/*
 * 			m c . c
 *
 * Multi-column filter
 *
 */

/*)BUILD
	$(TKBOPTIONS) = {
		TASK	=	...MCX
		UNITS	=	10
		ACTFIL	=	10
	}
*/

#ifdef	DOCUMENTATION

title	mc	Convert One or More Files To Multi-column Format
index		Convert a file to multi-column format
index		Combine files in multi-column format

Synopsis

	mc [-t] [-c columns] [-h height] [-g gutter] [-w width]
		[filespec | aliasspec]...

Description

	mc reads one or more files and converts them to a single multi-column
	file that it writes to the standard output.

	Each line of each input file will occupy one row-column position in
	the output file.  If an item is too wide for its column, it is
	truncated with no message.  The items from any one file are placed in
	order going down a column, and then across columns.  Thus, consider a
	simple case first:

	.tp 11
		mc a -c 2 -h 10

	produces a file whose first page looks like this:

		a1		a11
		a2		a12
		:		:
		:		:
		a10		a20

	("-c 2" requests two columns; "-h 10" requests ten lines per page).

File Specifications

	The mc command line may contain more than one file specification;
	however, the specifications may not be wild-carded.

	When there are multiple files, each column will come from a single
	file:

	.tp 9
		mc a b -c 2 -h 10

	produces:

		a1	b1
		a2	b2
		:	:
		:	:
		a10	b10

	Columns are filled by consecutive files, in rotating order:

	.tp 9
		mc a b -c 4 -h 10

	produces:

		a1	b1	a11	b11
		a2	b2	a12	b12
		:	:	:	:
		:	:	:	:
		a10	b10	a20	b20

	If there is more than one file, and the number of columns does not
	evenly divide the number of files, successive pages will be different.

	If a file reaches EOF while there is still data to be read from other
	files, the ended file's columns will be blank from that point on.

	The use of "-" as a file specification causes the standard input to
	be read.  If mc is invoked with no file arguments at all, it reads
	the standard input file once.

Alias Specifications

	Alias specifications provide a method for controlling the placement
	of file data.  An alias specification is a reference to another file
	(or alias) specification.  File and alias specifications are numbered,
	starting at one for the left-most such specification; switches and
	their arguments do not affect the numbering.  The alias specification
	#n indicates that the n'th specification is to be repeated.  Such a
	specification is legal only if it refers to an earlier specification;
	i.e. #n is only legal as the n+1'st, n+2'nd, etc. specification.
	Thus:

	.tp 9
		mc a #1 b #3 -c 4 -h 10

	produces:

		a1	a11	b1	b11
		a2	a12	b2	b12
		:	:	:	:
		:	:	:	:
		a10	a20	b10	b20

	This should be compared with:

		mc a a b b -c 4 -h 10

	which opens each of a and b twice and reads the copies in parallel,
	placing two copies of each item on the page.

Last-page Handling

	mc will attempt to make the columns on the last page of output as
	close in length as possible, rather than simply filling some columns
	all the way to the bottom and leaving others empty.  This special
	handling is enabled only when mc is given no more than one file
	specification.

Switches

	The following switches are available:
	.lm +8;

 -c	Next argument is the number of columns
 -h	Next argument is the height, in lines, of a page
 -g	Next argument is the gutter width (the space between columns)
 -w	Next argument is the width, in characters, of a page
 -t	Terminal mode; sets default height to 23, default width to 80, and, if
	stdout is your terminal, pauses after each page
 -d	Debug (conditionally-compiled code)

	.lm -8;

Defaults

	Height 58, width 132, no terminal mode; note that -t alters all three.
	Gutter 1, max(number-of-file-and-alias-specs,2) columns.

Control Character Handling

	mc is designed to operate on text files, not binary files.  It sets
	columns up based on how they will look when displayed.  Hence, it
	processes control characters (anything that isprint() returns FALSE
	to) as follows:

		<TAB> ("\t") is expanded into the equivalent number of spaces.
		mc always assumes that there are tab stops every 8 character
		positions.

		<BS> ("\b") subtracts one from the current cursor position.
		Any printable characters received when the current cursor
		position is over a previously read character is ignored -
		i.e. overstruck combinations retain only the first character
		read.  However, if the character being overstruck is a space
		or an underscore ("_"), the overstriking character replaces
		the current character.

		<BS> when the current cursor position is over the first
		character in the line is ignored.

		<CR> ("\r") resets the current cursor position to the first
		character of the line.

		<LF> ("\n") ends the current input item.

		All other control characters are discarded.

File Limits

	Different systems impose different limits on the number of files
	mc may simultaneously have open.

	On RT-based systems, this limit is totally dynamic; opening too many
	files is most likely to cause an error due to insufficient memory,
	rather than a file system error per se.

	On RSX-based systems, the absolute limit is set at task-build time.
	The distributed source, when built with BUILD, will allow for 10
	open files.  Note that this total includes at least one file for
	stdin and stdout (two if either is redirected).  Of course, it is
	possible to run into memory limitations even under this limit.

	Aliases do not count against this limit, since they refer to
	already-opened files.  Similarly, a "-" argument, implying stdin,
	does not count, as it is simply a reference to the already-open
	standard input.  If you are right at the limit, be sure to use
	the standard input as one of your files; you are paying for it
	to be open whether you use it or not.

	mc itself imposes another limit, which does include aliases.  In the
	distributed code, this limit is set to a total of 20 file and alias
	arguments.

Other Limits

	No column can contain more than 256 characters (compile-time
	constant).

Diagnostics

	Insufficient memory - sorry

	Too many file and alias arguments

	.tp 2
	Unreasonable -c/-g/-w combination
		-- for example, c > w

	.tp 2
	<value>: Bad <what> specification
		-- Invalid value for something like -h

	<filespec>: Can't open: <why>

Suggested Improvements

	Anyone interested in improving this program might want to consider
	the following suggestions.  Be warned that they are not as easy to
	implement as they look!

	Make the last-page cleanup algorithm work for the multiple-files case.

	Add the ability to fold long items to the next entry for this file
	(probably indented) rather than just chopping them off.  (This only
	gets hard when you consider both overstrike handling and multiple
	files!)

	Allow the automatic printing of the file name above the appropriate
	columns at the top of each page.

	The techniques used are wasteful of space; in particular, the
	gutters should not be taking up space in the data array!

Bugs

Author

	Original author unknown; extensively modified by Jerry Leichter

#endif

/*
)EDITLEVEL=40
 * Edit history
 * 0.0 ??-???-?? ???	Original implementation distributed with DECUS C.
 * 1.0 19-May-81 JSL	Extensive reorganization; added -t option, balancing
 *			of columns on final page.  Bugfix:  Don't put out a
 *			blank initial item.
 * 2.0 20-Jul-82 JSL	Converted to tool standards.
 * 2.1 23-Jul-82 JSL	Added -g switch.
 * 2.2 27-Jul-82 JSL	Added multiple-file handling.
 * 2.3  1-Aug-82 JSL	Redid overstrike handling; much more extensive error
 *			and bounds checks; debug conditionally compiled.
 * 2.4 ??-Aug-82  MM	Change default page height to 60
 * 2.5 23-Sep-82 JSL	Added conditional code for VAX-11 C
 */

char	*documentation[] = {
"	mc [-t] [-c columns] [-h height] [-g gutter] [-w width]",
"		[filespec | aliasspec]...",
"",
"mc reads one or more files and converts them to a single multi-column file",
"that it writes to the standard output.	",
"",
"The mc command line may contain more than one file specification; however,",
"the specifications may not be wild-carded.",
"",
"Each line of each input file will occupy one row-column position in the output",
"file.  If an item is too wide for its column, it is truncated with no message.",
"",
"The items from any one file are placed in order going down a column, and then",
"across columns.  Columns are filled by consecutive files, in rotating order.",
"",
"The use of \"-\" as a file specification causes the standard input to be read.",
"If mc is invoked with no file arguments at all, it reads the standard input",
"file once.",
"",
"Alias specifications provide a method for controlling the placement of file",
"data.  An alias specification is a reference to another file (or alias)",
"specification.  File and alias specifications are numbered, starting at one",
"for the left-most such specification; switches and their arguments do not",
"affect the numbering.  The alias specification #n indicates that the n'th",
"specification is to be repeated.  Such a specification is legal only if it",
"refers to an earlier specification; i.e. #n is only legal as the n+1'st,",
"n+2'nd, etc. specification.",
"",
"mc will attempt to make the columns on the last page of output as close in",
"length as possible, rather than simply filling some columns all the way to",
"the bottom and leaving others empty.  This special handling is enabled only",
"when mc is given no more than one file specification.",
"",
"The following switches are available:",
"	",
" -c	Next argument is the number of columns",
" -h	Next argument is the height, in lines, of a page",
" -g	Next argument is the gutter width (the space between columns)",
" -w	Next argument is the width, in characters, of a page",
" -t	Terminal mode; sets default height to 23, default width to 80,",
"	and, if stdout is your terminal, pauses after each page",
"",
"The default values are:",
"",
"	Height 58, width 132, no terminal mode; note that -t alters all three.",
"	Gutter 1, max(number-of-file-and-alias-specs,2) columns.",
0 };

#ifdef vax11c
#include ctype.h
#include stdio.h
#define exits(x)	exit(x)
#define IO_ERROR	2
#define FALSE		0
#define TRUE		1
#define EOS		0
#else
#include <stdio.h>
#endif

/*
 * Turn on to include debugging code
 */
/* #define DEBUG */

#define	LINEMAX	256			/* Maximum line length handled	*/
					/*  (also maximum column width)	*/
#define	NFILES	20			/* Maximum files (including	*/
					/*  aliased files)		*/
#define	ALIAS	'#'			/* Marks an alias argument	*/
					/*  (Can't be "-")		*/
#ifdef DEBUG
int	debug	= 0;
#endif
int	columns	= -1;			/* All these will be given	*/
int	gutter	= -1;			/*  default values later unless	*/
int	height	= -1;			/*  the user sets them first	*/
int	width	= -1;			/*  (to a positive value!)	*/

int	pause	= FALSE;		/* Pause-at-end of page flag	*/
int	first	= TRUE;			/* First-time-through flag	*/
int	cwidth;				/* Total (column+gutter) width	*/
int	pagesize;			/* Total bytes in page		*/
int	nf;				/* Number of file & alias specs	*/
int	files	= 0;			/* Number of files still open	*/
int	aliases	= 0;			/* Number of alias specs	*/

FILE	*file[NFILES];			/* File pointers for our files	*/
char	line[LINEMAX];			/* Input line buffer		*/
int	linelen;			/* Length of a line in line[]	*/
int	lineend;			/* Last usable line[] position	*/
char	*page;				/* -> page paste-up matrix	*/

main(argc,argv)
int argc;
char *argv[];
{	register char *p;
	register int c,i;
	int n;
	FILE *fp;

	if (argc == 2 && argv[1][0] == '?' && strlen(argv[1]) == 1)
	{	help();
		return;
	}

	nf = argc - 1;
	for (i = 1; i < argc; i++) {
		p = argv[i];
		if (*p == '-') {
			if (p[1] == '\0')	/* stdin as a file	*/
				continue;	/* skip this one	*/

			argv[i] = 0;
			--nf;
			for (++p; c = *p++;)
				switch(tolower(c))
				{
#ifdef DEBUG
				case 'd':
					debug++;
					break;
#endif
				case 'c':
					if (++i >= argc)
						usage();
					columns = atoi(argv[i]);
					if (columns <= 0)
						bad(argv[i],"columns");
					argv[i] = 0;
					--nf;
					break;

				case 'g':
					if (++i >= argc)
						usage();
					gutter = atoi(argv[i]);
					if (gutter <= 0)
						bad(argv[i],"gutter");
					argv[i] = 0;
					--nf;
					break;

				case 'h':
					if (++i >= argc)
						usage();
					height = atoi(argv[i]);
					if (height <= 0)
						bad(argv[i],"height");
					argv[i] = 0;
					--nf;
					break;

				case 't':
					if (height<0)
						height = 23;
					if (width<0)
						width = 80;
					if (ftty(stdout))
						pause++;
					break;

				case 'w':
					if (++i >= argc)
						usage();
					width = atoi(argv[i]);
					if (width <= 0)
						bad(argv[i],"width");
					argv[i] = 0;
					--nf;
					break;

				default:
					usage();
					break;
				}
		}
	}

	if (nf > NFILES)
		error("Too many file and alias arguments");

	if (nf == 0)
	{	nf = 1;				/* Run as a filter	*/
		file[files++] = stdin;
	}
	else
		for (i = 1; i < argc; i++)
			if (p = argv[i])
				switch (*p)
				{
				case '-':	/* stdin as a file	*/
					file[files++] = stdin;
					break;

				case ALIAS:
					n = atoi(&p[1]) - 1;
					if (n < 0 || n >= files)
						error(
		"\"%s\": bad alias specification - no such file\n",p
						);
					file[files++] = file[n];
					aliases++;
					break;

				default:
					if ((fp = fopen(p,"r")) == NULL)
					{	fprintf(stderr,
							"%s: ",p);
						perror("Can't open");
						exits(IO_ERROR);
					}
					file[files++] = fp;
					break;
				}

	files -= aliases;			/* Aliases aren't open	*/

/*
 * Establish defaults for any parameters the user didn't set
 */
	if (width < 0)
		width = 132;
	if (gutter < 0)
		gutter = 1;
	if (height < 0)
		height = 58;
	if (columns < 0)
		if (nf > 1)
			columns = nf;
		else
			columns = 2;

/*
 * The last column isn't followed by a gutter, but dealing with this makes
 * the computation too complex; so we simply pretend the page is wider, which
 * is ok since the code trims the trailing spaces that would go there anyway.
 * This is, of course, quite wasteful of space, but then so is the whole algo-
 * rithm; we shouldn't be storing ANY of the gutters explicitly.
 */
	width += gutter;
	cwidth = width/columns;

	if (cwidth <= gutter || (cwidth - gutter) > LINEMAX)
		error("Unreasonable -c/-g/-w combination\n");

	lineend = line + (cwidth - gutter);

	page = malloc(pagesize = height * width);
	if (page == NULL)
		error("Insufficient memory - sorry\n");

#ifdef DEBUG
	if (debug)
	{	fprintf(stderr,"width %d, height %d, columns %d, cwidth %d\n",
			width,height,columns,cwidth);
		fprintf(stderr,
			"\tgutter %d, pause %d, pagesize %d, page at 0%o\n",
			gutter,pause,pagesize,page);
		fprintf(stderr,"%d files(%d real + %d aliases)\n",
			nf,files,aliases);
	}
#endif

	process();
	free(page);
}

/*
 * Process all the data
 */
process()
{	register int	offset;			/* Offset into page	*/
	register int	items;			/* Counts items added	*/
	register int	maxitems;		/* Room for this many	*/
	int curfile;				/* Current file		*/

	maxitems = columns * height;
	blank();
	curfile = items = offset = 0;
	while (get(file[curfile]))
	{	if (items >= maxitems)
		{	output(items);
			blank();
			items = offset = 0;
		}
#ifdef DEBUG
		if (debug > 3)
			fprintf(stderr,"Inserting %s at offset %d, file %d\n",
				line,offset,curfile);
#endif
		copy(page+offset,line,linelen);
		items++;
		if ((items % height) == 0)	/* Bottom of a column	*/
		{	curfile = (curfile + 1) % nf;
#ifdef DEBUG
			if (debug > 1)
				fprintf(stderr,"Switching to file %d of %d\n",
					curfile,files);
#endif
		}
		offset += cwidth;
	}
	output(items);
}

/*
 * Print out the buffered page, which has been filled with items items.
 */
output(items)
int items;				/* # of items the caller used	*/
{	int nrows;
	register int i,col,row;

#ifdef DEBUG
	if (debug)
		fprintf(stderr,"output(%d)\n",items);
#endif

	if (items <= 0)			/* Nothin' to do		*/
		return;

/*
 * Get number of rows we'll need.  This is the basis of the "last page"
 * optimization - we don't use all the rows, just enough to hold everything
 * (items/columns, rounded up).  If there's more than are one file, just use
 * the whole page.
 */
	if (nf == 1)
		nrows = (items + (columns - 1)) / columns;
	else
		nrows = height;

#ifdef DEBUG
	if (debug > 1)
		fprintf(stderr,"items %d, nrows %d\n",items,nrows);
	if (debug > 2)
	{	page[pagesize] = 0;
		fprintf(stderr,"Dump of page:\n%s\n",page);
	}
#endif

	if (first)
		first = FALSE;
	else
	{	if (pause)
		{	printf("\t\t\t      Type CTRL/Z to exit, any other key to continue...");
			fflush(stdout);
			i = kbin();
			putchar('\n');
			if (i == 26)		/* CTRL/Z		*/
				exit();
		}
		putchar('\f');
	}

/*
 * Scan through page[] row-wise, after having filled it column-wise.  (Page[]
 * is laid out column-wise in memory.)
 */
	for (row = 0; row < nrows; row++)
	{	for (col = 0; col < columns; col++)
			putitem(page+(row+col*nrows)*cwidth,
				(col == columns - 1));
		putchar('\n');
	}
}

/*
 * Put out one item, possibly trimming trailing spaces
 */
putitem(base,trim)
register char *base;				/* First char to put	*/
int trim;					/* Trim trailing spaces	*/
{	register char *end;			/* End of item		*/

	end = &base[cwidth - 1];
	if (trim)
		while (*end == ' ')
			--end;

	while (base <= end)
		putchar(*base++);
}

/*
 * Blank out page[]
 */
blank()
{	register int n;

	for (n = 0; n < pagesize;)
		page[n++] = ' ';
}

/*
 * Fill line[]; return FALSE when all files have reached EOF, TRUE until then.
 */
get(fp)
FILE *fp;
{	register char *p;			/* Current char pos	*/
	register char *high;			/* Char pos high water	*/
	register int c;				/* Character		*/

	if (feof(fp))
	{	linelen = 0;			/* Pretend we read ""	*/
		return(TRUE);
	}

	high = p = line;
	while ((c = getc(fp)) != EOF && c != '\n')
		switch(c)
		{
		case '\b':
			if (p > line)
				--p;
			break;

		case '\r':
			p = line;
			break;

		case '\t':
			if (((p - line) & 07) != 07)
				ungetc(c,fp);
			c = ' ';
		/*
		 * Fall through...
		 */
		default:
			if (isprint(c))
			{	if ((p < lineend)
				 && (p == high || *p == '_' || *p == ' '))
				{	*p = c;
					if (p == high)
						high++;
				}
				p++;
				}
			break;
		}

	linelen = high - line;

 	if (c != EOF)
 		return(TRUE);
 	else
 		return((--files != 0));
}

bad(v,s)
char *v;
char *s;
{	error("\"%s\": bad %s specification\n",v,s);	}

usage()
{
	fprintf(stderr,"Usage:\n mc [-t] [-c columns] [-g gutter] ");
		fprintf(stderr,"[-h height] [-w width] [file | #n]...\n");
	error("mc ? for help");
}

help()
/*
 * Give good help
 */
{	register char	**dp;

	for (dp = documentation; *dp; dp++)
		printf("%s\n",*dp);
}