# HG changeset patch # User Bruno Haible # Date 1192357767 -7200 # Node ID 014260dbb02a0f0eb679ca0a704d9bf45c229d30 # Parent 212d6f041290858f7a8071396944df2f6f43c285 Test for module 'iconv_open-utf'. diff --git a/ChangeLog b/ChangeLog --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,8 @@ 2007-10-14 Bruno Haible + * modules/iconv_open-utf-tests: New file. + * tests/test-iconv-utf.c: New file. + Enhance iconv_open to support UTF-16BE, UTF-16LE, UTF-32BE, UTF-32LE. * modules/iconv_open-utf: New file. * lib/iconv.in.h (_ICONV_UTF8_UTF*, _ICONV_UTF*_UTF8): New macros. diff --git a/modules/iconv_open-utf-tests b/modules/iconv_open-utf-tests new file mode 100644 --- /dev/null +++ b/modules/iconv_open-utf-tests @@ -0,0 +1,12 @@ +Files: +tests/test-iconv-utf.c + +Depends-on: + +configure.ac: + +Makefile.am: +TESTS += test-iconv-utf +check_PROGRAMS += test-iconv-utf +test_iconv_utf_LDADD = $(LDADD) @LIBICONV@ + diff --git a/tests/test-iconv-utf.c b/tests/test-iconv-utf.c new file mode 100644 --- /dev/null +++ b/tests/test-iconv-utf.c @@ -0,0 +1,299 @@ +/* Test of character set conversion. + 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 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 . */ + +/* Written by Bruno Haible , 2007. */ + +#include + +#if HAVE_ICONV +# include +#endif + +#include +#include +#include +#include + +#define ASSERT(expr) \ + do \ + { \ + if (!(expr)) \ + { \ + fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \ + abort (); \ + } \ + } \ + while (0) + +int +main () +{ +#if HAVE_ICONV + /* Assume that iconv() supports at least the encoding UTF-8. */ + + /* The text is "Japanese (日本語) [\U0001D50D\U0001D51E\U0001D52D]". */ + + /* Test conversion from UTF-8 to UTF-16BE with no errors. */ + { + static const char input[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + static const char expected[] = + "\000J\000a\000p\000a\000n\000e\000s\000e\000 \000(\145\345\147\054\212\236\000)\000 \000[\330\065\335\015\330\065\335\036\330\065\335\055\000]"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-16BE", "UTF-8"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-8 to UTF-16LE with no errors. */ + { + static const char input[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + static const char expected[] = + "J\000a\000p\000a\000n\000e\000s\000e\000 \000(\000\345\145\054\147\236\212)\000 \000[\000\065\330\015\335\065\330\036\335\065\330\055\335]\000"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-16LE", "UTF-8"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-8 to UTF-32BE with no errors. */ + { + static const char input[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + static const char expected[] = + "\000\000\000J\000\000\000a\000\000\000p\000\000\000a\000\000\000n\000\000\000e\000\000\000s\000\000\000e\000\000\000 \000\000\000(\000\000\145\345\000\000\147\054\000\000\212\236\000\000\000)\000\000\000 \000\000\000[\000\001\325\015\000\001\325\036\000\001\325\055\000\000\000]"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-32BE", "UTF-8"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-8 to UTF-32LE with no errors. */ + { + static const char input[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + static const char expected[] = + "J\000\000\000a\000\000\000p\000\000\000a\000\000\000n\000\000\000e\000\000\000s\000\000\000e\000\000\000 \000\000\000(\000\000\000\345\145\000\000\054\147\000\000\236\212\000\000)\000\000\000 \000\000\000[\000\000\000\015\325\001\000\036\325\001\000\055\325\001\000]\000\000\000"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-32LE", "UTF-8"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-16BE to UTF-8 with no errors. */ + { + static const char input[] = + "\000J\000a\000p\000a\000n\000e\000s\000e\000 \000(\145\345\147\054\212\236\000)\000 \000[\330\065\335\015\330\065\335\036\330\065\335\055\000]"; + static const char expected[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-8", "UTF-16BE"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-16LE to UTF-8 with no errors. */ + { + static const char input[] = + "J\000a\000p\000a\000n\000e\000s\000e\000 \000(\000\345\145\054\147\236\212)\000 \000[\000\065\330\015\335\065\330\036\335\065\330\055\335]\000"; + static const char expected[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-8", "UTF-16LE"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-32BE to UTF-8 with no errors. */ + { + static const char input[] = + "\000\000\000J\000\000\000a\000\000\000p\000\000\000a\000\000\000n\000\000\000e\000\000\000s\000\000\000e\000\000\000 \000\000\000(\000\000\145\345\000\000\147\054\000\000\212\236\000\000\000)\000\000\000 \000\000\000[\000\001\325\015\000\001\325\036\000\001\325\055\000\000\000]"; + static const char expected[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-8", "UTF-32BE"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } + + /* Test conversion from UTF-32LE to UTF-8 with no errors. */ + { + static const char input[] = + "J\000\000\000a\000\000\000p\000\000\000a\000\000\000n\000\000\000e\000\000\000s\000\000\000e\000\000\000 \000\000\000(\000\000\000\345\145\000\000\054\147\000\000\236\212\000\000)\000\000\000 \000\000\000[\000\000\000\015\325\001\000\036\325\001\000\055\325\001\000]\000\000\000"; + static const char expected[] = + "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; + iconv_t cd; + char buf[100]; + const char *inptr; + size_t inbytesleft; + char *outptr; + size_t outbytesleft; + size_t res; + + cd = iconv_open ("UTF-8", "UTF-32LE"); + ASSERT (cd != (iconv_t)(-1)); + + inptr = input; + inbytesleft = sizeof (input) - 1; + outptr = buf; + outbytesleft = sizeof (buf); + res = iconv (cd, + (ICONV_CONST char **) &inptr, &inbytesleft, + &outptr, &outbytesleft); + ASSERT (res == 0 && inbytesleft == 0); + ASSERT (outptr == buf + (sizeof (expected) - 1)); + ASSERT (memcmp (buf, expected, sizeof (expected) - 1) == 0); + + ASSERT (iconv_close (cd) == 0); + } +#endif + + return 0; +}