summaryrefslogtreecommitdiff
path: root/tests/unicase/test-u8-totitle.c
diff options
context:
space:
mode:
Diffstat (limited to 'tests/unicase/test-u8-totitle.c')
-rw-r--r--tests/unicase/test-u8-totitle.c217
1 files changed, 217 insertions, 0 deletions
diff --git a/tests/unicase/test-u8-totitle.c b/tests/unicase/test-u8-totitle.c
new file mode 100644
index 00000000..c2506ac5
--- /dev/null
+++ b/tests/unicase/test-u8-totitle.c
@@ -0,0 +1,217 @@
+/* Test of titlecase mapping for UTF-8 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 uint8_t *input, size_t input_length,
+ const char *iso639_language, uninorm_t nf,
+ const uint8_t *expected, size_t expected_length)
+{
+ size_t length;
+ uint8_t *result;
+
+ /* Test return conventions with resultbuf == NULL. */
+ result = u8_totitle (input, input_length, iso639_language, nf, NULL, &length);
+ if (!(result != NULL))
+ return 1;
+ if (!(length == expected_length))
+ return 2;
+ if (!(u8_cmp (result, expected, expected_length) == 0))
+ return 3;
+ free (result);
+
+ /* Test return conventions with resultbuf too small. */
+ if (expected_length > 0)
+ {
+ uint8_t *preallocated;
+
+ length = expected_length - 1;
+ preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
+ result = u8_totitle (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 (!(u8_cmp (result, expected, expected_length) == 0))
+ return 7;
+ free (result);
+ free (preallocated);
+ }
+
+ /* Test return conventions with resultbuf large enough. */
+ {
+ uint8_t *preallocated;
+
+ length = expected_length;
+ preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
+ result = u8_totitle (input, input_length, iso639_language, nf, preallocated, &length);
+ if (!(result != NULL))
+ return 8;
+ if (!(preallocated == NULL || result == preallocated))
+ return 9;
+ if (!(length == expected_length))
+ return 10;
+ if (!(u8_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 uint8_t input[] =
+ { 'G', 'R', 0xC3, 0x9C, 0xC3, 0x9F, ' ', 'G', 'O', 'T', 'T', '.', ' ',
+ 0xD0, 0x97, 0xD0, 0x94, 0xD0, 0xA0, 0xD0, 0x90, 0xD0, 0x92, 0xD0, 0xA1,
+ 0xD0, 0xA2, 0xD0, 0x92, 0xD0, 0xA3, 0xD0, 0x99, 0xD0, 0xA2, 0xD0, 0x95,
+ '!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'Q', 'R', 'T', '(',
+ 'B', 0xC2, 0xB2, '-', '4', 'A', 'C', ')', ')', '/', '(', '2', 'A', ')',
+ ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
+ 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
+ 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
+ };
+ static const uint8_t casemapped[] =
+ { 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
+ 0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
+ 0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
+ '!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'q', 'r', 't', '(',
+ 'B', 0xC2, 0xB2, '-', '4', 'A', 'c', ')', ')', '/', '(', '2', 'A', ')',
+ ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
+ 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
+ 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
+ };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+
+ /* Case mapping can increase the number of Unicode characters. */
+ { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
+ static const uint8_t input[] = { 0xC5, 0x89 };
+ static const uint8_t casemapped[] = { 0xCA, 0xBC, 0x4E };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+ { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
+ static const uint8_t input[] = { 0xCE, 0x90 };
+ static const uint8_t casemapped[] = { 0xCE, 0x99, 0xCC, 0x88, 0xCC, 0x81 };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+
+ /* Turkish letters i İ ı I */
+ { /* LATIN CAPITAL LETTER I */
+ static const uint8_t input[] = { 0x49 };
+ static const uint8_t casemapped[] = { 0x49 };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+ { /* LATIN SMALL LETTER I */
+ static const uint8_t input[] = { 0x69 };
+ static const uint8_t casemapped[] = { 0x49 };
+ static const uint8_t casemapped_tr[] = { 0xC4, 0xB0 };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped_tr, SIZEOF (casemapped_tr)) == 0);
+ }
+ { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
+ static const uint8_t input[] = { 0xC4, 0xB0 };
+ static const uint8_t casemapped[] = { 0xC4, 0xB0 };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+ { /* LATIN SMALL LETTER DOTLESS I */
+ static const uint8_t input[] = { 0xC4, 0xB1 };
+ static const uint8_t casemapped[] = { 0x49 };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+ { /* "topkapı" */
+ static const uint8_t input[] =
+ { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
+ static const uint8_t casemapped[] =
+ { 0x54, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+
+ /* Uppercasing can increase the number of Unicode characters. */
+ { /* "heiß" */
+ static const uint8_t input[] = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
+ static const uint8_t casemapped[] = { 0x48, 0x65, 0x69, 0xC3, 0x9F };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+
+ /* Case mappings for some characters can depend on the surrounding characters. */
+ { /* "περισσότερες πληροφορίες" */
+ static const uint8_t input[] =
+ {
+ 0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
+ 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
+ ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
+ 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
+ };
+ static const uint8_t casemapped[] =
+ {
+ 0xCE, 0xA0, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
+ 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
+ ' ', 0xCE, 0xA0, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
+ 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
+ };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ }
+
+ /* Case mapping can require subsequent normalization. */
+ { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
+ static const uint8_t input[] = { 0xC7, 0xB0, 0xCC, 0xA3 };
+ static const uint8_t casemapped[] = { 0x4A, 0xCC, 0x8C, 0xCC, 0xA3 };
+ static const uint8_t casemapped_normalized[] = { 0x4A, 0xCC, 0xA3, 0xCC, 0x8C };
+ ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
+ ASSERT (check (input, SIZEOF (input), NULL, UNINORM_NFC, casemapped_normalized, SIZEOF (casemapped_normalized)) == 0);
+ }
+
+ return 0;
+}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-11 03:15:22 +0000