utf8.cpp

Symbian操作系统手机上可执行程序的安装打包程序的源码

/*
 * Copyright 2001 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.

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

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


/** Symbian Note: 

	The following and complete source can be retrieved from :
    http://www.unicode.org/Public/ALPHA/CVTUTF-1-1/
	files UTF8.h and UTF8.c were renamed from the original ConvertUTF8.h
	and ConvertUTF8.c respectively and most functions (which are not used, were
	gently removed from these files without hurting them :-)
*/

#include  "utf8.h" 

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

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


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

/*
 * 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.
 */
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... six byte sequence.)
 */
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.
 */

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


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

/*
 * Utility routine to tell whether a sequence of bytes is legal UTF-8.
 * This must be called with the length pre-determined by the first byte.
 * If not calling this from ConvertUTF8to*, then the length can be set by:
 *  length = trailingBytesForUTF8[*source]+1;
 * and the sequence is illegal right away if there aren't that many bytes
 * available.
 * If presented with a length > 4, this returns false.  The Unicode
 * definition of UTF-8 goes up to 4-byte sequences.
 */

static Boolean isLegalUTF8(const UTF8 *source, int length) {
    UTF8 a;
    const UTF8 *srcptr = source+length;
    switch (length) {
    default: return false;
	/* Everything else falls through when "true"... */
    case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
    case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
    case 2: if ((a = (*--srcptr)) > 0xBF) return false;
	switch (*source) {
	    /* no fall-through in this inner switch */
	    case 0xE0: if (a < 0xA0) return false; break;
	    case 0xF0: if (a < 0x90) return false; break;
	    case 0xF4: if (a > 0x8F) return false; break;
	    default:  if (a < 0x80) return false;
	}
	case 1: if (*source >= 0x80 && *source < 0xC2) return false;
	if (*source > 0xF4) return false;
    }
    return true;
}


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

ConversionResult ConvertUTF8toUTF16 (
	const UTF8** sourceStart, const UTF8* sourceEnd, 
	UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
    ConversionResult result = conversionOK;
    const UTF8* source = *sourceStart;
    UTF16* target = *targetStart;
    while (source < sourceEnd) {
	UTF32 ch = 0;
	unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
	if (source + extraBytesToRead >= sourceEnd) {
	    result = sourceExhausted; break;
	}
	/* Do this check whether lenient or strict */
	if (! isLegalUTF8(source, extraBytesToRead+1)) {
	    result = sourceIllegal;
	    break;
	}
	/*
	 * The cases all fall through. See "Note A" below.
	 */
	switch (extraBytesToRead) {
	    case 3: ch += *source++; ch <<= 6;
	    case 2: ch += *source++; ch <<= 6;
	    case 1: ch += *source++; ch <<= 6;
	    case 0: ch += *source++;
	}
	ch -= offsetsFromUTF8[extraBytesToRead];

	if (target >= targetEnd) {
	    source -= (extraBytesToRead+1); /* Back up source pointer! */
	    result = targetExhausted; break;
	}
	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) || ((ch & 0xFFFE) == 0xFFFE)) {
		if (flags == strictConversion) {
		    source -= (extraBytesToRead+1); /* 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_UTF16) {
	    if (flags == strictConversion) {
		result = sourceIllegal;
		source -= (extraBytesToRead+1); /* return to the start */
		break; /* Bail out; shouldn't continue */
	    } else {
		*target++ = UNI_REPLACEMENT_CHAR;
	    }
	} else {
	    /* target is a character in range 0xFFFF - 0x10FFFF. */
	    if (target + 1 >= targetEnd) {
		source -= (extraBytesToRead+1); /* 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;
}