From a691312d8794d5516402bb6bb0d3e90c40ba188b Mon Sep 17 00:00:00 2001 From: Carmelo Amoroso Date: Wed, 9 Jul 2008 15:05:36 +0000 Subject: Added several tests for locale support (8 bit and multibyte UTF-8) Basically all tests have been taken from glibc. For testing multibyte encoding EUC_JP parts have been commented out and added new section for UTF-8 that is the only multibyte codeset currently supported on uCLibc. Some tests are still failing due to unsupported/missing features, other have been fixed. Signed-off-by: Filippo Arcidiacono Signed-off-by: Carmelo Amoroso --- test/locale/Makefile | 31 ++ test/locale/bug-iconv-trans.c | 68 +++ test/locale/bug-usesetlocale.c | 38 ++ test/locale/collate-test.c | 133 +++++ test/locale/dump-ctype.c | 164 +++++++ test/locale/gen-unicode-ctype.c | 785 ++++++++++++++++++++++++++++++ test/locale/show-ucs-data.c | 62 +++ test/locale/tst-C-locale.c | 498 +++++++++++++++++++ test/locale/tst-ctype-de_DE.ISO-8859-1.in | 56 +++ test/locale/tst-ctype.c | 447 +++++++++++++++++ test/locale/tst-digits.c | 249 ++++++++++ test/locale/tst-fmon.c | 68 +++ test/locale/tst-langinfo.c | 284 +++++++++++ test/locale/tst-langinfo.input | 303 ++++++++++++ test/locale/tst-leaks.c | 18 + test/locale/tst-mbswcs1.c | 63 +++ test/locale/tst-mbswcs2.c | 65 +++ test/locale/tst-mbswcs3.c | 76 +++ test/locale/tst-mbswcs4.c | 63 +++ test/locale/tst-mbswcs5.c | 75 +++ test/locale/tst-mbswcs6.c | 74 +++ test/locale/tst-numeric.c | 74 +++ test/locale/tst-rpmatch.c | 37 ++ test/locale/tst-setlocale.c | 25 + test/locale/tst-sscanf.c | 56 +++ test/locale/tst-strfmon1.c | 42 ++ test/locale/tst-trans.c | 71 +++ test/locale/tst-wctype.c | 144 ++++++ test/locale/tst-xlocale1.c | 75 +++ test/locale/tst-xlocale2.c | 64 +++ test/locale/tst_nl_langinfo.c | 296 +++++++++++ test/locale/xfrm-test.c | 144 ++++++ 32 files changed, 4648 insertions(+) create mode 100644 test/locale/Makefile create mode 100644 test/locale/bug-iconv-trans.c create mode 100644 test/locale/bug-usesetlocale.c create mode 100644 test/locale/collate-test.c create mode 100644 test/locale/dump-ctype.c create mode 100644 test/locale/gen-unicode-ctype.c create mode 100644 test/locale/show-ucs-data.c create mode 100644 test/locale/tst-C-locale.c create mode 100644 test/locale/tst-ctype-de_DE.ISO-8859-1.in create mode 100644 test/locale/tst-ctype.c create mode 100644 test/locale/tst-digits.c create mode 100644 test/locale/tst-fmon.c create mode 100644 test/locale/tst-langinfo.c create mode 100644 test/locale/tst-langinfo.input create mode 100644 test/locale/tst-leaks.c create mode 100644 test/locale/tst-mbswcs1.c create mode 100644 test/locale/tst-mbswcs2.c create mode 100644 test/locale/tst-mbswcs3.c create mode 100644 test/locale/tst-mbswcs4.c create mode 100644 test/locale/tst-mbswcs5.c create mode 100644 test/locale/tst-mbswcs6.c create mode 100644 test/locale/tst-numeric.c create mode 100644 test/locale/tst-rpmatch.c create mode 100644 test/locale/tst-setlocale.c create mode 100644 test/locale/tst-sscanf.c create mode 100644 test/locale/tst-strfmon1.c create mode 100644 test/locale/tst-trans.c create mode 100644 test/locale/tst-wctype.c create mode 100644 test/locale/tst-xlocale1.c create mode 100644 test/locale/tst-xlocale2.c create mode 100644 test/locale/tst_nl_langinfo.c create mode 100644 test/locale/xfrm-test.c (limited to 'test/locale') diff --git a/test/locale/Makefile b/test/locale/Makefile new file mode 100644 index 000000000..0ab07f7aa --- /dev/null +++ b/test/locale/Makefile @@ -0,0 +1,31 @@ +# uClibc locale tests +# Licensed under the LGPL v2.1, see the file COPYING.LIB in this tarball. +# tst_mbtowc tst_strcoll tst_strfmon tst_strxfrm \ + +TESTS := bug-iconv-trans bug-usesetlocale collate-test dump-ctype \ + gen-unicode-ctype show-ucs-data tst-ctype \ + tst-digits tst-fmon tst-langinfo tst-leaks tst-mbswcs1 \ + tst-mbswcs2 tst-mbswcs3 tst-mbswcs4 tst-mbswcs5 tst-mbswcs6 \ + tst_nl_langinfo tst-numeric tst-rpmatch tst-setlocale \ + tst-sscanf tst-strfmon1 tst-trans tst-wctype tst-xlocale1 \ + tst-xlocale2 xfrm-test + + +# NOTE: For now disabled some tests that are known not build +TESTS_DISABLED := tst-ctype tst-fmon tst-leaks tst-rpmatch tst-strfmon1 + +ifneq ($(UCLIBC_HAS_XLOCALE),y) +TESTS_DISABLED += bug-usesetlocale tst-xlocale1 tst-xlocale2 xfrm-test tst-C-locale +endif + +include ../Test.mak + +DODIFF_rint := 1 + +EXTRA_CFLAGS := -D__USE_GNU -fno-builtin + +OPTS_dump-ctype = C +OPTS_tst-ctype = < tst-ctype-de_DE.ISO-8859-1.in +OPTS_tst-langinfo = < tst-langinfo.input + +EXTRA_CLEAN := C diff --git a/test/locale/bug-iconv-trans.c b/test/locale/bug-iconv-trans.c new file mode 100644 index 000000000..3886247c3 --- /dev/null +++ b/test/locale/bug-iconv-trans.c @@ -0,0 +1,68 @@ +#include +#include +#include +#include + +int +main (void) +{ + iconv_t cd; + const char str[] = "ÄäÖöÜüß"; + const char expected[] = "AEaeOEoeUEuess"; + char *inptr = (char *) str; + size_t inlen = strlen (str) + 1; + char outbuf[500]; + char *outptr = outbuf; + size_t outlen = sizeof (outbuf); + int result = 0; + size_t n; + + if (setlocale (LC_ALL, "de_DE.UTF-8") == NULL) + { + puts ("setlocale failed"); + return 1; + } + + cd = iconv_open ("ANSI_X3.4-1968//TRANSLIT", "ISO-8859-1"); + if (cd == (iconv_t) -1) + { + puts ("iconv_open failed"); + return 1; + } + + n = iconv (cd, &inptr, &inlen, &outptr, &outlen); + if (n != 7) + { + if (n == (size_t) -1) + printf ("iconv() returned error: %m\n"); + else + printf ("iconv() returned %Zd, expected 7\n", n); + result = 1; + } + if (inlen != 0) + { + puts ("not all input consumed"); + result = 1; + } + else if (inptr - str != strlen (str) + 1) + { + printf ("inptr wrong, advanced by %td\n", inptr - str); + result = 1; + } + if (memcmp (outbuf, expected, sizeof (expected)) != 0) + { + printf ("result wrong: \"%.*s\", expected: \"%s\"\n", + (int) (sizeof (outbuf) - outlen), outbuf, expected); + result = 1; + } + else if (outlen != sizeof (outbuf) - sizeof (expected)) + { + printf ("outlen wrong: %Zd, expected %Zd\n", outlen, + sizeof (outbuf) - 15); + result = 1; + } + else + printf ("output is \"%s\" which is OK\n", outbuf); + + return result; +} diff --git a/test/locale/bug-usesetlocale.c b/test/locale/bug-usesetlocale.c new file mode 100644 index 000000000..0637067de --- /dev/null +++ b/test/locale/bug-usesetlocale.c @@ -0,0 +1,38 @@ +/* Test case for setlocale vs uselocale (LC_GLOBAL_LOCALE) bug. */ + +#define _GNU_SOURCE 1 +#include +#include +#include + +static int +do_test (void) +{ + __locale_t loc_new, loc_old; + + int first = !!isalpha(0xE4); + + setlocale (LC_ALL, "de_DE"); + + int global_de = !!isalpha(0xE4); + + loc_new = newlocale (1 << LC_ALL, "C", 0); + loc_old = uselocale (loc_new); + + int used_c = !!isalpha(0xE4); + + uselocale (loc_old); + + int used_global = !!isalpha(0xE4); + + printf ("started %d, after setlocale %d\n", first, global_de); + printf ("after uselocale %d, after LC_GLOBAL_LOCALE %d\n", + used_c, used_global); + + freelocale (loc_new); + return !(used_c == first && used_global == global_de); +} + + +#define TEST_FUNCTION do_test () +#include "test-skeleton.c" diff --git a/test/locale/collate-test.c b/test/locale/collate-test.c new file mode 100644 index 000000000..e8f43218f --- /dev/null +++ b/test/locale/collate-test.c @@ -0,0 +1,133 @@ +/* Test collation function using real data. + Copyright (C) 1997, 1999, 2000, 2003 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Ulrich Drepper , 1997. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +#include +#include +#include +#include +#include +#include + + +struct lines +{ + char *key; + char *line; +}; + +static int xstrcoll (const void *, const void *); + +int +main (int argc, char *argv[]) +{ + int result = 0; + size_t nstrings, nstrings_max; + struct lines *strings; + char *line = NULL; + size_t len = 0; + size_t n; + + if (argc < 2) + error (1, 0, "usage: %s ", argv[0]); + + setlocale (LC_ALL, ""); + + nstrings_max = 100; + nstrings = 0; + strings = (struct lines *) malloc (nstrings_max * sizeof (struct lines)); + if (strings == NULL) + { + perror (argv[0]); + exit (1); + } + + while (1) + { + int l; + if (getline (&line, &len, stdin) < 0) + break; + + if (nstrings == nstrings_max) + { + strings = (struct lines *) realloc (strings, + (nstrings_max *= 2) + * sizeof (*strings)); + if (strings == NULL) + { + perror (argv[0]); + exit (1); + } + } + strings[nstrings].line = strdup (line); + l = strcspn (line, ":(;"); + while (l > 0 && isspace (line[l - 1])) + --l; + strings[nstrings].key = strndup (line, l); + ++nstrings; + } + free (line); + + /* First shuffle. */ + srandom (atoi (argv[1])); + for (n = 0; n < 10 * nstrings; ++n) + { + int r1, r2, r; + size_t idx1 = random () % nstrings; + size_t idx2 = random () % nstrings; + struct lines tmp = strings[idx1]; + strings[idx1] = strings[idx2]; + strings[idx2] = tmp; + + /* While we are at it a first little test. */ + r1 = strcoll (strings[idx1].key, strings[idx2].key); + r2 = strcoll (strings[idx2].key, strings[idx1].key); + r = r1 * r2; + + if (r > 0 || (r == 0 && r1 != 0) || (r == 0 && r2 != 0)) + printf ("`%s' and `%s' collate wrong: %d vs. %d\n", + strings[idx1].key, strings[idx2].key, r1, r2); + } + + /* Now sort. */ + qsort (strings, nstrings, sizeof (struct lines), xstrcoll); + + /* Print the result. */ + for (n = 0; n < nstrings; ++n) + { + fputs (strings[n].line, stdout); + free (strings[n].line); + free (strings[n].key); + } + free (strings); + + return result; +} + + +static int +xstrcoll (ptr1, ptr2) + const void *ptr1; + const void *ptr2; +{ + const struct lines *l1 = (const struct lines *) ptr1; + const struct lines *l2 = (const struct lines *) ptr2; + + return strcoll (l1->key, l2->key); +} diff --git a/test/locale/dump-ctype.c b/test/locale/dump-ctype.c new file mode 100644 index 000000000..a1f24c656 --- /dev/null +++ b/test/locale/dump-ctype.c @@ -0,0 +1,164 @@ +/* Dump the character classes and character maps of a locale to a bunch + of individual files which can be processed with diff, sed etc. + Copyright (C) 2000 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Bruno Haible , 2000. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +/* Usage example: + $ dump-ctype de_DE.UTF-8 + */ + +#include +#include +#include +#include +#include +#include +#include + +static const char *program_name = "dump-ctype"; +static const char *locale; + +static const char *class_names[] = + { + "alnum", "alpha", "blank", "cntrl", "digit", "graph", "lower", + "print", "punct", "space", "upper", "xdigit" + }; + +static const char *map_names[] = + { + "tolower", "toupper", "totitle" + }; + +static void dump_class (const char *class_name) +{ + wctype_t class; + FILE *f; + unsigned int ch; + + class = wctype (class_name); + if (class == (wctype_t) 0) + { + fprintf (stderr, "%s %s: noexistent class %s\n", program_name, + locale, class_name); + return; + } + + f = fopen (class_name, "w"); + if (f == NULL) + { + fprintf (stderr, "%s %s: cannot open file %s/%s\n", program_name, + locale, locale, class_name); + exit (1); + } + + for (ch = 0; ch < 0x10000; ch++) + if (iswctype (ch, class)) + fprintf (f, "0x%04X\n", ch); + + if (ferror (f) || fclose (f)) + { + fprintf (stderr, "%s %s: I/O error on file %s/%s\n", program_name, + locale, locale, class_name); + exit (1); + } +} + +static void dump_map (const char *map_name) +{ + wctrans_t map; + FILE *f; + unsigned int ch; + + map = wctrans (map_name); + if (map == (wctrans_t) 0) + { + fprintf (stderr, "%s %s: noexistent map %s\n", program_name, + locale, map_name); + return; + } + + f = fopen (map_name, "w"); + if (f == NULL) + { + fprintf (stderr, "%s %s: cannot open file %s/%s\n", program_name, + locale, locale, map_name); + exit (1); + } + + for (ch = 0; ch < 0x10000; ch++) + if (towctrans (ch, map) != ch) + fprintf (f, "0x%04X\t0x%04X\n", ch, towctrans (ch, map)); + + if (ferror (f) || fclose (f)) + { + fprintf (stderr, "%s %s: I/O error on file %s/%s\n", program_name, + locale, locale, map_name); + exit (1); + } +} + +int +main (int argc, char *argv[]) +{ + size_t i; + + if (argc != 2) + { + fprintf (stderr, "Usage: dump-ctype locale\n"); + exit (1); + } + locale = argv[1]; + + if (setlocale (LC_ALL, locale) == NULL) + { + fprintf (stderr, "%s: setlocale cannot switch to locale %s\n", + program_name, locale); + exit (1); + } + + if (mkdir (locale, 0777) < 0) + { + char buf[100]; + int save_errno = errno; + + sprintf (buf, "%s: cannot create directory %s", program_name, locale); + errno = save_errno; + perror (buf); + exit (1); + } + + if (chdir (locale) < 0) + { + char buf[100]; + int save_errno = errno; + + sprintf (buf, "%s: cannot chdir to %s", program_name, locale); + errno = save_errno; + perror (buf); + exit (1); + } + + for (i = 0; i < sizeof (class_names) / sizeof (class_names[0]); i++) + dump_class (class_names[i]); + + for (i = 0; i < sizeof (map_names) / sizeof (map_names[0]); i++) + dump_map (map_names[i]); + + return 0; +} diff --git a/test/locale/gen-unicode-ctype.c b/test/locale/gen-unicode-ctype.c new file mode 100644 index 000000000..849f272ed --- /dev/null +++ b/test/locale/gen-unicode-ctype.c @@ -0,0 +1,785 @@ +/* Generate a Unicode conforming LC_CTYPE category from a UnicodeData file. + Copyright (C) 2000-2001 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Bruno Haible , 2000. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +/* Usage example: + $ gen-unicode /usr/local/share/Unidata/UnicodeData.txt 3.1 + */ + +#include +#include +#include +#include +#include + +/* This structure represents one line in the UnicodeData.txt file. */ +struct unicode_attribute +{ + const char *name; /* Character name */ + const char *category; /* General category */ + const char *combining; /* Canonical combining classes */ + const char *bidi; /* Bidirectional category */ + const char *decomposition; /* Character decomposition mapping */ + const char *decdigit; /* Decimal digit value */ + const char *digit; /* Digit value */ + const char *numeric; /* Numeric value */ + int mirrored; /* mirrored */ + const char *oldname; /* Old Unicode 1.0 name */ + const char *comment; /* Comment */ + unsigned int upper; /* Uppercase mapping */ + unsigned int lower; /* Lowercase mapping */ + unsigned int title; /* Titlecase mapping */ +}; + +/* Missing fields are represented with "" for strings, and NONE for + characters. */ +#define NONE (~(unsigned int)0) + +/* The entire contents of the UnicodeData.txt file. */ +struct unicode_attribute unicode_attributes [0x110000]; + +/* Stores in unicode_attributes[i] the values from the given fields. */ +static void +fill_attribute (unsigned int i, + const char *field1, const char *field2, + const char *field3, const char *field4, + const char *field5, const char *field6, + const char *field7, const char *field8, + const char *field9, const char *field10, + const char *field11, const char *field12, + const char *field13, const char *field14) +{ + struct unicode_attribute * uni; + + if (i >= 0x110000) + { + fprintf (stderr, "index too large\n"); + exit (1); + } + if (strcmp (field2, "Cs") == 0) + /* Surrogates are UTF-16 artefacts, not real characters. Ignore them. */ + return; + uni = &unicode_attributes[i]; + /* Copy the strings. */ + uni->name = strdup (field1); + uni->category = (field2[0] == '\0' ? "" : strdup (field2)); + uni->combining = (field3[0] == '\0' ? "" : strdup (field3)); + uni->bidi = (field4[0] == '\0' ? "" : strdup (field4)); + uni->decomposition = (field5[0] == '\0' ? "" : strdup (field5)); + uni->decdigit = (field6[0] == '\0' ? "" : strdup (field6)); + uni->digit = (field7[0] == '\0' ? "" : strdup (field7)); + uni->numeric = (field8[0] == '\0' ? "" : strdup (field8)); + uni->mirrored = (field9[0] == 'Y'); + uni->oldname = (field10[0] == '\0' ? "" : strdup (field10)); + uni->comment = (field11[0] == '\0' ? "" : strdup (field11)); + uni->upper = (field12[0] =='\0' ? NONE : strtoul (field12, NULL, 16)); + uni->lower = (field13[0] =='\0' ? NONE : strtoul (field13, NULL, 16)); + uni->title = (field14[0] =='\0' ? NONE : strtoul (field14, NULL, 16)); +} + +/* Maximum length of a field in the UnicodeData.txt file. */ +#define FIELDLEN 120 + +/* Reads the next field from STREAM. The buffer BUFFER has size FIELDLEN. + Reads up to (but excluding) DELIM. + Returns 1 when a field was successfully read, otherwise 0. */ +static int +getfield (FILE *stream, char *buffer, int delim) +{ + int count = 0; + int c; + + for (; (c = getc (stream)), (c != EOF && c != delim); ) + { + /* The original unicode.org UnicodeData.txt file happens to have + CR/LF line terminators. Silently convert to LF. */ + if (c == '\r') + continue; + + /* Put c into the buffer. */ + if (++count >= FIELDLEN - 1) + { + fprintf (stderr, "field too long\n"); + exit (1); + } + *buffer++ = c; + } + + if (c == EOF) + return 0; + + *buffer = '\0'; + return 1; +} + +/* Stores in unicode_attributes[] the entire contents of the UnicodeData.txt + file. */ +static void +fill_attributes (const char *unicodedata_filename) +{ + unsigned int i, j; + FILE *stream; + char field0[FIELDLEN]; + char field1[FIELDLEN]; + char field2[FIELDLEN]; + char field3[FIELDLEN]; + char field4[FIELDLEN]; + char field5[FIELDLEN]; + char field6[FIELDLEN]; + char field7[FIELDLEN]; + char field8[FIELDLEN]; + char field9[FIELDLEN]; + char field10[FIELDLEN]; + char field11[FIELDLEN]; + char field12[FIELDLEN]; + char field13[FIELDLEN]; + char field14[FIELDLEN]; + int lineno = 0; + + for (i = 0; i < 0x110000; i++) + unicode_attributes[i].name = NULL; + + stream = fopen (unicodedata_filename, "r"); + if (stream == NULL) + { + fprintf (stderr, "error during fopen of '%s'\n", unicodedata_filename); + exit (1); + } + + for (;;) + { + int n; + + lineno++; + n = getfield (stream, field0, ';'); + n += getfield (stream, field1, ';'); + n += getfield (stream, field2, ';'); + n += getfield (stream, field3, ';'); + n += getfield (stream, field4, ';'); + n += getfield (stream, field5, ';'); + n += getfield (stream, field6, ';'); + n += getfield (stream, field7, ';'); + n += getfield (stream, field8, ';'); + n += getfield (stream, field9, ';'); + n += getfield (stream, field10, ';'); + n += getfield (stream, field11, ';'); + n += getfield (stream, field12, ';'); + n += getfield (stream, field13, ';'); + n += getfield (stream, field14, '\n'); + if (n == 0) + break; + if (n != 15) + { + fprintf (stderr, "short line in'%s':%d\n", + unicodedata_filename, lineno); + exit (1); + } + i = strtoul (field0, NULL, 16); + if (field1[0] == '<' + && strlen (field1) >= 9 + && !strcmp (field1 + strlen(field1) - 8, ", First>")) + { + /* Deal with a range. */ + lineno++; + n = getfield (stream, field0, ';'); + n += getfield (stream, field1, ';'); + n += getfield (stream, field2, ';'); + n += getfield (stream, field3, ';'); + n += getfield (stream, field4, ';'); + n += getfield (stream, field5, ';'); + n += getfield (stream, field6, ';'); + n += getfield (stream, field7, ';'); + n += getfield (stream, field8, ';'); + n += getfield (stream, field9, ';'); + n += getfield (stream, field10, ';'); + n += getfield (stream, field11, ';'); + n += getfield (stream, field12, ';'); + n += getfield (stream, field13, ';'); + n += getfield (stream, field14, '\n'); + if (n != 15) + { + fprintf (stderr, "missing end range in '%s':%d\n", + unicodedata_filename, lineno); + exit (1); + } + if (!(field1[0] == '<' + && strlen (field1) >= 8 + && !strcmp (field1 + strlen (field1) - 7, ", Last>"))) + { + fprintf (stderr, "missing end range in '%s':%d\n", + unicodedata_filename, lineno); + exit (1); + } + field1[strlen (field1) - 7] = '\0'; + j = strtoul (field0, NULL, 16); + for (; i <= j; i++) + fill_attribute (i, field1+1, field2, field3, field4, field5, + field6, field7, field8, field9, field10, + field11, field12, field13, field14); + } + else + { + /* Single character line */ + fill_attribute (i, field1, field2, field3, field4, field5, + field6, field7, field8, field9, field10, + field11, field12, field13, field14); + } + } + if (ferror (stream) || fclose (stream)) + { + fprintf (stderr, "error reading from '%s'\n", unicodedata_filename); + exit (1); + } +} + +/* Character mappings. */ + +static unsigned int +to_upper (unsigned int ch) +{ + if (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].upper != NONE) + return unicode_attributes[ch].upper; + else + return ch; +} + +static unsigned int +to_lower (unsigned int ch) +{ + if (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].lower != NONE) + return unicode_attributes[ch].lower; + else + return ch; +} + +static unsigned int +to_title (unsigned int ch) +{ + if (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].title != NONE) + return unicode_attributes[ch].title; + else + return ch; +} + +/* Character class properties. */ + +static bool +is_upper (unsigned int ch) +{ + return (to_lower (ch) != ch); +} + +static bool +is_lower (unsigned int ch) +{ + return (to_upper (ch) != ch) + /* is lowercase, but without simple to_upper mapping. */ + || (ch == 0x00DF); +} + +static bool +is_alpha (unsigned int ch) +{ + return (unicode_attributes[ch].name != NULL + && ((unicode_attributes[ch].category[0] == 'L' + /* Theppitak Karoonboonyanan says + , should belong to is_punct. */ + && (ch != 0x0E2F) && (ch != 0x0E46)) + /* Theppitak Karoonboonyanan says + , .., .. are is_alpha. */ + || (ch == 0x0E31) + || (ch >= 0x0E34 && ch <= 0x0E3A) + || (ch >= 0x0E47 && ch <= 0x0E4E) + /* Avoid warning for . */ + || (ch == 0x0345) + /* Avoid warnings for ... */ + || (unicode_attributes[ch].category[0] == 'N' + && unicode_attributes[ch].category[1] == 'l') + /* Avoid warnings for ... */ + || (unicode_attributes[ch].category[0] == 'S' + && unicode_attributes[ch].category[1] == 'o' + && strstr (unicode_attributes[ch].name, " LETTER ") + != NULL) + /* Consider all the non-ASCII digits as alphabetic. + ISO C 99 forbids us to have them in category "digit", + but we want iswalnum to return true on them. */ + || (unicode_attributes[ch].category[0] == 'N' + && unicode_attributes[ch].category[1] == 'd' + && !(ch >= 0x0030 && ch <= 0x0039)))); +} + +static bool +is_digit (unsigned int ch) +{ +#if 0 + return (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].category[0] == 'N' + && unicode_attributes[ch].category[1] == 'd'); + /* Note: U+0BE7..U+0BEF and U+1369..U+1371 are digit systems without + a zero. Must add <0> in front of them by hand. */ +#else + /* SUSV2 gives us some freedom for the "digit" category, but ISO C 99 + takes it away: + 7.25.2.1.5: + The iswdigit function tests for any wide character that corresponds + to a decimal-digit character (as defined in 5.2.1). + 5.2.1: + the 10 decimal digits 0 1 2 3 4 5 6 7 8 9 + */ + return (ch >= 0x0030 && ch <= 0x0039); +#endif +} + +static bool +is_outdigit (unsigned int ch) +{ + return (ch >= 0x0030 && ch <= 0x0039); +} + +static bool +is_blank (unsigned int ch) +{ + return (ch == 0x0009 /* '\t' */ + /* Category Zs without mention of "" */ + || (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].category[0] == 'Z' + && unicode_attributes[ch].category[1] == 's' + && !strstr (unicode_attributes[ch].decomposition, ""))); +} + +static bool +is_space (unsigned int ch) +{ + /* Don't make U+00A0 a space. Non-breaking space means that all programs + should treat it like a punctuation character, not like a space. */ + return (ch == 0x0020 /* ' ' */ + || ch == 0x000C /* '\f' */ + || ch == 0x000A /* '\n' */ + || ch == 0x000D /* '\r' */ + || ch == 0x0009 /* '\t' */ + || ch == 0x000B /* '\v' */ + /* Categories Zl, Zp, and Zs without mention of "" */ + || (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].category[0] == 'Z' + && (unicode_attributes[ch].category[1] == 'l' + || unicode_attributes[ch].category[1] == 'p' + || (unicode_attributes[ch].category[1] == 's' + && !strstr (unicode_attributes[ch].decomposition, + ""))))); +} + +static bool +is_cntrl (unsigned int ch) +{ + return (unicode_attributes[ch].name != NULL + && (!strcmp (unicode_attributes[ch].name, "") + /* Categories Zl and Zp */ + || (unicode_attributes[ch].category[0] == 'Z' + && (unicode_attributes[ch].category[1] == 'l' + || unicode_attributes[ch].category[1] == 'p')))); +} + +static bool +is_xdigit (unsigned int ch) +{ +#if 0 + return is_digit (ch) + || (ch >= 0x0041 && ch <= 0x0046) + || (ch >= 0x0061 && ch <= 0x0066); +#else + /* SUSV2 gives us some freedom for the "xdigit" category, but ISO C 99 + takes it away: + 7.25.2.1.12: + The iswxdigit function tests for any wide character that corresponds + to a hexadecimal-digit character (as defined in 6.4.4.1). + 6.4.4.1: + hexadecimal-digit: one of 0 1 2 3 4 5 6 7 8 9 a b c d e f A B C D E F + */ + return (ch >= 0x0030 && ch <= 0x0039) + || (ch >= 0x0041 && ch <= 0x0046) + || (ch >= 0x0061 && ch <= 0x0066); +#endif +} + +static bool +is_graph (unsigned int ch) +{ + return (unicode_attributes[ch].name != NULL + && strcmp (unicode_attributes[ch].name, "") + && !is_space (ch)); +} + +static bool +is_print (unsigned int ch) +{ + return (unicode_attributes[ch].name != NULL + && strcmp (unicode_attributes[ch].name, "") + /* Categories Zl and Zp */ + && !(unicode_attributes[ch].name != NULL + && unicode_attributes[ch].category[0] == 'Z' + && (unicode_attributes[ch].category[1] == 'l' + || unicode_attributes[ch].category[1] == 'p'))); +} + +static bool +is_punct (unsigned int ch) +{ +#if 0 + return (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].category[0] == 'P'); +#else + /* The traditional POSIX definition of punctuation is every graphic, + non-alphanumeric character. */ + return (is_graph (ch) && !is_alpha (ch) && !is_digit (ch)); +#endif +} + +static bool +is_combining (unsigned int ch) +{ + /* Up to Unicode 3.0.1 we took the Combining property from the PropList.txt + file. In 3.0.1 it was identical to the union of the general categories + "Mn", "Mc", "Me". In Unicode 3.1 this property has been dropped from the + PropList.txt file, so we take the latter definition. */ + return (unicode_attributes[ch].name != NULL + && unicode_attributes[ch].category[0] == 'M' + && (unicode_attributes[ch].category[1] == 'n' + || unicode_attributes[ch].category[1] == 'c' + || unicode_attributes[ch].category[1] == 'e')); +} + +static bool +is_combining_level3 (unsigned int ch) +{ + return is_combining (ch) + && !(unicode_attributes[ch].combining[0] != '\0' + && unicode_attributes[ch].combining[0] != '0' + && strtoul (unicode_attributes[ch].combining, NULL, 10) >= 200); +} + +/* Return the UCS symbol string for a Unicode character. */ +static const char * +ucs_symbol (unsigned int i) +{ + static char buf[11+1]; + + sprintf (buf, (i < 0x10000 ? "" : ""), i); + return buf; +} + +/* Return the UCS symbol range string for a Unicode characters interval. */ +static const char * +ucs_symbol_range (unsigned int low, unsigned int high) +{ + static char buf[24+1]; + + strcpy (buf, ucs_symbol (low)); + strcat (buf, ".."); + strcat (buf, ucs_symbol (high)); + return buf; +} + +/* Output a character class (= property) table. */ + +static void +output_charclass (FILE *stream, const char *classname, + bool (*func) (unsigned int)) +{ + char table[0x110000]; + unsigned int i; + bool need_semicolon; + const int max_column = 75; + int column; + + for (i = 0; i < 0x110000; i++) + table[i] = (int) func (i); + + fprintf (stream, "%s ", classname); + need_semicolon = false; + column = 1000; + for (i = 0; i < 0x110000; ) + { + if (!table[i]) + i++; + else + { + unsigned int low, high; + char buf[25]; + + low = i; + do + i++; + while (i < 0x110000 && table[i]); + high = i - 1; + + if (low == high) + strcpy (buf, ucs_symbol (low)); + else + strcpy (buf, ucs_symbol_range (low, high)); + + if (need_semicolon) + { + fprintf (stream, ";"); + column++; + } + + if (column + strlen (buf) > max_column) + { + fprintf (stream, "/\n "); + column = 3; + } + + fprintf (stream, "%s", buf); + column += strlen (buf); + need_semicolon = true; + } + } + fprintf (stream, "\n"); +} + +/* Output a character mapping table. */ + +static void +output_charmap (FILE *stream, const char *mapname, + unsigned int (*func) (unsigned int)) +{ + char table[0x110000]; + unsigned int i; + bool need_semicolon; + const int max_column = 75; + int column; + + for (i = 0; i < 0x110000; i++) + table[i] = (func (i) != i); + + fprintf (stream, "%s ", mapname); + need_semicolon = false; + column = 1000; + for (i = 0; i < 0x110000; i++) + if (table[i]) + { + char buf[25+1]; + + strcpy (buf, "("); + strcat (buf, ucs_symbol (i)); + strcat (buf, ","); + strcat (buf, ucs_symbol (func (i))); + strcat (buf, ")"); + + if (need_semicolon) + { + fprintf (stream, ";"); + column++; + } + + if (column + strlen (buf) > max_column) + { + fprintf (stream, "/\n "); + column = 3; + } + + fprintf (stream, "%s", buf); + column += strlen (buf); + need_semicolon = true; + } + fprintf (stream, "\n"); +} + +/* Output the width table. */ + +static void +output_widthmap (FILE *stream) +{ +} + +/* Output the tables to the given file. */ + +static void +output_tables (const char *filename, const char *version) +{ + FILE *stream; + unsigned int ch; + + stream = fopen (filename, "w"); + if (stream == NULL) + { + fprintf (stderr, "cannot open '%s' for writing\n", filename); + exit (1); + } + + fprintf (stream, "escape_char /\n"); + fprintf (stream, "comment_char %%\n"); + fprintf (stream, "\n"); + fprintf (stream, "%% Generated automatically by gen-unicode-ctype for Unicode %s.\n", + version); + fprintf (stream, "\n"); + + fprintf (stream, "LC_IDENTIFICATION\n"); + fprintf (stream, "title \"Unicode %s FDCC-set\"\n", version); + fprintf (stream, "source \"UnicodeData.txt, PropList.txt\"\n"); + fprintf (stream, "address \"\"\n"); + fprintf (stream, "contact \"\"\n"); + fprintf (stream, "email \"bug-glibc-locales@gnu.org\"\n"); + fprintf (stream, "tel \"\"\n"); + fprintf (stream, "fax \"\"\n"); + fprintf (stream, "language \"\"\n"); + fprintf (stream, "territory \"Earth\"\n"); + fprintf (stream, "revision \"%s\"\n", version); + { + time_t now; + char date[11]; + now = time (NULL); + strftime (date, sizeof (date), "%Y-%m-%d", gmtime (&now)); + fprintf (stream, "date \"%s\"\n", date); + } + fprintf (stream, "category \"unicode:2001\";LC_CTYPE\n"); + fprintf (stream, "END LC_IDENTIFICATION\n"); + fprintf (stream, "\n"); + + /* Verifications. */ + for (ch = 0; ch < 0x110000; ch++) + { + /* toupper restriction: "Only characters specified for the keywords + lower and upper shall be specified. */ + if (to_upper (ch) != ch && !(is_lower (ch) || is_upper (ch))) + fprintf (stderr, + "%s is not upper|lower but toupper(0x%04X) = 0x%04X\n", + ucs_symbol (ch), ch, to_upper (ch)); + + /* tolower restriction: "Only characters specified for the keywords + lower and upper shall be specified. */ + if (to_lower (ch) != ch && !(is_lower (ch) || is_upper (ch))) + fprintf (stderr, + "%s is not upper|lower but tolower(0x%04X) = 0x%04X\n", + ucs_symbol (ch), ch, to_lower (ch)); + + /* alpha restriction: "Characters classified as either upper or lower + shall automatically belong to this class. */ + if ((is_lower (ch) || is_upper (ch)) && !is_alpha (ch)) + fprintf (stderr, "%s is upper|lower but not alpha\n", ucs_symbol (ch)); + + /* alpha restriction: "No character specified for the keywords cntrl, + digit, punct or space shall be specified." */ + if (is_alpha (ch) && is_cntrl (ch)) + fprintf (stderr, "%s is alpha and cntrl\n", ucs_symbol (ch)); + if (is_alpha (ch) && is_digit (ch)) + fprintf (stderr, "%s is alpha and digit\n", ucs_symbol (ch)); + if (is_alpha (ch) && is_punct (ch)) + fprintf (stderr, "%s is alpha and punct\n", ucs_symbol (ch)); + if (is_alpha (ch) && is_space (ch)) + fprintf (stderr, "%s is alpha and space\n", ucs_symbol (ch)); + + /* space restriction: "No character specified for the keywords upper, + lower, alpha, digit, graph or xdigit shall be specified." + upper, lower, alpha already checked above. */ + if (is_space (ch) && is_digit (ch)) + fprintf (stderr, "%s is space and digit\n", ucs_symbol (ch)); + if (is_space (ch) && is_graph (ch)) + fprintf (stderr, "%s is space and graph\n", ucs_symbol (ch)); + if (is_space (ch) && is_xdigit (ch)) + fprintf (stderr, "%s is space and xdigit\n", ucs_symbol (ch)); + + /* cntrl restriction: "No character specified for the keywords upper, + lower, alpha, digit, punct, graph, print or xdigit shall be + specified." upper, lower, alpha already checked above. */ + if (is_cntrl (ch) && is_digit (ch)) + fprintf (stderr, "%s is cntrl and digit\n", ucs_symbol (ch)); + if (is_cntrl (ch) && is_punct (ch)) + fprintf (stderr, "%s is cntrl and punct\n", ucs_symbol (ch)); + if (is_cntrl (ch) && is_graph (ch)) + fprintf (stderr, "%s is cntrl and graph\n", ucs_symbol (ch)); + if (is_cntrl (ch) && is_print (ch)) + fprintf (stderr, "%s is cntrl and print\n", ucs_symbol (ch)); + if (is_cntrl (ch) && is_xdigit (ch)) + fprintf (stderr, "%s is cntrl and xdigit\n", ucs_symbol (ch)); + + /* punct restriction: "No character specified for the keywords upper, + lower, alpha, digit, cntrl, xdigit or as the character shall + be specified." upper, lower, alpha, cntrl already checked above. */ + if (is_punct (ch) && is_digit (ch)) + fprintf (stderr, "%s is punct and digit\n", ucs_symbol (ch)); + if (is_punct (ch) && is_xdigit (ch)) + fprintf (stderr, "%s is punct and xdigit\n", ucs_symbol (ch)); + if (is_punct (ch) && (ch == 0x0020)) + fprintf (stderr, "%s is punct\n", ucs_symbol (ch)); + + /* graph restriction: "No character specified for the keyword cntrl + shall be specified." Already checked above. */ + + /* print restriction: "No character specified for the keyword cntrl + shall be specified." Already checked above. */ + + /* graph - print relation: differ only in the character. + How is this possible if there are more than one space character?! + I think susv2/xbd/locale.html should speak of "space characters", + not "space character". */ + if (is_print (ch) && !(is_graph (ch) || /* ch == 0x0020 */ is_space (ch))) + fprintf (stderr, + "%s is print but not graph|\n", ucs_symbol (ch)); + if (!is_print (ch) && (is_graph (ch) || ch == 0x0020)) + fprintf (stderr, + "%s is graph| but not print\n", ucs_symbol (ch)); + } + + fprintf (stream, "LC_CTYPE\n"); + output_charclass (stream, "upper", is_upper); + output_charclass (stream, "lower", is_lower); + output_charclass (stream, "alpha", is_alpha); + output_charclass (stream, "digit", is_digit); + output_charclass (stream, "outdigit", is_outdigit); + output_charclass (stream, "blank", is_blank); + output_charclass (stream, "space", is_space); + output_charclass (stream, "cntrl", is_cntrl); + output_charclass (stream, "punct", is_punct); + output_charclass (stream, "xdigit", is_xdigit); + output_charclass (stream, "graph", is_graph); + output_charclass (stream, "print", is_print); + output_charclass (stream, "class \"combining\";", is_combining); + output_charclass (stream, "class \"combining_level3\";", is_combining_level3); + output_charmap (stream, "toupper", to_upper); + output_charmap (stream, "tolower", to_lower); + output_charmap (stream, "map \"totitle\";", to_title); + output_widthmap (stream); + fprintf (stream, "END LC_CTYPE\n"); + + if (ferror (stream) || fclose (stream)) + { + fprintf (stderr, "error writing to '%s'\n", filename); + exit (1); + } +} + +int +main (int argc, char * argv[]) +{ + if (argc != 3) + { + fprintf (stderr, "Usage: %s UnicodeData.txt version\n", argv[0]); + exit (1); + } + + fill_attributes (argv[1]); + + output_tables ("unicode", argv[2]); + + return 0; +} diff --git a/test/locale/show-ucs-data.c b/test/locale/show-ucs-data.c new file mode 100644 index 000000000..9992ece42 --- /dev/null +++ b/test/locale/show-ucs-data.c @@ -0,0 +1,62 @@ +#include +#include +#include +#include + +int +main (int argc, char *argv[]) +{ + int n; + char *line = NULL; + size_t len = 0; + + for (n = 1; n < argc; ++n) + { + FILE *fp = fopen (argv[n], "r"); + if (fp == NULL) + continue; + + while (! feof (fp)) + { + ssize_t cnt = getline (&line, &len, fp); + char *runp; + if (cnt <= 0) + break; + + runp = line; + do + { + if (runp[0] == '<' && runp[1] == 'U' && isxdigit (runp[2]) + && isxdigit (runp[3]) && isxdigit (runp[4]) + && isxdigit (runp[5]) && runp[6] == '>') + { + unsigned int val = strtoul (runp + 2, NULL, 16); + + //putchar ('<'); + if (val < 128) + putchar (val); + else if (val < 0x800) + { + putchar (0xc0 | (val >> 6)); + putchar (0x80 | (val & 0x3f)); + } + else + { + putchar (0xe0 | (val >> 12)); + putchar (0x80 | ((val >> 6) & 0x3f)); + putchar (0x80 | (val & 0x3f)); + } + //putchar ('>'); + runp += 7; + } + else + putchar (*runp++); + } + while (runp < &line[cnt]); + } + + fclose (fp); + } + + return 0; +} diff --git a/test/locale/tst-C-locale.c b/test/locale/tst-C-locale.c new file mode 100644 index 000000000..c568cf404 --- /dev/null +++ b/test/locale/tst-C-locale.c @@ -0,0 +1,498 @@ +/* Tests of C and POSIX locale contents. + Copyright (C) 2000, 2001, 2002, 2003, 2004 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Ulrich Drepper , 2000. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +#include +#include +#include +#include +#include +#include +#include +#include + + +static int +run_test (const char *locname) +{ + struct lconv *lc; + const char *str; + const wchar_t *wstr; + int result = 0; + locale_t loc; + + /* ISO C stuff. */ + lc = localeconv (); + if (lc == NULL) + { + printf ("localeconv failed for locale %s\n", locname); + result = 1; + } + else + { +#define STRTEST(name, exp) \ + do \ + if (strcmp (lc->name, exp) != 0) \ + { \ + printf (#name " in locale %s wrong (is \"%s\", should be \"%s\")\n",\ + locname, lc->name, exp); \ + result = 1; \ + } \ + while (0) + STRTEST (decimal_point, "."); + STRTEST (thousands_sep, ""); + STRTEST (grouping, ""); + STRTEST (mon_decimal_point, ""); + STRTEST (mon_thousands_sep, ""); + STRTEST (mon_grouping, ""); + STRTEST (positive_sign, ""); + STRTEST (negative_sign, ""); + STRTEST (currency_symbol, ""); + STRTEST (int_curr_symbol, ""); + +#define CHARTEST(name, exp) \ + do \ + if (lc->name != exp) \ + { \ + printf (#name " in locale %s wrong (is %d, should be %d)\n", \ + locname, lc->name, CHAR_MAX); \ + result = 1; \ + } \ + while (0) + CHARTEST (frac_digits, CHAR_MAX); + CHARTEST (p_cs_precedes, CHAR_MAX); + CHARTEST (n_cs_precedes, CHAR_MAX); + CHARTEST (p_sep_by_space, CHAR_MAX); + CHARTEST (n_sep_by_space, CHAR_MAX); + CHARTEST (p_sign_posn, CHAR_MAX); + CHARTEST (n_sign_posn, CHAR_MAX); + CHARTEST (int_frac_digits, CHAR_MAX); + CHARTEST (int_p_cs_precedes, CHAR_MAX); + CHARTEST (int_n_cs_precedes, CHAR_MAX); + CHARTEST (int_p_sep_by_space, CHAR_MAX); + CHARTEST (int_n_sep_by_space, CHAR_MAX); + CHARTEST (int_p_sign_posn, CHAR_MAX); + CHARTEST (int_n_sign_posn, CHAR_MAX); + } + +#undef STRTEST +#define STRTEST(name, exp) \ + str = nl_langinfo (name); \ + if (strcmp (str, exp) != 0) \ + { \ + printf ("nl_langinfo(" #name ") in locale %s wrong " \ + "(is \"%s\", should be \"%s\")\n", locname, str, exp); \ + result = 1; \ + } +#define WSTRTEST(name, exp) \ + wstr = (wchar_t *) nl_langinfo (name); \ + if (wcscmp (wstr, exp) != 0) \ + { \ + printf ("nl_langinfo(" #name ") in locale %s wrong " \ + "(is \"%S\", should be \"%S\")\n", locname, wstr, exp); \ + result = 1; \ + } + + /* Unix stuff. */ + STRTEST (ABDAY_1, "Sun"); + STRTEST (ABDAY_2, "Mon"); + STRTEST (ABDAY_3, "Tue"); + STRTEST (ABDAY_4, "Wed"); + STRTEST (ABDAY_5, "Thu"); + STRTEST (ABDAY_6, "Fri"); + STRTEST (ABDAY_7, "Sat"); + STRTEST (DAY_1, "Sunday"); + STRTEST (DAY_2, "Monday"); + STRTEST (DAY_3, "Tuesday"); + STRTEST (DAY_4, "Wednesday"); + STRTEST (DAY_5, "Thursday"); + STRTEST (DAY_6, "Friday"); + STRTEST (DAY_7, "Saturday"); + STRTEST (ABMON_1, "Jan"); + STRTEST (ABMON_2, "Feb"); + STRTEST (ABMON_3, "Mar"); + STRTEST (ABMON_4, "Apr"); + STRTEST (ABMON_5, "May"); + STRTEST (ABMON_6, "Jun"); + STRTEST (ABMON_7, "Jul"); + STRTEST (ABMON_8, "Aug"); + STRTEST (ABMON_9, "Sep"); + STRTEST (ABMON_10, "Oct"); + STRTEST (ABMON_11, "Nov"); + STRTEST (ABMON_12, "Dec"); + STRTEST (MON_1, "January"); + STRTEST (MON_2, "February"); + STRTEST (MON_3, "March"); + STRTEST (MON_4, "April"); + STRTEST (MON_5, "May"); + STRTEST (MON_6, "June"); + STRTEST (MON_7, "July"); + STRTEST (MON_8, "August"); + STRTEST (MON_9, "September"); + STRTEST (MON_10, "October"); + STRTEST (MON_11, "November"); + STRTEST (MON_12, "December"); + STRTEST (AM_STR, "AM"); + STRTEST (PM_STR, "PM"); + STRTEST (D_T_FMT, "%a %b %e %H:%M:%S %Y"); + STRTEST (D_FMT, "%m/%d/%y"); + STRTEST (T_FMT, "%H:%M:%S"); + STRTEST (T_FMT_AMPM, "%I:%M:%S %p"); + STRTEST (ERA, ""); + STRTEST (ERA_D_FMT, ""); + STRTEST (ERA_T_FMT, ""); + STRTEST (ERA_D_T_FMT, ""); + STRTEST (ALT_DIGITS, ""); + + STRTEST (RADIXCHAR, "."); + STRTEST (THOUSEP, ""); + + STRTEST (YESEXPR, "^[yY]"); + STRTEST (NOEXPR, "^[nN]"); + + /* Extensions. */ + WSTRTEST (_NL_WABDAY_1, L"Sun"); + WSTRTEST (_NL_WABDAY_2, L"Mon"); + WSTRTEST (_NL_WABDAY_3, L"Tue"); + WSTRTEST (_NL_WABDAY_4, L"Wed"); + WSTRTEST (_NL_WABDAY_5, L"Thu"); + WSTRTEST (_NL_WABDAY_6, L"Fri"); + WSTRTEST (_NL_WABDAY_7, L"Sat"); + WSTRTEST (_NL_WDAY_1, L"Sunday"); + WSTRTEST (_NL_WDAY_2, L"Monday"); + WSTRTEST (_NL_WDAY_3, L"Tuesday"); + WSTRTEST (_NL_WDAY_4, L"Wednesday"); + WSTRTEST (_NL_WDAY_5, L"Thursday"); + WSTRTEST (_NL_WDAY_6, L"Friday"); + WSTRTEST (_NL_WDAY_7, L"Saturday"); + WSTRTEST (_NL_WABMON_1, L"Jan"); + WSTRTEST (_NL_WABMON_2, L"Feb"); + WSTRTEST (_NL_WABMON_3, L"Mar"); + WSTRTEST (_NL_WABMON_4, L"Apr"); + WSTRTEST (_NL_WABMON_5, L"May"); + WSTRTEST (_NL_WABMON_6, L"Jun"); + WSTRTEST (_NL_WABMON_7, L"Jul"); + WSTRTEST (_NL_WABMON_8, L"Aug"); + WSTRTEST (_NL_WABMON_9, L"Sep"); + WSTRTEST (_NL_WABMON_10, L"Oct"); + WSTRTEST (_NL_WABMON_11, L"Nov"); + WSTRTEST (_NL_WABMON_12, L"Dec"); + WSTRTEST (_NL_WMON_1, L"January"); + WSTRTEST (_NL_WMON_2, L"February"); + WSTRTEST (_NL_WMON_3, L"March"); + WSTRTEST (_NL_WMON_4, L"April"); + WSTRTEST (_NL_WMON_5, L"May"); + WSTRTEST (_NL_WMON_6, L"June"); + WSTRTEST (_NL_WMON_7, L"July"); + WSTRTEST (_NL_WMON_8, L"August"); + WSTRTEST (_NL_WMON_9, L"September"); + WSTRTEST (_NL_WMON_10, L"October"); + WSTRTEST (_NL_WMON_11, L"November"); + WSTRTEST (_NL_WMON_12, L"December"); + WSTRTEST (_NL_WAM_STR, L"AM"); + WSTRTEST (_NL_WPM_STR, L"PM"); + WSTRTEST (_NL_WD_T_FMT, L"%a %b %e %H:%M:%S %Y"); + WSTRTEST (_NL_WD_FMT, L"%m/%d/%y"); + WSTRTEST (_NL_WT_FMT, L"%H:%M:%S"); + WSTRTEST (_NL_WT_FMT_AMPM, L"%I:%M:%S %p"); + WSTRTEST (_NL_WERA_D_FMT, L""); + WSTRTEST (_NL_WERA_T_FMT, L""); + WSTRTEST (_NL_WERA_D_T_FMT, L""); + WSTRTEST (_NL_WALT_DIGITS, L""); + + STRTEST (_DATE_FMT, "%a %b %e %H:%M:%S %Z %Y"); + WSTRTEST (_NL_W_DATE_FMT, L"%a %b %e %H:%M:%S %Z %Y"); + + STRTEST (INT_CURR_SYMBOL, ""); + STRTEST (CURRENCY_SYMBOL, ""); + STRTEST (MON_DECIMAL_POINT, ""); + STRTEST (MON_THOUSANDS_SEP, ""); + STRTEST (MON_GROUPING, ""); + STRTEST (POSITIVE_SIGN, ""); + STRTEST (NEGATIVE_SIGN, ""); + STRTEST (GROUPING, ""); + + STRTEST (YESSTR, ""); + STRTEST (NOSTR, ""); + + /* Test the new locale mechanisms. */ + loc = newlocale (LC_ALL_MASK, locname, NULL); + if (loc == NULL) + { + printf ("cannot create locale object for locale %s\n", locname); + result = 1; + } + else + { + int c; + +#undef STRTEST +#define STRTEST(name, exp) \ + str = nl_langinfo_l (name, loc); \ + if (strcmp (str, exp) != 0) \ + { \ + printf ("nl_langinfo_l(" #name ") in locale %s wrong " \ + "(is \"%s\", should be \"%s\")\n", locname, str, exp); \ + result = 1; \ + } +#undef WSTRTEST +#define WSTRTEST(name, exp) \ + wstr = (wchar_t *) nl_langinfo_l (name, loc); \ + if (wcscmp (wstr, exp) != 0) \ + { \ + printf ("nl_langinfo_l(" #name ") in locale %s wrong " \ + "(is \"%S\", should be \"%S\")\n", locname, wstr, exp); \ + result = 1; \ + } + + /* Unix stuff. */ + STRTEST (ABDAY_1, "Sun"); + STRTEST (ABDAY_2, "Mon"); + STRTEST (ABDAY_3, "Tue"); + STRTEST (ABDAY_4, "Wed"); + STRTEST (ABDAY_5, "Thu"); + STRTEST (ABDAY_6, "Fri"); + STRTEST (ABDAY_7, "Sat"); + STRTEST (DAY_1, "Sunday"); + STRTEST (DAY_2, "Monday"); + STRTEST (DAY_3, "Tuesday"); + STRTEST (DAY_4, "Wednesday"); + STRTEST (DAY_5, "Thursday"); + STRTEST (DAY_6, "Friday"); + STRTEST (DAY_7, "Saturday"); + STRTEST (ABMON_1, "Jan"); + STRTEST (ABMON_2, "Feb"); + STRTEST (ABMON_3, "Mar"); + STRTEST (ABMON_4, "Apr"); + STRTEST (ABMON_5, "May"); + STRTEST (ABMON_6, "Jun"); + STRTEST (ABMON_7, "Jul"); + STRTEST (ABMON_8, "Aug"); + STRTEST (ABMON_9, "Sep"); + STRTEST (ABMON_10, "Oct"); + STRTEST (ABMON_11, "Nov"); + STRTEST (ABMON_12, "Dec"); + STRTEST (MON_1, "January"); + STRTEST (MON_2, "February"); + STRTEST (MON_3, "March"); + STRTEST (MON_4, "April"); + STRTEST (MON_5, "May"); + STRTEST (MON_6, "June"); + STRTEST (MON_7, "July"); + STRTEST (MON_8, "August"); + STRTEST (MON_9, "September"); + STRTEST (MON_10, "October"); + STRTEST (MON_11, "November"); + STRTEST (MON_12, "December"); + STRTEST (AM_STR, "AM"); + STRTEST (PM_STR, "PM"); + STRTEST (D_T_FMT, "%a %b %e %H:%M:%S %Y"); + STRTEST (D_FMT, "%m/%d/%y"); + STRTEST (T_FMT, "%H:%M:%S"); + STRTEST (T_FMT_AMPM, "%I:%M:%S %p"); + STRTEST (ERA, ""); + STRTEST (ERA_D_FMT, ""); + STRTEST (ERA_T_FMT, ""); + STRTEST (ERA_D_T_FMT, ""); + STRTEST (ALT_DIGITS, ""); + + STRTEST (RADIXCHAR, "."); + STRTEST (THOUSEP, ""); + + STRTEST (YESEXPR, "^[yY]"); + STRTEST (NOEXPR, "^[nN]"); + + /* Extensions. */ + WSTRTEST (_NL_WABDAY_1, L"Sun"); + WSTRTEST (_NL_WABDAY_2, L"Mon"); + WSTRTEST (_NL_WABDAY_3, L"Tue"); + WSTRTEST (_NL_WABDAY_4, L"Wed"); + WSTRTEST (_NL_WABDAY_5, L"Thu"); + WSTRTEST (_NL_WABDAY_6, L"Fri"); + WSTRTEST (_NL_WABDAY_7, L"Sat"); + WSTRTEST (_NL_WDAY_1, L"Sunday"); + WSTRTEST (_NL_WDAY_2, L"Monday"); + WSTRTEST (_NL_WDAY_3, L"Tuesday"); + WSTRTEST (_NL_WDAY_4, L"Wednesday"); + WSTRTEST (_NL_WDAY_5, L"Thursday"); + WSTRTEST (_NL_WDAY_6, L"Friday"); + WSTRTEST (_NL_WDAY_7, L"Saturday"); + WSTRTEST (_NL_WABMON_1, L"Jan"); + WSTRTEST (_NL_WABMON_2, L"Feb"); + WSTRTEST (_NL_WABMON_3, L"Mar"); + WSTRTEST (_NL_WABMON_4, L"Apr"); + WSTRTEST (_NL_WABMON_5, L"May"); + WSTRTEST (_NL_WABMON_6, L"Jun"); + WSTRTEST (_NL_WABMON_7, L"Jul"); + WSTRTEST (_NL_WABMON_8, L"Aug"); + WSTRTEST (_NL_WABMON_9, L"Sep"); + WSTRTEST (_NL_WABMON_10, L"Oct"); + WSTRTEST (_NL_WABMON_11, L"Nov"); + WSTRTEST (_NL_WABMON_12, L"Dec"); + WSTRTEST (_NL_WMON_1, L"January"); + WSTRTEST (_NL_WMON_2, L"February"); + WSTRTEST (_NL_WMON_3, L"March"); + WSTRTEST (_NL_WMON_4, L"April"); + WSTRTEST (_NL_WMON_5, L"May"); + WSTRTEST (_NL_WMON_6, L"June"); + WSTRTEST (_NL_WMON_7, L"July"); + WSTRTEST (_NL_WMON_8, L"August"); + WSTRTEST (_NL_WMON_9, L"September"); + WSTRTEST (_NL_WMON_10, L"October"); + WSTRTEST (_NL_WMON_11, L"November"); + WSTRTEST (_NL_WMON_12, L"December"); + WSTRTEST (_NL_WAM_STR, L"AM"); + WSTRTEST (_NL_WPM_STR, L"PM"); + WSTRTEST (_NL_WD_T_FMT, L"%a %b %e %H:%M:%S %Y"); + WSTRTEST (_NL_WD_FMT, L"%m/%d/%y"); + WSTRTEST (_NL_WT_FMT, L"%H:%M:%S"); + WSTRTEST (_NL_WT_FMT_AMPM, L"%I:%M:%S %p"); + WSTRTEST (_NL_WERA_D_FMT, L""); + WSTRTEST (_NL_WERA_T_FMT, L""); + WSTRTEST (_NL_WERA_D_T_FMT, L""); + WSTRTEST (_NL_WALT_DIGITS, L""); + + STRTEST (_DATE_FMT, "%a %b %e %H:%M:%S %Z %Y"); + WSTRTEST (_NL_W_DATE_FMT, L"%a %b %e %H:%M:%S %Z %Y"); + + STRTEST (INT_CURR_SYMBOL, ""); + STRTEST (CURRENCY_SYMBOL, ""); + STRTEST (MON_DECIMAL_POINT, ""); + STRTEST (MON_THOUSANDS_SEP, ""); + STRTEST (MON_GROUPING, ""); + STRTEST (POSITIVE_SIGN, ""); + STRTEST (NEGATIVE_SIGN, ""); + STRTEST (GROUPING, ""); + + STRTEST (YESSTR, ""); + STRTEST (NOSTR, ""); + + /* Character class tests. */ + for (c = 0; c < 128; ++c) + { +#define CLASSTEST(name) \ + if (is##name (c) != is##name##_l (c, loc)) \ + { \ + printf ("is%s('\\%o') != is%s_l('\\%o')\n", \ + #name, c, #name, c); \ + result = 1; \ + } + CLASSTEST (alnum); + CLASSTEST (alpha); + CLASSTEST (blank); + CLASSTEST (cntrl); + CLASSTEST (digit); + CLASSTEST (lower); + CLASSTEST (graph); + CLASSTEST (print); + CLASSTEST (punct); + CLASSTEST (space); + CLASSTEST (upper); + CLASSTEST (xdigit); + + /* Character mapping tests. */ +#define MAPTEST(name) \ + if (to##name (c) != to##name##_l (c, loc)) \ + { \ + printf ("to%s('\\%o') != to%s_l('\\%o'): '\\%o' vs '\\%o'\n", \ + #name, c, #name, c, \ + to##name (c), to##name##_l (c, loc)); \ + result = 1; \ + } + MAPTEST (lower); + MAPTEST (upper); + } + + /* Character class tests, this time for wide characters. Note that + this only works because we know that the internal encoding is + UCS4. */ + for (c = 0; c < 128; ++c) + { +#undef CLASSTEST +#define CLASSTEST(name) \ + if (isw##name (c) != isw##name##_l (c, loc)) \ + { \ + printf ("isw%s('\\%o') != isw%s_l('\\%o')\n", \ + #name, c, #name, c); \ + result = 1; \ + } + CLASSTEST (alnum); + CLASSTEST (alpha); + CLASSTEST (blank); + CLASSTEST (cntrl); + CLASSTEST (digit); + CLASSTEST (lower); + CLASSTEST (graph); + CLASSTEST (print); + CLASSTEST (punct); + CLASSTEST (space); + CLASSTEST (upper); + CLASSTEST (xdigit); + + /* Character mapping tests. Note that + this only works because we know that the internal encoding is + UCS4. */ +#undef MAPTEST +#define MAPTEST(name) \ + if (tow##name (c) != tow##name##_l (c, loc)) \ + { \ + printf ("tow%s('\\%o') != tow%s_l('\\%o'): '\\%o' vs '\\%o'\n",\ + #name, c, #name, c, \ + tow##name (c), tow##name##_l (c, loc)); \ + result = 1; \ + } + MAPTEST (lower); + MAPTEST (upper); + } + + freelocale (loc); + } + + return result; +} + + +static int +do_test (void) +{ + int result; + + /* First use the name "C". */ + if (setlocale (LC_ALL, "C") == NULL) + { + puts ("cannot set C locale"); + result = 1; + } + else + result = run_test ("C"); + + /* Then the name "POSIX". */ + if (setlocale (LC_ALL, "POSIX") == NULL) + { + puts ("cannot set POSIX locale"); + result = 1; + } + else + result |= run_test ("POSIX"); + + return result; +} + +#define TEST_FUNCTION do_test () +#include "../test-skeleton.c" diff --git a/test/locale/tst-ctype-de_DE.ISO-8859-1.in b/test/locale/tst-ctype-de_DE.ISO-8859-1.in new file mode 100644 index 000000000..f71d76cc2 --- /dev/null +++ b/test/locale/tst-ctype-de_DE.ISO-8859-1.in @@ -0,0 +1,56 @@ +lower  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000100000000000000000000000000 +lower ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000000000000111111111111111111111111011111111 +upper  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000000000000001111111111111111 +upper ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 111111101111111000000000000000000000000000000000 +alpha  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000010000000000100001000001111111111111111 +alpha ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 111111101111111111111111111111111111111011111111 +digit  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000000000000000000000000000000 +digit ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000000000000000000000000000000000000000000000 +xdigit  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000000000000000000000000000000 +xdigit ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000000000000000000000000000000000000000000000 +space  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000000000000000000000000000000 +space ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000000000000000000000000000000000000000000000 +print  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 111111111111111111111111111111111111111111111111 +print ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 111111111111111111111111111111111111111111111111 +graph  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 111111111111111111111111111111111111111111111111 +graph ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 111111111111111111111111111111111111111111111111 +blank  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000000000000000000000000000000 +blank ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000000000000000000000000000000000000000000000 +cntrl  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000000000000000000000000000000000000000000 +cntrl ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000000000000000000000000000000000000000000000 +punct  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 111111111101111111111011110111110000000000000000 +punct ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 000000010000000000000000000000000000000100000000 +alnum  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ + 000000000010000000000100001000001111111111111111 +alnum ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + 111111101111111111111111111111111111111011111111 +tolower  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ +  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿àáâãäåæçèéêëìíîï +tolower ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + ðñòóôõö×øùúûüýþßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ +toupper  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ +  ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ +toupper ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ + ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ÷ØÙÚÛÜÝÞÿ diff --git a/test/locale/tst-ctype.c b/test/locale/tst-ctype.c new file mode 100644 index 000000000..c03c2dab3 --- /dev/null +++ b/test/locale/tst-ctype.c @@ -0,0 +1,447 @@ +/* Copyright (C) 2000,02, 05 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Ulrich Drepper , 2000. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +#include +#include +#include +#include +#include + + +static const char lower[] = "abcdefghijklmnopqrstuvwxyz"; +static const char upper[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; +static const char digits[] = "0123456789"; +static const char cntrl[] = "\ +\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\ +\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f "; + + +static struct classes +{ + const char *name; + int mask; +} classes[] = +{ +#define ENTRY(name) { #name, _IS##name } + ENTRY (upper), + ENTRY (lower), + ENTRY (alpha), + ENTRY (digit), + ENTRY (xdigit), + ENTRY (space), + ENTRY (print), + ENTRY (graph), + ENTRY (blank), + ENTRY (cntrl), + ENTRY (punct), + ENTRY (alnum) +}; +#define nclasses (sizeof (classes) / sizeof (classes[0])) + + +#define FAIL(str, args...) \ + { \ + printf (" " str "\n", ##args); \ + ++errors; \ + } + + +int +main (void) +{ + const char *cp; + const char *cp2; + int errors = 0; + char *inpline = NULL; + size_t inplinelen = 0; + char *resline = NULL; + size_t reslinelen = 0; + size_t n; + + setlocale (LC_ALL, ""); + + printf ("Testing the ctype data of the `%s' locale\n", + setlocale (LC_CTYPE, NULL)); + +#if 0 + /* Just for debugging. */ + + /* Contents of the class array. */ + printf ("\ +upper = %04x lower = %04x alpha = %04x digit = %04x xdigit = %04x\n\ +space = %04x print = %04x graph = %04x blank = %04x cntrl = %04x\n\ +punct = %04x alnum = %04x\n", + _ISupper, _ISlower, _ISalpha, _ISdigit, _ISxdigit, + _ISspace, _ISprint, _ISgraph, _ISblank, _IScntrl, + _ISpunct, _ISalnum); + + while (n < 256) + { + if (n % 8 == 0) + printf ("%02x: ", n); + printf ("%04x%s", __ctype_b[n], (n + 1) % 8 == 0 ? "\n" : " "); + ++n; + } +#endif + + puts (" Test of ASCII charact