Example Lexical Analyzer
This is an example of a Flex scanner for the instructional programming language PL/0.
The tokens recognized are: '+', '-', '*', '/', '=', '(', ')', ',', ';', '.', ':=', '<', '<=', '<>', '>', '>='; numbers: 0-9 {0-9}; identifiers: a-zA-Z {a-zA-Z0-9} and keywords: begin, call, const, do, end, if, odd, procedure, then, var, while.
%{
#include "y.tab.h"
%}
digit
letter
%%
"+" { return PLUS; }
"-" { return MINUS; }
"*" { return TIMES; }
"/" { return SLASH; }
"(" { return LPAREN; }
")" { return RPAREN; }
";" { return SEMICOLON; }
"," { return COMMA; }
"." { return PERIOD; }
":=" { return BECOMES; }
"=" { return EQL; }
"<>" { return NEQ; }
"<" { return LSS; }
">" { return GTR; }
"<=" { return LEQ; }
">=" { return GEQ; }
"begin" { return BEGINSYM; }
"call" { return CALLSYM; }
"const" { return CONSTSYM; }
"do" { return DOSYM; }
"end" { return ENDSYM; }
"if" { return IFSYM; }
"odd" { return ODDSYM; }
"procedure" { return PROCSYM; }
"then" { return THENSYM; }
"var" { return VARSYM; }
"while" { return WHILESYM; }
{letter}({letter}|{digit})* { yylval.id = strdup(yytext); return IDENT; }
{digit}+ { yylval.num = atoi(yytext); return NUMBER; } /* skip whitespace */
. { printf("Unknown character \n",yytext); return UNKNOWN; }
%%
int yywrap(void){return 1;}
The hand-written C code equivalent would likely be at least twice as many lines, and considerably harder to read.