我正在使用jflex和cup,尝试制作一个HTML解析器, 但无法使其正常工作,
Netbeans,编译过程不停,始终如一, 无法在解析树中正确添加更多“标记”, 也无法在“TEXTO”中添加空间,这会破坏整个树
lexicoh.jlex
package compiladorhtml;
import java_cup.runtime.*;
%%
%class Lexer
%line
%column
%cup
%{
private Symbol symbol(int type) {
return new Symbol(type, yyline, yycolumn);
}
private Symbol symbol(int type, Object value) {
return new Symbol(type, yyline, yycolumn, value);
}
%}
LineTerminator = \r|\n|\r\n
WhiteSpace = {LineTerminator} | [ \t\f]
texto = [a-zA-Z0-9_]*
%%
<YYINITIAL> {
"::" { System.out.print("<"); return symbol(sym.INI);}
"ENCA" { System.out.print("HEAD>"); return symbol(sym.HEAD);}
"/" { System.out.print("</"); return symbol(sym.FIN);}
{texto} { System.out.print(yytext()); return symbol(sym.TEXTO);}
{WhiteSpace} { /* just skip what was found, do nothing */ }
"&&" { System.out.print(""); return symbol(sym.FINAL); }
}
[^] { throw new Error("Illegal character <"+yytext()+">"); }
sintaticoh.cup
package compiladorhtml;
import java_cup.runtime.*;
parser code {:
public void report_error(String message, Object info) {
StringBuilder m = new StringBuilder("Error");
if (info instanceof java_cup.runtime.Symbol) {
java_cup.runtime.Symbol s = ((java_cup.runtime.Symbol) info);
if (s.left >= 0) {
m.append(" in line "+(s.left+1));
if (s.right >= 0)
m.append(", column "+(s.right+1));
}
}
m.append(" : "+message);
System.err.println(m);
}
public void report_fatal_error(String message, Object info) {
report_error(message, info);
System.exit(1);
}
:};
terminal INI, HEAD, TEXTO, FIN, FINAL;
non terminal Object expr_list, expr_part;
non terminal String expr;
expr_list ::= expr_list expr_part | expr_part;
expr_part ::= expr:e;
expr ::= INI HEAD
| TEXTO
| FIN HEAD
| FINAL;
java Main
public static void main(String[] args) throws IOException, Exception {
//CreateFiles();
//EJECUTAR PARA VER SI FUNCIONA, YA LO VI Y FUNCIONA
File fichero = new File("fichero.txt");
PrintWriter writer;
try {
writer = new PrintWriter(fichero);
writer.print("::ENCA NOMBRE ENCABEZADO /ENCA &&");
writer.close();
} catch (FileNotFoundException ex) {
System.out.println(ex);
}
Lexer thisscanner = new Lexer(new FileReader("fichero.txt"));
parser thisparser = new parser(thisscanner);
thisparser.parse();
}
public static void CreateFiles() {
String filelex = "path\\lexicoh.jlex";
File file = new File(filelex);
jflex.Main.generate(file);
String opciones[] = new String[5];
opciones[0] = "-destdir";
opciones[1] = "path";
opciones[2] = "-parser";
opciones[3] = "parser";
opciones[4] = "path\\sintacticoh.cup";
try {
java_cup.Main.main(opciones);
} catch (Exception ex) {
Logger.getLogger(CompiladorHTML.class.getName()).log(Level.SEVERE, null, ex);
}
}
感谢
答案 0 :(得分:1)
我认为你应该这样做:
对于{texto},因为它是由文本和数字组成的字符串,所以您应该以这种方式重新定义它:
{texto} { System.out.println (yytext()); return new symbol(sym.TEXTO, new String (yytext())); }
然后,如果程序没有停止,则在读取源文件时可能会出现一些问题。