diff options
Diffstat (limited to 'tests/unistr/test-u8-mbsnlen.c')
| -rw-r--r-- | tests/unistr/test-u8-mbsnlen.c | 32 |
1 files changed, 28 insertions, 4 deletions
diff --git a/tests/unistr/test-u8-mbsnlen.c b/tests/unistr/test-u8-mbsnlen.c index 7b8f0292..ca31d856 100644 --- a/tests/unistr/test-u8-mbsnlen.c +++ b/tests/unistr/test-u8-mbsnlen.c @@ -1,5 +1,5 @@ /* Test of u8_mbsnlen() function. - Copyright (C) 2010-2022 Free Software Foundation, Inc. + Copyright (C) 2010-2024 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 @@ -61,9 +61,18 @@ main () that a "malformed sequence" is interpreted in the same way as "a character that is outside the adopted subset". Reference: + ISO 10646-1 amendment 2 + <https://www.cl.cam.ac.uk/~mgk25/ucs/ISO-10646-UTF-8.html> Markus Kuhn: UTF-8 decoder capability and stress test <https://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt> <https://www.w3.org/2001/06/utf-8-wrong/UTF-8-test.html> + These old specifications (from ca. 2000) were a bit ambiguous, and the + definition of UTF-8 has changed a bit as well. The newer specification + we obey is the Unicode Standard, version 15. + Reference: + Unicode Standard 15.0.0, section 3.9 + <https://www.unicode.org/versions/Unicode15.0.0/ch03.pdf> + pages 124..129, especially table 3-7. */ /* 3.1. Test that each unexpected continuation byte is signalled as a malformed sequence of its own. */ @@ -97,9 +106,14 @@ main () } /* 3.3.2. 3-byte sequence with last byte missing. */ { - static const uint8_t input[] = { '"', 0xE0, 0x80, '"' }; + static const uint8_t input[] = { '"', 0xE0, 0xA0, '"' }; ASSERT (u8_mbsnlen (input, 4) == 3); } + { + /* Outdated example: 0xE0 0x80 is an ill-formed sequence. */ + static const uint8_t input[] = { '"', 0xE0, 0x80, '"' }; + ASSERT (u8_mbsnlen (input, 4) == 4); + } /* 3.3.7. 3-byte sequence with last byte missing. */ { static const uint8_t input[] = { '"', 0xEF, 0xBF, '"' }; @@ -107,14 +121,24 @@ main () } /* 3.3.3. 4-byte sequence with last byte missing. */ { - static const uint8_t input[] = { '"', 0xF0, 0x80, 0x80, '"' }; + static const uint8_t input[] = { '"', 0xF0, 0x90, 0x80, '"' }; ASSERT (u8_mbsnlen (input, 5) == 3); } + { + /* Outdated example: 0xF0 0x80 is an ill-formed sequence. */ + static const uint8_t input[] = { '"', 0xF0, 0x80, 0x80, '"' }; + ASSERT (u8_mbsnlen (input, 5) == 5); + } /* 3.3.8. 4-byte sequence with last byte missing. */ { - static const uint8_t input[] = { '"', 0xF7, 0xBF, 0xBF, '"' }; + static const uint8_t input[] = { '"', 0xF3, 0xBF, 0xBF, '"' }; ASSERT (u8_mbsnlen (input, 5) == 3); } + { + /* Outdated example: 0xF7 is an invalid first byte. */ + static const uint8_t input[] = { '"', 0xF7, 0xBF, 0xBF, '"' }; + ASSERT (u8_mbsnlen (input, 5) == 5); + } return 0; } |