%{
/*
 * This is part of the definitions section.  It starts with %{ and ends with %}.
 * Any text placed in this area will be copied verbatim into the lex.yy.c
 * output file that lex generates, and will be placed near the top of that file.
 *
 * Typically this section is used to #include header files that will be needed
 * in the generated scanner, but any legal C code can be placed here.  This
 * scanner does not need any extra header files, so we don't #include any here.
 *
 * Please see https://en.wikipedia.org/wiki/Lex_(software) for further details.
 */
%}
    /*
     * This is also part of the definitions section. Anything after the %} above
     * until the %% below is interpreted by lex as formal definitions.  Things
     * here won't be copied verbatim into the generated lex.yy.c output file,
     * but will be analyzed by lex.  Some definitions have been placed below.
     * You may add more definitons here.  You may also add comments, but they
     * must be indented because anything that appears in the leftmost column
     * is considered the start of a formal definition.
     */
DIGIT    [0-9]
HEXD     [A-Fa-f]
ID       [a-z][_a-z0-9]*
NUMLIT   [0-9][0-9a-fA-F_.#]*
%%
    /*
     * This is the rules section.  It starts with the %% above and continues
     * until the %% down below.  This section contains rules that are analyzed
     * by lex.  Each rule is composed of a pattern and an action. The pattern
     * of a rule uses UNIX-ish regular expressions to indicate what the lexeme
     * "looks like", and the action of a rule specifies what is to be done when
     * a lexeme matching the pattern is encountered.  The pattern and the action
     * of a rule are separated by whitespace.  Patterns of a rule can be chained
     * together using the | operator so that any lexeme matching any of the
     * chained patterns will provoke the action associated with that rule. An
     * example of this appears in the "keyword" rule below.
     *
     * You may also place comments here, but they also must be indented because
     * anything that appears in the leftmost column is considered the start of
     * the pattern of a rule by lex.
     *
     * Please see https://en.wikipedia.org/wiki/Lex_(software) for further details.
     */
{NUMLIT} { printf("%s (num-lit)\n", yytext); }

begin |
end |
function |
if | 
interface |
module |
procedure |
then {
    /* The action to be taken when we encounter a keyword */
    printf("%s (keyword)\n", yytext );
    }
     
{ID}        printf("%s (identifier)\n", yytext);
     
"+"|";"|"-"|"*"|"/"   printf("%s (operator)\n", yytext);
     
[ \t\n]+          /* discard whitespace */
     
.           printf("Unrecognized character: %s\n", yytext);
     
%%
/*
 * This section is the user subroutines section.  It starts after the %% above
 * and continues to the end of the file. Anything appearing in the section is
 * copied verbatim into the lex.yy.c file generated by lex, and will appear
 * toward the bottom of that file.
 *
 * This section is where subroutines specific to a given scanner are placed.
 * Any legal C code can be placed here.
 *
 * The scanner for this application is not intended to be used by yacc, so
 * here we define a main function that will "drive" the lexer.
 */
int main(int argc, char **argv)
{
    if (argc > 1)
        yyin = fopen(argv[1], "r");
    else
        yyin = stdin;
     
    yylex();
}

/*
 * This defines yywrap, a special function used by lex to determine what should
 * be done when the end of an input file is encountered.  You can read more
 * about this at http://flex.sourceforge.net.
 */
int yywrap()
{
    return 1;
}