[9fans] CRLFication (was: libbio and CR-LF)

[Geoff Collyer <geoff@collyer.net>]

Coincidentally, I just wrote a bidirectional copy with optional
CRLFication.  I think it's mostly useful for letting shell scripts
talk ye olde Internet protocols, but pushing CRLFication out to the
edge of the system (to the interface with the network) seems better
than requiring programs to understand it natively.  Not that this
helps with Windows text files particularly.

I've also enclosed dial, a script that uses bicp to connect and copy
bidirectionally.  As its EXAMPLE shows, it can be used to print when
lp is broken.


# To unbundle, run this file
echo bicp
sed 's/^X//' >bicp <<'!'
X.TH BICP 1
X.SH NAME
bicp \- bidirectional copy with optional crlfication
X.SH SYNOPSIS
X.B bicp
X[
X.B -c
X]
command
X[ argument ... ]
X.SH DESCRIPTION
X.I Bicp
copies its standard input to a pipe to
X.IR command ,
and copies from that pipe to its standard output.
X.PP
Under
X.BR -c ,
X.I bicp
also deletes CRs from its standard input and
inserts CRs before newlines in its standard output if there are none.
This permits ordinary programs (including shell scripts)
to serve the usual lousy Internet protocols without
having to deal with their silly end-of-line conventions.
In effect, this pushes crlfication out to the interface with the network.
X.SH EXAMPLES
Implement the
X.I daytime
protocol.
X.EE
X.ti +0.5i
X{echo '#!/bin/rc'; echo exec bicp -c date} >/bin/service/tcp13
X.EX
X.\" .SH FILES
X.SH SEE ALSO
X.IR dial (1),
X.IR listen (8)
X.SH HISTORY
Written by Geoff Collyer.
X.SH BUGS
Arguably,
X.IR listen (8)
and
X.IR dial (2)
should provide crlfication as an optional service.
!
echo dial
sed 's/^X//' >dial <<'!'
X.TH DIAL 1
X.SH NAME
dial \- place an outgoing call and run a command on the resulting connection
X.SH SYNOPSIS
X.B dial
X[
X.B -x
X] [
X.B -p
X]
dialstring [ command ]
X.SH DESCRIPTION
X.I Dial
connects to
X.I dialstring
and runs
X.RI ` command
X.BR /net/ proto/conn /data ',
where
X.BR /net/ proto/conn
is the network directory of the resultant connection.
The default
X.I command
is
X.IR bicp (1).
X.B -x
uses
X.B /net.alt
instead of
X.BR /net .
X.B -p
retries (after a pause) until a connection is made.
X.PP
X.I Dial
and
X.I bicp
provide most of the machinery needed for a simple printer spooler.
X.SH EXAMPLES
X.EX
X# epsps [file...] - emergency printing system; print postscript on $LPDEST
aux/download -f -H/sys/lib/postscript/font -mfontmap -plw+ $* |
X	dial -p tcp!$LPDEST!printer
X.EE
X.SH FILES
X.B /net/tcp
subtree of TCP connections
X.SH SEE ALSO
X.IR bicp (1),
X.IR lp (1)
X.SH HISTORY
Written by Geoff Collyer.
!
# To unbundle, run this file
echo bicp.c
sed 's/^X//' >bicp.c <<'!'
X/*
X * bicp [-c] cmd [arg ...] - bidirectional copy
X *
X * copy from stdin to pipe-to-cmd, and simultaneously copy from
X * pipe-from-cmd to stdout.  Under -c, delete CRs so cmd doesn't see
X * them in its input and add CRs before newlines to its output.
X *
X * stdin & stdout are typically a network connection.  this is
X * intended to be like a streams line discipline.
X */

X#include <u.h>
X#include <libc.h>
X#include <bio.h>	/* too much context switching with byte-at-a-time i/o */

X#define	STREQ(a, b)	(*(a) == *(b) && strcmp((a), (b)) == 0)

enum {
X	Pcopy, Pcmd, Npipe,		// pipe indices
X};
enum {
X	Stdin, Stdout, Stderr,		// pipe indices
X};
enum {
X	Child,
X	Hackdelay = 500,		// in ms
X};

static int wasintr, crlfy;

static void
killmypg(void)
X{
X	int npf;
X	char fullnm[64];

X	snprint(fullnm, sizeof fullnm, "/proc/%d/notepg", getpid());
X	npf = open(fullnm, OWRITE);
X	if (npf >= 0) {
X		write(npf, "kill", 4);
X		close(npf);
X	}
X}

static void
pipeclose(int pipe[Npipe])
X{
X	close(pipe[Pcopy]);
X	close(pipe[Pcmd]);
X}

X/* chop line (ln) at CR of CRLF, if present, else at newline */
static void
chopateol(Biobuf *bp, char *ln)
X{
X	int len = Blinelen(bp);
X	char *eol = &ln[len - 1];		// points at newline

X	if (len >= 2 && eol[-1] == '\r')
X		--eol;
X	*eol = '\0';
X}

X// copy net → cmd, optionally deleting CRs
static void
copyfromnet(int net, int cmd[Npipe])
X{
X	char *ln;
X	Biobuf netbuf, *netb = &netbuf;

X	Binit(netb, net, OREAD);
X	while ((ln = Brdline(netb, '\n')) != nil && !wasintr) {
X		if (crlfy)
X			chopateol(netb, ln);
X		else
X			ln[Blinelen(netb) - 1] = '\0';
X		fprint(cmd[Pcopy], "%s\n", ln);
X	}
X	Bterm(netb);
X}

X// copy cmd → net, optionally inserting CRs before newlines
static void
copytonet(int net, int cmd[Npipe])
X{
X	char *ln;
X	Biobuf cmdbuf, *cmdb = &cmdbuf;

X	Binit(cmdb, cmd[Pcopy], OREAD);
X	while ((ln = Brdline(cmdb, '\n')) != nil) {
X		chopateol(cmdb, ln);
X		if (crlfy)
X			fprint(net, "%s\r\n", ln);
X		else
X			fprint(net, "%s\n", ln);
X	}
X	Bterm(cmdb);
X}

static void
docopy(void (*copy)(int, int [Npipe]), int net, int clfd, int cmd[Npipe])
X{
X	close(clfd);
X	close(Stderr);
X	close(cmd[Pcmd]);	// we aren't the command side
X	(*copy)(net, cmd);
X	close(cmd[Pcopy]);	// pass on the EOF to command
X	close(net);		//  and network
X	sleep(Hackdelay);	// wait for output to drain
X	killmypg();		// kill other copying process & cmd
X	exits(0);
X}

static void
forkcopy(void (*copy)(int, int [Npipe]), int net, int clfd, int cmd[Npipe])
X{
X	if (rfork(RFPROC|RFFDG|RFNOWAIT) == Child)
X		docopy(copy, net, clfd, cmd);
X}

void
notifyf(void *, char *s)
X{
X	if (STREQ(s, "interrupt")) {
X		wasintr++;
X		noted(NCONT);
X	}
X	killmypg();
X	noted(NDFLT);
X}

static void
execcmd(char **argv, int cmd[Npipe])
X{
X	char *prog;
X	char fullnm[256];

X	dup(cmd[Pcmd], Stdin);	// cross-connected pipe halves
X	dup(cmd[Pcmd], Stdout);
X	pipeclose(cmd);

X	prog = argv[0];
X	exec(prog, argv);
X	if (prog[0] != '/') {
X		snprint(fullnm, sizeof fullnm, "/bin/%s", prog);
X		exec(fullnm, argv);
X	}
X	killmypg();
X	sysfatal("can't exec %s nor %s: %r", prog, fullnm);
X}

void
main(int argc, char *argv[])
X{
X	int errflg = 0;
X	int cmd[Npipe];

X	ARGBEGIN {
X	case 'c':
X		++crlfy;
X		break;
X	default:
X		errflg++;
X		break;
X	} ARGEND
X	if (argc <= 0 || errflg)
X		sysfatal("usage: %s [-c] cmd [arg]...", argv0);

X	if (pipe(cmd) < 0)
X		sysfatal("pipe: %r");
X	// cmd[0] is the copying side; cmd[1] is the command side
X	rfork(RFNOTEG);

X	notify(notifyf);
X	forkcopy(copyfromnet, Stdin, Stdout, cmd);
X	if (fork() == Child)
X		execcmd(argv, cmd);
X	docopy(copytonet, Stdout, Stdin, cmd);
X}
!
# To unbundle, run this file
echo dial
sed 's/^X//' >dial <<'!'
X#!/bin/rc
X# dial [-x][-p] string [cmd] - place an outgoing call to string and
X#	run `cmd /net/.../data'.  -x uses /net.alt; -p persists.
rfork e
opt=''
persist=no
silent=no
while (test $#* -gt 0 && ~ $1 -*) {
X	switch ($1) {
X	case -x
X		opt=/net.alt/cs
X	case -p
X		persist=yes
X	case *
X		echo usage: $0 '[-x][-p] dialstr [cmd]' >[1=2]
X		exit usage
X	}
X	shift
X}
cmd=bicp		# dialcp
if (~ $#* 2)
X	cmd=$2

X# csquery needs an option to shut it up, at the very least.
X# prints /net/tcp/clone ip!port
conn=`{echo $1 | eval ndb/csquery $opt | sed 's/^> //'}
clone=$conn(1)		# clone file, opening it yields a ctl file
addr=$conn(2)
net=`{echo $clone | sed 's;/clone$;;'}

X# each open of $clone yields a distinct connection and rc lacks bourne's <>,
X# so get connection number from $clone, then open & write its ctl file.
X# apparently, closing the clone file drops the connection.
while () {
X	{
X		# the connection is reserved now
X		netdir=$net/`{read <[0=3]}
X		if (echo 'connect '$addr >$netdir/ctl >[2]/dev/null)
X			if (! ~ `{cat $netdir/remote} 0.0.0.0!0 ::!0)
X				# no ip v4 nor v6 failure?
X				# the connection will be established when
X				# $netdir/data is opened and can fail then.
X				eval exec $cmd $netdir/data
X		if (~ $persist yes) {
X			echo -n .
X			sleep 5
X		}
X		if not
X			exit 'conn refused'
X	} <[3]$clone
X}
!