Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!shadooby!ginosko!usc!rutgers!att!chinet!bill
From: bill@chinet.chi.il.us (Bill Mitchell)
Newsgroups: comp.os.minix
Subject: important new program: cleanit.c
Message-ID: <9771@chinet.chi.il.us>
Date: 8 Oct 89 23:16:14 GMT
Organization: Chinet - Chicago, Ill.
Lines: 335


AST recently posted a program, cleanit.c, to strip leading junk
ahead of a shar file from a USENET posting.

Problem:  The leading junk often contains very useful info about
the shar file.

Problem:  Cleanup.c requires posters to discipine themselves to include
a "cut line" with 20 leading dashes.  Fat chance.

Problem:  Postings often include unshared C programs.

Solution:  One is needed.  My contribution below.

This is my first cut at a program, comment.c, which is intended
to comment leading junk in a posting containing a shar file or 
an unshared C program, leaving the junk intact in case it is useful.
Emphasize that this is a first cut.  It has not been used or tested
much at all.

It seems to work OK except for postings I've seen which include the
cute trailer line "#include <disclaimer.std>".  The leading '#' causes
comment.c to think a shar file is coming, and it considers all text
before the cute trailer line to be leading junk.  The moral of that
story is that it ought to be smarter about identifying shar files.
Anybody care to add the needed smarts?

/*
** comment.c - bill mitchell 07 oct 89
**
** this program reads files and tries to identify an imbedded shar file
** or c program
**
** if a shar file or c program is found, it comments out leading junk
** leaving the commented leading junk in the file for future reference
**
** it announces its conclusions about c programs and shar files on stdout
** it tries to avoid trashing the files if run multiple times
** it has options to test files without modifying them, to back out changes,
** and to force "# " shell comments onto a specified number of lines.
**
** it thinks all c programs begin with "/*"
** and shar files begin with "echo x - "
** or on the line following one or more "#" shell comment lines
**
** usage:    comment [options & filenames]
**           see the usage() function for details on the options
**
** with Microsoft C -- cl comment.c \msc5\lib\setargv /link /NOE
** under MINIX      -- cc -DMINIX -o comment comment.c
**
*/

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

#ifdef MSDOS
#include <stdlib.h>
#include <direct.h>
#include <io.h>
#endif

#ifdef MINIX
#define fputs(a, b) fputs(a, b), 0
#endif

#define NOTHING 	0
#define CPROG 		1
#define SHARFILE 	2

#define BUFSZ 256	/* longer than the longest line in a usenet article */

int Line;		/* line number starting shar file or c prog */

#ifdef MINIX
main(argc, argv)
int argc;
char **argv;
{
#else
main(int argc, char **argv) {
#endif
	FILE *fp;
	char *progname = *argv;
	char *cp;
	int tflag = 0;
	int type;

	if (--argc) {
		while(argc--) {
			cp = *++argv;
			if (!strncmp(cp, "-t", 2)) {
				if (!argc--)
					break;
				tflag = 1;
				cp = *++argv;
			}
			else if (!strncmp(cp, "-c", 2)) {
				if (!argc--)
					break;
				recomment(*++argv, atoi(cp + 2));
				continue;
			}
			if ((type = scan(cp)) != NOTHING && tflag == 0)
				comment(*argv, type);
		}
	}
	else {
		usage(progname);
	}
	exit(0);
}

#ifdef MINIX
usage(name)
char *name;
{
#else
usage(char *name) {
#endif
	printf("this program comments out junk ahead of a C program or shar file\n\n");
	printf("usage:    %s [options & filenames]\n", name);
	printf("options:  -t tests but does not modify subsequent files\n");
	printf("          -c file removes inserted comments\n");
	printf("          -clines file inserts \"# \" comments onto lines at the head of file\n");
}

#ifdef MINIX
scan(name)
char *name;
{
#else
scan(char *name) {
#endif
	FILE *fp;
	char buffer[BUFSZ];
	static char starget[] = "echo x - ";
	static int slen = sizeof(starget) -1;
	static char ctarget[] = "/*";
	static int clen = sizeof(ctarget) -1;
	int rv = NOTHING;

	if (fp = fopen(name, "r")) {
		for (Line = 1; fgets(buffer, sizeof(buffer) - 1, fp); Line++) {
			if (*buffer == '#') {
				rv = SHARFILE;
				continue;		/* Line++ while the comments last */
			}
			else if (rv == SHARFILE) {
				printf("%s contains a shar file at line %d\n", name, Line);
				break;
			}
			if (!strncmp(buffer, ctarget, clen)) {
				rv = CPROG;
				if (Line == 1)
					continue;	/* probably inserted by me - look for another */
				printf("%s contains a C comment at line %d\n", name, Line);
				break;
			}
			if (!strncmp(buffer, starget, slen)) {
				rv = SHARFILE;
				break;
			}
		}
		fclose(fp);
	}
	else
		fprintf(stderr, "unable to open file %s\n", name);
	return(rv);
}

#ifdef MINIX
comment(name, type)
char *name;
int type;
{
#else
comment(char *name, int type) {
#endif
	FILE *fp1, *fp2;
	static char template[9] = "zzXXXXXX";
	char tempname[9];
	char buffer[BUFSZ];
	int line;

	if (fp1 = fopen(name, "r")) {
		fgets(buffer, sizeof(buffer) - 1, fp1);
		if (*buffer == '#' || !strncmp(buffer, "/*", 2)) {
			fclose(fp1);	/* already commented - bail out */
			return;
		}
		strcpy(tempname, template);
		if (mktemp(tempname) == NULL) {
			fprintf(stderr, "mktemp() error\n");
			exit(1);
		}
		if ( (fp2 = fopen(tempname, "w")) == NULL) {
			fprintf(stderr, "fopen(%s, \"w\") error\n", tempname);
			exit(1);
		}
		for (line = 1; line < Line; line++) {
			if (line == 1 && type == CPROG)
					my_fputs("/*\n", fp2);
			else if (type == SHARFILE) {
				if (*buffer == '#')
					break;
				my_fputs("# ", fp2);
			}
			my_fputs(buffer, fp2);
			fgets(buffer, sizeof(buffer) - 1, fp1);
		}
		if (type == CPROG)
			my_fputs("*/\n", fp2);
		my_fputs(buffer, fp2);
		while (fgets(buffer, sizeof(buffer) - 1, fp1))
			my_fputs(buffer, fp2);
		fclose(fp1);
		fclose(fp2);
		movefile(tempname, name);
	}
	else
		fprintf(stderr, "unable to open file %s\n", name);
}

#ifdef MINIX
recomment(name, nlines)
char *name;
int nlines;
{
#else
recomment(char *name, int nlines) {
#endif
	FILE *fp1, *fp2;
	static char template[9] = "zzXXXXXX";
	char tempname[9];
	char buffer[BUFSZ];
	int line;

	if (fp1 = fopen(name, "r")) {
		strcpy(tempname, template);
		if (mktemp(tempname) == NULL) {
			fprintf(stderr, "mktemp() error\n");
			exit(1);
		}
		if ( (fp2 = fopen(tempname, "w")) == NULL) {
			fprintf(stderr, "fopen(%s, \"w\") error\n", tempname);
			exit(1);
		}
	}
	if (nlines) {
		/*  insert "# " comments onto nlines */
		for (line = 0; line < nlines; line++) {
			if (!fgets(buffer, sizeof(buffer) - 1, fp1))
				break;
			my_fputs("# ", fp2);
			my_fputs(buffer, fp2);
		}
		while (fgets(buffer, sizeof(buffer) - 1, fp1))
			my_fputs(buffer, fp2);
	}
	else {
		fgets(buffer, sizeof(buffer) - 1, fp1);
		if (!strncmp(buffer, "/*", 2)) {
			/* uncomment C comment block beginning on line 1 */
			while (fgets(buffer, sizeof(buffer) - 1, fp1)) {
				if (!strncmp(buffer, "*/", 2))
					break;
				my_fputs(buffer, fp2);
			}
			while (fgets(buffer, sizeof(buffer) - 1, fp1))
				my_fputs(buffer, fp2);
		}
		else {			
			/* strip leading "# " from all lines */
			do {
				if (!strncmp(buffer, "# ", 2))
					my_fputs(buffer + 2, fp2);
				else
					my_fputs(buffer, fp2);
			} while (fgets(buffer, sizeof(buffer) - 1, fp1));
		}
	}
	fclose(fp1);
	fclose(fp2);
	movefile(tempname, name);
}

#ifdef MINIX
movefile(from, to)
char *from, *to;
{
#else
movefile (char *from, char *to) {
#endif
	if (remove(to)) {
		fprintf(stderr, "problem with remove(\"%s\")\n", to);
		exit(1);
	}									
	else if (rename(from, to)) {
		fprintf(stderr, "problem with rename(\"%s\", \"%s\")\n", from, to);
		exit(1);
	}									
}		

#ifdef MINIX
my_fputs(cp, fp)
char *cp;
FILE *fp;
{
#else
my_fputs(char *cp, FILE *fp) {
#endif
	if (fputs(cp, fp)) {
		fprintf(stderr, "fputs() error\n");
		exit(1);
	}
}

#ifdef MINIX
rename(old, new)
char *old, *new;
{
	if (link(old, new) < 0)
		fprintf(stderr, "problem with link(\"%s\", \"%s\")\n", old, new);
	else
		unlink(old);
}

remove(old)
char *old;
{
	unlink(old);
}
#endif