void test_operator()
{
printf( ">>>>>>>>> 연산자\n" );
CUString str1 ="hello";
CUString str2 = "bye";
printf( "문자열1:%s\n", str1.GetStr() );
printf( "문자열2:%s\n", str2.GetStr() );
// +
CUString str = str1 + str2;
printf( "operator +: %s\n", str.GetStr() );
// +=
str += " ^^;";
printf( "operator +=: %s\n", str.GetStr() );
// ==
printf( "operator ==: " );
str = "hello";
if( str == "hello" ) {
printf( "%s == hello\n", str.GetStr() );
}
// +=
printf( "operator !=: " );
str = "hello";
if( str != "___" ) {
printf( "%s != ___\n", str.GetStr() );
}
printf( "\n" );
}
void test_debug()
{
CUString t= "ab안녕하세요cd";
printf( "%s\n", t.GetStr() );
printf( "%d\n", t.GetLength() );
printf( "%d\n", t.GetCharLength() );
CUString str_org = "adk안녕하세요zzz";
CUString str = str_org.GetChar(-2);
printf( "[%s]\n", str.GetStr() );
CUString str_org2 = "adk안녕하세요zzz";
CUString str2 = str_org2.GetChars(-2,2);
printf( "[%s]\n", str2.GetStr() );
CUString str_org3 = "adk안녕하세요zzz";
int diff = str_org3.DeleteChars(3,400);
printf( "[%s]%d\n", str_org3.GetStr(), diff );
CUString rev_test = "abcd1a234";
int find = rev_test.ReverseFind( '4' );
printf( "[%s]%d\n", rev_test.GetStr(), find );
str = "a b";
str.Replace( " ", " " );
printf( "%s\n", str.GetStr() );
}
void test_del()
{
CUString str = "hello<TAG>this should be deleted.</TAG>bye and <TAG>this also</TAG>bye";
fprintf( stderr, "before:%s\n", str.GetStr() );
int cnt = str.DeleteBoundTag( "<TAG>", "</TAG>" );
fprintf( stderr, "after :%s\n%d", str.GetStr(), cnt );
fprintf( stderr, "\n");
fprintf( stderr, "\n");
}
void load( char *prefix, char *key )
{
CUMGT mgt;
if( mgt.Load( prefix ) == false )
{
fprintf( stderr, "Error: fail to load %s\n", prefix );
return;
}
fprintf( stderr, "Record: %d\n", mgt.GetNumRecord() );
CUMGTInfo info;
if( mgt.GetInfo( key, info ) == false )
{
fprintf( stderr, "No key: %s\n", key );
}
else
{
CUString ret;
if( mgt.GetContent( info, ret ) == false )
{
fprintf( stderr, "Fail to get content\n" );
}
else
{
fprintf( stdout, "%s", ret.GetStr() );
}
}
}
void test_replace()
{
printf( ">>>>>>>>> Replace 테스트\n" );
CUString str;
str = "hello this is my ... ";
int num = str.Replace( "...", "" );
str.Print( stderr );
fprintf( stderr, "%s[%d]\n",str.GetStr(), num );
printf( "\n" );
}
void replace_test()
{
CUString str;
str = "hello this is my ... ";
str = "abababab___";
int num = str.Replace( "aba", "$" );
str.Print( stderr );
fprintf( stderr, "%s[%d]\n",str.GetStr(), num );
}
void test_checknum()
{
printf( ">>>>>>>>> 숫자체크\n" );
CUString str;
str="123344";
if(str.IsNumber() ) {
fprintf(stderr, "%s is number\n", str.GetStr() );
}
else {
fprintf(stderr, "%s is not number\n", str.GetStr() );
}
str="12,344";
if(str.IsNumber() ) {
fprintf(stderr, "%s is number\n", str.GetStr() );
}
else {
fprintf(stderr, "%s is not number\n", str.GetStr() );
}
str="1344하이";
if(str.IsNumber() ) {
fprintf(stderr, "%s is number\n", str.GetStr() );
}
else {
fprintf(stderr, "%s is not number\n", str.GetStr() );
}
printf( "\n" );
}
bool CUIndexFile::Load( char *prefix )
{
Close();
char buf[1024];
sprintf( buf, "%s.uidx-key", prefix );
if( key_file.OpenFile( buf, "r" ) == false )
{
return false;
}
sprintf( buf, "%s.uidx-value", prefix );
if( value_file.OpenFile( buf, "r" ) == false )
{
return false;
}
info_map.clear();
while( true )
{
CUString line;
if( key_file.ReadLine( line ) == false ) break;
CUStringList list( line, "\t" );
if( list.GetSize() != 4 ) {
fprintf( stderr, "Error: Invalid format: %s\n", line.GetStr() );
return false;
}
if( info_map.find( list.GetAt(0) ) != info_map.end() )
{
fprintf( stderr, "Error: Duplicated key: %s\n", list.GetAt(0) );
return false;
}
CUIndexFileInfo info;
info.start = atol( list.GetAt(1) );
info.end = atol( list.GetAt(2) );
if( strcmp( list.GetAt(3), "0" ) == 0 ) info.enable = false;
else info.enable = true;
info_map[ list.GetAt(0) ] = info;
}
return true;
}
CUString EncodeUTF8( CUString &str )
{
CUString ret = "";
if( str.GetLength() == 6 ) {
ret = str.SubStr( 2,6 );
unsigned long index;
index = strtoul( ret.GetStr(), 0, 16 );
if( 0x00 <= index && index <= 0x7F ) {
char buf[4]; sprintf( buf, "%c", (char)index );
ret = buf;
}
else if( 0x80 <= index && index <= 0x07FF ) {
// 2byte;
int enc_ch1 = 0xC0; // 11000000
int enc_ch2 = 0x80; // 10000000
char ch1 = (char)strtoul( ret.SubStr(0,2).GetStr(), 0, 16 );
char ch2 = (char)strtoul( ret.SubStr(2,4).GetStr(), 0, 16 );
if( ch1 & (1 << (3-1) ) ) { enc_ch1 |= (1 << (5-1) ); }
if( ch1 & (1 << (2-1) ) ) { enc_ch1 |= (1 << (4-1) ); }
if( ch1 & (1 << (1-1) ) ) { enc_ch1 |= (1 << (3-1) ); }
if( ch2 & (1 << (8-1) ) ) { enc_ch1 |= (1 << (2-1) ); }
if( ch2 & (1 << (7-1) ) ) { enc_ch1 |= (1 << (1-1) ); }
if( ch2 & (1 << (6-1) ) ) { enc_ch2 |= (1 << (6-1) ); }
if( ch2 & (1 << (5-1) ) ) { enc_ch2 |= (1 << (5-1) ); }
if( ch2 & (1 << (4-1) ) ) { enc_ch2 |= (1 << (4-1) ); }
if( ch2 & (1 << (3-1) ) ) { enc_ch2 |= (1 << (3-1) ); }
if( ch2 & (1 << (2-1) ) ) { enc_ch2 |= (1 << (2-1) ); }
if( ch2 & (1 << (1-1) ) ) { enc_ch2 |= (1 << (1-1) ); }
//dumptoBin( enc_ch1 ); dumptoBin( enc_ch2 );
char buf[4]; sprintf( buf, "%c%c", enc_ch1, enc_ch2 );
ret = buf;
}
else if( 0x0800 <= index && index <= 0xFFFF ) {
// 3byte;
char enc_ch1 = 0xE0; // 11100000
char enc_ch2 = 0x80; // 10000000
char enc_ch3 = 0x80; // 10000000
char ch1 = (char)strtoul( ret.SubStr(0,2).GetStr(), 0, 16 );
char ch2 = (char)strtoul( ret.SubStr(2,4).GetStr(), 0, 16 );
if( ch1 & (1 << (8-1) ) ) { enc_ch1 |= (1 << (4-1) ); }
if( ch1 & (1 << (7-1) ) ) { enc_ch1 |= (1 << (3-1) ); }
if( ch1 & (1 << (6-1) ) ) { enc_ch1 |= (1 << (2-1) ); }
if( ch1 & (1 << (5-1) ) ) { enc_ch1 |= (1 << (1-1) ); }
if( ch1 & (1 << (4-1) ) ) { enc_ch2 |= (1 << (6-1) ); }
if( ch1 & (1 << (3-1) ) ) { enc_ch2 |= (1 << (5-1) ); }
if( ch1 & (1 << (2-1) ) ) { enc_ch2 |= (1 << (4-1) ); }
if( ch1 & (1 << (1-1) ) ) { enc_ch2 |= (1 << (3-1) ); }
if( ch2 & (1 << (8-1) ) ) { enc_ch2 |= (1 << (2-1) ); }
if( ch2 & (1 << (7-1) ) ) { enc_ch2 |= (1 << (1-1) ); }
if( ch2 & (1 << (6-1) ) ) { enc_ch3 |= (1 << (6-1) ); }
if( ch2 & (1 << (5-1) ) ) { enc_ch3 |= (1 << (5-1) ); }
if( ch2 & (1 << (4-1) ) ) { enc_ch3 |= (1 << (4-1) ); }
if( ch2 & (1 << (3-1) ) ) { enc_ch3 |= (1 << (3-1) ); }
if( ch2 & (1 << (2-1) ) ) { enc_ch3 |= (1 << (2-1) ); }
if( ch2 & (1 << (1-1) ) ) { enc_ch3 |= (1 << (1-1) ); }
//dumptoBin( enc_ch1 ); dumptoBin( enc_ch2 ); dumptoBin( enc_ch3 );
char buf[4]; sprintf( buf, "%c%c%c", enc_ch1, enc_ch2, enc_ch3 );
ret = buf;
}
}
return ret;
}
bool CDecoder::LoadFoundation( CUOption* option )
{
if( option == NULL ) return false;
this->option = option;
// check options
CUString key="foundation";
CUString foundation_dn;
if( option->GetValue( key, foundation_dn ) == false ) { fprintf( stderr, "Required option is not defined: foundation\n" ); return false; }
this->foundation_dn = foundation_dn;
char fn[1024];
sprintf( fn ,"%s/pair.utf8", foundation_dn.GetStr() );
CUTextFile file( fn, "r" );
if( file.CheckOpen() == false ) return false;
CUString content;
file.LoadToStr( content );
CUStringListRO content_list( content, "\n" );
if( content_list.GetSize() < 4 ) { fprintf( stderr, "Error: Invalid pair.utf\n" ); return false; }
src_org = content_list.GetAt(0);
tgt_org = content_list.GetAt(1);
src_tok = content_list.GetAt(2);
tgt_tok = content_list.GetAt(3);
// load trans tree
CUStringListRO src_tok_list( src_tok, " " );
trans_tree.Set( src_tok_list );
for( int i=4; i<content_list.GetSize(); i++ ) {
CUString str = content_list.GetAt(i);
if( str.Find( "S-P\t") == 0 ) {
CUStringListRO tmp_list( str.Mid(4), ":" );
if( trans_tree.ApplyParse( tmp_list ) == false ) {
fprintf( stderr, "Error: Invalid parse rule: %s\n", str.GetStr() );
return false;
}
else {
//trans_tree.Print( stderr );
}
}
}
// apply trans rule
for( int i=4; i<content_list.GetSize(); i++ ) {
CUString str = content_list.GetAt(i);
if( str.Find( "TR\t") == 0 ) {
CUStringListRO tmp_list( str.Mid(3), "\t" );
if( trans_tree.ApplyTransRule( tmp_list ) == false ) {
fprintf( stderr, "Error: Invalid parse rule: %s\n", str.GetStr() );
return false;
}
else {
//trans_tree.Print( stderr );
}
}
}
// apply trans rule
for( int i=4; i<content_list.GetSize(); i++ ) {
CUString str = content_list.GetAt(i);
if( str.Find( "TL\t") == 0 ) {
CUStringListRO tmp_list( str.Mid(3), "\t" );
if( trans_tree.ApplyTransLexical( tmp_list ) == false ) {
fprintf( stderr, "Error: Invalid parse lexical: %s\n", str.GetStr() );
return false;
}
else {
//trans_tree.Print( stderr );
}
}
}
trans_tree.OrderByTrans();
trans_tree.Print( stderr );
CUString trans_str = trans_tree.GetTransStr();
CUStringListRO tmp1( tgt_tok, " " );
fprintf( stderr, "TGT: " );
for( int i=0; i<tmp1.GetSize(); i++ ) {
CUString tmp = tmp1.GetAt(i);
fprintf( stderr, " %s", tmp.Left( tmp.ReverseFind('/') ).GetStr() );
}
fprintf( stderr, "\n" );
CUStringListRO tmp2( trans_str, " " );
fprintf( stderr, "OUT: " );
for( int i=0; i<tmp2.GetSize(); i++ ) {
CUString tmp = tmp2.GetAt(i);
fprintf( stderr, " %s", tmp.Left( tmp.ReverseFind('/') ).GetStr() );
}
fprintf( stderr, "\n" );
return true;
}
bool CUStringNode::SetData( CUString &arg_str )
{
return SetData( (char*)arg_str.GetStr() );
}
