C编码转换：gbk转unicode utf8转unicode

#include "stdafx.h" #include "string_conv.h" #include "gbk_to_unicode.h" #include "unicode_to_gbk.h" int dprintf(char *format, ... ) { #if 0 char buf[1024]; va_list marker; int n; va_start(marker, format); // 开始分析字符串 n = vsprintf(buf, format, marker); // 格式化输出字符串 printf("%s", buf); va_end(marker); // 结束分析 return 0; #else return 0; #endif } /*-----------------+-------------------------+------------------------ | endian = 1 大端 | | endian = 0 小端 | -------------------+-------------------------+-----------------------*/ int gbk_to_unicode(unsigned char *gbk_buf, unsigned short *unicode_buf, int max_unicode_buf_size, int endian) { unsigned short word; unsigned char *gbk_ptr = gbk_buf; unsigned short *uni_ptr = unicode_buf; unsigned int uni_ind = 0, gbk_ind = 0, uni_num = 0; unsigned char ch; int word_pos; if( !gbk_buf || !unicode_buf ) return -1; while(1) { ch = *(gbk_ptr + gbk_ind); if(ch == 0x00) break; if( ch > 0x80 ) { //chinese //word = *p *256 + *(p+1); if(endian == 1) //大端 { word = *(gbk_ptr + gbk_ind); word <<= 8; gbk_ind++; word += *(gbk_ptr + gbk_ind); gbk_ind++; } else { word = *(gbk_ptr + gbk_ind + 1); word <<= 8; word += *(gbk_ptr + gbk_ind); gbk_ind += 2; } //printf("word: 0x%x\n", word); word_pos = word - g_gbk_first_code; if(word >= g_gbk_first_code && word <= g_gbk_last_code && (word_pos < g_gbk_to_unicode_buf_size)) { //*p_out = g_gbk_to_unicode_buf[word_pos]; //*p_out ++; //n++; *(uni_ptr + uni_ind) = g_gbk_to_unicode_buf[word_pos]; uni_ind++; uni_num++; } } else { //for ASCII //*p_out = (unsigned short)*p; //*p_out ++; //n++; gbk_ind++; //*(uni_ptr + uni_ind) = g_gbk_to_unicode_buf[word_pos]; *(uni_ptr + uni_ind) = ch; uni_ind++; uni_num++; } if(uni_num > max_unicode_buf_size - 1) break; } return uni_num; } int unicode_to_gbk(unsigned short *unicode_buf, unsigned char *gbk_buf, int max_gbk_buf_size, int endian) { unsigned short word; unsigned short gbk_word; unsigned char ch; unsigned char *gbk_ptr = gbk_buf; unsigned short *uni_ptr = unicode_buf; unsigned int uni_ind = 0, gbk_ind = 0, gbk_num = 0; int word_pos; if( !gbk_buf || !unicode_buf ) return -1; while(1) { word = *(uni_ptr + uni_ind); uni_ind++; if(word == 0x0000) //字符串结束符 break; //dprintf("[0]word: 0x%x\n", word); if(endian == 1) //大端 { //高低位交换 ch = (unsigned char)word; word = word >> 8; word += ch << 8; } //dprintf("[1]word: 0x%x\n", word); if(word < 0x80) /*ASCII不用查表*/ { *(gbk_ptr + gbk_ind) = (unsigned char)word; //dprintf("gbk_ptr[%d]: 0x%x\n", gbk_ind, *(gbk_ptr + gbk_ind)); gbk_ind++; } else { word_pos = word - g_unicode_first_code; //dprintf("word_pos: %d\n", word_pos); if(word >= g_unicode_first_code && word <= g_unicode_last_code && word_pos < g_unicode_to_gbk_buf_size) { gbk_word = g_unicode_to_gbk_buf[word_pos]; //dprintf("gbk_word: 0x%x\n", gbk_word); *(gbk_ptr + gbk_ind) = (unsigned char)(gbk_word >> 8); gbk_ind++; *(gbk_ptr + gbk_ind) = (unsigned char)(gbk_word >> 0); gbk_ind++; gbk_num++; } } if(gbk_num > max_gbk_buf_size - 1) break; } return gbk_num; } int unicode_to_utf8(unsigned short *unicode_buf, unsigned char *utf8_buf, int max_utf8_buf_size, int endian) { unsigned short *uni_ptr = unicode_buf; unsigned char *utf_ptr = utf8_buf; unsigned short word; unsigned char ch; unsigned int uni_ind = 0, utf_ind = 0, utf_num = 0; while(1) { word = *(uni_ptr + uni_ind); uni_ind++; if(word == 0x0000) //结束符 break; if(endian == 1) //大端 { //高低位交换 ch = (unsigned char)word; word = word >> 8; word += ch << 8; } if(word < 0x80) { *(utf_ptr + utf_ind) = word & 0x7F | 0x00; utf_ind++; utf_num++; } else if(word < 0x0800) { *(utf_ptr + utf_ind) = (word >> 6) & 0x1F | 0xC0; utf_ind++; *(utf_ptr + utf_ind) = word & 0x3F | 0x80; utf_ind++; utf_num++; } else if(word < 0x010000) { *(utf_ptr + utf_ind) = (word >> 12) & 0x0F | 0xE0; utf_ind++; *(utf_ptr + utf_ind) = (word >> 6) & 0x3F | 0x80; utf_ind++; *(utf_ptr + utf_ind) = word & 0x3F | 0x80; utf_ind++; utf_num++; } else if(word < 0x110000) { *(utf_ptr + utf_ind) = (word >> 18) & 0x07 | 0xF0; utf_ind++; *(utf_ptr + utf_ind) = (word >> 12) & 0x3F | 0x80; utf_ind++; *(utf_ptr + utf_ind) = (word >> 6) & 0x3F | 0x80; utf_ind++; *(utf_ptr + utf_ind) = word & 0x3F | 0x80; utf_ind++; utf_num++; } if(utf_num > max_utf8_buf_size - 1) { break; } } return utf_num; } int utf8_to_unicode(unsigned char *utf8_buf, unsigned short *unicode_buf, int max_unicode_buf_size, int endian) { unsigned short *uni_ptr = unicode_buf; unsigned char *utf_ptr = utf8_buf; unsigned short word; unsigned char ch; unsigned int uni_ind = 0, utf_ind = 0, utf_num = 0; while(1) { ch = *(utf_ptr + utf_ind); if(ch == 0x00) //结束符 break; if ((ch & 0x80) == 0) { *(unicode_buf + uni_ind) = *(utf_ptr + utf_ind); uni_ind++; utf_ind++; utf_num++; } else if((ch & 0xE0) == 0xC0) ///< 110x-xxxx 10xx-xxxx { word = (*(utf_ptr + utf_ind) & 0x3F) << 6; word |= (*(utf_ptr + utf_ind + 1) & 0x3F); *(unicode_buf + uni_ind) = word; uni_ind++; utf_ind += 2; utf_num++; } else if((ch & 0xF0) == 0xE0) ///< 1110-xxxx 10xx-xxxx 10xx-xxxx { word = (*(utf_ptr + utf_ind) & 0x1F) << 12; word |= (*(utf_ptr + utf_ind + 1) & 0x3F) << 6; word |= (*(utf_ptr + utf_ind + 2) & 0x3F); *(unicode_buf + uni_ind) = word; uni_ind++; utf_ind += 3; utf_num++; } else if((ch & 0xF8) == 0xF0) ///< 1111-0xxx 10xx-xxxx 10xx-xxxx 10xx-xxxx { word = (*(utf_ptr + utf_ind) & 0x0F) << 18; word = (*(utf_ptr + utf_ind + 1) & 0x3F) << 12; word |= (*(utf_ptr + utf_ind + 2) & 0x3F) << 6; word |= (*(utf_ptr + utf_ind + 3) & 0x3F); *(unicode_buf + uni_ind) = word; uni_ind++; utf_ind += 4; utf_num++; } else ///< 1111-10xx 10xx-xxxx 10xx-xxxx 10xx-xxxx 10xx-xxxx { word = (*(utf_ptr + utf_ind) & 0x07) << 24; word = (*(utf_ptr + utf_ind + 1) & 0x3F) << 18; word = (*(utf_ptr + utf_ind + 2) & 0x3F) << 12; word = (*(utf_ptr + utf_ind + 3) & 0x3F) << 6; word = (*(utf_ptr + utf_ind + 4) & 0x3F); *(unicode_buf + uni_ind) = word; uni_ind++; utf_ind += 5; utf_num++; } if(utf_num > max_unicode_buf_size - 1) { break; } } return utf_num; }