>From 671f3d4b10ee39e9b79a6b4522f7a59d1d654aa7 Mon Sep 17 00:00:00 2001 From: Bruno Haible Date: Sun, 26 Jan 2020 00:01:21 +0100 Subject: [PATCH 21/25] c32isspace: Add tests. * tests/test-c32isspace.c: New file. * tests/test-c32isspace.sh: New file. * modules/c32isspace-tests: New file. --- ChangeLog | 5 ++ modules/c32isspace-tests | 29 +++++++ tests/test-c32isspace.c | 194 +++++++++++++++++++++++++++++++++++++++++++++++ tests/test-c32isspace.sh | 39 ++++++++++ 4 files changed, 267 insertions(+) create mode 100644 modules/c32isspace-tests create mode 100644 tests/test-c32isspace.c create mode 100755 tests/test-c32isspace.sh diff --git a/ChangeLog b/ChangeLog index 45774c3..faba429 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,10 @@ 2020-01-25 Bruno Haible + c32isspace: Add tests. + * tests/test-c32isspace.c: New file. + * tests/test-c32isspace.sh: New file. + * modules/c32isspace-tests: New file. + c32isspace: New module. * lib/c32isspace.c: New file. * modules/c32isspace: New file. diff --git a/modules/c32isspace-tests b/modules/c32isspace-tests new file mode 100644 index 0000000..a37b528 --- /dev/null +++ b/modules/c32isspace-tests @@ -0,0 +1,29 @@ +Files: +tests/test-c32isspace.sh +tests/test-c32isspace.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 +setlocale + +configure.ac: +gt_LOCALE_FR +gt_LOCALE_FR_UTF8 +gt_LOCALE_JA +gt_LOCALE_ZH_CN + +Makefile.am: +TESTS += test-c32isspace.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-c32isspace +test_c32isspace_LDADD = $(LDADD) $(LIB_SETLOCALE) $(LIB_MBRTOWC) diff --git a/tests/test-c32isspace.c b/tests/test-c32isspace.c new file mode 100644 index 0000000..5cd83f7 --- /dev/null +++ b/tests/test-c32isspace.c @@ -0,0 +1,194 @@ +/* Test of c32isspace() function. + Copyright (C) 2020 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 . */ + +#include + +#include + +#include "signature.h" +SIGNATURE_CHECK (c32isspace, int, (wint_t)); + +#include +#include +#include +#include + +#include "macros.h" + +/* Returns the value of c32isspace for the multibyte character s[0..n-1]. */ +static int +for_character (const char *s, size_t n) +{ + mbstate_t state; + char32_t wc; + size_t ret; + + memset (&state, '\0', sizeof (mbstate_t)); + wc = (char32_t) 0xBADFACE; + ret = mbrtoc32 (&wc, s, n, &state); + ASSERT (ret == n); + + return c32isspace (wc); +} + +int +main (int argc, char *argv[]) +{ + int is; + char buf[4]; + + /* configure should already have checked that the locale is supported. */ + if (setlocale (LC_ALL, "") == NULL) + return 1; + + /* Test WEOF. */ + is = c32isspace (WEOF); + ASSERT (is == 0); + + /* Test single-byte characters. + POSIX specifies in + + that + - in all locales, the white-space characters include the , + , , , , + characters, + - in the "POSIX" locale (which is usually the same as the "C" locale), + the white-space characters include only the ASCII , , + , , , characters. */ + { + int c; + + for (c = 0; c < 0x100; c++) + switch (c) + { + case '\f': case '\n': case '\r': case '\t': case '\v': + 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" or one of the explicitly + mentioned white-space characters. */ + buf[0] = (unsigned char) c; + is = for_character (buf, 1); + switch (c) + { + case ' ': case '\f': case '\n': case '\r': case '\t': case '\v': + ASSERT (is != 0); + break; + default: + ASSERT (is == 0); + 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+00B7 MIDDLE DOT */ + is = for_character ("\267", 1); + ASSERT (is == 0); + } + return 0; + + case '2': + /* Locale encoding is EUC-JP. */ + { + #if !(defined __FreeBSD__ || defined __DragonFly__) + /* U+3000 IDEOGRAPHIC SPACE */ + is = for_character ("\241\241", 2); + ASSERT (is != 0); + #endif + /* U+3001 IDEOGRAPHIC COMMA */ + is = for_character ("\241\242", 2); + ASSERT (is == 0); + } + return 0; + + case '3': + /* Locale encoding is UTF-8. */ + { + /* U+00B7 MIDDLE DOT */ + is = for_character ("\302\267", 2); + ASSERT (is == 0); + /* U+2002 EN SPACE */ + is = for_character ("\342\200\202", 3); + ASSERT (is != 0); + /* U+3000 IDEOGRAPHIC SPACE */ + is = for_character ("\343\200\200", 3); + ASSERT (is != 0); + /* U+3001 IDEOGRAPHIC COMMA */ + is = for_character ("\343\200\201", 3); + ASSERT (is == 0); + /* U+E0020 TAG SPACE */ + is = for_character ("\363\240\200\240", 4); + ASSERT (is == 0); + } + return 0; + + case '4': + /* Locale encoding is GB18030. */ + { + /* U+00B7 MIDDLE DOT */ + is = for_character ("\241\244", 2); + ASSERT (is == 0); + #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun) + /* U+2002 EN SPACE */ + is = for_character ("\201\066\243\070", 4); + ASSERT (is != 0); + #endif + #if !(defined __FreeBSD__ || defined __DragonFly__) + /* U+3000 IDEOGRAPHIC SPACE */ + is = for_character ("\241\241", 2); + ASSERT (is != 0); + #endif + /* U+3001 IDEOGRAPHIC COMMA */ + is = for_character ("\241\242", 2); + ASSERT (is == 0); + /* U+E0020 TAG SPACE */ + is = for_character ("\323\066\231\060", 4); + ASSERT (is == 0); + } + return 0; + + } + + return 1; +} diff --git a/tests/test-c32isspace.sh b/tests/test-c32isspace.sh new file mode 100755 index 0000000..7304489 --- /dev/null +++ b/tests/test-c32isspace.sh @@ -0,0 +1,39 @@ +#!/bin/sh + +# Test in the POSIX locale. +LC_ALL=C ${CHECKER} ./test-c32isspace${EXEEXT} 0 || exit 1 +LC_ALL=POSIX ${CHECKER} ./test-c32isspace${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 \ + ${CHECKER} ./test-c32isspace${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 \ + ${CHECKER} ./test-c32isspace${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 \ + ${CHECKER} ./test-c32isspace${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 \ + ${CHECKER} ./test-c32isspace${EXEEXT} 4 \ + || exit 1 +fi + +exit 0 -- 2.7.4