From db6135d5d5bc642bb8c95c384512f3f1aff68ebb Mon Sep 17 00:00:00 2001 From: Bruno Haible Date: Mon, 3 Apr 2023 14:24:45 +0200 Subject: [PATCH] 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 + + 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 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; } -- 2.39.5