• <ins id="pjuwb"></ins>
    <blockquote id="pjuwb"><pre id="pjuwb"></pre></blockquote>
    <noscript id="pjuwb"></noscript>
          <sup id="pjuwb"><pre id="pjuwb"></pre></sup>
            <dd id="pjuwb"></dd>
            <abbr id="pjuwb"></abbr>

            Kisser Leon

            這個kisser不太冷
            posts - 100, comments - 102, trackbacks - 0, articles - 0

            ConvertUTF.c

            Posted on 2007-03-08 16:02 kk 閱讀(3323) 評論(0)  編輯 收藏 引用 所屬分類: IT
            UTF8和UTF16和UTF32之間的相互轉化

            /* ================================================================ */
            /*
            File:?? ?ConvertUTF.C
            Author: Mark E. Davis
            Copyright (C) 1994 Taligent, Inc. All rights reserved.

            This code is copyrighted. Under the copyright laws, this code may not
            be copied, in whole or part, without prior written consent of Taligent.

            Taligent grants the right to use or reprint this code as long as this
            ENTIRE copyright notice is reproduced in the code or reproduction.
            The code is provided AS-IS, AND TALIGENT DISCLAIMS ALL WARRANTIES,
            EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO IMPLIED
            WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.? IN
            NO EVENT WILL TALIGENT BE LIABLE FOR ANY DAMAGES WHATSOEVER (INCLUDING,
            WITHOUT LIMITATION, DAMAGES FOR LOSS OF BUSINESS PROFITS, BUSINESS
            INTERRUPTION, LOSS OF BUSINESS INFORMATION, OR OTHER PECUNIARY
            LOSS) ARISING OUT OF THE USE OR INABILITY TO USE THIS CODE, EVEN
            IF TALIGENT HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
            BECAUSE SOME STATES DO NOT ALLOW THE EXCLUSION OR LIMITATION OF
            LIABILITY FOR CONSEQUENTIAL OR INCIDENTAL DAMAGES, THE ABOVE
            LIMITATION MAY NOT APPLY TO YOU.

            RESTRICTED RIGHTS LEGEND: Use, duplication, or disclosure by the
            government is subject to restrictions as set forth in subparagraph
            (c)(l)(ii) of the Rights in Technical Data and Computer Software
            clause at DFARS 252.227-7013 and FAR 52.227-19.

            This code may be protected by one or more U.S. and International
            Patents.

            TRADEMARKS: Taligent and the Taligent Design Mark are registered
            trademarks of Taligent, Inc.
            */
            /* ================================================================ */

            #include "ConvertUTF.h"

            /* ================================================================ */

            const int halfShift?? ??? ??? ??? ?= 10;
            const UCS4 halfBase?? ??? ??? ??? ?= 0x0010000UL;
            const UCS4 halfMask?? ??? ??? ??? ?= 0x3FFUL;
            const UCS4 kSurrogateHighStart?? ?= 0xD800UL;
            const UCS4 kSurrogateHighEnd?? ?= 0xDBFFUL;
            const UCS4 kSurrogateLowStart?? ?= 0xDC00UL;
            const UCS4 kSurrogateLowEnd?? ??? ?= 0xDFFFUL;

            /* ================================================================ */

            ConversionResult?? ?ConvertUCS4toUTF16 (
            ?? ??? ?UCS4** sourceStart, const UCS4* sourceEnd,
            ?? ??? ?UTF16** targetStart, const UTF16* targetEnd) {
            ?? ?ConversionResult result = kUTFConversionOK;
            ?? ?register UCS4* source = *sourceStart;
            ?? ?register UTF16* target = *targetStart;
            ?? ?while (source < sourceEnd) {
            ?? ??? ?register UCS4 ch;
            ?? ??? ?if (target >= targetEnd) {
            ?? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ?};
            ?? ??? ?ch = *source++;
            ?? ??? ?if (ch <= kMaximumUCS2) {
            ?? ??? ??? ?*target++ = ch;
            ?? ??? ?} else if (ch > kMaximumUTF16) {
            ?? ??? ??? ?*target++ = kReplacementCharacter;
            ?? ??? ?} else {
            ?? ??? ??? ?if (target + 1 >= targetEnd) {
            ?? ??? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ??? ?};
            ?? ??? ??? ?ch -= halfBase;
            ?? ??? ??? ?*target++ = (ch >> halfShift) + kSurrogateHighStart;
            ?? ??? ??? ?*target++ = (ch & halfMask) + kSurrogateLowStart;
            ?? ??? ?};
            ?? ?};
            ?? ?*sourceStart = source;
            ?? ?*targetStart = target;
            ?? ?return result;
            };

            /* ================================================================ */

            ConversionResult?? ?ConvertUTF16toUCS4 (
            ?? ??? ?UTF16** sourceStart, UTF16* sourceEnd,
            ?? ??? ?UCS4** targetStart, const UCS4* targetEnd) {
            ?? ?ConversionResult result = kUTFConversionOK;
            ?? ?register UTF16* source = *sourceStart;
            ?? ?register UCS4* target = *targetStart;
            ?? ?while (source < sourceEnd) {
            ?? ??? ?register UCS4 ch;
            ?? ??? ?ch = *source++;
            ?? ??? ?if (ch >= kSurrogateHighStart && ch <= kSurrogateHighEnd && source < sourceEnd) {
            ?? ??? ??? ?register UCS4 ch2 = *source;
            ?? ??? ??? ?if (ch2 >= kSurrogateLowStart && ch2 <= kSurrogateLowEnd) {
            ?? ??? ??? ??? ?ch = ((ch - kSurrogateHighStart) << halfShift)
            ?? ??? ??? ??? ??? ?+ (ch2 - kSurrogateLowStart) + halfBase;
            ?? ??? ??? ??? ?++source;
            ?? ??? ??? ?};
            ?? ??? ?};
            ?? ??? ?if (target >= targetEnd) {
            ?? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ?};
            ?? ??? ?*target++ = ch;
            ?? ?};
            ?? ?*sourceStart = source;
            ?? ?*targetStart = target;
            ?? ?return result;
            };

            /* ================================================================ */

            UCS4 offsetsFromUTF8[6] =?? ?{0x00000000UL, 0x00003080UL, 0x000E2080UL,
            ?? ??? ??? ??? ??? ? ?? ? ?? ? 0x03C82080UL, 0xFA082080UL, 0x82082080UL};
            char bytesFromUTF8[256] = {
            ?? ?0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
            ?? ?0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
            ?? ?0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
            ?? ?0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
            ?? ?0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
            ?? ?0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
            ?? ?1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
            ?? ?2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5};

            UTF8 firstByteMark[7] = {0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC};

            /* ================================================================ */
            /*?? ?This code is similar in effect to making successive calls on the
            mbtowc and wctomb routines in FSS-UTF. However, it is considerably
            different in code:
            * it is adapted to be consistent with UTF16,
            * the interface converts a whole buffer to avoid function-call overhead
            * constants have been gathered.
            * loops & conditionals have been removed as much as possible for
            efficiency, in favor of drop-through switch statements.
            */

            /* ================================================================ */
            ConversionResult?? ?ConvertUTF16toUTF8 (
            ?? ??? ?UTF16** sourceStart, const UTF16* sourceEnd,
            ?? ??? ?UTF8** targetStart, const UTF8* targetEnd)
            {
            ?? ?ConversionResult result = kUTFConversionOK;
            ?? ?register UTF16* source = *sourceStart;
            ?? ?register UTF8* target = *targetStart;
            ?? ?while (source < sourceEnd) {
            ?? ??? ?register UCS4 ch;
            ?? ??? ?register unsigned short bytesToWrite = 0;
            ?? ??? ?register const UCS4 byteMask = 0xBF;
            ?? ??? ?register const UCS4 byteMark = 0x80;
            ?? ??? ?ch = *source++;
            ?? ??? ?if (ch >= kSurrogateHighStart && ch <= kSurrogateHighEnd
            ?? ??? ??? ??? ?&& source < sourceEnd) {
            ?? ??? ??? ?register UCS4 ch2 = *source;
            ?? ??? ??? ?if (ch2 >= kSurrogateLowStart && ch2 <= kSurrogateLowEnd) {
            ?? ??? ??? ??? ?ch = ((ch - kSurrogateHighStart) << halfShift)
            ?? ??? ??? ??? ??? ?+ (ch2 - kSurrogateLowStart) + halfBase;
            ?? ??? ??? ??? ?++source;
            ?? ??? ??? ?};
            ?? ??? ?};
            ?? ??? ?if (ch < 0x80) {?? ??? ??? ??? ?bytesToWrite = 1;
            ?? ??? ?} else if (ch < 0x800) {?? ??? ?bytesToWrite = 2;
            ?? ??? ?} else if (ch < 0x10000) {?? ??? ?bytesToWrite = 3;
            ?? ??? ?} else if (ch < 0x200000) {?? ??? ?bytesToWrite = 4;
            ?? ??? ?} else if (ch < 0x4000000) {?? ?bytesToWrite = 5;
            ?? ??? ?} else if (ch <= kMaximumUCS4){?? ?bytesToWrite = 6;
            ?? ??? ?} else {?? ??? ??? ??? ??? ??? ?bytesToWrite = 2;
            ?? ??? ??? ??? ??? ??? ??? ??? ??? ??? ?ch = kReplacementCharacter;
            ?? ??? ?}; /* I wish there were a smart way to avoid this conditional */
            ?? ??? ?
            ?? ??? ?target += bytesToWrite;
            ?? ??? ?if (target > targetEnd) {
            ?? ??? ??? ?target -= bytesToWrite; result = kUTFConversionTargetExhausted; break;
            ?? ??? ?};
            ?? ??? ?switch (bytesToWrite) {?? ?/* note: code falls through cases! */
            ?? ??? ??? ?case 6:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 5:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 4:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 3:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 2:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 1:?? ?*--target =? ch | firstByteMark[bytesToWrite];
            ?? ??? ?};
            ?? ??? ?target += bytesToWrite;
            ?? ?};
            ?? ?*sourceStart = source;
            ?? ?*targetStart = target;
            ?? ?return result;
            };

            /* ================================================================ */

            ConversionResult?? ?ConvertUTF8toUTF16 (
            ?? ??? ?UTF8** sourceStart, const UTF8* sourceEnd,
            ?? ??? ?UTF16** targetStart, const UTF16* targetEnd)
            {
            ?? ?ConversionResult result = kUTFConversionOK;
            ?? ?register UTF8* source = *sourceStart;
            ?? ?register UTF16* target = *targetStart;
            ?? ?while (source < sourceEnd) {
            ?? ??? ?register UCS4 ch = 0;
            ?? ??? ?register unsigned short extraBytesToWrite = bytesFromUTF8[*source];
            ?? ??? ?if (source + extraBytesToWrite > sourceEnd) {
            ?? ??? ??? ?result = kUTFConversionSourceExhausted; break;
            ?? ??? ?};
            ?? ??? ?switch(extraBytesToWrite) {?? ?/* note: code falls through cases! */
            ?? ??? ??? ?case 5:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 4:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 3:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 2:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 1:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 0:?? ?ch += *source++;
            ?? ??? ?};
            ?? ??? ?ch -= offsetsFromUTF8[extraBytesToWrite];

            ?? ??? ?if (target >= targetEnd) {
            ?? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ?};
            ?? ??? ?if (ch <= kMaximumUCS2) {
            ?? ??? ??? ?*target++ = ch;
            ?? ??? ?} else if (ch > kMaximumUTF16) {
            ?? ??? ??? ?*target++ = kReplacementCharacter;
            ?? ??? ?} else {
            ?? ??? ??? ?if (target + 1 >= targetEnd) {
            ?? ??? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ??? ?};
            ?? ??? ??? ?ch -= halfBase;
            ?? ??? ??? ?*target++ = (ch >> halfShift) + kSurrogateHighStart;
            ?? ??? ??? ?*target++ = (ch & halfMask) + kSurrogateLowStart;
            ?? ??? ?};
            ?? ?};
            ?? ?*sourceStart = source;
            ?? ?*targetStart = target;
            ?? ?return result;
            };

            /* ================================================================ */
            ConversionResult?? ?ConvertUCS4toUTF8 (
            ?? ??? ?UCS4** sourceStart, const UCS4* sourceEnd,
            ?? ??? ?UTF8** targetStart, const UTF8* targetEnd)
            {
            ?? ?ConversionResult result = kUTFConversionOK;
            ?? ?register UCS4* source = *sourceStart;
            ?? ?register UTF8* target = *targetStart;
            ?? ?while (source < sourceEnd) {
            ?? ??? ?register UCS4 ch;
            ?? ??? ?register unsigned short bytesToWrite = 0;
            ?? ??? ?register const UCS4 byteMask = 0xBF;
            ?? ??? ?register const UCS4 byteMark = 0x80;
            ?? ??? ?ch = *source++;
            ?? ??? ?if (ch >= kSurrogateHighStart && ch <= kSurrogateHighEnd
            ?? ??? ??? ??? ?&& source < sourceEnd) {
            ?? ??? ??? ?register UCS4 ch2 = *source;
            ?? ??? ??? ?if (ch2 >= kSurrogateLowStart && ch2 <= kSurrogateLowEnd) {
            ?? ??? ??? ??? ?ch = ((ch - kSurrogateHighStart) << halfShift)
            ?? ??? ??? ??? ??? ?+ (ch2 - kSurrogateLowStart) + halfBase;
            ?? ??? ??? ??? ?++source;
            ?? ??? ??? ?};
            ?? ??? ?};
            ?? ??? ?if (ch < 0x80) {?? ??? ??? ??? ?bytesToWrite = 1;
            ?? ??? ?} else if (ch < 0x800) {?? ??? ?bytesToWrite = 2;
            ?? ??? ?} else if (ch < 0x10000) {?? ??? ?bytesToWrite = 3;
            ?? ??? ?} else if (ch < 0x200000) {?? ??? ?bytesToWrite = 4;
            ?? ??? ?} else if (ch < 0x4000000) {?? ?bytesToWrite = 5;
            ?? ??? ?} else if (ch <= kMaximumUCS4){?? ?bytesToWrite = 6;
            ?? ??? ?} else {?? ??? ??? ??? ??? ??? ?bytesToWrite = 2;
            ?? ??? ??? ??? ??? ??? ??? ??? ??? ??? ?ch = kReplacementCharacter;
            ?? ??? ?}; /* I wish there were a smart way to avoid this conditional */
            ?? ??? ?
            ?? ??? ?target += bytesToWrite;
            ?? ??? ?if (target > targetEnd) {
            ?? ??? ??? ?target -= bytesToWrite; result = kUTFConversionTargetExhausted; break;
            ?? ??? ?};
            ?? ??? ?switch (bytesToWrite) {?? ?/* note: code falls through cases! */
            ?? ??? ??? ?case 6:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 5:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 4:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 3:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 2:?? ?*--target = (ch | byteMark) & byteMask; ch >>= 6;
            ?? ??? ??? ?case 1:?? ?*--target =? ch | firstByteMark[bytesToWrite];
            ?? ??? ?};
            ?? ??? ?target += bytesToWrite;
            ?? ?};
            ?? ?*sourceStart = source;
            ?? ?*targetStart = target;
            ?? ?return result;
            };

            /* ================================================================ */

            ConversionResult?? ?ConvertUTF8toUCS4 (
            ?? ??? ?UTF8** sourceStart, const UTF8* sourceEnd,
            ?? ??? ?UCS4** targetStart, const UCS4* targetEnd)
            {
            ?? ?ConversionResult result = kUTFConversionOK;
            ?? ?register UTF8* source = *sourceStart;
            ?? ?register UCS4* target = *targetStart;
            ?? ?while (source < sourceEnd) {
            ?? ??? ?register UCS4 ch = 0;
            ?? ??? ?register unsigned short extraBytesToWrite = bytesFromUTF8[*source];
            ?? ??? ?if (source + extraBytesToWrite > sourceEnd) {
            ?? ??? ??? ?result = kUTFConversionSourceExhausted; break;
            ?? ??? ?};
            ?? ??? ?switch(extraBytesToWrite) {?? ?/* note: code falls through cases! */
            ?? ??? ??? ?case 5:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 4:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 3:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 2:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 1:?? ?ch += *source++; ch <<= 6;
            ?? ??? ??? ?case 0:?? ?ch += *source++;
            ?? ??? ?};
            ?? ??? ?ch -= offsetsFromUTF8[extraBytesToWrite];

            ?? ??? ?if (target >= targetEnd) {
            ?? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ?};
            ?? ??? ?if (ch <= kMaximumUCS2) {
            ?? ??? ??? ?*target++ = ch;
            ?? ??? ?} else if (ch > kMaximumUCS4) {
            ?? ??? ??? ?*target++ = kReplacementCharacter;
            ?? ??? ?} else {
            ?? ??? ??? ?if (target + 1 >= targetEnd) {
            ?? ??? ??? ??? ?result = kUTFConversionTargetExhausted; break;
            ?? ??? ??? ?};
            ?? ??? ??? ?ch -= halfBase;
            ?? ??? ??? ?*target++ = (ch >> halfShift) + kSurrogateHighStart;
            ?? ??? ??? ?*target++ = (ch & halfMask) + kSurrogateLowStart;
            ?? ??? ?};
            ?? ?};
            ?? ?*sourceStart = source;
            ?? ?*targetStart = target;
            ?? ?return result;
            };

            日韩精品久久久肉伦网站 | 久久久久亚洲Av无码专| 久久亚洲美女精品国产精品| 亚洲中文字幕久久精品无码APP| 久久九九兔免费精品6| 久久婷婷国产综合精品| 久久九九青青国产精品| 久久精品国产一区二区三区不卡| 一级做a爰片久久毛片毛片| 久久久久久精品免费免费自慰| 久久成人影院精品777| 国产亚洲成人久久| 99久久99久久精品国产片果冻| 国内精品久久九九国产精品| 亚洲国产精品成人久久蜜臀 | 99久久精品免费看国产| 欧美黑人激情性久久| 久久美女人爽女人爽| 亚洲午夜久久久久久久久久| 大蕉久久伊人中文字幕| 人妻少妇久久中文字幕| 亚洲人成电影网站久久| 久久99亚洲综合精品首页 | 国产成人精品综合久久久| 狠狠色丁香婷婷综合久久来| 人妻少妇久久中文字幕一区二区 | 亚洲午夜久久久| 久久av高潮av无码av喷吹| 国产精品久久网| 99久久精品费精品国产一区二区| 香蕉久久夜色精品国产2020| 久久综合久久性久99毛片| 久久久久久国产精品无码下载| 久久精品国产久精国产| 丰满少妇高潮惨叫久久久| 青青草原精品99久久精品66| 一本久道久久综合狠狠爱| 国产精品久久婷婷六月丁香| 免费一级做a爰片久久毛片潮| 久久精品成人一区二区三区| 久久93精品国产91久久综合|