构建 GB2312 汉字库的 unicode 码表

构建 GB2312 汉字库的 unicode 码表

作者：乾坤一笑

下载源代码

　　构建 GB2312 汉字库的 unicode 码表嵌入式系统总离不了处理汉字。一般汉字的处理方法是（以手机接受短信为例）：比如你收到了一封短信，该短信解码后是按照 UTF-16 表示的，那么我们需要根据每一个汉字的unicode 码找到它在 GB2312 库中的位置，然后再用对应的点阵数据在屏幕上显示出来。
　　于是乎，必须有一种手段将 unicode 码和汉字字模的数据对应起来。最常用的手段是做一个 unicode 码表，在该数组中查找到匹配的 unicode 码后，用匹配的 index（数组索引）值在另外一个由该 index 值对应的字模记录的数组中的数据去显示。

+-----------------+ 查表 +-----------------+ 同index +-------------------+
| 汉字的unicode码 | ==> | unicode码表数组 | =======> | 汉字字模数据数组 | ==> 显示输出
+-----------------+ +-----------------+ +-------------------+

本文简要介绍一下如何生成 unicode 码表，其它相关的汉字处理技术不在本文的讨论范围之内。:)

用下面两个函数可以把 unicode 码表构造出来（*注1）：

void UnicodeToGB2312(unsigned char* pOut,unsigned short uData){    WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(unsigned short),NULL,NULL);    return;}      void Gb2312ToUnicode(unsigned short* pOut,unsigned char *gbBuffer){    MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);    return;}

/*-----------------------------------------------*\|  GB2312 unicode table constructor               ||  author: Spark Song                             ||  file  : build_uni_table.c                      ||  date  : 2005-11-18                             |\*-----------------------------------------------*/#include <stdio.h>#include <windows.h>void UnicodeToGB2312(unsigned char* pOut,unsigned short uData);void Gb2312ToUnicode(unsigned short* pOut,unsigned char *gbBuffer);void construct_unicode_table();int main(int argc, char *argv[]){construct_unicode_table();return 0;}void construct_unicode_table(){    #define GB2312_MATRIX   (94)    #define DELTA           (0xA0)    #define FONT_ROW_BEGIN (16  + DELTA)    #define FONT_ROW_END   (87 + DELTA)    #define FONT_COL_BEGIN (1  + DELTA)    #define FONT_COL_END   (GB2312_MATRIX + DELTA)    #define FONT_TOTAL     (72 * GB2312_MATRIX)    int i, j;    unsigned char   chr[2];    unsigned short  uni;    unsigned short  data[FONT_TOTAL] = {0};    int index = 0;    unsigned short buf;    //生成unicode码表    for (i=FONT_ROW_BEGIN; i<=FONT_ROW_END; i++)        for(j=FONT_COL_BEGIN; j<=FONT_COL_END; j++)        {            chr[0] = i;             chr[1] = j;            Gb2312ToUnicode(&uni, chr);            data[index] = uni; index++;        }   //排个序，以后检索的时候就可以用binary-search了    for (i=0;i<index-1; i++)        for(j=i+1; j<index; j++)            if (data[i]>data[j])            {                buf = data[i];                 data[i] = data[j];                data[j] = buf;            }                    //输出到STD_OUT    printf("const unsigned short uni_table[]={\n");    for (i=0; i<index; i++)    {        uni = data[i];        UnicodeToGB2312(chr, uni);        printf("    0x%.4X%s /* GB2312 Code: 0x%.2X%.2X ==> Row:%.2d Col:%.2d */\n",                 uni,                 i==index-1?" ":",",                chr[0],                chr[1],                chr[0] - DELTA,                chr[1] - DELTA                );    }    printf("};\n");    return ;}void UnicodeToGB2312(unsigned char* pOut,unsigned short uData){    WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(unsigned short),NULL,NULL);    return;}      void Gb2312ToUnicode(unsigned short* pOut,unsigned char *gbBuffer){    MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);    return;}      

build_uni_table.exe > report.txt

const unsigned short  uni_table[]={    0x4E00, /* GB2312 Code: 0xD2BB ==> Row:50 Col:27 */    0x4E01, /* GB2312 Code: 0xB6A1 ==> Row:22 Col:01 */    0x4E03, /* GB2312 Code: 0xC6DF ==> Row:38 Col:63 */    0x4E07, /* GB2312 Code: 0xCDF2 ==> Row:45 Col:82 */... ...    0x9F9F, /* GB2312 Code: 0xB9EA ==> Row:25 Col:74 */    0x9FA0, /* GB2312 Code: 0xD9DF ==> Row:57 Col:63 */    0xE810, /* GB2312 Code: 0xD7FA ==> Row:55 Col:90 */    0xE811, /* GB2312 Code: 0xD7FB ==> Row:55 Col:91 */    0xE812, /* GB2312 Code: 0xD7FC ==> Row:55 Col:92 */    0xE813, /* GB2312 Code: 0xD7FD ==> Row:55 Col:93 */    0xE814  /* GB2312 Code: 0xD7FE ==> Row:55 Col:94 */};