minibidi.c

大名鼎鼎的远程登录软件putty的Symbian版源码

/************************************************************************
 * $Id: minibidi.c,v 1.1.2.1 2004/12/29 11:32:15 pekangas Exp $
 *
 * ------------
 * Description:
 * ------------
 * This is an implemention of Unicode's Bidirectional Algorithm
 * (known as UAX #9).
 *
 *   http://www.unicode.org/reports/tr9/
 * 
 * Author: Ahmad Khalifa
 *
 * -----------------
 * Revision Details:    (Updated by Revision Control System)
 * -----------------
 *  $Date: 2004/12/29 11:32:15 $
 *  $Author: pekangas $
 *  $Revision: 1.1.2.1 $
 *  $Source: /cygdrive/c/home/pekangas/.cvsroot/s2putty/putty/minibidi.c,v $
 *
 * (www.arabeyes.org - under MIT license)
 *
 ************************************************************************/

/*
 * TODO:
 * =====
 * - Explicit marks need to be handled (they are not 100% now)
 * - Ligatures
 */

#include "minibidi.h"

/*
 * Flips the text buffer, according to max level, and
 * all higher levels
 * 
 * Input:
 * from: text buffer, on which to apply flipping
 * level: resolved levels buffer
 * max: the maximum level found in this line (should be unsigned char)
 * count: line size in bidi_char
 */
void flipThisRun(bidi_char *from, unsigned char *level, int max, int count)
{
    int i, j, rcount, tlevel;
    bidi_char temp;

    j = i = 0;
    while(i<count && j<count)
    {

	/* find the start of the run of level=max */
	tlevel = max;
	i = j = findIndexOfRun(level, i, count, max);
	/* find the end of the run */
	while(tlevel <= level[i] && i<count)
	{
	    i++;
	}
	rcount = i-j;
	for(; rcount>((i-j)/2); rcount--)
	{
	    temp = from[j+rcount-1];
	    from[j+rcount-1] = from[i-rcount];
	    from[i-rcount] = temp;
	}
    }
}

/*
 * Finds the index of a run with level equals tlevel
 */
int findIndexOfRun(unsigned char* level , int start, int count, int tlevel)
{
    int i;
    for(i=start; i<count; i++)
    {
	if(tlevel == level[i])
	{
	    return i;
	}
    }
    return count;
}

/*
 * Returns character type of ch, by calling RLE table lookup
 * function
 */
unsigned char getType(wchar_t ch)
{
    return getRLE(ch);
}

/*
 * The most significant 2 bits of each level are used to store
 * Override status of each character
 * This function sets the override bits of level according
 * to the value in override, and reurns the new byte.
 */
unsigned char setOverrideBits(unsigned char level, unsigned char override)
{
    if(override == ON)
	return level;
    else if(override == R)
	return level | OISR;
    else if(override == L)
	return level | OISL;
    return level;
}

/* Dont remember what this was used for :-) */
unsigned char getPreviousLevel(unsigned char* level, int from)
{
    unsigned char current;
    from--;
    current = level[from];
    while(from>0 && level[from] == current)
    {
	from--;
    }
    return level[++from];
}

/*
 * Returns the first odd value greater than x
 */
unsigned char leastGreaterOdd(unsigned char x)
{
    if((x % 2) == 0)
	return x+1;
    else
	return x+2;
}

/*
 * Returns the first even value greater than x
 */
unsigned char leastGreaterEven(unsigned char x)
{
    if((x % 2) == 0)
	return x+2;
    else
	return x+1;
}

/*
 * Loops over the RLE_table array looking for the
 * type of ch
 */
unsigned char getRLE(wchar_t ch)
{
    int offset, i, freq;

    freq = offset = 0;
    for(i=0; i<0xFFFF; i++)
    {
	freq = ((RLENode*)RLE_table)[i].f;
	offset += freq;
	if(offset == ch)
	    return ((RLENode*)RLE_table)[i].d;
	else if(offset > ch)
	    return ((RLENode*)RLE_table)[i-1].d;
    }
    /* this is here to stop compiler nagging */
    return ON;
}

/* The Main shaping function, and the only one to be used
 * by the outside world.
 *
 * line: buffer to apply shaping to. this must be passed by doBidi() first
 * to: output buffer for the shaped data
 * count: number of characters in line
 */
int do_shape(bidi_char *line, bidi_char *to, int count)
{
    int i, tempShape, ligFlag;

    for(ligFlag=i=0; i<count; i++)
    {
	to[i] = line[i];
	tempShape = STYPE(line[i].wc);
	switch(tempShape )
	{
	  case SC:
	    break;

	  case SU:
	    break;

	  case SR:
	    tempShape = STYPE(line[i+1].wc);
	    if((tempShape == SL) || (tempShape == SD) || (tempShape == SC))
		to[i].wc = SFINAL((SISOLATED(line[i].wc)));
	    else
		to[i].wc = SISOLATED(line[i].wc);
	    break;


	  case SD:
	    /* Make Ligatures */
	    tempShape = STYPE(line[i+1].wc);
	    if(line[i].wc == 0x644)
	    {
		switch(line[i-1].wc)
		{
		  case 0x622:
		    ligFlag = 1;
		    if((tempShape == SL) || (tempShape == SD) || (tempShape == SC))
			to[i].wc = 0xFEF6;
		    else
			to[i].wc = 0xFEF5;
		    break;
		  case 0x623:
		    ligFlag = 1;
		    if((tempShape == SL) || (tempShape == SD) || (tempShape == SC))
			to[i].wc = 0xFEF8;
		    else
			to[i].wc = 0xFEF7;
		    break;
		  case 0x625:
		    ligFlag = 1;
		    if((tempShape == SL) || (tempShape == SD) || (tempShape == SC))
			to[i].wc = 0xFEFA;
		    else
			to[i].wc = 0xFEF9;
		    break;
		  case 0x627:
		    ligFlag = 1;
		    if((tempShape == SL) || (tempShape == SD) || (tempShape == SC))
			to[i].wc = 0xFEFC;
		    else
			to[i].wc = 0xFEFB;
		    break;
		}
		if(ligFlag)
		{
		    to[i-1].wc = 0x20;
		    ligFlag = 0;
		    break;
		}
	    }

	    if((tempShape == SL) || (tempShape == SD) || (tempShape == SC))
	    {
		tempShape = STYPE(line[i-1].wc);
		if((tempShape == SR) || (tempShape == SD) || (tempShape == SC))
		    to[i].wc = SMEDIAL( (SISOLATED(line[i].wc)) );
		else
		    to[i].wc = SFINAL((SISOLATED(line[i].wc)));
		break;
	    }

	    tempShape = STYPE(line[i-1].wc);
	    if((tempShape == SR) || (tempShape == SD) || (tempShape == SC))
		to[i].wc = SINITIAL((SISOLATED(line[i].wc)));
	    else
		to[i].wc = SISOLATED(line[i].wc);
	    break;


	}
    }
    return 1;
}

/*
 * The Main Bidi Function, and the only function that should
 * be used by the outside world.
 *
 * line: a buffer of size count containing text to apply
 * the Bidirectional algorithm to.
 */

int do_bidi(bidi_char *line, int count)
{
    unsigned char* types;
    unsigned char* levels;
    unsigned char paragraphLevel;
    unsigned char currentEmbedding;
    unsigned char currentOverride;
    unsigned char tempType;
    int i, j, imax, yes, bover;

    /* Check the presence of R or AL types as optimization */
    yes = 0;
    for(i=0; i<count; i++)
    {
	if(getType(line[i].wc) == R || getType(line[i].wc) == AL)
	{
	    yes = 1;
	    break;
	}
    }
    if(yes == 0)
	return L;

    /* Initialize types, levels */
    types = malloc(sizeof(unsigned char) * count);
    levels = malloc(sizeof(unsigned char) * count);

    /* Rule (P1)  NOT IMPLEMENTED
     * P1. Split the text into separate paragraphs. A paragraph separator is
     * kept with the previous paragraph. Within each paragraph, apply all the
     * other rules of this algorithm.
     */

    /* Rule (P2), (P3)
     * P2. In each paragraph, find the first character of type L, AL, or R.
     * P3. If a character is found in P2 and it is of type AL or R, then set
     * the paragraph embedding level to one; otherwise, set it to zero.
     */
    paragraphLevel = 0;
    for( i=0; i<count ; i++)
    {
	if(getType(line[i].wc) == R || getType(line[i].wc) == AL)
	{
	    paragraphLevel = 1;
	    break;
	}
	else if(getType(line[i].wc) == L)
	    break;
    }

    /* Rule (X1)
     * X1. Begin by setting the current embedding level to the paragraph
     * embedding level. Set the directional override status to neutral.
     */
    currentEmbedding = paragraphLevel;
    currentOverride = ON;

    /* Rule (X2), (X3), (X4), (X5), (X6), (X7), (X8)
     * X2. With each RLE, compute the least greater odd embedding level.
     * X3. With each LRE, compute the least greater even embedding level.
     * X4. With each RLO, compute the least greater odd embedding level.
     * X5. With each LRO, compute the least greater even embedding level.
     * X6. For all types besides RLE, LRE, RLO, LRO, and PDF:
     *		a. Set the level of the current character to the current
     *		    embedding level.
     *		b.  Whenever the directional override status is not neutral,
     *               reset the current character type to the directional
     *               override status.
     * X7. With each PDF, determine the matching embedding or override code.
     * If there was a valid matching code, restore (pop) the last
     * remembered (pushed) embedding level and directional override.
     * X8. All explicit directional embeddings and overrides are completely
     * terminated at the end of each paragraph. Paragraph separators are not
     * included in the embedding. (Useless here) NOT IMPLEMENTED
     */
    bover = 0;
    for( i=0; i<count; i++)
    {
	tempType = getType(line[i].wc);
	switch(tempType)
	{
	  case RLE:
	    currentEmbedding = levels[i] = leastGreaterOdd(currentEmbedding);
	    levels[i] = setOverrideBits(levels[i], currentOverride);
	    currentOverride = ON;
	    break;

	  case LRE:
	    currentEmbedding = levels[i] = leastGreaterEven(currentEmbedding);
	    levels[i] = setOverrideBits(levels[i], currentOverride);
	    currentOverride = ON;
	    break;

	  case RLO:
	    currentEmbedding = levels[i] = leastGreaterOdd(currentEmbedding);
	    tempType = currentOverride = R;
	    bover = 1;
	    break;

	  case LRO:
	    currentEmbedding = levels[i] = leastGreaterEven(currentEmbedding);
	    tempType = currentOverride = L;
	    bover = 1;
	    break;

	  case PDF:
	    currentEmbedding = getPreviousLevel(levels, i);
	    currentOverride = currentEmbedding & OMASK;
	    currentEmbedding = currentEmbedding & ~OMASK;
	    levels[i] = currentEmbedding;
	    break;

	    /* Whitespace is treated as neutral for now */
	  case WS:
	  case S:
	    levels[i] = currentEmbedding;
	    tempType = ON;
	    if(currentOverride != ON)
		tempType = currentOverride;
	    break;

	  default:
	    levels[i] = currentEmbedding;
	    if(currentOverride != ON)
		tempType = currentOverride;
	    break;

	}
	types[i] = tempType;
    }
    /* this clears out all overrides, so we can use levels safely... */
    /* checks bover first */
    if(bover)
	for( i=0; i<count; i++)
	    levels[i] = levels[i] & LMASK;

    /* Rule (X9)
     * X9. Remove all RLE, LRE, RLO, LRO, PDF, and BN codes.
     * Here, they're converted to BN.
     */
    for(i=0; i<count; i++)
    {
	switch(types[i])
	{
	  case RLE:
	  case LRE:
	  case RLO:
	  case LRO:
	  case PDF:
	    types[i] = BN;
	    break;
	}
    }

    /* Rule (W1)
     * W1. Examine each non-spacing mark (NSM) in the level run, and change
     * the type of the NSM to the type of the previous character. If the NSM
     * is at the start of the level run, it will get the type of sor.
     */
    if(types[0] == NSM)
	types[0] = paragraphLevel;

    for(i=1; i<count; i++)
    {
	if(types[i] == NSM)
	    types[i] = types[i-1];
	/* Is this a safe assumption?
	 * I assumed the previous, IS a character.
	 */
    }

    /* Rule (W2)
     * W2. Search backwards from each instance of a European number until the
     * first strong type (R, L, AL, or sor) is found.  If an AL is found,
     * change the type of the European number to Arabic number.
     */
    for(i=0; i<count; i++)
    {
	if(types[i] == EN)
	{
	    j=i;
	    while(j >= 0)
	    {
		if(types[j] == AL)
		{
		    types[i] = AN;
		    break;
		}else if(types[j] == R || types[j] == L)
		    {
			break;
		    }
		j--;
	    }
	}
    }

    /* Rule (W3)
     * W3. Change all ALs to R.
     *
     * Optimization: on Rule Xn, we might set a flag on AL type
     * to prevent this loop in L R lines only...
     */
    for(i=0; i<count; i++)
    {
	if(types[i] == AL)
	    types[i] = R;
    }

    /* Rule (W4)
     * W4. A single European separator between two European numbers changes
     * to a European number. A single common separator between two numbers
     * of the same type changes to that type.
     */
    for( i=0; i<(count-1); i++)
    {
	if(types[i] == ES)
	{
	    if(types[i-1] == EN && types[i+1] == EN)
		types[i] = EN;
	}else if(types[i] == CS)
	    {
		if(types[i-1] == EN && types[i+1] == EN)
		    types[i] = EN;
		else if(types[i-1] == AN && types[i+1] == AN)
		    types[i] = AN;
	    }
    }

    /* Rule (W5)
     * W5. A sequence of European terminators adjacent to European numbers
     * changes to all European numbers.
     *
     * Optimization: lots here... else ifs need rearrangement
     */
    for(i=0; i<count; i++)
    {
	if(types[i] == ET)
	{
	    if(types[i-1] == EN)
	    {
		types[i] = EN;
		continue;
	    }else if(types[i+1] == EN)
		{
		    types[i] = EN;
		    continue;
		}else if(types[i+1] == ET)
		    {
			j=i;
			while(j <count && types[j] == ET)
			{
			    j++;
			}
			if(types[j] == EN)
			    types[i] = EN;
		    }
	}
    }

    /* Rule (W6)
     * W6. Otherwise, separators and terminators change to Other Neutral:
     */
    for(i=0; i<count; i++)
    {
	switch(types[i])
	{
	  case ES:
	  case ET:
	  case CS:
	    types[i] = ON;
	    break;
	}
    }

    /* Rule (W7)
     * W7. Search backwards from each instance of a European number until
     * the first strong type (R, L, or sor) is found. If an L is found,
     * then change the type of the European number to L.
     */
    for(i=0; i<count; i++)
    {
	if(types[i] == EN)
	{
	    j=i;
	    while(j >= 0)
	    {
		if(types[j] == L)
		{
		    types[i] = L;
		    break;
		}
		else if(types[j] == R || types[j] == AL)
		{
		    break;
		}
		j--;
	    }
	}
    }

    /* Rule (N1)
     * N1. A sequence of neutrals takes the direction of the surrounding
     * strong text if the text on both sides has the same direction. European
     * and Arabic numbers are treated as though they were R.
     */
    if(types[0] == ON)
    {
	if((types[1] == R) || (types[1] == EN) || (types[1] == AN))
	    types[0] = R;
	else if(types[1] == L)
	    types[0] = L;
    }
    for(i=1; i<(count-1); i++)
    {
	if(types[i] == ON)
	{
	    if(types[i-1] == L)
	    {
		j=i;
		while(j<(count-1) && types[j] == ON)