From c6ea812a629073f9815aa1057351bcd88321a4e8 Mon Sep 17 00:00:00 2001 From: Bruno Haible Date: Sat, 27 Jan 2007 00:40:10 +0000 Subject: [PATCH] Tests for module 'uniconv/u8-conv-from-enc'. --- modules/uniconv/u8-conv-from-enc-tests | 15 ++ tests/uniconv/test-u8-conv-from-enc.c | 212 +++++++++++++++++++++++++ 2 files changed, 227 insertions(+) create mode 100644 modules/uniconv/u8-conv-from-enc-tests create mode 100644 tests/uniconv/test-u8-conv-from-enc.c diff --git a/modules/uniconv/u8-conv-from-enc-tests b/modules/uniconv/u8-conv-from-enc-tests new file mode 100644 index 0000000000..cc243626af --- /dev/null +++ b/modules/uniconv/u8-conv-from-enc-tests @@ -0,0 +1,15 @@ +Files: +tests/uniconv/test-u8-conv-from-enc.c + +Depends-on: +unistr/u8-strlen +unistr/u8-cmp + +configure.ac: + +Makefile.am: +TESTS += test-u8-conv-from-enc +check_PROGRAMS += test-u8-conv-from-enc +test_u8_conv_from_enc_SOURCES = uniconv/test-u8-conv-from-enc.c +test_u8_conv_from_enc_LDADD = @LIBICONV@ $(LDADD) + 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 0000000000..69e44d54a6 --- /dev/null +++ b/tests/uniconv/test-u8-conv-from-enc.c @@ -0,0 +1,212 @@ +/* Test of conversion to UTF-8 from legacy encodings. + Copyright (C) 2007 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 2, 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, write to the Free Software Foundation, + Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + +/* Written by Bruno Haible , 2007. */ + +#ifdef HAVE_CONFIG_H +# include +#endif + +#include "uniconv.h" + +#include +#include + +#include "unistr.h" + +#define SIZEOF(array) (sizeof (array) / sizeof (array[0])) +#define ASSERT(expr) if (!(expr)) abort (); + +/* 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); + uint8_t *result = NULL; + size_t length = 0; + int retval = u8_conv_from_encoding ("ISO-8859-1", handler, + input, strlen (input), + offsets, + &result, &length); + ASSERT (retval == 0); + ASSERT (length == u8_strlen (expected)); + ASSERT (result != NULL && 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); + uint8_t *result = NULL; + size_t length = 0; + int retval = u8_conv_from_encoding ("ISO-8859-2", handler, + input, strlen (input), + offsets, + &result, &length); + ASSERT (retval == 0); + ASSERT (length == u8_strlen (expected)); + ASSERT (result != NULL && 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); + } + } + + /* 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); + uint8_t *result = NULL; + size_t length = 0; + int retval = u8_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + &result, &length); + ASSERT (retval == 0); + ASSERT (length == u8_strlen (expected)); + ASSERT (result != NULL && 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); + uint8_t *result = NULL; + size_t length = 0; + int retval = u8_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + &result, &length); + ASSERT (retval == 0); + ASSERT (length == u8_strlen (expected)); + ASSERT (result != NULL && 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); + uint8_t *result = NULL; + size_t length = 0; + int retval = u8_conv_from_encoding ("autodetect_jp", handler, + input, strlen (input), + offsets, + &result, &length); + ASSERT (retval == 0); + ASSERT (length == u8_strlen (expected)); + ASSERT (result != NULL && 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 + + return 0; +} -- 2.30.2