breakCommentenddashloop;
// goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
goto default;
// fall thru
default:
/*
* Anything else Append a U+002D HYPHEN-MINUS
* (-) character and the input character to the
* comment token's data.
*/
AppendLongStrBuf(c);
/*
* Switch to the comment state.
*/
goto continueStateloop;
}
}
breakCommentenddashloop:
goto case COMMENT_END;
// FALLTHRU DON'T REORDER
case COMMENT_END:
/*commentendloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Comment end dash state Consume the next input
* character:
*/
switch (c)
{
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the comment
* token.
*/
EmitComment(2, pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '-':
/* U+002D HYPHEN-MINUS (-) Parse error. */
/*
* Append a U+002D HYPHEN-MINUS (-) character to
* the comment token's data.
*/
AdjustDoubleHyphenAndAppendToLongStrBufAndErr(c);
/*
* Stay in the comment end state.
*/
continue;
case '\r':
AdjustDoubleHyphenAndAppendToLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AdjustDoubleHyphenAndAppendToLongStrBufLineFeed();
goto continueStateloop;
case '!':
ErrHyphenHyphenBang();
AppendLongStrBuf(c);
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Append two U+002D HYPHEN-MINUS (-) characters
* and the input character to the comment
* token's data.
*/
AdjustDoubleHyphenAndAppendToLongStrBufAndErr(c);
/*
* Switch to the comment state.
*/
goto continueStateloop;
}
}
// XXX reorder point
case COMMENT_END_BANG:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Comment end bang state
*
* Consume the next input character:
*/
switch (c)
{
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the comment
* token.
*/
EmitComment(3, pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '-':
/*
* Append two U+002D HYPHEN-MINUS (-) characters
* and a U+0021 EXCLAMATION MARK (!) character
* to the comment token's data.
*/
AppendLongStrBuf(c);
/*
* Switch to the comment end dash state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append two U+002D HYPHEN-MINUS
* (-) characters, a U+0021 EXCLAMATION MARK (!)
* character, and the input character to the
* comment token's data. Switch to the comment
* state.
*/
AppendLongStrBuf(c);
/*
* Switch to the comment state.
*/
goto continueStateloop;
}
}
// XXX reorder point
case COMMENT_START_DASH:
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Comment start dash state
*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Switch to the comment end
* state
*/
AppendLongStrBuf(c);
goto continueStateloop;
case '>':
ErrPrematureEndOfComment();
/* Emit the comment token. */
EmitComment(1, pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Append a U+002D HYPHEN-MINUS character (-) and
* the current input character to the comment
* token's data.
*/
AppendLongStrBuf(c);
/*
* Switch to the comment state.
*/
goto continueStateloop;
}
// XXX reorder point
case CDATA_START:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
if (index < 6)
{ // CDATA_LSQB.Length
if (c == Tokenizer.CDATA_LSQB[index])
{
AppendLongStrBuf(c);
}
else
{
ErrBogusComment();
reconsume = true;
goto continueStateloop;
}
index++;
continue;
}
else
{
cstart = pos; // start coalescing
reconsume = true;
break; // FALL THROUGH goto continueStateloop;
}
}
goto case CDATA_SECTION;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case CDATA_SECTION:
/*cdatasectionloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
switch (c)
{
case ']':
FlushChars(buf, pos);
goto breakCdatasectionloop; // FALL THROUGH
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
// fall thru
default:
continue;
}
}
breakCdatasectionloop:
goto case CDATA_RSQB;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case CDATA_RSQB:
/*cdatarsqb:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
switch (c)
{
case ']':
goto breakCdatarsqb;
default:
TokenHandler.Characters(Tokenizer.RSQB_RSQB, 0,
1);
cstart = pos;
reconsume = true;
goto continueStateloop;
}
}
breakCdatarsqb:
goto case CDATA_RSQB_RSQB;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case CDATA_RSQB_RSQB:
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
switch (c)
{
case '>':
cstart = pos + 1;
goto continueStateloop;
default:
TokenHandler.Characters(Tokenizer.RSQB_RSQB, 0, 2);
cstart = pos;
reconsume = true;
goto continueStateloop;
}
// XXX reorder point
case ATTRIBUTE_VALUE_SINGLE_QUOTED:
/*attributevaluesinglequotedloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '\'':
/*
* U+0027 APOSTROPHE (') Switch to the after
* attribute value (quoted) state.
*/
AddAttributeWithValue();
goto continueStateloop;
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the character
* reference in attribute value state, with the
* + additional allowed character being U+0027
* APOSTROPHE (').
*/
ClearStrBufAndAppend(c);
SetAdditionalAndRememberAmpersandLocation('\'');
returnState = state;
goto breakAttributevaluesinglequotedloop;
// goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
goto default;
// fall thru
default:
/*
* Anything else Append the current input
* character to the current attribute's value.
*/
AppendLongStrBuf(c);
/*
* Stay in the attribute value (double-quoted)
* state.
*/
continue;
}
}
breakAttributevaluesinglequotedloop:
goto case CONSUME_CHARACTER_REFERENCE;
// FALLTHRU DON'T REORDER
case CONSUME_CHARACTER_REFERENCE:
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
if (c == '\u0000')
{
goto breakStateloop;
}
/*
* Unlike the definition is the spec, this state does not
* return a value and never requires the caller to
* backtrack. This state takes care of emitting characters
* or appending to the current attribute value. It also
* takes care of that in the case when consuming the
* character reference fails.
*/
/*
* This section defines how to consume a character
* reference. This definition is used when parsing character
* references in text and in attributes.
*
* The behavior depends on the identity of the next
* character (the one immediately after the U+0026 AMPERSAND
* character):
*/
switch (c)
{
case ' ':
case '\t':
case '\n':
case '\r': // we'll reconsume!
case '\u000C':
case '<':
case '&':
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
case '#':
/*
* U+0023 NUMBER SIGN (#) Consume the U+0023 NUMBER
* SIGN.
*/
AppendStrBuf('#');
goto continueStateloop;
default:
if (c == additional)
{
EmitOrAppendStrBuf(returnState);
reconsume = true;
goto continueStateloop;
}
if (c >= 'a' && c <= 'z')
{
firstCharKey = c - 'a' + 26;
}
else if (c >= 'A' && c <= 'Z')
{
firstCharKey = c - 'A';
}
else
{
// No match
/*
* If no match can be made, then this is a parse
* error.
*/
ErrNoNamedCharacterMatch();
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
}
// Didn't fail yet
AppendStrBuf(c);
// FALL THROUGH goto continueStateloop;
break;
}
goto case CHARACTER_REFERENCE_HILO_LOOKUP;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case CHARACTER_REFERENCE_HILO_LOOKUP:
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
if (c == '\u0000')
{
goto breakStateloop;
}
/*
* The data structure is as follows:
*
* HILO_ACCEL is a two-dimensional int array whose major
* index corresponds to the second character of the
* character reference (code point as index) and the
* minor index corresponds to the first character of the
* character reference (packed so that A-Z runs from 0
* to 25 and a-z runs from 26 to 51). This layout makes
* it easier to use the sparseness of the data structure
* to omit parts of it: The second dimension of the
* table is null when no character reference starts with
* the character corresponding to that row.
*
* The int value HILO_ACCEL (by these indeces) is zero
* if there exists no character reference starting with
* that two-letter prefix. Otherwise, the value is an
* int that packs two shorts so that the higher short is
* the index of the highest character reference name
* with that prefix in NAMES and the lower short
* corresponds to the index of the lowest character
* reference name with that prefix. (It happens that the
* first two character reference names share their
* prefix so the packed int cannot be 0 by packing the
* two shorts.)
*
* NAMES is an array of byte arrays where each byte
* array encodes the name of a character references as
* ASCII. The names omit the first two letters of the
* name. (Since storing the first two letters would be
* redundant with the data contained in HILO_ACCEL.) The
* entries are lexically sorted.
*
* For a given index in NAMES, the same index in VALUES
* contains the corresponding expansion as an array of
* two UTF-16 code units (either the character and
* U+0000 or a suggogate pair).
*/
int hilo = 0;
if (c <= 'z')
{
int[] row = NamedCharactersAccel.HILO_ACCEL[c];
if (row != null)
{
hilo = row[firstCharKey];
}
}
if (hilo == 0)
{
/*
* If no match can be made, then this is a parse
* error.
*/
ErrNoNamedCharacterMatch();
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
}
// Didn't fail yet
AppendStrBuf(c);
lo = hilo & 0xFFFF;
hi = hilo >> 16;
entCol = -1;
candidate = -1;
strBufMark = 0;
// FALL THROUGH goto continueStateloop;
goto case CHARACTER_REFERENCE_TAIL;
}
case CHARACTER_REFERENCE_TAIL:
/*outer:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
if (c == '\u0000')
{
goto breakStateloop;
}
entCol++;
/*
* Consume the maximum number of characters possible,
* with the consumed characters matching one of the
* identifiers in the first column of the named
* character references table (in a case-sensitive
* manner).
*/
/*loloop:*/
for (; ; )
{
if (hi < lo)
{
goto breakOuter;
}
if (entCol == NamedCharacters.NAMES[lo].Length)
{
candidate = lo;
strBufMark = strBufLen;
lo++;
}
else if (entCol > NamedCharacters.NAMES[lo].Length)
{
goto breakOuter;
}
else if (c > NamedCharacters.NAMES[lo][entCol])
{
lo++;
}
else
{
goto breakLoloop;
}
}
breakLoloop:
/*hiloop:*/
for (; ; )
{
if (hi < lo)
{
goto breakOuter;
}
if (entCol == NamedCharacters.NAMES[hi].Length)
{
goto breakHiloop;
}
if (entCol > NamedCharacters.NAMES[hi].Length)
{
goto breakOuter;
}
else if (c < NamedCharacters.NAMES[hi][entCol])
{
hi--;
}
else
{
goto breakHiloop;
}
}
breakHiloop:
if (hi < lo)
{
goto breakOuter;
}
AppendStrBuf(c);
continue;
}
breakOuter:
if (candidate == -1)
{
// reconsume deals with CR, LF or nul
/*
* If no match can be made, then this is a parse error.
*/
ErrNoNamedCharacterMatch();
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
}
else
{
// c can't be CR, LF or nul if we got here
string candidateName = NamedCharacters.NAMES[candidate];
if (candidateName.Length == 0
|| candidateName[candidateName.Length - 1] != ';')
{
/*
* If the last character matched is not a U+003B
* SEMICOLON (;), there is a parse error.
*/
if ((returnState & DATA_AND_RCDATA_MASK) != 0)
{
/*
* If the entity is being consumed as part of an
* attribute, and the last character matched is
* not a U+003B SEMICOLON (;),
*/
char ch;
if (strBufMark == strBufLen)
{
ch = c;
}
else
{
// if (strBufOffset != -1) {
// ch = buf[strBufOffset + strBufMark];
// } else {
ch = strBuf[strBufMark];
// }
}
if (ch == '=' || (ch >= '0' && ch <= '9')
|| (ch >= 'A' && ch <= 'Z')
|| (ch >= 'a' && ch <= 'z'))
{
/*
* and the next character is either a U+003D
* EQUALS SIGN character (=) or in the range
* U+0030 DIGIT ZERO to U+0039 DIGIT NINE,
* U+0041 LATIN CAPITAL LETTER A to U+005A
* LATIN CAPITAL LETTER Z, or U+0061 LATIN
* SMALL LETTER A to U+007A LATIN SMALL
* LETTER Z, then, for historical reasons,
* all the characters that were matched
* after the U+0026 AMPERSAND (&) must be
* unconsumed, and nothing is returned.
*/
ErrNoNamedCharacterMatch();
AppendStrBufToLongStrBuf();
reconsume = true;
goto continueStateloop;
}
}
if ((returnState & DATA_AND_RCDATA_MASK) != 0)
{
ErrUnescapedAmpersandInterpretedAsCharacterReference();
}
else
{
ErrNotSemicolonTerminated();
}
}
/*
* Otherwise, return a character token for the character
* corresponding to the entity name (as given by the
* second column of the named character references
* table).
*/
char[] val = NamedCharacters.VALUES[candidate];
if (val[1] == 0)
{
EmitOrAppendOne(val, returnState);
}
else
{
EmitOrAppendTwo(val, returnState);
}
// this is so complicated!
if (strBufMark < strBufLen)
{
if ((returnState & DATA_AND_RCDATA_MASK) != 0)
{
for (int i = strBufMark; i < strBufLen; i++)
{
AppendLongStrBuf(strBuf[i]);
}
}
else
{
TokenHandler.Characters(strBuf, strBufMark,
strBufLen - strBufMark);
}
// }
}
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
/*
* If the markup contains I'm ¬it; I tell you, the
* entity is parsed as "not", as in, I'm ¬it; I tell
* you. But if the markup was I'm ∉ I tell you,
* the entity would be parsed as "notin;", resulting in
* I'm ∉ I tell you.
*/
}
// XXX reorder point
case CONSUME_NCR:
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
prevValue = -1;
value = 0;
seenDigits = false;
/*
* The behavior further depends on the character after the
* U+0023 NUMBER SIGN:
*/
switch (c)
{
case 'x':
case 'X':
/*
* U+0078 LATIN SMALL LETTER X U+0058 LATIN CAPITAL
* LETTER X Consume the X.
*
* Follow the steps below, but using the range of
* characters U+0030 DIGIT ZERO through to U+0039
* DIGIT NINE, U+0061 LATIN SMALL LETTER A through
* to U+0066 LATIN SMALL LETTER F, and U+0041 LATIN
* CAPITAL LETTER A, through to U+0046 LATIN CAPITAL
* LETTER F (in other words, 0-9, A-F, a-f).
*
* When it comes to interpreting the number,
* interpret it as a hexadecimal number.
*/
AppendStrBuf(c);
goto continueStateloop;
default:
/*
* Anything else Follow the steps below, but using
* the range of characters U+0030 DIGIT ZERO through
* to U+0039 DIGIT NINE (i.e. just 0-9).
*
* When it comes to interpreting the number,
* interpret it as a decimal number.
*/
reconsume = true;
// FALL THROUGH goto continueStateloop;
break;
}
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
goto case DECIMAL_NRC_LOOP;
case DECIMAL_NRC_LOOP:
/*decimalloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
// Deal with overflow gracefully
if (value < prevValue)
{
value = 0x110000; // Value above Unicode range but
// within int
// range
}
prevValue = value;
/*
* Consume as many characters as match the range of
* characters given above.
*/
if (c >= '0' && c <= '9')
{
seenDigits = true;
value *= 10;
value += c - '0';
continue;
}
else if (c == ';')
{
if (seenDigits)
{
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos + 1;
}
// FALL THROUGH goto continueStateloop;
goto breakDecimalloop;
}
else
{
ErrNoDigitsInNCR();
AppendStrBuf(';');
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos + 1;
}
goto continueStateloop;
}
}
else
{
/*
* If no characters match the range, then don't
* consume any characters (and unconsume the U+0023
* NUMBER SIGN character and, if appropriate, the X
* character). This is a parse error; nothing is
* returned.
*
* Otherwise, if the next character is a U+003B
* SEMICOLON, consume that too. If it isn't, there
* is a parse error.
*/
if (!seenDigits)
{
ErrNoDigitsInNCR();
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
}
else
{
ErrCharRefLacksSemicolon();
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
// FALL THROUGH goto continueStateloop;
goto breakDecimalloop;
}
}
}
breakDecimalloop:
goto case HANDLE_NCR_VALUE;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case HANDLE_NCR_VALUE:
// WARNING previous state sets reconsume
// XXX inline this case if the method size can take it
HandleNcrValue(returnState);
goto continueStateloop;
// XXX reorder point
case HEX_NCR_LOOP:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
// Deal with overflow gracefully
if (value < prevValue)
{
value = 0x110000; // Value above Unicode range but
// within int
// range
}
prevValue = value;
/*
* Consume as many characters as match the range of
* characters given above.
*/
if (c >= '0' && c <= '9')
{
seenDigits = true;
value *= 16;
value += c - '0';
continue;
}
else if (c >= 'A' && c <= 'F')
{
seenDigits = true;
value *= 16;
value += c - 'A' + 10;
continue;
}
else if (c >= 'a' && c <= 'f')
{
seenDigits = true;
value *= 16;
value += c - 'a' + 10;
continue;
}
else if (c == ';')
{
if (seenDigits)
{
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos + 1;
}
goto continueStateloop;
}
else
{
ErrNoDigitsInNCR();
AppendStrBuf(';');
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos + 1;
}
goto continueStateloop;
}
}
else
{
/*
* If no characters match the range, then don't
* consume any characters (and unconsume the U+0023
* NUMBER SIGN character and, if appropriate, the X
* character). This is a parse error; nothing is
* returned.
*
* Otherwise, if the next character is a U+003B
* SEMICOLON, consume that too. If it isn't, there
* is a parse error.
*/
if (!seenDigits)
{
ErrNoDigitsInNCR();
EmitOrAppendStrBuf(returnState);
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
}
else
{
ErrCharRefLacksSemicolon();
if ((returnState & DATA_AND_RCDATA_MASK) == 0)
{
cstart = pos;
}
reconsume = true;
goto continueStateloop;
}
}
}
// XXX reorder point
case PLAINTEXT:
/*plaintextloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
switch (c)
{
case '\u0000':
EmitPlaintextReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Stay in the
* RAWTEXT state.
*/
continue;
}
}
// XXX reorder point
case CLOSE_TAG_OPEN:
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Otherwise, if the content model flag is set to the PCDATA
* state, or if the next few characters do match that tag
* name, consume the next input character:
*/
switch (c)
{
case '>':
/* U+003E GREATER-THAN SIGN (>) Parse error. */
ErrLtSlashGt();
/*
* Switch to the data state.
*/
cstart = pos + 1;
goto continueStateloop;
case '\r':
SilentCarriageReturn();
/* Anything else Parse error. */
ErrGarbageAfterLtSlash();
/*
* Switch to the bogus comment state.
*/
ClearLongStrBufAndAppend('\n');
goto breakStateloop;
case '\n':
SilentLineFeed();
/* Anything else Parse error. */
ErrGarbageAfterLtSlash();
/*
* Switch to the bogus comment state.
*/
ClearLongStrBufAndAppend('\n');
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
if (c >= 'A' && c <= 'Z')
{
c += (char)0x20;
}
if (c >= 'a' && c <= 'z')
{
/*
* U+0061 LATIN SMALL LETTER A through to U+007A
* LATIN SMALL LETTER Z Create a new end tag
* token,
*/
endTag = true;
/*
* set its tag name to the input character,
*/
ClearStrBufAndAppend(c);
/*
* then switch to the tag name state. (Don't
* emit the token yet; further details will be
* filled in before it is emitted.)
*/
goto continueStateloop;
}
else
{
/* Anything else Parse error. */
ErrGarbageAfterLtSlash();
/*
* Switch to the bogus comment state.
*/
ClearLongStrBufAndAppend(c);
goto continueStateloop;
}
}
// XXX reorder point
case RCDATA:
/*rcdataloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
switch (c)
{
case '&':
/*
* U+0026 AMPERSAND (&) Switch to the character
* reference in RCDATA state.
*/
FlushChars(buf, pos);
ClearStrBufAndAppend(c);
additional = '\u0000';
returnState = state;
goto continueStateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the
* RCDATA less-than sign state.
*/
FlushChars(buf, pos);
returnState = state;
goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Emit the current input character as a
* character token. Stay in the RCDATA state.
*/
continue;
}
}
// XXX reorder point
case RAWTEXT:
/*rawtextloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
switch (c)
{
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the
* RAWTEXT less-than sign state.
*/
FlushChars(buf, pos);
returnState = state;
goto breakRawtextloop;
// FALL THRU goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Emit the current input character as a
* character token. Stay in the RAWTEXT state.
*/
continue;
}
}
breakRawtextloop:
goto case RAWTEXT_RCDATA_LESS_THAN_SIGN;
// XXX fallthru don't reorder
case RAWTEXT_RCDATA_LESS_THAN_SIGN:
/*rawtextrcdatalessthansignloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
switch (c)
{
case '/':
/*
* U+002F SOLIDUS (/) Set the temporary buffer
* to the empty string. Switch to the script
* data end tag open state.
*/
index = 0;
ClearStrBuf();
goto breakRawtextrcdatalessthansignloop;
// FALL THRU goto continueStateloop;
default:
/*
* Otherwise, emit a U+003C LESS-THAN SIGN
* character token
*/
TokenHandler.Characters(Tokenizer.LT_GT, 0, 1);
/*
* and reconsume the current input character in
* the data state.
*/
cstart = pos;
reconsume = true;
goto continueStateloop;
}
}
breakRawtextrcdatalessthansignloop:
goto case NON_DATA_END_TAG_NAME;
// XXX fall thru. don't reorder.
case NON_DATA_END_TAG_NAME:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* ASSERT! when entering this state, set index to 0 and
* call clearStrBuf() assert (contentModelElement !=
* null); Let's implement the above without lookahead.
* strBuf is the 'temporary buffer'.
*/
if (index < endTagExpectationAsArray.Length)
{
char e = endTagExpectationAsArray[index];
char folded = c;
if (c >= 'A' && c <= 'Z')
{
folded += (char)0x20;
}
if (folded != e)
{
TokenHandler.Characters(Tokenizer.LT_SOLIDUS,
0, 2);
EmitStrBuf();
cstart = pos;
reconsume = true;
goto continueStateloop;
}
AppendStrBuf(c);
index++;
continue;
}
else
{
endTag = true;
// XXX replace contentModelElement with different
// type
tagName = endTagExpectation;
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
// fall thru
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE
* FEED (LF) U+000C FORM FEED (FF) U+0020
* SPACE If the current end tag token is an
* appropriate end tag token, then switch to
* the before attribute name state.
*/
goto continueStateloop;
case '/':
/*
* U+002F SOLIDUS (/) If the current end tag
* token is an appropriate end tag token,
* then switch to the self-closing start tag
* state.
*/
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) If the
* current end tag token is an appropriate
* end tag token, then emit the current tag
* token and switch to the data state.
*/
if (shouldSuspend)
{
goto breakStateloop;
}
goto continueStateloop;
default:
/*
* Emit a U+003C LESS-THAN SIGN character
* token, a U+002F SOLIDUS character token,
* a character token for each of the
* characters in the temporary buffer (in
* the order they were added to the buffer),
* and reconsume the current input character
* in the RAWTEXT state.
*/
TokenHandler.Characters(
Tokenizer.LT_SOLIDUS, 0, 2);
EmitStrBuf();
if (c == '\u0000')
{
EmitReplacementCharacter(buf, pos);
}
else
{
cstart = pos; // don't drop the
// character
}
goto continueStateloop;
}
}
}
// XXX reorder point
// BEGIN HOTSPOT WORKAROUND
case BOGUS_COMMENT:
/*boguscommentloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume every character up to and including the first
* U+003E GREATER-THAN SIGN character (>) or the end of
* the file (EOF), whichever comes first. Emit a comment
* token whose data is the concatenation of all the
* characters starting from and including the character
* that caused the state machine to switch into the
* bogus comment state, up to and including the
* character immediately before the last consumed
* character (i.e. up to the character just before the
* U+003E or EOF character). (If the comment was started
* by the end of the file (EOF), the token is empty.)
*
* Switch to the data state.
*
* If the end of the file was reached, reconsume the EOF
* character.
*/
switch (c)
{
case '>':
EmitComment(0, pos);
goto continueStateloop;
case '-':
AppendLongStrBuf(c);
goto breakBoguscommentloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
AppendLongStrBuf(c);
continue;
}
}
breakBoguscommentloop:
goto case BOGUS_COMMENT_HYPHEN;
// FALLTHRU DON'T REORDER
case BOGUS_COMMENT_HYPHEN:
/*boguscommenthyphenloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
switch (c)
{
case '>':
EmitComment(0, pos);
goto continueStateloop;
case '-':
AppendSecondHyphenToBogusComment();
goto continueBoguscommenthyphenloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
AppendLongStrBuf(c);
goto continueStateloop;
}
continueBoguscommenthyphenloop:
continue;
}
// XXX reorder point
case SCRIPT_DATA:
/*scriptdataloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
switch (c)
{
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the
* script data less-than sign state.
*/
FlushChars(buf, pos);
returnState = state;
goto breakScriptdataloop; // FALL THRU continue
// stateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Stay in the
* script data state.
*/
continue;
}
}
breakScriptdataloop:
goto case SCRIPT_DATA_LESS_THAN_SIGN;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_LESS_THAN_SIGN:
/*scriptdatalessthansignloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
switch (c)
{
case '/':
/*
* U+002F SOLIDUS (/) Set the temporary buffer
* to the empty string. Switch to the script
* data end tag open state.
*/
index = 0;
ClearStrBuf();
goto continueStateloop;
case '!':
TokenHandler.Characters(Tokenizer.LT_GT, 0, 1);
cstart = pos;
goto breakScriptdatalessthansignloop; // FALL THRU
// continue
// stateloop;
default:
/*
* Otherwise, emit a U+003C LESS-THAN SIGN
* character token
*/
TokenHandler.Characters(Tokenizer.LT_GT, 0, 1);
/*
* and reconsume the current input character in
* the data state.
*/
cstart = pos;
reconsume = true;
goto continueStateloop;
}
}
breakScriptdatalessthansignloop:
goto case SCRIPT_DATA_ESCAPE_START;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_ESCAPE_START:
/*scriptdataescapestartloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Switch to the
* script data escape start dash state.
*/
goto breakScriptdataescapestartloop; // FALL THRU
// continue
// stateloop;
default:
/*
* Anything else Reconsume the current input
* character in the script data state.
*/
reconsume = true;
goto continueStateloop;
}
}
breakScriptdataescapestartloop:
goto case SCRIPT_DATA_ESCAPE_START_DASH;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_ESCAPE_START_DASH:
/*scriptdataescapestartdashloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Switch to the
* script data escaped dash dash state.
*/
goto breakScriptdataescapestartdashloop;
// goto continueStateloop;
default:
/*
* Anything else Reconsume the current input
* character in the script data state.
*/
reconsume = true;
goto continueStateloop;
}
}
breakScriptdataescapestartdashloop:
goto case SCRIPT_DATA_ESCAPED_DASH_DASH;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_ESCAPED_DASH_DASH:
/*scriptdataescapeddashdashloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Stay in the
* script data escaped dash dash state.
*/
continue;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the
* script data escaped less-than sign state.
*/
FlushChars(buf, pos);
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit a U+003E
* GREATER-THAN SIGN character token. Switch to
* the script data state.
*/
goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
goto breakScriptdataescapeddashdashloop;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Switch to the
* script data escaped state.
*/
goto breakScriptdataescapeddashdashloop;
// goto continueStateloop;
}
}
breakScriptdataescapeddashdashloop:
goto case SCRIPT_DATA_ESCAPED;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_ESCAPED:
/*scriptdataescapedloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Switch to the
* script data escaped dash state.
*/
goto breakScriptdataescapedloop; // FALL THRU
// continue
// stateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the
* script data escaped less-than sign state.
*/
FlushChars(buf, pos);
goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Stay in the
* script data escaped state.
*/
continue;
}
}
breakScriptdataescapedloop:
goto case SCRIPT_DATA_ESCAPED_DASH;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_ESCAPED_DASH:
/*scriptdataescapeddashloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Switch to the
* script data escaped dash dash state.
*/
goto continueStateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Switch to the
* script data escaped less-than sign state.
*/
FlushChars(buf, pos);
goto breakScriptdataescapeddashloop;
// goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
goto continueStateloop;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Switch to the
* script data escaped state.
*/
goto continueStateloop;
}
}
breakScriptdataescapeddashloop:
goto case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN:
/*scriptdataescapedlessthanloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '/':
/*
* U+002F SOLIDUS (/) Set the temporary buffer
* to the empty string. Switch to the script
* data escaped end tag open state.
*/
index = 0;
ClearStrBuf();
returnState = Tokenizer.SCRIPT_DATA_ESCAPED;
goto continueStateloop;
case 'S':
case 's':
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Emit a U+003C
* LESS-THAN SIGN character token and the
* current input character as a character token.
*/
TokenHandler.Characters(Tokenizer.LT_GT, 0, 1);
cstart = pos;
index = 1;
/*
* Set the temporary buffer to the empty string.
* Append the lowercase version of the current
* input character (add 0x0020 to the
* character's code point) to the temporary
* buffer. Switch to the script data double
* escape start state.
*/
goto breakScriptdataescapedlessthanloop;
// goto continueStateloop;
default:
/*
* Anything else Emit a U+003C LESS-THAN SIGN
* character token and reconsume the current
* input character in the script data escaped
* state.
*/
TokenHandler.Characters(Tokenizer.LT_GT, 0, 1);
cstart = pos;
reconsume = true;
goto continueStateloop;
}
}
breakScriptdataescapedlessthanloop:
goto case SCRIPT_DATA_DOUBLE_ESCAPE_START;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_DOUBLE_ESCAPE_START:
/*scriptdatadoubleescapestartloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
Debug.Assert(index > 0);
if (index < 6)
{ // SCRIPT_ARR.Length
char folded = c;
if (c >= 'A' && c <= 'Z')
{
folded += (char)0x20;
}
if (folded != Tokenizer.SCRIPT_ARR[index])
{
reconsume = true;
goto continueStateloop;
}
index++;
continue;
}
switch (c)
{
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
case ' ':
case '\t':
case '\u000C':
case '/':
case '>':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* U+002F SOLIDUS (/) U+003E GREATER-THAN SIGN
* (>) Emit the current input character as a
* character token. If the temporary buffer is
* the string "script", then switch to the
* script data double escaped state.
*/
goto breakScriptdatadoubleescapestartloop;
// goto continueStateloop;
default:
/*
* Anything else Reconsume the current input
* character in the script data escaped state.
*/
reconsume = true;
goto continueStateloop;
}
}
breakScriptdatadoubleescapestartloop:
goto case SCRIPT_DATA_DOUBLE_ESCAPED;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_DOUBLE_ESCAPED:
/*scriptdatadoubleescapedloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Switch to the
* script data double escaped dash state.
*/
goto breakScriptdatadoubleescapedloop; // FALL THRU
// continue
// stateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Emit a U+003C
* LESS-THAN SIGN character token. Switch to the
* script data double escaped less-than sign
* state.
*/
goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
continue;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Stay in the
* script data double escaped state.
*/
continue;
}
}
breakScriptdatadoubleescapedloop:
goto case SCRIPT_DATA_DOUBLE_ESCAPED_DASH;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_DOUBLE_ESCAPED_DASH:
/*scriptdatadoubleescapeddashloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Switch to the
* script data double escaped dash dash state.
*/
goto breakScriptdatadoubleescapeddashloop;
// goto continueStateloop;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Emit a U+003C
* LESS-THAN SIGN character token. Switch to the
* script data double escaped less-than sign
* state.
*/
goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
goto continueStateloop;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Switch to the
* script data double escaped state.
*/
goto continueStateloop;
}
}
breakScriptdatadoubleescapeddashloop:
goto case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH:
/*scriptdatadoubleescapeddashdashloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '-':
/*
* U+002D HYPHEN-MINUS (-) Emit a U+002D
* HYPHEN-MINUS character token. Stay in the
* script data double escaped dash dash state.
*/
continue;
case '<':
/*
* U+003C LESS-THAN SIGN (<) Emit a U+003C
* LESS-THAN SIGN character token. Switch to the
* script data double escaped less-than sign
* state.
*/
goto breakScriptdatadoubleescapeddashdashloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit a U+003E
* GREATER-THAN SIGN character token. Switch to
* the script data state.
*/
goto continueStateloop;
case '\u0000':
EmitReplacementCharacter(buf, pos);
goto continueStateloop;
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto default;
default:
/*
* Anything else Emit the current input
* character as a character token. Switch to the
* script data double escaped state.
*/
goto continueStateloop;
}
}
breakScriptdatadoubleescapeddashdashloop:
goto case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN:
/*scriptdatadoubleescapedlessthanloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '/':
/*
* U+002F SOLIDUS (/) Emit a U+002F SOLIDUS
* character token. Set the temporary buffer to
* the empty string. Switch to the script data
* double escape end state.
*/
index = 0;
goto breakScriptdatadoubleescapedlessthanloop;
default:
/*
* Anything else Reconsume the current input
* character in the script data double escaped
* state.
*/
reconsume = true;
goto continueStateloop;
}
}
breakScriptdatadoubleescapedlessthanloop:
goto case SCRIPT_DATA_DOUBLE_ESCAPE_END;
// WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
case SCRIPT_DATA_DOUBLE_ESCAPE_END:
/*scriptdatadoubleescapeendloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
if (index < 6)
{ // SCRIPT_ARR.Length
char folded = c;
if (c >= 'A' && c <= 'Z')
{
folded += (char)0x20;
}
if (folded != Tokenizer.SCRIPT_ARR[index])
{
reconsume = true;
goto continueStateloop;
}
index++;
continue;
}
switch (c)
{
case '\r':
EmitCarriageReturn(buf, pos);
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
case ' ':
case '\t':
case '\u000C':
case '/':
case '>':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* U+002F SOLIDUS (/) U+003E GREATER-THAN SIGN
* (>) Emit the current input character as a
* character token. If the temporary buffer is
* the string "script", then switch to the
* script data escaped state.
*/
goto continueStateloop;
default:
/*
* Reconsume the current input character in the
* script data double escaped state.
*/
reconsume = true;
goto continueStateloop;
}
}
// XXX reorder point
case MARKUP_DECLARATION_OCTYPE:
/*markupdeclarationdoctypeloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
if (index < 6)
{ // OCTYPE.Length
char folded = c;
if (c >= 'A' && c <= 'Z')
{
folded += (char)0x20;
}
if (folded == Tokenizer.OCTYPE[index])
{
AppendLongStrBuf(c);
}
else
{
ErrBogusComment();
reconsume = true;
goto continueStateloop;
}
index++;
continue;
}
else
{
reconsume = true;
goto breakMarkupdeclarationdoctypeloop;
// goto continueStateloop;
}
}
breakMarkupdeclarationdoctypeloop:
goto case DOCTYPE;
// FALLTHRU DON'T REORDER
case DOCTYPE:
/*doctypeloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
InitDoctypeFields();
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
// fall thru
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the before DOCTYPE name state.
*/
goto breakDoctypeloop;
// goto continueStateloop;
default:
/*
* Anything else Parse error.
*/
ErrMissingSpaceBeforeDoctypeName();
/*
* Reconsume the current character in the before
* DOCTYPE name state.
*/
reconsume = true;
goto breakDoctypeloop;
// goto continueStateloop;
}
}
breakDoctypeloop:
goto case BEFORE_DOCTYPE_NAME;
// FALLTHRU DON'T REORDER
case BEFORE_DOCTYPE_NAME:
/*beforedoctypenameloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the before DOCTYPE name state.
*/
continue;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Parse error.
*/
ErrNamelessDoctype();
/*
* Create a new DOCTYPE token. Set its
* force-quirks flag to on.
*/
forceQuirks = true;
/*
* Emit the token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
if (c >= 'A' && c <= 'Z')
{
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Create a
* new DOCTYPE token. Set the token's name
* to the lowercase version of the input
* character (add 0x0020 to the character's
* code point).
*/
c += (char)0x20;
}
/* Anything else Create a new DOCTYPE token. */
/*
* Set the token's name name to the current
* input character.
*/
ClearStrBufAndAppend(c);
/*
* Switch to the DOCTYPE name state.
*/
goto breakBeforedoctypenameloop;
// goto continueStateloop;
}
}
breakBeforedoctypenameloop:
goto case DOCTYPE_NAME;
// FALLTHRU DON'T REORDER
case DOCTYPE_NAME:
/*doctypenameloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
StrBufToDoctypeName();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the after DOCTYPE name state.
*/
StrBufToDoctypeName();
goto breakDoctypenameloop;
// goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* DOCTYPE token.
*/
StrBufToDoctypeName();
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* U+0041 LATIN CAPITAL LETTER A through to
* U+005A LATIN CAPITAL LETTER Z Append the
* lowercase version of the input character (add
* 0x0020 to the character's code point) to the
* current DOCTYPE token's name.
*/
if (c >= 'A' && c <= 'Z')
{
c += (char)0x0020;
}
/*
* Anything else Append the current input
* character to the current DOCTYPE token's
* name.
*/
AppendStrBuf(c);
/*
* Stay in the DOCTYPE name state.
*/
continue;
}
}
breakDoctypenameloop:
goto case AFTER_DOCTYPE_NAME;
// FALLTHRU DON'T REORDER
case AFTER_DOCTYPE_NAME:
/*afterdoctypenameloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the after DOCTYPE name state.
*/
continue;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case 'p':
case 'P':
index = 0;
goto breakAfterdoctypenameloop;
// goto continueStateloop;
case 's':
case 'S':
index = 0;
goto continueStateloop;
default:
/*
* Otherwise, this is the parse error.
*/
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakAfterdoctypenameloop:
goto case DOCTYPE_UBLIC;
// FALLTHRU DON'T REORDER
case DOCTYPE_UBLIC:
/*doctypeublicloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* If the six characters starting from the current input
* character are an ASCII case-insensitive match for the
* word "PUBLIC", then consume those characters and
* switch to the before DOCTYPE public identifier state.
*/
if (index < 5)
{ // UBLIC.Length
char folded = c;
if (c >= 'A' && c <= 'Z')
{
folded += (char)0x20;
}
if (folded != Tokenizer.UBLIC[index])
{
BogusDoctype();
// forceQuirks = true;
reconsume = true;
goto continueStateloop;
}
index++;
continue;
}
else
{
reconsume = true;
goto breakDoctypeublicloop;
// goto continueStateloop;
}
}
breakDoctypeublicloop:
goto case AFTER_DOCTYPE_PUBLIC_KEYWORD;
// FALLTHRU DON'T REORDER
case AFTER_DOCTYPE_PUBLIC_KEYWORD:
/*afterdoctypepublickeywordloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the before DOCTYPE public
* identifier state.
*/
goto breakAfterdoctypepublickeywordloop;
// FALL THROUGH continue stateloop
case '"':
/*
* U+0022 QUOTATION MARK (") Parse Error.
*/
ErrNoSpaceBetweenDoctypePublicKeywordAndQuote();
/*
* Set the DOCTYPE token's public identifier to
* the empty string (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE public identifier
* (double-quoted) state.
*/
goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Parse Error.
*/
ErrNoSpaceBetweenDoctypePublicKeywordAndQuote();
/*
* Set the DOCTYPE token's public identifier to
* the empty string (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE public identifier
* (single-quoted) state.
*/
goto continueStateloop;
case '>':
/* U+003E GREATER-THAN SIGN (>) Parse error. */
ErrExpectedPublicId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakAfterdoctypepublickeywordloop:
goto case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER;
// FALLTHRU DON'T REORDER
case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER:
/*beforedoctypepublicidentifierloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the before DOCTYPE public identifier
* state.
*/
continue;
case '"':
/*
* U+0022 QUOTATION MARK (") Set the DOCTYPE
* token's public identifier to the empty string
* (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE public identifier
* (double-quoted) state.
*/
goto breakBeforedoctypepublicidentifierloop;
// goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Set the DOCTYPE token's
* public identifier to the empty string (not
* missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE public identifier
* (single-quoted) state.
*/
goto continueStateloop;
case '>':
/* U+003E GREATER-THAN SIGN (>) Parse error. */
ErrExpectedPublicId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakBeforedoctypepublicidentifierloop:
goto case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED;
// FALLTHRU DON'T REORDER
case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED:
/*doctypepublicidentifierdoublequotedloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '"':
/*
* U+0022 QUOTATION MARK (") Switch to the after
* DOCTYPE public identifier state.
*/
publicIdentifier = LongStrBufToString();
goto breakDoctypepublicidentifierdoublequotedloop;
// goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Parse error.
*/
ErrGtInPublicId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
publicIdentifier = LongStrBufToString();
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the current input
* character to the current DOCTYPE token's
* public identifier.
*/
AppendLongStrBuf(c);
/*
* Stay in the DOCTYPE public identifier
* (double-quoted) state.
*/
continue;
}
}
breakDoctypepublicidentifierdoublequotedloop:
goto case AFTER_DOCTYPE_PUBLIC_IDENTIFIER;
// FALLTHRU DON'T REORDER
case AFTER_DOCTYPE_PUBLIC_IDENTIFIER:
/*afterdoctypepublicidentifierloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the between DOCTYPE public and
* system identifiers state.
*/
goto breakAfterdoctypepublicidentifierloop;
// goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '"':
/*
* U+0022 QUOTATION MARK (") Parse error.
*/
ErrNoSpaceBetweenPublicAndSystemIds();
/*
* Set the DOCTYPE token's system identifier to
* the empty string (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE system identifier
* (double-quoted) state.
*/
goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Parse error.
*/
ErrNoSpaceBetweenPublicAndSystemIds();
/*
* Set the DOCTYPE token's system identifier to
* the empty string (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE system identifier
* (single-quoted) state.
*/
goto continueStateloop;
default:
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakAfterdoctypepublicidentifierloop:
goto case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS;
// FALLTHRU DON'T REORDER
case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS:
/*betweendoctypepublicandsystemidentifiersloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
// fall thru
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the between DOCTYPE public and system
* identifiers state.
*/
continue;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '"':
/*
* U+0022 QUOTATION MARK (") Set the DOCTYPE
* token's system identifier to the empty string
* (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE system identifier
* (double-quoted) state.
*/
goto breakBetweendoctypepublicandsystemidentifiersloop;
// goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Set the DOCTYPE token's
* system identifier to the empty string (not
* missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE system identifier
* (single-quoted) state.
*/
goto continueStateloop;
default:
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakBetweendoctypepublicandsystemidentifiersloop:
goto case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED;
// FALLTHRU DON'T REORDER
case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED:
/*doctypesystemidentifierdoublequotedloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '"':
/*
* U+0022 QUOTATION MARK (") Switch to the after
* DOCTYPE system identifier state.
*/
systemIdentifier = LongStrBufToString();
goto continueStateloop;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Parse error.
*/
ErrGtInSystemId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
systemIdentifier = LongStrBufToString();
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the current input
* character to the current DOCTYPE token's
* system identifier.
*/
AppendLongStrBuf(c);
/*
* Stay in the DOCTYPE system identifier
* (double-quoted) state.
*/
continue;
}
}
breakDoctypesystemidentifierdoublequotedloop:
goto case AFTER_DOCTYPE_SYSTEM_IDENTIFIER;
// FALLTHRU DON'T REORDER
case AFTER_DOCTYPE_SYSTEM_IDENTIFIER:
/*afterdoctypesystemidentifierloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
goto case ' ';
// fall thru
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the after DOCTYPE system identifier state.
*/
continue;
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit the current
* DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
/*
* Switch to the bogus DOCTYPE state. (This does
* not set the DOCTYPE token's force-quirks flag
* to on.)
*/
BogusDoctypeWithoutQuirks();
goto breakAfterdoctypesystemidentifierloop;
// goto continueStateloop;
}
}
breakAfterdoctypesystemidentifierloop:
goto case BOGUS_DOCTYPE;
// FALLTHRU DON'T REORDER
case BOGUS_DOCTYPE:
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '>':
/*
* U+003E GREATER-THAN SIGN (>) Emit that
* DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto default;
default:
/*
* Anything else Stay in the bogus DOCTYPE
* state.
*/
continue;
}
}
// XXX reorder point
case DOCTYPE_YSTEM:
/*doctypeystemloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Otherwise, if the six characters starting from the
* current input character are an ASCII case-insensitive
* match for the word "SYSTEM", then consume those
* characters and switch to the before DOCTYPE system
* identifier state.
*/
if (index < 5)
{ // YSTEM.Length
char folded = c;
if (c >= 'A' && c <= 'Z')
{
folded += (char)0x20;
}
if (folded != Tokenizer.YSTEM[index])
{
BogusDoctype();
reconsume = true;
goto continueStateloop;
}
index++;
goto continueStateloop;
}
else
{
reconsume = true;
goto breakDoctypeystemloop;
// goto continueStateloop;
}
}
breakDoctypeystemloop:
goto case AFTER_DOCTYPE_SYSTEM_KEYWORD;
// FALLTHRU DON'T REORDER
case AFTER_DOCTYPE_SYSTEM_KEYWORD:
/*afterdoctypesystemkeywordloop:*/
for (; ; )
{
if (reconsume)
{
reconsume = false;
}
else
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
}
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE
* Switch to the before DOCTYPE public
* identifier state.
*/
goto breakAfterdoctypesystemkeywordloop;
// FALL THROUGH continue stateloop
case '"':
/*
* U+0022 QUOTATION MARK (") Parse Error.
*/
ErrNoSpaceBetweenDoctypeSystemKeywordAndQuote();
/*
* Set the DOCTYPE token's system identifier to
* the empty string (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE public identifier
* (double-quoted) state.
*/
goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Parse Error.
*/
ErrNoSpaceBetweenDoctypeSystemKeywordAndQuote();
/*
* Set the DOCTYPE token's public identifier to
* the empty string (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE public identifier
* (single-quoted) state.
*/
goto continueStateloop;
case '>':
/* U+003E GREATER-THAN SIGN (>) Parse error. */
ErrExpectedPublicId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakAfterdoctypesystemkeywordloop:
goto case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER;
// FALLTHRU DON'T REORDER
case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER:
/*beforedoctypesystemidentifierloop:*/
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\r':
SilentCarriageReturn();
goto breakStateloop;
case '\n':
SilentLineFeed();
// fall thru
goto case ' ';
case ' ':
case '\t':
case '\u000C':
/*
* U+0009 CHARACTER TABULATION U+000A LINE FEED
* (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
* in the before DOCTYPE system identifier
* state.
*/
continue;
case '"':
/*
* U+0022 QUOTATION MARK (") Set the DOCTYPE
* token's system identifier to the empty string
* (not missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE system identifier
* (double-quoted) state.
*/
goto continueStateloop;
case '\'':
/*
* U+0027 APOSTROPHE (') Set the DOCTYPE token's
* system identifier to the empty string (not
* missing),
*/
ClearLongStrBuf();
/*
* then switch to the DOCTYPE system identifier
* (single-quoted) state.
*/
goto breakBeforedoctypesystemidentifierloop;
// goto continueStateloop;
case '>':
/* U+003E GREATER-THAN SIGN (>) Parse error. */
ErrExpectedSystemId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
default:
BogusDoctype();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
// done by bogusDoctype();
/*
* Switch to the bogus DOCTYPE state.
*/
goto continueStateloop;
}
}
breakBeforedoctypesystemidentifierloop:
goto case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED;
// FALLTHRU DON'T REORDER
case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\'':
/*
* U+0027 APOSTROPHE (') Switch to the after
* DOCTYPE system identifier state.
*/
systemIdentifier = LongStrBufToString();
goto continueStateloop;
case '>':
ErrGtInSystemId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
systemIdentifier = LongStrBufToString();
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the current input
* character to the current DOCTYPE token's
* system identifier.
*/
AppendLongStrBuf(c);
/*
* Stay in the DOCTYPE system identifier
* (double-quoted) state.
*/
continue;
}
}
// XXX reorder point
case DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED:
for (; ; )
{
if (++pos == endPos)
{
goto breakStateloop;
}
c = CheckChar(buf, pos);
/*
* Consume the next input character:
*/
switch (c)
{
case '\'':
/*
* U+0027 APOSTROPHE (') Switch to the after
* DOCTYPE public identifier state.
*/
publicIdentifier = LongStrBufToString();
goto continueStateloop;
case '>':
ErrGtInPublicId();
/*
* Set the DOCTYPE token's force-quirks flag to
* on.
*/
forceQuirks = true;
/*
* Emit that DOCTYPE token.
*/
publicIdentifier = LongStrBufToString();
EmitDoctypeToken(pos);
/*
* Switch to the data state.
*/
goto continueStateloop;
case '\r':
AppendLongStrBufCarriageReturn();
goto breakStateloop;
case '\n':
AppendLongStrBufLineFeed();
continue;
case '\u0000':
c = '\uFFFD';
// fall thru
goto default;
default:
/*
* Anything else Append the current input
* character to the current DOCTYPE token's
* public identifier.
*/
AppendLongStrBuf(c);
/*
* Stay in the DOCTYPE public identifier
* (single-quoted) state.
*/
continue;
}
}
// END HOTSPOT WORKAROUND
}
} // stateloop
breakStateloop:
FlushChars(buf, pos);
/*
* if (prevCR && pos != endPos) { // why is this needed pos--; col--; }
*/
// Save locals
stateSave = state;
returnStateSave = returnState;
return pos;
}
/**
* The constructor.
*
* @param tokenHandler
* the handler for receiving tokens
*/
public Tokenizer(ITreeBuilder tokenHandler)
{
this.TokenHandler = tokenHandler;
this.bmpChar = new char[1];
this.astralChar = new char[2];
this.tagName = null;
this.attributeName = null;
this.doctypeName = null;
this.publicIdentifier = null;
this.systemIdentifier = null;
this.attributes = null;
}
private int EmitCurrentTagToken(bool selfClosing, int pos)
{
cstart = pos + 1;
MaybeErrSlashInEndTag(selfClosing);
stateSave = Tokenizer.DATA;
HtmlAttributes attrs = (attributes == null ? HtmlAttributes.EMPTY_ATTRIBUTES : attributes);
if (endTag)
{
/*
* When an end tag token is emitted, the content model flag must be
* switched to the PCDATA state.
*/
MaybeErrAttributesOnEndTag(attrs);
TokenHandler.EndTag(tagName);
}
else
{
TokenHandler.StartTag(tagName, attrs, selfClosing);
}
tagName = null;
ResetAttributes();
/*
* The token handler may have called setStateAndEndTagExpectation
* and changed stateSave since the start of this method.
*/
return stateSave;
}
/**
* 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(int specialTokenizerState, ElementName endTagExpectation)
{
this.stateSave = specialTokenizerState;
this.endTagExpectation = endTagExpectation;
EndTagExpectationToArray();
}
// 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(int specialTokenizerState, String endTagExpectation)
{
this.stateSave = specialTokenizerState;
if (specialTokenizerState == Tokenizer.DATA)
{
return;
}
char[] asArray = endTagExpectation.ToCharArray();
this.endTagExpectation = new ElementName(endTagExpectation);
EndTagExpectationToArray();
}
public void ResetToDataState()
{
strBufLen = 0;
longStrBufLen = 0;
stateSave = Tokenizer.DATA;
// 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;
shouldSuspend = false;
InitDoctypeFields();
if (tagName != null)
{
tagName = null;
}
if (attributeName != null)
{
attributeName = null;
}
if (attributes != null)
{
attributes = null;
}
}
private void StrBufToElementNameString()
{
// if (strBufOffset != -1) {
// return ElementName.elementNameByBuffer(buf, strBufOffset, strBufLen);
// } else {
tagName = ElementName.ElementNameByBuffer(strBuf, 0, strBufLen);
// }
}
