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

/*
 * 11/07/2008
 *
 * PlainTextTokenMaker.flex - Scanner for plain text files.
 * 
 * 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 plain text files.
 *
 * 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 <code>PlainTextTokenMaker.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 0.5
 *
 */
%%

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


%{


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


    /**
     * Adds the token specified to the current linked list of tokens.
     *
     * @param tokenType The token's type.
     * @param link Whether this token is a hyperlink.
     */
    private void addToken(int tokenType, boolean link) {
        int so = zzStartRead + offsetShift;
        super.addToken(zzBuffer, zzStartRead,zzMarkedPos-1, tokenType, so, link);
        zzStartRead = zzMarkedPos;
    }


    /**
     * Always returns <code>Token.NULL</code>, as there are no multiline
     * tokens in properties files.
     *
     * @param text The line of tokens to examine.
     * @param initialTokenType The token type to start with (i.e., the value
     *        of <code>getLastTokenTypeOnLine</code> for the line before
     *        <code>text</code>).
     * @return <code>Token.NULL</code>.
     */
    public int getLastTokenTypeOnLine(Segment text, int initialTokenType) {
        return Token.NULL;
    }


    /**
     * Returns the text to place at the beginning and end of a
     * line to "comment" it in a this programming language.
     *
     * @return <code>null</code>, as there are no comments in plain text.
     */
    public String[] getLineCommentStartAndEnd() {
        return null;
    }


    /**
     * Always returns <tt>false</tt>, as you never want "mark occurrences"
     * working in plain text 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 <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.
        s = text;
        try {
            yyreset(zzReader);
            yybegin(YYINITIAL);
            return yylex();
        } catch (IOException ioe) {
            ioe.printStackTrace();
            return new DefaultToken();
        }

    }


    /**
     * Refills the input buffer.
     *
     * @return      <code>true</code> if EOF was reached, otherwise
     *              <code>false</code>.
     * @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 
     * <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;
    }


%}

LetterOrDigit   = ([a-zA-Z0-9])
Identifier      = ({LetterOrDigit}+)
Separator       = ([^a-zA-Z0-9 \t\n])
WhiteSpace      = ([ \t]+)
LineTerminator  = ([\n])

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

%%

<YYINITIAL> {
    {URL}               { addToken(Token.IDENTIFIER, true); }
    {Identifier}        { addToken(Token.IDENTIFIER, false); }
    {Separator}         { addToken(Token.IDENTIFIER, false); }
    {WhiteSpace}        { addToken(Token.WHITESPACE, false); }
    {LineTerminator}    { addNullToken(); return firstToken; }
    <<EOF>>             { addNullToken(); return firstToken; }
    .                   { /* Never happens */ addToken(Token.IDENTIFIER, false); }
}