diff options
author | Manuel A. Fernandez Montecelo <manuel.montezelo@gmail.com> | 2016-05-27 14:28:30 +0100 |
---|---|---|
committer | Manuel A. Fernandez Montecelo <manuel.montezelo@gmail.com> | 2016-05-27 14:28:30 +0100 |
commit | a9a31b1de5776a3b08a82101a4fa711294f0dd1d (patch) | |
tree | 159134a624e51509f40ed8823249f09a70d1dda3 /tests/unistr/test-u8-mbtouc.c | |
parent | 5f2b09982312c98863eb9a8dfe2c608b81f58259 (diff) |
Imported Upstream version 0.9.6+really0.9.3upstream/0.9.6+really0.9.3
Diffstat (limited to 'tests/unistr/test-u8-mbtouc.c')
-rw-r--r-- | tests/unistr/test-u8-mbtouc.c | 161 |
1 files changed, 1 insertions, 160 deletions
diff --git a/tests/unistr/test-u8-mbtouc.c b/tests/unistr/test-u8-mbtouc.c index 9e3b9601..f6960a68 100644 --- a/tests/unistr/test-u8-mbtouc.c +++ b/tests/unistr/test-u8-mbtouc.c @@ -1,5 +1,5 @@ /* Test of u8_mbtouc() function. - Copyright (C) 2010-2015 Free Software Foundation, Inc. + Copyright (C) 2010 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 @@ -24,169 +24,10 @@ #include "test-u8-mbtouc.h" -static void -test_safe_function (int (*my_u8_mbtouc) (ucs4_t *, const uint8_t *, size_t)) -{ - ucs4_t uc; - int ret; - - /* Test behaviour required by ISO 10646-1, sections R.7 and 2.3c, namely, - that a "malformed sequence" is interpreted in the same way as - "a character that is outside the adopted subset". - Reference: - Markus Kuhn: UTF-8 decoder capability and stress test - <http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt> - <http://www.w3.org/2001/06/utf-8-wrong/UTF-8-test.html> - */ - /* 3.1. Test that each unexpected continuation byte is signalled as a - malformed sequence of its own. */ - { - static const uint8_t input[] = { '"', 0x80, 0xBF, 0x80, 0xBF, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 6); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 5); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 2, 4); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 3, 3); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 4, 2); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 5, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } - /* 3.2. Lonely start characters. */ - { - ucs4_t c; - uint8_t input[2]; - - for (c = 0xC0; c <= 0xFF; c++) - { - input[0] = c; - input[1] = ' '; - - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 2); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - } - } - /* 3.3. Sequences with last continuation byte missing. */ - /* 3.3.1. 2-byte sequence with last byte missing. */ - { - static const uint8_t input[] = { '"', 0xC0, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 3); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 2); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 2, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } - /* 3.3.6. 2-byte sequence with last byte missing. */ - { - static const uint8_t input[] = { '"', 0xDF, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 3); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 2); - ASSERT (ret == 1); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 2, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } - /* 3.3.2. 3-byte sequence with last byte missing. */ - { - static const uint8_t input[] = { '"', 0xE0, 0x80, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 4); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 3); - ASSERT (ret == 2); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 3, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } - /* 3.3.7. 3-byte sequence with last byte missing. */ - { - static const uint8_t input[] = { '"', 0xEF, 0xBF, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 4); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 3); - ASSERT (ret == 2); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 3, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } - /* 3.3.3. 4-byte sequence with last byte missing. */ - { - static const uint8_t input[] = { '"', 0xF0, 0x80, 0x80, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 5); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 4); - ASSERT (ret == 3); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 4, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } - /* 3.3.8. 4-byte sequence with last byte missing. */ - { - static const uint8_t input[] = { '"', 0xF7, 0xBF, 0xBF, '"' }; - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input, 5); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 1, 4); - ASSERT (ret == 3); - ASSERT (uc == 0xFFFD); - uc = 0xBADFACE; - ret = my_u8_mbtouc (&uc, input + 4, 1); - ASSERT (ret == 1); - ASSERT (uc == 0x0022); - } -} - int main () { test_function (u8_mbtouc); - test_safe_function (u8_mbtouc); return 0; } |