aki*_*kim 6 c++ boost utf-8 c++11
我正在寻找一种方法来显示UTF-8字符串及其非打印/无效字符转义.在ASCII时代,我习惯用来isprint
决定一个角色是按原样打印还是转义.使用UTF-8,迭代更加困难,但Boost.Locale做得很好.但是我没有找到任何内容来决定某些字符是否可打印,甚至实际上是否有效.
在以下源代码中,字符串"Hello ??? ? ? \x02\x01\b \xff\xff\xff "
包含一些不可打印的坏人(\b
例如),而其他人则是普通的无效序列(\xff\xff\xff
).我应该进行什么测试才能确定角色是否可打印?
// Based on an example of Boost.Locale.
#include <boost/locale.hpp>
#include <iostream>
#include <iomanip>
int main()
{
using namespace boost::locale;
using namespace std;
generator gen;
std::locale loc = gen("");
locale::global(loc);
cout.imbue(loc);
string text = "Hello ??? ? ? \x02\x01\b \xff\xff\xff ";
cout << text << endl;
boundary::ssegment_index index(boundary::character, text.begin(), text.end());
for (auto p: index)
{
cout << '[' << p << '|';
for (uint8_t c: p)
cout << std::hex << std::setw(2) << std::setfill('0') << int(c);
cout << "] ";
}
cout << '\n';
}
Run Code Online (Sandbox Code Playgroud)
运行时,它给出了
[H|48] [e|65] [l|6c] [l|6c] [o|6f] [ |20] [?|e38182] [?|e381ab] [?|e381be]
[ |20] [?|e29ea6] [ |20] [|f09f9199] [ |20] [|f09d95ab]
[?|e28a86] [|f09d95a2] [ |20] [|02] [|01] |08] [ |20] [??? |ffffff20]
Run Code Online (Sandbox Code Playgroud)
我该如何判断它[|01]
是不可打印的,也不是[??? |ffffff20]
,但是,[o|6f]
是,等等[|f09f9199]
?粗略地说,测试应该允许我决定是否打印[|]对的左侧成员,或者是否打印右侧成员isprint
.
谢谢
小智 3
Unicode 具有每个代码点的属性,其中包括一般类别,技术报告列出了正则表达式分类(字母、图形等)。unicodeprint
分类包括制表符,而std::isprint
(使用 C 语言环境)则不包括制表符。print
确实包括字母、标记、数字、标点符号、符号、空格和格式代码点。格式化代码点不包含CR
或LF
,但包含影响外观的代码点外观的我相信这正是您想要的(选项卡除外);该规范经过精心设计以支持这些字符属性。
大多数分类函数(例如std::isprint
)一次只能给出一个标量值,因此 UTF32 是明显的编码选择。不幸的是,我们不能保证您的系统支持 UTF32 语言环境,也不能保证是wchar_t
保存所有 unicode 代码点所需的 20 位。因此,boost::spirit::char_encoding::unicode
如果可以的话,我会考虑用于分类。它有一个包含所有 unicode 类别的内部表,并实现了正则表达式技术报告中列出的分类。看起来它使用的是较旧的 Unicode 5.2 数据库,但提供了用于生成表的 C++,并且可以应用于较新的文件。
多字节 UTF8 序列仍然需要转换为单独的代码点 (UTF32),并且您特别提到了跳过无效 UTF8 序列的能力。由于我是一名 C++ 程序员,我决定不必要地向您的屏幕发送垃圾邮件,并实现 constexpr UTF8->UTF32 函数:
\n\n#include <cstdint>\n#include <iomanip>\n#include <iostream>\n#include <iterator>\n#include <boost/range/iterator_range.hpp>\n#include <boost/spirit/home/support/char_encoding/unicode.hpp>\n\nnamespace {\nstruct multi_byte_info {\n std::uint8_t id_mask;\n std::uint8_t id_matcher;\n std::uint8_t data_mask;\n};\n\nconstexpr const std::uint8_t multi_byte_id_mask = 0xC0;\nconstexpr const std::uint8_t multi_byte_id_matcher = 0x80;\nconstexpr const std::uint8_t multi_byte_data_mask = 0x3F;\nconstexpr const std::uint8_t multi_byte_bits = 6;\nconstexpr const multi_byte_info multi_byte_infos[] = {\n // skip 1 byte info\n {0xE0, 0xC0, 0x1F},\n {0xF0, 0xE0, 0x0F},\n {0xF8, 0xF0, 0x07}};\nconstexpr const unsigned max_length =\n (sizeof(multi_byte_infos) / sizeof(multi_byte_info));\n\nconstexpr const std::uint32_t overlong[] = {0x80, 0x800, 0x10000};\nconstexpr const std::uint32_t max_code_point = 0x10FFFF;\n}\n\nenum class extraction : std::uint8_t { success, failure };\n\nstruct extraction_attempt {\n std::uint32_t code_point;\n std::uint8_t bytes_processed;\n extraction status;\n};\n\ntemplate <typename Iterator>\nconstexpr extraction_attempt next_code_point(Iterator position,\n const Iterator &end) {\n static_assert(\n std::is_same<typename std::iterator_traits<Iterator>::iterator_category,\n std::random_access_iterator_tag>{},\n "bad iterator type");\n\n extraction_attempt result{0, 0, extraction::failure};\n\n if (end - position) {\n result.code_point = std::uint8_t(*position);\n ++position;\n ++result.bytes_processed;\n\n if (0x7F < result.code_point) {\n unsigned expected_length = 1;\n\n for (const auto info : multi_byte_infos) {\n if ((result.code_point & info.id_mask) == info.id_matcher) {\n result.code_point &= info.data_mask;\n break;\n }\n ++expected_length;\n }\n\n if (max_length < expected_length || (end - position) < expected_length) {\n return result;\n }\n\n for (unsigned byte = 0; byte < expected_length; ++byte) {\n const std::uint8_t next_byte = *(position + byte);\n if ((next_byte & multi_byte_id_mask) != multi_byte_id_matcher) {\n return result;\n }\n\n result.code_point <<= multi_byte_bits;\n result.code_point |= (next_byte & multi_byte_data_mask);\n ++result.bytes_processed;\n }\n\n if (max_code_point < result.code_point) {\n return result;\n }\n\n if (overlong[expected_length - 1] > result.code_point) {\n return result;\n }\n }\n\n result.status = extraction::success;\n } // end multi-byte processing\n\n return result;\n}\n\ntemplate <typename Range>\nconstexpr extraction_attempt next_code_point(const Range &range) {\n return next_code_point(std::begin(range), std::end(range));\n}\n\ntemplate <typename T>\nboost::iterator_range<T>\nnext_character_bytes(const boost::iterator_range<T> &range,\n const extraction_attempt result) {\n return boost::make_iterator_range(range.begin(),\n range.begin() + result.bytes_processed);\n}\n\ntemplate <std::size_t Length>\nconstexpr bool test(const char (&range)[Length],\n const extraction expected_status,\n const std::uint32_t expected_code_point,\n const std::uint8_t expected_bytes_processed) {\n const extraction_attempt result =\n next_code_point(std::begin(range), std::end(range) - 1);\n switch (expected_status) {\n case extraction::success:\n return result.status == extraction::success &&\n result.bytes_processed == expected_bytes_processed &&\n result.code_point == expected_code_point;\n case extraction::failure:\n return result.status == extraction::failure &&\n result.bytes_processed == expected_bytes_processed;\n default:\n return false;\n }\n}\n\nint main() {\n static_assert(test("F", extraction::success, \'F\', 1), "");\n static_assert(test("\\0", extraction::success, 0, 1), "");\n static_assert(test("\\x7F", extraction::success, 0x7F, 1), "");\n static_assert(test("\\xFF\\xFF", extraction::failure, 0, 1), "");\n\n static_assert(test("\\xDF", extraction::failure, 0, 1), "");\n static_assert(test("\\xDF\\xFF", extraction::failure, 0, 1), "");\n static_assert(test("\\xC1\\xBF", extraction::failure, 0, 2), "");\n static_assert(test("\\xC2\\x80", extraction::success, 0x80, 2), "");\n static_assert(test("\\xDF\\xBF", extraction::success, 0x07FF, 2), "");\n\n static_assert(test("\\xEF\\xBF", extraction::failure, 0, 1), "");\n static_assert(test("\\xEF\\xBF\\xFF", extraction::failure, 0, 2), "");\n static_assert(test("\\xE0\\x9F\\xBF", extraction::failure, 0, 3), "");\n static_assert(test("\\xE0\\xA0\\x80", extraction::success, 0x800, 3), "");\n static_assert(test("\\xEF\\xBF\\xBF", extraction::success, 0xFFFF, 3), "");\n\n static_assert(test("\\xF7\\xBF\\xBF", extraction::failure, 0, 1), "");\n static_assert(test("\\xF7\\xBF\\xBF\\xFF", extraction::failure, 0, 3), "");\n static_assert(test("\\xF0\\x8F\\xBF\\xBF", extraction::failure, 0, 4), "");\n static_assert(test("\\xF0\\x90\\x80\\x80", extraction::success, 0x10000, 4), "");\n static_assert(test("\\xF4\\x8F\\xBF\\xBF", extraction::success, 0x10FFFF, 4), "");\n static_assert(test("\\xF7\\xBF\\xBF\\xBF", extraction::failure, 0, 4), "");\n\n static_assert(test("", extraction::success, 0x1D56B, 4), "");\n\n constexpr const static char text[] =\n "Hello \xe3\x81\x82\xe3\x81\xab\xe3\x81\xbe \xe2\x9e\xa6 \xe2\x8a\x86 \\x02\\x01\\b \\xff\\xff\\xff ";\n\n std::cout << text << std::endl;\n\n auto data = boost::make_iterator_range(text);\n while (!data.empty()) {\n const extraction_attempt result = next_code_point(data);\n switch (result.status) {\n case extraction::success:\n if (boost::spirit::char_encoding::unicode::isprint(result.code_point)) {\n std::cout << next_character_bytes(data, result);\n break;\n }\n\n default:\n case extraction::failure:\n std::cout << "[";\n std::cout << std::hex << std::setw(2) << std::setfill(\'0\');\n for (const auto byte : next_character_bytes(data, result)) {\n std::cout << int(std::uint8_t(byte));\n }\n std::cout << "]";\n break;\n }\n\n data.advance_begin(result.bytes_processed);\n }\n\n return 0;\n}\n
Run Code Online (Sandbox Code Playgroud)\n\n输出:
\n\nHello \xe3\x81\x82\xe3\x81\xab\xe3\x81\xbe \xe2\x9e\xa6 \xe2\x8a\x86 \xef\xbf\xbd\xef\xbf\xbd\xef\xbf\xbd \nHello \xe3\x81\x82\xe3\x81\xab\xe3\x81\xbe \xe2\x9e\xa6 \xe2\x8a\x86 [02][01][08] [ff][ff][ff] [00]\n
Run Code Online (Sandbox Code Playgroud)\n\n如果我的 UTF8->UTF32 实现让您感到害怕,或者您需要对用户区域设置的支持:
\n\nstd::mbtoc32
\n\nboost::locale::conv
和 C++11std::codecvt
\n\nutf::next
(和非抛出utf8::internal::validate_next
)。\n\n\n\n\n它:对指向 UTF-8 编码代码点开头的迭代器的引用。函数返回后,它会递增以指向下一个代码点的开头。
\n
这并不表明异常的副作用(肯定有一些)。
\n 归档时间: |
|
查看次数: |
490 次 |
最近记录: |