Files
dl_old/dl/memory/dl_code_cvt.cpp
T
2023-07-28 00:21:52 +08:00

275 lines
6.2 KiB
C++
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#include "dl_code_cvt.h"
#include <cassert>
#include <iconv.h>
#include "io/dl_log.h"
#include "memory/dl_memory.h"
namespace dl::CodeCvt
{
std::string CvtString(std::string_view from, std::string_view to, const char* buf, size_t buf_size)
{
//前置条件检查
if (buf_size == 0)
return {};
iconv_t cd = iconv_open(std::string{ to }.c_str(), std::string{ from }.c_str());
if ((iconv_t)(-1) == cd)
{
// 此处打印日志小心递归调用
assert(0 && "iconv_open失败!");
return {};
}
char temp[SIZE_BUFFER_STRING_CONVERT];//缓冲区
std::string ret;//输出
char* in_buf = (char*)buf; //输入指针
size_t in_size = buf_size; //输入大小,直到0停止转换
char* out_buf = temp; //输出缓冲区指针
size_t out_size = SIZE_BUFFER_STRING_CONVERT;//输出缓冲区大小
do
{//直到转换完
if (-1 == iconv(cd, &in_buf, &in_size, &out_buf, &out_size))
{
if (errno != E2BIG)
{
assert(0 && "转换编码失败!");
iconv_close(cd);
return {};
}
else
{
size_t num = SIZE_BUFFER_STRING_CONVERT - out_size;
ret += std::string(temp, num);
//没有转换完,重设输出位置
out_size = SIZE_BUFFER_STRING_CONVERT;
out_buf = temp;
}
}
else
{//完整转换,增加num
assert(in_size == 0);
size_t num = SIZE_BUFFER_STRING_CONVERT - out_size;
if (ret.empty())//第一次就结束了,优化直接return
{
iconv_close(cd);
return std::string(temp, num);
}
ret += std::string(temp, num);
}
} while (in_size);
iconv_close(cd);
return ret;
}
namespace Utf8
{
int Check(std::string_view str)
{
unsigned n_bytes = 0;//UFT8可用1-6个字节编码,ASCII用一个字节
unsigned char ch;
bool b_all_ascii = true; //如果全部都是ASCII, 说明不是UTF-8
for (size_t i = 0; i < str.size(); ++i)
{
ch = str[i];
if ((ch & 0x80) != 0) // 判断是否ASCII编码,如果不是,说明有可能是UTF-8,ASCII用7位编码,但用一个字节存,最高位标记为0,o0xxxxxxx
b_all_ascii = false;
if (n_bytes == 0) //如果不是ASCII码,应该是多字节符,计算字节数
{
if (ch >= 0x80)
{
if (ch >= 0xFC && ch <= 0xFD)
n_bytes = 6;
else if (ch >= 0xF8)
n_bytes = 5;
else if (ch >= 0xF0)
n_bytes = 4;
else if (ch >= 0xE0)
n_bytes = 3;
else if (ch >= 0xC0)
n_bytes = 2;
else
return 0;
--n_bytes;
}
}
else //多字节符的非首字节,应为 10xxxxxx
{
if ((ch & 0xC0) != 0x80)
return 0;
--n_bytes;
}
}
if (n_bytes > 0) //违返规则mb
return 0;
if (b_all_ascii) //如果全部都是ASCII, 说明不是UTF-8
return 1;
return 2;//utf8
}
void Copy(char* target, size_t size, std::string_view source, bool log /*= true*/)
{
if (size == 0)
{
log_warn0("缓冲区大小为0!");
return;
}
//如果加上结束符 超过缓冲区
size_t size_source = source.size();
if (size_source + 1 > size)
{
//std::string str_mb = CodeCvt::cvt_u8_mb(source);
if (log)
log_warn("字符串过比缓冲区大:", source );
size_t sub_size = Sub(source, size - 1);
Memory::Copy(target, size - 1, source.data(), sub_size);
target[sub_size] = 0;
}
else
{
memcpy(target, source.data(), size_source);
target[size_source] = 0;
}
}
size_t Sub(std::string_view str, size_t max)
{
if (max == 0)
return 0;
//源下标(与子串下标相同)
size_t i = 0;
size_t size = str.length();
size_t cut_len = 0;
unsigned char ch;
while (i < size)
{
ch = (unsigned char)str[i];
if (ch >= 252)
cut_len = 6;
else if (ch >= 248)
cut_len = 5;
else if (ch >= 240)
cut_len = 4;
else if (ch >= 224)
cut_len = 3;
else if (ch >= 192)
cut_len = 2;
else if (ch >= 65 && ch <= 90)
cut_len = 1;
else
cut_len = 1;
if (i + cut_len > max)
return i;
i += cut_len;
}
return size;
}
}
std::string Utf8ToMultiByte(std::string_view str, std::string_view code_page /*= ""*/)
{
return CvtString("UTF-8", code_page, str.data(), str.size());
}
std::string MultiByteToUtf8(const char* str, std::string_view code_page)
{
return CvtString(code_page, "UTF-8", str, strlen(str));
}
std::string MultiByteToUtf8(std::string_view str, std::string_view code_page)
{
return CvtString(code_page, "UTF-8", str.data(), str.size());
}
std::string Utf32ToUtf8(std::u32string_view str)
{
return CvtString("UTF-32", "UTF-8", (char*)str.data(), str.size() * sizeof(char32_t));
}
// std::wstring cvt_u8_wc(string_view str)
// {
// string out = CvtString("UTF-8", "wchar_t", str.data(), str.size());
//
// dnd_assert(out.size() % sizeof(wchar_t) == 0);//必须是sizeof(wchar_t)的倍数
// std::wstring ret((wchar_t*)out.c_str(), out.size() / sizeof(wchar_t));
// return ret;
// }
//
// string cvt_u8_mb(string_view str)
// {
// return CvtString("UTF-8", "", str.data(), str.size());
// }
//
// dnd::utf_string cvt_u8_utf(string_view str)
// {
// string out = CvtString("UTF-8", "UCS-4-INTERNAL", str.data(), str.size());
//
// dnd_assert(out.size() % sizeof(char32_t) == 0);//必须是sizeof(char32_t)的倍数
// dnd::utf_string ret((char32_t*)out.c_str(), out.size() / sizeof(char32_t));
// return ret;
// }
//
// string cvt_wc_u8(const wchar_t* str)
// {
// size_t size = wcslen(str) * sizeof(wchar_t);
// return CvtString("wchar_t", "UTF-8", (char*)str, size);
// }
//
// std::string cvt_wc_u8(std::wstring_view str)
// {
// return CvtString("wchar_t", "UTF-8", (char*)str.data(), str.size() * sizeof(wchar_t));
// }
//
//
//
// string cvt_wc_mb(const wchar_t* str, string_view code_name)
// {
// size_t size = wcslen(str) * sizeof(wchar_t);
// return CvtString("wchar_t", code_name, (char*)str, size);
// }
//
// std::string cvt_mb_u8(string_view str, string_view code_name /*= ""*/)
// {
// return CvtString(code_name, "UTF-8", str.data(), str.size());
// }
//
//
//
// std::wstring cvt_mb_wc(const char* str, string_view code_name)
// {
// string out = CvtString(code_name, "wchar_t", str, strlen(str));
//
// dnd_assert(out.size() % sizeof(wchar_t) == 0);//必须是sizeof(wchar_t)的倍数
// std::wstring ret((wchar_t*)out.c_str(), out.size() / sizeof(wchar_t));
// return ret;
// }
//
// string cvt_utf_u8(const utf_string& str)
// {
// return CvtString("UCS-4-INTERNAL", "UTF-8", (char*)str.c_str(), str.size() * sizeof(wchar_t));
// }
//
}