From a52c0ea420dade81a9426c51a14942d78c02c968 Mon Sep 17 00:00:00 2001
From: Yuri Pankov <yuripv@FreeBSD.org>
Date: Thu, 6 Dec 2018 10:41:22 +0000
Subject: [PATCH] MFC r340144: Add hybrid C.UTF-8 locale being identical to
 default C locale except that it uses the same ctype maps and functions as
 other UTF-8 locales.

Reviewed by:	bapt, cem, eadler
Differential Revision:	https://reviews.freebsd.org/D17833
---
 lib/libc/locale/collate.c                     |   6 +-
 lib/libc/locale/ldpart.c                      |   3 +-
 .../ctypedef/{en_US.UTF-8.src => C.UTF-8.src} |   0
 share/ctypedef/Makefile                       | 155 +++++++++---------
 tools/tools/locale/Makefile                   |   4 +-
 tools/tools/locale/tools/cldr2def.pl          |  23 +--
 6 files changed, 99 insertions(+), 92 deletions(-)
 rename share/ctypedef/{en_US.UTF-8.src => C.UTF-8.src} (100%)

diff --git a/lib/libc/locale/collate.c b/lib/libc/locale/collate.c
index 5017433a9d9..15ce3b2f52e 100644
--- a/lib/libc/locale/collate.c
+++ b/lib/libc/locale/collate.c
@@ -84,7 +84,8 @@ destruct_collate(void *t)
 void *
 __collate_load(const char *encoding, __unused locale_t unused)
 {
-	if (strcmp(encoding, "C") == 0 || strcmp(encoding, "POSIX") == 0) {
+	if (strcmp(encoding, "C") == 0 || strcmp(encoding, "POSIX") == 0 ||
+	    strncmp(encoding, "C.", 2) == 0) {
 		return &__xlocale_C_collate;
 	}
 	struct xlocale_collate *table = calloc(sizeof(struct xlocale_collate), 1);
@@ -122,7 +123,8 @@ __collate_load_tables_l(const char *encoding, struct xlocale_collate *table)
 	table->__collate_load_error = 1;
 
 	/* 'encoding' must be already checked. */
-	if (strcmp(encoding, "C") == 0 || strcmp(encoding, "POSIX") == 0) {
+	if (strcmp(encoding, "C") == 0 || strcmp(encoding, "POSIX") == 0 ||
+	    strncmp(encoding, "C.", 2) == 0) {
 		return (_LDP_CACHE);
 	}
 
diff --git a/lib/libc/locale/ldpart.c b/lib/libc/locale/ldpart.c
index ed794337e11..889291cf316 100644
--- a/lib/libc/locale/ldpart.c
+++ b/lib/libc/locale/ldpart.c
@@ -63,7 +63,8 @@ __part_load_locale(const char *name,
 	size_t		namesize, bufsize;
 
 	/* 'name' must be already checked. */
-	if (strcmp(name, "C") == 0 || strcmp(name, "POSIX") == 0) {
+	if (strcmp(name, "C") == 0 || strcmp(name, "POSIX") == 0 ||
+	    strncmp(name, "C.", 2) == 0) {
 		*using_locale = 0;
 		return (_LDP_CACHE);
 	}
diff --git a/share/ctypedef/en_US.UTF-8.src b/share/ctypedef/C.UTF-8.src
similarity index 100%
rename from share/ctypedef/en_US.UTF-8.src
rename to share/ctypedef/C.UTF-8.src
diff --git a/share/ctypedef/Makefile b/share/ctypedef/Makefile
index 279e7e4492c..ab002fc82c9 100644
--- a/share/ctypedef/Makefile
+++ b/share/ctypedef/Makefile
@@ -14,6 +14,7 @@ MAPLOC=		${.CURDIR}/../../tools/tools/locale/etc/final-maps
 	-f ${MAPLOC}/map.${.IMPSRC:T:R:E} \
 	-i ${.IMPSRC} ${.OBJDIR}/${.IMPSRC:T:R}  || true
 
+LOCALES+=	C.UTF-8
 LOCALES+=	be_BY.CP1131
 LOCALES+=	ca_IT.ISO8859-1
 LOCALES+=	ca_IT.ISO8859-15
@@ -21,7 +22,6 @@ LOCALES+=	el_GR.ISO8859-7
 LOCALES+=	en_US.ISO8859-1
 LOCALES+=	en_US.ISO8859-15
 LOCALES+=	en_US.US-ASCII
-LOCALES+=	en_US.UTF-8
 LOCALES+=	hi_IN.ISCII-DEV
 LOCALES+=	hy_AM.ARMSCII-8
 LOCALES+=	ja_JP.SJIS
@@ -45,82 +45,83 @@ LOCALES+=	zh_TW.Big5
 
 
 
-SAME+=		en_US.UTF-8 ru_RU.UTF-8
-SAME+=		en_US.UTF-8 zh_TW.UTF-8
-SAME+=		en_US.UTF-8 zh_HK.UTF-8
-SAME+=		en_US.UTF-8 zh_CN.UTF-8
-SAME+=		en_US.UTF-8 uk_UA.UTF-8
-SAME+=		en_US.UTF-8 tr_TR.UTF-8
-SAME+=		en_US.UTF-8 sv_SE.UTF-8
-SAME+=		en_US.UTF-8 sv_FI.UTF-8
-SAME+=		en_US.UTF-8 sr_RS.UTF-8@latin
-SAME+=		en_US.UTF-8 sr_RS.UTF-8
-SAME+=		en_US.UTF-8 sl_SI.UTF-8
-SAME+=		en_US.UTF-8 sk_SK.UTF-8
-SAME+=		en_US.UTF-8 se_NO.UTF-8
-SAME+=		en_US.UTF-8 se_FI.UTF-8
-SAME+=		en_US.UTF-8 ro_RO.UTF-8
-SAME+=		en_US.UTF-8 pt_PT.UTF-8
-SAME+=		en_US.UTF-8 pt_BR.UTF-8
-SAME+=		en_US.UTF-8 pl_PL.UTF-8
-SAME+=		en_US.UTF-8 nn_NO.UTF-8
-SAME+=		en_US.UTF-8 nl_NL.UTF-8
-SAME+=		en_US.UTF-8 nl_BE.UTF-8
-SAME+=		en_US.UTF-8 nb_NO.UTF-8
-SAME+=		en_US.UTF-8 mn_MN.UTF-8
-SAME+=		en_US.UTF-8 lv_LV.UTF-8
-SAME+=		en_US.UTF-8 lt_LT.UTF-8
-SAME+=		en_US.UTF-8 ko_KR.UTF-8
-SAME+=		en_US.UTF-8 kk_KZ.UTF-8
-SAME+=		en_US.UTF-8 ja_JP.UTF-8
-SAME+=		en_US.UTF-8 it_IT.UTF-8
-SAME+=		en_US.UTF-8 it_CH.UTF-8
-SAME+=		en_US.UTF-8 is_IS.UTF-8
-SAME+=		en_US.UTF-8 hy_AM.UTF-8
-SAME+=		en_US.UTF-8 hu_HU.UTF-8
-SAME+=		en_US.UTF-8 hr_HR.UTF-8
-SAME+=		en_US.UTF-8 hi_IN.UTF-8
-SAME+=		en_US.UTF-8 he_IL.UTF-8
-SAME+=		en_US.UTF-8 fr_FR.UTF-8
-SAME+=		en_US.UTF-8 fr_CH.UTF-8
-SAME+=		en_US.UTF-8 fr_CA.UTF-8
-SAME+=		en_US.UTF-8 fr_BE.UTF-8
-SAME+=		en_US.UTF-8 fi_FI.UTF-8
-SAME+=		en_US.UTF-8 eu_ES.UTF-8
-SAME+=		en_US.UTF-8 et_EE.UTF-8
-SAME+=		en_US.UTF-8 es_MX.UTF-8
-SAME+=		en_US.UTF-8 es_ES.UTF-8
-SAME+=		en_US.UTF-8 es_CR.UTF-8
-SAME+=		en_US.UTF-8 es_AR.UTF-8
-SAME+=		en_US.UTF-8 en_ZA.UTF-8
-SAME+=		en_US.UTF-8 en_SG.UTF-8
-SAME+=		en_US.UTF-8 en_PH.UTF-8
-SAME+=		en_US.UTF-8 en_NZ.UTF-8
-SAME+=		en_US.UTF-8 en_IE.UTF-8
-SAME+=		en_US.UTF-8 en_HK.UTF-8
-SAME+=		en_US.UTF-8 en_GB.UTF-8
-SAME+=		en_US.UTF-8 en_CA.UTF-8
-SAME+=		en_US.UTF-8 en_AU.UTF-8
-SAME+=		en_US.UTF-8 el_GR.UTF-8
-SAME+=		en_US.UTF-8 de_DE.UTF-8
-SAME+=		en_US.UTF-8 de_CH.UTF-8
-SAME+=		en_US.UTF-8 de_AT.UTF-8
-SAME+=		en_US.UTF-8 da_DK.UTF-8
-SAME+=		en_US.UTF-8 cs_CZ.UTF-8
-SAME+=		en_US.UTF-8 ca_IT.UTF-8
-SAME+=		en_US.UTF-8 ca_FR.UTF-8
-SAME+=		en_US.UTF-8 ca_ES.UTF-8
-SAME+=		en_US.UTF-8 ca_AD.UTF-8
-SAME+=		en_US.UTF-8 bg_BG.UTF-8
-SAME+=		en_US.UTF-8 be_BY.UTF-8
-SAME+=		en_US.UTF-8 ar_SA.UTF-8
-SAME+=		en_US.UTF-8 ar_QA.UTF-8
-SAME+=		en_US.UTF-8 ar_MA.UTF-8
-SAME+=		en_US.UTF-8 ar_JO.UTF-8
-SAME+=		en_US.UTF-8 ar_EG.UTF-8
-SAME+=		en_US.UTF-8 ar_AE.UTF-8
-SAME+=		en_US.UTF-8 am_ET.UTF-8
-SAME+=		en_US.UTF-8 af_ZA.UTF-8
+SAME+=		C.UTF-8 en_US.UTF-8
+SAME+=		C.UTF-8 ru_RU.UTF-8
+SAME+=		C.UTF-8 zh_TW.UTF-8
+SAME+=		C.UTF-8 zh_HK.UTF-8
+SAME+=		C.UTF-8 zh_CN.UTF-8
+SAME+=		C.UTF-8 uk_UA.UTF-8
+SAME+=		C.UTF-8 tr_TR.UTF-8
+SAME+=		C.UTF-8 sv_SE.UTF-8
+SAME+=		C.UTF-8 sv_FI.UTF-8
+SAME+=		C.UTF-8 sr_RS.UTF-8@latin
+SAME+=		C.UTF-8 sr_RS.UTF-8
+SAME+=		C.UTF-8 sl_SI.UTF-8
+SAME+=		C.UTF-8 sk_SK.UTF-8
+SAME+=		C.UTF-8 se_NO.UTF-8
+SAME+=		C.UTF-8 se_FI.UTF-8
+SAME+=		C.UTF-8 ro_RO.UTF-8
+SAME+=		C.UTF-8 pt_PT.UTF-8
+SAME+=		C.UTF-8 pt_BR.UTF-8
+SAME+=		C.UTF-8 pl_PL.UTF-8
+SAME+=		C.UTF-8 nn_NO.UTF-8
+SAME+=		C.UTF-8 nl_NL.UTF-8
+SAME+=		C.UTF-8 nl_BE.UTF-8
+SAME+=		C.UTF-8 nb_NO.UTF-8
+SAME+=		C.UTF-8 mn_MN.UTF-8
+SAME+=		C.UTF-8 lv_LV.UTF-8
+SAME+=		C.UTF-8 lt_LT.UTF-8
+SAME+=		C.UTF-8 ko_KR.UTF-8
+SAME+=		C.UTF-8 kk_KZ.UTF-8
+SAME+=		C.UTF-8 ja_JP.UTF-8
+SAME+=		C.UTF-8 it_IT.UTF-8
+SAME+=		C.UTF-8 it_CH.UTF-8
+SAME+=		C.UTF-8 is_IS.UTF-8
+SAME+=		C.UTF-8 hy_AM.UTF-8
+SAME+=		C.UTF-8 hu_HU.UTF-8
+SAME+=		C.UTF-8 hr_HR.UTF-8
+SAME+=		C.UTF-8 hi_IN.UTF-8
+SAME+=		C.UTF-8 he_IL.UTF-8
+SAME+=		C.UTF-8 fr_FR.UTF-8
+SAME+=		C.UTF-8 fr_CH.UTF-8
+SAME+=		C.UTF-8 fr_CA.UTF-8
+SAME+=		C.UTF-8 fr_BE.UTF-8
+SAME+=		C.UTF-8 fi_FI.UTF-8
+SAME+=		C.UTF-8 eu_ES.UTF-8
+SAME+=		C.UTF-8 et_EE.UTF-8
+SAME+=		C.UTF-8 es_MX.UTF-8
+SAME+=		C.UTF-8 es_ES.UTF-8
+SAME+=		C.UTF-8 es_CR.UTF-8
+SAME+=		C.UTF-8 es_AR.UTF-8
+SAME+=		C.UTF-8 en_ZA.UTF-8
+SAME+=		C.UTF-8 en_SG.UTF-8
+SAME+=		C.UTF-8 en_PH.UTF-8
+SAME+=		C.UTF-8 en_NZ.UTF-8
+SAME+=		C.UTF-8 en_IE.UTF-8
+SAME+=		C.UTF-8 en_HK.UTF-8
+SAME+=		C.UTF-8 en_GB.UTF-8
+SAME+=		C.UTF-8 en_CA.UTF-8
+SAME+=		C.UTF-8 en_AU.UTF-8
+SAME+=		C.UTF-8 el_GR.UTF-8
+SAME+=		C.UTF-8 de_DE.UTF-8
+SAME+=		C.UTF-8 de_CH.UTF-8
+SAME+=		C.UTF-8 de_AT.UTF-8
+SAME+=		C.UTF-8 da_DK.UTF-8
+SAME+=		C.UTF-8 cs_CZ.UTF-8
+SAME+=		C.UTF-8 ca_IT.UTF-8
+SAME+=		C.UTF-8 ca_FR.UTF-8
+SAME+=		C.UTF-8 ca_ES.UTF-8
+SAME+=		C.UTF-8 ca_AD.UTF-8
+SAME+=		C.UTF-8 bg_BG.UTF-8
+SAME+=		C.UTF-8 be_BY.UTF-8
+SAME+=		C.UTF-8 ar_SA.UTF-8
+SAME+=		C.UTF-8 ar_QA.UTF-8
+SAME+=		C.UTF-8 ar_MA.UTF-8
+SAME+=		C.UTF-8 ar_JO.UTF-8
+SAME+=		C.UTF-8 ar_EG.UTF-8
+SAME+=		C.UTF-8 ar_AE.UTF-8
+SAME+=		C.UTF-8 am_ET.UTF-8
+SAME+=		C.UTF-8 af_ZA.UTF-8
 SAME+=		en_US.ISO8859-1 sv_SE.ISO8859-1
 SAME+=		en_US.ISO8859-1 sv_FI.ISO8859-1
 SAME+=		en_US.ISO8859-1 pt_PT.ISO8859-1
diff --git a/tools/tools/locale/Makefile b/tools/tools/locale/Makefile
index 9e8483dc445..79b44749233 100644
--- a/tools/tools/locale/Makefile
+++ b/tools/tools/locale/Makefile
@@ -54,7 +54,7 @@ LC:=	--lc=${LC}
 .endif
 
 all:
-	cp ${ETCDIR}/common.UTF-8.src ${CLDRDIR}/posix/xx_Comm_US.UTF-8.src
+	cp ${ETCDIR}/common.UTF-8.src ${CLDRDIR}/posix/xx_Comm_C.UTF-8.src
 .for t in ${TYPES}
 .  if ${KNOWN:M${t}}
 	test -d ${t} || mkdir ${t}
@@ -105,7 +105,7 @@ static-colldef:
 .endfor
 
 transfer-rollup:
-	cp ${ETCDIR}/common.UTF-8.src ${CLDRDIR}/posix/xx_Comm_US.UTF-8.src
+	cp ${ETCDIR}/common.UTF-8.src ${CLDRDIR}/posix/xx_Comm_C.UTF-8.src
 
 rollup:
 	perl -I tools tools/utf8-rollup.pl \
diff --git a/tools/tools/locale/tools/cldr2def.pl b/tools/tools/locale/tools/cldr2def.pl
index a34c5477670..b52899fa4f3 100755
--- a/tools/tools/locale/tools/cldr2def.pl
+++ b/tools/tools/locale/tools/cldr2def.pl
@@ -416,6 +416,9 @@ sub get_languages {
 }
 
 sub transform_ctypes {
+	# Add the C.UTF-8
+	$languages{"C"}{"x"}{data}{"x"}{$DEFENCODING} = undef;
+
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
@@ -424,13 +427,12 @@ sub transform_ctypes {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
-		my $file;
-		$file = $l . "_";
-		$file .= $f . "_" if ($f ne "x");
-		$file .= $c;
+		my $file = $l;
+		$file .= "_" . $f if ($f ne "x");
+		$file .= "_" . $c if ($c ne "x");
 		my $actfile = $file;
 
-		my $filename = "$CLDRDIR/posix/xx_Comm_US.UTF-8.src";
+		my $filename = "$CLDRDIR/posix/xx_Comm_C.UTF-8.src";
 		if (! -f $filename) {
 			print STDERR "Cannot open $filename\n";
 			next;
@@ -939,8 +941,8 @@ EOF
 				} keys(%{$hashtable{$hash}});
 		} elsif ($TYPE eq "ctypedef") {
 			@files = sort {
-				if ($a eq 'en_x_US.UTF-8') { return -1; }
-				elsif ($b eq 'en_x_US.UTF-8') { return 1; }
+				if ($a eq 'C_x_x.UTF-8') { return -1; }
+				elsif ($b eq 'C_x_x.UTF-8') { return 1; }
 				if ($a =~ /^en_x_US/) { return -1; }
 				elsif ($b =~ /^en_x_US/) { return 1; }
 
@@ -962,6 +964,7 @@ EOF
 		}
 		if ($#files > 0) {
 			my $link = shift(@files);
+			$link =~ s/_x_x//;	# special case for C
 			$link =~ s/_x_/_/;	# strip family if none there
 			foreach my $file (@files) {
 				my @a = split(/_/, $file);
@@ -987,9 +990,9 @@ EOF
 			next;
 		}
 		foreach my $e (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
-			my $file = $l . "_";
-			$file .= $f . "_" if ($f ne "x");
-			$file .= $c;
+			my $file = $l;
+			$file .= "_" . $f if ($f ne "x");
+			$file .= "_" . $c if ($c ne "x");
 			next if (!defined $languages{$l}{$f}{data}{$c}{$e});
 			print FOUT "LOCALES+=\t$file.$e\n";
 		}
-- 
2.45.0