upstream-mirrors/gnulib
1
0
Fork 0
mirror of https://https.git.savannah.gnu.org/git/gnulib.git synced 2026-05-13 15:13:36 +00:00
Code Activity

c32toupper: Add tests.

Browse Source 
* tests/test-c32toupper.sh: New file.
* tests/test-c32toupper.c: New file, based on tests/test-c32islower.c.
* modules/c32toupper-tests: New file.
This commit is contained in:
Bruno Haible
2023-04-10 01:51:54 +02:00
parent d47ae89803
commit 99fc85c723
4 changed files with 525 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ChangeLog
View File

@@ -1,5 +1,10 @@
2023-04-09 Bruno Haible <bruno@clisp.org>
c32toupper: Add tests.
* tests/test-c32toupper.sh: New file.
* tests/test-c32toupper.c: New file, based on tests/test-c32islower.c.
* modules/c32toupper-tests: New file.
c32toupper: New module.
* lib/uchar.in.h (c32toupper): New declaration.
* lib/c32toupper.c: New file.

30
modules/c32toupper-tests Normal file
View File

@@ -0,0 +1,30 @@
Files:
tests/test-c32toupper.sh
tests/test-c32toupper.c
tests/signature.h
tests/macros.h
m4/locale-fr.m4
m4/locale-ja.m4
m4/locale-zh.m4
m4/codeset.m4
Depends-on:
mbrtoc32
c32rtomb
setlocale
configure.ac:
gt_LOCALE_FR
gt_LOCALE_FR_UTF8
gt_LOCALE_JA
gt_LOCALE_ZH_CN
Makefile.am:
TESTS += test-c32toupper.sh
TESTS_ENVIRONMENT += \
LOCALE_FR='@LOCALE_FR@' \
LOCALE_FR_UTF8='@LOCALE_FR_UTF8@' \
LOCALE_JA='@LOCALE_JA@' \
LOCALE_ZH_CN='@LOCALE_ZH_CN@'
check_PROGRAMS += test-c32toupper
test_c32toupper_LDADD = $(LDADD) $(SETLOCALE_LIB) $(MBRTOWC_LIB) $(LIBUNISTRING)

448
tests/test-c32toupper.c Normal file
View File

@@ -0,0 +1,448 @@
/* Test of c32toupper() function.
Copyright (C) 2020-2023 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>. */
#include <config.h>
#include <uchar.h>
#include "signature.h"
SIGNATURE_CHECK (c32toupper, wint_t, (wint_t));
#include <locale.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>
#include "macros.h"
/* Representation of a multibyte character. */
#define MBCHAR_BUF_SIZE 6
struct multibyte
{
size_t nbytes; /* number of bytes of current character, > 0 */
char buf[MBCHAR_BUF_SIZE]; /* room for the bytes */
};
/* Returns the value of c32toupper for the multibyte character s[0..n-1],
as a multibyte character. */
static struct multibyte
for_character (const char *s, size_t n)
{
mbstate_t state;
char32_t wc;
size_t ret;
struct multibyte result;
memset (&state, '\0', sizeof (mbstate_t));
wc = (char32_t) 0xBADFACE;
ret = mbrtoc32 (&wc, s, n, &state);
ASSERT (ret == n);
wc = c32toupper (wc);
ASSERT (wc != WEOF);
memset (&state, '\0', sizeof (mbstate_t));
ret = c32rtomb (result.buf, wc, &state);
ASSERT (ret != 0);
if (ret == (size_t)(-1))
/* wc cannot be converted back to multibyte. */
result.nbytes = 0;
else
{
ASSERT (ret <= MBCHAR_BUF_SIZE);
result.nbytes = ret;
}
return result;
}
int
main (int argc, char *argv[])
{
wint_t wc;
struct multibyte mb;
char buf[4];
/* configure should already have checked that the locale is supported. */
if (setlocale (LC_ALL, "") == NULL)
return 1;
/* Test WEOF. */
wc = c32toupper (WEOF);
ASSERT (wc == WEOF);
/* Test single-byte characters.
POSIX specifies in
<https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html>
that
- in all locales, the lowercase characters include the a ... z
characters, and the corresponding characters A ... Z (if not in a
Turkish locale) are uppercase,
- in the "POSIX" locale (which is usually the same as the "C" locale),
the lowercase characters include only the ASCII a ... z characters,
and the corresponding characters A ... Z are uppercase.
*/
#if defined __NetBSD__
/* towupper is broken in the zh_CN.GB18030 locale on NetBSD 9.0.
See <https://gnats.netbsd.org/cgi-bin/query-pr-single.pl?number=57339>. */
if (!(argc > 1 && argv[1][0] == '4'))
#endif
{
int c;
for (c = 0; c < 0x100; c++)
switch (c)
{
case '\t': case '\v': case '\f':
case ' ': case '!': case '"': case '#': case '%':
case '&': case '\'': case '(': case ')': case '*':
case '+': case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>':
case '?':
case 'A': case 'B': case 'C': case 'D': case 'E':
case 'F': case 'G': case 'H': case 'I': case 'J':
case 'K': case 'L': case 'M': case 'N': case 'O':
case 'P': case 'Q': case 'R': case 'S': case 'T':
case 'U': case 'V': case 'W': case 'X': case 'Y':
case 'Z':
case '[': case '\\': case ']': case '^': case '_':
case 'a': case 'b': case 'c': case 'd': case 'e':
case 'f': case 'g': case 'h': case 'i': case 'j':
case 'k': case 'l': case 'm': case 'n': case 'o':
case 'p': case 'q': case 'r': case 's': case 't':
case 'u': case 'v': case 'w': case 'x': case 'y':
case 'z': case '{': case '|': case '}': case '~':
/* c is in the ISO C "basic character set". */
buf[0] = (unsigned char) c;
mb = for_character (buf, 1);
switch (c)
{
case 'a': case 'b': case 'c': case 'd': case 'e':
case 'f': case 'g': case 'h': case 'i': case 'j':
case 'k': case 'l': case 'm': case 'n': case 'o':
case 'p': case 'q': case 'r': case 's': case 't':
case 'u': case 'v': case 'w': case 'x': case 'y':
case 'z':
ASSERT (mb.nbytes == 1);
ASSERT ((unsigned char) mb.buf[0] == (unsigned char) c - 'a' + 'A');
break;
default:
ASSERT (mb.nbytes == 1);
ASSERT ((unsigned char) mb.buf[0] == c);
break;
}
break;
}
}
if (argc > 1)
switch (argv[1][0])
{
case '0':
/* C locale; tested above. */
return 0;
case '1':
/* Locale encoding is ISO-8859-1 or ISO-8859-15. */
{
/* U+00B2 SUPERSCRIPT TWO */
mb = for_character ("\262", 1);
ASSERT (mb.nbytes == 1);
ASSERT (memcmp (mb.buf, "\262", 1) == 0);
#if !(defined __GLIBC__ || defined __sun || defined __CYGWIN__)
/* U+00B5 MICRO SIGN */
mb = for_character ("\265", 1);
ASSERT (mb.nbytes == 1);
ASSERT (memcmp (mb.buf, "\265", 1) == 0);
#endif
/* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
mb = for_character ("\311", 1);
ASSERT (mb.nbytes == 1);
ASSERT (memcmp (mb.buf, "\311", 1) == 0);
/* U+00DF LATIN SMALL LETTER SHARP S */
mb = for_character ("\337", 1);
ASSERT (mb.nbytes == 1);
ASSERT (memcmp (mb.buf, "\337", 1) == 0);
/* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
mb = for_character ("\351", 1);
ASSERT (mb.nbytes == 1);
ASSERT (memcmp (mb.buf, "\311", 1) == 0);
#if !(defined __GLIBC__ || defined __DragonFly__ || defined __sun || defined __CYGWIN__ || (defined _WIN32 && !defined __CYGWIN__))
/* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
mb = for_character ("\377", 1);
ASSERT (mb.nbytes == 1);
ASSERT (memcmp (mb.buf, "\377", 1) == 0);
#endif
}
return 0;
case '2':
/* Locale encoding is EUC-JP. */
{
/* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
mb = for_character ("\217\252\261", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\217\252\261", 3) == 0);
#if !defined __NetBSD__
/* U+00DF LATIN SMALL LETTER SHARP S */
mb = for_character ("\217\251\316", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\217\251\316", 3) == 0);
#endif
#if !((defined __APPLE__ && defined __MACH__) || defined __DragonFly__)
/* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
mb = for_character ("\217\253\261", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\217\252\261", 3) == 0);
#endif
#if !((defined __APPLE__ && defined __MACH__) || defined __DragonFly__ || defined __NetBSD__)
/* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
mb = for_character ("\217\253\363", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\217\252\363", 3) == 0);
#endif
/* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
mb = for_character ("\217\251\250", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\217\251\250", 3) == 0);
#if !((defined __APPLE__ && defined __MACH__) || defined __DragonFly__)
/* U+0142 LATIN SMALL LETTER L WITH STROKE */
mb = for_character ("\217\251\310", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\217\251\250", 3) == 0);
#endif
/* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
mb = for_character ("\247\273", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
#if !defined __DragonFly__
/* U+0449 CYRILLIC SMALL LETTER SHCHA */
mb = for_character ("\247\353", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
#endif
/* U+3073 HIRAGANA LETTER BI */
mb = for_character ("\244\323", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\244\323", 2) == 0);
/* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
mb = for_character ("\243\307", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
#if !defined __DragonFly__
/* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
mb = for_character ("\243\347", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
#endif
}
return 0;
case '3':
/* Locale encoding is UTF-8. */
{
/* U+00B2 SUPERSCRIPT TWO */
mb = for_character ("\302\262", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\302\262", 2) == 0);
#if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined _AIX || defined __sun || defined __CYGWIN__)
/* U+00B5 MICRO SIGN */
mb = for_character ("\302\265", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\302\265", 2) == 0);
#endif
/* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
mb = for_character ("\303\211", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\303\211", 2) == 0);
/* U+00DF LATIN SMALL LETTER SHARP S */
mb = for_character ("\303\237", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\303\237", 2) == 0);
#if !(defined _WIN32 && !defined __CYGWIN__)
/* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
mb = for_character ("\303\251", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\303\211", 2) == 0);
/* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
mb = for_character ("\303\277", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\305\270", 2) == 0);
#endif
/* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
mb = for_character ("\305\201", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\305\201", 2) == 0);
/* U+0142 LATIN SMALL LETTER L WITH STROKE */
mb = for_character ("\305\202", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\305\201", 2) == 0);
/* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
mb = for_character ("\320\251", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\320\251", 2) == 0);
/* U+0449 CYRILLIC SMALL LETTER SHCHA */
mb = for_character ("\321\211", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\320\251", 2) == 0);
/* U+05D5 HEBREW LETTER VAV */
mb = for_character ("\327\225", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\327\225", 2) == 0);
/* U+3073 HIRAGANA LETTER BI */
mb = for_character ("\343\201\263", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\343\201\263", 3) == 0);
/* U+3162 HANGUL LETTER YI */
mb = for_character ("\343\205\242", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\343\205\242", 3) == 0);
/* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
mb = for_character ("\357\274\247", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\357\274\247", 3) == 0);
/* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
mb = for_character ("\357\275\207", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\357\274\247", 3) == 0);
/* U+FFDB HALFWIDTH HANGUL LETTER YI */
mb = for_character ("\357\277\233", 3);
ASSERT (mb.nbytes == 3);
ASSERT (memcmp (mb.buf, "\357\277\233", 3) == 0);
/* U+10419 DESERET CAPITAL LETTER EF */
mb = for_character ("\360\220\220\231", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\360\220\220\231", 4) == 0);
#if !(defined __DragonFly__ || defined __sun)
/* U+10441 DESERET SMALL LETTER EF */
mb = for_character ("\360\220\221\201", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\360\220\220\231", 4) == 0);
#endif
/* U+E0041 TAG LATIN CAPITAL LETTER A */
mb = for_character ("\363\240\201\201", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\363\240\201\201", 4) == 0);
/* U+E0061 TAG LATIN SMALL LETTER A */
mb = for_character ("\363\240\201\241", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\363\240\201\241", 4) == 0);
}
return 0;
case '4':
/* Locale encoding is GB18030. */
{
/* U+00B2 SUPERSCRIPT TWO */
mb = for_character ("\201\060\205\065", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\205\065", 4) == 0);
#if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __NetBSD__)
/* U+00B5 MICRO SIGN */
mb = for_character ("\201\060\205\070", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\205\070", 4) == 0);
#endif
/* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
mb = for_character ("\201\060\207\067", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\207\067", 4) == 0);
/* U+00DF LATIN SMALL LETTER SHARP S */
mb = for_character ("\201\060\211\070", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\211\070", 4) == 0);
#if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
/* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
mb = for_character ("\250\246", 2);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\207\067", 4) == 0);
/* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
mb = for_character ("\201\060\213\067", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\227\060", 4) == 0);
#endif
/* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
mb = for_character ("\201\060\221\071", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\221\071", 4) == 0);
#if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
/* U+0142 LATIN SMALL LETTER L WITH STROKE */
mb = for_character ("\201\060\222\060", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\221\071", 4) == 0);
#endif
/* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
mb = for_character ("\247\273", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
#if !(defined __FreeBSD__ || defined __DragonFly__)
/* U+0449 CYRILLIC SMALL LETTER SHCHA */
mb = for_character ("\247\353", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
#endif
/* U+05D5 HEBREW LETTER VAV */
mb = for_character ("\201\060\371\067", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\060\371\067", 4) == 0);
/* U+3073 HIRAGANA LETTER BI */
mb = for_character ("\244\323", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\244\323", 2) == 0);
/* U+3162 HANGUL LETTER YI */
mb = for_character ("\201\071\256\062", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\201\071\256\062", 4) == 0);
/* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
mb = for_character ("\243\307", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
#if !defined __DragonFly__
/* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
mb = for_character ("\243\347", 2);
ASSERT (mb.nbytes == 2);
ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
#endif
/* U+FFDB HALFWIDTH HANGUL LETTER YI */
mb = for_character ("\204\061\241\071", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\204\061\241\071", 4) == 0);
/* U+10419 DESERET CAPITAL LETTER EF */
mb = for_character ("\220\060\351\071", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\220\060\351\071", 4) == 0);
#if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
/* U+10441 DESERET SMALL LETTER EF */
mb = for_character ("\220\060\355\071", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\220\060\351\071", 4) == 0);
#endif
/* U+E0041 TAG LATIN CAPITAL LETTER A */
mb = for_character ("\323\066\234\063", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\323\066\234\063", 4) == 0);
/* U+E0061 TAG LATIN SMALL LETTER A */
mb = for_character ("\323\066\237\065", 4);
ASSERT (mb.nbytes == 4);
ASSERT (memcmp (mb.buf, "\323\066\237\065", 4) == 0);
}
return 0;
}
return 1;
}

42
tests/test-c32toupper.sh Executable file
View File

@@ -0,0 +1,42 @@
#!/bin/sh
# Allow distinguishing the various invocations in the .log file.
set -x
# Test in the POSIX locale.
LC_ALL=C ${CHECKER} ./test-c32toupper${EXEEXT} 0 || exit 1
LC_ALL=POSIX ${CHECKER} ./test-c32toupper${EXEEXT} 0 || exit 1
# Test in an ISO-8859-1 or ISO-8859-15 locale.
: "${LOCALE_FR=fr_FR}"
if test $LOCALE_FR != none; then
LC_ALL=$LOCALE_FR \
${CHECKER} ./test-c32toupper${EXEEXT} 1 \
|| exit 1
fi
# Test whether a specific EUC-JP locale is installed.
: "${LOCALE_JA=ja_JP}"
if test $LOCALE_JA != none; then
LC_ALL=$LOCALE_JA \
${CHECKER} ./test-c32toupper${EXEEXT} 2 \
|| exit 1
fi
# Test whether a specific UTF-8 locale is installed.
: "${LOCALE_FR_UTF8=fr_FR.UTF-8}"
if test $LOCALE_FR_UTF8 != none; then
LC_ALL=$LOCALE_FR_UTF8 \
${CHECKER} ./test-c32toupper${EXEEXT} 3 \
|| exit 1
fi
# Test whether a specific GB18030 locale is installed.
: "${LOCALE_ZH_CN=zh_CN.GB18030}"
if test $LOCALE_ZH_CN != none; then
LC_ALL=$LOCALE_ZH_CN \
${CHECKER} ./test-c32toupper${EXEEXT} 4 \
|| exit 1
fi
exit 0