25 files changed, 483 insertions, 0 deletions
diff --git a/usr.bin/awk/Makefile b/usr.bin/awk/Makefile
new file mode 100644
index 000000000000..8a3a43f5421b
--- /dev/null
+++ b/usr.bin/awk/Makefile
@@ -0,0 +1,34 @@
+# $NetBSD: Makefile,v 1.2 2012/03/11 18:35:59 jruoho Exp $
+
+.include <bsd.own.mk>
+
+TESTSDIR=	${TESTSBASE}/usr.bin/awk
+TESTS_SH=	t_awk
+NOMAN=		# defined
+
+FILESDIR=	${TESTSDIR}
+FILES=		d_big_regexp.awk
+FILES+=		d_big_regexp.in
+FILES+=		d_big_regexp.out
+FILES+=		d_end1.awk
+FILES+=		d_end1.in
+FILES+=		d_end1.out
+FILES+=		d_end2.awk
+FILES+=		d_end2.in
+FILES+=		d_end2.out
+FILES+=		d_period.awk
+FILES+=		d_period.in
+FILES+=		d_period.out
+FILES+=		d_string1.awk
+FILES+=		d_string1.out
+FILES+=		d_tolower.awk
+FILES+=		d_tolower.in
+FILES+=		d_tolower.out
+FILES+=		d_toupper.awk
+FILES+=		d_toupper.in
+FILES+=		d_toupper.out
+FILES+=		d_assign_NF.awk
+FILES+=		d_assign_NF.in
+FILES+=		d_assign_NF.out
+
+.include <bsd.test.mk>
+\ No newline at end of file
diff --git a/usr.bin/awk/d_assign_NF.awk b/usr.bin/awk/d_assign_NF.awk
new file mode 100644
index 000000000000..52c39124cbf6
--- /dev/null
+++ b/usr.bin/awk/d_assign_NF.awk
@@ -0,0 +1,16 @@
+# $NetBSD: d_assign_NF.awk,v 1.1 2012/03/11 18:35:59 jruoho Exp $
+
+{
+	NF = 2
+	print "$0=`" $0 "`"
+	print "$3=`" $3 "`"
+	print "$4=`" $4 "`"
+	NF = 3
+	print "$0=`" $0 "`"
+	print "$3=`" $3 "`"
+	print "$4=`" $4 "`"
+	NF = 4
+	print "$0=`" $0 "`"
+	print "$3=`" $3 "`"
+	print "$4=`" $4 "`"
+}
diff --git a/usr.bin/awk/d_assign_NF.in b/usr.bin/awk/d_assign_NF.in
new file mode 100644
index 000000000000..1245b922123b
--- /dev/null
+++ b/usr.bin/awk/d_assign_NF.in
@@ -0,0 +1 @@
+ 1    2  3
diff --git a/usr.bin/awk/d_assign_NF.out b/usr.bin/awk/d_assign_NF.out
new file mode 100644
index 000000000000..2631a7a92db8
--- /dev/null
+++ b/usr.bin/awk/d_assign_NF.out
@@ -0,0 +1,9 @@
+$0=`1 2`
+$3=``
+$4=``
+$0=`1 2 `
+$3=``
+$4=``
+$0=`1 2  `
+$3=``
+$4=``
diff --git a/usr.bin/awk/d_big_regexp.awk b/usr.bin/awk/d_big_regexp.awk
new file mode 100644
index 000000000000..1502b5e75462
--- /dev/null
+++ b/usr.bin/awk/d_big_regexp.awk
@@ -0,0 +1,3 @@
+# $NetBSD: d_big_regexp.awk,v 1.1 2012/03/11 18:36:00 jruoho Exp $
+
+/^[^_][^ ]*_NNIFO([ ]+[^_]+[^ ]*_(CC|INR|JJFO|JJMA|JJPG|NNIFG|NNIFO|NNIMPG|NNIMR|NNING|PP3FD|PQINO|PQMO|PSFR|RQ|TC|VIIR3|VPIPN|VPLIPF|NOTAG|RQR))*$/
diff --git a/usr.bin/awk/d_big_regexp.in b/usr.bin/awk/d_big_regexp.in
new file mode 100644
index 000000000000..ad82078afc0d
--- /dev/null
+++ b/usr.bin/awk/d_big_regexp.in
@@ -0,0 +1 @@
+1_NNIFO 1_PSFR 1_JJFO 1_NNIFO 1_INR 1_NNIMR 1_CC 1_NNING 1_RQ 1_VPLIPF 1_NNIFG 1_JJPG 1_NNIMPG 1_PQINO 1_VPIPN 1_PP3FD 1_JJMA 1_PQMO 1_TC 1_VIIR3
diff --git a/usr.bin/awk/d_big_regexp.out b/usr.bin/awk/d_big_regexp.out
new file mode 100644
index 000000000000..ad82078afc0d
--- /dev/null
+++ b/usr.bin/awk/d_big_regexp.out
@@ -0,0 +1 @@
+1_NNIFO 1_PSFR 1_JJFO 1_NNIFO 1_INR 1_NNIMR 1_CC 1_NNING 1_RQ 1_VPLIPF 1_NNIFG 1_JJPG 1_NNIMPG 1_PQINO 1_VPIPN 1_PP3FD 1_JJMA 1_PQMO 1_TC 1_VIIR3
diff --git a/usr.bin/awk/d_end1.awk b/usr.bin/awk/d_end1.awk
new file mode 100644
index 000000000000..cb8b0d0ed208
--- /dev/null
+++ b/usr.bin/awk/d_end1.awk
@@ -0,0 +1,5 @@
+# $NetBSD: d_end1.awk,v 1.1 2012/03/11 18:36:00 jruoho Exp $
+
+END {
+	print NF;
+}
diff --git a/usr.bin/awk/d_end1.in b/usr.bin/awk/d_end1.in
new file mode 100644
index 000000000000..8e13e468a002
--- /dev/null
+++ b/usr.bin/awk/d_end1.in
@@ -0,0 +1 @@
+a b c d
diff --git a/usr.bin/awk/d_end1.out b/usr.bin/awk/d_end1.out
new file mode 100644
index 000000000000..b8626c4cff28
--- /dev/null
+++ b/usr.bin/awk/d_end1.out
@@ -0,0 +1 @@
+4
diff --git a/usr.bin/awk/d_end2.awk b/usr.bin/awk/d_end2.awk
new file mode 100644
index 000000000000..8b10b828779c
--- /dev/null
+++ b/usr.bin/awk/d_end2.awk
@@ -0,0 +1,5 @@
+# $NetBSD: d_end2.awk,v 1.1 2012/03/11 18:36:00 jruoho Exp $
+
+END {
+	print $0;
+}
diff --git a/usr.bin/awk/d_end2.in b/usr.bin/awk/d_end2.in
new file mode 100644
index 000000000000..8e13e468a002
--- /dev/null
+++ b/usr.bin/awk/d_end2.in
@@ -0,0 +1 @@
+a b c d
diff --git a/usr.bin/awk/d_end2.out b/usr.bin/awk/d_end2.out
new file mode 100644
index 000000000000..8e13e468a002
--- /dev/null
+++ b/usr.bin/awk/d_end2.out
@@ -0,0 +1 @@
+a b c d
diff --git a/usr.bin/awk/d_period.awk b/usr.bin/awk/d_period.awk
new file mode 100644
index 000000000000..d1dabf751304
--- /dev/null
+++ b/usr.bin/awk/d_period.awk
@@ -0,0 +1 @@
+{print x + $1 + 0.125}
diff --git a/usr.bin/awk/d_period.in b/usr.bin/awk/d_period.in
new file mode 100644
index 000000000000..d10c0e2f9d08
--- /dev/null
+++ b/usr.bin/awk/d_period.in
@@ -0,0 +1 @@
+0,25
diff --git a/usr.bin/awk/d_period.out b/usr.bin/awk/d_period.out
new file mode 100644
index 000000000000..3382aa6e35b8
--- /dev/null
+++ b/usr.bin/awk/d_period.out
@@ -0,0 +1 @@
+0.625
diff --git a/usr.bin/awk/d_string1.awk b/usr.bin/awk/d_string1.awk
new file mode 100644
index 000000000000..d690240fa17b
--- /dev/null
+++ b/usr.bin/awk/d_string1.awk
@@ -0,0 +1,7 @@
+# $NetBSD: d_string1.awk,v 1.1 2012/03/11 18:36:00 jruoho Exp $
+
+BEGIN {
+	print "A\
+B";
+	print "CD"
+}
diff --git a/usr.bin/awk/d_string1.out b/usr.bin/awk/d_string1.out
new file mode 100644
index 000000000000..96c017b97b70
--- /dev/null
+++ b/usr.bin/awk/d_string1.out
@@ -0,0 +1,2 @@
+AB
+CD
diff --git a/usr.bin/awk/d_tolower.awk b/usr.bin/awk/d_tolower.awk
new file mode 100644
index 000000000000..258d181ce30b
--- /dev/null
+++ b/usr.bin/awk/d_tolower.awk
@@ -0,0 +1,5 @@
+# $NetBSD: d_tolower.awk,v 1.1 2012/03/11 18:36:00 jruoho Exp $
+
+END {
+	print tolower($0);
+}
diff --git a/usr.bin/awk/d_tolower.in b/usr.bin/awk/d_tolower.in
new file mode 100644
index 000000000000..66ed03c2d27a
--- /dev/null
+++ b/usr.bin/awk/d_tolower.in
@@ -0,0 +1 @@
+ABCÆØÅ
diff --git a/usr.bin/awk/d_tolower.out b/usr.bin/awk/d_tolower.out
new file mode 100644
index 000000000000..83b2bf51cdf4
--- /dev/null
+++ b/usr.bin/awk/d_tolower.out
@@ -0,0 +1 @@
+abcæøå
diff --git a/usr.bin/awk/d_toupper.awk b/usr.bin/awk/d_toupper.awk
new file mode 100644
index 000000000000..0719aa9b86e9
--- /dev/null
+++ b/usr.bin/awk/d_toupper.awk
@@ -0,0 +1,5 @@
+# $NetBSD: d_toupper.awk,v 1.1 2012/03/11 18:36:01 jruoho Exp $
+
+END {
+	print toupper($0);
+}
diff --git a/usr.bin/awk/d_toupper.in b/usr.bin/awk/d_toupper.in
new file mode 100644
index 000000000000..83b2bf51cdf4
--- /dev/null
+++ b/usr.bin/awk/d_toupper.in
@@ -0,0 +1 @@
+abcæøå
diff --git a/usr.bin/awk/d_toupper.out b/usr.bin/awk/d_toupper.out
new file mode 100644
index 000000000000..66ed03c2d27a
--- /dev/null
+++ b/usr.bin/awk/d_toupper.out
@@ -0,0 +1 @@
+ABCÆØÅ
diff --git a/usr.bin/awk/t_awk.sh b/usr.bin/awk/t_awk.sh
new file mode 100755
index 000000000000..77cb5f86df01
--- /dev/null
+++ b/usr.bin/awk/t_awk.sh
@@ -0,0 +1,378 @@
+# $NetBSD: t_awk.sh,v 1.5 2012/12/10 20:30:06 christos Exp $
+#
+# Copyright (c) 2012 The NetBSD Foundation, Inc.
+# All rights reserved.
+#
+# This code is derived from software contributed to The NetBSD Foundation
+# by Christos Zoulas
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
+# ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+# TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
+# BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+#
+
+awk=awk
+
+h_check()
+{
+	local fname=d_$1
+	for sfx in in out awk; do
+		cp -r $(atf_get_srcdir)/$fname.$sfx .
+	done
+	shift 1
+	atf_check -o file:$fname.out -x "awk $@ -f $fname.awk < $fname.in"
+}
+
+atf_test_case big_regexp
+
+big_regexp_head() {
+	atf_set "descr" "Checks matching long regular expressions (PR/33392)"
+}
+
+big_regexp_body() {
+	h_check big_regexp
+}
+
+atf_test_case end
+
+end_head() {
+	atf_set "descr" "Checks that the last line of the input" \
+	                "is available under END pattern (PR/29659)"
+}
+
+end_body() {
+	h_check end1
+	h_check end2
+}
+
+atf_test_case string1
+
+string1_head() {
+	atf_set "descr" "Checks escaping newlines in string literals"
+}
+
+string1_body() {
+	for sfx in out awk; do
+		cp -r $(atf_get_srcdir)/d_string1.$sfx .
+	done
+	atf_check -o file:d_string1.out awk -f d_string1.awk
+}
+
+atf_test_case multibyte
+
+multibyte_head() {
+	atf_set "descr" "Checks multibyte charsets support" \
+	                "in tolower and toupper (PR/36394)"
+}
+
+multibyte_body() {
+	export LANG=en_US.UTF-8
+
+	h_check tolower
+	h_check toupper
+}
+
+atf_test_case period
+
+period_head() {
+	atf_set "descr" "Checks that the period character is recognised" \
+	                "in awk program regardless of locale (bin/42320)"
+}
+
+period_body() {
+	export LANG=ru_RU.KOI8-R
+
+	h_check period -v x=0.5
+}
+
+atf_test_case assign_NF
+
+assign_NF_head() {
+	atf_set "descr" 'Checks that assign to NF changes $0 and $n (PR/44063)'
+}
+
+assign_NF_body() {
+	h_check assign_NF
+}
+
+atf_test_case single_char_rs
+
+single_char_rs_head() {
+	atf_set "descr" "Test awk(1) with single character RS"
+}
+
+single_char_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n\n3\n\n\n4\n\n" \
+		-x "echo 1a2aa3aaa4 | $awk 1 RS=a"
+}
+
+atf_test_case two_char_rs
+
+two_char_rs_head() {
+	atf_set "descr" "Test awk(1) with two characters RS"
+}
+
+two_char_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n3\n4\n\n" \
+		-x "echo 1ab2ab3ab4 | $awk 1 RS=ab"
+}
+
+atf_test_case single_char_regex_group_rs
+
+single_char_regex_group_rs_head() {
+	atf_set "descr" "Test awk(1) with single character regex group RS"
+}
+
+single_char_regex_group_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n\n3\n\n\n4\n\n" \
+		-x "echo 1a2aa3aaa4 | $awk 1 RS='[a]'"
+}
+
+atf_test_case two_char_regex_group_rs
+
+two_char_regex_group_rs_head() {
+	atf_set "descr" "Test awk(1) with two characters regex group RS"
+}
+
+two_char_regex_group_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n\n3\n\n\n4\n\n" \
+		-x "echo 1a2ab3aba4 | $awk 1 RS='[ab]'"
+}
+
+atf_test_case single_char_regex_star_rs
+
+single_char_regex_star_rs_head() {
+	atf_set "descr" "Test awk(1) with single character regex star RS"
+}
+
+single_char_regex_star_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n3\n4\n\n" \
+		-x "echo 1a2aa3aaa4 | $awk 1 RS='a*'"
+}
+
+atf_test_case two_char_regex_star_rs
+
+two_char_regex_star_rs_head() {
+	atf_set "descr" "Test awk(1) with two characters regex star RS"
+}
+
+two_char_regex_star_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n3\n4\n\n" \
+		-x "echo 1a2aa3aaa4 | $awk 1 RS='aa*'"
+}
+
+atf_test_case regex_two_star_rs
+
+regex_two_star_rs_head() {
+	atf_set "descr" "Test awk(1) with regex two star RS"
+}
+
+regex_two_star_rs_body() {
+	atf_check \
+		-o "inline:1\n2\n3\n4\n\n" \
+		-x "echo 1a2ab3aab4 | $awk 1 RS='aa*b*'"
+}
+
+atf_test_case regex_or_1_rs
+
+regex_or_1_rs_head() {
+	atf_set "descr" "Test awk(1) with regex | case 1 RS"
+}
+
+regex_or_1_rs_body() {
+	atf_check \
+		-o "inline:1a\nc\n\n" \
+		-x "echo 1abc | $awk 1 RS='abcde|b'"
+}
+
+atf_test_case regex_or_2_rs
+
+regex_or_2_rs_head() {
+	atf_set "descr" "Test awk(1) with regex | case 2 RS"
+}
+
+regex_or_2_rs_body() {
+	atf_check \
+		-o "inline:1a\ncdf2\n\n" \
+		-x "echo 1abcdf2 | $awk 1 RS='abcde|b'"
+}
+
+atf_test_case regex_or_3_rs
+
+regex_or_3_rs_head() {
+	atf_set "descr" "Test awk(1) with regex | case 3 RS"
+}
+
+regex_or_3_rs_body() {
+	atf_check \
+		-o "inline:1\n\nf2\n\n" \
+		-x "echo 1abcdebf2 | $awk 1 RS='abcde|b'"
+}
+
+atf_test_case regex_or_4_rs
+
+regex_or_4_rs_head() {
+	atf_set "descr" "Test awk(1) with regex | case 4 RS"
+}
+
+regex_or_4_rs_body() {
+	atf_check \
+		-o "inline:1\nbcdf2\n\n" \
+		-x "echo 1abcdf2 | $awk 1 RS='abcde|a'"
+
+}
+
+atf_test_case regex_caret_1_rs
+
+regex_caret_1_rs_head() {
+	atf_set "descr" "Test awk(1) with regex ^ case 1 RS"
+}
+
+regex_caret_1_rs_body() {
+	atf_check \
+		-o "inline:\n1a2a3a\n\n" \
+		-x "echo a1a2a3a | $awk 1 RS='^a'"
+
+}
+
+atf_test_case regex_caret_2_rs
+
+regex_caret_2_rs_head() {
+	atf_set "descr" "Test awk(1) with regex ^ case 2 RS"
+}
+
+regex_caret_2_rs_body() {
+	atf_check \
+		-o "inline:\naa1a2a\n\n" \
+		-x "echo aaa1a2a | $awk 1 RS='^a'"
+
+}
+
+atf_test_case regex_dollar_1_rs
+
+regex_dollar_1_rs_head() {
+	atf_set "descr" "Test awk(1) with regex $ case 1 RS"
+}
+
+regex_dollar_1_rs_body() {
+	atf_check \
+		-o "inline:a1a2a3a\n\n" \
+		-x "echo a1a2a3a | $awk 1 RS='a$'"
+
+}
+
+atf_test_case regex_dollar_2_rs
+
+regex_dollar_2_rs_head() {
+	atf_set "descr" "Test awk(1) with regex $ case 2 RS"
+}
+
+regex_dollar_2_rs_body() {
+	atf_check \
+		-o "inline:a1a2aaa\n\n" \
+		-x "echo a1a2aaa | $awk 1 RS='a$'"
+
+}
+
+atf_test_case regex_reallocation_rs
+
+regex_reallocation_rs_head() {
+	atf_set "descr" "Test awk(1) with regex reallocation RS"
+}
+
+regex_reallocation_rs_body() {
+	atf_check \
+		-o "inline:a\na\na\na\na\na\na\na\na\na10000\n\n" \
+		-x "jot -s a 10000 | $awk 'NR>1' RS='999[0-9]'"
+
+}
+
+atf_test_case empty_rs
+
+empty_rs_head() {
+	atf_set "descr" "Test awk(1) with empty RS"
+}
+
+empty_rs_body() {
+	atf_check \
+		-o "inline:foo\n" \
+		-x "echo foo | $awk 1 RS=''"
+
+}
+
+atf_test_case newline_rs
+
+newline_rs_head() {
+	atf_set "descr" "Test awk(1) with newline RS"
+}
+
+newline_rs_body() {
+	atf_check \
+		-o "inline:r1f1:r1f2\nr2f1:r2f2\n" \
+		-x "printf '\n\n\nr1f1\nr1f2\n\nr2f1\nr2f2\n\n\n' | $awk '{\$1=\$1}1' RS= OFS=:"
+}
+
+atf_test_case modify_subsep
+
+modify_subsep_head() {
+	atf_set "descr" "Test awk(1) SUPSEP modification (PR/47306)"
+}
+
+modify_subsep_body() {
+	atf_check \
+		-o "inline:1\n1\n1\n" \
+		-x "printf '1\n1 2\n' | \
+		$awk '1{ arr[\$1 SUBSEP \$2 SUBSEP ++cnt[\$1]]=1} {for (f in arr) print arr[f];}'"
+}
+
+atf_init_test_cases() {
+
+	atf_add_test_case big_regexp
+	atf_add_test_case end
+	atf_add_test_case string1
+	atf_add_test_case multibyte
+	atf_add_test_case period
+	atf_add_test_case assign_NF
+
+	atf_add_test_case single_char_rs
+	atf_add_test_case two_char_rs
+	atf_add_test_case single_char_regex_group_rs
+	atf_add_test_case two_char_regex_group_rs
+	atf_add_test_case two_char_regex_star_rs
+	atf_add_test_case single_char_regex_star_rs
+	atf_add_test_case regex_two_star_rs
+	atf_add_test_case regex_or_1_rs
+	atf_add_test_case regex_or_2_rs
+	atf_add_test_case regex_or_3_rs
+	atf_add_test_case regex_caret_1_rs
+	atf_add_test_case regex_caret_2_rs
+	atf_add_test_case regex_dollar_1_rs
+	atf_add_test_case regex_dollar_2_rs
+	atf_add_test_case regex_reallocation_rs
+	atf_add_test_case empty_rs
+	atf_add_test_case newline_rs
+	atf_add_test_case modify_subsep
+}