summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/source/latex/base/utf8ienc.dtx
blob: abd5d627ff7f98e9214ade0697f70bd1e32f238f (plain)
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
% \iffalse meta-comment
%
% Copyright 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009
% The LaTeX3 Project and any individual authors listed elsewhere
% in this file.
%
% This file is part of the LaTeX base system.
% -------------------------------------------
%
% It may be distributed and/or modified under the
% conditions of the LaTeX Project Public License, either version 1.3c
% of this license or (at your option) any later version.
% The latest version of this license is in
%    http://www.latex-project.org/lppl.txt
% and version 1.3c or later is part of all distributions of LaTeX
% version 2005/12/01 or later.
%
% This file has the LPPL maintenance status "maintained".
%
% The list of all files belonging to the LaTeX base distribution is
% given in the file `manifest.txt'. See also `legal.txt' for additional
% information.
%
% The list of derived (unpacked) files belonging to the distribution
% and covered by LPPL is defined by the unpacking scripts (with
% extension .ins) which are part of the distribution.
%
% \fi
%
% \iffalse
%<*driver>
\documentclass{ltxdoc}
\GetFileInfo{utf8.def}
\title{Providing some UTF-8 support via \texttt{inputenc}}
\date{\fileversion\space\filedate{} printed \today}
 \author{%
  Frank Mittelbach \and Chris Rowley\thanks{Borrowing heavily from
      code by David Carlisle and tables by Sebastian Rahtz; some table
      and code cleanup by Javier Bezos}}
\usepackage[utf8]{inputenc}
\begin{document}
 \maketitle
 \tableofcontents
 \DocInput{utf8ienc.dtx}
\end{document}
%</driver>
% \fi
%
% \CheckSum{1232}
%
% \newpage
%
% \section{Introduction}
%
% [The whole section is rather unfinished \ldots\ just like the code, sorry!]
%
% \subsection{Background and general stuff}
%
% For many reasons what this package provides is a long way from any
% type of `Unicode compliance'.
%
% In stark contrast to 8-bit character sets, with 16 or more bits it can
% easily be very inefficient to support the full range.\footnote{In
% fact, \LaTeX's current 8-bit support does not go so far as to make
% all 8-bit characters into valid input.}  Moreover, useful support of
% character input by a typesetting system overwhelmingly means finding
% an acceptable visual representation of a sequence of characters and
% this, for \LaTeX{}, means having available a suitably encoded 8-bit
% font.
%
% Unfortunately it is not possible to predict exactly what valid UTF-8
% octet sequences will appear in a particular file so it is best to
% make all the unsupported but valid sequences produce a reasonably
% clear and noticeable error message.
%
% There are two directions from which to approach the question of what
% to load.  One is to specify the ranges of Unicode characters that will
% result in some sensible typesetting; this requires the provider to
% ensure that suitable fonts are loaded and that these input characters
% generate the correct typesetting via the encodings of those fonts.  The
% other is to inspect the font encodings to be used and use these to
% define which input Unicode characters should be supported.
%
% For Western European languages, at least, going in either direction
% leads to many straightforward decisions and a few that are more
% subjective.  In both cases some of the specifications are \TeX{}
% specific whilst most are independent of the particular typesetting
% software in use.
%
% As we have argued elsewhere, \LaTeX{} needs to refer to characters via
% `seven-bit-text' names and, so far, these have been chosen by
% reference to historical sources such as Plain \TeX{} or Adobe encoding
% descriptions.  It is unclear whether this ad hoc naming structure should
% simply be extended or whether it would be useful to
% supplement it with standardised internal Unicode character names such as
% one or more of the following:\footnote{Burkhard und Holger Mittelbach
%   spielen mit mir!  Sie haben etwas hier geschrieben.}
%
% \begin{verbatim}
%   \ltxutwochar <4 hex digits>
%
%   \ltxuchar {<hex digits>}
%     B H U R R R
%
%   \ltxueightchartwo   <2 utf8 octets as 8-bit char tokens>
%   \ltxueightcharthree <3 utf8 octets ...>
%   \ltxueightcharfour  <4 utf8 octets ...>
% \end{verbatim}
%
%
% \subsection{More specific stuff}
%
% In addition to setting up the mechanism for reading UTF-8 characters
% and specifying the \LaTeX-level support available, this package
% contains support for some default historically expected \TeX-related
% characters and some example `Unicode definition files' for standard
% font encodings.
%
%
% \subsection{Notes}
%
% This package does not support Unicode combining characters as \TeX{}
% is not really equipped to make this possible.
%
%  No attempt is made to be useful beyond Latin, and maybe Cyrillic,
%  for European languages (as of now).
%
%
% \subsection{Basic operation of the code}
%
% The \texttt{inputenc} package makes the upper 8-bit characters active and
%    assigns to all of them an error message. It then waits for the
%    input encoding files to change this set-up.  Similarly, whenever
%    |\inputencoding| is encountered in a document, first the upper
%    8-bit characters are set back to produce an error and then the
%    definitions for the new input encoding are loaded, changing some of the
%    previous settings.
%
%    The 8-bit input encodings currently supported by \texttt{inputenc}
%    all use declarations such as |\DeclareInputText| and the like to map an
%    8-bit number to some \LaTeX{} internal form, e.g.~to |\"a|.
%
%    The situation when supporting UTF-8 as the input encoding is
%    different, however. Here we only have to set up the actions of
%    those 8-bit numbers that can be the first octet in a UTF-8
%    representation of a Unicode character.  But we cannot simply set
%    this to some internal \LaTeX{} form since the Unicode character
%    consists of more than one octet; instead we have to define this
%    starting octet to parse the right number of further octets that
%    together form the UTF-8 representation of some Unicode character.
%
%    Therefore when switching to \texttt{utf8} within the
%    \texttt{inputenc} framework the characters with numbers (hex)
%    from \texttt{"C2} to \texttt{"DF} are defined to parse for a
%    second octet following, the characters from \texttt{"E0} to
%    \texttt{"EF} are defined to parse for two more octets and finally
%    the characters from \texttt{"F0} to \texttt{"F3} are defined to
%    parse for three additional octets.  These additional octets are
%    always in the range \texttt{"80} to \texttt{"B9}.
%
%    Thus, when such a character is encountered in the document (so
%    long as expansion is not prohibited) a defined number of
%    additional octets (8-bit characters) are read and from them a
%    unique control sequence name is immediately constructed.
%
%    This control sequence is either defined (good) or undefined
%    (likely); in the latter case the user gets an error message
%    saying that this UTF-8 sequence (or, better, Unicode character)
%    is not supported.
%
%    If the control sequence is set up to do something useful then it will
%    expand to a \LaTeX{} internal form: e.g.~for the utf8 sequence of
%    two octets \texttt{"C3 "A4} we get |\"a| as the
%    internal form which then, depending on the font encoding,
%    eventually resolves to the single glyph `latin-a-umlaut' or to
%    the composite glyph `latin-a with an umlaut accent'.
%
%    These mappings from (UTF-8 encoded) Unicode characters to \LaTeX{}
%    internal forms are made indirectly.  The code below provides a
%    declaration |\DeclareUnicodeCharacter| which maps Unicode numbers
%    (as hexadecimal) to \LaTeX{} internal forms.
%
%    This mapping needs to be set up only once so here it is done at
%    |\begin{document}| by looking at the list of font encodings that
%    are loaded by the document and providing mappings related to
%    those font encodings whenever these are available. Thus at most
%    only those Unicode characters that can be represented by the glyphs
%    available in these encodings will be defined.
%
%    Technically this is done by loading one file per encoding,
%    if available, that is supposed to provide the necessary mapping
%    information.
%
%
% \StopEventually{}
%
%
%
%
% \section{Coding}
%
% \subsection{Housekeeping}
%
%    The usual introductory bits and pieces:
%
%    \begin{macrocode}
%<utf8>\ProvidesFile{utf8.def}
%<test>\ProvidesFile{utf8-test.tex}
%<+lcy> \ProvidesFile{lcyenc.dfu}
%<+ly1> \ProvidesFile{ly1enc.dfu}
%<+oms> \ProvidesFile{omsenc.dfu}
%<+ot1> \ProvidesFile{ot1enc.dfu}
%<+ot2> \ProvidesFile{ot2enc.dfu}
%<+t1>  \ProvidesFile{t1enc.dfu}
%<+t2a> \ProvidesFile{t2aenc.dfu}
%<+t2b> \ProvidesFile{t2benc.dfu}
%<+t2c> \ProvidesFile{t2cenc.dfu}
%<+ts1> \ProvidesFile{ts1enc.dfu}
%<+x2>  \ProvidesFile{x2enc.dfu}
%<+all> \ProvidesFile{utf8enc.dfu}
   [2008/04/05 v1.1m UTF-8 support for inputenc]
%    \end{macrocode}
%
%    \begin{macrocode}
%<*utf8>
\makeatletter
%    \end{macrocode}
%    We restore the |\catcode| of space (which is set to ignore in
%    \texttt{inputenc}) while reading \texttt{.def} files. Otherwise
%    we would need to explicitly use |\space| all over the place in
%    error and log messages.
% \changes{v1.1d}{2004/05/08}{Explicitly set catcode of space}
%    \begin{macrocode}
\catcode`\ \saved@space@catcode
%    \end{macrocode}
%
%
%
% \subsection{Parsing UTF-8 input}
%
% \begin{macro}{\UTFviii@two@octets}
% \begin{macro}{\UTFviii@three@octets}
% \begin{macro}{\UTFviii@four@octets}
%    A UTF-8 char (that is not actually a 7-bit char, i.e.~a single
%    octet) is parsed as follows: each starting octet is an active
%    \TeX{} character token; each of these is defined below to be a
%    macro with one to three arguments nominally (depending on the
%    starting octet). It calls one of |\UTFviii@two@octets|,
%    |\UTFviii@three@octets|, or |\UTFviii@four@octets| which then
%    actually picks up the argument(s).
%
%    From the arguments a control sequence with a name of the form
%    \verb=u8:#1#2...= is constructed where the |#i| ($i>1$) are the
%    arguments and |#1| is the starting octet (as a \TeX{} character
%    token).  Since some or even all of these characters are active
%    (when inputenc is loaded) we need to use |\string| when building
%    the csname.
%
%    The csname thus constructed can of course be undefined but to
%    avoid producing an unhelpful low-level undefined command error we
%    pass it to |\UTFviii@defined| which is responsible for producing
%    a more sensible error message (not yet done!!).  If, however, it is
%    defined we simply execute the thing (which should then expand to
%    an encoding specific internal \LaTeX{} form).
%    \begin{macrocode}
\def\UTFviii@two@octets#1#2{\expandafter
    \UTFviii@defined\csname u8:#1\string#2\endcsname}
%    \end{macrocode}
% \end{macro}
%
%    \begin{macrocode}
\def\UTFviii@three@octets#1#2#3{\expandafter
    \UTFviii@defined\csname u8:#1\string#2\string#3\endcsname}
%    \end{macrocode}
% \end{macro}
%
%    \begin{macrocode}
\def\UTFviii@four@octets#1#2#3#4{\expandafter
    \UTFviii@defined\csname u8:#1\string#2\string#3\string#4\endcsname}
%    \end{macrocode}
% \end{macro}
%
% \begin{macro}{\UTFviii@defined}
%    This tests whether its argument is different from |\relax|: it
%    either calls for a sensible error message (not done), or it gets
%    the |\fi| out of the way (in case the command has arguments) and
%    executes it.
%    \begin{macrocode}
\def\UTFviii@defined#1{%
  \ifx#1\relax
%    \end{macrocode}
%    The endline character has a special definition within the
%    inputenc package (it is gobbling spaces). For this reason we
%    can't produce multiline strings without some precaution.
% \changes{v1.1b}{2004/02/09}{No newlines allowed in error messages}
% \changes{v1.1g}{2005/09/27}{Real spaces do not show up so use \cs{space}}
%    \begin{macrocode}
      \PackageError{inputenc}{Unicode\space char\space \string#1\space
                              not\space set\space up\space
                              for\space use\space with\space LaTeX}\@eha
  \else\expandafter
    #1%
  \fi
}
%    \end{macrocode}
% \end{macro}
%
% \begin{macro}{\UTFviii@loop}
%    This wonderful bit of code from Dr Carlisle defines the starting
%    octets to call |\UTFviii@two@octets| etc as appropriate. The starting
%    octet itself is passed directly as the first argument, the others
%    are picked up later en route.
%
%    The |\UTFviii@loop| loops through the numbers starting at
%    |\count@| and ending at |\@tempcnta|${} - 1$, each time executing
%    the code in |\UTFviii@tmp|.
%
%    All this is done in a group so that temporary catcode changes
%    etc.~vanish after everything is set up.
%
%    It may be a good idea to add code to deal with `illegal utf8 octets':
%    at present these will be handled by whatever code was in use for 8-bit
%    input before this code is executed.
%
%    \begin{macrocode}
\begingroup
\catcode`\~13
\catcode`\"12
%    \end{macrocode}
%
%    \begin{macrocode}
\def\UTFviii@loop{%
  \uccode`\~\count@
  \uppercase\expandafter{\UTFviii@tmp}%
  \advance\count@\@ne
  \ifnum\count@<\@tempcnta
  \expandafter\UTFviii@loop
  \fi}
%    \end{macrocode}
%
%    Setting up 2-byte UTF-8:
%    \begin{macrocode}
    \count@"C2
    \@tempcnta"E0
    \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@two@octets\string~}}
\UTFviii@loop
%    \end{macrocode}
%    Setting up 3-byte UTF-8:
%    \begin{macrocode}
    \count@"E0
    \@tempcnta"F0
    \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@three@octets\string~}}
\UTFviii@loop
%    \end{macrocode}
%
%    Setting up 4-byte UTF-8:
%    \begin{macrocode}
    \count@"F0
    \@tempcnta"F4
    \def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@four@octets\string~}}
\UTFviii@loop
\endgroup
%    \end{macrocode}
% \end{macro}
%
%    For this case we must disable the warning generated by
%    \texttt{inputenc} if it doesn't see any new |\DeclareInputText|
%    commands.
%    \begin{macrocode}
\@inpenc@test
%    \end{macrocode}
%
%
%    If this file (\texttt{utf8.def}) is not being read while setting
%    up \texttt{inputenc}, i.e.~in the preamble, but when
%    |\inputencoding| is called somewhere within the document, we do not
%    need to input the specific Unicode mappings again. We therefore
%    stop reading the file at this point.
%    \begin{macrocode}
\ifx\@begindocumenthook\@undefined
  \makeatother
%    \end{macrocode}
%    The |\fi| must be on the same line as |\endinput| or else it will
%    never be seen!
%    \begin{macrocode}
  \endinput \fi
%    \end{macrocode}
%
%
% \subsection{Mapping Unicode codes to \LaTeX{} internal forms}
%
%
% \begin{macro}{\DeclareUnicodeCharacter}
%    The |\DeclareUnicodeCharacter| declaration defines a mapping from
%    a Unicode character code point to a \LaTeX{} internal form. The first
%    argument is the Unicode number as hexadecimal digits and the second is
%    the actual \LaTeX{} internal form.
%
%    We start by making sure that some characters have the right
%    |\catcode| when they are used in the definitions below.
%    \begin{macrocode}
\begingroup
\catcode`\"=12
\catcode`\<=12
\catcode`\.=12
\catcode`\,=12
\catcode`\;=12
\catcode`\!=12
\catcode`\~=13
%    \end{macrocode}
%
%    \begin{macrocode}
\gdef\DeclareUnicodeCharacter#1#2{%
   \count@"#1\relax
   \wlog{ \space\space defining Unicode char U+#1 (decimal \the\count@)}%
   \begingroup
%    \end{macrocode}
%    Next we do the parsing of the number stored in |\count@| and assign the
%    result to |\UTFviii@tmp|. Actually all this could be done in-line,
%    the macro |\parse@XML@charref| is only there to extend this code
%    to parsing Unicode numbers in other contexts one day (perhaps).
%    \begin{macrocode}
    \parse@XML@charref
%    \end{macrocode}
%
%    Here is an example of what is happening, for the pair \texttt{"C2 "A3}
%    (which is the utf8 represenation for the character \textsterling{}).
%    After |\parse@XML@charref| we have, stored in |\UTFviii@tmp|, a
%    single command with two character tokens as arguments:
%    \begin{quote}
%      [$t_{C2}$ and $t_{A3}$ are the characters corresponding to these
%      two octets]\\
%      |\UTFviii@two@octets| $t_{\rm C2}t_{\rm A3}$
%    \end{quote}
%    what we actually need to produce is a definition of the form
%    \begin{quote}
%    |\def\u8:|$t_{\rm C2}$$t_{\rm A3}$ |{|\textit{\LaTeX{} internal form}|}|\,.
%    \end{quote}
%    So here we temporarily redefine the prefix commands
%    |\UTFviii@two@octets|, etc.~to
%    generate the csname that we wish to define>  the |\string|s are
%    added in case these tokens are still active.
%    \begin{macrocode}
    \def\UTFviii@two@octets##1##2{\csname u8:##1\string##2\endcsname}%
    \def\UTFviii@three@octets##1##2##3{\csname u8:##1%
                                     \string##2\string##3\endcsname}%
    \def\UTFviii@four@octets##1##2##3##4{\csname u8:##1%
                           \string##2\string##3\string##4\endcsname}%
%    \end{macrocode}
%    Now we simply:-) need to use the right number of |\expandafter|s to
%    finally construct the definition: expanding |\UTFviii@tmp| once to get
%    its contents, a second time to replace the prefix command by its
%    |\csname| expansion, and a third time to turn the expansion into
%    a csname after which the |\gdef| finally gets applied.
%    We add an irrelevant |\IeC| and braces around the definition, in
%    order to avoid any space after the command being gobbled up
%    when the text is written out to an auxiliary file (see
%    \texttt{inputenc} for further details
%    \begin{macrocode}
    \expandafter\expandafter\expandafter
    \expandafter\expandafter\expandafter
    \expandafter
     \gdef\UTFviii@tmp{\IeC{#2}}%
   \endgroup
}
%    \end{macrocode}
% \end{macro}
%
%
% \begin{macro}{\parse@XML@charref}
%    This macro parses a Unicode number (decimal) and returns its
%    UTF-8 representation as a sequence of non-active \TeX{} character
%    tokens. In the
%    original code it had two arguments delimited by \texttt{;} here,
%    however, we supply the Unicode number implicitly.
%    \begin{macrocode}
\gdef\parse@XML@charref{%
%    \end{macrocode}
%    We need to keep a few things local, mainly the |\uccode|'s that
%    are set up below. However, the group originally used here is
%    actually unnecessary since we call this macro only within another
%    group; but it will be important to restore the group if this
%    macro gets used for other purposes.
%    \begin{macrocode}
%  \begingroup
%    \end{macrocode}
%    The original code from David supported the convention that a
%    Unicode slot number could be given either as a decimal or as a
%    hexadecimal (by starting with \texttt{x}).  We do not do this so
%    this code is also removed.  This could be reactivated if one
%    wants to support document commands that accept Unicode numbers
%    (but then the first case needs to be changed from an error
%    message back to something more useful again).
%    \begin{macrocode}
%  \uppercase{\count@\if x\noexpand#1"\else#1\fi#2}\relax
%    \end{macrocode}
%    As |\count@| already contains the right value we make
%    |\parse@XML@charref| work without arguments.
% \changes{v1.1g}{2005/09/27}{Real spaces do not show up so use \cs{space}}
%    \begin{macrocode}
  \ifnum\count@<"A0\relax
     \PackageError{inputenc}{Cannot\space define\space Unicode\space
                             char\space value\space <\space 00A0}\@eha
%    \end{macrocode}
%    Do not ask us to provide an explanation for the code below, it is
%    borrowed straight from \texttt{xmltex} by David and we trust him
%    totally (and we are too lazy to reread the Unicode book to see if
%    this is the correct algorithm).\footnote{We were hoping to also
%    find in his work the \TeX{} code for going the other way: from
%    UTF-8 octets to Unicode slot number, but no luck!}
%    \begin{macrocode}
  \else\ifnum\count@<"800\relax
     \parse@UTFviii@a,%
     \parse@UTFviii@b C\UTFviii@two@octets.,%
  \else\ifnum\count@<"10000\relax
     \parse@UTFviii@a;%
     \parse@UTFviii@a,%
     \parse@UTFviii@b E\UTFviii@three@octets.{,;}%
   \else
     \parse@UTFviii@a;%
     \parse@UTFviii@a,%
     \parse@UTFviii@a!%
     \parse@UTFviii@b F\UTFviii@four@octets.{!,;}%
    \fi
    \fi
  \fi
%  \endgroup
}
%    \end{macrocode}
% \end{macro}
%
% \begin{macro}{\parse@UTFviii@a}
%    \ldots so somebody else can document this part :-) \ldots~David?:-))))!
% \changes{v1.1b}{2004/02/09}{Space in the wrong place \cs{count @64}}
%    \begin{macrocode}
\gdef\parse@UTFviii@a#1{%
     \@tempcnta\count@
     \divide\count@ 64
     \@tempcntb\count@
     \multiply\count@ 64
     \advance\@tempcnta-\count@
     \advance\@tempcnta 128
     \uccode`#1\@tempcnta
     \count@\@tempcntb}
%    \end{macrocode}
% \end{macro}
%
% \begin{macro}{\parse@UTFviii@b}
%    \ldots same here
%    \begin{macrocode}
\gdef\parse@UTFviii@b#1#2#3#4{%
     \advance\count@ "#10\relax
     \uccode`#3\count@
     \uppercase{\gdef\UTFviii@tmp{#2#3#4}}}
%    \end{macrocode}
%
%    \begin{macrocode}
\endgroup
%    \end{macrocode}
% \end{macro}
%
%    \begin{macrocode}
\@onlypreamble\DeclareUnicodeCharacter
%    \end{macrocode}
%    These are preamble only as long as we don't support Unicode
%    charrefs in documents.
%    \begin{macrocode}
\@onlypreamble\parse@XML@charref
\@onlypreamble\parse@UTFviii@a
\@onlypreamble\parse@UTFviii@b
%    \end{macrocode}
%
%
% \subsection{Loading Unicode mappings at begin document}
%
% The original plan was to set up the UTF-8 support at
% |\begin{document}|; but then any text characters used in the preamble
% (as people do even though advised against it) would fail in one way or
% the other.
% So the implementation was changed and the Unicode definition files
% for already defined encodings are loaded here.
%
%    We loop through all defined font encodings
%    (stored in |\cdp@list|) and for each load a file
%    \textit{name}\texttt{enc.dfu} if it exist. That file is then
%    supposed to contain |\DeclareUnicodeCharacter| declarations.
%    \begin{macrocode}
\begingroup
  \def\cdp@elt#1#2#3#4{%
    \wlog{Now handling font encoding #1 ...}%
    \lowercase{%
        \InputIfFileExists{#1enc.dfu}}%
           {\wlog{... processing UTF-8 mapping file for font %
                     encoding #1}%
%    \end{macrocode}
% \changes{v1.1m}{2008/04/05}{Ensure we don't lose spaces in the log}
%    The previous line is written to the log with the newline char being
%    ignored (thus not producing a space). Therefore either everything has to
%    be on a single input line or some specical care must be taken.  From this
%    point on we ignore spaces again, i.e., while we are reading the
%    \texttt{.dfu} file. The |\endgroup| below will restore it again.
% \changes{v1.1d}{2004/05/08}{Explicitly set catcode of space}
% \changes{v1.1g}{2005/09/27}{We lost the ``false'' case}
%    \begin{macrocode}
            \catcode`\ 9\relax}%
          {\wlog{... no UTF-8 mapping file for font encoding #1}}%
  }
  \cdp@list
\endgroup
%    \end{macrocode}
% However, we don't know if there are font encodings still to be
% loaded (either with \texttt{fontenc} or directly with |\input| by
% some some package). Font enconding files are loaded only if the
% corresponding encoding has not been loaded yet, and they always
% begin with |\DeclareFontEncoding|. We now redefine the internal
% kernel version of the latter to load the Unicode file if available.
%
%    \begin{macrocode}
\def\DeclareFontEncoding@#1#2#3{%
  \expandafter
  \ifx\csname T@#1\endcsname\relax
    \def\cdp@elt{\noexpand\cdp@elt}%
    \xdef\cdp@list{\cdp@list\cdp@elt{#1}%
                    {\default@family}{\default@series}%
                    {\default@shape}}%
    \expandafter\let\csname#1-cmd\endcsname\@changed@cmd
    \begingroup
      \wlog{Now handling font encoding #1 ...}%
      \lowercase{%
        \InputIfFileExists{#1enc.dfu}}%
           {\wlog{... processing UTF-8 mapping file for font %
                      encoding #1}}%
           {\wlog{... no UTF-8 mapping file for font encoding #1}}%
    \endgroup
  \else
     \@font@info{Redeclaring font encoding #1}%
  \fi
  \global\@namedef{T@#1}{#2}%
  \global\@namedef{M@#1}{\default@M#3}%
  \xdef\LastDeclaredEncoding{#1}%
  }
%</utf8>
%    \end{macrocode}
%
%
%
% \section{Mapping characters ---\newline based on font (glyph) encodings}
%
% This section is a first attempt to provide Unicode definitions for
% characters whose standard glyphs are currently provided by the
% standard \LaTeX{} font-encodings |T1|, |OT1|, etc. They are by
% no means completed and need checking.
%
% For example, one should check the already existing input encodings
%    for glyphs that may in fact be available and required,
%    e.g.~\texttt{latin4} has a number of glyphs with the |\=|
%    accent. Since the |T1| encoding does not provide such glyphs,
%    these characters are not listed below (yet).
%
% The list below was generated by looking at the current \LaTeX{} font
%    encoding files, e.g., \texttt{t1enc.def} and using the work by
%    Sebastian Rahtz in (\texttt{ucharacters.sty}), with a few
%    modifications. In combinations such as |\^\i| the preferred form
%    is that and not |\^i|.
%
% This list has been built from several sources, obviously including
% the Unicode Standard itself. These sources include Passive \TeX{} by
% Sebastian Rahtz, the \texttt{unicode}
% package by Dominique P. G. Unruh (mainly for Latin encodings) and
% \texttt{text4ht} by Eitan Gurari (for Cyrillic ones).
%
% Note that it strictly follows the Mittelbach principles for
% input character encodings: thus it offers no support for using utf8
% representations of math symbols such as $\times$ or $\div$ (in math mode).
%
%
% \subsection{About the table itself}
%
% In addition to generating indivdual files, the table below is, at present,
% a one-one (we think) partial relationship between the (ill-defined) set
% of LICRs and the Unicode slots "0080 to "FFFF.  At present these entries
% are used only to define a collection of partial mappings from Unicode
% slots to LICRs; each of these mappings becomes full if we add an exception
% value (`not defined') to the set of LICRs.
%
% It is probably not essential for the relationship in the full table to be
% one-one; this raises questions suach as: the exact role of LICRs;
% the formal relationships on the set of LICRs; the (non-mathematical)
% relationship between
% LICRs and Unicode (which has its own somewhat fuzzy equivalences);
% and ultimately what a character is and what a character representation
% and/or name is.
%
% Viewed this a way, the result has, perhaps puzzingly, just two (we think)
% gaps in the second 128 `Unicode slots' (00A0 and 00AD): neither of these
% is really a character, of course.
%
% It is unclear the extent to which entries in this table should
% resemble the closely related ones in the 8-bit \texttt{inputenc} files.
% The Unicode standard claims that the first 256 slots `are' ASCII and
% Latin-1.
%
% Of course, \TeX{} itself typically does not treat even many perfectly
% `normal text' 7-bit slots as text characters, so it is unclear
% whether \LaTeX{} should even attempt to deal in any consistent way with
% those Unicode slots that are not definitive text characters.
%
%
% \subsection{The mapping table}
%
% Note that the first argument must be a 4-hex-digit number greater
% than \texttt{00BF}.
%
% There are few notes about inconsistencies etc at the end of the table.
%
%    \begin{macrocode}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00A1}{\textexclamdown}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00A2}{\textcent}
%<all,ts1,t1,ot1,ly1>\DeclareUnicodeCharacter{00A3}{\textsterling}
%<all,x2,ts1,t2c,t2b,t2a,ly1,lcy>\DeclareUnicodeCharacter{00A4}{\textcurrency}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00A5}{\textyen}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00A6}{\textbrokenbar}
%<all,x2,ts1,t2c,t2b,t2a,oms,ly1>\DeclareUnicodeCharacter{00A7}{\textsection}
%<all,ts1>\DeclareUnicodeCharacter{00A8}{\textasciidieresis}
%<all,ts1,utf8>\DeclareUnicodeCharacter{00A9}{\textcopyright}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00AA}{\textordfeminine}
%<all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>\DeclareUnicodeCharacter{00AB}{\guillemotleft}
%<all,ts1>\DeclareUnicodeCharacter{00AC}{\textlnot}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00AE}{\textregistered}
%<all,ts1>\DeclareUnicodeCharacter{00AF}{\textasciimacron}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00B0}{\textdegree}
%<all,ts1>\DeclareUnicodeCharacter{00B1}{\textpm}
%<all,ts1>\DeclareUnicodeCharacter{00B2}{\texttwosuperior}
%<all,ts1>\DeclareUnicodeCharacter{00B3}{\textthreesuperior}
%<all,ts1>\DeclareUnicodeCharacter{00B4}{\textasciiacute}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00B5}{\textmu} % micro sign
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{00B6}{\textparagraph}
%<all,oms,ts1,ly1>\DeclareUnicodeCharacter{00B7}{\textperiodcentered}
%<all,ot1>\DeclareUnicodeCharacter{00B8}{\c\ }
%<all,ts1>\DeclareUnicodeCharacter{00B9}{\textonesuperior}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00BA}{\textordmasculine}
%<all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>\DeclareUnicodeCharacter{00BB}{\guillemotright}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BC}{\textonequarter}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BD}{\textonehalf}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BE}{\textthreequarters}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00BF}{\textquestiondown}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C0}{\@tabacckludge`A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C1}{\@tabacckludge'A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C2}{\^A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C3}{\~A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C4}{\"A}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00C5}{\r A}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00C6}{\AE}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C7}{\c C}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C8}{\@tabacckludge`E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C9}{\@tabacckludge'E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CA}{\^E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CB}{\"E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CC}{\@tabacckludge`I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CD}{\@tabacckludge'I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CE}{\^I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CF}{\"I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D0}{\DH}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D1}{\~N}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D2}{\@tabacckludge`O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D3}{\@tabacckludge'O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D4}{\^O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D5}{\~O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D6}{\"O}
%<all,ts1>\DeclareUnicodeCharacter{00D7}{\texttimes}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00D8}{\O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D9}{\@tabacckludge`U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DA}{\@tabacckludge'U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DB}{\^U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DC}{\"U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DD}{\@tabacckludge'Y}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DE}{\TH}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00DF}{\ss}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E0}{\@tabacckludge`a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E1}{\@tabacckludge'a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E2}{\^a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E3}{\~a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E4}{\"a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E5}{\r a}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00E6}{\ae}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E7}{\c c}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E8}{\@tabacckludge`e}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E9}{\@tabacckludge'e}
%<all,t1,ly1>\DeclareUnicodeCharacter{00EA}{\^e}
%<all,t1,ly1>\DeclareUnicodeCharacter{00EB}{\"e}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00EC}{\@tabacckludge`\i}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00ED}{\@tabacckludge'\i}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00EE}{\^\i}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00EF}{\"\i}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F0}{\dh}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F1}{\~n}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F2}{\@tabacckludge`o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F3}{\@tabacckludge'o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F4}{\^o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F5}{\~o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F6}{\"o}
%<all,ts1>\DeclareUnicodeCharacter{00F7}{\textdiv}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00F8}{\o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F9}{\@tabacckludge`u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FA}{\@tabacckludge'u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FB}{\^u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FC}{\"u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FD}{\@tabacckludge'y}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FE}{\th}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FF}{\"y}
%<all,t1>\DeclareUnicodeCharacter{0102}{\u A}
%<all,t1>\DeclareUnicodeCharacter{0103}{\u a}
%<all,t1>\DeclareUnicodeCharacter{0104}{\k A}
%<all,t1>\DeclareUnicodeCharacter{0105}{\k a}
%<all,t1>\DeclareUnicodeCharacter{0106}{\@tabacckludge'C}
%<all,t1>\DeclareUnicodeCharacter{0107}{\@tabacckludge'c}
%<all,t1>\DeclareUnicodeCharacter{010C}{\v C}
%<all,t1>\DeclareUnicodeCharacter{010D}{\v c}
%<all,t1>\DeclareUnicodeCharacter{010E}{\v D}
%<all,t1>\DeclareUnicodeCharacter{010F}{\v d}
%<all,t1>\DeclareUnicodeCharacter{0110}{\DJ}
%<all,t1>\DeclareUnicodeCharacter{0111}{\dj}
%<all,t1>\DeclareUnicodeCharacter{0118}{\k E}
%<all,t1>\DeclareUnicodeCharacter{0119}{\k e}
%<all,t1>\DeclareUnicodeCharacter{011A}{\v E}
%<all,t1>\DeclareUnicodeCharacter{011B}{\v e}
%<all,t1>\DeclareUnicodeCharacter{011E}{\u G}
%<all,t1>\DeclareUnicodeCharacter{011F}{\u g}
%<all,t1>\DeclareUnicodeCharacter{0130}{\.I}
%<all,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{0131}{\i}
%<all,t1>\DeclareUnicodeCharacter{0132}{\IJ}
%<all,t1>\DeclareUnicodeCharacter{0133}{\ij}
%<all,t1>\DeclareUnicodeCharacter{0139}{\@tabacckludge'L}
%<all,t1>\DeclareUnicodeCharacter{013A}{\@tabacckludge'l}
%<all,t1>\DeclareUnicodeCharacter{013D}{\v L}
%<all,t1>\DeclareUnicodeCharacter{013E}{\v l}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0141}{\L}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0142}{\l}
%<all,t1>\DeclareUnicodeCharacter{0143}{\@tabacckludge'N}
%<all,t1>\DeclareUnicodeCharacter{0144}{\@tabacckludge'n}
%<all,t1>\DeclareUnicodeCharacter{0147}{\v N}
%<all,t1>\DeclareUnicodeCharacter{0148}{\v n}
%<all,t1>\DeclareUnicodeCharacter{014A}{\NG}
%<all,t1>\DeclareUnicodeCharacter{014B}{\ng}
%<all,t1>\DeclareUnicodeCharacter{0150}{\H O}
%<all,t1>\DeclareUnicodeCharacter{0151}{\H o}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{0152}{\OE}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{0153}{\oe}
%<all,t1>\DeclareUnicodeCharacter{0154}{\@tabacckludge'R}
%<all,t1>\DeclareUnicodeCharacter{0155}{\@tabacckludge'r}
%<all,t1>\DeclareUnicodeCharacter{0158}{\v R}
%<all,t1>\DeclareUnicodeCharacter{0159}{\v r}
%<all,t1>\DeclareUnicodeCharacter{015A}{\@tabacckludge'S}
%<all,t1>\DeclareUnicodeCharacter{015B}{\@tabacckludge's}
%<all,t1>\DeclareUnicodeCharacter{015E}{\c S}
%<all,t1>\DeclareUnicodeCharacter{015F}{\c s}
%<all,t1,ly1>\DeclareUnicodeCharacter{0160}{\v S}
%<all,t1,ly1>\DeclareUnicodeCharacter{0161}{\v s}
%<all,t1>\DeclareUnicodeCharacter{0162}{\c T}
%<all,t1>\DeclareUnicodeCharacter{0163}{\c t}
%<all,t1>\DeclareUnicodeCharacter{0164}{\v T}
%<all,t1>\DeclareUnicodeCharacter{0165}{\v t}
%<all,t1>\DeclareUnicodeCharacter{016E}{\r U}
%<all,t1>\DeclareUnicodeCharacter{016F}{\r u}
%<all,t1>\DeclareUnicodeCharacter{0170}{\H U}
%<all,t1>\DeclareUnicodeCharacter{0171}{\H u}
%<all,t1,ly1>\DeclareUnicodeCharacter{0178}{\"Y}
%<all,t1>\DeclareUnicodeCharacter{0179}{\@tabacckludge'Z}
%<all,t1>\DeclareUnicodeCharacter{017A}{\@tabacckludge'z}
%<all,t1>\DeclareUnicodeCharacter{017B}{\.Z}
%<all,t1>\DeclareUnicodeCharacter{017C}{\.z}
%<all,t1,ly1>\DeclareUnicodeCharacter{017D}{\v Z}
%<all,t1,ly1>\DeclareUnicodeCharacter{017E}{\v z}
%<all,ts1,ly1>\DeclareUnicodeCharacter{0192}{\textflorin}
%<all,ly1,utf8>\DeclareUnicodeCharacter{02C6}{\textasciicircum}
%<all,ts1>\DeclareUnicodeCharacter{02C7}{\textasciicaron}
%<all,ly1,utf8>\DeclareUnicodeCharacter{02DC}{\textasciitilde}
%<all,ts1>\DeclareUnicodeCharacter{02D8}{\textasciibreve}
%<all,ts1>\DeclareUnicodeCharacter{02DD}{\textacutedbl}
%    \end{macrocode}
%    The Cyrillic code points have been recently checked (2007) and extended
%    and corrected by Matthias Noe (\verb=a9931078@unet.univie.ac.at=) --- thanks.
% \changes{v1.1j}{2007/11/09}{Added a few new unicode decls in cyrillic (pr/3988)}
% \changes{v1.1k}{2007/11/11}{Added and further unicode decls in cyrillic}
%    \begin{macrocode}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0400}{\@tabacckludge`\CYRE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0401}{\CYRYO}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{0402}{\CYRDJE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0403}{\@tabacckludge`\CYRG}
%<all,x2,t2a,ot2,lcy>\DeclareUnicodeCharacter{0404}{\CYRIE}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0405}{\CYRDZE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0406}{\CYRII}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0407}{\CYRYI}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0408}{\CYRJE}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{0409}{\CYRLJE}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{040A}{\CYRNJE}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{040B}{\CYRTSHE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{040C}{\@tabacckludge`\CYRK}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{040D}{\@tabacckludge`\CYRI}
%<all,x2,t2b,t2a,lcy>\DeclareUnicodeCharacter{040E}{\CYRUSHRT}
%<all,x2,t2c,t2a,ot2>\DeclareUnicodeCharacter{040F}{\CYRDZHE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0410}{\CYRA}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0411}{\CYRB}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0412}{\CYRV}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0413}{\CYRG}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0414}{\CYRD}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0415}{\CYRE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0416}{\CYRZH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0417}{\CYRZ}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0418}{\CYRI}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0419}{\CYRISHRT}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{041A}{\CYRK}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{041B}{\CYRL}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{041C}{\CYRM}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{041D}{\CYRN}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{041E}{\CYRO}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{041F}{\CYRP}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0420}{\CYRR}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0421}{\CYRS}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0422}{\CYRT}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0423}{\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0424}{\CYRF}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0425}{\CYRH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0426}{\CYRC}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0427}{\CYRCH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0428}{\CYRSH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0429}{\CYRSHCH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{042A}{\CYRHRDSN}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{042B}{\CYRERY}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{042C}{\CYRSFTSN}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{042D}{\CYREREV}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{042E}{\CYRYU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{042F}{\CYRYA}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0430}{\cyra}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0431}{\cyrb}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0432}{\cyrv}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0433}{\cyrg}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0434}{\cyrd}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0435}{\cyre}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0436}{\cyrzh}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0437}{\cyrz}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0438}{\cyri}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0439}{\cyrishrt}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{043A}{\cyrk}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{043B}{\cyrl}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{043C}{\cyrm}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{043D}{\cyrn}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{043E}{\cyro}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{043F}{\cyrp}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0440}{\cyrr}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0441}{\cyrs}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0442}{\cyrt}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0443}{\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0444}{\cyrf}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0445}{\cyrh}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0446}{\cyrc}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0447}{\cyrch}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0448}{\cyrsh}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0449}{\cyrshch}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044A}{\cyrhrdsn}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044B}{\cyrery}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044C}{\cyrsftsn}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044D}{\cyrerev}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044E}{\cyryu}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044F}{\cyrya}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0450}{\@tabacckludge`\cyre}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0451}{\cyryo}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{0452}{\cyrdje}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0453}{\@tabacckludge`\cyrg}
%<all,x2,t2a,ot2,lcy>\DeclareUnicodeCharacter{0454}{\cyrie}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0455}{\cyrdze}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0456}{\cyrii}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0457}{\cyryi}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0458}{\cyrje}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{0459}{\cyrlje}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{045A}{\cyrnje}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{045B}{\cyrtshe}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{045C}{\@tabacckludge`\cyrk}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{045D}{\@tabacckludge`\cyri}
%<all,x2,t2b,t2a,lcy>\DeclareUnicodeCharacter{045E}{\cyrushrt}
%<all,x2,t2c,t2a,ot2>\DeclareUnicodeCharacter{045F}{\cyrdzhe}
%<all,x2,ot2>\DeclareUnicodeCharacter{0462}{\CYRYAT}
%<all,x2,ot2>\DeclareUnicodeCharacter{0463}{\cyryat}
%<all,x2>\DeclareUnicodeCharacter{046A}{\CYRBYUS}
%<all,x2>\DeclareUnicodeCharacter{046B}{\cyrbyus}
%    \end{macrocode}
%    The next two declarations are questionable, the encoding definition
%    should probably contain |\CYROTLD| and |\cyrotld|. Or alternatively, if
%    the characters in the X2 encodings are really meant to represent the
%    historical characters in Ux0472 and Ux0473 (they look like them) then
%    they would need to change instead.
%
%    However, their looks are probably a font designers decision and the next
%    two mappings are wrong or rather the names in OT2 should change for
%    consistancy.
%
%    On the other hand the names |\CYROTLD| are somewhat questionabled as the
%    Unicode standard only describes ``Cyrillic barred O'' while |TLD| refers
%    to a tilde (which is more less what the ``Cyrillic FITA looks according
%    to the Unicode book).
%    \begin{macrocode}
%<all,ot2>\DeclareUnicodeCharacter{0472}{\CYRFITA}
%<all,ot2>\DeclareUnicodeCharacter{0473}{\cyrfita}
%    \end{macrocode}
%
%    \begin{macrocode}
%<all,x2,ot2>\DeclareUnicodeCharacter{0474}{\CYRIZH}
%<all,x2,ot2>\DeclareUnicodeCharacter{0475}{\cyrizh}
%    \end{macrocode}
%    While the double grave accent seems to exist in X2, T2A, T2B and T2C
%    encoding, the letter izhitsa exists only in X2 and OT2. Therefore,
%    izhitsa with double grave seems to be possible only using X2.
%    \begin{macrocode}
%<all,x2>\DeclareUnicodeCharacter{0476}{\C\CYRIZH}
%<all,x2>\DeclareUnicodeCharacter{0477}{\C\cyrizh}
%    \end{macrocode}
%
%    \begin{macrocode}
%<all,t2c>\DeclareUnicodeCharacter{048C}{\CYRSEMISFTSN}
%<all,t2c>\DeclareUnicodeCharacter{048D}{\cyrsemisftsn}
%<all,t2c>\DeclareUnicodeCharacter{048E}{\CYRRTICK}
%<all,t2c>\DeclareUnicodeCharacter{048F}{\cyrrtick}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0490}{\CYRGUP}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0491}{\cyrgup}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0492}{\CYRGHCRS}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0493}{\cyrghcrs}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{0494}{\CYRGHK}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{0495}{\cyrghk}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0496}{\CYRZHDSC}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0497}{\cyrzhdsc}
%<all,x2,t2a>\DeclareUnicodeCharacter{0498}{\CYRZDSC}
%<all,x2,t2a>\DeclareUnicodeCharacter{0499}{\cyrzdsc}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{049A}{\CYRKDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{049B}{\cyrkdsc}
%<all,x2,t2a>\DeclareUnicodeCharacter{049C}{\CYRKVCRS}
%<all,x2,t2a>\DeclareUnicodeCharacter{049D}{\cyrkvcrs}
%<all,x2,t2c>\DeclareUnicodeCharacter{049E}{\CYRKHCRS}
%<all,x2,t2c>\DeclareUnicodeCharacter{049F}{\cyrkhcrs}
%<all,x2,t2a>\DeclareUnicodeCharacter{04A0}{\CYRKBEAK}
%<all,x2,t2a>\DeclareUnicodeCharacter{04A1}{\cyrkbeak}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04A2}{\CYRNDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04A3}{\cyrndsc}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04A4}{\CYRNG}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04A5}{\cyrng}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A6}{\CYRPHK}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A7}{\cyrphk}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A8}{\CYRABHHA}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A9}{\cyrabhha}
%<all,x2,t2a>\DeclareUnicodeCharacter{04AA}{\CYRSDSC}
%<all,x2,t2a>\DeclareUnicodeCharacter{04AB}{\cyrsdsc}
%<all,x2,t2c>\DeclareUnicodeCharacter{04AC}{\CYRTDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04AD}{\cyrtdsc}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04AE}{\CYRY}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04AF}{\cyry}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B0}{\CYRYHCRS}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B1}{\cyryhcrs}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B2}{\CYRHDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B3}{\cyrhdsc}
%<all,x2,t2c>\DeclareUnicodeCharacter{04B4}{\CYRTETSE}
%<all,x2,t2c>\DeclareUnicodeCharacter{04B5}{\cyrtetse}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B6}{\CYRCHRDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B7}{\cyrchrdsc}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B8}{\CYRCHVCRS}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B9}{\cyrchvcrs}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04BA}{\CYRSHHA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04BB}{\cyrshha}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BC}{\CYRABHCH}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BD}{\cyrabhch}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BE}{\CYRABHCHDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BF}{\cyrabhchdsc}
%    \end{macrocode}
%    The character |\CYRpalochka| is not defined by OT2 and LCY. However it is
%    looking identical to |\CYRII| and the Unicode standard explicitly refers
%    to that (and to Latin I). So perhaps those encodings could get an alias?
%    On the other hand, why are there two distinct slots in the T2 encodings
%    even though they are so pressed for space? Perhaps they don't always look
%    alike.
%    \begin{macrocode}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04C0}{\CYRpalochka}
%    \end{macrocode}
%
%    \begin{macrocode}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04C1}{\U\CYRZH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04C2}{\U\cyrzh}
%<all,x2,t2b>\DeclareUnicodeCharacter{04C3}{\CYRKHK}
%<all,x2,t2b>\DeclareUnicodeCharacter{04C4}{\cyrkhk}
%    \end{macrocode}
%    According to the Unicode standard Ux04C5 should be an L with ``tail'' not
%    with descender (which also exists as Ux04A2) but it looks as if the char
%    names do not make this distinction). Should they?
%    \begin{macrocode}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C5}{\CYRLDSC}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C6}{\cyrldsc}
%    \end{macrocode}
%
%    \begin{macrocode}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C7}{\CYRNHK}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C8}{\cyrnhk}
%<all,x2,t2b>\DeclareUnicodeCharacter{04CB}{\CYRCHLDSC}
%<all,x2,t2b>\DeclareUnicodeCharacter{04CC}{\cyrchldsc}
%    \end{macrocode}
%    According to the Unicode standard Ux04CD should be an M with ``tail'' not
%    with descender. However this time there is no M with descender in the
%    Unicode standard.
%    \begin{macrocode}
%<all,x2,t2c>\DeclareUnicodeCharacter{04CD}{\CYRMDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04CE}{\cyrmdsc}
%    \end{macrocode}
%
%    \begin{macrocode}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D0}{\U\CYRA}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D1}{\U\cyra}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D2}{\"\CYRA}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D3}{\"\cyra}
%<all,x2,t2a>\DeclareUnicodeCharacter{04D4}{\CYRAE}
%<all,x2,t2a>\DeclareUnicodeCharacter{04D5}{\cyrae}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D6}{\U\CYRE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D7}{\U\cyre}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04D8}{\CYRSCHWA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04D9}{\cyrschwa}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04DA}{\"\CYRSCHWA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04DB}{\"\cyrschwa}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DC}{\"\CYRZH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DD}{\"\cyrzh}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DE}{\"\CYRZ}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DF}{\"\cyrz}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04E0}{\CYRABHDZE}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04E1}{\cyrabhdze}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E2}{\=\CYRI}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E3}{\=\cyri}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E4}{\"\CYRI}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E5}{\"\cyri}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E6}{\"\CYRO}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E7}{\"\cyro}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04E8}{\CYROTLD}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04E9}{\cyrotld}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EC}{\"\CYREREV}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04ED}{\"\cyrerev}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EE}{\=\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EF}{\=\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F0}{\"\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F1}{\"\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F2}{\H\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F3}{\H\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F4}{\"\CYRCH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F5}{\"\cyrch}
%<all,x2,t2b>\DeclareUnicodeCharacter{04F6}{\CYRGDSC}
%<all,x2,t2b>\DeclareUnicodeCharacter{04F7}{\cyrgdsc}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F8}{\"\CYRERY}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F9}{\"\cyrery}
%<all,t2b>\DeclareUnicodeCharacter{04FA}{\CYRGDSCHCRS}
%<all,t2b>\DeclareUnicodeCharacter{04FB}{\cyrgdschcrs}
%<all,x2,t2b>\DeclareUnicodeCharacter{04FC}{\CYRHHK}
%<all,x2,t2b>\DeclareUnicodeCharacter{04FD}{\cyrhhk}
%<all,t2b>\DeclareUnicodeCharacter{04FE}{\CYRHHCRS}
%<all,t2b>\DeclareUnicodeCharacter{04FF}{\cyrhhcrs}
%<all,ts1>\DeclareUnicodeCharacter{0E3F}{\textbaht}
%<all,x2,t2c,t2b,t2a,t1,utf8>\DeclareUnicodeCharacter{200C}{\textcompwordmark}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{2013}{\textendash}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{2014}{\textemdash}
%<all,ts1>\DeclareUnicodeCharacter{2016}{\textbardbl}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,lcy>\DeclareUnicodeCharacter{2018}{\textquoteleft}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,lcy>\DeclareUnicodeCharacter{2019}{\textquoteright}
%<all,t1>\DeclareUnicodeCharacter{201A}{\quotesinglbase}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{201C}{\textquotedblleft}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{201D}{\textquotedblright}
%<all,x2,t2c,t2b,t2a,t1,lcy>\DeclareUnicodeCharacter{201E}{\quotedblbase}
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2020}{\textdagger}
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2021}{\textdaggerdbl}
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2022}{\textbullet}
%<all,ly1,utf8>\DeclareUnicodeCharacter{2026}{\textellipsis}
%<all,x2,ts1,t2c,t2b,t2a,t1,ly1>\DeclareUnicodeCharacter{2030}{\textperthousand}
%<all,x2,ts1,t2c,t2b,t2a,t1>\DeclareUnicodeCharacter{2031}{\textpertenthousand}
%<all,t1,ly1>\DeclareUnicodeCharacter{2039}{\guilsinglleft}
%<all,t1,ly1>\DeclareUnicodeCharacter{203A}{\guilsinglright}
%<all,ts1>\DeclareUnicodeCharacter{203B}{\textreferencemark}
%<all,ts1>\DeclareUnicodeCharacter{203D}{\textinterrobang}
%<all,ts1>\DeclareUnicodeCharacter{2044}{\textfractionsolidus}
%<all,ts1>\DeclareUnicodeCharacter{204E}{\textasteriskcentered} % LOW ASTERISK
%<all,ts1>\DeclareUnicodeCharacter{2052}{\textdiscount}
%<all,ts1>\DeclareUnicodeCharacter{20A1}{\textcolonmonetary}
%<all,ts1>\DeclareUnicodeCharacter{20A4}{\textlira}
%<all,ts1>\DeclareUnicodeCharacter{20A6}{\textnaira}
%<all,ts1>\DeclareUnicodeCharacter{20A9}{\textwon}
%<all,ts1>\DeclareUnicodeCharacter{20AB}{\textdong}
%<all,ts1>\DeclareUnicodeCharacter{20AC}{\texteuro}
%<all,ts1>\DeclareUnicodeCharacter{20B1}{\textpeso}
%<all,ts1>\DeclareUnicodeCharacter{2103}{\textcelsius}
%<all,x2,ts1,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{2116}{\textnumero}
%<all,ts1>\DeclareUnicodeCharacter{2117}{\textcircledP}
%<all,ts1>\DeclareUnicodeCharacter{211E}{\textrecipe}
%<all,ts1>\DeclareUnicodeCharacter{2120}{\textservicemark}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{2122}{\texttrademark}
%<all,ts1>\DeclareUnicodeCharacter{2126}{\textohm}
%<all,ts1>\DeclareUnicodeCharacter{2127}{\textmho}
%<all,ts1>\DeclareUnicodeCharacter{212E}{\textestimated}
%<all,ts1>\DeclareUnicodeCharacter{2190}{\textleftarrow}
%<all,ts1>\DeclareUnicodeCharacter{2191}{\textuparrow}
%<all,ts1>\DeclareUnicodeCharacter{2192}{\textrightarrow}
%<all,ts1>\DeclareUnicodeCharacter{2193}{\textdownarrow}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{2329}{\textlangle}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{232A}{\textrangle}
%<all,ts1>\DeclareUnicodeCharacter{2422}{\textblank}
%<all,x2,t2c,t2b,t2a,t1,utf8>\DeclareUnicodeCharacter{2423}{\textvisiblespace}
%<all,ts1>\DeclareUnicodeCharacter{25E6}{\textopenbullet}
%<all,ts1>\DeclareUnicodeCharacter{25EF}{\textbigcircle}
%<all,ts1>\DeclareUnicodeCharacter{266A}{\textmusicalnote}
%    \end{macrocode}
%
% \subsection{Notes}
%
% \changes{v1.1e}{2004/05/22}{Added notes on inconsistency with `8-bit files'.}
% The following inputs are inconsistent with the 8-bit inputenc files
% since they will always only produce the `text character'.  This is an
% area where inputenc is notoriously confused.
% \begin{verbatim}
% %<all,ts1,t1,ot1,ly1>\DeclareUnicodeCharacter{00A3}{\textsterling}
% %<all,x2,ts1,t2c,t2b,t2a,oms,ly1>\DeclareUnicodeCharacter{00A7}{\textsection}
% %<all,ts1,utf8>\DeclareUnicodeCharacter{00A9}{\textcopyright}
% %<all,ts1>\DeclareUnicodeCharacter{00B1}{\textpm}
% %<all,ts1,oms,ly1>\DeclareUnicodeCharacter{00B6}{\textparagraph}
% %<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2020}{\textdagger}
% %<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2021}{\textdaggerdbl}
% %<all,ly1,utf8>\DeclareUnicodeCharacter{2026}{\textellipsis}
% \end{verbatim}
%
%    The following definitions are in an encoding file but have no
%    direct equivalent in Unicode, or they simply do not make sense in that
%    context (or we have not yet found anything or \ldots :-).  For
%    example, the non-combining accent charcaters are certainly
%    available somehwere but these are not equivalent to a \TeX{}
%    accent command.
%\begin{verbatim}
%\DeclareTextSymbol{\j}{OT1}{17}
%\DeclareTextSymbol{\SS}{T1}{223}
%\DeclareTextSymbol{\textcompwordmark}{T1}{23}
%
%\DeclareTextAccent{\"}{OT1}{127}
%\DeclareTextAccent{\'}{OT1}{19}
%\DeclareTextAccent{\.}{OT1}{95}
%\DeclareTextAccent{\=}{OT1}{22}
%\DeclareTextAccent{\H}{OT1}{125}
%\DeclareTextAccent{\^}{OT1}{94}
%\DeclareTextAccent{\`}{OT1}{18}
%\DeclareTextAccent{\r}{OT1}{23}
%\DeclareTextAccent{\u}{OT1}{21}
%\DeclareTextAccent{\v}{OT1}{20}
%\DeclareTextAccent{\~}{OT1}{126}
%\DeclareTextCommand{\b}{OT1}[1]
%\DeclareTextCommand{\c}{OT1}[1]
%\DeclareTextCommand{\d}{OT1}[1]
%\DeclareTextCommand{\k}{T1}[1]
%\end{verbatim}
%
%
%
% \subsection{Mappings for OT1 glyphs}
%
%    This is even more incomplete as again it covers only the single
%    glyphs from |OT1| plus some that have been explicitly defined for
%    this encoding. Everything that is provided in |T1|, and that
%    could be provided as composite glyphs via |OT1|, could and
%    probably should be set up as well.  Which leaves the many things
%    that are not provided in |T1| but can be provided in |OT1| (and
%    in |T1|) by composite glyphs.

%    \begin{macrocode}
%    \end{macrocode}
% Stuff not mapped (note that |\j| ($\jmath$) is not equivalent to any
% Unicode character):
%\begin{verbatim}
%\DeclareTextSymbol{\j}{OT1}{17}
%\DeclareTextAccent{\"}{OT1}{127}
%\DeclareTextAccent{\'}{OT1}{19}
%\DeclareTextAccent{\.}{OT1}{95}
%\DeclareTextAccent{\=}{OT1}{22}
%\DeclareTextAccent{\^}{OT1}{94}
%\DeclareTextAccent{\`}{OT1}{18}
%\DeclareTextAccent{\~}{OT1}{126}
%\DeclareTextAccent{\H}{OT1}{125}
%\DeclareTextAccent{\u}{OT1}{21}
%\DeclareTextAccent{\v}{OT1}{20}
%\DeclareTextAccent{\r}{OT1}{23}
%\DeclareTextCommand{\b}{OT1}[1]
%\DeclareTextCommand{\c}{OT1}[1]
%\DeclareTextCommand{\d}{OT1}[1]
%\end{verbatim}
%
%
%
% \subsection{Mappings for OMS glyphs}
%
% Characters like |\textbackslash| are not mapped as they are
%    (primarily) only in the lower 127 and the code here only sets up
%    mappings for UTF-8 characters that are at least 2 octets long.
%\begin{verbatim}
%\DeclareTextSymbol{\textbackslash}{OMS}{110}        % "6E
%\DeclareTextSymbol{\textbar}{OMS}{106}              % "6A
%\DeclareTextSymbol{\textbraceleft}{OMS}{102}        % "66
%\DeclareTextSymbol{\textbraceright}{OMS}{103}       % "67
%\end{verbatim}
%
% But the following (and some others) might actually lurk in Unicode
%    somewhere\ldots
%\begin{verbatim}
%\DeclareTextSymbol{\textasteriskcentered}{OMS}{3}   % "03
%\DeclareTextCommand{\textcircled}{OMS}
%\end{verbatim}
%
%
%
%
% \subsection{Mappings for TS1 glyphs}
%
% Exercise for somebody else.
%
%
% \subsection{Mappings for \texttt{latex.ltx} glyphs}
%
% There is also a collection of characters already set up in the kernel,
% one way or the other. Since these do not clearly relate to any
%    particular font encoding they are mapped when the
% \texttt{utf8} support is first set up.
%
% Also there are a number of |\providecommand|s in the various input
% encoding files which may or may not go into this part.
% \changes{v1.1b}{2004/02/09}{Added commands already defined in the kernel}
%    \begin{macrocode}
%<*utf8>
% This space is intentionally empty ...
%</utf8>
%    \end{macrocode}
%
%
% \section{A test document}
%
%    Here is a very small test document which may or may not survive
%    if the current document is transfered from one place to the
%    other.
%    \begin{macrocode}
%<*test>
\documentclass{article}

\usepackage[latin1,utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{trace}

\scrollmode  % to run past the error below

\begin{document}

 German umlauts in UTF-8: ^^c3^^a4^^c3^^b6^^c3^^bc  %%% äöü

\inputencoding{latin1}  % switch to latin1

 German umlauts in UTF-8 but read by latin1 (and will produce one
 error since \verb=\textcurrency= is not provided): ^^c3^^a4^^c3^^b6^^c3^^bc

\inputencoding{utf8}    % switch back to utf8

 German umlauts in UTF-8: ^^c3^^a4^^c3^^b6^^c3^^bc


Some codes that should produce errors as nothing is set up
for them: ^^c3F ^^e1^^a4^^b6

And some that are not legal utf8 sequences: ^^c3X ^^e1XY

\showoutput
\tracingstats=2
\stop
%</test>
%    \end{macrocode}
%
% \Finale
%
\endinput