convert_utf.c

来自「SumatraPDF是一款小型开源的pdf阅读工具。虽然玲珑小巧（只有800多K」· C语言 代码 · 共 534 行 · 第 1/2 页

/*
 * Copyright 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.
 */

/* ---------------------------------------------------------------------

Conversions between UTF32, UTF-16, and UTF-8. Source code file.
Author: Mark E. Davis, 1994.
Rev History: Rick McGowan, fixes & updates May 2001.
Sept 2001: fixed const & error conditions per
mods suggested by S. Parent & A. Lillich.
June 2002: Tim Dodd added detection and handling of incomplete
source sequences, enhanced error detection, added casts
to eliminate compiler warnings.
July 2003: slight mods to back out aggressive FFFE detection.
Jan 2004: updated switches in from-UTF8 conversions.
Oct 2004: updated to use UNI_MAX_LEGAL_UTF32 in UTF-32 conversions.

See the header file "ConvertUTF.h" for complete documentation.

------------------------------------------------------------------------ */


#include "convert_UTF.h"
#ifdef CVTUTF_DEBUG
#include <stdio.h>
#endif

static const int halfShift  = 10; /* used for shifting by 10 bits */

static const UTF32 halfBase = 0x0010000UL;
static const UTF32 halfMask = 0x3FFUL;

#define UNI_SUR_HIGH_START  (UTF32)0xD800
#define UNI_SUR_HIGH_END    (UTF32)0xDBFF
#define UNI_SUR_LOW_START   (UTF32)0xDC00
#define UNI_SUR_LOW_END     (UTF32)0xDFFF
#define false	   0
#define true	    1

/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF32toUTF16 (const UTF32** sourceStart, const UTF32* sourceEnd,
                                      UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
  ConversionResult result = conversionOK;
  const UTF32* source = *sourceStart;
  UTF16* target = *targetStart;
  while (source < sourceEnd) {
    UTF32 ch;
    if (target >= targetEnd) {
	    result = targetExhausted; break;
    }
    ch = *source++;
    if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
	    /* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
	    if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
        if (flags == strictConversion) {
          --source; /* return to the illegal value itself */
          result = sourceIllegal;
          break;
        } else {
          *target++ = UNI_REPLACEMENT_CHAR;
        }
	    } else {
        *target++ = (UTF16)ch; /* normal case */
	    }
    } else if (ch > UNI_MAX_LEGAL_UTF32) {
	    if (flags == strictConversion) {
        result = sourceIllegal;
	    } else {
        *target++ = UNI_REPLACEMENT_CHAR;
	    }
    } else {
	    /* target is a character in range 0xFFFF - 0x10FFFF. */
	    if (target + 1 >= targetEnd) {
        --source; /* Back up source pointer! */
        result = targetExhausted; break;
	    }
	    ch -= halfBase;
	    *target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
	    *target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
    }
  }
*sourceStart = source;
*targetStart = target;
return result;
}

/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF16toUTF32 (const UTF16** sourceStart, const UTF16* sourceEnd,
                                      UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
  ConversionResult result = conversionOK;
  const UTF16* source = *sourceStart;
  UTF32* target = *targetStart;
  UTF32 ch, ch2;
  while (source < sourceEnd) {
    const UTF16* oldSource = source; /*  In case we have to back up because of target overflow. */
    ch = *source++;
    /* If we have a surrogate pair, convert to UTF32 first. */
    if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
	    /* If the 16 bits following the high surrogate are in the source buffer... */
	    if (source < sourceEnd) {
        ch2 = *source;
        /* If it's a low surrogate, convert to UTF32. */
        if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
          ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
          + (ch2 - UNI_SUR_LOW_START) + halfBase;
          ++source;
        } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
          --source; /* return to the illegal value itself */
          result = sourceIllegal;
          break;
        }
	    } else { /* We don't have the 16 bits following the high surrogate. */
        --source; /* return to the high surrogate */
        result = sourceExhausted;
        break;
	    }
    } else if (flags == strictConversion) {
	    /* UTF-16 surrogate values are illegal in UTF-32 */
	    if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
        --source; /* return to the illegal value itself */
        result = sourceIllegal;
        break;
	    }
    }
    if (target >= targetEnd) {
	    source = oldSource; /* Back up source pointer! */
	    result = targetExhausted; break;
    }
    *target++ = ch;
  }
  *sourceStart = source;
  *targetStart = target;
#ifdef CVTUTF_DEBUG
  if (result == sourceIllegal) {
    fprintf(stderr, "ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2);
    fflush(stderr);
  }
#endif
  return result;
}

/* --------------------------------------------------------------------- */

/*
 * Index into the table below with the first byte of a UTF-8 sequence to
 * get the number of trailing bytes that are supposed to follow it.
 * Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
 * left as-is for anyone who may want to do such conversion, which was
 * allowed in earlier algorithms.
 */
static const char trailingBytesForUTF8[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
};

/*
 * Magic values subtracted from a buffer value during UTF8 conversion.
 * This table contains as many values as there might be trailing bytes
 * in a UTF-8 sequence.
 */
static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
  0x03C82080UL, 0xFA082080UL, 0x82082080UL };

/*
 * Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
 * into the first byte, depending on how many bytes follow.  There are
 * as many entries in this table as there are UTF-8 sequence types.
 * (I.e., one byte sequence, two byte... etc.). Remember that sequencs
 * for *legal* UTF-8 will be 4 or fewer bytes total.
 */
static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };

/* --------------------------------------------------------------------- */

/* 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 switches.
* (See "Note A" at the bottom of the file for equivalent code.)
* If your compiler supports it, the "isLegalUTF8" call can be turned
* into an inline function.
*/

/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF16toUTF8 (const UTF16** sourceStart, const UTF16* sourceEnd,
                                     UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
  ConversionResult result = conversionOK;
  const UTF16* source = *sourceStart;
  UTF8* target = *targetStart;
  while (source < sourceEnd) {
    UTF32 ch;
    unsigned short bytesToWrite = 0;
    const UTF32 byteMask = 0xBF;
    const UTF32 byteMark = 0x80;
    const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
    ch = *source++;
    /* If we have a surrogate pair, convert to UTF32 first. */
    if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
	    /* If the 16 bits following the high surrogate are in the source buffer... */
	    if (source < sourceEnd) {
        UTF32 ch2 = *source;
        /* If it's a low surrogate, convert to UTF32. */
        if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
          ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
          + (ch2 - UNI_SUR_LOW_START) + halfBase;
          ++source;
        } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
          --source; /* return to the illegal value itself */
          result = sourceIllegal;
          break;
        }
	    } else { /* We don't have the 16 bits following the high surrogate. */
        --source; /* return to the high surrogate */
        result = sourceExhausted;
        break;
	    }
    } else if (flags == strictConversion) {
	    /* UTF-16 surrogate values are illegal in UTF-32 */
	    if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
        --source; /* return to the illegal value itself */
        result = sourceIllegal;
        break;
	    }
    }
    /* Figure out how many bytes the result will require */
    if (ch < (UTF32)0x80) {	     bytesToWrite = 1;
    } else if (ch < (UTF32)0x800) {     bytesToWrite = 2;
    } else if (ch < (UTF32)0x10000) {   bytesToWrite = 3;
    } else if (ch < (UTF32)0x110000) {  bytesToWrite = 4;
    } else {			    bytesToWrite = 3;
      ch = UNI_REPLACEMENT_CHAR;
    }

    target += bytesToWrite;
    if (target > targetEnd) {
	    source = oldSource; /* Back up source pointer! */
	    target -= bytesToWrite; result = targetExhausted; break;
    }
    switch (bytesToWrite) { /* note: everything falls through. */
	    case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;