pythontokenmaker.flex

具有不同语法高亮的编辑器实例

/*
 * 12/06/2005
 *
 * PythonTokenMaker.java - Token maker for the Python programming language.
 * Copyright (C) 2005 Robert Futrell
 * [e-mail]
 * www.website.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 */
package org.fife.ui.rsyntaxtextarea.modes;

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

import org.fife.ui.rsyntaxtextarea.AbstractJFlexTokenMaker;
import org.fife.ui.rsyntaxtextarea.DefaultToken;
import org.fife.ui.rsyntaxtextarea.Token;
import org.fife.ui.rsyntaxtextarea.TokenMaker;


/**
 * Scanner for the Python programming language.
 *
 * @author Robert Futrell
 * @version 0.3
 */
%%

%public
%class PythonTokenMaker
%extends AbstractJFlexTokenMaker
%implements TokenMaker
%unicode
%type org.fife.ui.rsyntaxtextarea.Token


%{


/*****************************************************************************/


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


/*****************************************************************************/


	/**
	 * 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;
	}


/*****************************************************************************/


	/**
	 * 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 Token.LITERAL_STRING_DOUBLE_QUOTE:
				state = LONG_STRING_2;
				break;
			case Token.LITERAL_CHAR:
				state = LONG_STRING_1;
				break;
			default:
				state = Token.NULL;
		}

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

	}


/*****************************************************************************/


	/**
	 * 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) throws java.io.IOException {
		// '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;
	}


/*****************************************************************************/


	/**
	 * 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() throws java.io.IOException {
		return zzCurrentPos>=s.offset+s.count;
	}


/*****************************************************************************/

%}

/* This part is taken from http://www.python.org/doc/2.2.3/ref/grammar.txt */
identifier		= (({letter}|"_")({letter}|{digit}|"_")*)
letter			= ({lowercase}|{uppercase})
lowercase			= ([a-z])
uppercase			= ([A-Z])
digit			= ([0-9])
stringliteral		= ({stringprefix}?{shortstring})
stringprefix		= ("r"|"u"[rR]?|"R"|"U"[rR]?)
shortstring1		= ([\']{shortstring1item}*[\']?)
shortstring2		= ([\"]{shortstring2item}*[\"]?)
shortstring		= ({shortstring1}|{shortstring2})
shortstring1item	= ({shortstring1char}|{escapeseq})
shortstring2item	= ({shortstring2char}|{escapeseq})
shortstring1char	= ([^\\\n\'])
shortstring2char	= ([^\\\n\"])
escapeseq			= ([\\].)
longinteger		= ({integer}[lL])
integer			= ({decimalinteger}|{octinteger}|{hexinteger})
decimalinteger		= ({nonzerodigit}{digit}*|"0")
octinteger		= ("0"{octdigit}+)
hexinteger		= ("0"[xX]{hexdigit}+)
nonzerodigit		= ([1-9])
octdigit			= ([0-7])
hexdigit			= ({digit}|[a-f]|[A-F])
floatnumber		= ({pointfloat}|{exponentfloat})
pointfloat		= ({intpart}?{fraction}|{intpart}".")
exponentfloat		= (({intpart}|{pointfloat}){exponent})