www.digitalmars.com         C & C++   DMDScript  

digitalmars.D.learn - How-to: input/output "Japanese Characters"?

reply "Tyro[a.c.edwards]" <nospam home.com> writes:
I'm on a Japanese system attempting to input/output Japanese Characters
and cannot seem to accomplish it. How would I read
"憲法記念日　理念と現実、広がる格差" from stdin/file and
output the same 
to stdout/file?

Thanks,
Andrew
May 02 2009
parent reply Georg Wrede <georg.wrede iki.fi> writes:
Tyro[a.c.edwards] wrote:

 I'm on a Japanese system attempting to input/output Japanese Characters
 and cannot seem to accomplish it. How would I read
 "憲法記念日　理念と現実、広がる格差" from stdin/file and
output the same 
 to stdout/file?


import std.stdio;

void main()
{
     auto lin = readln();
     writeln(lin);
}

Works with your Japanese strings. It just works(tm).
May 02 2009
next sibling parent "Tyro[a.c.edwards]" <nospam home.com> writes:
On 5/3/2009 7:41 AM, Georg Wrede wrote:

 Tyro[a.c.edwards] wrote:

 I'm on a Japanese system attempting to input/output Japanese Characters
 and cannot seem to accomplish it. How would I read
 "憲法記念日　理念と現実、広がる格差" from stdin/file and
output the
 same to stdout/file?


 import std.stdio;

 void main()
 {
 auto lin = readln();
 writeln(lin);
 }

 Works with your Japanese strings. It just works(tm).


Interesting... for whatever reason I thought I had to cast/convert
to!dstring in order to get the correct output. Which kept resulting in:

  std.utf.UtfException: 4invalid UTF-8 sequence

thank you very much.
May 02 2009
prev sibling parent reply "Carlos Smith" <carlos-smith sympatico.ca> writes:
"Georg Wrede" <georg.wrede iki.fi> a écrit dans le message de news:


 import std.stdio;

 void main()
 {
     auto lin = readln();
     writeln(lin);
 }

 Works with your Japanese strings. It just works(tm).


I am trying this on a North American WinXP station.
I am using DMD V1.

You will find a small program at the end of this
message who does not work for me.

The console use Lucida COnsole font. The CP is 65001.
cmd.exe can read/write utf strings, but not my
program.

I want to be able to read an utf string from stdin.
That string will contains characters > 256, ie glyphs
you can only see with an unicode font.

I have read some documentation on MSDN that confirm
it can't work. So why does it work for you ?

Can anyone, explain to me what am i doing wrong ?

Thanks a lot...

--------- program ----------
//
//  readln.d
//  testing readln()
//
//  This file saved with BOM: FF FE
//  Edit with Lucida Console font
//

import std.stdio;
import std.c.windows.windows;
import std.c.locale;
import std.utf;

extern( Windows )
{
  HANDLE GetStdHandle( DWORD nStdHandle );
  BOOL WriteConsoleW(
    HANDLE hConsoleOutput,
    in VOID* lpBuffer,
    DWORD nNumberOfCharsToWrite,
    DWORD* lpNumberOfCharsWritten,
    void* lpReserved = null );
  BOOL WriteConsoleA(
    HANDLE hConsoleOutput,
    in VOID* lpBuffer,
    DWORD nNumberOfCharsToWrite,
    DWORD* lpNumberOfCharsWritten,
    void* lpReserved = null );
  BOOL ReadConsoleW( HANDLE hConsoleInput, LPVOID lpBuffer, uint 
nNumberOfCharsToRead,
    uint* lpNumberOfCharsRead, void* pInputControl = null );
  BOOL ReadConsoleA( HANDLE hConsoleInput, LPVOID lpBuffer,  uint 
nNumberOfCharsToRead,
    uint* lpNumberOfCharsRead, void* pInputControl = null );
  version (UNICODE)
    alias ReadConsoleA ReadConsole;
  else
    alias ReadConsoleW ReadConsole;
}


UINT CP, OCP;

void DisplayCP()
{
  writef("Console CP: %s\n", GetConsoleCP());
  writef("Console Output CP: %s\n", GetConsoleOutputCP());
}

void SaveCP()
{
  CP = GetConsoleCP();
  OCP = GetConsoleOutputCP();
}

void SetUnicode()
{
  SetConsoleCP( 65001 );
  SetConsoleOutputCP( 65001 );
}

void ResetCP()
{
  SetConsoleCP( CP );
  SetConsoleOutputCP( OCP );
}

int main( )
{
  HANDLE cout;
  DWORD nw;
  cout = GetStdHandle(STD_OUTPUT_HANDLE);

  DisplayCP();
  SaveCP();
  SetUnicode();
  DisplayCP();

  // writef() do print Unicode string constant
  // next 5 lines contains utf chars.
  wchar[] utfstr = "←↑→↔↨∂∆∏∑−√∞∟∩∫≈═┼┴⌠⌐≥≤≡≠ѕєіїњљ\n";
  writef("1: %s","←↑→↔↨∂∆∏∑−√∞∟∩∫≈═┼┴⌠⌐≥≤≡≠ѕєіїњљ\n");
  writef("2: %s",utfstr);
  // so do WriteConsoleW()
  wchar[] utfstr3 = "3:
←↑→↔↨∂∆∏∑−√∞∟∩∫≈═┼┴⌠⌐≥≤≡≠ѕєіїњљ\n";
  WriteConsoleW(cout, utfstr3.ptr, utfstr3.length, &nw);

  // but not  readln()`ed strings
  writef("Type a line of Unicode characters:\n");
  auto line = readln();
  writef("line len: %s\n", line.length);
  writef("%s\n", "Next line is what You typed:");
  writef("%s\n",line);
  writef("%s\n", "Your line again (with WriteConsoleA):");
  WriteConsoleA(cout, line.ptr, line.length, &nw);
  writef("%s\n", "Your line again (with WriteConsoleW):");
  WriteConsoleW(cout, line.ptr, line.length, &nw);


  writef("Done. Resetting code page.\n");
  ResetCP();
  DisplayCP();
  return 0;
}
--------- eof ---------
May 03 2009
parent reply Georg Wrede <georg.wrede iki.fi> writes:
Carlos Smith wrote:

 "Georg Wrede" <georg.wrede iki.fi> a écrit dans le message de news:
 

 import std.stdio;

 void main()
 {
     auto lin = readln();
     writeln(lin);
 }

 Works with your Japanese strings. It just works(tm).


 
 I am trying this on a North American WinXP station.
 I am using DMD V1.



Sorry, somebody else has to help, I'm not using Windows. :/



 You will find a small program at the end of this
 message who does not work for me.
 
 The console use Lucida COnsole font. The CP is 65001.
 cmd.exe can read/write utf strings, but not my
 program.
 
 I want to be able to read an utf string from stdin.
 That string will contains characters > 256, ie glyphs
 you can only see with an unicode font.
 
 I have read some documentation on MSDN that confirm
 it can't work. So why does it work for you ?
 
 Can anyone, explain to me what am i doing wrong ?
 
 Thanks a lot...
 
 --------- program ----------
 //
 //  readln.d
 //  testing readln()
 //
 //  This file saved with BOM: FF FE
 //  Edit with Lucida Console font
 //
 
 import std.stdio;
 import std.c.windows.windows;
 import std.c.locale;
 import std.utf;
 
 extern( Windows )
 {
  HANDLE GetStdHandle( DWORD nStdHandle );
  BOOL WriteConsoleW(
    HANDLE hConsoleOutput,
    in VOID* lpBuffer,
    DWORD nNumberOfCharsToWrite,
    DWORD* lpNumberOfCharsWritten,
    void* lpReserved = null );
  BOOL WriteConsoleA(
    HANDLE hConsoleOutput,
    in VOID* lpBuffer,
    DWORD nNumberOfCharsToWrite,
    DWORD* lpNumberOfCharsWritten,
    void* lpReserved = null );
  BOOL ReadConsoleW( HANDLE hConsoleInput, LPVOID lpBuffer, uint 
 nNumberOfCharsToRead,
    uint* lpNumberOfCharsRead, void* pInputControl = null );
  BOOL ReadConsoleA( HANDLE hConsoleInput, LPVOID lpBuffer,  uint 
 nNumberOfCharsToRead,
    uint* lpNumberOfCharsRead, void* pInputControl = null );
  version (UNICODE)
    alias ReadConsoleA ReadConsole;
  else
    alias ReadConsoleW ReadConsole;
 }
 
 
 UINT CP, OCP;
 
 void DisplayCP()
 {
  writef("Console CP: %s\n", GetConsoleCP());
  writef("Console Output CP: %s\n", GetConsoleOutputCP());
 }
 
 void SaveCP()
 {
  CP = GetConsoleCP();
  OCP = GetConsoleOutputCP();
 }
 
 void SetUnicode()
 {
  SetConsoleCP( 65001 );
  SetConsoleOutputCP( 65001 );
 }
 
 void ResetCP()
 {
  SetConsoleCP( CP );
  SetConsoleOutputCP( OCP );
 }
 
 int main( )
 {
  HANDLE cout;
  DWORD nw;
  cout = GetStdHandle(STD_OUTPUT_HANDLE);
 
  DisplayCP();
  SaveCP();
  SetUnicode();
  DisplayCP();
 
  // writef() do print Unicode string constant
  // next 5 lines contains utf chars.
  wchar[] utfstr = "←↑→↔↨∂∆∏∑−√∞∟∩∫≈═┼┴⌠⌐≥≤≡≠ѕєіїњљ\n";
  writef("1: %s","←↑→↔↨∂∆∏∑−√∞∟∩∫≈═┼┴⌠⌐≥≤≡≠ѕєіїњљ\n");
  writef("2: %s",utfstr);
  // so do WriteConsoleW()
  wchar[] utfstr3 = "3:
←↑→↔↨∂∆∏∑−√∞∟∩∫≈═┼┴⌠⌐≥≤≡≠ѕєіїњљ\n";
  WriteConsoleW(cout, utfstr3.ptr, utfstr3.length, &nw);
 
  // but not  readln()`ed strings
  writef("Type a line of Unicode characters:\n");
  auto line = readln();
  writef("line len: %s\n", line.length);
  writef("%s\n", "Next line is what You typed:");
  writef("%s\n",line);
  writef("%s\n", "Your line again (with WriteConsoleA):");
  WriteConsoleA(cout, line.ptr, line.length, &nw);
  writef("%s\n", "Your line again (with WriteConsoleW):");
  WriteConsoleW(cout, line.ptr, line.length, &nw);
 
 
  writef("Done. Resetting code page.\n");
  ResetCP();
  DisplayCP();
  return 0;
 }
 --------- eof ---------
May 03 2009
parent "Carlos Smith" <carlos-smith sympatico.ca> writes:
"Georg Wrede" <georg.wrede iki.fi>

 Sorry, somebody else has to help, I'm not using Windows. :/


LOL!

You actualy helped a lot. You are not using Windows !
It works on Linux but not on Windows.

Now, it may work on Windows too. But stream.d must
be modified to take care of the differences between
the following cases:
    
    reading/writing to the console (true stdin/stdout)
    reading/writing to stdin/out redirected
    and probably some others (undocumented) quirks...
    
After some reading on MSDN, i have done some testing and
it works for me now.

Have a very nice Linux Day...
:-)

Thanks.
May 03 2009