kcharsets.cpp
00001
00002
00003
00004
00005
00006
00007
00008
00009
00010
00011
00012
00013
00014
00015
00016
00017
00018
00019
00020
#include "kcharsets.h"
00021
00022
#include "kentities.c"
00023
00024
#include <kapplication.h>
00025
#include <kglobal.h>
00026
#include <klocale.h>
00027
#include <kconfig.h>
00028
00029
#include <qfontinfo.h>
00030
#include <qstrlist.h>
00031
#include <qfontdatabase.h>
00032
#include <kdebug.h>
00033
00034
#include <qtextcodec.h>
00035
#include <qmap.h>
00036
#include <qcstring.h>
00037
00038
#include <assert.h>
00039
00040
#define CHARSETS_COUNT 33
00041
00042
static const char *
const language_names[] = {
00043 I18N_NOOP(
"Other" ),
00044 I18N_NOOP(
"Arabic" ),
00045 I18N_NOOP(
"Baltic" ),
00046 I18N_NOOP(
"Central European" ),
00047 I18N_NOOP(
"Chinese Simplified" ),
00048 I18N_NOOP(
"Chinese Traditional" ),
00049 I18N_NOOP(
"Cyrillic" ),
00050 I18N_NOOP(
"Greek" ),
00051 I18N_NOOP(
"Hebrew" ),
00052 I18N_NOOP(
"Japanese" ),
00053 I18N_NOOP(
"Korean" ),
00054 I18N_NOOP(
"Thai" ),
00055 I18N_NOOP(
"Turkish" ),
00056 I18N_NOOP(
"Western European" ),
00057 I18N_NOOP(
"Tamil" ),
00058 I18N_NOOP(
"Unicode" ),
00059 I18N_NOOP(
"Northern Saami" )
00060 };
00061
00062
00063
00064
00065
00066
00067
00068
00069
00070
static const char*
const charsets_for_encoding[] = {
00071
"koi8-r",
"koi8-r",
"cp 1251",
"koi8-u",
"iso-8859-5", 0,
00072
"koi8-u",
"koi8-u",
"cp 1251",
"iso-8859-5",
"koi8-r", 0,
00073
"iso 8859-1",
"iso8859-1",
"iso8859-15", 0,
00074
"iso 8859-2",
"iso8859-2",
"unicode",
"iso8859-1", 0,
00075
"iso 8859-3",
"iso8859-3",
"unicode",
"iso8859-1", 0,
00076
"iso 8859-4",
"iso8859-4",
"unicode",
"iso8859-13",
"iso8859-1", 0,
00077
"iso 8859-5",
"iso8859-5",
"koi8-u",
"koi8-r", 0,
00078
"iso 8859-6",
"unicode",
"iso8859-6", 0,
00079
"iso 8859-7",
"iso8859-7", 0,
00080
"iso 8859-8",
"iso8859-8", 0,
00081
"iso 8859-8-i",
"iso8859-8", 0,
00082
"iso 8859-9",
"iso8859-9",
"unicode",
"iso8859-1", 0,
00083
"iso 8859-11",
"iso8859-11", 0,
00084
"iso 8859-13",
"iso8859-13",
"unicode",
"iso8859-4",
"iso8859-1", 0,
00085
"iso 8859-15",
"iso8859-15",
"unicode",
"iso8859-1", 0,
00086
"utf8",
"unicode",
"iso8859-1", 0,
00087
"utf16",
"unicode",
"iso8859-1", 0,
00088
"iso-10646-ucs-2",
"unicode",
"iso8859-1", 0,
00089
"cp 1250",
"iso8859-2", 0,
00090
"cp 1251",
"cp 1251",
"koi8-u",
"koi8-r",
"iso8859-5", 0,
00091
"cp 1252",
"iso8859-1", 0,
00092
"cp 1253",
"iso8859-7", 0,
00093
"cp 1254",
"iso8859-9", 0,
00094
"cp 1255",
"iso8859-8", 0,
00095
"cp 1256",
"unicode",
"iso8859-6", 0,
00096
"cp 1257",
"iso8859-13",
"iso8859-4", 0,
00097
"ibm850",
"ibm850",
"unicode",
"iso8859-1", 0,
00098
"ibm852",
"unicode",
"iso-8859-2", 0,
00099
"ibm866",
"ibm866",
"cp 1251",
"koi8-u",
"koi8-r",
"iso8859-5", 0,
00100
"tis620",
"iso8859-11", 0,
00101
"eucjp",
"eucjp",
"unicode",
"iso8859-1", 0,
00102
"sjis",
"eucjp",
"unicode",
"iso8859-1", 0,
00103
"jis7",
"eucjp",
"unicode",
"iso8859-1", 0,
00104
"big5",
"big5",
"unicode",
"iso8859-1", 0,
00105
"gbk",
"gb2312.1980-0",
"gbk-0",
"unicode",
"iso8859-1", 0,
00106
"gb18030",
"gb18030.2000-1",
"gb18030.2000-0",
"unicode",
"gbk-0",
"gb2313.1980-0",
"iso8859-1", 0,
00107
"gb2312",
"gb2312.1980-0",
"unicode",
"iso8859-1", 0,
00108
"euckr",
"euckr",
"unicode",
"iso8859-1", 0,
00109
"tscii",
"tscii", 0,
00110
"pt 154",
"pt 154",
"cp 1251",
"koi8-u",
"koi8-r",
"iso8859-5", 0,
00111
"winsami2",
"winsami2",
"cp1252",
"unicode", 0,
00112 0 };
00113
00114
00115
00116
00117
00118
00119
00120
00121
00122
00123
00124
00125
00126
00127
00128
00129
00130
00131
static struct LanguageForEncoding
00132 {
00133
const char* index;
00134
int data;
00135 }
const language_for_encoding[] = {
00136 {
"iso 8859-1", 13 },
00137 {
"iso 8859-15", 13 },
00138 {
"cp 1252", 13 },
00139 {
"ibm850", 13 },
00140 {
"iso 8859-2", 3 },
00141 {
"iso 8859-3", 3 },
00142 {
"iso 8859-4", 2 },
00143 {
"iso 8859-13", 2 },
00144 {
"cp 1250", 3 },
00145 {
"cp 1254", 12 },
00146 {
"cp 1257", 2 },
00147 {
"ibm852", 3 },
00148 {
"koi8-r", 6 },
00149 {
"iso 8859-5", 6 },
00150 {
"cp 1251", 6 },
00151 {
"koi8-u", 6 },
00152 {
"pt 154", 6 },
00153 {
"ibm866", 6 },
00154 {
"big5", 5 },
00155 {
"gb18030", 4 },
00156 {
"gbk", 4 },
00157 {
"gb2312", 4 },
00158 {
"euckr", 10 },
00159 {
"sjis", 9 },
00160 {
"jis7", 9 },
00161 {
"eucjp", 9 },
00162 {
"iso 8859-7", 7 },
00163 {
"cp 1253", 7 },
00164 {
"iso 8859-6", 1 },
00165 {
"cp 1256", 1 },
00166 {
"iso 8859-8", 8 },
00167 {
"iso 8859-8-i", 8 },
00168 {
"cp 1255", 8 },
00169 {
"iso 8859-9", 12 },
00170 {
"tis620", 11 },
00171 {
"iso 8859-11", 11 },
00172 {
"utf8", 15 },
00173 {
"utf16", 15 },
00174 {
"utf7", 15 },
00175 {
"ucs2", 15 },
00176 {
"iso-10646-ucs-2", 15 },
00177 {
"winsami2", 16},
00178 { 0, 0 } };
00179
00180
00181
static struct Builtin
00182 {
00183
const char* index;
00184
const char* data;
00185 }
const builtin[] = {
00186 {
"iso-ir-111",
"koi8-r" },
00187 {
"koi8-ru",
"koi8-u" },
00188 {
"koi8r",
"koi8-r" },
00189 {
"koi8u",
"koi8-u" },
00190 {
"koi unified",
"koi8-r" },
00191 {
"us-ascii",
"iso 8859-1" },
00192 {
"usascii",
"iso 8859-1" },
00193 {
"x-utf-8",
"utf-8" },
00194 {
"x-utf-7",
"utf-7" },
00195 {
"unicode-1-1-utf-7",
"utf-7" },
00196 {
"ucs2",
"iso-10646-ucs-2" },
00197 {
"iso10646-1",
"iso-10646-ucs-2" },
00198 {
"gb18030.2000-1",
"gb18030" },
00199 {
"gb18030.2000-0",
"gb18030" },
00200 {
"gbk-0",
"gbk" },
00201 {
"gb2312",
"gbk" },
00202 {
"gb2312.1980-0",
"gbk" },
00203 {
"big5-0",
"big5" },
00204 {
"euc-kr",
"euckr" },
00205 {
"x-euc-kr",
"euckr" },
00206 {
"euc-jp",
"eucjp" },
00207 {
"x-euc-jp",
"eucjp" },
00208 {
"jisx0201.1976-0",
"eucjp" },
00209 {
"jisx0208.1983-0",
"eucjp" },
00210 {
"jisx0208.1990-0",
"eucjp" },
00211 {
"jisx0208.1997-0",
"eucjp" },
00212 {
"jisx0212.1990-0",
"eucjp" },
00213 {
"jisx0213.2000-1",
"eucjp" },
00214 {
"jisx0213.2000-2",
"eucjp" },
00215 {
"shift_jis",
"sjis" },
00216 {
"shift-jis",
"sjis" },
00217 {
"x-sjis",
"sjis" },
00218 {
"iso-2022-jp",
"jis7" },
00219 {
"windows850",
"ibm850" },
00220 {
"windows866",
"ibm866" },
00221 {
"windows1251",
"cp 1251" },
00222 {
"windows1252",
"cp 1252" },
00223 {
"windows1253",
"cp 1253" },
00224 {
"windows1254",
"cp 1254" },
00225 {
"windows1255",
"cp 1255" },
00226 {
"windows1256",
"cp 1256" },
00227 {
"windows1257",
"cp 1257" },
00228 {
"windows-850",
"ibm850" },
00229 {
"windows-866",
"ibm866" },
00230 {
"windows-1250",
"cp 1250" },
00231 {
"windows-1251",
"cp 1251" },
00232 {
"windows-1252",
"cp 1252" },
00233 {
"windows-1253",
"cp 1253" },
00234 {
"windows-1254",
"cp 1254" },
00235 {
"windows-1255",
"cp 1255" },
00236 {
"windows-1256",
"cp 1256" },
00237 {
"windows-1257",
"cp 1257" },
00238 {
"x-windows-850",
"ibm850" },
00239 {
"x-windows-866",
"ibm866" },
00240 {
"x-windows-1250",
"cp 1250" },
00241 {
"x-windows-1251",
"cp 1251" },
00242 {
"x-windows-1252",
"cp 1252" },
00243 {
"x-windows-1253",
"cp 1253" },
00244 {
"x-windows-1254",
"cp 1254" },
00245 {
"x-windows-1255",
"cp 1255" },
00246 {
"x-windows-1256",
"cp 1256" },
00247 {
"x-windows-1257",
"cp 1257" },
00248 {
"cp850",
"ibm850" },
00249 {
"cp866",
"ibm866" },
00250 {
"cp-850",
"ibm850" },
00251 {
"cp-866",
"ibm866" },
00252 {
"cp-1250",
"cp 1250" },
00253 {
"cp-1251",
"cp 1251" },
00254 {
"cp-1252",
"cp 1252" },
00255 {
"cp-1253",
"cp 1253" },
00256 {
"cp-1254",
"cp 1254" },
00257 {
"cp-1255",
"cp 1255" },
00258 {
"cp-1256",
"cp 1256" },
00259 {
"cp-1257",
"cp 1257" },
00260 {
"x-cp-850",
"ibm850" },
00261 {
"x-cp-866",
"ibm866" },
00262 {
"x-cp-1250",
"cp 1250" },
00263 {
"x-cp-1251",
"cp 1251" },
00264 {
"x-cp-1252",
"cp 1252" },
00265 {
"x-cp-1253",
"cp 1253" },
00266 {
"x-cp-1254",
"cp 1254" },
00267 {
"x-cp-1255",
"cp 1255" },
00268 {
"x-cp-1256",
"cp 1256" },
00269 {
"x-cp-1257",
"cp 1257" },
00270 {
"tis620",
"iso 8859-11" },
00271 {
"tis-620",
"iso 8859-11" },
00272 {
"thai-tis620",
"iso 8859-11" },
00273 {
"windows-874",
"iso 8859-11" },
00274 {
"windows874",
"iso 8859-11" },
00275 {
"x-windows-874",
"iso 8859-11" },
00276 {
"cp874",
"iso 8859-11" },
00277 {
"cp-874",
"iso 8859-11" },
00278 {
"x-cp-874",
"iso 8859-11" },
00279 {
"ksc5601.1987-0",
"euckr" },
00280 {
"ks_c_5601-1987",
"euckr" },
00281 {
"iso-8859-1",
"iso 8859-1" },
00282 {
"iso-8859-2",
"iso 8859-2" },
00283 {
"iso-8859-3",
"iso 8859-3" },
00284 {
"iso-8859-4",
"iso 8859-4" },
00285 {
"iso-8859-5",
"iso 8859-5" },
00286 {
"iso-8859-6",
"iso 8859-6" },
00287 {
"iso-8859-7",
"iso 8859-7" },
00288 {
"iso-8859-8",
"iso 8859-8" },
00289 {
"iso-8859-9",
"iso 8859-9" },
00290 {
"iso-8859-10",
"iso 8859-10" },
00291 {
"iso-8859-11",
"iso 8859-11" },
00292 {
"iso-8859-12",
"iso 8859-12" },
00293 {
"iso-8859-13",
"iso 8859-13" },
00294 {
"iso-8859-14",
"iso 8859-14" },
00295 {
"iso-8859-15",
"iso 8859-15" },
00296 {
"tscii",
"tscii" },
00297 {
"paratype-154",
"pt 154" },
00298 {
"pt-154",
"pt 154" },
00299 {
"x-winsami2",
"winsami2" },
00300 { 0, 0 }};
00301
00302
00303
00304
static struct Aliases
00305 {
00306
const char* index;
00307
const char* data;
00308 }
const aliases[] = {
00309 {
"cp852",
"ibm852" },
00310 {
"cp-852",
"ibm852" },
00311 {
"x-cp-852",
"ibm852" },
00312 {
"windows852",
"ibm852" },
00313 {
"windows-852",
"ibm852" },
00314 {
"x-windows-852",
"ibm852" },
00315 { 0, 0 }};
00316
00317
00318
00319
00320
static struct ConversionHints
00321 {
00322
const char* index;
00323
const char* data;
00324 }
const conversion_hints[] = {
00325 {
"cp1250",
"iso-8859-2" },
00326 {
"koi8-r",
"iso-8859-5" },
00327 {
"koi8-u",
"koi8-r" },
00328 {
"utf16",
"iso-10646-ucs-2" },
00329 { 0, 0 }};
00330
00331
00332
00333
00334
template<
typename T,
typename Data >
00335
static Data kcharsets_array_search(
const T* start,
const char* entry )
00336 {
00337
for(
const T* pos = start;
00338 pos->index != 0;
00339 ++pos )
00340
if( qstrcmp( pos->index, entry ) == 0 )
00341
return pos->data;
00342
return 0;
00343 }
00344
00345
00346
class KCharsetsPrivate
00347 {
00348
public:
00349 KCharsetsPrivate(
KCharsets* _kc)
00350 : codecForNameDict(43, false)
00351 {
00352 db = 0;
00353 kc = _kc;
00354 }
00355 ~KCharsetsPrivate()
00356 {
00357
delete db;
00358 }
00359
QFontDatabase *db;
00360
QAsciiDict<QTextCodec> codecForNameDict;
00361
KCharsets* kc;
00362 };
00363
00364
00365
00366 KCharsets::KCharsets()
00367 {
00368 d =
new KCharsetsPrivate(
this);
00369 }
00370
00371 KCharsets::~KCharsets()
00372 {
00373
delete d;
00374 }
00375
00376 QChar KCharsets::fromEntity(
const QString &str)
00377 {
00378
QChar res = QChar::null;
00379
00380
int pos = 0;
00381
if(str[pos] ==
'&') pos++;
00382
00383
00384
if (str[pos] ==
'#' && str.length()-pos > 1) {
00385
bool ok;
00386 pos++;
00387
if (str[pos] ==
'x' || str[pos] ==
'X') {
00388 pos++;
00389
00390
QString tmp(str.unicode()+pos, str.length()-pos);
00391 res = tmp.toInt(&ok, 16);
00392 }
else {
00393
00394
QString tmp(str.unicode()+pos, str.length()-pos);
00395 res = tmp.toInt(&ok, 10);
00396 }
00397
return res;
00398 }
00399
00400
const entity *e = kde_findEntity(str.ascii(), str.length());
00401
00402
if(!e)
00403 {
00404
00405
return QChar::null;
00406 }
00407
00408
00409
return QChar(e->code);
00410 }
00411
00412 QChar KCharsets::fromEntity(
const QString &str,
int &len)
00413 {
00414
00415
00416 len = 8;
00417
while(len > 0)
00418 {
00419
QString tmp = str.left(len);
00420
QChar res =
fromEntity(tmp);
00421
if( res != QChar::null )
return res;
00422 len--;
00423 }
00424
return QChar::null;
00425 }
00426
00427
00428 QString KCharsets::toEntity(
const QChar &ch)
00429 {
00430
QString ent;
00431 ent.sprintf(
"�x%x;", ch.unicode());
00432
return ent;
00433 }
00434
00435 QString KCharsets::resolveEntities(
const QString &input )
00436 {
00437
QString text = input;
00438
const QChar *p = text.unicode();
00439
const QChar *end = p + text.length();
00440
const QChar *ampersand = 0;
00441
bool scanForSemicolon =
false;
00442
00443
for ( ; p < end; ++p ) {
00444
const QChar ch = *p;
00445
00446
if ( ch ==
'&' ) {
00447 ampersand = p;
00448 scanForSemicolon =
true;
00449
continue;
00450 }
00451
00452
if ( ch !=
';' || scanForSemicolon ==
false )
00453
continue;
00454
00455 assert( ampersand );
00456
00457 scanForSemicolon =
false;
00458
00459
const QChar *entityBegin = ampersand + 1;
00460
00461
const uint entityLength = p - entityBegin;
00462
if ( entityLength == 0 )
00463
continue;
00464
00465
const QChar entityValue =
KCharsets::fromEntity(
QConstString( entityBegin, entityLength ).string() );
00466
if ( entityValue.isNull() )
00467
continue;
00468
00469
const uint ampersandPos = ampersand - text.unicode();
00470
00471 text[ ampersandPos ] = entityValue;
00472 text.remove( ampersandPos + 1, entityLength + 1 );
00473 p = text.unicode() + ampersandPos;
00474 end = text.unicode() + text.length();
00475 ampersand = 0;
00476 }
00477
00478
return text;
00479 }
00480
00481 QStringList KCharsets::availableEncodingNames()
00482 {
00483
QStringList available;
00484
00485
const char*
const* pos = charsets_for_encoding;
00486
while( *pos != 0 ) {
00487
00488
00489
00490
00491
for(
const char*
const* charsets = pos + 1;
00492 *charsets != 0;
00493 ++charsets ) {
00494
00495
#ifdef __GNUC__
00496
#warning FIXME?
00497
#endif
00498
if(
true ) {
00499
00500 available.append( QString::fromLatin1( *pos ));
00501
break;
00502 }
00503 }
00504
while( *pos != 0 )
00505 ++pos;
00506 ++pos;
00507 }
00508
return available;
00509 }
00510
00511 QString KCharsets::languageForEncoding(
const QString &encoding )
00512 {
00513
int lang = kcharsets_array_search< LanguageForEncoding, int >
00514 ( language_for_encoding, encoding.latin1());
00515
return i18n( language_names[lang] );
00516 }
00517
00518 QString KCharsets::encodingForName(
const QString &descriptiveName )
00519 {
00520
const int left = descriptiveName.findRev(
'(' );
00521
00522
if (left<0)
00523
return descriptiveName.stripWhiteSpace();
00524
00525
QString name(descriptiveName.mid(left+1));
00526
00527
const int right = name.findRev(
')' );
00528
00529
if (right<0)
00530
return name;
00531
00532
return name.left(right).stripWhiteSpace();
00533 }
00534
00535 QStringList KCharsets::descriptiveEncodingNames()
00536 {
00537
QStringList encodings =
availableEncodingNames();
00538 QStringList::Iterator it;
00539
for( it = encodings.begin(); it != encodings.end(); ++it ) {
00540
QString lang =
KGlobal::charsets()->
languageForEncoding( *it );
00541 *it = i18n(
"Descriptive Encoding Name",
"%1 ( %2 )") .arg(lang) .arg(*it);
00542 }
00543 encodings.sort();
00544
return encodings;
00545 }
00546
00547 QTextCodec *
KCharsets::codecForName(
const QString &n)
const
00548
{
00549
bool b;
00550
return codecForName( n, b );
00551 }
00552
00553 QTextCodec *
KCharsets::codecForName(
const QString &n,
bool &ok)
const
00554
{
00555 ok =
true;
00556
00557
QTextCodec* codec = 0;
00558
00559
if((codec = d->codecForNameDict[n.isEmpty() ?
"->locale<-" : n.latin1()]))
00560
return codec;
00561
00562
if (n.isEmpty()) {
00563 codec =
KGlobal::locale()->
codecForEncoding();
00564 d->codecForNameDict.replace(
"->locale<-", codec);
00565
return codec;
00566 }
00567
00568
QCString name = n.lower().latin1();
00569
QCString key = name;
00570
if (name.right(8) ==
"_charset")
00571 name.truncate(name.length()-8);
00572
00573
if (name.isEmpty()) {
00574 ok =
false;
00575
return QTextCodec::codecForName(
"iso8859-1");
00576 }
00577
00578 codec = QTextCodec::codecForName(name);
00579
00580
if(codec) {
00581 d->codecForNameDict.replace(key, codec);
00582
return codec;
00583 }
00584
00585
00586
00587
QCString cname = kcharsets_array_search< Builtin, const char* >( builtin, name.data());
00588
00589
if(!cname.isEmpty())
00590 codec = QTextCodec::codecForName(cname);
00591
00592
if(codec)
00593 {
00594 d->codecForNameDict.replace(key, codec);
00595
return codec;
00596 }
00597
00598
QString dir;
00599 {
00600
KConfigGroupSaver cfgsav( KGlobal::config(),
"i18n" );
00601 dir =
KGlobal::config()->
readPathEntry(
"i18ndir", QString::fromLatin1(
"/usr/share/i18n/charmaps"));
00602 dir +=
"/";
00603 }
00604
00605
00606
00607 cname = kcharsets_array_search< Aliases, const char* >( aliases, name.data());
00608
00609
if(cname.isEmpty())
00610 cname = name;
00611 cname = cname.upper();
00612
00613 codec = QTextCodec::loadCharmapFile((
QString)(dir + cname.data()));
00614
00615
if(codec) {
00616 d->codecForNameDict.replace(key, codec);
00617
return codec;
00618 }
00619
00620
00621
00622 cname = cname.lower();
00623 cname = kcharsets_array_search< ConversionHints, const char* >( conversion_hints, (
const char*)cname );
00624
00625
if(!cname.isEmpty())
00626 codec = QTextCodec::codecForName(cname);
00627
00628
if(codec) {
00629 d->codecForNameDict.replace(key, codec);
00630
return codec;
00631 }
00632
00633
00634 ok =
false;
00635
return QTextCodec::codecForName(
"iso8859-1");
00636 }
This file is part of the documentation for kdecore Library Version 3.3.0.