%s

%{ /* George Ruban 9-14-95 gmn@cs.bu.edu 2html.lex: Lex program for HTML production. Parses input, puts hotlinks around href'erences, mailto:'s around email addresses, coats w/ begin/end html's. Remember (1) to put paren's around all expressions (2) to avoid in-expression spaces. To make: lex 2html.lex cc -o 2html lex.yy.c -ll To run, for ASCII tab/space formatted text: 2html < inputfile > outputfile.html or 2html inputfile outputfile.html 9-15-95: Modified to give a Title, and

 tags.
  9-25-95: Modified after Jonathan Sari 
  to "turn --- and ==='s three long or longer into
  
's and \n\n or longer into 's."
  10-25-95: Modified to insert time of creation into document,
  separate printf's rather than string concatenation - cc can't take it,
  treat \n\r as 1 newline, not 2.  Option to not format text failed.
  10-26-95: Modified to optionally take input & output on command line,
  since VMS/VAX allegedly doesn't have easy i/o redirection.
  10-30-95: Modified to include news: around newsgroups.
  3-20-97: Modified to replace <, >, &, with < >, &.
*/
#include  /* for printf() */
#include /* for getenv() */
#include /* for strlen() */
#include   /* for ctime() */
%}
alpha     ([a-zA-Z])
sym       ([\_\-\~\%\+\'\!])
num       ([0-9])
ws        ([ \t])
nl        ([\n\r])
para      ((\n\n+)|(\r\r+)|(\n\r{nl}+)|(\r\n{nl}+))
alphanum  ({alpha}|{num}|{sym})
dash      ([-=_])
dashlin   (({nl}|{para}){ws}*{dash}+{ws}*({nl}|{para}))

word      ({alphanum}+(\.{alphanum}+)*)
server    ({word}(:{num}+)?)
path      ((\/{word})*\/?)

email     ({word}\@{server})
href      ({alpha}+:\/\/{server}{path})
news      ({alpha}{3,10}(\.[A-Za-z\-\_]+)+)

%%
{news}    { if(!strncmp(yytext, "rec.", 4) || !strncmp(yytext, "news.", 5) ||
	       !strncmp(yytext, "alt.", 4) || !strncmp(yytext, "misc.", 5) ||
	       !strncmp(yytext, "soc.", 4) || !strncmp(yytext, "talk.", 5) ||
	       !strncmp(yytext, "comp.", 5) || !strncmp(yytext, "clari.", 6) ||
	       !strncmp(yytext, "humanities.", 11) || 
	       !strncmp(yytext, "biz.", 4)){
              fprintf(yyout, "%s", yytext, yytext); 
	    } else ECHO;
	  }
{para}    { fprintf(yyout, "\n
\n"); }
{dashlin} { fprintf(yyout, "\n
\n"); }
{href}    { fprintf(yyout, "%s", yytext, yytext); }
{email}   { fprintf(yyout, "%s", yytext, yytext); }
\<        { fprintf(yyout, "<"); } 
\>        { fprintf(yyout, ">"); } 
\&        { fprintf(yyout, "&"); } 
.|\n      { ECHO; }
%%

main(argc, argv)
int argc;
char *argv[];
{
  char title[255];
  time_t now;    /* time of running */

  if(argc > 1) { /* arguments are considered to be in and out file */
    if(argc != 3){
      fprintf(stderr, "Usage: %s [inputfile outputfile]\n", argv[0]);
      fprintf(stderr, "Converts a text file to HTML, hotlinks links.\n");
      fprintf(stderr, "If files unspecified, reads stdin, writes stdout.\n");
      fprintf(stderr, "George Ruban 03-20-97, gmn@cs.bu.edu.\n");
      exit(1);
    }
    yyin = fopen(argv[1], "r");
    if(yyin==0){
      fprintf(stderr, "Error: Could not open \"%s\" for reading.\n", argv[1]);
      exit(1);
    }
    yyout = fopen(argv[2], "w");
    if(yyout==0){
      fprintf(stderr, "Error: Could not open \"%s\" for writing.\n", argv[2]);
      exit(1);
    }
  }
  fprintf(yyout, "\n\n");
  fgets(title, 255, yyin);
  if(strlen(title) > 1){ /* title more than just a blank line */
    fprintf(yyout, "%s\n", title);
    fprintf(yyout, "\n%s\n", title); 
  } else {
    fprintf(yyout, "\n"); 
  }
  fprintf(yyout, "\n\n");
  yylex();  /* do the parsing */
  fprintf(yyout, "\n\n");
  fprintf(yyout, "\n");
  time(&now);
  fprintf(yyout, "\n");
  fprintf(yyout, "Document created %s\n", ctime(&now));
  fprintf(yyout, "\n\n");
  return 0;
}