Re: Proposal to drop MKCATPAGES

[David Holland <dholland-tech%netbsd.org@localhost>]

On Mon, Oct 26, 2020 at 05:39:30PM +0700, Robert Elz wrote:
 >   | Also if inserting newlines is an intended use case, I kinda think it
 >   | ought to accept \n in there, which it currently doesn't.
 > 
 > That would be "C string quoting" which is $'\n' which isn't yet in POSIX
 > but should be coming sometime, it is supported by most (Bournish) shells

I was thinking in lam itself, like this:
(after all, sed has something similar)
I made it specifically recognize only \n and \t (and not \\ or
anything else) to minimize the chances of it breaking anything.


Index: lam.1
===================================================================
RCS file: /cvsroot/src/usr.bin/lam/lam.1,v
retrieving revision 1.14
diff -u -r1.14 lam.1
--- lam.1	26 Oct 2020 04:09:32 -0000	1.14
+++ lam.1	26 Oct 2020 04:12:48 -0000
@@ -91,6 +91,9 @@
 This option may appear after the last file.
 (A capitalized version appearing before the last file is not carried
 over past the last file.)
+Instances of the sequences "\en" and "\et" are replaced with hard
+newlines and tabs, respectively.
+(No other escapes are recognized.)
 .It Fl t Ar c
 The input line terminator is
 .Ar c
Index: lam.c
===================================================================
RCS file: /cvsroot/src/usr.bin/lam/lam.c,v
retrieving revision 1.8
diff -u -r1.8 lam.c
--- lam.c	4 Sep 2011 20:28:09 -0000	1.8
+++ lam.c	26 Oct 2020 04:12:48 -0000
@@ -74,6 +74,7 @@
 static char	*gatherline(struct openfile *);
 static void	 getargs(char *[]);
 static char	*pad(struct openfile *);
+static const char *getseparator(const char *arg);
 
 int
 main(int argc, char *argv[])
@@ -128,7 +129,7 @@
 		switch (tolower((unsigned char) *c)) {
 		case 's':
 			if (*++p || (p = *++av))
-				ip->sepstring = p;
+				ip->sepstring = getseparator(p);
 			else
 				error("Need string after -%s", c);
 			S = (*c == 'S' ? 1 : 0);
@@ -216,6 +217,50 @@
 	return (lp);
 }
 
+static const char *
+getseparator(const char *arg)
+{
+	size_t i, j;
+	int seen;
+	char *p;
+
+	seen = 0;
+	for (i = 0; arg[i] != '\0'; i++) {
+		/*
+		 * React only specifically to \n and \t; leave
+		 * anything else alone.
+		 */
+		if (arg[i] == '\\' && (arg[i+1] == 'n' || arg[i+1] == 't')) {
+			seen = 1;
+		}
+	}
+	if (!seen) {
+		warnx("blah");
+		return arg;
+	}
+
+	/* sufficient: length of result is at most strlen(arg) - 1 */
+	p = malloc(strlen(arg));
+	if (p == NULL) {
+		err(1, "malloc");
+	}
+	for (i = j = 0; arg[i] != '\0'; i++) {
+		if (arg[i] == '\\' && arg[i+1] == 'n') {
+			p[j++] = '\n';
+			/* skip the \\ */
+			i++;
+		} else if (arg[i] == '\\' && arg[i+1] == 't') {
+			p[j++] = '\t';
+			/* skip the \\ */
+			i++;
+		} else {
+			p[j++] = arg[i];
+		}
+	}
+	p[j] = '\0';
+	return p;
+}
+
 static void
 error(const char *msg, const char *s)
 {


-- 
David A. Holland
dholland%netbsd.org@localhost