/*
 * 09/03/2005
 *
 * CSSTokenMaker.java - Token maker for CSS 3 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.*;


/**
 * This class splits up text into tokens representing a CSS 3 file.  It's
 * written with a few extra internal states so that it can easily be copy
 * and pasted into HTML, PHP, and JSP TokenMakres when it is updated.<p>
 *
 * 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 CSSTokenMaker.java</code> file will contain 2
 *       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 CSSTokenMaker
%extends AbstractJFlexTokenMaker
%implements TokenMaker
%unicode
%type org.fife.ui.rsyntaxtextarea.Token


%{

	/**
	 * Internal type denoting a line ending in a CSS property.
	 */
	public static final int INTERNAL_CSS_PROPERTY			= -1;

	/**
	 * Internal type denoting a line ending in a CSS property value.
	 */
	public static final int INTERNAL_CSS_VALUE				= -2;

	/**
	 * Internal type denoting line ending in a CSS double-quote string.
	 * The state to return to is embedded in the actual end token type.
	 */
	public static final int INTERNAL_CSS_STRING				= -(1<<11);

	/**
	 * Internal type denoting line ending in a CSS single-quote string.
	 * The state to return to is embedded in the actual end token type.
	 */
	public static final int INTERNAL_CSS_CHAR				= -(2<<11);

	/**
	 * Internal type denoting line ending in a CSS multi-line comment.
	 * The state to return to is embedded in the actual end token type.
	 */
	public static final int INTERNAL_CSS_MLC				= -(3<<11);

	/**
	 * The state previous CSS-related state we were in before going into a CSS
	 * string, multi-line comment, etc.
	 */
	private int cssPrevState;


	/**
	 * Constructor.  This must be here because JFlex does not generate a
	 * no-parameter constructor.
	 */
	public CSSTokenMaker() {
		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.
	 * @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.
	 */
	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 <code>true</code> since CSS uses curly braces.
	 *
	 * @return <code>true</code> always.
	 */
	public boolean getCurlyBracesDenoteCodeBlocks() {
		return true;
	}


	/**
	 * 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;
		cssPrevState = YYINITIAL; // Shouldn't be necessary

		// Start off in the proper state.
		int state = Token.NULL;
		switch (initialTokenType) {
			case Token.LITERAL_STRING_DOUBLE_QUOTE:
				state = CSS_STRING;
				break;
			case Token.LITERAL_CHAR:
				state = CSS_CHAR_LITERAL;
				break;
			case Token.COMMENT_MULTILINE:
				state = CSS_C_STYLE_COMMENT;
				break;
			case INTERNAL_CSS_PROPERTY:
				state = CSS_PROPERTY;
				break;
			case INTERNAL_CSS_VALUE:
				state = CSS_VALUE;
				break;
			default:
				if (initialTokenType<-1024) {
					int main = -(-initialTokenType & 0xffffff00);
					switch (main) {
						default: // Should never happen
						case INTERNAL_CSS_STRING:
							state = CSS_STRING;
							break;
						case INTERNAL_CSS_CHAR:
							state = CSS_CHAR_LITERAL;
							break;
						case INTERNAL_CSS_MLC:
							state = CSS_C_STYLE_COMMENT;
							break;
					}
					cssPrevState = -initialTokenType&0xff;
				}
				else {
					state = Token.NULL;
				}
		}

		start = text.offset;
		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>.
	 */
	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;
	}


%}

Digit						= ([0-9])
Letter						= ([A-Za-z])
LetterOrUnderscore			= ({Letter}|[_])
LetterOrUnderscoreOrDash	= ({LetterOrUnderscore}|[\-])

CSS_SelectorPiece			= (("*"|"."|{LetterOrUnderscoreOrDash})({LetterOrUnderscoreOrDash}|"."|{Digit})*)
CSS_PseudoClass				= (":"("root"|"nth-child"|"nth-last-child"|"nth-of-type"|"nth-last-of-type"|"first-child"|"last-child"|"first-of-type"|"last-of-type"|"only-child"|"only-of-type"|"empty"|"link"|"visited"|"active"|"hover"|"focus"|"target"|"lang"|"enabled"|"disabled"|"checked"|":first-line"|":first-letter"|":before"|":after"|"not"))
CSS_AtKeyword				= ("@"{CSS_SelectorPiece})
CSS_Id						= ("#"{CSS_SelectorPiece})
CSS_Separator				= ([;\(\)\[\]])
WhiteSpace					= ([ \t]+)
MlcStart					= ("/*")
MlcEnd						= ("*/")

CSS_Property				= ([\*]?{LetterOrUnderscoreOrDash}({LetterOrUnderscoreOrDash}|{Digit})*)
CSS_ValueChar				= ({LetterOrUnderscoreOrDash}|[\\/])
CSS_Value					= ({CSS_ValueChar}*)
CSS_Function				= ({CSS_Value}\()
CSS_Digits					= ([\-]?{Digit}+([0-9\.]+)?(pt|pc|in|mm|cm|em|ex|px|ms|s|%)?)
CSS_Hex						= ("#"[0-9a-fA-F]+)
CSS_Number					= ({CSS_Digits}|{CSS_Hex})

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


%state CSS_PROPERTY
%state CSS_VALUE
%state CSS_STRING
%state CSS_CHAR_LITERAL
%state CSS_C_STYLE_COMMENT


%%

<YYINITIAL> {
	{CSS_SelectorPiece}	{ addToken(Token.DATA_TYPE); }
	{CSS_PseudoClass}	{ addToken(Token.RESERVED_WORD); }
	":"					{ /* Unknown pseudo class */ addToken(Token.DATA_TYPE); }
	{CSS_AtKeyword}		{ addToken(Token.REGEX); }
	{CSS_Id}			{ addToken(Token.VARIABLE); }
	"{"					{ addToken(Token.SEPARATOR); yybegin(CSS_PROPERTY); }
	[,]					{ addToken(Token.IDENTIFIER); }
	\"					{ start = zzMarkedPos-1; cssPrevState = zzLexicalState; yybegin(CSS_STRING); }
	\'					{ start = zzMarkedPos-1; cssPrevState = zzLexicalState; yybegin(CSS_CHAR_LITERAL); }
	[+>~\^$\|=]			{ addToken(Token.OPERATOR); }
	{CSS_Separator}		{ addToken(Token.SEPARATOR); }
	{WhiteSpace}		{ addToken(Token.WHITESPACE); }
	{MlcStart}			{ start = zzMarkedPos-2; cssPrevState = zzLexicalState; yybegin(CSS_C_STYLE_COMMENT); }
	.					{ /*System.out.println("yyinitial: " + yytext());*/ addToken(Token.IDENTIFIER); }
	"\n" |
	<<EOF>>				{ addNullToken(); return firstToken; }
}

<CSS_PROPERTY> {
	{CSS_Property}		{ addToken(Token.RESERVED_WORD); }
	"}"					{ addToken(Token.SEPARATOR); yybegin(YYINITIAL); }
	":"					{ addToken(Token.OPERATOR); yybegin(CSS_VALUE); }
	{WhiteSpace}		{ addToken(Token.WHITESPACE); }
	{MlcStart}			{ start = zzMarkedPos-2; cssPrevState = zzLexicalState; yybegin(CSS_C_STYLE_COMMENT); }
	.					{ /*System.out.println("css_property: " + yytext());*/ addToken(Token.IDENTIFIER); }
	"\n" |
	<<EOF>>				{ addEndToken(INTERNAL_CSS_PROPERTY); return firstToken; }
}

<CSS_VALUE> {
	{CSS_Value}			{ addToken(Token.IDENTIFIER); }
	"!important"		{ addToken(Token.ANNOTATION); }
	{CSS_Function}		{ int temp = zzMarkedPos - 2;
						  addToken(zzStartRead, temp, Token.FUNCTION);
						  addToken(zzMarkedPos-1, zzMarkedPos-1, Token.SEPARATOR);
						  zzStartRead = zzCurrentPos = zzMarkedPos;
						}
	{CSS_Number}		{ addToken(Token.LITERAL_NUMBER_DECIMAL_INT); }
	\"					{ start = zzMarkedPos-1; cssPrevState = zzLexicalState; yybegin(CSS_STRING); }
	\'					{ start = zzMarkedPos-1; cssPrevState = zzLexicalState; yybegin(CSS_CHAR_LITERAL); }
	")"					{ /* End of a function */ addToken(Token.SEPARATOR); }
	[;]					{ addToken(Token.OPERATOR); yybegin(CSS_PROPERTY); }
	[,\.]				{ addToken(Token.IDENTIFIER); }
	"}"					{ addToken(Token.SEPARATOR); yybegin(YYINITIAL); }
	{WhiteSpace}		{ addToken(Token.WHITESPACE); }
	{MlcStart}			{ start = zzMarkedPos-2; cssPrevState = zzLexicalState; yybegin(CSS_C_STYLE_COMMENT); }
	.					{ /*System.out.println("css_value: " + yytext());*/ addToken(Token.IDENTIFIER); }
	"\n" |
	<<EOF>>				{ addEndToken(INTERNAL_CSS_VALUE); return firstToken; }
}

<CSS_STRING> {
	[^\n\\\"]+			{}
	\\.?				{ /* Skip escaped chars. */ }
	\"					{ addToken(start,zzStartRead, Token.LITERAL_STRING_DOUBLE_QUOTE); yybegin(cssPrevState); }
	\n |
	<<EOF>>				{ addToken(start,zzStartRead-1, Token.LITERAL_STRING_DOUBLE_QUOTE); addEndToken(INTERNAL_CSS_STRING - cssPrevState); return firstToken; }
}

<CSS_CHAR_LITERAL> {
	[^\n\\\']+			{}
	\\.?				{ /* Skip escaped chars. */ }
	\'					{ addToken(start,zzStartRead, Token.LITERAL_CHAR); yybegin(cssPrevState); }
	\n |
	<<EOF>>				{ addToken(start,zzStartRead-1, Token.LITERAL_CHAR); addEndToken(INTERNAL_CSS_CHAR - cssPrevState); return firstToken; }
}

<CSS_C_STYLE_COMMENT> {
	[^hwf\n\*]+			{}
	{URL}				{ int temp=zzStartRead; addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addHyperlinkToken(temp,zzMarkedPos-1, Token.COMMENT_MULTILINE); start = zzMarkedPos; }
	[hwf]				{}
	{MlcEnd}			{ addToken(start,zzStartRead+1, Token.COMMENT_MULTILINE); yybegin(cssPrevState); }
	\*					{}
	\n |
	<<EOF>>				{ addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addEndToken(INTERNAL_CSS_MLC - cssPrevState); return firstToken; }
}