org.fife.ui.rsyntaxtextarea.modes.LatexTokenMaker.flex Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of ui4j-ide Show documentation
Web Automation for Java
The newest version!
/*
 * 04/24/2012
 *
 * LatexTokenMaker.java - Scanner for LaTeX.
 * 
 * This library is distributed under a modified BSD license.  See the included
 * RSyntaxTextArea.License.txt file for details.
 */
package org.fife.ui.rsyntaxtextarea.modes;

import java.io.*;
import javax.swing.text.Segment;

import org.fife.ui.rsyntaxtextarea.*;


/**
 * Scanner for the LaTeX.
 *
 * This implementation was created using
 * JFlex 1.4.1; however, the generated file
 * was modified for performance.  Memory allocation needs to be almost
 * completely removed to be competitive with the handwritten lexers (subclasses
 * of 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 RSTA 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:
 * 
 *   The generated LatexTokenMaker.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.
 *   You should also change the declaration/definition of zzBuffer to NOT
 *       be initialized.  This is a needless memory allocation for us since we
 *       will be pointing the array somewhere else anyway.
 *   You should NOT call yylex() on the generated scanner
 *       directly; rather, you should use getTokenList as you would
 *       with any other TokenMaker instance.
 * 
 *
 * @author Robert Futrell
 * @version 0.5
 *
 */
%%

%public
%class LatexTokenMaker
%extends AbstractJFlexTokenMaker
%unicode
%type org.fife.ui.rsyntaxtextarea.Token


%{


	/**
	 * Constructor.  This must be here because JFlex does not generate a
	 * no-parameter constructor.
	 */
	public LatexTokenMaker() {
	}


	/**
	 * 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.
	 * @see #addHyperlinkToken(int, int, int)
	 */
	private void addToken(int start, int end, int tokenType) {
		int so = start + offsetShift;
		addToken(zzBuffer, start,end, tokenType, so, false);
	}


	/**
	 * 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.
	 * @param hyperlink Whether this token is a hyperlink.
	 */
	@Override
	public void addToken(char[] array, int start, int end, int tokenType,
						int startOffset, boolean hyperlink) {
		super.addToken(array, start,end, tokenType, startOffset, hyperlink);
		zzStartRead = zzMarkedPos;
	}


	/**
	 * ${inheritDoc}
	 */
	@Override
	public String[] getLineCommentStartAndEnd(int languageIndex) {
		return new String[] { "%", null };
	}


	/**
	 * 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;

		// Start off in the proper state.
		int state = Token.NULL;

		s = text;
		try {
			yyreset(zzReader);
			yybegin(state);
			return yylex();
		} catch (IOException ioe) {
			ioe.printStackTrace();
			return new TokenImpl();
		}

	}


	/**
	 * Refills the input buffer.
	 *
	 * @return      true if EOF was reached, otherwise
	 *              false.
	 * @exception   IOException  if any I/O-Error occurs.
	 */
	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;
	}


%}

Letter					= ([A-Za-z])
Digit					= ([0-9])
LetterOrUnderscore		= ({Letter}|[_])
AnyChar					= ({LetterOrUnderscore}|{Digit}|[\-])
Whitespace				= ([ \t\f])
LineCommentBegin		= "%"

URLGenDelim				= ([:\/\?#\[\]@])
URLSubDelim				= ([\!\$&'\(\)\*\+,;=])
URLUnreserved			= ({LetterOrUnderscore}|{Digit}|[\-\.\~])
URLCharacter			= ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
URLCharacters			= ({URLCharacter}*)
URLEndCharacter			= ([\/\$]|{Letter}|{Digit})
URL						= (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)


%state EOL_COMMENT

%%

 {

	([\\]{AnyChar}+)			{ addToken(Token.FUNCTION); }
	[\{\}]						{ addToken(Token.SEPARATOR); }
	("\\begin{"{AnyChar}+"}")   { int temp = zzStartRead;
							addToken(temp, temp+5, Token.RESERVED_WORD);
							addToken(temp+6, temp+6, Token.SEPARATOR);
							addToken(temp+7, zzMarkedPos-2, Token.RESERVED_WORD);
							addToken(zzMarkedPos-1, zzMarkedPos-1, Token.SEPARATOR);
								}
	("\\end{"{AnyChar}+"}")		{ int temp = zzStartRead;
							addToken(temp, temp+3, Token.RESERVED_WORD);
							addToken(temp+4, temp+4, Token.SEPARATOR);
							addToken(temp+5, zzMarkedPos-2, Token.RESERVED_WORD);
							addToken(zzMarkedPos-1, zzMarkedPos-1, Token.SEPARATOR);
								}
	{Whitespace}				{ addToken(Token.WHITESPACE); }

	{LineCommentBegin}			{ start = zzMarkedPos-1; yybegin(EOL_COMMENT); }

	"\n" |
	<>						{ addNullToken(); return firstToken; }

	/* Catch any other (unhandled) characters and flag them as identifiers. */
	{AnyChar}+ |
	.							{ addToken(Token.IDENTIFIER); }

}


 {
	[^hwf\n]+				{}
	{URL}					{ int temp=zzStartRead; addToken(start,zzStartRead-1, Token.COMMENT_EOL); addHyperlinkToken(temp,zzMarkedPos-1, Token.COMMENT_EOL); start = zzMarkedPos; }
	[hwf]					{}
	\n |
	<>					{ addToken(start,zzStartRead-1, Token.COMMENT_EOL); addNullToken(); return firstToken; }
}