AbstractTokenMaker, so this class has been modified so that
* Strings are never allocated (via yytext()), and the scanner never has to
* worry about refilling its buffer (needlessly copying chars around).
* We can achieve this because RText always scans exactly 1 line of tokens at a
* time, and hands the scanner this line as an array of characters (a Segment
* really). Since tokens contain pointers to char arrays instead of Strings
* holding their contents, there is no need for allocating new memory for
* Strings.* * The actual algorithm generated for scanning has, of course, not been * modified.
* * If you wish to regenerate this file yourself, keep in mind the following: *
XMLTokenMaker.java file will contain two
* definitions of both zzRefill and yyreset.
* You should hand-delete the second of each definition (the ones
* generated by the lexer), as these generated methods modify the input
* buffer, which we'll never have to do.yylex() on the generated scanner
* directly; rather, you should use getTokenList as you would
* with any other TokenMaker instance.zzMarkedPos.
*
* @param tokenType The token's type.
*/
private void addEndToken(int tokenType) {
addToken(zzMarkedPos,zzMarkedPos, tokenType);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param tokenType The token's type.
* @see #addToken(int, int, int)
*/
private void addHyperlinkToken(int start, int end, int tokenType) {
int so = start + offsetShift;
addToken(zzBuffer, start,end, tokenType, so, true);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param tokenType The token's type.
*/
private void addToken(int tokenType) {
addToken(zzStartRead, zzMarkedPos-1, tokenType);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param tokenType The token's type.
*/
private void addToken(int start, int end, int tokenType) {
int so = start + offsetShift;
addToken(zzBuffer, start,end, tokenType, so);
}
/**
* Adds the token specified to the current linked list of tokens.
*
* @param array The character array.
* @param start The starting offset in the array.
* @param end The ending offset in the array.
* @param tokenType The token's type.
* @param startOffset The offset in the document at which this token
* occurs.
*/
public void addToken(char[] array, int start, int end, int tokenType, int startOffset) {
super.addToken(array, start,end, tokenType, startOffset);
zzStartRead = zzMarkedPos;
}
/**
* Always returns false, as you never want "mark occurrences"
* working in XML files.
*
* @param type The token type.
* @return Whether tokens of this type should have "mark occurrences"
* enabled.
*/
public boolean getMarkOccurrencesOfTokenType(int type) {
return false;
}
/**
* Returns the first token in the linked list of tokens generated
* from text. This method must be implemented by
* subclasses so they can correctly implement syntax highlighting.
*
* @param text The text from which to get tokens.
* @param initialTokenType The token type we should start with.
* @param startOffset The offset into the document at which
* text starts.
* @return The first Token in a linked list representing
* the syntax highlighted text.
*/
public Token getTokenList(Segment text, int initialTokenType, int startOffset) {
resetTokenList();
this.offsetShift = -text.offset + startOffset;
prevState = YYINITIAL;
// Start off in the proper state.
int state = YYINITIAL;
switch (initialTokenType) {
case INTERNAL_INTAG_START:
state = INTAG_START;
break;
case INTERNAL_INTAG_ELEMENT:
state = INTAG_ELEMENT;
break;
case INTERNAL_INTAG_ATTLIST:
state = INTAG_ATTLIST;
break;
default:
if (initialTokenType<-1024) { // INTERNAL_IN_COMMENT - prevState
int main = -(-initialTokenType & 0xffffff00);
switch (main) {
default: // Should never happen
case INTERNAL_IN_COMMENT:
state = COMMENT;
break;
}
prevState = -initialTokenType&0xff;
}
else { // Shouldn't happen
state = YYINITIAL;
}
}
start = text.offset;
s = text;
try {
yyreset(zzReader);
yybegin(state);
return yylex();
} catch (IOException ioe) {
ioe.printStackTrace();
return new DefaultToken();
}
}
/**
* Refills the input buffer.
*
* @return true if EOF was reached, otherwise
* false.
*/
private boolean zzRefill() {
return zzCurrentPos>=s.offset+s.count;
}
/**
* Resets the scanner to read from a new input stream.
* Does not close the old reader.
*
* All internal variables are reset, the old input stream
* cannot be reused (internal buffer is discarded and lost).
* Lexical state is set to YY_INITIAL.
*
* @param reader the new input stream
*/
public final void yyreset(java.io.Reader reader) {
// 's' has been updated.
zzBuffer = s.array;
/*
* We replaced the line below with the two below it because zzRefill
* no longer "refills" the buffer (since the way we do it, it's always
* "full" the first time through, since it points to the segment's
* array). So, we assign zzEndRead here.
*/
//zzStartRead = zzEndRead = s.offset;
zzStartRead = s.offset;
zzEndRead = zzStartRead + s.count - 1;
zzCurrentPos = zzMarkedPos = zzPushbackPos = s.offset;
zzLexicalState = YYINITIAL;
zzReader = reader;
zzAtBOL = true;
zzAtEOF = false;
}
%}
Whitespace = ([ \t\f])
LineTerminator = ([\n])
UnclosedString = ([\"][^\"]*)
UnclosedChar = ([\'][^\']*)
URLGenDelim = ([:\/\?#\[\]@])
URLSubDelim = ([\!\$&'\(\)\*\+,;=])
URLUnreserved = ([A-Za-z_0-9\-\.\~])
URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
URLCharacters = ({URLCharacter}*)
URLEndCharacter = ([\/\$A-Za-z0-9])
URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
%state COMMENT
%state INTAG_START
%state INTAG_ELEMENT
%state INTAG_ATTLIST
%%