Mercurial > hg > octave-kai > gnulib-hg
changeset 11334:b47f94d88504
Tests for module 'unicase/u32-casefold'.
author | Bruno Haible <bruno@clisp.org> |
---|---|
date | Sun, 08 Mar 2009 16:32:14 +0100 |
parents | 2d99a732f2af |
children | fdd1dfe176a5 |
files | ChangeLog modules/unicase/u32-casefold-tests tests/unicase/test-u32-casefold.c |
diffstat | 3 files changed, 233 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,9 @@ 2009-03-08 Bruno Haible <bruno@clisp.org> + Tests for module 'unicase/u32-casefold'. + * modules/unicase/u32-casefold-tests: New file. + * tests/unicase/test-u32-casefold.c: New file. + Tests for module 'unicase/u16-casefold'. * modules/unicase/u16-casefold-tests: New file. * tests/unicase/test-u16-casefold.c: New file.
new file mode 100644 --- /dev/null +++ b/modules/unicase/u32-casefold-tests @@ -0,0 +1,15 @@ +Files: +tests/unicase/test-u32-casefold.c + +Depends-on: +unistr/u32-cmp +uninorm/nfc +uninorm/nfd + +configure.ac: + +Makefile.am: +TESTS += test-u32-casefold +check_PROGRAMS += test-u32-casefold +test_u32_casefold_SOURCES = unicase/test-u32-casefold.c +
new file mode 100644 --- /dev/null +++ b/tests/unicase/test-u32-casefold.c @@ -0,0 +1,214 @@ +/* Test of casefolding mapping for UTF-32 strings. + Copyright (C) 2009 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 <http://www.gnu.org/licenses/>. */ + +/* Written by Bruno Haible <bruno@clisp.org>, 2009. */ + +#include <config.h> + +#include "unicase.h" + +#include <stdio.h> +#include <stdlib.h> + +#include "unistr.h" +#include "uninorm.h" + +#define SIZEOF(array) (sizeof (array) / sizeof (array[0])) +#define ASSERT(expr) \ + do \ + { \ + if (!(expr)) \ + { \ + fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \ + fflush (stderr); \ + abort (); \ + } \ + } \ + while (0) + +static int +check (const uint32_t *input, size_t input_length, + const char *iso639_language, uninorm_t nf, + const uint32_t *expected, size_t expected_length) +{ + size_t length; + uint32_t *result; + + /* Test return conventions with resultbuf == NULL. */ + result = u32_casefold (input, input_length, iso639_language, nf, NULL, &length); + if (!(result != NULL)) + return 1; + if (!(length == expected_length)) + return 2; + if (!(u32_cmp (result, expected, expected_length) == 0)) + return 3; + free (result); + + /* Test return conventions with resultbuf too small. */ + if (expected_length > 0) + { + uint32_t *preallocated; + + length = expected_length - 1; + preallocated = (uint32_t *) malloc (length * sizeof (uint32_t)); + result = u32_casefold (input, input_length, iso639_language, nf, preallocated, &length); + if (!(result != NULL)) + return 4; + if (!(result != preallocated)) + return 5; + if (!(length == expected_length)) + return 6; + if (!(u32_cmp (result, expected, expected_length) == 0)) + return 7; + free (result); + free (preallocated); + } + + /* Test return conventions with resultbuf large enough. */ + { + uint32_t *preallocated; + + length = expected_length; + preallocated = (uint32_t *) malloc (length * sizeof (uint32_t)); + result = u32_casefold (input, input_length, iso639_language, nf, preallocated, &length); + if (!(result != NULL)) + return 8; + if (!(result == preallocated)) + return 9; + if (!(length == expected_length)) + return 10; + if (!(u32_cmp (result, expected, expected_length) == 0)) + return 11; + free (preallocated); + } + + return 0; +} + +int +main () +{ + { /* Empty string. */ + ASSERT (check (NULL, 0, NULL, NULL, NULL, 0) == 0); + ASSERT (check (NULL, 0, NULL, UNINORM_NFC, NULL, 0) == 0); + } + + /* Simple string. */ + { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */ + static const uint32_t input[] = + { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ', + 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443, + 0x0439, 0x0442, 0x0435, '!', ' ', + 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2, + '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ', + 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n' + }; + static const uint32_t casefolded[] = + { 'g', 'r', 0x00FC, 0x0073, 0x0073, ' ', 'g', 'o', 't', 't', '.', ' ', + 0x0437, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443, + 0x0439, 0x0442, 0x0435, '!', ' ', + 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2, + '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ', + 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n' + }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + } + + /* Case mapping can increase the number of Unicode characters. */ + { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */ + static const uint32_t input[] = { 0x0149 }; + static const uint32_t casefolded[] = { 0x02BC, 0x006E }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + } + { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */ + static const uint32_t input[] = { 0x0390 }; + static const uint32_t casefolded[] = { 0x03B9, 0x0308, 0x0301 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + } + + /* Turkish letters i İ ı I */ + { /* LATIN CAPITAL LETTER I */ + static const uint32_t input[] = { 0x0049 }; + static const uint32_t casefolded[] = { 0x0069 }; + static const uint32_t casefolded_tr[] = { 0x0131 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded_tr, SIZEOF (casefolded_tr)) == 0); + } + { /* LATIN SMALL LETTER I */ + static const uint32_t input[] = { 0x0069 }; + static const uint32_t casefolded[] = { 0x0069 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded, SIZEOF (casefolded)) == 0); + } + { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */ + static const uint32_t input[] = { 0x0130 }; + static const uint32_t casefolded[] = { 0x0069, 0x0307 }; + static const uint32_t casefolded_tr[] = { 0x0069 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded_tr, SIZEOF (casefolded_tr)) == 0); + } + { /* LATIN SMALL LETTER DOTLESS I */ + static const uint32_t input[] = { 0x0131 }; + static const uint32_t casefolded[] = { 0x0131 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded, SIZEOF (casefolded)) == 0); + } + { /* "topkapı" */ + static const uint32_t input[] = + { 0x0074, 0x006F, 0x0070, 0x006B, 0x0061, 0x0070, 0x0131 }; + static const uint32_t casefolded[] = + { 0x0074, 0x006F, 0x0070, 0x006B, 0x0061, 0x0070, 0x0131 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded, SIZEOF (casefolded)) == 0); + } + + /* Uppercasing can increase the number of Unicode characters. */ + { /* "heiß" */ + static const uint32_t input[] = { 0x0068, 0x0065, 0x0069, 0x00DF }; + static const uint32_t casefolded[] = { 0x0068, 0x0065, 0x0069, 0x0073, 0x0073 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + } + + /* Case mappings for some characters can depend on the surrounding characters. */ + { /* "περισσότερες πληροφορίες" */ + static const uint32_t input[] = + { + 0x03C0, 0x03B5, 0x03C1, 0x03B9, 0x03C3, 0x03C3, 0x03CC, 0x03C4, + 0x03B5, 0x03C1, 0x03B5, 0x03C2, 0x0020, 0x03C0, 0x03BB, 0x03B7, + 0x03C1, 0x03BF, 0x03C6, 0x03BF, 0x03C1, 0x03AF, 0x03B5, 0x03C2 + }; + static const uint32_t casefolded[] = + { + 0x03C0, 0x03B5, 0x03C1, 0x03B9, 0x03C3, 0x03C3, 0x03CC, 0x03C4, + 0x03B5, 0x03C1, 0x03B5, 0x03C3, 0x0020, 0x03C0, 0x03BB, 0x03B7, + 0x03C1, 0x03BF, 0x03C6, 0x03BF, 0x03C1, 0x03AF, 0x03B5, 0x03C3 + }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + } + + /* Case mapping can require subsequent normalization. */ + { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */ + static const uint32_t input[] = { 0x01F0, 0x0323 }; + static const uint32_t casefolded[] = { 0x006A, 0x030C, 0x0323 }; + static const uint32_t casefolded_decomposed[] = { 0x006A, 0x0323, 0x030C }; + static const uint32_t casefolded_normalized[] = { 0x01F0, 0x0323 }; + ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0); + ASSERT (check (input, SIZEOF (input), NULL, UNINORM_NFD, casefolded_decomposed, SIZEOF (casefolded_decomposed)) == 0); + ASSERT (check (input, SIZEOF (input), NULL, UNINORM_NFC, casefolded_normalized, SIZEOF (casefolded_normalized)) == 0); + } + + return 0; +}