chromium/third_party/icu/source/common/ucnv_u16.cpp

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*  
**********************************************************************
*   Copyright (C) 2002-2015, International Business Machines
*   Corporation and others.  All Rights Reserved.
**********************************************************************
*   file name:  ucnv_u16.c
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2002jul01
*   created by: Markus W. Scherer
*
*   UTF-16 converter implementation. Used to be in ucnv_utf.c.
*/

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "unicode/ucnv.h"
#include "unicode/uversion.h"
#include "ucnv_bld.h"
#include "ucnv_cnv.h"
#include "cmemory.h"

enum { … };

U_CDECL_BEGIN
/*
 * The UTF-16 toUnicode implementation is also used for the Java-specific
 * "with BOM" variants of UTF-16BE and UTF-16LE.
 */
static void  U_CALLCONV
_UTF16ToUnicodeWithOffsets(UConverterToUnicodeArgs *pArgs,
                           UErrorCode *pErrorCode);

/* UTF-16BE ----------------------------------------------------------------- */

#if U_IS_BIG_ENDIAN
#define _UTF16PEFromUnicodeWithOffsets …
#else
#define _UTF16PEFromUnicodeWithOffsets …
#endif


static void  U_CALLCONV
_UTF16BEFromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
                               UErrorCode *pErrorCode) { … }

static void  U_CALLCONV
_UTF16BEToUnicodeWithOffsets(UConverterToUnicodeArgs *pArgs,
                             UErrorCode *pErrorCode) { … }

static UChar32  U_CALLCONV
_UTF16BEGetNextUChar(UConverterToUnicodeArgs *pArgs, UErrorCode *err) { … } 

static void  U_CALLCONV
_UTF16BEReset(UConverter *cnv, UConverterResetChoice choice) { … }

static void  U_CALLCONV
_UTF16BEOpen(UConverter *cnv,
             UConverterLoadArgs *pArgs,
             UErrorCode *pErrorCode) { … }

static const char *  U_CALLCONV
_UTF16BEGetName(const UConverter *cnv) { … }
U_CDECL_END

static const UConverterImpl _UTF16BEImpl= …;

static const UConverterStaticData _UTF16BEStaticData= …;


const UConverterSharedData _UTF16BEData= …;

/* UTF-16LE ----------------------------------------------------------------- */
U_CDECL_BEGIN
static void  U_CALLCONV
_UTF16LEFromUnicodeWithOffsets(UConverterFromUnicodeArgs *pArgs,
                               UErrorCode *pErrorCode) { … }

static void  U_CALLCONV
_UTF16LEToUnicodeWithOffsets(UConverterToUnicodeArgs *pArgs,
                             UErrorCode *pErrorCode) { … }

static UChar32  U_CALLCONV
_UTF16LEGetNextUChar(UConverterToUnicodeArgs *pArgs, UErrorCode *err) { … } 

static void  U_CALLCONV
_UTF16LEReset(UConverter *cnv, UConverterResetChoice choice) { … }

static void  U_CALLCONV
_UTF16LEOpen(UConverter *cnv,
             UConverterLoadArgs *pArgs,
             UErrorCode *pErrorCode) { … }

static const char *  U_CALLCONV
_UTF16LEGetName(const UConverter *cnv) { … }
U_CDECL_END

static const UConverterImpl _UTF16LEImpl= …;


static const UConverterStaticData _UTF16LEStaticData= …;


const UConverterSharedData _UTF16LEData= …;

/* UTF-16 (Detect BOM) ------------------------------------------------------ */

/*
 * Detect a BOM at the beginning of the stream and select UTF-16BE or UTF-16LE
 * accordingly.
 * This is a simpler version of the UTF-32 converter, with
 * fewer states for shorter BOMs.
 *
 * State values:
 * 0    initial state
 * 1    saw first byte
 * 2..5 -
 * 6..7 see _UTF16ToUnicodeWithOffsets() comments in state 1
 * 8    UTF-16BE mode
 * 9    UTF-16LE mode
 *
 * During detection: state==number of initial bytes seen so far.
 *
 * On output, emit U+FEFF as the first code point.
 *
 * Variants:
 * - UTF-16,version=1 (Java "Unicode" encoding) treats a missing BOM as an error.
 * - UTF-16BE,version=1 (Java "UnicodeBig" encoding) and
 *   UTF-16LE,version=1 (Java "UnicodeLittle" encoding) treat a reverse BOM as an error.
 */
U_CDECL_BEGIN
static void  U_CALLCONV
_UTF16Reset(UConverter *cnv, UConverterResetChoice choice) { … }
U_CDECL_END
extern const UConverterSharedData _UTF16v2Data;
U_CDECL_BEGIN
static void U_CALLCONV
_UTF16Open(UConverter *cnv,
           UConverterLoadArgs *pArgs,
           UErrorCode *pErrorCode) { … }

static const char *  U_CALLCONV
_UTF16GetName(const UConverter *cnv) { … }
U_CDECL_END
extern const UConverterSharedData _UTF16Data;

static inline bool IS_UTF16BE(const UConverter *cnv) { … }

static inline bool IS_UTF16LE(const UConverter *cnv) { … }

static inline bool IS_UTF16(const UConverter *cnv) { … }

U_CDECL_BEGIN
static void U_CALLCONV
_UTF16ToUnicodeWithOffsets(UConverterToUnicodeArgs *pArgs,
                           UErrorCode *pErrorCode) { … }

static UChar32 U_CALLCONV
_UTF16GetNextUChar(UConverterToUnicodeArgs *pArgs,
                   UErrorCode *pErrorCode) { … }
U_CDECL_END

static const UConverterImpl _UTF16Impl = …;

static const UConverterStaticData _UTF16StaticData = …;

const UConverterSharedData _UTF16Data = …;

static const UConverterImpl _UTF16v2Impl = …;

static const UConverterStaticData _UTF16v2StaticData = …;

const UConverterSharedData _UTF16v2Data = …;

#endif