source: other-projects/rsyntax-textarea/src/java/org/fife/ui/rsyntaxtextarea/modes/BBCodeTokenMaker.flex@ 25584

/*
 * 11/18/2009
 *
 * BBCodeTokenMaker.java - Generates tokens for BBCode syntax highlighting.
 * 
 * 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 BBCode.
 *
 * This implementation was created using
 * <a href="http://www.jflex.de/">JFlex</a> 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 <code>AbstractTokenMaker</code>, 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.<p>
 *
 * The actual algorithm generated for scanning has, of course, not been
 * modified.<p>
 *
 * If you wish to regenerate this file yourself, keep in mind the following:
 * <ul>
 *   <li>The generated BBCodeTokenMaker.java</code> file will contain two
 *       definitions of both <code>zzRefill</code> and <code>yyreset</code>.
 *       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.</li>
 *   <li>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.</li>
 *   <li>You should NOT call <code>yylex()</code> on the generated scanner
 *       directly; rather, you should use <code>getTokenList</code> as you would
 *       with any other <code>TokenMaker</code> instance.</li>
 * </ul>
 *
 * @author Robert Futrell
 * @version 0.7
 *
 */
%%

%public
%class BBCodeTokenMaker
%extends AbstractMarkupTokenMaker
%unicode
%type org.fife.ui.rsyntaxtextarea.Token


%{

    /**
     * Token type specific to BBCodeTokenMaker; this signals that the user has
     * ended a line with an unclosed tag; thus a new line is beginning
     * still inside of the tag.
     */
    public static final int INTERNAL_INTAG                  = -1;

    /**
     * Whether closing markup tags are automatically completed for BBCode.
     */
    private static boolean completeCloseTags = true;


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


    /**
     * 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;
    }


    /**
     * Sets whether markup close tags should be completed.  The default value
     * for BBCode is <code>true</code>.
     *
     * @return Whether closing markup tags are completed.
     * @see #setCompleteCloseTags(boolean)
     */
    public boolean getCompleteCloseTags() {
        return completeCloseTags;
    }


    /**
     * Returns <code>null</code> since BBCode has no comments.
     *
     * @return <code>null</code> always.
     */
    public String[] getLineCommentStartAndEnd() {
        return null;
    }


    /**
     * Returns the first token in the linked list of tokens generated
     * from <code>text</code>.  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
     *        <code>text</code> starts.
     * @return The first <code>Token</code> 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;
        switch (initialTokenType) {
            case INTERNAL_INTAG:
                state = INTAG;
                start = text.offset;
                break;
            default:
                state = Token.NULL;
        }

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

    }


    /**
     * Sets whether markup close tags should be completed.
     *
     * @param complete Whether closing markup tags are completed.
     * @see #getCompleteCloseTags()
     */
    public static void setCompleteCloseTags(boolean complete) {
        completeCloseTags = complete;
    }


    /**
     * Refills the input buffer.
     *
     * @return      <code>true</code> if EOF was reached, otherwise
     *              <code>false</code>.
     */
    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 
     * <b>cannot</b> be reused (internal buffer is discarded and lost).
     * Lexical state is set to <tt>YY_INITIAL</tt>.
     *
     * @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])
Identifier          = ([^ \t\f\n\[]+)
InTagIdentifier     = ([^ \t\f\n\[\]\/\=]+)
Tag                 = ("b"|"i"|"u"|"s"|"size"|"color"|"center"|"quote"|"url"|"img"|"ul"|"li"|"ol"|"youtube"|"gvideo")

%state INTAG

%%

<YYINITIAL> {
    {Identifier}            { addToken(Token.IDENTIFIER); }
    {Whitespace}            { addToken(Token.WHITESPACE); }
    "["                     { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(INTAG); }
    "[/"                    { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(INTAG); }
    {LineTerminator}        { addNullToken(); return firstToken; }
    <<EOF>>                 { addNullToken(); return firstToken; }
}

<INTAG> {
    "/"                     { addToken(Token.MARKUP_TAG_DELIMITER); }
    {Tag}                   { addToken(Token.MARKUP_TAG_NAME); }
    {InTagIdentifier}       { addToken(Token.MARKUP_TAG_ATTRIBUTE); }
    {Whitespace}            { addToken(Token.WHITESPACE); }
    "="                     { addToken(Token.OPERATOR); }
    "/]"                    { yybegin(YYINITIAL); addToken(Token.MARKUP_TAG_DELIMITER); }
    "]"                     { yybegin(YYINITIAL); addToken(Token.MARKUP_TAG_DELIMITER); }
    .                       { addToken(Token.IDENTIFIER); /* Unhandled chars, not likely */ }
    <<EOF>>                 { addToken(zzMarkedPos,zzMarkedPos, INTERNAL_INTAG); return firstToken; }
}