PPT Slide

import java_cup.runtime.*;

%class lex

%cup

%standalone

%unicode

LineTerminator = \r|\n|\r\n

XML_Declaration = "<?xml version="[\"']"1.0"[\"'][^\r\n]*"?>"{LineTerminator}

DOCTYPE_Declaration = "<!DOCTYPE "[^\r\n<>]+">"{LineTerminator}

Name = [^</>]+

StartTag = "<"{Name}">"

EndTag = "</"{Name}">"

PCDATA = [a-zA-Z0-9;& ,._\n\r\t-]+

Whitespace = [\n\r\t ]+

{XML_Declaration} { return new Symbol(sym.XML_DECLARATION, yytext()); }

{DOCTYPE_Declaration} { return new Symbol(sym.DOCTYPE_DECLARATION, yytext()); }

{StartTag} { return new Symbol(sym.START_TAG, yytext()); }

{EndTag} { return new Symbol(sym.END_TAG, yytext()); }

{Whitespace} { ; } /* Drop whitespace */

{PCDATA} { return new Symbol(sym.PCDATA, yytext()); }

<<EOF>> { return new Symbol(sym.EOF); }

mylexer.flex

See example20