嵌入式中 动态阿拉伯语字符串 转换 LCD显示字符串【感谢建国雄心】

本文参考CSDBN:建国雄心 的博客，这里找不到该帖子，放一个类似的仅供参考https://blog.csdn.net/qiaojiongzeng6321/article/details/74857245，实际代码因为字模脚本的问题跟大佬的有区别（字形转换地方）

阿语与其他语言有差异，阿语范围内字符需要从右向左写，中间碰到其他字符要从左向右写。

这里不考虑语法顺序和后面的练笔规则，转译后应为，0x600,0x63b,0x30,0x35,0x34,0x20,0x644,0x63c，在计算机显示时需要转成 0x63c,0x644,0x30,0x35,0x34,0x30,0x63b,0x600

连笔的规则不多说，感兴趣自己搜搜看，项目中一般使用的是python脚本转译的，有个项目接到了新需求，从外部接受到后动态显示，需求要求显示阿语，遂增加了此功能，使用时先用 gutCheckArabicReverse 接口检查是否有阿语需要反显，如果有通过 gutArabicSrcStrCovPrintStr 转换字符串。

Arbic_Position数组跟其他博客有区别，实际上字符字形都一样，可以忽略，这个问题主要是我手头字模和字形工具的问题，建议先copy其他人发布的数据结构，验证无问题即可

直接放干货，基于C语言

const uint16 Arbic_unicode[]={
          0x621,0x622,0x623,0x624,0x625,0x626,0x627,0x628,0x629,0x62A,0x62B,0x62C,0x62D,0x62E,0x62F,
    0x630,0x631,0x632,0x633,0x634,0x635,0x636,0x637,0x638,0x639,0x63A,0x63B,0x63C,0x63D,0x63E,0x63F,
    0x640,0x641,0x642,0x643,0x644,0x645,0x646,0x647,0x648,0x649,0x64A
};
/*
  The unicodes of alone are no mapping to Arabic Presentation Forms B area.
*/
  
const uint16 Arbic_Position[] = {
//#  first, last,   middle,  alone
    0x0621, 0x0621, 0x0621, 0x0621, //# 0xfe80),
    0xfe82, 0x0622, 0xfe82, 0x0622, //# 0xfe81),
    0xfe84, 0x0623, 0xfe84, 0x0623, //# 0xfe83),
    0xfe86, 0x0624, 0xfe86, 0x0624, //# 0xfe85),
    0xfe88, 0x0625, 0xfe88, 0x0625, //# 0xfe87),
    0xfe8a, 0xfe8b, 0xfe8c, 0x0626, //# 0xfe89),
    0xfe8e, 0x0627, 0xfe8e, 0x0627, //# 0xfe8d),
    0xfe90, 0xfe91, 0xfe92, 0x0628, //# 0xfe8f),
    0xfe94, 0x0629, 0xfe94, 0x0629, //# 0xfe93),
    0xfe96, 0xfe97, 0xfe98, 0x062a, //# 0xfe95),
    0xfe9a, 0xfe9b, 0xfe9c, 0x062b, //# 0xfe99),
    0xfe9e, 0xfe9f, 0xfea0, 0x062c, //# 0xfe9d),
    0xfea2, 0xfea3, 0xfea4, 0x062d, //# 0xfea1),
    0xfea6, 0xfea7, 0xfea8, 0x062e, //# 0xfea5),
    0xfeaa, 0x062f, 0xfeaa, 0x062f, //# 0xfea9),
    0xfeac, 0x0630, 0xfeac, 0x0630, //# 0xfeab),
    0xfeae, 0x0631, 0xfeae, 0x0631, //# 0xfead),
    0xfeb0, 0x0632, 0xfeb0, 0x0632, //# 0xfeaf),
    0xfeb2, 0xfeb3, 0xfeb4, 0x0633, //# 0xfeb1),
    0xfeb6, 0xfeb7, 0xfeb8, 0x0634, //# 0xfeb5),
    0xfeba, 0xfebb, 0xfebc, 0x0635, //# 0xfeb9),
    0xfebe, 0xfebf, 0xfec0, 0x0636, //# 0xfebd),
    0xfec2, 0xfec3, 0xfec4, 0x0637, //# 0xfec1),
    0xfec6, 0xfec7, 0xfec8, 0x0638, //# 0xfec5),
    0xfeca, 0xfecb, 0xfecc, 0x0639, //# 0xfec9),
    0xfece, 0xfecf, 0xfed0, 0x063a, //# 0xfecd),
    0x63b,  0x63b,  0x63b,  0x63b , //
    0x63c,  0x63c,  0x63c,  0x63c , //
    0x63d,  0x63d,  0x63d,  0x63d , //
    0x63e,  0x63e,  0x63e,  0x63e , //
    0x63f,  0x63f,  0x63f,  0x63f , //
    0x640,  0x640,  0x640,  0x640 , //
    0xfed2, 0xfed3, 0xfed4, 0x0641, //# 0xfed1),
    0xfed6, 0xfed7, 0xfed8, 0x0642, //# 0xfed5),
    0xfeda, 0xfedb, 0xfedc, 0x0643, //# 0xfed9),
    0xfede, 0xfedf, 0xfee0, 0x0644, //# 0xfedd),
    0xfee2, 0xfee3, 0xfee4, 0x0645, //# 0xfee1),
    0xfee6, 0xfee7, 0xfee8, 0x0646, //# 0xfee5),
    0xfeea, 0xfeeb, 0xfeec, 0x0647, //# 0xfee9),
    0xfeee, 0x0648, 0xfeee, 0x0648, //# 0xfeed),
    0xfef0, 0xfef3, 0xfef4, 0x0649, //# 0xfeef),
    0xfef2, 0xfef3, 0xfef4, 0x064a  //# 0xfef1))
};
/* 前连 - 当前字符 前一个字符 与 下表是否匹配 */
const uint16 U16FrontSet1[] = {
    0x626,0x628,0x62a,0x62b,0x62c,0x62d,0x62e,
    0x633,0x634,0x635,0x636,0x637,0x639,0x63a,
    0x640,0x641,0x642,0x643,0x644,0x645,0x646,0x647,0x638,0x64a
};

/* 后连 - 当前字符 后一个字符 与 下表是否匹配 */
const uint16 U16BackSet2[] ={
    0x622,0x623,0x624,0x625,0x626,0x627,0x628,0x629,0x62a,0x62b,0x62c,0x62d,0x62e,0x62f,
    0x630,0x631,0x632,0x633,0x634,0x635,0x636,0x637,0x638,0x639,0x63a,
    0x640,0x641,0x642,0x643,0x644,0x645,0x646,0x647,0x648,0x649, 0x64a,
};

/*-----------------------------------------
阿拉伯文连字符规则:

连字符是以0x644开头，后面跟的是0x622，0x623，0x625，0x627，并根据情况取下面的字符数组0或1，如果0x644前一个字符是在集合1（同上面的集合1）中间，那么取数组1，否则取数组0:
  0x644 + 0x622/0x623/0x625/0x627,
  n+0x644+append,
  n = (U16FrontSet1) ,0x644 use index_1
  else 0x644 use index_0
----------------------------------------- */
const uint16 arabic_specs[] ={
    0xFEF5,0xFEF6, /* 0x622 */
    0xFEF7,0xFEF8, /* 0x623 */
    0xFEF9,0xFEFA, /* 0x625 */
    0xFEFB,0xFEFC  /* 0x627 */
};
    
//const uint16 head = 0x644;
//const uint16 append[] = {0x622,0x623,0x625,0x627};

#define pos_first  0
#define pos_last   1
#define pos_middle 2
#define pos_alone  3

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

Araboc unicode range:
0x600-0x6FF
0x750-0x77F
Presentation:0xFB50 - FDFF

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

#define IsArabicUnicodeCode(uUin)    (((uUin >= 0x600) && (uUin <= 0x6FF)) || ((uUin >= 0x750) && (uUin <= 0x77F)))

#define IsSpecialChar(uCurUni,uUin)  ((uCurUni==0x644)&&((uUin==0x622)||(uUin==0x623)||(uUin==0x625)||(uUin == 0x627)))
#define SpecialCharInex(uUin)        ((uUin==0x622)?0:((uUin==0x623)?1:((uUin==0x625)?2:(uUin==0x627)?3:3)))

#define IsFrontCennectChar(uLastUni) ((uLastUni==0x626)||(uLastUni==0x628)||((uLastUni>=0x62A)&&(uLastUni<=0x62E))||\
                                       ((uLastUni>=0x633)&&(uLastUni<=0x63A))||((uLastUni>=0x640)&&(uLastUni<=0x648))||(uLastUni==0x64A))
#define IsBackCennectChar(uNextUni)  (((uNextUni>=0x622)&&(uNextUni<=0x63A))||((uNextUni>=0x640)&&(uNextUni<=0x64A)))

#define IsSpaceChar(uUin)            ((/*(uUin==0x00)||*/(uUin==0x0A) || (uUin==0x0D) || (uUin==0x20)))

#define IsCennectChar(uCurUni)       ((uCurUni>=0x621)&&(uCurUni<=0x64A))

#define ArabicListIndex(uUin)        (uUin - 0x621)

bool gutCheckArabicReverse(uint16* u16Src,uint8 u8StrLen){
uint8 u8i;
bool boRet;

    boRet = False;
    for(u8i = 0;(u8i < u8StrLen) && (u16Src[u8i] != 0) && (u8i < 32);u8i++) {
        if(IsArabicUnicodeCode(u16Src[u8i])) {
            boRet = True;
            break;
        }
    }
    return boRet;
}

bool gutArabicSrcStrCovPrintStr(uint16* u16Src,uint8 u8StrLen) {
    uint16 u16CopyStr[32];
    uint8 u8i,u8j,u8k,u8CurId,u8Start,u8LastArabicId;
    uint16 u16Unicode,u16LastUni,u16NextUni,u16CovUni;
    bool boIsFront,boIsBack;
    uint16* arbicSpecs;
    uint16* ArbicPosition;

    arbicSpecs = (uint16*)&(arabic_specs[0]);
    ArbicPosition = (uint16*)&(Arbic_Position[0]);
    for(u8i = 0;(u8i < u8StrLen) && (u16Src[u8i] != 0) && (u8i < 31);u8i++) {
        u16Unicode = u16Src[u8i];
        /* Reverse */
        if(IsArabicUnicodeCode(u16Unicode)) {
            u8Start = u8i;
            u8LastArabicId = u8i;
            
            u8j = u8Start + 1;
            while(u8j < 31) {
                u16Unicode = u16Src[u8j];
                if(IsArabicUnicodeCode(u16Unicode)) {
                    u8LastArabicId = u8j;
                } else {
                    if(!IsSpaceChar(u16Unicode)) {
                        break;
                    }
                }
                u8j++;
            }
            /* Reverse Dispary */
            for(u8k=0;u8j < 31 && u8j > u8Start;u8j--,u8k++) {
                u16CopyStr[u8j-1] = u16Src[u8i+(u8k)];
            }
            u8j = 0;
            while(u8j < (u8LastArabicId - u8Start + 1)) {
                u16Unicode = u16Src[(u8Start + u8j)];
                if(IsCennectChar(u16Unicode)) {
                    if((u8Start+u8j) > 0) {
                        u16LastUni = u16Src[(u8Start+u8j) - 1];
                    } else {
                        u16LastUni = 0xFFFF;
                    }
                    if((u8Start+u8j) < 30) {
                        u16NextUni = u16Src[(u8Start+u8j) + 1];
                    } else {
                        u16NextUni = 0xFFFF;
                    }
                    
                    boIsBack = False;
                    boIsFront = False;
                    if(IsBackCennectChar(u16NextUni)) {
                        boIsBack = True;
                    }
                    if(IsFrontCennectChar(u16LastUni)) {
                        boIsFront = True;
                    }
                    
                    if(IsSpecialChar(u16Unicode,u16NextUni)) {
                        u8CurId = SpecialCharInex(u16NextUni);
                        u16CovUni = *(arbicSpecs+(u8CurId*2)+boIsFront);
                        u16CopyStr[u8LastArabicId - u8j] = u16CovUni;
                        u8j++;
                        u16CopyStr[u8LastArabicId - u8j] = 0xFFFF;
                    } else if((boIsFront == True) && (boIsBack == True)) {
                        u8CurId = ArabicListIndex(u16Unicode);
                        u16CovUni = *(ArbicPosition+(u8CurId*4+2));
                        u16CopyStr[u8LastArabicId - u8j] = u16CovUni;
                    } else if(boIsFront == True) {
                        u8CurId = ArabicListIndex(u16Unicode);
                        u16CovUni = *(ArbicPosition+(u8CurId*4+0));
                        u16CopyStr[u8LastArabicId - u8j] = u16CovUni;
                    } else if(boIsBack == True) {
                        u8CurId = ArabicListIndex(u16Unicode);
                        u16CovUni = *(ArbicPosition+(u8CurId*4+1));
                        u16CopyStr[u8LastArabicId - u8j] = u16CovUni;
                    } else {
                        u8CurId = ArabicListIndex(u16Unicode);
                        u16CovUni = *(ArbicPosition+(u8CurId*4+3));
                        u16CopyStr[u8LastArabicId - u8j] = u16CovUni;
                    }
                } else {
                    u16CopyStr[u8LastArabicId - u8j] = u16Unicode;
                }
                
                if(u8j == 31) {
                    break;
                }
                u8j++;
            }

            u8i = u8LastArabicId;
        } else {
            /* No change */
            u16CopyStr[u8i] = u16Src[u8i];
        }
    }
    u16CopyStr[u8i] = 0;
    for(u8i = 0,u8j=0;(u8i < u8StrLen) && (u16CopyStr[u8i] != 0) && (u8i < 31);u8i++) {
        if(u16CopyStr[u8i] != 0xFFFF){
            u16Src[u8j] = u16CopyStr[u8i];
            u8j++;
        }
    }
    u16Src[u8j] = 0;
}