nuclear@1: /************************************************************************************
nuclear@1: 
nuclear@1: PublicHeader:   OVR.h
nuclear@1: Filename    :   OVR_UTF8Util.h
nuclear@1: Content     :   UTF8 Unicode character encoding/decoding support
nuclear@1: Created     :   September 19, 2012
nuclear@1: Notes       : 
nuclear@1: 
nuclear@1: Copyright   :   Copyright 2012 Oculus VR, Inc. All Rights reserved.
nuclear@1: 
nuclear@1: Use of this software is subject to the terms of the Oculus license
nuclear@1: agreement provided at the time of installation or download, or which
nuclear@1: otherwise accompanies this software in either electronic or hard copy form.
nuclear@1: 
nuclear@1: ************************************************************************************/
nuclear@1: 
nuclear@1: #ifndef OVR_UTF8Util_h
nuclear@1: #define OVR_UTF8Util_h
nuclear@1: 
nuclear@1: #include "OVR_Types.h"
nuclear@1: 
nuclear@1: namespace OVR { namespace UTF8Util {
nuclear@1: 
nuclear@1: //-----------------------------------------------------------------------------------
nuclear@1: 
nuclear@1: // *** UTF8 string length and indexing.
nuclear@1: 
nuclear@1: // Determines the length of UTF8 string in characters.
nuclear@1: // If source length is specified (in bytes), null 0 character is counted properly.
nuclear@1: SPInt    OVR_STDCALL GetLength(const char* putf8str, SPInt length = -1);
nuclear@1: 
nuclear@1: // Gets a decoded UTF8 character at index; you can access up to the index returned
nuclear@1: // by GetLength. 0 will be returned for out of bounds access.
nuclear@1: UInt32   OVR_STDCALL GetCharAt(SPInt index, const char* putf8str, SPInt length = -1);
nuclear@1: 
nuclear@1: // Converts UTF8 character index into byte offset.
nuclear@1: // -1 is returned if index was out of bounds.
nuclear@1: SPInt    OVR_STDCALL GetByteIndex(SPInt index, const char* putf8str, SPInt length = -1);
nuclear@1: 
nuclear@1: 
nuclear@1: // *** 16-bit Unicode string Encoding/Decoding routines.
nuclear@1: 
nuclear@1: // Determines the number of bytes necessary to encode a string.
nuclear@1: // Does not count the terminating 0 (null) character.
nuclear@1: SPInt    OVR_STDCALL GetEncodeStringSize(const wchar_t* pchar, SPInt length = -1);
nuclear@1: 
nuclear@1: // Encodes a unicode (UCS-2 only) string into a buffer. The size of buffer must be at
nuclear@1: // least GetEncodeStringSize() + 1.
nuclear@1: void     OVR_STDCALL EncodeString(char *pbuff, const wchar_t* pchar, SPInt length = -1);
nuclear@1: 
nuclear@1: // Decode UTF8 into a wchar_t buffer. Must have GetLength()+1 characters available.
nuclear@1: // Characters over 0xFFFF are replaced with 0xFFFD.
nuclear@1: // Returns the length of resulting string (number of characters)
nuclear@1: UPInt    OVR_STDCALL DecodeString(wchar_t *pbuff, const char* putf8str, SPInt bytesLen = -1);
nuclear@1: 
nuclear@1: 
nuclear@1: // *** Individual character Encoding/Decoding.
nuclear@1: 
nuclear@1: // Determined the number of bytes necessary to encode a UCS character.
nuclear@1: int      OVR_STDCALL GetEncodeCharSize(UInt32 ucsCharacter);
nuclear@1: 
nuclear@1: // Encodes the given UCS character into the given UTF-8 buffer.
nuclear@1: // Writes the data starting at buffer[offset], and 
nuclear@1: // increments offset by the number of bytes written.
nuclear@1: // May write up to 6 bytes, so make sure there's room in the buffer
nuclear@1: void     OVR_STDCALL EncodeChar(char* pbuffer, SPInt* poffset, UInt32 ucsCharacter);
nuclear@1: 
nuclear@1: // Return the next Unicode character in the UTF-8 encoded buffer.
nuclear@1: // Invalid UTF-8 sequences produce a U+FFFD character as output.
nuclear@1: // Advances *utf8_buffer past the character returned. Pointer advance
nuclear@1: // occurs even if the terminating 0 character is hit, since that allows
nuclear@1: // strings with middle '\0' characters to be supported.
nuclear@1: UInt32   OVR_STDCALL DecodeNextChar_Advance0(const char** putf8Buffer);
nuclear@1: 
nuclear@1: // Safer version of DecodeNextChar, which doesn't advance pointer if
nuclear@1: // null character is hit.
nuclear@1: inline UInt32 DecodeNextChar(const char** putf8Buffer)
nuclear@1: {
nuclear@1:     UInt32 ch = DecodeNextChar_Advance0(putf8Buffer);
nuclear@1:     if (ch == 0)
nuclear@1:         (*putf8Buffer)--;
nuclear@1:     return ch;
nuclear@1: }
nuclear@1: 
nuclear@1: 
nuclear@1: }} // OVR::UTF8Util
nuclear@1: 
nuclear@1: #endif