UTS6710/aps/include/middleware/common/unicode/unicode.h

/*! \addtogroup UNICODE
 * @{
 */
/*!
*
* @file		unicode.h
*
* @brief	This file specifies the Unicode translation APIs
*
* @note		Copyright (c) 2009 Sunplus Technology Co., Ltd. \n
*			All rights reserved.
*
* @author
*
******************************************************************************/
#ifndef __UNICODE_CODE_PAGE_H__
#define __UNICODE_CODE_PAGE_H__

/******************************************************************************/
/*!
 * @brief	Enumeration of all supported Unicode code pages
 *
 * @note	Because codepages BIG5 and GB2312 can be replaced with CP950 and CP936,
 * 			BIG5 and GB2312 codepages are removed.
 * 			But uiDesign tool has used name "BIG5" and "GB2312" in its codebase,
 * 			it is not suggested to remove these two codepage name here. (by mandy.wu)
 * 			Everyone is still able to use these 2 codepages, but it will be transferred
 * 			to call CP950 and CP936 translations inside UNI_Utf162Chr() and UNI_Chr2Utf16() APIs.
 * 			-- nicholas.lin 09-09-09
 *******************************************************************************/
typedef enum
{
	CP_437 = 0, // 0
	CP_932, // 1
	CP_936, // 2
	CP_950, // 3
	CP_1250, // 4
	CP_1251, // 5
	CP_1252, // 6
	CP_1253, // 7
	CP_1254, // 8
	CP_1255, // 9
	CP_1256, // 10
	CP_1257, // 11
	CP_1258, // 12
	CP_8256, // 13
	CP_8257, // 14
	CP_8258, // 15
	BIG5, // 16
	GB2312, // 17
	KSC5601, // 18
	ISO6937, // 19
	ISO8859_1, // 20
	ISO8859_2, // 21
	ISO8859_3, // 22
	ISO8859_4, // 23
	ISO8859_5, // 24
	ISO8859_6, // 25
	ISO8859_7, // 26
	ISO8859_8, // 27
	ISO8859_9, // 28
	ISO8859_10, // 29
	ISO8859_11, // 30
	ISO8859_12, // 31
	ISO8859_13, // 32
	ISO8859_14, // 33
	ISO8859_15, // 34
	ISO8859_16, // 35
	UTF8, // 36
	UNICODE, // 37
	UTF16_LE, //38
	UTF16_BE, //39
	CP_874,   // 40
	CODE_PAGE_MAX //ENCODETYPE_AUTO
}UNICODE_SUPPORT_CODE_PAGE;

/*!
 * @defgroup Unicode Unicode character and string translation APIs
 * @brief Unicode Unicode character and string translation APIs
 * @{
*/
/******************************************************************************/
/*!
 * @brief	Translation from unicode(UTF-16) to native code
 *
 * @param	codepage native code page
 * @param	uni source unicode character
 * @param	out output native code character
 *
 * @return	@a length of output native code character in bytes
 * @return	@a -1 on failure
 *
 * @note	Use UINT16 array to store unicode strings instead of UINT8 array
 *******************************************************************************/
INT32 UNI_Utf162Chr(const UINT32 codepage, const UINT16 uni, UINT8 *out);

/******************************************************************************/
/*!
 * @brief	Translation from native code to unicode(UTF-16)
 *
 * @param	codepage native code page
 * @param	rawchr source native code character
 * @param	uni output unicode character
 *
 * @return	@a length of output unicodecode character in bytes
 * @return	@a -1 on failure
 *
 * @note	Use UINT16 array to store unicode strings instead of UINT8 array
 *******************************************************************************/
INT32 UNI_Chr2Utf16(const UINT32 codepage, const UINT8 *rawchr, UINT16 *uni);

/******************************************************************************/
/*!
 * @brief	Translate a UTF-16 coded string to UTF-8 coded string
 *
 * @param	src pointer of source UTF-16 coded string
 * @param	srcLen string length of source UTF-16 coded string in dual-bytes.
 * @param	dest pointer to destination UTF-8 coded string
 * @param	destLen return value of string length of destination UTF-8 coded string in bytes
 *
 * @return	@a 0 on success
 * @return	@a -1 on failure
 *
 * @note	Use UINT16 array to store UTF-16 strings instead of UINT8 array;
 * @note	currently we can only process 16-bit length UTF-16 string;
 *******************************************************************************/
INT32 UNI_Utf16S2Utf8S(const UINT16 *src, const UINT32 srcLen, UINT8 *dest, UINT32 *destLen);

/******************************************************************************/
/*!
 * @brief	Translate a UTF-8 coded string to UTF-16 coded string
 *
 * @param	src pointer of source UTF-8 coded string
 * @param	srcLen string length of source UTF-8 coded string in bytes.
 * @param	dest pointer to destination UTF-16 coded string
 * @param	destLen return value of string length of destination UTF-16 coded string in dual-bytes
 *
 * @return	@a 0 on success
 * @return	@a -1 on failure
 *
 * @note	Use UINT16 array to store UTF-16 strings instead of UINT8 array;
 * @note	currently we can only process 16-bit length UTF-16 string;
 *******************************************************************************/
INT32 UNI_Utf8S2Utf16S(const UINT8 *src, const UINT32 srcLen, UINT16 *dest, UINT32 *destLen);

/******************************************************************************/
/*!
 * @brief	Translation from UTF-16 character to UTF-8 character
 *
 * @param	utf16 source UTF-16 character
 * @param	utf8 output UTF-8 character
 *
 * @return	@a length of output UTF-8 character in bytes
 * @return	@a -1 on failure
 *
 * @note	Use UINT16 array to store UTF-16 strings instead of UINT8 array
 *******************************************************************************/
INT32 UNI_Utf162Utf8(const UINT16 utf16, UINT8 *utf8);

/******************************************************************************/
/*!
 * @brief	Translation from UTF-8 character to UTF-16 character
 *
 * @param	utf8 source UTF-8 character
 * @param	utf16 output UTF-16 character
 *
 * @return	@a length of source UTF-8 character in bytes
 * @return	@a -1 on failure
 *
 * @note	Use UINT16 array to store UTF-16 strings instead of UINT8 array
 *******************************************************************************/
INT32 UNI_Utf82Utf16(const UINT8 *utf8, UINT16 *utf16);

#ifdef CONFIG_SUPPORT_CHARSETDET
/******************************************************************************/
/*!
 * @brief	Guess a codepage by a raw character stream
 *
 * @param	rawchr raw character stream
 * @param	size of raw character stream
 *
 * @return	guessed code page number
 *******************************************************************************/
UINT32 UNI_GuessCodePage(const UINT8 *rawchr, UINT32 size);
UINT32 UNI_FontType2CodePage(UINT32 font);
#endif

UINT8* UNI_StringToUtf8(UINT32 codepage, UINT8* string_ptr, INT32* len_ptr, bool skip_ctrl);

void UNI_GetUTF8EncodeSize(UINT8 *pString, UINT16 *pEncodeSize);

UINT8* UNI_SetUTF8Position(UINT8 *pString, INT32 *pLen, UINT32 *pPosition);
INT32 UNI_GetCodePage(UINT32 *pCodePage, UINT8 *rawchr, INT32 *size);
/*! @} end of defgroup Unicode */

#endif // __UNICODE_CODE_PAGE_H__

/*! @} end of addtogroup UNICODE */