src/iconvlite.cpp - main - singlwolf/Radiola-2S3

src/iconvlite.cpp
117 строк3 KB
SinglWolf
Public access
27 мар 2026, 07:00
27 мар 2026, 07:00642fcfc
#include <iostream> // IWYU pragma: keep
#include <iconvlite.h>

using namespace std;

void cp2utf1(char *out, const char *in)
{
  static const int table[128] = {
      0x82D0, 0x83D0, 0x9A80E2, 0x93D1, 0x9E80E2, 0xA680E2, 0xA080E2, 0xA180E2,
      0xAC82E2, 0xB080E2, 0x89D0, 0xB980E2, 0x8AD0, 0x8CD0, 0x8BD0, 0x8FD0,
      0x92D1, 0x9880E2, 0x9980E2, 0x9C80E2, 0x9D80E2, 0xA280E2, 0x9380E2, 0x9480E2,
      0, 0xA284E2, 0x99D1, 0xBA80E2, 0x9AD1, 0x9CD1, 0x9BD1, 0x9FD1,
      0xA0C2, 0x8ED0, 0x9ED1, 0x88D0, 0xA4C2, 0x90D2, 0xA6C2, 0xA7C2,
      0x81D0, 0xA9C2, 0x84D0, 0xABC2, 0xACC2, 0xADC2, 0xAEC2, 0x87D0,
      0xB0C2, 0xB1C2, 0x86D0, 0x96D1, 0x91D2, 0xB5C2, 0xB6C2, 0xB7C2,
      0x91D1, 0x9684E2, 0x94D1, 0xBBC2, 0x98D1, 0x85D0, 0x95D1, 0x97D1,
      0x90D0, 0x91D0, 0x92D0, 0x93D0, 0x94D0, 0x95D0, 0x96D0, 0x97D0,
      0x98D0, 0x99D0, 0x9AD0, 0x9BD0, 0x9CD0, 0x9DD0, 0x9ED0, 0x9FD0,
      0xA0D0, 0xA1D0, 0xA2D0, 0xA3D0, 0xA4D0, 0xA5D0, 0xA6D0, 0xA7D0,
      0xA8D0, 0xA9D0, 0xAAD0, 0xABD0, 0xACD0, 0xADD0, 0xAED0, 0xAFD0,
      0xB0D0, 0xB1D0, 0xB2D0, 0xB3D0, 0xB4D0, 0xB5D0, 0xB6D0, 0xB7D0,
      0xB8D0, 0xB9D0, 0xBAD0, 0xBBD0, 0xBCD0, 0xBDD0, 0xBED0, 0xBFD0,
      0x80D1, 0x81D1, 0x82D1, 0x83D1, 0x84D1, 0x85D1, 0x86D1, 0x87D1,
      0x88D1, 0x89D1, 0x8AD1, 0x8BD1, 0x8CD1, 0x8DD1, 0x8ED1, 0x8FD1};
  while (*in)
    if (*in & 0x80)
    {
      int v = table[(int)(0x7f & *in++)];
      if (!v)
        continue;
      *out++ = (char)v;
      *out++ = (char)(v >> 8);
      v >>= 16;
      if (v != 0)
        *out++ = (char)v;
    }
    else
      *out++ = *in++;
  *out = 0;
}
string cp2utf(string s)
{
  size_t c, i;
  auto len = s.size();
  string ns;
  for (i = 0; i < len; i++)
  {
    c = s[i];
    char buf[4], in[2] = {0, 0};
    *in = c;
    cp2utf1(buf, in);
    ns += string(buf);
  }
  return ns;
}

bool is_valid_utf8(const char *string)
{
  if (!string)
  {
    return true;
  }
  const unsigned char *bytes = (const unsigned char *)string;
  unsigned int cp;
  int num;
  while (*bytes != 0x00)
  {
    if ((*bytes & 0x80) == 0x00)
    {
      // U+0000 to U+007F
      cp = (*bytes & 0x7F);
      num = 1;
    }
    else if ((*bytes & 0xE0) == 0xC0)
    {
      // U+0080 to U+07FF
      cp = (*bytes & 0x1F);
      num = 2;
    }
    else if ((*bytes & 0xF0) == 0xE0)
    {
      // U+0800 to U+FFFF
      cp = (*bytes & 0x0F);
      num = 3;
    }
    else if ((*bytes & 0xF8) == 0xF0)
    {
      // U+10000 to U+10FFFF
      cp = (*bytes & 0x07);
      num = 4;
    }
    else
    {
      return false;
    }
    bytes += 1;
    for (int i = 1; i < num; ++i)
    {
      if ((*bytes & 0xC0) != 0x80)
      {
        return false;
      }
      cp = (cp << 6) | (*bytes & 0x3F);
      bytes += 1;
    }
    if ((cp > 0x10FFFF) ||
        ((cp <= 0x007F) && (num != 1)) ||
        ((cp >= 0xD800) && (cp <= 0xDFFF)) ||
        ((cp >= 0x0080) && (cp <= 0x07FF) && (num != 2)) ||
        ((cp >= 0x0800) && (cp <= 0xFFFF) && (num != 3)) ||
        ((cp >= 0x10000) && (cp <= 0x1FFFFF) && (num != 4)))
    {
      return false;
    }
  }
  return true;
}