hero_head_5_7/jni/str_conv.cpp

#include "str_conv.h"
#include "global_func.h"
#include <codecvt>
#include "log.h"

//-------------------------------------------------------------------------------------------------
wstring UTF8toUnicode(const string& s) {
  wstring ws;
  wchar_t wc;
  for (int i = 0; i < s.length();) {
    char c = s[i];
    if ((c & 0x80) == 0) {
      wc = c;
      ++i;
    } else if ((c & 0xE0) == 0xC0) {
      wc = (s[i] & 0x1F) << 6;
      wc |= (s[i + 1] & 0x3F);
      i += 2;
    } else if ((c & 0xF0) == 0xE0) {
      wc = (s[i] & 0xF) << 12;
      wc |= (s[i + 1] & 0x3F) << 6;
      wc |= (s[i + 2] & 0x3F);
      i += 3;
    } else if ((c & 0xF8) == 0xF0) {
      wc = (s[i] & 0x7) << 18;
      wc |= (s[i + 1] & 0x3F) << 12;
      wc |= (s[i + 2] & 0x3F) << 6;
      wc |= (s[i + 3] & 0x3F);
      i += 4;
    } else if ((c & 0xFC) == 0xF8) {
      wc = (s[i] & 0x3) << 24;
      wc |= (s[i] & 0x3F) << 18;
      wc |= (s[i] & 0x3F) << 12;
      wc |= (s[i] & 0x3F) << 6;
      wc |= (s[i] & 0x3F);
      i += 5;
    } else if ((c & 0xFE) == 0xFC) {
      wc = (s[i] & 0x1) << 30;
      wc |= (s[i] & 0x3F) << 24;
      wc |= (s[i] & 0x3F) << 18;
      wc |= (s[i] & 0x3F) << 12;
      wc |= (s[i] & 0x3F) << 6;
      wc |= (s[i] & 0x3F);
      i += 6;
    }
    ws += wc;
  }
  return ws;
}
//-------------------------------------------------------------------------------------------------
//002690C8
bool UnicodeToUTF8(char* pOutput0, const wchar_t* pWBuf1, uint dOutputLen2) {
  bool bret = false;
  int dr3;
  wchar_t wcr7;
  char var_20[4];
  for (; dOutputLen2 >= 2; dOutputLen2 -= dr3, pOutput0 += dr3) {
    //00269100
    wcr7 = *pWBuf1;
    dr3 = 0;
    bret = false;
    if (wcr7 == 0) {
      break;
    }

    //00269106
    if (wcr7 <= 0x7F) {
      //0026910A
      var_20[0] = wcr7;
      dr3 = 1;
    } else {
      // loc_269112
      if ((wcr7 >> 11) == 0) {
        //00269118
        dr3 = 2;
        var_20[0] = ((wcr7 >> 6) & 0x1F) | 0xC0;
        var_20[1] = (wcr7 & 0x3F) | 0x80;
      } else {
        // loc_26912E
        dr3 = 3;
        var_20[0] = (0xe0 | (wcr7 >> 12));
        var_20[1] = (0x80 | ((wcr7 >> 6) & 0x3f));
        var_20[2] = (0x80 | (wcr7 & 0x3f));
      }
    }

    // loc_26914A  dr3 + 1 的目录是为了结尾多一个0
    if (dOutputLen2 > (dr3 + 1)) {
      // loc_2690DE
      pWBuf1++;
      char* p = var_20;
      char* pr5 = pOutput0;
      for (int dr7 = dr3; dr7 != 0; dr7--) {  // loc_2690F2
        // loc_2690E8
        *pr5++ = *p++;
      }
    } else {
      //00269150
      bret = true;
      break;
    }
  }
  // loc_269154
  *pOutput0 = '\0';
  return bret;
}
//-------------------------------------------------------------------------------------------------
//00268EDC 此函数返汇编后与原始汇编有较大差异，但是经过单元测试是正确的
int UTF8ToUnicode(wchar_t* pWOut0, const char* pUtfStr1, uint dOutputLen2) {
  int dret = 0;

  for (; dOutputLen2 >= 2; dOutputLen2--) {
    uint cr4 = *pUtfStr1;  //00268FB0
    int dr3 = 0;
    int dr5 = (int((int)cr4 << 24)) >> 24;
    if (dr5) {
      dr3 = 2;
      if ((cr4 & 0xC0) != 0x80) {
        // loc_268EE8
        if ((cr4 - 0xF5) < 0xB || (cr4 & 0xFE) == 0xC0) {
          // loc_268FC6
          break;
        }

        const char* pr3 = pUtfStr1 + 1;  //00268EF8
        //00268EF8
        if (dr5 > -1) {
          pUtfStr1++;
        } else {
          // loc_268F04
          uint dr6_268F04 = dr5 + 0x3E;
          dr6_268F04 = UXTB_00(dr6_268F04);
          if (dr6_268F04 <= 0x1D) {
            //00268F0E
            dret = 2;
            char cr5 = *pr3;  //00268F0E
            if (cr5 == 0 || (cr5 & 0xC0) != 0x80) {
              break;
            }

            //00268F1E
            // dr3 = (cr4 & 0x1F);
            // int dr6 = cr5 & 0x3F;
            cr4 = (cr5 & 0x3F) | (cr4 & 0x1F);
            pUtfStr1 += 2;
          } else {
            // loc_268F2E
            if ((dr5 & 0xFFFFFFF0) == -32) {
              //00268F36
              char cr5 = *pr3;  //00268F36
              if (!cr5 || !pUtfStr1[2]) {
                dret = 2;
                break;
              }

              //00268F42
              dret = 2;
              if ((cr5 & 0xC0) == 0x80 && (pUtfStr1[2] & 0xC0) == 0x80) {
                //00268F54
                int ddr3 = UXTH_00((cr4 << 0xC));
                int dr7 = pUtfStr1[2] & 0x3F;
                pUtfStr1 += 3;
                ddr3 = ddr3 | ((cr5 & 0x3F) << 6);
                cr4 = ddr3 | dr7;
              } else {
                break;
              }
            } else {
              // loc_268F64
              int ddr4 = UXTB_00((dr5 + 0x10));
              if (ddr4 > 4) {
                dret = 2;
                break;
              }

              //00268F6E
              if (pUtfStr1[1] == 0 || pUtfStr1[2] == 0 || pUtfStr1[3] == 0) {
                dret = 2;
                break;
              }
              //00268F7A
              if ((pUtfStr1[1] & 0xC0) == 0x80 && (pUtfStr1[2] & 0xC0) == 0x80 && (pUtfStr1[3] & 0xC0) == 0x80) {
                //00268F94
                int dddr3 = 0xFC0 & (pUtfStr1[2] << 6);  //00268F94
                int dgr7 = pUtfStr1[3] & 0x3F;
                dddr3 = dddr3 | ((pUtfStr1[1] & 0x3F) << 12);
                pUtfStr1 += 4;
                cr4 = dddr3 | dgr7;
              } else {
                break;
              }
            }
            // loc_268FA2
          }
          // loc_268FA6
        }

        // loc_268FA6
        *pWOut0++ = cr4;
      } else {
        break;
      }
    } else {
      break;
    }
  }

  // loc_268FC6
  *pWOut0 = 0;
  return dret;
}
//-------------------------------------------------------------------------------------------------
//00268E6E 原始程序这儿有BUG
void UnicodeToAscii(char* pOut0, wchar_t const* pWBuf1, uint dLen2, char c3) {
  int dr12 = 0;
  for (; dr12 <= dLen2; dr12++) {
    if (pWBuf1[dr12] == 0) {
      break;
    }

    if (pWBuf1[dr12] >= 0x100) {
      pOut0[dr12] = c3;
    } else {
      pOut0[dr12] = pWBuf1[dr12];
    }
  }

  // loc_268E96
  pOut0[dr12] = '\0';
}
//-------------------------------------------------------------------------------------------------
//00268E9E
char* UTF8ToAscii(char* pOutAscii0, char const* pUtf81, uint dLen2, char c3) {
  wchar_t* pWBuf = new wchar_t[dLen2];
  UTF8ToUnicode(pWBuf, pUtf81, dLen2);  //00268EC0
  UnicodeToAscii(pOutAscii0, pWBuf, dLen2, c3);
  delete[] pWBuf;

  return pOutAscii0;
}
//-------------------------------------------------------------------------------------------------
//00268E4C //^_- 经过单元测试，功能正常
//循环取p_c_r1的元素：我的代码是p_c_r1++，原始代码是通过d_r12去取
void AsciiToUnicode(wchar_t* p_wc_r0, char const* p_c_r1, uint ud_r2) {
  LOGI("AsciiToUnicode entry");
  int d_r12;
  for (d_r12 = 0; (ud_r2 >= 2) && (p_c_r1[d_r12]); ud_r2--, d_r12++) {
    p_wc_r0[d_r12] = p_c_r1[d_r12];
  }
  p_wc_r0[d_r12] = 0;
  LOGI("AsciiToUnicode end");
}
//-------------------------------------------------------------------------------------------------
std::u16string s2ws(const std::string& str) {
  std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
  std::u16string dest = convert.from_bytes(str);
  return dest;
}
//-------------------------------------------------------------------------------------------------
std::string ws2s(const std::u16string& wstr) {
  using convert_typeX = std::codecvt_utf8<char16_t>;
  std::wstring_convert<convert_typeX, char16_t> converterX;

  return converterX.to_bytes(wstr);
}
//-------------------------------------------------------------------------------------------------
int strlen16(const char16_t* strarg) {
  if (!strarg)
    return -1;
  const char16_t* str = strarg;
  for (; *str; ++str)
    ;
  return str - strarg;
}
//-------------------------------------------------------------------------------------------------
string trim(const string& str) {
  size_t first = str.find_first_not_of(' ');
  if (string::npos == first) {
    return str;
  }
  size_t last = str.find_last_not_of(' ');
  return str.substr(first, (last - first + 1));
}
//-------------------------------------------------------------------------------------------------
vector<string> string_split(string s, char delim) {
  vector<string> result;
  stringstream ss(s);
  string item;
  while (getline(ss, item, delim)) {
    item = trim(item);
    result.push_back(item);
  }

  return result;
}
//-------------------------------------------------------------------------------------------------
void string_replace(std::string& data, std::string toSearch, std::string replaceStr) {
  size_t pos = data.find(toSearch);
  while (pos != std::string::npos) {
    data.replace(pos, toSearch.size(), replaceStr);
    pos = data.find(toSearch, pos + replaceStr.size());
  }
}
//-------------------------------------------------------------------------------------------------
void u16string_replace(std::u16string& data, std::u16string toSearch, std::u16string replaceStr) {
  size_t pos = data.find(toSearch);
  while (pos != std::u16string::npos) {
    data.replace(pos, toSearch.size(), replaceStr);
    pos = data.find(toSearch, pos + replaceStr.size());
  }
}
//-------------------------------------------------------------------------------------------------
//002691E4 //^_^ 经过单元测试，功能正常
wchar_t* CreateStringCopy(const wchar_t* pStr) {
  int dlen = strlen16((const char16_t*)pStr) + sizeof(wchar_t);
  wchar_t* pBuf = new wchar_t[dlen];
  memcpy(pBuf, pStr, dlen * sizeof(wchar_t));
  return pBuf;
}
//-------------------------------------------------------------------------------------------------
//00269218 //^_^ 经过单元测试，功能正常
char* CreateStringCopy(const char* pStr) {
  int dlen = strlen(pStr) + sizeof(char);
  char* pBuf = new char[dlen];
  strlcpy((uchar*)pBuf, (uchar*)pStr, dlen);
  return pBuf;
}
//-------------------------------------------------------------------------------------------------------
//00268C2C //^_^
size_t xstrlen(const wchar_t* a1) {
  wchar_t v2;
  const wchar_t* v1 = a1 - 1;
  do {
    v2 = v1[1];
    ++v1;
  } while (v2);
  return v1 - a1;
}
//-------------------------------------------------------------------------------------------------------
wchar_t* xstrchr(const wchar_t* pbuf, wchar_t c) {
  const wchar_t* r3 = pbuf;
  // loc_268DFE
  while (*r3) {
    r3++;
  }

  //00268E06
  int r12 = r3 - pbuf;
  int ir3 = 0;
  wchar_t* r0 = reinterpret_cast<wchar_t*>(const_cast<wchar_t*>(pbuf));
  while (1) {
    if (ir3 >= r12) {
      return nullptr;
    }

    //00268E18
    ir3++;
    if (*r0 == c) {
      return r0;
    }
    r0++;
  }
  return nullptr;
}
//-------------------------------------------------------------------------------------------------------
wchar_t* xstrrchr(const wchar_t* pbuf, wchar_t c) {
  const wchar_t* r2 = pbuf;
  // loc_268E2A
  while (*r2) {
    r2++;
  }

  wchar_t* r0 = static_cast<wchar_t*>(const_cast<wchar_t*>(pbuf));
  int ir2 = r2 - pbuf;
  while (ir2 > 0) {
    // loc_268E38
    ir2--;
    if (*r0 == c) {
      return r0;
    }
    r0++;
  }
  return nullptr;
}
//-------------------------------------------------------------------------------------------------------
//0014D150
char* strlwr(char* pBuf) {
  for (int i = 0; pBuf[i] != 0; ++i) {
    if ((pBuf[i] - 65) <= 0x19u)
      pBuf[i] = pBuf[i] + 32;
  }
  return pBuf;
}
//-------------------------------------------------------------------------------------------------------
string Unicode2String(char16_t const* pWBuf) {
  std::u16string u16str(pWBuf);
  return ws2s(u16str);
}
//-------------------------------------------------------------------------------------------------------
//00268CD2 ^_^ 经过单元测试，功能正常
int xstrcmp(const wchar_t* a1, const wchar_t* a2) {
  wchar_t v2;
  wchar_t v3;
  while (1) {
    v2 = *a2;
    v3 = *a1;
    if (!*a2)
      break;
    if (v3 < v2)
      return -1;
    if (v3 > v2)
      return 1;
    ++a1;
    ++a2;
  }
  if (*a1)
    v3 = 1;
  return v3;
}
//-------------------------------------------------------------------------------------------------------
//00268C3C ^_^ 经过单元测试，功能正常
ulong xstrlcpy(wchar_t* a1, const wchar_t* a2, unsigned int a3) {
  const wchar_t* v3 = a2;
  if (a3) {
    a3--;
    v3 = a2;
    while (a3) {
      wchar_t v5 = *v3++;
      a3--;
      *a1++ = v5;
      if (!v5)
        return ((ulong)v3 - (ulong)a2) / 2 - 1;
    }
    *a1 = 0;
  }

  while (*v3++)
    ;
  return ((ulong)v3 - (ulong)a2) / 2 - 1;
}
//-------------------------------------------------------------------------------------------------------
//001199C2 -_- 经过单元测试，功能正常
size_t strlcpy(unsigned char* a1, unsigned char* a2, int a3) {
  unsigned char* v3 = a2;
  if (a3) {
    a3--;
    v3 = a2;
    while (a3) {
      unsigned char v5 = *v3++;
      a3--;
      *a1++ = v5;
      if (!v5)
        return v3 - a2 - 1;
    }
    *a1 = 0;
  }
  while (*v3++)
    ;
  return v3 - a2 - 1;
}
//-------------------------------------------------------------------------------------------------------
const wchar_t* xstrstr(wchar_t const*a1, wchar_t const*a2){
  LOGE("xstrstr=%s%s",a1,a2);
  return a1+rand()%10;
}

size_t xstrlcat(wchar_t*a1, const wchar_t*a2, unsigned int a3)
{
  LOGE("xstrstr=%s%s%x",a1,a2,a3);
  return rand()%10;
}