Lines Matching defs:utf8
409 // code point lie in [0x00, 0x7F], the length of utf8 code element byte is 1
420 // code point lie in [0x80, 0x7FF], the length of utf8 code element byte is 2
432 // code point lie in [0x800, 0xD7FF] or [0xDC00,0xFFFF], the length of utf8 code element byte is 3.
433 // when code point lie in [0xD800, 0xDBFF], due to the use of UCS-2, it corresponds to 3 utf8 symbols.
444 // code point lie in [0x10000, 0x10FFFF], the length of utf8 code element byte is 4.
579 * unicode point and the byte length of the utf8 encoding sequence.
670 std::string utf8 = "Hello";
673 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
684 std::string utf8 = "你好，世界！";
687 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
698 std::string utf8 = "";
701 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
712 std::string utf8 = "Hello, 你好";
715 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
726 std::string utf8 = "你好，世界！";
729 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
740 std::string utf8 = "\xF0\x28\x8C\x28";
743 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
754 std::string utf8 = "ABC"; // All are single byte characters
757 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
768 std::string utf8 = "\xC2\xA2\xC3\xBC"; // They are ¢ and ü, respectively
771 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
782 std::string utf8 = "\xE2\x82\xAC"; // euro: €
785 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
796 std::string utf8 = "\xF0\x9F\x98\x8E"; // Emoji ?
799 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
810 std::string utf8 = "Hello\0World", utf8Nul = utf8 + '\0' + "World"; // Clearly including zero bytes
824 std::string utf8 = "\xC0\x80\xC0\x80"; // Continuous illegal sequence
827 size_t converted = Utf8ToUtf16Size(reinterpret_cast<const uint8_t*>(utf8.data()), utf8.size());
838 std::string utf8 = "Hello";
841 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
842 utf16.data(), utf8.size(), utf16.size());
853 std::string utf8 = "你好，世界！";
856 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
857 utf16.data(), utf8.size(), utf16.size());
868 std::string utf8 = "";
871 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
872 utf16.data(), utf8.size(), utf16.size());
883 std::string utf8 = "Hello, 你好";
886 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
898 std::string utf8 = "你好，世界！";
901 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
902 utf16.data(), utf8.size(), utf16.size());
913 std::string utf8 = "\xF0\x28\x8C\x28";
916 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
917 utf16.data(), utf8.size(), utf16.size());
928 std::string utf8 = "ABC"; // All are single byte characters
931 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
932 utf16.data(), utf8.size(), utf16.size());
943 std::string utf8 = "\xC2\xA2\xC3\xBC"; // They are ¢ and ü, respectively
946 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
947 utf16.data(), utf8.size(), utf16.size());
958 std::string utf8 = "\xE2\x82\xAC"; // euro €
961 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
962 utf16.data(), utf8.size(), utf16.size());
973 std::string utf8 = "\xF0\x9F\x98\x8E"; // Emoji ?
976 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
977 utf16.data(), utf8.size(), utf16.size());
988 std::string utf8 = "Hello\0World", utf8Nul = utf8 + '\0' + "World"; // Clearly including zero bytes
1004 std::string utf8 = "\xC0\x80\xC0\x80"; // Continuous illegal sequence
1007 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
1008 utf16.data(), utf8.size(), utf16.size());
1019 std::string utf8 = "\xF0\x9F\x98\x8E"; // Emoji ?
1022 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
1023 utf16.data(), utf8.size(), utf16.size());
1033 std::string utf8 = "\xF0\x9F\x98\x8E"; // Emoji ?
1036 size_t converted = ConvertRegionUtf8ToUtf16(reinterpret_cast<const uint8_t*>(utf8.data()),
1037 utf16.data(), utf8.size(), utf16.size());