For robustness, let me add tests against the glibc bug
https://sourceware.org/bugzilla/show_bug.cgi?id=19932
also to the mb*c32* unit tests.
Here, no fixes are needed, since the fixes are already in the mb*wc*
and mbrtoc32 modules.
2023-04-03 Bruno Haible <br...@clisp.org>
mbstoc32s tests: Check behaviour in the C locale.
* tests/test-mbstoc32s.c (main): Test behaviour in the C locale. Based
on tests/test-mbstowcs.c.
* tests/test-mbstoc32s-5.sh: New file, based on tests/test-mbstowcs5.sh.
* modules/mbstoc32s-tests (Files): Add it.
(Depends-on): Add btoc32.
(Makefile.am): Run test-mbstoc32s-5.sh.
2023-04-03 Bruno Haible <br...@clisp.org>
mbsnrtoc32s tests: Check behaviour in the C locale.
* tests/test-mbsnrtoc32s.c (main): Test behaviour in the C locale. Based
on tests/test-mbsnrtowcs.c.
* tests/test-mbsnrtoc32s-5.sh: New file, based on
tests/test-mbsrtowcs5.sh.
* modules/mbsnrtoc32s-tests (Files): Add it.
(Depends-on): Add btoc32.
(Makefile.am): Run test-mbsnrtoc32s-5.sh.
2023-04-03 Bruno Haible <br...@clisp.org>
mbsrtoc32s tests: Check behaviour in the C locale.
* tests/test-mbsrtoc32s.c (main): Test behaviour in the C locale. Based
on tests/test-mbsrtowcs.c.
* tests/test-mbsrtoc32s-5.sh: New file, based on
tests/test-mbsrtowcs5.sh.
* modules/mbsrtoc32s-tests (Files): Add it.
(Depends-on): Add btoc32.
(Makefile.am): Run test-mbsrtoc32s-5.sh.
2023-04-03 Bruno Haible <br...@clisp.org>
btoc32 tests: Check behaviour in the C locale.
* tests/test-btoc32.c (main): Test behaviour in the C locale. Based on
tests/test-btowc.c.
* tests/test-btoc32-3.sh: New file, based on tests/test-btowc3.sh.
* modules/btoc32-tests (Files): Add it.
(Makefile.am): Test it.
2023-04-03 Bruno Haible <br...@clisp.org>
mbrtoc32 tests: Prefer *c32* functions.
* tests/test-mbrtoc32.c (main): Use btoc32 instead of btowc.
* modules/mbrtoc32-tests (Depends-on): Add btoc32.
2023-04-03 Bruno Haible <br...@clisp.org>
mbrtoc32 tests: Add comment.
* m4/mbrtowc.m4 (gl_MBRTOWC_C_LOCALE): Add comment.
* m4/mbrtoc32.m4 (gl_MBRTOC32_C_LOCALE): Add comment.
* tests/test-mbrtoc32.c: Add comment.
* tests/test-mbrtoc32-5.sh: Use symmetric coding style.
* doc/posix-functions/mbrtoc32.texi: Update.
>From 09a9ccc95ddd3e4ffbf386cca440b944c91d3412 Mon Sep 17 00:00:00 2001
From: Bruno Haible <br...@clisp.org>
Date: Mon, 3 Apr 2023 14:24:37 +0200
Subject: [PATCH 1/6] mbrtoc32 tests: Add comment.
* m4/mbrtowc.m4 (gl_MBRTOWC_C_LOCALE): Add comment.
* m4/mbrtoc32.m4 (gl_MBRTOC32_C_LOCALE): Add comment.
* tests/test-mbrtoc32.c: Add comment.
* tests/test-mbrtoc32-5.sh: Use symmetric coding style.
* doc/posix-functions/mbrtoc32.texi: Update.
---
ChangeLog | 9 +++++++++
doc/posix-functions/mbrtoc32.texi | 2 +-
m4/mbrtoc32.m4 | 7 ++++++-
m4/mbrtowc.m4 | 4 ++++
tests/test-mbrtoc32-5.sh | 7 +++++--
tests/test-mbrtoc32.c | 4 ++++
6 files changed, 29 insertions(+), 4 deletions(-)
diff --git a/ChangeLog b/ChangeLog
index 2993b1561f..7bc1a008f1 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2023-04-03 Bruno Haible <br...@clisp.org>
+
+ mbrtoc32 tests: Add comment.
+ * m4/mbrtowc.m4 (gl_MBRTOWC_C_LOCALE): Add comment.
+ * m4/mbrtoc32.m4 (gl_MBRTOC32_C_LOCALE): Add comment.
+ * tests/test-mbrtoc32.c: Add comment.
+ * tests/test-mbrtoc32-5.sh: Use symmetric coding style.
+ * doc/posix-functions/mbrtoc32.texi: Update.
+
2023-04-02 Bruno Haible <br...@clisp.org>
trim: Fix trim_trailing result in multibyte locales.
diff --git a/doc/posix-functions/mbrtoc32.texi b/doc/posix-functions/mbrtoc32.texi
index d95c670200..7c3d6c294a 100644
--- a/doc/posix-functions/mbrtoc32.texi
+++ b/doc/posix-functions/mbrtoc32.texi
@@ -12,7 +12,7 @@
@item
In the C or POSIX locales, this function can return @code{(size_t) -1}
and set @code{errno} to @code{EILSEQ}:
-glibc 2.23.
+glibc 2.35.
@item
This function returns 0 instead of @code{(size_t) -2} when the input
is empty:
diff --git a/m4/mbrtoc32.m4 b/m4/mbrtoc32.m4
index f2de33aff6..d6401fe2e4 100644
--- a/m4/mbrtoc32.m4
+++ b/m4/mbrtoc32.m4
@@ -1,4 +1,4 @@
-# mbrtoc32.m4 serial 10
+# mbrtoc32.m4 serial 11
dnl Copyright (C) 2014-2023 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
@@ -101,6 +101,11 @@ AC_DEFUN([gl_MBRTOC32_EMPTY_INPUT]
])
])
+dnl <https://pubs.opengroup.org/onlinepubs/9699919799/functions/mbrtowc.html>
+dnl POSIX:2018 says regarding mbrtowc: "In the POSIX locale an [EILSEQ] error
+dnl cannot occur since all byte values are valid characters." It is reasonable
+dnl to expect mbrtoc32 to behave in the same way.
+
AC_DEFUN([gl_MBRTOC32_C_LOCALE],
[
AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles
diff --git a/m4/mbrtowc.m4 b/m4/mbrtowc.m4
index 4bf91bec3b..0c7a8bae69 100644
--- a/m4/mbrtowc.m4
+++ b/m4/mbrtowc.m4
@@ -712,6 +712,10 @@ AC_DEFUN([gl_MBRTOWC_EMPTY_INPUT]
dnl Although POSIX was never intended to allow this, the GNU C Library
dnl and other implementations do it. See:
dnl https://sourceware.org/bugzilla/show_bug.cgi?id=19932
+dnl POSIX has now clarified it:
+dnl <https://pubs.opengroup.org/onlinepubs/9699919799/functions/mbrtowc.html>
+dnl says: "In the POSIX locale an [EILSEQ] error cannot occur since all byte
+dnl values are valid characters."
AC_DEFUN([gl_MBRTOWC_C_LOCALE],
[
diff --git a/tests/test-mbrtoc32-5.sh b/tests/test-mbrtoc32-5.sh
index cd000fb3c7..4213772272 100755
--- a/tests/test-mbrtoc32-5.sh
+++ b/tests/test-mbrtoc32-5.sh
@@ -1,6 +1,9 @@
#!/bin/sh
+
# Test whether the POSIX locale has encoding errors.
LC_ALL=C \
-${CHECKER} ./test-mbrtoc32${EXEEXT} 5 || exit
+${CHECKER} ./test-mbrtoc32${EXEEXT} 5 || exit 1
LC_ALL=POSIX \
-${CHECKER} ./test-mbrtoc32${EXEEXT} 5
+${CHECKER} ./test-mbrtoc32${EXEEXT} 5 || exit 1
+
+exit 0
diff --git a/tests/test-mbrtoc32.c b/tests/test-mbrtoc32.c
index 0d75c3db14..a40309004e 100644
--- a/tests/test-mbrtoc32.c
+++ b/tests/test-mbrtoc32.c
@@ -386,6 +386,10 @@ main (int argc, char *argv[])
wc = (char32_t) 0xBADFACE;
ret = mbrtoc32 (&wc, buf, 1, &state);
+ /* POSIX:2018 says regarding mbrtowc: "In the POSIX locale an
+ [EILSEQ] error cannot occur since all byte values are valid
+ characters." It is reasonable to expect mbrtoc32 to behave
+ in the same way. */
ASSERT (ret == 1);
if (c < 0x80)
/* c is an ASCII character. */
--
2.34.1
>From 13679eb960abb41db5557bf364d7b31bc27d6f55 Mon Sep 17 00:00:00 2001
From: Bruno Haible <br...@clisp.org>
Date: Mon, 3 Apr 2023 14:24:39 +0200
Subject: [PATCH 2/6] mbrtoc32 tests: Prefer *c32* functions.
* tests/test-mbrtoc32.c (main): Use btoc32 instead of btowc.
* modules/mbrtoc32-tests (Depends-on): Add btoc32.
---
ChangeLog | 6 ++++++
modules/mbrtoc32-tests | 1 +
tests/test-mbrtoc32.c | 2 +-
3 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/ChangeLog b/ChangeLog
index 7bc1a008f1..901aa4331a 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2023-04-03 Bruno Haible <br...@clisp.org>
+
+ mbrtoc32 tests: Prefer *c32* functions.
+ * tests/test-mbrtoc32.c (main): Use btoc32 instead of btowc.
+ * modules/mbrtoc32-tests (Depends-on): Add btoc32.
+
2023-04-03 Bruno Haible <br...@clisp.org>
mbrtoc32 tests: Add comment.
diff --git a/modules/mbrtoc32-tests b/modules/mbrtoc32-tests
index e123772a20..95cc4750bd 100644
--- a/modules/mbrtoc32-tests
+++ b/modules/mbrtoc32-tests
@@ -22,6 +22,7 @@ m4/codeset.m4
Depends-on:
mbsinit
+btoc32
c32tob
setlocale
localcharset
diff --git a/tests/test-mbrtoc32.c b/tests/test-mbrtoc32.c
index a40309004e..ecde031f36 100644
--- a/tests/test-mbrtoc32.c
+++ b/tests/test-mbrtoc32.c
@@ -397,7 +397,7 @@ main (int argc, char *argv[])
else
/* On most platforms, the bytes 0x80..0xFF map to U+0080..U+00FF.
But on musl libc, the bytes 0x80..0xFF map to U+DF80..U+DFFF. */
- ASSERT (wc == (btowc (c) == 0xDF00 + c ? btowc (c) : c));
+ ASSERT (wc == (btoc32 (c) == 0xDF00 + c ? btoc32 (c) : c));
ASSERT (mbsinit (&state));
ret = mbrtoc32 (NULL, buf, 1, &state);
--
2.34.1
From d36467df509b488bc069a3c247a3ee595874f431 Mon Sep 17 00:00:00 2001
From: Bruno Haible <br...@clisp.org>
Date: Mon, 3 Apr 2023 14:24:42 +0200
Subject: [PATCH 3/6] btoc32 tests: Check behaviour in the C locale.
* tests/test-btoc32.c (main): Test behaviour in the C locale. Based on
tests/test-btowc.c.
* tests/test-btoc32-3.sh: New file, based on tests/test-btowc3.sh.
* modules/btoc32-tests (Files): Add it.
(Makefile.am): Test it.
---
ChangeLog | 9 +++++++++
modules/btoc32-tests | 3 ++-
tests/test-btoc32-3.sh | 9 +++++++++
tests/test-btoc32.c | 30 ++++++++++++++++++++++++++++++
4 files changed, 50 insertions(+), 1 deletion(-)
create mode 100755 tests/test-btoc32-3.sh
diff --git a/ChangeLog b/ChangeLog
index 901aa4331a..b05eb8f846 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2023-04-03 Bruno Haible <br...@clisp.org>
+
+ btoc32 tests: Check behaviour in the C locale.
+ * tests/test-btoc32.c (main): Test behaviour in the C locale. Based on
+ tests/test-btowc.c.
+ * tests/test-btoc32-3.sh: New file, based on tests/test-btowc3.sh.
+ * modules/btoc32-tests (Files): Add it.
+ (Makefile.am): Test it.
+
2023-04-03 Bruno Haible <br...@clisp.org>
mbrtoc32 tests: Prefer *c32* functions.
diff --git a/modules/btoc32-tests b/modules/btoc32-tests
index b3373f3cf8..b9d14eefd1 100644
--- a/modules/btoc32-tests
+++ b/modules/btoc32-tests
@@ -1,6 +1,7 @@
Files:
tests/test-btoc32-1.sh
tests/test-btoc32-2.sh
+tests/test-btoc32-3.sh
tests/test-btoc32.c
tests/signature.h
tests/macros.h
@@ -15,7 +16,7 @@ gt_LOCALE_FR
gt_LOCALE_FR_UTF8
Makefile.am:
-TESTS += test-btoc32-1.sh test-btoc32-2.sh
+TESTS += test-btoc32-1.sh test-btoc32-2.sh test-btoc32-3.sh
TESTS_ENVIRONMENT += LOCALE_FR='@LOCALE_FR@' LOCALE_FR_UTF8='@LOCALE_FR_UTF8@'
check_PROGRAMS += test-btoc32
test_btoc32_LDADD = $(LDADD) $(SETLOCALE_LIB)
diff --git a/tests/test-btoc32-3.sh b/tests/test-btoc32-3.sh
new file mode 100755
index 0000000000..422c3daed5
--- /dev/null
+++ b/tests/test-btoc32-3.sh
@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Test whether the POSIX locale has encoding errors.
+LC_ALL=C \
+${CHECKER} ./test-btoc32${EXEEXT} 3 || exit 1
+LC_ALL=POSIX \
+${CHECKER} ./test-btoc32${EXEEXT} 3 || exit 1
+
+exit 0
diff --git a/tests/test-btoc32.c b/tests/test-btoc32.c
index 90b38cfcf5..a2c48dde6f 100644
--- a/tests/test-btoc32.c
+++ b/tests/test-btoc32.c
@@ -40,6 +40,15 @@ main (int argc, char *argv[])
ASSERT (btoc32 (EOF) == WEOF);
+#ifdef __ANDROID__
+ /* On Android ≥ 5.0, the default locale is the "C.UTF-8" locale, not the
+ "C" locale. Furthermore, when you attempt to set the "C" or "POSIX"
+ locale via setlocale(), what you get is a "C" locale with UTF-8 encoding,
+ that is, effectively the "C.UTF-8" locale. */
+ if (argc > 1 && strcmp (argv[1], "3") == 0 && MB_CUR_MAX > 1)
+ argv[1] = "2";
+#endif
+
if (argc > 1)
switch (argv[1][0])
{
@@ -58,6 +67,27 @@ main (int argc, char *argv[])
for (c = 0x80; c < 0x100; c++)
ASSERT (btoc32 (c) == WEOF);
return 0;
+
+ case '3':
+ /* C or POSIX locale. */
+ for (c = 0; c < 0x100; c++)
+ if (c != 0)
+ {
+ /* We are testing all nonnull bytes. */
+ wint_t wc = btoc32 (c);
+ /* POSIX:2018 says regarding btowc: "In the POSIX locale, btowc()
+ shall not return WEOF if c has a value in the range 0 to 255
+ inclusive." It is reasonable to expect btoc32 to behave in
+ the same way. */
+ if (c < 0x80)
+ /* c is an ASCII character. */
+ ASSERT (wc == c);
+ else
+ /* On most platforms, the bytes 0x80..0xFF map to U+0080..U+00FF.
+ But on musl libc, the bytes 0x80..0xFF map to U+DF80..U+DFFF. */
+ ASSERT (wc == c || wc == 0xDF00 + c);
+ }
+ return 0;
}
return 1;
--
2.34.1
From db6135d5d5bc642bb8c95c384512f3f1aff68ebb Mon Sep 17 00:00:00 2001
From: Bruno Haible <br...@clisp.org>
Date: Mon, 3 Apr 2023 14:24:45 +0200
Subject: [PATCH 4/6] mbsrtoc32s tests: Check behaviour in the C locale.
* tests/test-mbsrtoc32s.c (main): Test behaviour in the C locale. Based
on tests/test-mbsrtowcs.c.
* tests/test-mbsrtoc32s-5.sh: New file, based on
tests/test-mbsrtowcs5.sh.
* modules/mbsrtoc32s-tests (Files): Add it.
(Depends-on): Add btoc32.
(Makefile.am): Run test-mbsrtoc32s-5.sh.
---
ChangeLog | 11 ++++++
modules/mbsrtoc32s-tests | 6 ++-
tests/test-mbsrtoc32s-5.sh | 9 +++++
tests/test-mbsrtoc32s.c | 77 ++++++++++++++++++++++++++++++++++++++
4 files changed, 102 insertions(+), 1 deletion(-)
create mode 100755 tests/test-mbsrtoc32s-5.sh
diff --git a/ChangeLog b/ChangeLog
index b05eb8f846..7fbb423791 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,14 @@
+2023-04-03 Bruno Haible <br...@clisp.org>
+
+ mbsrtoc32s tests: Check behaviour in the C locale.
+ * tests/test-mbsrtoc32s.c (main): Test behaviour in the C locale. Based
+ on tests/test-mbsrtowcs.c.
+ * tests/test-mbsrtoc32s-5.sh: New file, based on
+ tests/test-mbsrtowcs5.sh.
+ * modules/mbsrtoc32s-tests (Files): Add it.
+ (Depends-on): Add btoc32.
+ (Makefile.am): Run test-mbsrtoc32s-5.sh.
+
2023-04-03 Bruno Haible <br...@clisp.org>
btoc32 tests: Check behaviour in the C locale.
diff --git a/modules/mbsrtoc32s-tests b/modules/mbsrtoc32s-tests
index f794c5ae32..0adc62368e 100644
--- a/modules/mbsrtoc32s-tests
+++ b/modules/mbsrtoc32s-tests
@@ -3,6 +3,7 @@ tests/test-mbsrtoc32s-1.sh
tests/test-mbsrtoc32s-2.sh
tests/test-mbsrtoc32s-3.sh
tests/test-mbsrtoc32s-4.sh
+tests/test-mbsrtoc32s-5.sh
tests/test-mbsrtoc32s.c
tests/signature.h
tests/macros.h
@@ -14,6 +15,7 @@ m4/codeset.m4
Depends-on:
mbrtoc32
mbsinit
+btoc32
c32tob
setlocale
@@ -24,7 +26,9 @@ gt_LOCALE_JA
gt_LOCALE_ZH_CN
Makefile.am:
-TESTS += test-mbsrtoc32s-1.sh test-mbsrtoc32s-2.sh test-mbsrtoc32s-3.sh test-mbsrtoc32s-4.sh
+TESTS += \
+ test-mbsrtoc32s-1.sh test-mbsrtoc32s-2.sh test-mbsrtoc32s-3.sh \
+ test-mbsrtoc32s-4.sh test-mbsrtoc32s-5.sh
TESTS_ENVIRONMENT += \
LOCALE_FR='@LOCALE_FR@' \
LOCALE_FR_UTF8='@LOCALE_FR_UTF8@' \
diff --git a/tests/test-mbsrtoc32s-5.sh b/tests/test-mbsrtoc32s-5.sh
new file mode 100755
index 0000000000..fb922b2b26
--- /dev/null
+++ b/tests/test-mbsrtoc32s-5.sh
@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Test whether the POSIX locale has encoding errors.
+LC_ALL=C \
+${CHECKER} ./test-mbsrtoc32s${EXEEXT} 5 || exit 1
+LC_ALL=POSIX \
+${CHECKER} ./test-mbsrtoc32s${EXEEXT} 5 || exit 1
+
+exit 0
diff --git a/tests/test-mbsrtoc32s.c b/tests/test-mbsrtoc32s.c
index ef985fdc03..aed9d7b2fb 100644
--- a/tests/test-mbsrtoc32s.c
+++ b/tests/test-mbsrtoc32s.c
@@ -72,6 +72,15 @@ main (int argc, char *argv[])
ASSERT (mbsinit (&state));
}
+#ifdef __ANDROID__
+ /* On Android ≥ 5.0, the default locale is the "C.UTF-8" locale, not the
+ "C" locale. Furthermore, when you attempt to set the "C" or "POSIX"
+ locale via setlocale(), what you get is a "C" locale with UTF-8 encoding,
+ that is, effectively the "C.UTF-8" locale. */
+ if (argc > 1 && strcmp (argv[1], "5") == 0 && MB_CUR_MAX > 1)
+ argv[1] = "2";
+#endif
+
if (argc > 1)
{
int unlimited;
@@ -281,6 +290,74 @@ main (int argc, char *argv[])
}
break;
+ case '5':
+ /* C or POSIX locale. */
+ {
+ char input[] = "n/a";
+ memset (&state, '\0', sizeof (mbstate_t));
+
+ src = input;
+ temp_state = state;
+ ret = mbsrtoc32s (NULL, &src, unlimited ? BUFSIZE : 1, &temp_state);
+ ASSERT (ret == 3);
+ ASSERT (src == input);
+ ASSERT (mbsinit (&state));
+
+ src = input;
+ ret = mbsrtoc32s (buf, &src, unlimited ? BUFSIZE : 1, &state);
+ ASSERT (ret == (unlimited ? 3 : 1));
+ ASSERT (src == (unlimited ? NULL : input + 1));
+ ASSERT (buf[0] == 'n');
+ if (unlimited)
+ {
+ ASSERT (buf[1] == '/');
+ ASSERT (buf[2] == 'a');
+ ASSERT (buf[3] == 0);
+ ASSERT (buf[4] == (char32_t) 0xBADFACE);
+ }
+ else
+ ASSERT (buf[1] == (char32_t) 0xBADFACE);
+ ASSERT (mbsinit (&state));
+ }
+ {
+ int c;
+ char input[2];
+
+ memset (&state, '\0', sizeof (mbstate_t));
+ for (c = 0; c < 0x100; c++)
+ if (c != 0)
+ {
+ /* We are testing all nonnull bytes. */
+ input[0] = c;
+ input[1] = '\0';
+
+ src = input;
+ ret = mbsrtoc32s (NULL, &src, unlimited ? BUFSIZE : 1, &state);
+ ASSERT (ret == 1);
+ ASSERT (src == input);
+ ASSERT (mbsinit (&state));
+
+ buf[0] = buf[1] = (char32_t) 0xBADFACE;
+ src = input;
+ ret = mbsrtoc32s (buf, &src, unlimited ? BUFSIZE : 1, &state);
+ /* POSIX:2018 says regarding mbsrtowcs: "In the POSIX locale an
+ [EILSEQ] error cannot occur since all byte values are valid
+ characters." It is reasonable to expect mbsrtoc32s to behave
+ in the same way. */
+ ASSERT (ret == 1);
+ ASSERT (src == (unlimited ? NULL : input + 1));
+ if (c < 0x80)
+ /* c is an ASCII character. */
+ ASSERT (buf[0] == c);
+ else
+ /* On most platforms, the bytes 0x80..0xFF map to U+0080..U+00FF.
+ But on musl libc, the bytes 0x80..0xFF map to U+DF80..U+DFFF. */
+ ASSERT (buf[0] == (btoc32 (c) == 0xDF00 + c ? btoc32 (c) : c));
+ ASSERT (mbsinit (&state));
+ }
+ }
+ break;
+
default:
return 1;
}
--
2.34.1
From 52178721fa208bade898c3d14aed806e87bce642 Mon Sep 17 00:00:00 2001
From: Bruno Haible <br...@clisp.org>
Date: Mon, 3 Apr 2023 14:24:48 +0200
Subject: [PATCH 5/6] mbsnrtoc32s tests: Check behaviour in the C locale.
* tests/test-mbsnrtoc32s.c (main): Test behaviour in the C locale. Based
on tests/test-mbsnrtowcs.c.
* tests/test-mbsnrtoc32s-5.sh: New file, based on
tests/test-mbsrtowcs5.sh.
* modules/mbsnrtoc32s-tests (Files): Add it.
(Depends-on): Add btoc32.
(Makefile.am): Run test-mbsnrtoc32s-5.sh.
---
ChangeLog | 11 ++++++
modules/mbsnrtoc32s-tests | 6 ++-
tests/test-mbsnrtoc32s-5.sh | 9 +++++
tests/test-mbsnrtoc32s.c | 77 +++++++++++++++++++++++++++++++++++++
4 files changed, 102 insertions(+), 1 deletion(-)
create mode 100755 tests/test-mbsnrtoc32s-5.sh
diff --git a/ChangeLog b/ChangeLog
index 7fbb423791..4699781f9f 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,14 @@
+2023-04-03 Bruno Haible <br...@clisp.org>
+
+ mbsnrtoc32s tests: Check behaviour in the C locale.
+ * tests/test-mbsnrtoc32s.c (main): Test behaviour in the C locale. Based
+ on tests/test-mbsnrtowcs.c.
+ * tests/test-mbsnrtoc32s-5.sh: New file, based on
+ tests/test-mbsrtowcs5.sh.
+ * modules/mbsnrtoc32s-tests (Files): Add it.
+ (Depends-on): Add btoc32.
+ (Makefile.am): Run test-mbsnrtoc32s-5.sh.
+
2023-04-03 Bruno Haible <br...@clisp.org>
mbsrtoc32s tests: Check behaviour in the C locale.
diff --git a/modules/mbsnrtoc32s-tests b/modules/mbsnrtoc32s-tests
index 449c277aa0..c7af163045 100644
--- a/modules/mbsnrtoc32s-tests
+++ b/modules/mbsnrtoc32s-tests
@@ -3,6 +3,7 @@ tests/test-mbsnrtoc32s-1.sh
tests/test-mbsnrtoc32s-2.sh
tests/test-mbsnrtoc32s-3.sh
tests/test-mbsnrtoc32s-4.sh
+tests/test-mbsnrtoc32s-5.sh
tests/test-mbsnrtoc32s.c
tests/signature.h
tests/macros.h
@@ -14,6 +15,7 @@ m4/codeset.m4
Depends-on:
mbrtoc32
mbsinit
+btoc32
c32tob
setlocale
@@ -24,7 +26,9 @@ gt_LOCALE_JA
gt_LOCALE_ZH_CN
Makefile.am:
-TESTS += test-mbsnrtoc32s-1.sh test-mbsnrtoc32s-2.sh test-mbsnrtoc32s-3.sh test-mbsnrtoc32s-4.sh
+TESTS += \
+ test-mbsnrtoc32s-1.sh test-mbsnrtoc32s-2.sh test-mbsnrtoc32s-3.sh \
+ test-mbsnrtoc32s-4.sh test-mbsnrtoc32s-5.sh
TESTS_ENVIRONMENT += \
LOCALE_FR='@LOCALE_FR@' \
LOCALE_FR_UTF8='@LOCALE_FR_UTF8@' \
diff --git a/tests/test-mbsnrtoc32s-5.sh b/tests/test-mbsnrtoc32s-5.sh
new file mode 100755
index 0000000000..768d10b1e8
--- /dev/null
+++ b/tests/test-mbsnrtoc32s-5.sh
@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Test whether the POSIX locale has encoding errors.
+LC_ALL=C \
+${CHECKER} ./test-mbsnrtoc32s${EXEEXT} 5 || exit 1
+LC_ALL=POSIX \
+${CHECKER} ./test-mbsnrtoc32s${EXEEXT} 5 || exit 1
+
+exit 0
diff --git a/tests/test-mbsnrtoc32s.c b/tests/test-mbsnrtoc32s.c
index 88c11f5e47..c18b66ab06 100644
--- a/tests/test-mbsnrtoc32s.c
+++ b/tests/test-mbsnrtoc32s.c
@@ -72,6 +72,15 @@ main (int argc, char *argv[])
ASSERT (mbsinit (&state));
}
+#ifdef __ANDROID__
+ /* On Android ≥ 5.0, the default locale is the "C.UTF-8" locale, not the
+ "C" locale. Furthermore, when you attempt to set the "C" or "POSIX"
+ locale via setlocale(), what you get is a "C" locale with UTF-8 encoding,
+ that is, effectively the "C.UTF-8" locale. */
+ if (argc > 1 && strcmp (argv[1], "5") == 0 && MB_CUR_MAX > 1)
+ argv[1] = "2";
+#endif
+
if (argc > 1)
{
int unlimited;
@@ -281,6 +290,74 @@ main (int argc, char *argv[])
}
break;
+ case '5':
+ /* C or POSIX locale. */
+ {
+ char input[] = "n/a";
+ memset (&state, '\0', sizeof (mbstate_t));
+
+ src = input;
+ temp_state = state;
+ ret = mbsnrtoc32s (NULL, &src, 4, unlimited ? BUFSIZE : 1, &temp_state);
+ ASSERT (ret == 3);
+ ASSERT (src == input);
+ ASSERT (mbsinit (&state));
+
+ src = input;
+ ret = mbsnrtoc32s (buf, &src, 4, unlimited ? BUFSIZE : 1, &state);
+ ASSERT (ret == (unlimited ? 3 : 1));
+ ASSERT (src == (unlimited ? NULL : input + 1));
+ ASSERT (buf[0] == 'n');
+ if (unlimited)
+ {
+ ASSERT (buf[1] == '/');
+ ASSERT (buf[2] == 'a');
+ ASSERT (buf[3] == 0);
+ ASSERT (buf[4] == (char32_t) 0xBADFACE);
+ }
+ else
+ ASSERT (buf[1] == (char32_t) 0xBADFACE);
+ ASSERT (mbsinit (&state));
+ }
+ {
+ int c;
+ char input[2];
+
+ memset (&state, '\0', sizeof (mbstate_t));
+ for (c = 0; c < 0x100; c++)
+ if (c != 0)
+ {
+ /* We are testing all nonnull bytes. */
+ input[0] = c;
+ input[1] = '\0';
+
+ src = input;
+ ret = mbsnrtoc32s (NULL, &src, 2, unlimited ? BUFSIZE : 1, &state);
+ ASSERT (ret == 1);
+ ASSERT (src == input);
+ ASSERT (mbsinit (&state));
+
+ buf[0] = buf[1] = (char32_t) 0xBADFACE;
+ src = input;
+ ret = mbsnrtoc32s (buf, &src, 2, unlimited ? BUFSIZE : 1, &state);
+ /* POSIX:2018 says regarding mbsnrtowcs: "In the POSIX locale an
+ [EILSEQ] error cannot occur since all byte values are valid
+ characters." It is reasonable to expect mbsnrtoc32s to behave
+ in the same way. */
+ ASSERT (ret == 1);
+ ASSERT (src == (unlimited ? NULL : input + 1));
+ if (c < 0x80)
+ /* c is an ASCII character. */
+ ASSERT (buf[0] == c);
+ else
+ /* On most platforms, the bytes 0x80..0xFF map to U+0080..U+00FF.
+ But on musl libc, the bytes 0x80..0xFF map to U+DF80..U+DFFF. */
+ ASSERT (buf[0] == (btoc32 (c) == 0xDF00 + c ? btoc32 (c) : c));
+ ASSERT (mbsinit (&state));
+ }
+ }
+ break;
+
default:
return 1;
}
--
2.34.1
From 144cf2bd1009ecc82ea289fa2b05d89d7555f458 Mon Sep 17 00:00:00 2001
From: Bruno Haible <br...@clisp.org>
Date: Mon, 3 Apr 2023 14:24:50 +0200
Subject: [PATCH 6/6] mbstoc32s tests: Check behaviour in the C locale.
* tests/test-mbstoc32s.c (main): Test behaviour in the C locale. Based
on tests/test-mbstowcs.c.
* tests/test-mbstoc32s-5.sh: New file, based on tests/test-mbstowcs5.sh.
* modules/mbstoc32s-tests (Files): Add it.
(Depends-on): Add btoc32.
(Makefile.am): Run test-mbstoc32s-5.sh.
---
ChangeLog | 10 ++++++
modules/mbstoc32s-tests | 6 +++-
tests/test-mbstoc32s-5.sh | 9 ++++++
tests/test-mbstoc32s.c | 66 +++++++++++++++++++++++++++++++++++++++
4 files changed, 90 insertions(+), 1 deletion(-)
create mode 100755 tests/test-mbstoc32s-5.sh
diff --git a/ChangeLog b/ChangeLog
index 4699781f9f..5c916c133b 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,13 @@
+2023-04-03 Bruno Haible <br...@clisp.org>
+
+ mbstoc32s tests: Check behaviour in the C locale.
+ * tests/test-mbstoc32s.c (main): Test behaviour in the C locale. Based
+ on tests/test-mbstowcs.c.
+ * tests/test-mbstoc32s-5.sh: New file, based on tests/test-mbstowcs5.sh.
+ * modules/mbstoc32s-tests (Files): Add it.
+ (Depends-on): Add btoc32.
+ (Makefile.am): Run test-mbstoc32s-5.sh.
+
2023-04-03 Bruno Haible <br...@clisp.org>
mbsnrtoc32s tests: Check behaviour in the C locale.
diff --git a/modules/mbstoc32s-tests b/modules/mbstoc32s-tests
index 565796a06f..9e6dd61d26 100644
--- a/modules/mbstoc32s-tests
+++ b/modules/mbstoc32s-tests
@@ -3,6 +3,7 @@ tests/test-mbstoc32s-1.sh
tests/test-mbstoc32s-2.sh
tests/test-mbstoc32s-3.sh
tests/test-mbstoc32s-4.sh
+tests/test-mbstoc32s-5.sh
tests/test-mbstoc32s.c
tests/signature.h
tests/macros.h
@@ -12,6 +13,7 @@ m4/locale-zh.m4
m4/codeset.m4
Depends-on:
+btoc32
c32tob
setlocale
@@ -22,7 +24,9 @@ gt_LOCALE_JA
gt_LOCALE_ZH_CN
Makefile.am:
-TESTS += test-mbstoc32s-1.sh test-mbstoc32s-2.sh test-mbstoc32s-3.sh test-mbstoc32s-4.sh
+TESTS += \
+ test-mbstoc32s-1.sh test-mbstoc32s-2.sh test-mbstoc32s-3.sh \
+ test-mbstoc32s-4.sh test-mbstoc32s-5.sh
TESTS_ENVIRONMENT += \
LOCALE_FR='@LOCALE_FR@' \
LOCALE_FR_UTF8='@LOCALE_FR_UTF8@' \
diff --git a/tests/test-mbstoc32s-5.sh b/tests/test-mbstoc32s-5.sh
new file mode 100755
index 0000000000..edb36432b8
--- /dev/null
+++ b/tests/test-mbstoc32s-5.sh
@@ -0,0 +1,9 @@
+#!/bin/sh
+
+# Test whether the POSIX locale has encoding errors.
+LC_ALL=C \
+${CHECKER} ./test-mbstoc32s${EXEEXT} 5 || exit 1
+LC_ALL=POSIX \
+${CHECKER} ./test-mbstoc32s${EXEEXT} 5 || exit 1
+
+exit 0
diff --git a/tests/test-mbstoc32s.c b/tests/test-mbstoc32s.c
index 5358118906..e638999bb6 100644
--- a/tests/test-mbstoc32s.c
+++ b/tests/test-mbstoc32s.c
@@ -64,6 +64,15 @@ main (int argc, char *argv[])
ASSERT (wc == 0);
}
+#ifdef __ANDROID__
+ /* On Android ≥ 5.0, the default locale is the "C.UTF-8" locale, not the
+ "C" locale. Furthermore, when you attempt to set the "C" or "POSIX"
+ locale via setlocale(), what you get is a "C" locale with UTF-8 encoding,
+ that is, effectively the "C.UTF-8" locale. */
+ if (argc > 1 && strcmp (argv[1], "5") == 0 && MB_CUR_MAX > 1)
+ argv[1] = "2";
+#endif
+
if (argc > 1)
{
int unlimited;
@@ -232,6 +241,63 @@ main (int argc, char *argv[])
}
break;
+ case '5':
+ /* C or POSIX locale. */
+ {
+ char input[] = "n/a";
+
+ src = input;
+ ret = mbstoc32s (NULL, src, unlimited ? BUFSIZE : 1);
+ ASSERT (ret == 3);
+
+ src = input;
+ ret = mbstoc32s (buf, src, unlimited ? BUFSIZE : 1);
+ ASSERT (ret == (unlimited ? 3 : 1));
+ ASSERT (buf[0] == 'n');
+ if (unlimited)
+ {
+ ASSERT (buf[1] == '/');
+ ASSERT (buf[2] == 'a');
+ ASSERT (buf[3] == 0);
+ ASSERT (buf[4] == (char32_t) 0xBADFACE);
+ }
+ else
+ ASSERT (buf[1] == (char32_t) 0xBADFACE);
+ }
+ {
+ int c;
+ char input[2];
+
+ for (c = 0; c < 0x100; c++)
+ if (c != 0)
+ {
+ /* We are testing all nonnull bytes. */
+ input[0] = c;
+ input[1] = '\0';
+
+ src = input;
+ ret = mbstoc32s (NULL, src, unlimited ? BUFSIZE : 1);
+ ASSERT (ret == 1);
+
+ buf[0] = buf[1] = (char32_t) 0xBADFACE;
+ src = input;
+ ret = mbstoc32s (buf, src, unlimited ? BUFSIZE : 1);
+ /* POSIX:2018 says regarding mbstowcs: "In the POSIX locale an
+ [EILSEQ] error cannot occur since all byte values are valid
+ characters." It is reasonable to expect mbstoc32s to behave
+ in the same way. */
+ ASSERT (ret == 1);
+ if (c < 0x80)
+ /* c is an ASCII character. */
+ ASSERT (buf[0] == c);
+ else
+ /* On most platforms, the bytes 0x80..0xFF map to U+0080..U+00FF.
+ But on musl libc, the bytes 0x80..0xFF map to U+DF80..U+DFFF. */
+ ASSERT (buf[0] == (btoc32 (c) == 0xDF00 + c ? btoc32 (c) : c));
+ }
+ }
+ break;
+
default:
return 1;
}
--
2.34.1
