diff options
author | biao716.wang <biao716.wang@samsung.com> | 2020-03-19 01:04:30 +0900 |
---|---|---|
committer | biao716.wang <biao716.wang@samsung.com> | 2020-03-19 01:04:30 +0900 |
commit | 1d6613f4446f69f63beddf2d97c201154fb35e33 (patch) | |
tree | f32eae75900a0df14ab8fa1e2bd436af159ef91d /Tests/CMakeLib/testUTF8.cxx | |
parent | aabcd8e66e3268a232efe2e416635d5b6bf84ad5 (diff) | |
download | cmake-1d6613f4446f69f63beddf2d97c201154fb35e33.tar.gz cmake-1d6613f4446f69f63beddf2d97c201154fb35e33.tar.bz2 cmake-1d6613f4446f69f63beddf2d97c201154fb35e33.zip |
Imported Upstream version 3.16.4upstream/3.16.4
Change-Id: Ic5262ea6c0872b353ea2dc35fe1e944063ae8409
Signed-off-by: biao716.wang <biao716.wang@samsung.com>
Diffstat (limited to 'Tests/CMakeLib/testUTF8.cxx')
-rw-r--r-- | Tests/CMakeLib/testUTF8.cxx | 112 |
1 files changed, 102 insertions, 10 deletions
diff --git a/Tests/CMakeLib/testUTF8.cxx b/Tests/CMakeLib/testUTF8.cxx index fb5f3d815..986f5956e 100644 --- a/Tests/CMakeLib/testUTF8.cxx +++ b/Tests/CMakeLib/testUTF8.cxx @@ -1,15 +1,32 @@ /* Distributed under the OSI-approved BSD 3-Clause License. See accompanying file Copyright.txt or https://cmake.org/licensing for details. */ -#include <cm_utf8.h> #include <stdio.h> +#include <cm_utf8.h> + typedef char test_utf8_char[5]; static void test_utf8_char_print(test_utf8_char const c) { unsigned char const* d = reinterpret_cast<unsigned char const*>(c); - printf("[0x%02X,0x%02X,0x%02X,0x%02X]", (int)d[0], (int)d[1], (int)d[2], - (int)d[3]); + printf("[0x%02X,0x%02X,0x%02X,0x%02X]", static_cast<int>(d[0]), + static_cast<int>(d[1]), static_cast<int>(d[2]), + static_cast<int>(d[3])); +} + +static void byte_array_print(char const* s) +{ + unsigned char const* d = reinterpret_cast<unsigned char const*>(s); + bool started = false; + printf("["); + for (; *d; ++d) { + if (started) { + printf(","); + } + started = true; + printf("0x%02X", static_cast<int>(*d)); + } + printf("]"); } struct test_utf8_entry @@ -20,17 +37,36 @@ struct test_utf8_entry }; static test_utf8_entry const good_entry[] = { - { 1, "\x20\x00\x00\x00", 0x0020 }, /* Space. */ - { 2, "\xC2\xA9\x00\x00", 0x00A9 }, /* Copyright. */ - { 3, "\xE2\x80\x98\x00", 0x2018 }, /* Open-single-quote. */ - { 3, "\xE2\x80\x99\x00", 0x2019 }, /* Close-single-quote. */ - { 4, "\xF0\xA3\x8E\xB4", 0x233B4 }, /* Example from RFC 3629. */ + { 1, "\x20\x00\x00\x00", 0x0020 }, /* Space. */ + { 2, "\xC2\xA9\x00\x00", 0x00A9 }, /* Copyright. */ + { 3, "\xE2\x80\x98\x00", 0x2018 }, /* Open-single-quote. */ + { 3, "\xE2\x80\x99\x00", 0x2019 }, /* Close-single-quote. */ + { 4, "\xF0\xA3\x8E\xB4", 0x233B4 }, /* Example from RFC 3629. */ + { 3, "\xED\x80\x80\x00", 0xD000 }, /* Valid 0xED prefixed codepoint. */ + { 4, "\xF4\x8F\xBF\xBF", 0x10FFFF }, /* Highest valid RFC codepoint. */ { 0, { 0, 0, 0, 0, 0 }, 0 } }; static test_utf8_char const bad_chars[] = { - "\x80\x00\x00\x00", "\xC0\x00\x00\x00", "\xE0\x00\x00\x00", - "\xE0\x80\x80\x00", "\xF0\x80\x80\x80", { 0, 0, 0, 0, 0 } + "\x80\x00\x00\x00", /* Leading continuation byte. */ + "\xC0\x80\x00\x00", /* Overlong encoding. */ + "\xC1\x80\x00\x00", /* Overlong encoding. */ + "\xC2\x00\x00\x00", /* Missing continuation byte. */ + "\xE0\x00\x00\x00", /* Missing continuation bytes. */ + "\xE0\x80\x80\x00", /* Overlong encoding. */ + "\xF0\x80\x80\x80", /* Overlong encoding. */ + "\xED\xA0\x80\x00", /* UTF-16 surrogate half. */ + "\xED\xBF\xBF\x00", /* UTF-16 surrogate half. */ + "\xF4\x90\x80\x80", /* Lowest out-of-range codepoint. */ + "\xF5\x80\x80\x80", /* Prefix forces out-of-range codepoints. */ + { 0, 0, 0, 0, 0 } +}; + +static char const* good_strings[] = { "", "ASCII", "\xC2\xA9 Kitware", 0 }; + +static char const* bad_strings[] = { + "\xC0\x80", /* Modified UTF-8 for embedded 0-byte. */ + 0 }; static void report_good(bool passed, test_utf8_char const c) @@ -86,6 +122,46 @@ static bool decode_bad(test_utf8_char const s) return true; } +static void report_valid(bool passed, char const* s) +{ + printf("%s: validity good ", passed ? "pass" : "FAIL"); + byte_array_print(s); + printf(" (%s) ", s); +} + +static void report_invalid(bool passed, char const* s) +{ + printf("%s: validity bad ", passed ? "pass" : "FAIL"); + byte_array_print(s); + printf(" "); +} + +static bool is_valid(const char* s) +{ + bool valid = cm_utf8_is_valid(s) != 0; + if (!valid) { + report_valid(false, s); + printf("expected valid, reported as invalid\n"); + return false; + } + report_valid(true, s); + printf("valid as expected\n"); + return true; +} + +static bool is_invalid(const char* s) +{ + bool valid = cm_utf8_is_valid(s) != 0; + if (valid) { + report_invalid(false, s); + printf("expected invalid, reported as valid\n"); + return false; + } + report_invalid(true, s); + printf("invalid as expected\n"); + return true; +} + int testUTF8(int /*unused*/, char* /*unused*/ []) { int result = 0; @@ -93,11 +169,27 @@ int testUTF8(int /*unused*/, char* /*unused*/ []) if (!decode_good(*e)) { result = 1; } + if (!is_valid(e->str)) { + result = 1; + } } for (test_utf8_char const* c = bad_chars; (*c)[0]; ++c) { if (!decode_bad(*c)) { result = 1; } + if (!is_invalid(*c)) { + result = 1; + } + } + for (char const** s = good_strings; *s; ++s) { + if (!is_valid(*s)) { + result = 1; + } + } + for (char const** s = bad_strings; *s; ++s) { + if (!is_invalid(*s)) { + result = 1; + } } return result; } |