King_DuckZ
cb37f21502
Latin letters and spaces get converted to halfwidth utf-8 characters. Not ideal as this will break visualisation for Japanese users. Leading and trailing spaces are trimmed and repeated spaces in the names are replaced with a single space.
66 lines
2.1 KiB
C++
66 lines
2.1 KiB
C++
//see https://stackoverflow.com/questions/33165171/c-shiftjis-to-utf8-conversionhttps://stackoverflow.com/questions/33165171/c-shiftjis-to-utf8-conversion
|
|
//First download the "original" data from ftp://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/SHIFTJIS.TXT
|
|
//Then use this program while piping/redirecting above text file in, and redirecting the binary output to a new file.
|
|
|
|
#include<iostream>
|
|
#include<string>
|
|
#include<cstdio>
|
|
|
|
using namespace std;
|
|
|
|
// pipe SHIFTJIS.txt in and pipe to (binary) file out
|
|
int main()
|
|
{
|
|
string s;
|
|
uint8_t *mapping; //same bigendian array as in converting function
|
|
mapping = new uint8_t[2*(256 + 3*256*16)];
|
|
|
|
//initializing with space for invalid value, and then ASCII control chars
|
|
for(size_t i = 32; i < 256 + 3*256*16; i++)
|
|
{
|
|
mapping[2 * i] = 0;
|
|
mapping[2 * i + 1] = 0x20;
|
|
}
|
|
for(size_t i = 0; i < 32; i++)
|
|
{
|
|
mapping[2 * i] = 0;
|
|
mapping[2 * i + 1] = i;
|
|
}
|
|
|
|
while(getline(cin, s)) //pipe the file SHIFTJIS to stdin
|
|
{
|
|
if(s.substr(0, 2) != "0x") continue; //comment lines
|
|
|
|
uint16_t shiftJisValue, unicodeValue;
|
|
if(2 != sscanf(s.c_str(), "%hx %hx", &shiftJisValue, &unicodeValue)) //getting hex values
|
|
{
|
|
puts("Error hex reading");
|
|
continue;
|
|
}
|
|
|
|
size_t offset; //array offset
|
|
if((shiftJisValue >> 8) == 0) offset = 0;
|
|
else if((shiftJisValue >> 12) == 0x8) offset = 256;
|
|
else if((shiftJisValue >> 12) == 0x9) offset = 256 + 16*256;
|
|
else if((shiftJisValue >> 12) == 0xE) offset = 256 + 2*16*256;
|
|
else
|
|
{
|
|
puts("Error input values");
|
|
continue;
|
|
}
|
|
|
|
offset = 2 * (offset + (shiftJisValue & 0xfff));
|
|
if(mapping[offset] != 0 || mapping[offset + 1] != 0x20)
|
|
{
|
|
puts("Error mapping not 1:1");
|
|
continue;
|
|
}
|
|
|
|
mapping[offset] = unicodeValue >> 8;
|
|
mapping[offset + 1] = unicodeValue & 0xff;
|
|
}
|
|
|
|
fwrite(mapping, 1, 2*(256 + 3*256*16), stdout);
|
|
delete[] mapping;
|
|
return 0;
|
|
}
|