/** 
 * Stephanie Taylor
 * Spring 2026
 * CS333
 *
 * Read one line at a time from the command line and identify patterns
 * This intends to demo all of the special characters listed in the notes.
 * 
 * flex -o demo_special_characters.yy.c demo_special_characters.yy
 * gcc -o demo_special_characters demo_special_characters.yy.c -ll
 
 []: used to specify a set of single character alternatives (different from EBNF)
    [AEIOU]: one uppercase vowel
    T[ao]p: tap, top
    [0-9]: you can use ranges

  \: used as an escape character to permit use of other special character
    \s: whitespace
    Write a regex to match all CS courses. [CS\s[0-9][0-9][0-9] matches CS XXX]
    Note that \d is available in egrep, and it matches a single digit 
    \ can also be used to escape the meaning of a special character. E.g. if you want to look for the literal character “[“, then use \[. If your string is “[hi]”, you can match it with “\[..\]”, but not “[..]”.

  . : matches almost any character except line breaks 
    a.e: water, ate, gate 
    
  * : match the prior expression zero or more times
    \. : decimal point
    Write a regex to match floating point values with one digit after the decimal points. [\d*\.\d: .3, 12.5, 139.9]

  - : range indicator 
        [a-z]: one lowercase letter from a to z 
        
  ^: negates an expression when inside brackets, permits you to specify strings that don’t include a certain expression, or is the start of the string otherwise
    [^0-9]: matches any character that is not a digit 
    ^a:  matches strings start with a

  $: the end of the string 
    the end$: this is the end 
    Write a regex that can match any number between 1000 and 9999. 
    ^[1-9][0-9][0-9][0-9]$
    create a text.txt with following numbers, one on each line, 1231  21  5  57  0101  100001  1000a; key in the command egrep “^[1-9][0-9][0-9][0-9]$” text.txt; this command returns the matches in text.txt. 

  () : group tokens (different from EBNF)
    th(e|is) : the, this 

  + : match the prior expression one or more times 
    html tags: <html> </html>, <h1></h1>, <div id=“block1”></div>
    <[A-Za-z][A-Za-z0-9]*>: matches HTML tags without any attributes 
    <[A-Za-z0-9]+>: matches HTML tags without any attributes, but can have invalid tag like <1>
    <[^< >]+> : matches HTML tags without regard to attributes

  {min, max} : specify how many times a token can be repeated, min >=0 minimum number of matches, max >= min maximum number of matches. If {min, } the maximum number of matches is infinite. {min} repeat exactly min times. 
    {0, } same as *, {1, } same as + 
    ^[1-9][0-9]{3}$: matches a number between 1000 and 9999  
    ^[1-9][0-9]{2,4}$: matches a number between 100 and 99999

  ? : once or none

*/

DIGIT   [0-9]

%%

end$                                 printf( "Found end ending: %s\n", yytext );
earth(Inner|Middle)earth    printf( "Found inner or middle earth: %s\n", yytext );
[AEIOU]?                          printf( "Found 0 or 1 uppercase vowel: %s\n", yytext );
^[1-9][0-9]{3}$               printf( "found a number between 1000 and 9999: %s\n", yytext );
{DIGIT}+                         printf( "found a sequence of one or more decimal digits: %s\n", yytext );
\.                                     printf( "found a dot: %s\n", yytext );
.                                      printf( "found any character: %s\n", yytext );

%%

int main( int argc, char *argv[] ) {
		        
    yylex(); // a function of flex that read input till it is exhausted
        
    return 0;
}