/*
 * (c) 2007 Steve Parker http://steve-parker.org/
 * GPLv2
 *
 * Attempt to retrieve the **TEXT** from a Microsoft Publisher document.
 * This will not deal with any formatting. I just want the text.
 *
 * It seems (April 2007) that there is no current tool to read MS Publisher (.pub) 
 * files, other than MS Publisher itself, on any platform - Win, Mac, Linux, etc.
 * This tool certainly doesn't allow you to edit a MS Publisher file, but
 * it attempts to get some content out of it, in text form.
 * Due to a lack of documentation about the file format, and this being
 * an initial release after only an hour or so of reverse-engineering,
 * this tool gathers (hopefully) all of the text in the document, plus
 * other text which is not (or should not) be contained in the file.
 *
 * This tool has been written upon the basis of one PUB file (v3.0), and
 * the output of "od -c" on that file. It helps that I had some idea about
 * the content of the file. YMMV.
 *
 * Much of the output from this tool is useless; it errs on the side of caution.
 * It appears that there are flags within the PUB file to mark the start of
 * the content (and possibly also the end of the content). This warrants
 * further investigation.
*/

#include <stdio.h>
#include <string.h>

/*
 * Strings are of the form char \0 char \0 char \0 char \0 :
 * 
 * 0550660      \0      \0      \0   A  \0   c  \0   t  \0   i  \0   v  \0
 * 0550700   i  \0   t  \0   y  \0      \0   b  \0   a  \0   g  \0   s  \0
 * 
 * This says "  Activity bags"
 */


/* I don't want multiple spaces / linebreaks. */
#define MAXSPACES 2
#define MAXNEWLINES 2

void readstrings(FILE *f)
{
  int prev=0;
  int c=0;
  int i=0;
  int runofnewlines=0;
  int runofspaces=0;

  while ((c=fgetc(f))!=EOF) {
	  i++;
	  if (c==0) {
		  if (  ((prev>31) && (prev<127))  || (prev=='\t') ) {
			  if ((prev!=32) || (runofspaces<MAXSPACES)) {
			    printf("%c", prev);
			    runofnewlines=0;
			    runofspaces=0;
			  }
			  if (prev==32) runofspaces++;
		  }
		  // But if it's a \r, we'll do a "dos2unix", and limit the number of CRLFs at the same time.
		  else if ((prev=='\r')) { 
			  if (runofnewlines<MAXNEWLINES) printf("\n");  
			  runofnewlines++;
		  } else {
			  runofnewlines=0;
		  }
		  if (prev==' ') runofspaces++;
	  }
	  prev=c;
  }
  printf("\n\n\nDone ... %d characters read.\n", i);
}

int main(int argc, char *argv[])
{
	FILE *pub;
	char *filename;

	if (argc==2) filename=argv[1];
	else filename=strdup("NoticeSheet.pub");

	pub=fopen(filename, "r");
	if (pub) {
	  readstrings(pub);
	  fclose(pub);
	} else {
		fprintf(stderr, "Error: Cannot open file '%s'.\n", filename);
	}
	
	return 0;
}