Single-byte locales use locale settings for ignoring case.

10 files changed, 48 insertions, 12 deletions

diff --git a/ChangeLog b/ChangeLog
index 37de7911..7eacd7ab 100755
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2019-04-05         Arnold D. Robbins     <arnold@skeeve.com>
+
+	* eval.c (load_casetable): Always use the locale's settings.
+	(set_IGNORECASE): Don't call load_casetable.
+	* main.c (main): Call load_casetable if in a single-byte locale.
+
 2019-03-22         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* config.guess: Updated from GNULIB.
diff --git a/NEWS b/NEWS
index d87e0d5c..04965129 100644
--- a/NEWS
+++ b/NEWS
@@ -44,5 +44,8 @@ Changes from 4.2.1 to 5.0.0
 
    	gawk -e 'BEGIN {' -e 'print "hello" }'
 
-12. A number of bugs, some of them quite significant, have been fixed.
+12. Gawk now uses the locale settings for ignoring case in single byte
+    locales, instead of hardwiring in Latin-1.
+
+13. A number of bugs, some of them quite significant, have been fixed.
     See the ChangeLog for details.
diff --git a/eval.c b/eval.c
index 4650150b..132c8509 100644
--- a/eval.c
+++ b/eval.c
@@ -104,6 +104,12 @@ char casetable[] = {
 	'\170', '\171', '\172', '\173', '\174', '\175', '\176', '\177',
 
 	/* Latin 1: */
+	/*
+	 * 4/2019: This is now overridden; in single byte locales
+	 * we call load_casetable from main and it fills in the values
+	 * based on the current locale. In particular, we want LC_ALL=C
+	 * to work correctly for values >= 0200.
+	 */
 	C('\200'), C('\201'), C('\202'), C('\203'), C('\204'), C('\205'), C('\206'), C('\207'),
 	C('\210'), C('\211'), C('\212'), C('\213'), C('\214'), C('\215'), C('\216'), C('\217'),
 	C('\220'), C('\221'), C('\222'), C('\223'), C('\224'), C('\225'), C('\226'), C('\227'),
@@ -201,18 +207,12 @@ load_casetable(void)
 {
 #if defined(LC_CTYPE)
 	int i;
-	char *cp;
 	static bool loaded = false;
 
 	if (loaded || do_traditional)
 		return;
 
 	loaded = true;
-	cp = setlocale(LC_CTYPE, NULL);
-
-	/* this is not per standard, but it's pretty safe */
-	if (cp == NULL || strcmp(cp, "C") == 0 || strcmp(cp, "POSIX") == 0)
-		return;
 
 #ifndef USE_EBCDIC
 	/* use of isalpha is ok here (see is_alpha in awkgram.y) */
@@ -710,7 +710,7 @@ set_IGNORECASE()
 		warned = true;
 		lintwarn(_("`IGNORECASE' is a gawk extension"));
 	}
-	load_casetable();
+
 	if (do_traditional)
 		IGNORECASE = false;
    	else
diff --git a/main.c b/main.c
index e2bcd724..d6e34266 100644
--- a/main.c
+++ b/main.c
@@ -320,6 +320,10 @@ main(int argc, char **argv)
 	/* init the cache for checking bytes if they're characters */
 	init_btowc_cache();
 
+	/* set up the single byte case table */
+	if (gawk_mb_cur_max == 1)
+		load_casetable();
+
 	if (do_nostalgia)
 		nostalgia();
 
diff --git a/test/ChangeLog b/test/ChangeLog
index de10e221..389edc9a 100644
--- a/test/ChangeLog
+++ b/test/ChangeLog
@@ -1,3 +1,8 @@
+2019-04-07         Arnold D. Robbins     <arnold@skeeve.com>
+
+	* Makefile.am (EXTRA_DIST): New test: range2. Needs LC_ALL=C.
+	* range2.awk, range2.ok: New files.
+
 2019-03-17         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* Makefile.am (mbprintf5): Add a minus so that the tests
diff --git a/test/Makefile.am b/test/Makefile.am
index 37d49848..57d0444c 100644
--- a/test/Makefile.am
+++ b/test/Makefile.am
@@ -946,6 +946,8 @@ EXTRA_DIST = \
 	range1.awk \
 	range1.in \
 	range1.ok \
+	range2.awk \
+	range2.ok \
 	readbuf.awk \
 	readbuf.ok \
 	readdir.awk \
@@ -1301,7 +1303,7 @@ BASIC_TESTS = \
 	paramasfunc1 paramasfunc2 paramdup paramres paramtyp paramuninitglobal \
 	parse1 parsefld parseme pcntplus posix2008sub prdupval prec printf0 \
 	printf1 printfchar prmarscl prmreuse prt1eval prtoeval \
-	rand randtest range1 readbuf rebrackloc rebt8b1 rebuild redfilnm regeq \
+	rand randtest range1 range2 readbuf rebrackloc rebt8b1 rebuild redfilnm regeq \
 	regexpbrack regexpbrack2 regexprange regrange reindops reparse resplit \
 	rri1 rs rscompat rsnul1nl rsnulbig rsnulbig2 rstest1 rstest2 rstest3 \
 	rstest4 rstest5 rswhite \
@@ -1422,7 +1424,7 @@ CHECK_MPFR = \
 
 # Lists of tests that need particular locales
 NEED_LOCALE_C = \
-	clos1way gsubtst6
+	clos1way gsubtst6 range2
 
 NEED_LOCALE_EN = \
 	backbigs1 backsmalls1 backsmalls2 concat4 dfamb1 ignrcas2 lc_num1 \
diff --git a/test/Makefile.in b/test/Makefile.in
index b4c62c15..fea54584 100644
--- a/test/Makefile.in
+++ b/test/Makefile.in
@@ -1205,6 +1205,8 @@ EXTRA_DIST = \
 	range1.awk \
 	range1.in \
 	range1.ok \
+	range2.awk \
+	range2.ok \
 	readbuf.awk \
 	readbuf.ok \
 	readdir.awk \
@@ -1560,7 +1562,7 @@ BASIC_TESTS = \
 	paramasfunc1 paramasfunc2 paramdup paramres paramtyp paramuninitglobal \
 	parse1 parsefld parseme pcntplus posix2008sub prdupval prec printf0 \
 	printf1 printfchar prmarscl prmreuse prt1eval prtoeval \
-	rand randtest range1 readbuf rebrackloc rebt8b1 rebuild redfilnm regeq \
+	rand randtest range1 range2 readbuf rebrackloc rebt8b1 rebuild redfilnm regeq \
 	regexpbrack regexpbrack2 regexprange regrange reindops reparse resplit \
 	rri1 rs rscompat rsnul1nl rsnulbig rsnulbig2 rstest1 rstest2 rstest3 \
 	rstest4 rstest5 rswhite \
@@ -1683,7 +1685,7 @@ CHECK_MPFR = \
 
 # Lists of tests that need particular locales
 NEED_LOCALE_C = \
-	clos1way gsubtst6
+	clos1way gsubtst6 range2
 
 NEED_LOCALE_EN = \
 	backbigs1 backsmalls1 backsmalls2 concat4 dfamb1 ignrcas2 lc_num1 \
@@ -3584,6 +3586,12 @@ range1:
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
 	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
 
+range2:
+	@echo $@
+	@[ -z "$$GAWKLOCALE" ] && GAWKLOCALE=C; export GAWKLOCALE; \
+	AWKPATH="$(srcdir)" $(AWK) -f $@.awk  >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
+	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
+
 readbuf:
 	@echo $@
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
diff --git a/test/Maketests b/test/Maketests
index 48b24333..e557cb2b 100644
--- a/test/Maketests
+++ b/test/Maketests
@@ -850,6 +850,12 @@ range1:
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
 	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
 
+range2:
+	@echo $@
+	@[ -z "$$GAWKLOCALE" ] && GAWKLOCALE=C; export GAWKLOCALE; \
+	AWKPATH="$(srcdir)" $(AWK) -f $@.awk  >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
+	@-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@
+
 readbuf:
 	@echo $@
 	@AWKPATH="$(srcdir)" $(AWK) -f $@.awk  >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@
diff --git a/test/range2.awk b/test/range2.awk
new file mode 100644
index 00000000..c4f11eaa
--- /dev/null
+++ b/test/range2.awk
@@ -0,0 +1 @@
+BEGIN { print("a" ~ /^[\300-\337]/) }
diff --git a/test/range2.ok b/test/range2.ok
new file mode 100644
index 00000000..573541ac
--- /dev/null
+++ b/test/range2.ok
@@ -0,0 +1 @@
+0