Input- to font-encoding character translation in unixTeX


 This file contains patches to TeX's source files so that, after
 recompiling, TeX reads the environment variable TEXCHARTRANSLATE
 and, according to its value, it sets the appropriate translation
 table. The translation tables affect the translation between
 external character encoding (`inputencoding') and internal TeX's
 symbol encoding (`fontencoding').

 Currently, two translation tables exist:
      ISO 8859-1 <--> T1 (Cork)  when TEXCHARTRANSLATE=="IL1.T1",
 and  ISO 8859-2 <--> T1 (Cork)  when TEXCHARTRANSLATE=="IL2.T1".
 If the environment variable is not set or has value "<x>.<x>"
 (<x> is a string not containing a dot) the mapping is identical
 (trivial translation).
 Otherwise (for all other settings), the mapping makes all characters
 below ' ' and above '~' undefined (i.e. restricts to OT1 font encoding).

 This scheme is extensible -- please make suggestions for adding new
 tables.

 To apply these patches successfully you must
  * place it in the directory where TeX's source is located
    (usually .../src/web2c-6.1/web2c/tex/) under the name
    chartranslate.patch
  * cd there
  * type      ` patch <chartranslate.patch '
    this applies the patches to four files: tex.ch,
    ../lib/texmf.defines, ../lib/texmf.h, and ../lib/texmf.c
  * then recompile TeX (type `make' on the shell prompt)
  * dump the new version of format file(s) you use:
    ./initex ../../.../latex2e
    and answer `\dump' on the `*' prompt
    (make sure you dump the format file still with the variable
    TEXCHARTRANSLATE unset)
  After this is done, TeX will understand the environment variable
  TEXCHARTRANSLATE as described above.

 Notes:
 This patch (version 0.2 dated 23-Jan-95) was tested with
 current (6.1) web2c distribution under Solaris 2.3,
 but we don't see any reason why it wouldn't work with the previous ones.
 The patched TeX passes the trip-trap test.

 Latest version of this patch can be found on URL
 ftp://ftp.fi.muni.cz/pub/tex/local/unixtexpatch/

 Content of the patches:
 file: tex.ch                change to section [2.23] is extended,
                             change to section [4.49] is added
       ../lib/texmf.defines  declaration of function extenc
       ../lib/texmf.h        constant NONASCII defined
       ../lib/texmf.c        function extenc
 The patches were generated by
 diff -b -c xxx yyy >>chartranslate.patch
 command.

 Enjoy!
 Libor Skarvada <libor@informatics.muni.cz>
 Petr Sojka <sojka@informatics.muni.cz>


--- tex.ch
***************
*** 275,287 ****
  
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  % [2.23] Allow any character as input.
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  @x
  for i:=0 to @'37 do xchr[i]:=' ';
  for i:=@'177 to @'377 do xchr[i]:=' ';
  @y
! for i:=0 to @'37 do xchr[i]:=chr(i);
! for i:=@'177 to @'377 do xchr[i]:=chr(i);
  @z
  
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
--- 275,347 ----
  
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  % [2.23] Allow any character as input.
+ % enable  T1 (Cork)  <->  ISO 8859-[12]  transcription { on request (if
+ % TEXCHARTRANSLATE environment variable is set to "IL1.T1", "IL2.T1") }
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
  @x
+ To get the most ``permissive'' character set, change |' '| on the
+ right of these assignment statements to |chr(i)|.
+ @y
+ To get the most ``permissive'' character set, change |' '| on the
+ right of these assignment statements to |chr(i)|.
+ 
+ If we, however, want \TeX\ would ``understand'' more than one character
+ set on input, the content of |xchr| and |xord| arrays will depend on
+ the encoding.
+ We define function |ext_enc| (written in C) which reads the environment
+ variable TEXCHARTRANSLATE whose value is the pair of character encodings
+ (external, internal) being in use. Then the apprpriate ``translation
+ tables'' |xchr|, |xord| are chosen.
+ 
+ So far only translations ISO~8859-1$\leftrightarrow$T1 and
+ iso~8859-2$\leftrightarrow$T1 are supported (when |ext_enc| returns
+ the value 1 or 2 respectively).
+ 
+ The following macro saves some typing.
+ |xc(i)(j)|  stands for  |xchr[i]:=chr(j)|.
+ @d xc(#)==xchr[#]:=cccc
+ @d cccc(#)==chr(#)
+ @z
+ %
+ @x
  for i:=0 to @'37 do xchr[i]:=' ';
  for i:=@'177 to @'377 do xchr[i]:=' ';
  @y
! for i:=0 to 31 do xc(i)(i);
! for i:=127 to 191 do xc(i)(32);
! case ext_enc of
!       0: { do 1-1 identity mapping }
!          for i:=127 to 255 do xc(i)(i);
!       1: { external encoding is ISO~8859-1, internal encoding is T1 }
!        begin
!          for i:=192 to 255 do xc(i)(i);
!          xc(158)(240); xc(159)(167); xc(184)(255); xc(189)(161); xc(190)(191);
!          xc(191)(163); xc(215)(32);  xc(223)(32);  xc(240)(32);  xc(247)(32);
!          xc(255)(223)
!        end;
!       2: { external encoding is ISO~8859-2, internal encoding is T1 }
!        begin
!          for i:=192 to 255 do xc(i)(32);
!          xc(128)(195); xc(129)(161); xc(130)(198); xc(131)(200); xc(132)(207);
!          xc(133)(204); xc(134)(202); xc(136)(197); xc(137)(165); xc(138)(163);
!          xc(139)(209); xc(140)(210); xc(142)(213); xc(143)(192); xc(144)(216);
!          xc(145)(166); xc(146)(169); xc(147)(170); xc(148)(171); xc(149)(222);
!          xc(150)(219); xc(151)(217); xc(153)(172); xc(154)(174); xc(155)(175);
!          xc(158)(240); xc(159)(167); xc(160)(227); xc(161)(177); xc(162)(230);
!          xc(163)(232); xc(164)(239); xc(165)(236); xc(166)(234); xc(168)(229);
!          xc(169)(181); xc(170)(179); xc(171)(241); xc(172)(242); xc(174)(245);
!          xc(175)(224); xc(176)(248); xc(177)(182); xc(178)(185); xc(179)(186);
!          xc(180)(187); xc(181)(254); xc(182)(251); xc(183)(249); xc(185)(188);
!          xc(186)(190); xc(187)(191); xc(193)(193); xc(194)(194); xc(196)(196);
!          xc(199)(199); xc(201)(201); xc(203)(203); xc(205)(205); xc(206)(206);
!          xc(208)(208); xc(211)(211); xc(212)(212); xc(214)(214); xc(218)(218);
!          xc(220)(220); xc(221)(221); xc(223)(223); xc(225)(225); xc(226)(226);
!          xc(228)(228); xc(231)(231); xc(233)(233); xc(235)(235); xc(237)(237);
!          xc(238)(238); xc(243)(243); xc(244)(244); xc(246)(246); xc(250)(250);
!          xc(252)(252); xc(253)(253); xc(255)(223)
!        end
!      { else do nothing --- external encoding is 7-bit ASCII }
! endcases;@/
  @z
  
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
***************
*** 547,552 ****
--- 607,621 ----
      end;
  exit:
  end;
+ @z
+ 
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ % [4.49] Make characters 128--255 printable
+ %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+ @x
+   (k<" ")or(k>"~")
+ @y
+   (k<" ")or(k=invalid_code)  {or(k>=128)and(k<160)}
  @z
  
  %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
--- ../lib/texmf.defines
***************
*** 29,34 ****
--- 29,35 ----
  @define function inputln ();
  @define function wopenin ();
  @define function wopenout ();
+ @define function extenc;
  
  @define procedure bclose ();
  @define procedure blankrectangle ();
--- ../lib/texmf.h
***************
*** 10,15 ****
--- 10,17 ----
  #define NO_DEBUG
  #endif
  
+ #define NONASCII 1
+ 
  #include "cpascal.h"
  
  #ifdef TeX
--- ../lib/texmf.c
***************
*** 799,801 ****
--- 799,821 ----
  #endif /* TRAP */
  }
  #endif /* MF */
+ 
+ 
+ /* This reads the environment to find out which pair of
+    external-internal character encodings is used  */
+ 
+ integer
+ extenc ()
+ {
+ char *tt;
+ tt = getenv("TEXCHARTRANSLATE");
+ if (tt == NULL) return 0;
+ if (strcasecmp(tt,"IL1.T1")==0) return 1;
+ if (strcasecmp(tt,"IL2.T1")==0) return 2;
+ if (strchr(tt,'.')!=NULL)
+    { int le;
+      le = strcspn(tt,".");
+      if (strncmp(tt,tt+le+1,le)==0) return 0;
+    }
+ return -1;
+ }