From 628bd30ab5a492839b84dbf2aaf25848dae3866a Mon Sep 17 00:00:00 2001
From: Warner Losh <imp@FreeBSD.org>
Date: Wed, 21 Jul 2021 20:22:43 -0600
Subject: [PATCH] awk: revert to upstream behavior for ranges for gawk
 compatibility

In 2005, FreeBSD changed one-true-awk to honor the locale's collating
order. This was billed as a temporary patch. It was also compatible with
the then-current behavior of gawk. That temporary patch has lasted 16
years now.

However, IEEE Std 1003.1-2008 changed the behaivor of ranges in regular
expressions outside of the "C" and "POSIX" locales to be undefined.

Starting in 2011, gawk 4.0 stopped using the locale for the range
regular expressions and used the traditional behavior only. The
maintainer had grown weary of answering why '[A-Z]' would sometimes
match lower-case expressions. The details about are explained here:
https://www.gnu.org/software/gawk/manual/html_node/Ranges-and-Locales.html

To restore compatibility with other implementaitons of awk, revert this
patch. FreeBSD is the odd-system out. It also has the nice side effect
of eliminating the last of our differences with upstream one-true-awk.

Reviewed by:		cy, rgrimes
MFC After:		2 weeks
Sponsored by:		Netflix
Differential Revision:	https://reviews.freebsd.org/D31114
---
 contrib/one-true-awk/b.c    | 22 ++++------------------
 contrib/one-true-awk/main.c |  1 -
 contrib/one-true-awk/run.c  |  2 +-
 3 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/contrib/one-true-awk/b.c b/contrib/one-true-awk/b.c
index dd64f09647b0..01119470de05 100644
--- a/contrib/one-true-awk/b.c
+++ b/contrib/one-true-awk/b.c
@@ -361,20 +361,9 @@ int quoted(const uschar **pp)	/* pick up next thing after a \\ */
 	return c;
 }
 
-static int collate_range_cmp(int a, int b)
-{
-	static char s[2][2];
-
-	if ((uschar)a == (uschar)b)
-		return 0;
-	s[0][0] = a;
-	s[1][0] = b;
-	return (strcoll(s[0], s[1]));
-}
-
 char *cclenter(const char *argp)	/* add a character class */
 {
-	int i, c, c2, j;
+	int i, c, c2;
 	const uschar *op, *p = (const uschar *) argp;
 	uschar *bp;
 	static uschar *buf = NULL;
@@ -393,18 +382,15 @@ char *cclenter(const char *argp)	/* add a character class */
 				c2 = *p++;
 				if (c2 == '\\')
 					c2 = quoted(&p);
-				if (collate_range_cmp(c, c2) > 0) {
+				if (c > c2) {	/* empty; ignore */
 					bp--;
 					i--;
 					continue;
 				}
-				for (j = 0; j < NCHARS; j++) {
-					if ((collate_range_cmp(c, j) > 0) ||
-					    collate_range_cmp(j, c2) > 0)
-						continue;
+				while (c < c2) {
 					if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, "cclenter1"))
 						FATAL("out of space for character class [%.10s...] 2", p);
-					*bp++ = j;
+					*bp++ = ++c;
 					i++;
 				}
 				continue;
diff --git a/contrib/one-true-awk/main.c b/contrib/one-true-awk/main.c
index cfe3fafaf7fe..95eeba00d9ca 100644
--- a/contrib/one-true-awk/main.c
+++ b/contrib/one-true-awk/main.c
@@ -117,7 +117,6 @@ int main(int argc, char *argv[])
 	char *fn, *vn;
 
 	setlocale(LC_CTYPE, "");
-	setlocale(LC_COLLATE, "");
 	setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */
 	cmdname = argv[0];
 	if (argc == 1) {
diff --git a/contrib/one-true-awk/run.c b/contrib/one-true-awk/run.c
index 9752cd773630..3342eb274e3a 100644
--- a/contrib/one-true-awk/run.c
+++ b/contrib/one-true-awk/run.c
@@ -665,7 +665,7 @@ Cell *relop(Node **a, int n)	/* a[0 < a[1], etc. */
 		j = x->fval - y->fval;
 		i = j<0? -1: (j>0? 1: 0);
 	} else {
-		i = strcoll(getsval(x), getsval(y));
+		i = strcmp(getsval(x), getsval(y));
 	}
 	tempfree(x);
 	tempfree(y);