htmltokenmaker.flex

具有不同语法高亮的编辑器实例

/*
 * 01/24/2005
 *
 * HTMLTokenMaker.java - Generates tokens for HTML syntax highlighting.
 * 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.*;


/**
 * Scanner for HTML 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 HTMLTokenMaker.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 0.4
 *
 */
%%

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


%{

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

	/**
	 * Token type specific to HTMLTokenMaker; this signals that the user has
	 * ended a line with an unclosed <code>&lt;script&gt;</code> tag.
	 */
	public static final int INTERNAL_INTAG_SCRIPT			= -2;

	/**
	 * Token type specifying we're in JavaScript.
	 */
	public static final int INTERNAL_IN_JS					= -3;

	/**
	 * Token type specifying we're in a JavaScript multiline comment.
	 */
	public static final int INTERNAL_IN_JS_MLC				= -4;


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


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


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


	/**
	 * Adds the token specified to the current linked list of tokens as an
	 * "end token;" that is, at <code>zzMarkedPos</code>.
	 *
	 * @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.
	 */
	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.COMMENT_MULTILINE:
				state = COMMENT;
				start = text.offset;
				break;
			case Token.PREPROCESSOR:
				state = PI;
				start = text.offset;
				break;
			case Token.VARIABLE:
				state = DTD;
				start = text.offset;
				break;
			case INTERNAL_INTAG:
				state = INTAG;
				start = text.offset;
				break;
			case INTERNAL_INTAG_SCRIPT:
				state = INTAG_SCRIPT;
				start = text.offset;
				break;
			case INTERNAL_IN_JS:
				state = JAVASCRIPT;
				start = text.offset;
				break;
			case INTERNAL_IN_JS_MLC:
				state = JS_MLC;
				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();
		}

	}


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


	/**
	 * 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;
	}


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


	/**
	 * 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;
	}


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

%}

// HTML-specific stuff.
Whitespace			= ([ \t\f])
LineTerminator			= ([\n])
Identifier			= ([^ \t\n<&]+)
AmperItem				= ([&][A-Za-z]*[;]?)
InTagIdentifier		= ([^ \t\n\"\'/=>]+)
UnclosedStringLiteral	= ([\"][^\"]*)
StringLiteral			= ({UnclosedStringLiteral}[\"])
UnclosedCharLiteral		= ([\'][^\']*)
CharLiteral			= ({UnclosedCharLiteral}[\'])
EndScriptTag			= ("</script>")


// JavaScript stuff.
Letter							= [A-Za-z]
NonzeroDigit						= [1-9]
Digit							= ("0"|{NonzeroDigit})
HexDigit							= ({Digit}|[A-Fa-f])
OctalDigit						= ([0-7])
AnyCharacterButApostropheOrBackSlash	= ([^\\'])
AnyCharacterButDoubleQuoteOrBackSlash	= ([^\\\"\n])
EscapedSourceCharacter				= ("u"{HexDigit}{HexDigit}{HexDigit}{HexDigit})
Escape							= ("\\"(([btnfr\"'\\])|([0123]{OctalDigit}?{OctalDigit}?)|({OctalDigit}{OctalDigit}?)|{EscapedSourceCharacter}))
NonSeparator						= ([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\']|"#"|"\\")
IdentifierStart					= ({Letter}|"_"|"$")
IdentifierPart						= ({IdentifierStart}|{Digit}|("\\"{EscapedSourceCharacter}))
JS_UnclosedCharLiteral		= ("'"({AnyCharacterButApostropheOrBackSlash}|{Escape}))
JS_CharLiteral				= ({JS_UnclosedCharLiteral}"'")
JS_UnclosedErrorCharLiteral	= ([\'][^\'\n]*)
JS_ErrorCharLiteral			= (([\'][\'])|{JS_UnclosedErrorCharLiteral}[\'])
JS_UnclosedStringLiteral		= ([\"]({AnyCharacterButDoubleQuoteOrBackSlash}|{Escape})*)
JS_StringLiteral			= ({JS_UnclosedStringLiteral}[\"])
JS_UnclosedErrorStringLiteral	= ([\"]([^\"\n]|"\\\"")*)
JS_ErrorStringLiteral		= ({JS_UnclosedErrorStringLiteral}[\"])
JS_MLCBegin				= "/*"
JS_MLCEnd					= "*/"
JS_LineCommentBegin			= "//"
JS_IntegerHelper1			= (({NonzeroDigit}{Digit}*)|"0")
JS_IntegerHelper2			= ("0"(([xX]{HexDigit}+)|({OctalDigit}*)))
JS_IntegerLiteral			= ({JS_IntegerHelper1}[lL]?)
JS_HexLiteral				= ({JS_IntegerHelper2}[lL]?)
JS_FloatHelper1			= ([fFdD]?)