diff options
Diffstat (limited to 'tests/uniconv')
| -rw-r--r-- | tests/uniconv/test-u16-conv-from-enc.c | 232 | ||||
| -rw-r--r-- | tests/uniconv/test-u16-conv-to-enc.c | 188 | ||||
| -rw-r--r-- | tests/uniconv/test-u16-strconv-from-enc.c | 132 | ||||
| -rw-r--r-- | tests/uniconv/test-u16-strconv-to-enc.c | 121 | ||||
| -rw-r--r-- | tests/uniconv/test-u32-conv-from-enc.c | 232 | ||||
| -rw-r--r-- | tests/uniconv/test-u32-conv-to-enc.c | 163 | ||||
| -rw-r--r-- | tests/uniconv/test-u32-strconv-from-enc.c | 132 | ||||
| -rw-r--r-- | tests/uniconv/test-u32-strconv-to-enc.c | 108 | ||||
| -rw-r--r-- | tests/uniconv/test-u8-conv-from-enc.c | 218 | ||||
| -rw-r--r-- | tests/uniconv/test-u8-conv-to-enc.c | 193 | ||||
| -rw-r--r-- | tests/uniconv/test-u8-strconv-from-enc.c | 114 | ||||
| -rw-r--r-- | tests/uniconv/test-u8-strconv-to-enc.c | 112 |
12 files changed, 1945 insertions, 0 deletions
diff --git a/tests/uniconv/test-u16-conv-from-enc.c b/tests/uniconv/test-u16-conv-from-enc.c new file mode 100644 index 0000000..ac7617b --- /dev/null +++ b/tests/uniconv/test-u16-conv-from-enc.c @@ -0,0 +1,232 @@ +/* Test of conversion to UTF-16 from legacy encodings. + Copyright (C) 2007-2009 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "unistr.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) + +/* Magic number for detecting bounds violations. */ +#define MAGIC 0x1983EFF1 + +static size_t * +new_offsets (size_t n) +{ + size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t)); + offsets[n] = MAGIC; + return offsets; +} + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + size_t o; + size_t i; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static const uint16_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint16_t *result = u16_conv_from_encoding ("ISO-8859-1", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u16_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 37; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[37] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */ + static const uint16_t expected[] = + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i' + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint16_t *result = u16_conv_from_encoding ("ISO-8859-2", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u16_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */ +# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__) + /* Test conversions from autodetect_jp to UTF-16. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */ + static const uint16_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint16_t *result = u16_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u16_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 10; i++) + ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1))); + ASSERT (offsets[10] == MAGIC); + free (offsets); + } + free (result); + } + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */ + static const uint16_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint16_t *result = u16_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u16_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 10; i++) + ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1))); + ASSERT (offsets[10] == MAGIC); + free (offsets); + } + free (result); + } + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */ + static const uint16_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint16_t *result = u16_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u16_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == (i == 0 ? 0 : + i == 5 ? 1 : + i == 7 ? 2 : + i == 9 ? 3 : + i == 11 ? 4 : + i == 13 ? 5 : + (size_t)(-1))); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u16-conv-to-enc.c b/tests/uniconv/test-u16-conv-to-enc.c new file mode 100644 index 0000000..a2dc3c6 --- /dev/null +++ b/tests/uniconv/test-u16-conv-to-enc.c @@ -0,0 +1,188 @@ +/* Test of conversion from UTF-16 to legacy encodings. + Copyright (C) 2007-2009 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.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) + +/* Magic number for detecting bounds violations. */ +#define MAGIC 0x1983EFF1 + +static size_t * +new_offsets (size_t n) +{ + size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t)); + offsets[n] = MAGIC; + return offsets; +} + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + size_t o; + size_t i; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from UTF-16 to ISO-8859-1 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint16_t input[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF + }; + static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (SIZEOF (input)) : NULL); + size_t length; + char *result = u16_conv_to_encoding ("ISO-8859-1", handler, + input, SIZEOF (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0); + if (o) + { + for (i = 0; i < 37; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[37] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* Test conversion from UTF-16 to ISO-8859-1 with EILSEQ. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint16_t input[] = /* Rafał Maszkowski */ + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i' + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (SIZEOF (input)) : NULL); + size_t length = 0xdead; + char *result = u16_conv_to_encoding ("ISO-8859-1", handler, + input, SIZEOF (input), + offsets, + NULL, &length); + switch (handler) + { + case iconveh_error: + ASSERT (result == NULL); + ASSERT (errno == EILSEQ); + ASSERT (length == 0xdead); + break; + case iconveh_question_mark: + { + static const char expected[] = "Rafa? Maszkowski"; + static const char expected_translit[] = "Rafal Maszkowski"; + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0 + || memcmp (result, expected_translit, length) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + break; + case iconveh_escape_sequence: + { + static const char expected[] = "Rafa\\u0142 Maszkowski"; + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == (i < 5 ? i : i + 5)); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + break; + } + } + } + + /* Test conversion from UTF-16 to ISO-8859-1 with EINVAL. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint16_t input[] = { 0xD845 }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (SIZEOF (input)) : NULL); + size_t length; + char *result = u16_conv_to_encoding ("ISO-8859-1", handler, + input, SIZEOF (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == strlen ("")); + if (o) + { + ASSERT (offsets[0] == 0); + ASSERT (offsets[1] == MAGIC); + free (offsets); + } + free (result); + } + } + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u16-strconv-from-enc.c b/tests/uniconv/test-u16-strconv-from-enc.c new file mode 100644 index 0000000..f2f173a --- /dev/null +++ b/tests/uniconv/test-u16-strconv-from-enc.c @@ -0,0 +1,132 @@ +/* Test of conversion to UTF-16 from legacy encodings. + Copyright (C) 2007-2008 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <stdio.h> +#include <stdlib.h> + +#include "unistr.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) + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static const uint16_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0 + }; + uint16_t *result = u16_strconv_from_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (u16_strcmp (result, expected) == 0); + free (result); + } + + /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */ + static const uint16_t expected[] = + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i', 0 + }; + uint16_t *result = u16_strconv_from_encoding (input, "ISO-8859-2", handler); + ASSERT (result != NULL); + ASSERT (u16_strcmp (result, expected) == 0); + free (result); + } + + /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */ +# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__) + /* Test conversions from autodetect_jp to UTF-16. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */ + static const uint16_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0 + }; + uint16_t *result = u16_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u16_strcmp (result, expected) == 0); + free (result); + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */ + static const uint16_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0 + }; + uint16_t *result = u16_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u16_strcmp (result, expected) == 0); + free (result); + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */ + static const uint16_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0 + }; + uint16_t *result = u16_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u16_strcmp (result, expected) == 0); + free (result); + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u16-strconv-to-enc.c b/tests/uniconv/test-u16-strconv-to-enc.c new file mode 100644 index 0000000..95a7206 --- /dev/null +++ b/tests/uniconv/test-u16-strconv-to-enc.c @@ -0,0 +1,121 @@ +/* Test of conversion from UTF-16 to legacy encodings. + Copyright (C) 2007-2008 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.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) + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from UTF-16 to ISO-8859-1 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint16_t input[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0 + }; + static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + char *result = u16_strconv_to_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0); + free (result); + } + + /* Test conversion from UTF-16 to ISO-8859-1 with EILSEQ. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint16_t input[] = /* Rafał Maszkowski */ + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i', 0 + }; + char *result = u16_strconv_to_encoding (input, "ISO-8859-1", handler); + switch (handler) + { + case iconveh_error: + ASSERT (result == NULL && errno == EILSEQ); + break; + case iconveh_question_mark: + { + static const char expected[] = "Rafa? Maszkowski"; + static const char expected_translit[] = "Rafal Maszkowski"; + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0 + || strcmp (result, expected_translit) == 0); + free (result); + } + break; + case iconveh_escape_sequence: + { + static const char expected[] = "Rafa\\u0142 Maszkowski"; + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0); + free (result); + } + break; + } + } + +# if 0 + /* Test conversion from UTF-16 to ISO-8859-1 with EINVAL. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint16_t input[] = { 0xD845, 0 }; + char *result = u16_strconv_to_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (strcmp (result, "") == 0); + free (result); + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u32-conv-from-enc.c b/tests/uniconv/test-u32-conv-from-enc.c new file mode 100644 index 0000000..8f709f1 --- /dev/null +++ b/tests/uniconv/test-u32-conv-from-enc.c @@ -0,0 +1,232 @@ +/* Test of conversion to UTF-32 from legacy encodings. + Copyright (C) 2007-2009 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "unistr.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) + +/* Magic number for detecting bounds violations. */ +#define MAGIC 0x1983EFF1 + +static size_t * +new_offsets (size_t n) +{ + size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t)); + offsets[n] = MAGIC; + return offsets; +} + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + size_t o; + size_t i; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint32_t *result = u32_conv_from_encoding ("ISO-8859-1", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 37; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[37] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */ + static const uint32_t expected[] = + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i' + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint32_t *result = u32_conv_from_encoding ("ISO-8859-2", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */ +# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__) + /* Test conversions from autodetect_jp to UTF-16. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */ + static const uint32_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 10; i++) + ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1))); + ASSERT (offsets[10] == MAGIC); + free (offsets); + } + free (result); + } + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */ + static const uint32_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 10; i++) + ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1))); + ASSERT (offsets[10] == MAGIC); + free (offsets); + } + free (result); + } + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */ + static const uint32_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint32_t *result = u32_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == SIZEOF (expected)); + ASSERT (u32_cmp (result, expected, SIZEOF (expected)) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == (i == 0 ? 0 : + i == 5 ? 1 : + i == 7 ? 2 : + i == 9 ? 3 : + i == 11 ? 4 : + i == 13 ? 5 : + (size_t)(-1))); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u32-conv-to-enc.c b/tests/uniconv/test-u32-conv-to-enc.c new file mode 100644 index 0000000..585b737 --- /dev/null +++ b/tests/uniconv/test-u32-conv-to-enc.c @@ -0,0 +1,163 @@ +/* Test of conversion from UTF-32 to legacy encodings. + Copyright (C) 2007-2009 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.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) + +/* Magic number for detecting bounds violations. */ +#define MAGIC 0x1983EFF1 + +static size_t * +new_offsets (size_t n) +{ + size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t)); + offsets[n] = MAGIC; + return offsets; +} + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + size_t o; + size_t i; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from UTF-32 to ISO-8859-1 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint32_t input[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF + }; + static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (SIZEOF (input)) : NULL); + size_t length; + char *result = u32_conv_to_encoding ("ISO-8859-1", handler, + input, SIZEOF (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0); + if (o) + { + for (i = 0; i < 37; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[37] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* Test conversion from UTF-32 to ISO-8859-1 with EILSEQ. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint32_t input[] = /* Rafał Maszkowski */ + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i' + }; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (SIZEOF (input)) : NULL); + size_t length = 0xdead; + char *result = u32_conv_to_encoding ("ISO-8859-1", handler, + input, SIZEOF (input), + offsets, + NULL, &length); + switch (handler) + { + case iconveh_error: + ASSERT (result == NULL); + ASSERT (errno == EILSEQ); + ASSERT (length == 0xdead); + break; + case iconveh_question_mark: + { + static const char expected[] = "Rafa? Maszkowski"; + static const char expected_translit[] = "Rafal Maszkowski"; + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0 + || memcmp (result, expected_translit, length) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == i); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + break; + case iconveh_escape_sequence: + { + static const char expected[] = "Rafa\\u0142 Maszkowski"; + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == (i < 5 ? i : i + 5)); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + break; + } + } + } + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u32-strconv-from-enc.c b/tests/uniconv/test-u32-strconv-from-enc.c new file mode 100644 index 0000000..96af738 --- /dev/null +++ b/tests/uniconv/test-u32-strconv-from-enc.c @@ -0,0 +1,132 @@ +/* Test of conversion to UTF-32 from legacy encodings. + Copyright (C) 2007-2008 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <stdio.h> +#include <stdlib.h> + +#include "unistr.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) + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0 + }; + uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (u32_strcmp (result, expected) == 0); + free (result); + } + + /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */ + static const uint32_t expected[] = + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i', 0 + }; + uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-2", handler); + ASSERT (result != NULL); + ASSERT (u32_strcmp (result, expected) == 0); + free (result); + } + + /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */ +# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__) + /* Test conversions from autodetect_jp to UTF-16. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */ + static const uint32_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0 + }; + uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u32_strcmp (result, expected) == 0); + free (result); + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */ + static const uint32_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0 + }; + uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u32_strcmp (result, expected) == 0); + free (result); + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */ + static const uint32_t expected[] = /* こんにちは */ + { + 0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0 + }; + uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u32_strcmp (result, expected) == 0); + free (result); + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u32-strconv-to-enc.c b/tests/uniconv/test-u32-strconv-to-enc.c new file mode 100644 index 0000000..eef3d04 --- /dev/null +++ b/tests/uniconv/test-u32-strconv-to-enc.c @@ -0,0 +1,108 @@ +/* Test of conversion from UTF-32 to legacy encodings. + Copyright (C) 2007-2008 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.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) + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from UTF-32 to ISO-8859-1 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint32_t input[] = /* Ärger mit bösen Bübchen ohne Augenmaß */ + { + 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's', + 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h', + 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0 + }; + static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + char *result = u32_strconv_to_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0); + free (result); + } + + /* Test conversion from UTF-32 to ISO-8859-1 with EILSEQ. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint32_t input[] = /* Rafał Maszkowski */ + { + 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w', + 's', 'k', 'i', 0 + }; + char *result = u32_strconv_to_encoding (input, "ISO-8859-1", handler); + switch (handler) + { + case iconveh_error: + ASSERT (result == NULL && errno == EILSEQ); + break; + case iconveh_question_mark: + { + static const char expected[] = "Rafa? Maszkowski"; + static const char expected_translit[] = "Rafal Maszkowski"; + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0 + || strcmp (result, expected_translit) == 0); + free (result); + } + break; + case iconveh_escape_sequence: + { + static const char expected[] = "Rafa\\u0142 Maszkowski"; + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0); + free (result); + } + break; + } + } + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u8-conv-from-enc.c b/tests/uniconv/test-u8-conv-from-enc.c new file mode 100644 index 0000000..0768be6 --- /dev/null +++ b/tests/uniconv/test-u8-conv-from-enc.c @@ -0,0 +1,218 @@ +/* Test of conversion to UTF-8 from legacy encodings. + Copyright (C) 2007-2009 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "unistr.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) + +/* Magic number for detecting bounds violations. */ +#define MAGIC 0x1983EFF1 + +static size_t * +new_offsets (size_t n) +{ + size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t)); + offsets[n] = MAGIC; + return offsets; +} + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + size_t o; + size_t i; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static const uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint8_t *result = u8_conv_from_encoding ("ISO-8859-1", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == u8_strlen (expected)); + ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0); + if (o) + { + for (i = 0; i < 37; i++) + ASSERT (offsets[i] == (i < 1 ? i : + i < 12 ? i + 1 : + i < 18 ? i + 2 : + i + 3)); + ASSERT (offsets[37] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */ + static const uint8_t expected[] = "Rafa\305\202 Maszkowski"; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint8_t *result = u8_conv_from_encoding ("ISO-8859-2", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == u8_strlen (expected)); + ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == (i < 5 ? i : + i + 1)); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */ +# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__) + /* Test conversions from autodetect_jp to UTF-8. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */ + static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */ + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == u8_strlen (expected)); + ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0); + if (o) + { + for (i = 0; i < 10; i++) + ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1))); + ASSERT (offsets[10] == MAGIC); + free (offsets); + } + free (result); + } + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */ + static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */ + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == u8_strlen (expected)); + ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0); + if (o) + { + for (i = 0; i < 10; i++) + ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1))); + ASSERT (offsets[10] == MAGIC); + free (offsets); + } + free (result); + } + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */ + static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */ + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (strlen (input)) : NULL); + size_t length; + uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == u8_strlen (expected)); + ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0); + if (o) + { + for (i = 0; i < 16; i++) + ASSERT (offsets[i] == (i == 0 ? 0 : + i == 5 ? 3 : + i == 7 ? 6 : + i == 9 ? 9 : + i == 11 ? 12 : + i == 13 ? 15 : + (size_t)(-1))); + ASSERT (offsets[16] == MAGIC); + free (offsets); + } + free (result); + } + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u8-conv-to-enc.c b/tests/uniconv/test-u8-conv-to-enc.c new file mode 100644 index 0000000..271fb05 --- /dev/null +++ b/tests/uniconv/test-u8-conv-to-enc.c @@ -0,0 +1,193 @@ +/* Test of conversion from UTF-8 to legacy encodings. + Copyright (C) 2007-2009 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "unistr.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) + +/* Magic number for detecting bounds violations. */ +#define MAGIC 0x1983EFF1 + +static size_t * +new_offsets (size_t n) +{ + size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t)); + offsets[n] = MAGIC; + return offsets; +} + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + size_t o; + size_t i; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint8_t input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; + static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL); + size_t length; + char *result = u8_conv_to_encoding ("ISO-8859-1", handler, + input, u8_strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0); + if (o) + { + for (i = 0; i < 41; i++) + ASSERT (offsets[i] == (i < 1 ? i : + i == 1 ? (size_t)(-1) : + i < 13 ? i - 1 : + i == 13 ? (size_t)(-1) : + i < 20 ? i - 2 : + i == 20 ? (size_t)(-1) : + i < 40 ? i - 3 : + i == 40 ? (size_t)(-1) : + i - 4)); + ASSERT (offsets[41] == MAGIC); + free (offsets); + } + free (result); + } + } + + /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint8_t input[] = "Rafa\305\202 Maszkowski"; /* Rafał Maszkowski */ + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL); + size_t length = 0xdead; + char *result = u8_conv_to_encoding ("ISO-8859-1", handler, + input, u8_strlen (input), + offsets, + NULL, &length); + switch (handler) + { + case iconveh_error: + ASSERT (result == NULL); + ASSERT (errno == EILSEQ); + ASSERT (length == 0xdead); + break; + case iconveh_question_mark: + { + static const char expected[] = "Rafa? Maszkowski"; + static const char expected_translit[] = "Rafal Maszkowski"; + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0 + || memcmp (result, expected_translit, length) == 0); + if (o) + { + for (i = 0; i < 17; i++) + ASSERT (offsets[i] == (i < 5 ? i : + i == 5 ? (size_t)(-1) : + i - 1)); + ASSERT (offsets[17] == MAGIC); + free (offsets); + } + free (result); + } + break; + case iconveh_escape_sequence: + { + static const char expected[] = "Rafa\\u0142 Maszkowski"; + ASSERT (result != NULL); + ASSERT (length == strlen (expected)); + ASSERT (memcmp (result, expected, length) == 0); + if (o) + { + for (i = 0; i < 17; i++) + ASSERT (offsets[i] == (i < 5 ? i : + i == 5 ? (size_t)(-1) : + i + 4)); + ASSERT (offsets[17] == MAGIC); + free (offsets); + } + free (result); + } + break; + } + } + } + + /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint8_t input[] = "\342"; + for (o = 0; o < 2; o++) + { + size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL); + size_t length; + char *result = u8_conv_to_encoding ("ISO-8859-1", handler, + input, u8_strlen (input), + offsets, + NULL, &length); + ASSERT (result != NULL); + ASSERT (length == strlen ("")); + if (o) + { + ASSERT (offsets[0] == 0); + ASSERT (offsets[1] == MAGIC); + free (offsets); + } + free (result); + } + } + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u8-strconv-from-enc.c b/tests/uniconv/test-u8-strconv-from-enc.c new file mode 100644 index 0000000..7f70c29 --- /dev/null +++ b/tests/uniconv/test-u8-strconv-from-enc.c @@ -0,0 +1,114 @@ +/* Test of conversion to UTF-8 from legacy encodings. + Copyright (C) 2007-2008 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <stdio.h> +#include <stdlib.h> + +#include "unistr.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) + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static const uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; + uint8_t *result = u8_strconv_from_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (u8_strcmp (result, expected) == 0); + free (result); + } + + /* Test conversion from ISO-8859-2 to UTF-8 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */ + static const uint8_t expected[] = "Rafa\305\202 Maszkowski"; + uint8_t *result = u8_strconv_from_encoding (input, "ISO-8859-2", handler); + ASSERT (result != NULL); + ASSERT (u8_strcmp (result, expected) == 0); + free (result); + } + + /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */ +# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__) + /* Test conversions from autodetect_jp to UTF-8. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */ + static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */ + uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u8_strcmp (result, expected) == 0); + free (result); + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */ + static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */ + uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u8_strcmp (result, expected) == 0); + free (result); + } + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */ + static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* こんにちは */ + uint8_t *result = u8_strconv_from_encoding (input, "autodetect_jp", handler); + ASSERT (result != NULL); + ASSERT (u8_strcmp (result, expected) == 0); + free (result); + } +# endif + +#endif + + return 0; +} diff --git a/tests/uniconv/test-u8-strconv-to-enc.c b/tests/uniconv/test-u8-strconv-to-enc.c new file mode 100644 index 0000000..73085b5 --- /dev/null +++ b/tests/uniconv/test-u8-strconv-to-enc.c @@ -0,0 +1,112 @@ +/* Test of conversion from UTF-8 to legacy encodings. + Copyright (C) 2007-2008 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>, 2007. */ + +#include <config.h> + +#include "uniconv.h" + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.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) + +int +main () +{ + static enum iconv_ilseq_handler handlers[] = + { iconveh_error, iconveh_question_mark, iconveh_escape_sequence }; + size_t h; + +#if HAVE_ICONV + /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, + ISO-8859-2, and UTF-8. */ + + /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint8_t input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; + static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + char *result = u8_strconv_to_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0); + free (result); + } + + /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint8_t input[] = "Rafa\305\202 Maszkowski"; /* Rafał Maszkowski */ + char *result = u8_strconv_to_encoding (input, "ISO-8859-1", handler); + switch (handler) + { + case iconveh_error: + ASSERT (result == NULL && errno == EILSEQ); + break; + case iconveh_question_mark: + { + static const char expected[] = "Rafa? Maszkowski"; + static const char expected_translit[] = "Rafal Maszkowski"; + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0 + || strcmp (result, expected_translit) == 0); + free (result); + } + break; + case iconveh_escape_sequence: + { + static const char expected[] = "Rafa\\u0142 Maszkowski"; + ASSERT (result != NULL); + ASSERT (strcmp (result, expected) == 0); + free (result); + } + break; + } + } + +# if 0 + /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */ + for (h = 0; h < SIZEOF (handlers); h++) + { + enum iconv_ilseq_handler handler = handlers[h]; + static const uint8_t input[] = "\342"; + char *result = u8_strconv_to_encoding (input, "ISO-8859-1", handler); + ASSERT (result != NULL); + ASSERT (strcmp (result, "") == 0); + free (result); + } +# endif + +#endif + + return 0; +} |