flourish /classes/fUTF8.php

Language PHP Lines 1640
MD5 Hash c9f6b48fb2a19f8390197d74b4538bcb Estimated Cost $27,159 (why?)
Repository https://bitbucket.org/wbond/flourish/ View Raw File View Project SPDX
   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
<?php
/**
 * Provides string functions for UTF-8 strings
 * 
 * This class is implemented to provide a UTF-8 version of almost every built-in
 * PHP string function. For more information about UTF-8, please visit
 * http://flourishlib.com/docs/UTF-8.
 * 
 * @copyright  Copyright (c) 2008-2011 Will Bond
 * @author     Will Bond [wb] <will@flourishlib.com>
 * @license    http://flourishlib.com/license
 * 
 * @package    Flourish
 * @link       http://flourishlib.com/fUTF8
 * 
 * @version    1.0.0b15
 * @changes    1.0.0b15  Fixed a bug with using IBM's iconv implementation on AIX [wb, 2011-07-29]
 * @changes    1.0.0b14  Added a workaround for iconv having issues in MAMP 1.9.4+ [wb, 2011-07-26]
 * @changes    1.0.0b13  Fixed notices from being thrown when invalid data is sent to ::clean() [wb, 2011-06-10]
 * @changes    1.0.0b12  Fixed a variable name typo in ::sub() [wb, 2011-05-09]
 * @changes    1.0.0b11  Updated the class to not using phpinfo() to determine the iconv implementation [wb, 2010-11-04]
 * @changes    1.0.0b10  Fixed a bug with capitalizing a lowercase i resulting in a dotted upper-case I [wb, 2010-11-01]
 * @changes    1.0.0b9   Updated class to use fCore::startErrorCapture() instead of `error_reporting()` [wb, 2010-08-09]
 * @changes    1.0.0b8   Removed `e` flag from preg_replace() calls [wb, 2010-06-08]
 * @changes    1.0.0b7   Added the methods ::trim(), ::rtrim() and ::ltrim() [wb, 2010-05-11]
 * @changes    1.0.0b6   Fixed ::clean() to work with PHP installs that use an iconv library that doesn't support //IGNORE [wb, 2010-03-02]
 * @changes    1.0.0b5   Changed ::ucwords() to also uppercase words right after various punctuation [wb, 2009-09-18]
 * @changes    1.0.0b4   Changed replacement values in preg_replace() calls to be properly escaped [wb, 2009-06-11]
 * @changes    1.0.0b3   Fixed a parameter name in ::rpos() from `$search` to `$needle` [wb, 2009-02-06]
 * @changes    1.0.0b2   Fixed a bug in ::explode() with newlines and zero-length delimiters [wb, 2009-02-05]
 * @changes    1.0.0b    The initial implementation [wb, 2008-06-01]
 */
class fUTF8
{
	// The following constants allow for nice looking callbacks to static methods
	const ascii    = 'fUTF8::ascii';
	const chr      = 'fUTF8::chr';
	const clean    = 'fUTF8::clean';
	const cmp      = 'fUTF8::cmp';
	const explode  = 'fUTF8::explode';
	const icmp     = 'fUTF8::icmp';
	const inatcmp  = 'fUTF8::inatcmp';
	const ipos     = 'fUTF8::ipos';
	const ireplace = 'fUTF8::ireplace';
	const irpos    = 'fUTF8::irpos';
	const istr     = 'fUTF8::istr';
	const len      = 'fUTF8::len';
	const lower    = 'fUTF8::lower';
	const ltrim    = 'fUTF8::ltrim';
	const natcmp   = 'fUTF8::natcmp';
	const ord      = 'fUTF8::ord';
	const pad      = 'fUTF8::pad';
	const pos      = 'fUTF8::pos';
	const replace  = 'fUTF8::replace';
	const reset    = 'fUTF8::reset';
	const rev      = 'fUTF8::rev';
	const rpos     = 'fUTF8::rpos';
	const rtrim    = 'fUTF8::rtrim';
	const str      = 'fUTF8::str';
	const sub      = 'fUTF8::sub';
	const trim     = 'fUTF8::trim';
	const ucfirst  = 'fUTF8::ucfirst';
	const ucwords  = 'fUTF8::ucwords';
	const upper    = 'fUTF8::upper';
	const wordwrap = 'fUTF8::wordwrap';
	
	
	/**
	 * Depending how things are compiled, NetBSD and Solaris don't support //IGNORE in iconv()
	 * 
	 * If //IGNORE support is not provided strings with invalid characters will be truncated
	 * 
	 * @var boolean
	 */
	static private $can_ignore_invalid = NULL;
	
	/**
	 * All lowercase UTF-8 characters mapped to uppercase characters
	 * 
	 * @var array
	 */
	static private $lower_to_upper = array(
		'a' => 'A', 'b' => 'B', 'c' => 'C', 'd' => 'D', 'e' => 'E', 'f' => 'F',
		'g' => 'G', 'h' => 'H', 'i' => 'I', 'j' => 'J', 'k' => 'K', 'l' => 'L',
		'm' => 'M', 'n' => 'N', 'o' => 'O', 'p' => 'P', 'q' => 'Q', 'r' => 'R',
		's' => 'S', 't' => 'T', 'u' => 'U', 'v' => 'V', 'w' => 'W', 'x' => 'X',
		'y' => 'Y', 'z' => 'Z', 'ŕ' => 'Ŕ', 'á' => 'Á', 'â' => 'Â', 'ă' => 'Ă',
		'ä' => 'Ä', 'ĺ' => 'Ĺ', 'ć' => 'Ć', 'ç' => 'Ç', 'č' => 'Č', 'é' => 'É',
		'ę' => 'Ę', 'ë' => 'Ë', 'ě' => 'Ě', 'í' => 'Í', 'î' => 'Î', 'ď' => 'Ď',
		'đ' => 'Đ', 'ń' => 'Ń', 'ň' => 'Ň', 'ó' => 'Ó', 'ô' => 'Ô', 'ő' => 'Ő',
		'ö' => 'Ö', 'ř' => 'Ř', 'ů' => 'Ů', 'ú' => 'Ú', 'ű' => 'Ű', 'ü' => 'Ü',
		'ý' => 'Ý', 'ţ' => 'Ţ', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', 'œ' => 'Œ',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'š' => 'Š', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'˙' => 'Ÿ', '?' => '?', '?' => '?', 'ž' => 'Ž', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', 'ƒ' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?'
	);
	
	/**
	 * All lowercase UTF-8 characters not properly handled by [http://php.net/mb_strtoupper mb_strtoupper()] mapped to uppercase characters
	 * 
	 * @var array
	 */
	static private $mb_lower_to_upper_fix = array(
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?'
	);
	
	/**
	 * All uppercase UTF-8 characters not properly handled by [http://php.net/mb_strtolower mb_strtolower()] mapped to lowercase characters
	 * 
	 * @var array
	 */
	static private $mb_upper_to_lower_fix = array(
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?'
	);
	
	/**
	 * All uppercase UTF-8 characters mapped to lowercase characters
	 * 
	 * @var array
	 */
	static private $upper_to_lower = array(
		'A' => 'a', 'B' => 'b', 'C' => 'c', 'D' => 'd', 'E' => 'e', 'F' => 'f',
		'G' => 'g', 'H' => 'h', 'I' => 'i', 'J' => 'j', 'K' => 'k', 'L' => 'l',
		'M' => 'm', 'N' => 'n', 'O' => 'o', 'P' => 'p', 'Q' => 'q', 'R' => 'r',
		'S' => 's', 'T' => 't', 'U' => 'u', 'V' => 'v', 'W' => 'w', 'X' => 'x',
		'Y' => 'y', 'Z' => 'z', 'Ŕ' => 'ŕ', 'Á' => 'á', 'Â' => 'â', 'Ă' => 'ă',
		'Ä' => 'ä', 'Ĺ' => 'ĺ', 'Ć' => 'ć', 'Ç' => 'ç', 'Č' => 'č', 'É' => 'é',
		'Ę' => 'ę', 'Ë' => 'ë', 'Ě' => 'ě', 'Í' => 'í', 'Î' => 'î', 'Ď' => 'ď',
		'Đ' => 'đ', 'Ń' => 'ń', 'Ň' => 'ň', 'Ó' => 'ó', 'Ô' => 'ô', 'Ő' => 'ő',
		'Ö' => 'ö', 'Ř' => 'ř', 'Ů' => 'ů', 'Ú' => 'ú', 'Ű' => 'ű', 'Ü' => 'ü',
		'Ý' => 'ý', 'Ţ' => 'ţ', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => 'i', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'Œ' => 'œ', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', 'Š' => 'š', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', 'Ÿ' => '˙', '?' => '?', '?' => '?', 'Ž' => 'ž', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => 'ƒ', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?', '?' => '?',
		'?' => '?', '?' => '?', '?' => '?'
	);
	
	/**
	 * A mapping of all ASCII-based latin characters, puntuation, symbols and number forms to ASCII.
	 * 
	 * Includes elements form the following unicode blocks:
	 * 
	 *  - Latin-1 Supplement
	 *  - Latin Extended-A
	 *  - Latin Extended-B
	 *  - IPA Extensions
	 *  - Latin Extended Additional
	 *  - General Punctuation
	 *  - Letterlike symbols
	 *  - Number Forms
	 * 
	 * @var array
	 */
	static private $utf8_to_ascii = array(
		// Latin-1 Supplement
		'Š' => '(c)', 'Ť' => '<<',  'Ž' => '(R)', 'ť' => '>>',  'ź' => '1/4',
		'˝' => '1/2', 'ž' => '3/4', 'Ŕ' => 'A',   'Á' => 'A',   'Â' => 'A',
		'Ă' => 'A',   'Ä' => 'A',   'Ĺ' => 'A',   'Ć' => 'AE',  'Ç' => 'C',
		'Č' => 'E',   'É' => 'E',   'Ę' => 'E',   'Ë' => 'E',   'Ě' => 'I',
		'Í' => 'I',   'Î' => 'I',   'Ď' => 'I',   'Ń' => 'N',   'Ň' => 'O',
		'Ó' => 'O',   'Ô' => 'O',   'Ő' => 'O',   'Ö' => 'O',   'Ř' => 'O',
		'Ů' => 'U',   'Ú' => 'U',   'Ű' => 'U',   'Ü' => 'U',   'Ý' => 'Y',
		'ŕ' => 'a',   'á' => 'a',   'â' => 'a',   'ă' => 'a',   'ä' => 'a',
		'ĺ' => 'a',   'ć' => 'ae',  'ç' => 'c',   'č' => 'e',   'é' => 'e',
		'ę' => 'e',   'ë' => 'e',   'ě' => 'i',   'í' => 'i',   'î' => 'i',
		'ď' => 'i',   'ń' => 'n',   'ň' => 'o',   'ó' => 'o',   'ô' => 'o',
		'ő' => 'o',   'ö' => 'o',   'ř' => 'o',   'ů' => 'u',   'ú' => 'u',
		'ű' => 'u',   'ü' => 'u',   'ý' => 'y',   '˙' => 'y',
		// Latin Extended-A
		'?' => 'A',   '?' => 'a',   '?' => 'A',   '?' => 'a',   '?' => 'A',
		'?' => 'a',   '?' => 'C',   '?' => 'c',   '?' => 'C',   '?' => 'c',
		'?' => 'C',   '?' => 'c',   '?' => 'C',   '?' => 'c',   '?' => 'D',
		'?' => 'd',   '?' => 'D',   '?' => 'd',   '?' => 'E',   '?' => 'e',
		'?' => 'E',   '?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'E',
		'?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'G',   '?' => 'g',
		'?' => 'G',   '?' => 'g',   '?' => 'G',   '?' => 'g',   '?' => 'G',
		'?' => 'g',   '?' => 'H',   '?' => 'h',   '?' => 'H',   '?' => 'h',
		'?' => 'I',   '?' => 'i',   '?' => 'I',   '?' => 'i',   '?' => 'I',
		'?' => 'i',   '?' => 'I',   '?' => 'i',   '?' => 'I',   '?' => 'i',
		'?' => 'IJ',  '?' => 'ij',  '?' => 'J',   '?' => 'j',   '?' => 'K',
		'?' => 'k',   '?' => 'L',   '?' => 'l',   '?' => 'L',   '?' => 'l',
		'?' => 'L',   '?' => 'l',   '?' => 'L',   '?' => 'l',   '?' => 'L',
		'?' => 'l',   '?' => 'N',   '?' => 'n',   '?' => 'N',   '?' => 'n',
		'?' => 'N',   '?' => 'n',   '?' => "'n", '?' => 'N',   '?' => 'n',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'O',
		'?' => 'o',   'Œ' => 'OE',  'œ' => 'oe',  '?' => 'R',   '?' => 'r',
		'?' => 'R',   '?' => 'r',   '?' => 'R',   '?' => 'r',   '?' => 'S',
		'?' => 's',   '?' => 'S',   '?' => 's',   '?' => 'S',   '?' => 's',
		'Š' => 'S',   'š' => 's',   '?' => 'T',   '?' => 't',   '?' => 'T',
		'?' => 't',   '?' => 'T',   '?' => 't',   '?' => 'U',   '?' => 'u',
		'?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'U',
		'?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',
		'?' => 'W',   '?' => 'w',   '?' => 'Y',   '?' => 'y',   'Ÿ' => 'Y',
		'?' => 'Z',   '?' => 'z',   '?' => 'Z',   '?' => 'z',   'Ž' => 'Z',
		'ž' => 'z',
		// Latin Extended-B
		'?' => 'b',   '?' => 'B',   '?' => 'B',   '?' => 'b',   '?' => 'O',
		'?' => 'C',   '?' => 'c',   '?' => 'D',   '?' => 'D',   '?' => 'D',
		'?' => 'd',   '?' => 'E',   '?' => 'E',   '?' => 'F',   'ƒ' => 'f',
		'?' => 'G',   '?' => 'I',   '?' => 'K',   '?' => 'k',   '?' => 'l',
		'?' => 'M',   '?' => 'N',   '?' => 'n',   '?' => 'O',   '?' => 'O',
		'?' => 'o',   '?' => 'OI',  '?' => 'oi',  '?' => 'P',   '?' => 'p',
		'?' => 't',   '?' => 'T',   '?' => 't',   '?' => 'T',   '?' => 'U',
		'?' => 'u',   '?' => 'V',   '?' => 'Y',   '?' => 'y',   '?' => 'Z',
		'?' => 'z',   '?' => '2',   '?' => 'DZ',  '?' => 'Dz',  '?' => 'dz',
		'?' => 'LJ',  '?' => 'Lj',  '?' => 'lj',  '?' => 'Nj',  '?' => 'Nj',
		'?' => 'nj',  '?' => 'A',   '?' => 'a',   '?' => 'I',   '?' => 'i',
		'?' => 'O',   '?' => 'o',   '?' => 'U',   '?' => 'u',   '?' => 'U',
		'?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',
		'?' => 'U',   '?' => 'u',   '?' => 'e',   '?' => 'A',   '?' => 'a',
		'?' => 'A',   '?' => 'a',   '?' => 'AE',  '?' => 'ae',  '?' => 'G',
		'?' => 'g',   '?' => 'G',   '?' => 'g',   '?' => 'K',   '?' => 'k',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'j',
		'?' => 'DZ',  '?' => 'Dz',  '?' => 'dz',  '?' => 'G',   '?' => 'g',
		'?' => 'N',   '?' => 'n',   '?' => 'A',   '?' => 'a',   '?' => 'AE',
		'?' => 'ae',  '?' => 'O',   '?' => 'o',   '?' => 'A',   '?' => 'a',
		'?' => 'A',   '?' => 'a',   '?' => 'E',   '?' => 'e',   '?' => 'E',
		'?' => 'e',   '?' => 'I',   '?' => 'i',   '?' => 'I',   '?' => 'i',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'R',
		'?' => 'r',   '?' => 'R',   '?' => 'r',   '?' => 'U',   '?' => 'u',
		'?' => 'U',   '?' => 'u',   '?' => 'S',   '?' => 's',   '?' => 'T',
		'?' => 't',   '?' => 'H',   '?' => 'h',   '?' => 'N',   '?' => 'd',
		'?' => 'Z',   '?' => 'z',   '?' => 'A',   '?' => 'a',   '?' => 'E',
		'?' => 'e',   '?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'Y',
		'?' => 'y',   '?' => 'l',   '?' => 'n',   '?' => 't',   '?' => 'j',
		'?' => 'db',  '?' => 'qp',  '?' => 'A',   '?' => 'C',   '?' => 'c',
		'?' => 'L',   '?' => 'T',   '?' => 's',   '?' => 'z',   '?' => 'B',
		'?' => 'U',   '?' => 'V',   '?' => 'E',   '?' => 'e',   '?' => 'J',
		'?' => 'j',   '?' => 'Q',   '?' => 'q',   '?' => 'R',   '?' => 'r',
		'?' => 'Y',   '?' => 'y',
		// IPA Extensions
		'?' => 'a',   '?' => 'b',   '?' => 'o',   '?' => 'c',   '?' => 'd',
		'?' => 'd',   '?' => 'e',   '?' => 'e',   '?' => 'e',   '?' => 'e',
		'?' => 'e',   '?' => 'j',   '?' => 'g',   '?' => 'g',   '?' => 'G',
		'?' => 'h',   '?' => 'h',   '?' => 'i',   '?' => 'I',   '?' => 'l',
		'?' => 'l',   '?' => 'l',   '?' => 'm',   '?' => 'm',   '?' => 'm',
		'?' => 'n',   '?' => 'n',   '?' => 'N',   '?' => 'o',   '?' => 'OE',
		'?' => 'r',   '?' => 'r',   '?' => 'r',   '?' => 'r',   '?' => 'r',
		'?' => 'r',   '?' => 'r',   '?' => 'R',   '?' => 'R',   '?' => 's',
		'?' => 't',   '?' => 't',   '?' => 'u',   '?' => 'v',   '?' => 'v',
		'?' => 'w',   '?' => 'y',   '?' => 'Y',   '?' => 'z',   '?' => 'z',
		'?' => 'C',   '?' => 'B',   '?' => 'e',   '?' => 'G',   '?' => 'H',
		'?' => 'j',   '?' => 'k',   '?' => 'L',   '?' => 'q',   '?' => 'dz',
		'?' => 'dz',  '?' => 'ts',  '?' => 'tc',  '?' => 'ls',  '?' => 'lz',
		'?' => 'h',   '?' => 'h',
		// Latin Extended Additional
		'?' => 'A',   '?' => 'a',   '?' => 'B',   '?' => 'b',   '?' => 'B',
		'?' => 'b',   '?' => 'B',   '?' => 'b',   '?' => 'C',   '?' => 'c',
		'?' => 'D',   '?' => 'd',   '?' => 'D',   '?' => 'd',   '?' => 'D',
		'?' => 'd',   '?' => 'D',   '?' => 'd',   '?' => 'D',   '?' => 'd',
		'?' => 'E',   '?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'E',
		'?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'E',   '?' => 'e',
		'?' => 'F',   '?' => 'f',   '?' => 'G',   '?' => 'g',   '?' => 'H',
		'?' => 'h',   '?' => 'H',   '?' => 'h',   '?' => 'H',   '?' => 'h',
		'?' => 'H',   '?' => 'h',   '?' => 'H',   '?' => 'h',   '?' => 'I',
		'?' => 'i',   '?' => 'I',   '?' => 'i',   '?' => 'K',   '?' => 'k',
		'?' => 'K',   '?' => 'k',   '?' => 'K',   '?' => 'k',   '?' => 'L',
		'?' => 'l',   '?' => 'L',   '?' => 'l',   '?' => 'L',   '?' => 'l',
		'?' => 'L',   '?' => 'l',   '?' => 'M',   '?' => 'm',   '?' => 'M',
		'?' => 'm',   '?' => 'M',   '?' => 'm',   '?' => 'N',   '?' => 'n',
		'?' => 'N',   '?' => 'n',   '?' => 'N',   '?' => 'n',   '?' => 'N',
		'?' => 'n',   '?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'P',
		'?' => 'p',   '?' => 'P',   '?' => 'p',   '?' => 'R',   '?' => 'r',
		'?' => 'R',   '?' => 'r',   '?' => 'R',   '?' => 'r',   '?' => 'R',
		'?' => 'r',   '?' => 'S',   '?' => 's',   '?' => 'S',   '?' => 's',
		'?' => 'S',   '?' => 's',   '?' => 'S',   '?' => 's',   '?' => 'S',
		'?' => 's',   '?' => 'T',   '?' => 't',   '?' => 'T',   '?' => 't',
		'?' => 'T',   '?' => 't',   '?' => 'T',   '?' => 't',   '?' => 'U',
		'?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',
		'?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'V',
		'?' => 'v',   '?' => 'V',   '?' => 'v',   '?' => 'W',   '?' => 'w',
		'?' => 'W',   '?' => 'w',   '?' => 'W',   '?' => 'w',   '?' => 'W',
		'?' => 'w',   '?' => 'W',   '?' => 'w',   '?' => 'X',   '?' => 'x',
		'?' => 'X',   '?' => 'x',   '?' => 'Y',   '?' => 'y',   '?' => 'Z',
		'?' => 'z',   '?' => 'Z',   '?' => 'z',   '?' => 'Z',   '?' => 'z',
		'?' => 'h',   '?' => 't',   '?' => 'w',   '?' => 'y',   '?' => 'a',
		'?' => 'A',   '?' => 'a',   '?' => 'A',   '?' => 'a',   '?' => 'A',
		'?' => 'a',   '?' => 'A',   '?' => 'a',   '?' => 'A',   '?' => 'a',
		'?' => 'A',   '?' => 'a',   '?' => 'A',   '?' => 'a',   '?' => 'A',
		'?' => 'a',   '?' => 'A',   '?' => 'a',   '?' => 'A',   '?' => 'a',
		'?' => 'A',   '?' => 'a',   '?' => 'A',   '?' => 'a',   '?' => 'E',
		'?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'E',   '?' => 'e',
		'?' => 'E',   '?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'E',
		'?' => 'e',   '?' => 'E',   '?' => 'e',   '?' => 'E',   '?' => 'e',
		'?' => 'I',   '?' => 'i',   '?' => 'I',   '?' => 'i',   '?' => 'O',
		'?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'O',
		'?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',
		'?' => 'O',   '?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'O',
		'?' => 'o',   '?' => 'O',   '?' => 'o',   '?' => 'U',   '?' => 'u',
		'?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'U',
		'?' => 'u',   '?' => 'U',   '?' => 'u',   '?' => 'U',   '?' => 'u',
		'?' => 'U',   '?' => 'u',   '?' => 'Y',   '?' => 'y',   '?' => 'Y',
		'?' => 'y',   '?' => 'Y',   '?' => 'y',   '?' => 'Y',   '?' => 'y',
		// General Punctuation
		'?' => ' ',   '?' => ' ',   '?' => ' ',   '?' => ' ',   '?' => ' ',
		'?' => ' ',   '?' => ' ',   '?' => ' ',   '?' => ' ',   '?' => ' ',
		'?' => ' ',   '?' => '',    '?' => '',    '?' => '',    '?' => '-',
		'?' => '-',   '?' => '-',   '–' => '-',   '—' => '-',   '?' => '-',
		'?' => '||',  '‘' => "'",   '’' => "'",   '‚' => ',',   '?' => "'",
		'“' => '"',   '”' => '"',   '?' => '"',   '?' => '.',   '?' => '..',
		'…' => '...', '?' => ' ',   '?' => "'",   '?' => '"',   '?' => '\'"',
		'?' => "'",   '?' => '"',   '?' => '"\'', '‹' => '<',   '›' => '>',
		'?' => '!!',  '?' => '?!',  '?' => '/',   '?' => '?/',  '?' => '?!',
		'?' => '!?',
		// Letterlike Symbols
		'?' => 'SM',  '™' => 'TM',
		// Number Forms
		'?' => '1/3', '?' => '2/3', '?' => '1/5', '?' => '2/5', '?' => '3/5',
		'?' => '4/5', '?' => '1/6', '?' => '5/6', '?' => '1/8', '?' => '3/8',
		'?' => '5/8', '?' => '7/8', '?' => 'I',   '?' => 'II',  '?' => 'III',
		'?' => 'IV',  '?' => 'V',   '?' => 'Vi',  '?' => 'VII', '?' => 'VIII',
		'?' => 'IX',  '?' => 'X',   '?' => 'XI',  '?' => 'XII', '?' => 'L',
		'?' => 'C',   '?' => 'D',   '?' => 'M',   '?' => 'i',   '?' => 'ii',
		'?' => 'iii', '?' => 'iv',  '?' => 'v',   '?' => 'vi',  '?' => 'vii',
		'?' => 'viii','?' => 'ix',  '?' => 'x',   '?' => 'xi',  '?' => 'xii',
		'?' => 'l',   '?' => 'c',   '?' => 'd',   '?' => 'm'
	);
	
	/**
	 * If the [http://php.net/mbstring mbstring] extension is available
	 * 
	 * @var boolean
	 */
	static private $mbstring_available = NULL;
	
	
	/**
	 * Maps UTF-8 ASCII-based latin characters, puntuation, symbols and number forms to ASCII
	 * 
	 * Any characters or symbols that can not be translated will be removed.
	 * 
	 * This function is most useful for situation that only allows ASCII, such
	 * as in URLs.
	 * 
	 * Translates elements form the following unicode blocks:
	 * 
	 *  - Latin-1 Supplement
	 *  - Latin Extended-A
	 *  - Latin Extended-B
	 *  - IPA Extensions
	 *  - Latin Extended Additional
	 *  - General Punctuation
	 *  - Letterlike symbols
	 *  - Number Forms
	 * 
	 * @internal
	 * 
	 * @param  string $string  The string to convert
	 * @return string  The input string in pure ASCII
	 */
	static public function ascii($string)
	{
		if (!self::detect($string)) {
			return $string;
		}
		
		$string = strtr($string, self::$utf8_to_ascii);
		return preg_replace('#[^\x00-\x7F]#', '', $string);
	}
	
	
	/**
	 * Checks to see if the [http://php.net/mbstring mbstring] extension is available
	 * 
	 * @return void
	 */
	static private function checkMbString()
	{
		self::$mbstring_available = extension_loaded('mbstring');
	}
	
	
	/**
	 * Converts a unicode value into a UTF-8 character
	 * 
	 * @param  mixed $unicode_code_point  The character to create, either the `U+hex` or decimal code point
	 * @return string  The UTF-8 character
	 */
	static public function chr($unicode_code_point)
	{
		if (is_string($unicode_code_point) && substr($unicode_code_point, 0, 2) == 'U+') {
			$unicode_code_point = substr($unicode_code_point, 2);
			$unicode_code_point = hexdec($unicode_code_point);
		}
		
		$bin = decbin($unicode_code_point);
		$digits = strlen($bin);
		
		$first = $second = $third = $fourth = NULL;
		
		// One byte characters
		if ($digits <= 7) {
			$first = chr(bindec($bin));
			
		// Two byte characters
		} elseif ($digits <= 11) {
			$first  = chr(bindec('110' . str_pad(substr($bin, 0, -6), 5, '0', STR_PAD_LEFT)));
			$second = chr(bindec('10' . substr($bin, -6)));
			
		// Three byte characters
		} elseif ($digits <= 16) {
			$first  = chr(bindec('1110' . str_pad(substr($bin, 0, -12), 4, '0', STR_PAD_LEFT)));
			$second = chr(bindec('10' . substr($bin, -12, -6)));
			$third  = chr(bindec('10' . substr($bin, -6)));
			
		// Four byte characters
		} elseif ($digits <= 21) {
			$first  = chr(bindec('11110' . str_pad(substr($bin, 0, -18), 3, '0', STR_PAD_LEFT)));
			$second = chr(bindec('10' . substr($bin, -18, -12)));
			$third  = chr(bindec('10' . substr($bin, -12, -6)));
			$fourth = chr(bindec('10' . substr($bin, -6)));
		}
		
		$ord = ord($first);
		if ($digits > 21 || $ord == 0xC0 || $ord == 0xC1 || $ord > 0xF4) {
			throw new fProgrammerException(
				'The code point specified, %s, is invalid.',
				$unicode_code_point
			);
		}
		
		return $first . $second . $third . $fourth;
	}
	
	
	/**
	 * Removes any invalid UTF-8 characters from a string or array of strings
	 * 
	 * @param  array|string $value  The string or array of strings to clean
	 * @return string  The cleaned string
	 */
	static public function clean($value)
	{
		if (!is_array($value)) {
			if (self::$can_ignore_invalid === NULL) {
				self::$can_ignore_invalid = !in_array(strtolower(ICONV_IMPL), array('unknown', 'ibm iconv'));	
			}
			fCore::startErrorCapture(E_NOTICE);
			$value = self::iconv('UTF-8', 'UTF-8' . (self::$can_ignore_invalid ? '//IGNORE' : ''), (string) $value);
			fCore::stopErrorCapture();
			return $value;
		}
		
		$keys = array_keys($value);
		$num_keys = sizeof($keys);
		for ($i=0; $i<$num_keys; $i++) {
			$value[$keys[$i]] = self::clean($value[$keys[$i]]);
		}
		
		return $value;
	}
	
	
	/**
	 * Compares strings, with the resulting order having latin characters that are based on ASCII letters placed after the relative ASCII characters
	 * 
	 * Please note that this function sorts based on English language sorting
	 * rules only. Locale-sepcific sorting is done by
	 * [http://php.net/strcoll strcoll()], however there are technical
	 * limitations.
	 * 
	 * @param  string $str1  The first string to compare
	 * @param  string $str2  The second string to compare
	 * @return integer  < 0 if $str1 < $str2, 0 if they are equal, > 0 if $str1 > $str2
	 */
	static public function cmp($str1, $str2)
	{
		$ascii_str1 = strtr($str1, self::$utf8_to_ascii);
		$ascii_str2 = strtr($str2, self::$utf8_to_ascii);
		
		$res = strcmp($ascii_str1, $ascii_str2);
		
		// If the ASCII representations are the same, sort by the UTF-8 representations
		if ($res === 0) {
			$res = strcmp($str1, $str2);
		}
		
		return $res;
	}
	
	
	/**
	 * Converts an offset in characters to an offset in bytes to that we can use the built-in functions for some operations
	 * 
	 * @param  string  $string  The string to base the offset on
	 * @param  integer $offset  The character offset to conver to bytes
	 * @return integer  The converted offset
	 */
	static private function convertOffsetToBytes($string, $offset)
	{
		if ($offset == 0) {
			return 0;
		}
		
		$len = strlen($string);
		
		$byte_offset     = 0;
		$measured_offset = 0;
		$sign            = 1;
		
		// Negative offsets require us to reverse some stuff
		if ($offset < 0) {
			$string    = strrev($string);
			$sign      = -1;
			$offset    = abs($offset);
		}
			
		for ($i=0; $i<$len && $measured_offset<$offset; $i++) {
			$char = $string[$i];
			++$byte_offset;
			if (ord($char) < 0x80) {
				++$measured_offset;
			} else {
				switch (ord($char) & 0xF0) {
					case 0xF0:
					case 0xE0:
					case 0xD0:
					case 0xC0:
						++$measured_offset;
						break;
				}
			}
		}
		
		return $byte_offset * $sign;
	}
	
	
	/**
	 * Detects if a UTF-8 string contains any non-ASCII characters
	 * 
	 * @param  string $string  The string to check
	 * @return boolean  If the string contains any non-ASCII characters
	 */
	static private function detect($string)
	{
		return (boolean) preg_match('#[^\x00-\x7F]#', $string);
	}
	
	
	/**
	 * Explodes a string on a delimiter
	 * 
	 * If no delimiter is provided, the string will be exploded with each
	 * characters being an element in the array.
	 * 
	 * @param  string  $string     The string to explode
	 * @param  string  $delimiter  The string to explode on. If `NULL` or `''` this method will return one character per array index.
	 * @return array  The exploded string
	 */
	static public function explode($string, $delimiter=NULL)
	{
		// If a delimiter was passed, we just do an explode
		if ($delimiter || (!$delimiter && is_numeric($delimiter))) {
			return explode($delimiter, $string);
		}
		
		// If no delimiter was passed, we explode the characters into an array
		preg_match_all('#.|^\z#us', $string, $matches);
		return $matches[0];
	}


	/**
	 * This works around a bug in MAMP 1.9.4+ and PHP 5.3 where iconv()
	 * does not seem to properly assign the return value to a variable, but
	 * does work when returning the value.
	 *
	 * @param string $in_charset   The incoming character encoding
	 * @param string $out_charset  The outgoing character encoding
	 * @param string $string       The string to convert
	 * @return string  The converted string
	 */
	static private function iconv($in_charset, $out_charset, $string)
	{
		return iconv($in_charset, $out_charset, $string);
	}
	
	
	/**
	 * Compares strings in a case-insensitive manner, with the resulting order having characters that are based on ASCII letters placed after the relative ASCII characters
	 * 
	 * Please note that this function sorts based on English language sorting
	 * rules only. Locale-sepcific sorting is done by
	 * [http://php.net/strcoll strcoll()], however there are technical
	 * limitations.
	 * 
	 * @param  string $str1  The first string to compare
	 * @param  string $str2  The second string to compare
	 * @return integer  < 0 if $str1 < $str2, 0 if they are equal, > 0 if $str1 > $str2
	 */
	static public function icmp($str1, $str2)
	{
		$str1 = self::lower($str1);
		$str2 = self::lower($str2);
		
		return self::cmp($str1, $str2);
	}
	
	
	/**
	 * Compares strings using a natural order algorithm in a case-insensitive manner, with the resulting order having latin characters that are based on ASCII letters placed after the relative ASCII characters
	 * 
	 * Please note that this function sorts based on English language sorting
	 * rules only. Locale-sepcific sorting is done by
	 * [http://php.net/strcoll strcoll()], however there are technical
	 * limitations.
	 * 
	 * @param  string $str1  The first string to compare
	 * @param  string $str2  The second string to compare
	 * @return integer  `< 0` if `$str1 < $str2`, `0` if they are equal, `> 0` if `$str1 > $str2`
	 */
	static public function inatcmp($str1, $str2)
	{
		$str1 = self::lower($str1);
		$str2 = self::lower($str2);
		
		return self::natcmp($str1, $str2);
	}
	
	
	/**
	 * Finds the first position (in characters) of the search value in the string - case is ignored when doing performing a match
	 * 
	 * @param  string  $haystack  The string to search in
	 * @param  string  $needle    The string to search for. This match will be done in a case-insensitive manner.
	 * @param  integer $offset    The character position to start searching from
	 * @return mixed  The integer character position of the first occurence of the needle or `FALSE` if no match
	 */
	static public function ipos($haystack, $needle, $offset=0)
	{
		// We get better performance falling back for ASCII strings
		if (!self::detect($haystack)) {
			return stripos($haystack, $needle, $offset);
		}
		
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available && function_exists('mb_stripos')) {
			return mb_stripos($haystack, $needle, $offset, 'UTF-8');
		}
		
		$haystack = self::lower($haystack);
		$needle   = self::lower($needle);
		
		return self::pos($haystack, $needle, $offset);
	}
	
	
	/**
	 * Replaces matching parts of the string, with matches being done in a a case-insensitive manner
	 * 
	 * If `$search` and `$replace` are both arrays and `$replace` is shorter,
	 * the extra `$search` string will be replaced with an empty string. If
	 * `$search` is an array and `$replace` is a string, all `$search` values
	 * will be replaced with the string specified.
	 * 
	 * @param  string $string   The string to perform the replacements on
	 * @param  mixed  $search   The string (or array of strings) to search for - see method description for details
	 * @param  mixed  $replace  The string (or array of strings) to replace with - see method description for details
	 * @return string  The input string with the specified replacements
	 */
	static public function ireplace($string, $search, $replace)
	{
		if (is_array($search)) {
			foreach ($search as &$needle) {
				$needle = '#' . preg_quote($needle, '#') . '#ui';
			}
		} else {
			$search = '#' . preg_quote($search, '#') . '#ui';
		}
		return preg_replace(
			$search,
			strtr($replace, array('\\' => '\\\\', '$' => '\\$')),
			$string
		);
	}
	
	
	/**
	 * Finds the last position (in characters) of the search value in the string - case is ignored when doing performing a match
	 * 
	 * @param  string  $haystack  The string to search in
	 * @param  string  $needle    The string to search for. This match will be done in a case-insensitive manner.
	 * @param  integer $offset    The character position to start searching from. A negative value will stop looking that many characters from the end of the string
	 * @return mixed  The integer character position of the last occurence of the needle or `FALSE` if no match
	 */
	static public function irpos($haystack, $needle, $offset=0)
	{
		// We get better performance falling back for ASCII strings
		if (!self::detect($haystack)) {
			return strripos($haystack, $needle, $offset);
		}
		
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available && function_exists('mb_strripos')) {
			return mb_strripos($haystack, $needle, $offset, 'UTF-8');
		}
		
		$haystack = self::lower($haystack);
		$needle   = self::lower($needle);
		
		return self::rpos($haystack, $needle, $offset);
	}
	
	
	/**
	 * Matches a string needle in the string haystack, returning a substring from the beginning of the needle to the end of the haystack
	 * 
	 * Can optionally return the part of the haystack before the needle. Matching
	 * is done in a case-insensitive manner.
	 * 
	 * @param  string  $haystack       The string to search in
	 * @param  string  $needle         The string to search for. This match will be done in a case-insensitive manner.
	 * @param  boolean $before_needle  If a substring of the haystack before the needle should be returned instead of the substring from the needle to the end of the haystack
	 * @return mixed  The specified part of the haystack, or `FALSE` if the needle was not found
	 */
	static public function istr($haystack, $needle, $before_needle=FALSE)
	{
		// We get better performance falling back for ASCII strings
		if ($before_needle == FALSE && !self::detect($haystack)) {
			return stristr($haystack, $needle);
		}
		
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available && function_exists('mb_stristr')) {
			return mb_stristr($haystack, $needle, $before_needle, 'UTF-8');
		}
		
		$lower_haystack = self::lower($haystack);
		$lower_needle   = self::lower($needle);
		
		$pos = strpos($lower_haystack, $lower_needle);
		
		if ($before_needle) {
			return substr($haystack, 0, $pos);
		}
		
		return substr($haystack, $pos);
	}
	
	
	/**
	 * Determines the length (in characters) of a string
	 * 
	 * @param  string $string  The string to measure
	 * @return integer  The number of characters in the string
	 */
	static public function len($string)
	{
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available) {
			return mb_strlen($string, 'UTF-8');
		}
		
		return strlen(utf8_decode($string));
	}
	
	
	/**
	 * Converts all uppercase characters to lowercase
	 * 
	 * @param  string $string  The string to convert
	 * @return string  The input string with all uppercase characters in lowercase
	 */
	static public function lower($string)
	{
		// We get better performance falling back for ASCII strings
		if (!self::detect($string)) {
			return strtolower($string);
		}
		
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available) {
			$string = mb_strtolower($string, 'utf-8');
			// For some reason mb_strtolower misses some character
			return strtr($string, self::$mb_upper_to_lower_fix);
		}
		
		return strtr($string, self::$upper_to_lower);
	}
	
	
	/**
	 * Trims whitespace, or any specified characters, from the beginning of a string
	 * 
	 * @param  string $string    The string to trim
	 * @param  string $charlist  The characters to trim
	 * @return string  The trimmed string
	 */
	static public function ltrim($string, $charlist=NULL)
	{
		if (strlen($charlist) === 0) {
			return ltrim($string);
		}
		
		$search = preg_quote($charlist, '#');
		$search = str_replace('-', '\-', $search);
		$search = str_replace('\.\.', '-', $search);
		return preg_replace('#^[' . $search . ']+#Du', '', $string);
	}
	
	
	/**
	 * Compares strings using a natural order algorithm, with the resulting order having latin characters that are based on ASCII letters placed after the relative ASCII characters
	 * 
	 * Please note that this function sorts based on English language sorting
	 * rules only. Locale-sepcific sorting is done by
	 * [http://php.net/strcoll strcoll()], however there are technical
	 * limitations.
	 * 
	 * @param  string $str1  The first string to compare
	 * @param  string $str2  The second string to compare
	 * @return integer  `< 0` if `$str1 < $str2`, `0` if they are equal, `> 0` if `$str1 > $str2`
	 */
	static public function natcmp($str1, $str2)
	{
		$ascii_str1 = strtr($str1, self::$utf8_to_ascii);
		$ascii_str2 = strtr($str2, self::$utf8_to_ascii);
		
		$res = strnatcmp($ascii_str1, $ascii_str2);
		
		// If the ASCII representations are the same, sort by the UTF-8 representations
		if ($res === 0) {
			$res = strnatcmp($str1, $str2);
		}
		
		return $res;
	}
	
	
	/**
	 * Converts a UTF-8 character to a unicode code point
	 * 
	 * @param  string $character  The character to decode
	 * @return string  The U+hex unicode code point for the character
	 */
	static public function ord($character)
	{
		$b       = array_map('ord', str_split($character));
		$invalid = FALSE;
		
		switch (strlen($character)) {
			case 1:
				if ($b[0] > 0x7F) {
					$invalid = TRUE;
					break;
				}
				$bin = decbin($b[0]);
				break;
			
			case 2:
				if ($b[0] < 0xC2 || $b[0] > 0xDF ||
					  $b[1] < 0x80 || $b[1] > 0xBF) {
					$invalid = TRUE;
					break;
				}
				$bin = substr(decbin($b[0]), 3) .
						   substr(decbin($b[1]), 2);
				break;
			
			case 3:
				if ($b[0] < 0xE0 || $b[0] > 0xEF ||
					  $b[1] < 0x80 || $b[1] > 0xBF ||
					  $b[2] < 0x80 || $b[2] > 0xBF) {
					$invalid = TRUE;
					break;
				}
				$bin = substr(decbin($b[0]), 4) .
						   substr(decbin($b[1]), 2) .
						   substr(decbin($b[2]), 2);
				break;
			
			case 4:
				if ($b[0] < 0xF0 || $b[0] > 0xF4 ||
					  $b[1] < 0x80 || $b[1] > 0xBF ||
					  $b[2] < 0x80 || $b[2] > 0xBF ||
					  $b[3] < 0x80 || $b[3] > 0xBF) {
					$invalid = TRUE;
					break;
				}
				$bin = substr(decbin($b[0]), 5) .
						   substr(decbin($b[1]), 2) .
						   substr(decbin($b[2]), 2) .
						   substr(decbin($b[3]), 2);
				break;
			
			default:
				$invalid = TRUE;
				break;
		}
		
		if ($invalid) {
			throw new fProgrammerException(
				'The UTF-8 character specified is invalid'
			);
		}
		
		$hex = strtoupper(dechex(bindec($bin)));
		return 'U+' . str_pad($hex, 4, '0', STR_PAD_LEFT);
	}
	
	
	/**
	 * Pads a string to the number of characters specified
	 * 
	 * @param  string  $string      The string to pad
	 * @param  integer $pad_length  The character length to pad the string to
	 * @param  string  $pad_string  The string to pad the source string with
	 * @param  string  $pad_type    The type of padding to do: `'left'`, `'right'`, `'both'`
	 * @return string  The input string padded to the specified character width
	 */
	static public function pad($string, $pad_length, $pad_string=' ', $pad_type='right')
	{
		$valid_pad_types = array('right', 'left', 'both');
		if (!in_array($pad_type, $valid_pad_types)) {
			throw new fProgrammerException(
				'The pad type specified, %1$s, is not valid. Must be one of: %2$s.',
				$pad_type,
				join(', ', $valid_pad_types)
			);
		}
		
		// We get better performance falling back for ASCII strings
		if (!self::detect($string) && !self::detect($pad_string)) {
			static $type_map = array(
				'left'  => STR_PAD_LEFT,
				'right' => STR_PAD_RIGHT,
				'both'  => STR_PAD_BOTH
			);
			return str_pad($string, $pad_length, $pad_string, $type_map[$pad_type]);
		}
		
		
		$string_length     = self::len($string);
		$pad_string_length = self::len($pad_string);
		
		$pad_to_length     = $pad_length - $string_length;
		
		if ($pad_to_length < 1) {
			return $string;
		}
		
		$padded           = 0;
		$next_side        = 'left';
		$left_pad_string  = '';
		$right_pad_string = '';
		
		while ($padded < $pad_to_length) {
			
			// For pad strings over 1 characters long, they may be too long to fit
			if ($pad_to_length - $padded < $pad_string_length) {
				$pad_string = self::sub($pad_string, 0, $pad_to_length - $padded);
			}
			
			switch (($pad_type != 'both') ? $pad_type : $next_side) {
				case 'right':
					$right_pad_string .= $pad_string;
					$next_side = 'left';
					break;
					
				case 'left':
					$left_pad_string .= $pad_string;
					$next_side = 'right';
					break;
			}
			
			$padded += $pad_string_length;
		}
		
		return $left_pad_string . $string . $right_pad_string;
	}
	
	
	/**
	 * Finds the first position (in characters) of the search value in the string
	 * 
	 * @param  string  $haystack  The string to search in
	 * @param  string  $needle    The string to search for
	 * @param  integer $offset    The character position to start searching from
	 * @return mixed  The integer character position of the first occurence of the needle or `FALSE` if no match
	 */
	static public function pos($haystack, $needle, $offset=0)
	{
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available) {
			return mb_strpos($haystack, $needle, $offset, 'UTF-8');
		}
		
		$offset = self::convertOffsetToBytes($haystack, $offset);
		
		$position = strpos($haystack, $needle, $offset);
		
		if ($position === FALSE) {
			return FALSE;
		}
		
		return strlen(utf8_decode(substr($haystack, 0, $position)));
	}
	
	
	/**
	 * Replaces matching parts of the string
	 * 
	 * If `$search` and `$replace` are both arrays and `$replace` is shorter,
	 * the extra `$search` string will be replaced with an empty string. If
	 * `$search` is an array and `$replace` is a string, all `$search` values
	 * will be replaced with the string specified.
	 * 
	 * @param  string $string   The string to perform the replacements on
	 * @param  mixed  $search   The string (or array of strings) to search for - see method description for details
	 * @param  mixed  $replace  The string (or array of strings) to replace with - see method description for details
	 * @return string  The input string with the specified replacements
	 */
	static public function replace($string, $search, $replace)
	{
		return str_replace($search, $replace, $string);
	}
	
	
	/**
	 * Resets the configuration of the class
	 * 
	 * @internal
	 * 
	 * @return void
	 */
	static public function reset()
	{
		self::$mbstring_available = NULL;
	}
	
	
	/**
	 * Reverses a string
	 * 
	 * @param  string $string   The string to reverse
	 * @return string  The reversed string
	 */
	static public function rev($string)
	{
		$output = '';
		$len = strlen($string);
		
		static $char_lens = array(
			0xF0 => 4,
			0xE0 => 3,
			0xD0 => 2,
			0xC0 => 2
		);
		
		$mb_char = '';
		for ($i=0; $i<$len; $i++) {
			$char = $string[$i];
			if (ord($char) < 128) {
				$output = $char . $output;
			} else {
				switch (ord($char) & 0xF0) {
					case 0xF0:
						$output = $string[$i] . $string[$i+1] . $string[$i+2] . $string[$i+3] . $output;
						$i += 3;
						break;
						
					case 0xE0:
						$output = $string[$i] . $string[$i+1] . $string[$i+2] . $output;
						$i += 2;
						break;
						
					case 0xD0:
					case 0xC0:
						$output = $string[$i] . $string[$i+1] . $output;
						$i += 1;
						break;
				}
			}
		}
		
		return $output;
	}
	
	
	/**
	 * Finds the last position (in characters) of the search value in the string
	 * 
	 * @param  string  $haystack  The string to search in
	 * @param  string  $needle    The string to search for.
	 * @param  integer $offset    The character position to start searching from. A negative value will stop looking that many characters from the end of the string
	 * @return mixed  The integer character position of the last occurence of the needle or `FALSE` if no match
	 */
	static public function rpos($haystack, $needle, $offset=0)
	{
		// We get better performance falling back for ASCII strings
		if (!self::detect($haystack)) {
			return strrpos($haystack, $needle, $offset);
		}
		
		// We don't even both trying mb_strrpos since this method is faster
		
		$offset = self::convertOffsetToBytes($haystack, $offset);
		
		$position = strrpos($haystack, $needle, $offset);
		
		if ($position === FALSE) {
			return FALSE;
		}
		
		return strlen(utf8_decode(substr($haystack, 0, $position)));
	}
	
	
	/**
	 * Trims whitespace, or any specified characters, from the end of a string
	 * 
	 * @param  string $string    The string to trim
	 * @param  string $charlist  The characters to trim
	 * @return string  The trimmed string
	 */
	static public function rtrim($string, $charlist=NULL)
	{
		if (strlen($charlist) === 0) {
			return rtrim($string);
		}
		
		$search = preg_quote($charlist, '#');
		$search = str_replace('-', '\-', $search);
		$search = str_replace('\.\.', '-', $search);
		return preg_replace('#[' . $search . ']+$#Du', '', $string);
	}
	
	
	/**
	 * Matches a string needle in the string haystack, returning a substring from the beginning of the needle to the end of the haystack
	 * 
	 * Can optionally return the part of the haystack before the needle.
	 * 
	 * @param  string  $haystack       The string to search in
	 * @param  string  $needle         The string to search for
	 * @param  boolean $before_needle  If a substring of the haystack before the needle should be returned instead of the substring from the needle to the end of the haystack
	 * @return mixed  The specified part of the haystack, or `FALSE` if the needle was not found
	 */
	static public function str($haystack, $needle, $before_needle=FALSE)
	{
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available && function_exists('mb_strstr')) {
			return mb_strstr($haystack, $needle, $before_needle, 'UTF-8');
		}
		
		$pos = strpos($haystack, $needle);
		
		if ($pos === FALSE) {
			return $pos;
		}
		
		if ($before_needle) {
			return substr($haystack, 0, $pos);
		}
		
		return substr($haystack, $pos);
	}
	
	
	/**
	 * Extracts part of a string
	 * 
	 * @param  string  $string  The string to extract from
	 * @param  integer $start   The zero-based starting index to extract from. Negative values will start the extraction that many characters from the end of the string.
	 * @param  integer $length  The length of the string to extract. If an empty value is provided, the remainder of the string will be returned.
	 * @return mixed  The extracted subtring or `FALSE` if the start is out of bounds
	 */
	static public function sub($string, $start, $length=NULL)
	{
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available) {
			$str_len = mb_strlen($string, 'UTF-8');
			if (abs($start) > $str_len) {
				return FALSE;
			}
			if ($length === NULL) {
				if ($start >= 0) {
					$length = $str_len-$start;
				} else {
					$length = abs($start);
				}
			}
			return mb_substr($string, $start, $length, 'UTF-8');
		}
		
		// We get better performance falling back for ASCII strings
		if (!self::detect($string)) {
			if ($length === NULL) {
				if ($start >= 0) {
					$length = strlen($string)-$start;
				} else {
					$length = abs($start);
				}
			}
			return substr($string, $start, $length);
		}
		
		
		// This is the slowest version
		$str_len = strlen(utf8_decode($string));
		
		if (abs($start) > $str_len) {
			return FALSE;
		}
		
		// Optimize looking by changing to negative start positions if the
		// start is in the second half of the string
		if ($start > $str_len/2) {
			$start = 0-($str_len-$start);
		}
		
		// Substrings to the end of the string are pretty simple
		$start  = self::convertOffsetToBytes($string, $start);
		$string = substr($string, $start);
		
		if ($length === NULL) {
			return $string;
		}
		
		$length = self::convertOffsetToBytes($string, $length);
		return substr($string, 0, $length);
	}
	
	
	/**
	 * Trims whitespace, or any specified characters, from the beginning and end of a string
	 * 
	 * @param  string $string    The string to trim
	 * @param  string $charlist  The characters to trim, .. indicates a range
	 * @return string  The trimmed string
	 */
	static public function trim($string, $charlist=NULL)
	{
		if (strlen($charlist) === 0) {
			return trim($string);
		}
		
		$search = preg_quote($charlist, '#');
		$search = str_replace('-', '\-', $search);
		$search = str_replace('\.\.', '-', $search);
		return preg_replace('#^[' . $search . ']+|[' . $search . ']+$#Du', '', $string);
	}
	
	
	/**
	 * Converts the first character of the string to uppercase.
	 * 
	 * @param  string $string  The string to process
	 * @return string  The processed string
	 */
	static public function ucfirst($string)
	{
		return self::upper(self::sub($string, 0, 1)) . self::sub($string, 1);
	}
	
	
	/**
	 * Converts the first character of every word to uppercase
	 * 
	 * Words are considered to start at the beginning of the string, or after any
	 * whitespace character.
	 * 
	 * @param  string $string  The string to process
	 * @return string  The processed string
	 */
	static public function ucwords($string)
	{
		return preg_replace_callback(
			'#(?<=^|\s|[\x{2000}-\x{200A}]|/|-|\(|\[|\{|\||"|^\'|\s\'|‘|“)(.)#u',
			array('self', 'ucwordsCallback'),
			$string
		);
	}
	
	
	/**
	 * Handles converting a character to uppercase for ::ucwords()
	 * 
	 * @param array $match  The regex match from ::ucwords()
	 * @return string  The uppercase character
	 */
	static private function ucwordsCallback($match)
	{
		return self::upper($match[1]);
	}
	
	
	/**
	 * Converts all lowercase characters to uppercase
	 * 
	 * @param  string $string  The string to convert
	 * @return string  The input string with all lowercase characters in uppercase
	 */
	static public function upper($string)
	{
		// We get better performance falling back for ASCII strings
		if (!self::detect($string)) {
			return strtoupper($string);
		}
		
		if (self::$mbstring_available === NULL) {
			self::checkMbString();
		}
		
		if (self::$mbstring_available) {
			$string = mb_strtoupper($string, 'utf-8');
			// For some reason mb_strtoupper misses some character
			return strtr($string, self::$mb_lower_to_upper_fix);
		}
		
		return strtr($string, self::$lower_to_upper);
	}
	
	
	/**
	 * Wraps a string to a specific character width
	 * 
	 * @param  string  $string  The string to wrap
	 * @param  integer $width	The character width to wrap to
	 * @param  string  $break   The string to insert as a break
	 * @param  boolean $cut     If words longer than the character width should be split to fit
	 * @return string  The input string with all lowercase characters in uppercase
	 */
	static public function wordwrap($string, $width=75, $break="\n", $cut=FALSE)
	{
		// We get better performance falling back for ASCII strings
		if (!self::detect($string)) {
			return wordwrap($string, $width, $break, $cut);
		}
		
		$words = preg_split('#(?<=\s|[\x{2000}-\x{200A}])#ue', $string);
		
		$output = '';
		
		$line_len = 0;
		foreach ($words as $word) {
			$word_len = self::len($word);
			
			// Shorten up words that are too long
			while ($cut && $word_len > $width) {
				$output  .= $break;
				$output  .= self::sub($word, 0, $width);
				$line_len = $width;
				$word	  = self::sub($word, $width);
				$word_len = self::len($word);
			}
			
			if ($line_len && $line_len + $word_len > $width) {
				$output  .= $break;
				$line_len = 0;
			}
			$output   .= $word;
			$line_len += $word_len;
		}
		
		return $output;
	}
	
	
	/**
	 * Forces use as a static class
	 * 
	 * @return fUTF8
	 */
	private function __construct() { }
}



/**
 * Copyright (c) 2008-2011 Will Bond <will@flourishlib.com>
 * 
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject t
Back to Top