OCCT

// Created on: 2013-01-28
// Created by: Kirill GAVRILOV
// Copyright (c) 2013-2014 OPEN CASCADE SAS
//
// This file is part of Open CASCADE Technology software library.
//
// This library is free software; you can redistribute it and/or modify it under
// the terms of the GNU Lesser General Public License version 2.1 as published
// by the Free Software Foundation, with special exception defined in the file
// OCCT_LGPL_EXCEPTION.txt. Consult the file LICENSE_LGPL_21.txt included in OCCT
// distribution for complete text of the license and disclaimer of any warranty.
//
// Alternatively, this file may be used under the terms of Open CASCADE
// commercial license or contractual agreement.

// Portions of code are copyrighted by Unicode, Inc.
//
// Copyright (c) 2001-2004 Unicode, Inc.
//
// Disclaimer
//
// This source code is provided as is by Unicode, Inc. No claims are
// made as to fitness for any particular purpose. No warranties of any
// kind are expressed or implied. The recipient agrees to determine
// applicability of information provided. If this file has been
// purchased on magnetic or optical media from Unicode, Inc., the
// sole remedy for any claim will be exchange of defective media
// within 90 days of receipt.
//
// Limitations on Rights to Redistribute This Code
//
// Unicode, Inc. hereby grants the right to freely use the information
// supplied in this file in the creation of products supporting the
// Unicode Standard, and to make copies of this file in any form
// for internal or external distribution as long as this notice
// remains attached.

// =======================================================================
// function : readUTF8
// purpose  : Get a UTF-8 character; leave the tracking pointer at the start of the next character.
//            Not protected against invalid UTF-8.
// =======================================================================
template <typename Type>
inline void NCollection_UtfIterator<Type>::readUTF8()
{
  // unsigned arithmetic used
  unsigned char*      aPos         = (unsigned char*)myPosNext;
  const unsigned char aBytesToRead = UTF8_BYTES_MINUS_ONE[*aPos];
  myCharUtf32                      = 0;
  switch (aBytesToRead)
  {
    case 5:
      myCharUtf32 += *aPos++;
      myCharUtf32 <<= 6; // remember, illegal UTF-8
      [[fallthrough]];
    case 4:
      myCharUtf32 += *aPos++;
      myCharUtf32 <<= 6; // remember, illegal UTF-8
      [[fallthrough]];
    case 3:
      myCharUtf32 += *aPos++;
      myCharUtf32 <<= 6;
      [[fallthrough]];
    case 2:
      myCharUtf32 += *aPos++;
      myCharUtf32 <<= 6;
      [[fallthrough]];
    case 1:
      myCharUtf32 += *aPos++;
      myCharUtf32 <<= 6;
      [[fallthrough]];
    case 0:
      myCharUtf32 += *aPos++;
  }
  myCharUtf32 -= offsetsFromUTF8[aBytesToRead];
  myPosNext = (Type*)aPos;
}

//=================================================================================================

template <typename Type>
inline void NCollection_UtfIterator<Type>::readUTF16()
{
  char32_t aChar = *myPosNext++;
  // if we have the first half of the surrogate pair
  if (aChar >= UTF16_SURROGATE_HIGH_START && aChar <= UTF16_SURROGATE_HIGH_END)
  {
    const char32_t aChar2 = *myPosNext;
    // complete the surrogate pair
    if (aChar2 >= UTF16_SURROGATE_LOW_START && aChar2 <= UTF16_SURROGATE_LOW_END)
    {
      aChar = ((aChar - UTF16_SURROGATE_HIGH_START) << UTF16_SURROGATE_HIGH_SHIFT)
              + (aChar2 - UTF16_SURROGATE_LOW_START) + UTF16_SURROGATE_LOW_BASE;
      ++myPosNext;
    }
  }
  myCharUtf32 = aChar;
}

//=================================================================================================

template <typename Type>
inline int NCollection_UtfIterator<Type>::AdvanceBytesUtf8() const
{
  if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
  {
    // UTF-16 surrogate values are illegal in UTF-32
    return 0;
  }
  else if (myCharUtf32 < char32_t(0x80))
  {
    return 1;
  }
  else if (myCharUtf32 < char32_t(0x800))
  {
    return 2;
  }
  else if (myCharUtf32 < char32_t(0x10000))
  {
    return 3;
  }
  else if (myCharUtf32 <= UTF32_MAX_LEGAL)
  {
    return 4;
  }
  else
  {
    // illegal
    return 0;
  }
}

//=================================================================================================

template <typename Type>
inline char* NCollection_UtfIterator<Type>::GetUtf8(char* theBuffer) const
{
  // unsigned arithmetic used
  return (char*)GetUtf8((unsigned char*)theBuffer);
}

//=================================================================================================

template <typename Type>
inline unsigned char* NCollection_UtfIterator<Type>::GetUtf8(unsigned char* theBuffer) const
{
  char32_t aChar = myCharUtf32;
  if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
  {
    // UTF-16 surrogate values are illegal in UTF-32
    return theBuffer;
  }
  else if (myCharUtf32 < char32_t(0x80))
  {
    *theBuffer++ = static_cast<unsigned char>(aChar | UTF8_FIRST_BYTE_MARK[1]);
    return theBuffer;
  }
  else if (myCharUtf32 < char32_t(0x800))
  {
    *++theBuffer = static_cast<unsigned char>((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK);
    aChar >>= 6;
    *--theBuffer = static_cast<unsigned char>(aChar | UTF8_FIRST_BYTE_MARK[2]);
    return theBuffer + 2;
  }
  else if (myCharUtf32 < char32_t(0x10000))
  {
    theBuffer += 3;
    *--theBuffer = static_cast<unsigned char>((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK);
    aChar >>= 6;
    *--theBuffer = static_cast<unsigned char>((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK);
    aChar >>= 6;
    *--theBuffer = static_cast<unsigned char>(aChar | UTF8_FIRST_BYTE_MARK[3]);
    return theBuffer + 3;
  }
  else if (myCharUtf32 <= UTF32_MAX_LEGAL)
  {
    theBuffer += 4;
    *--theBuffer = static_cast<unsigned char>((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK);
    aChar >>= 6;
    *--theBuffer = static_cast<unsigned char>((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK);
    aChar >>= 6;
    *--theBuffer = static_cast<unsigned char>((aChar | UTF8_BYTE_MARK) & UTF8_BYTE_MASK);
    aChar >>= 6;
    *--theBuffer = static_cast<unsigned char>(aChar | UTF8_FIRST_BYTE_MARK[4]);
    return theBuffer + 4;
  }
  else
  {
    // illegal
    return theBuffer;
  }
}

//=================================================================================================

template <typename Type>
inline int NCollection_UtfIterator<Type>::AdvanceBytesUtf16() const
{
  return AdvanceCodeUnitsUtf16() * sizeof(char16_t);
}

//=================================================================================================

template <typename Type>
inline int NCollection_UtfIterator<Type>::AdvanceCodeUnitsUtf16() const
{
  if (myCharUtf32 <= UTF32_MAX_BMP) // target is a character <= 0xFFFF
  {
    // UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values
    if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
    {
      return 0;
    }
    else
    {
      return 1;
    }
  }
  else if (myCharUtf32 > UTF32_MAX_LEGAL)
  {
    // illegal
    return 0;
  }
  else
  {
    // target is a character in range 0xFFFF - 0x10FFFF
    // surrogate pair
    return 2;
  }
}

//=================================================================================================

template <typename Type>
inline char16_t* NCollection_UtfIterator<Type>::GetUtf16(char16_t* theBuffer) const
{
  if (myCharUtf32 <= UTF32_MAX_BMP) // target is a character <= 0xFFFF
  {
    // UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values
    if (myCharUtf32 >= UTF16_SURROGATE_HIGH_START && myCharUtf32 <= UTF16_SURROGATE_LOW_END)
    {
      return theBuffer;
    }
    else
    {
      *theBuffer++ = char16_t(myCharUtf32);
      return theBuffer;
    }
  }
  else if (myCharUtf32 > UTF32_MAX_LEGAL)
  {
    // illegal
    return theBuffer;
  }
  else
  {
    // surrogate pair
    char32_t aChar = myCharUtf32 - UTF16_SURROGATE_LOW_BASE;
    *theBuffer++   = char16_t((aChar >> UTF16_SURROGATE_HIGH_SHIFT) + UTF16_SURROGATE_HIGH_START);
    *theBuffer++   = char16_t((aChar & UTF16_SURROGATE_LOW_MASK) + UTF16_SURROGATE_LOW_START);
    return theBuffer;
  }
}

//=================================================================================================

template <typename Type>
inline char32_t* NCollection_UtfIterator<Type>::GetUtf32(char32_t* theBuffer) const
{
  *theBuffer++ = myCharUtf32;
  return theBuffer;
}