diff -acprNC5 recode-3.5.orig/contrib/config.site recode-3.5.djgpp/contrib/config.site *** recode-3.5.orig/contrib/config.site Thu Jan 1 00:00:00 1970 --- recode-3.5.djgpp/contrib/config.site Sat Sep 30 23:52:32 2000 *************** *** 0 **** --- 1,35 ---- + #! /bin/sh + + # This is the config.site file for configuring GNU packages + # which are to be built with DJGPP tools. + + # These two variables are required, otherwise looking for + # programs along the PATH will not work. + PATH_SEPARATOR=: + PATH_EXPAND=y + + # This is required in for "test -f foo" to find foo.exe + export TEST_FINDS_EXE=y + + # The root of the DJGPP tree serves as the default prefix + test "x$prefix" = xNONE && prefix='/dev/env/DJDIR' + + # This is required for config.status script to be run, since + # ./configure runs it by invoking ${CONFIG_SHELL-/bin/sh} + CONFIG_SHELL=${CONFIG_SHELL='sh'} + + # These are set here so the generated Makefile's will be good + # for every DJGPP installation, not only the one where the + # package was configured. + # $INSTALL must be an absolute path name, otherwise config.status + # will try to prepend ./ and ../ to it when it goes into subdirs. + INSTALL=${INSTALL='/dev/env/DJDIR/bin/ginstall -c'} + RANLIB=${RANLIB='ranlib'} + NM=${NM='nm'} + LD=${LD='ld'} + GMSGFMT=${GMSGFMT='/dev/env/DJDIR/bin/msgfmt'} + MSGFMT=${MSGFMT='/dev/env/DJDIR/bin/msgfmt'} + XGETTEXT=${XGETTEXT='/dev/env/DJDIR/bin/xgettext'} + + # Force the test for 'ln -s' to report 'cp -pf'. + ac_cv_prog_LN_S='cp -pf' diff -acprNC5 recode-3.5.orig/contrib/configdj.bat recode-3.5.djgpp/contrib/configdj.bat *** recode-3.5.orig/contrib/configdj.bat Thu Jan 1 00:00:00 1970 --- recode-3.5.djgpp/contrib/configdj.bat Mon Jun 18 00:33:40 2001 *************** *** 0 **** --- 1,174 ---- + @echo off + echo Configuring Free Recode for DJGPP v2.x... + + Rem The SmallEnv tests protect against fixed and too small size + Rem of the environment in stock DOS shell. + + Rem Find out if NLS is wanted or not + Rem and where the sources are. + Rem We always default to NLS support + Rem and to in place configuration. + set NLS=enabled + if not "%NLS%" == "enabled" goto SmallEnv + set XSRC=. + if not "%XSRC%" == "." goto SmallEnv + + Rem This checks the case: + Rem %1 contains the NLS option. + Rem %2 contains the src path option. + if "%1" == "" goto InPlace + if "%1" == "NLS" goto SrcDir2 + if not "%1" == "no-NLS" goto SrcDir1 + set NLS=disabled + if not "%NLS%" == "disabled" goto SmallEnv + :SrcDir2 + Rem Find out where the sources are + if "%2" == "" goto InPlace + set XSRC=%2 + if not "%XSRC%" == "%2" goto SmallEnv + goto NotInPlace + + Rem This checks the case: + Rem %1 contains the src path option. + Rem %2 contains the NLS option. + :SrcDir1 + Rem Find out where the sources are + if "%1" == "" goto InPlace + set XSRC=%1 + if not "%XSRC%" == "%1" goto SmallEnv + if "%2" == "" goto NotInPlace + if "%2" == "NLS" goto NotInPlace + if not "%2" == "no-NLS" goto NotInPlace + set NLS=disabled + if not "%NLS%" == "disabled" goto SmallEnv + + :NotInPlace + redir -e /dev/null update %XSRC%/configure.orig ./configure + test -f ./configure + if errorlevel 1 update %XSRC%/configure ./configure + + :InPlace + Rem Update configuration files + echo Updating configuration scripts... + test -f ./configure.orig + if errorlevel 1 update configure configure.orig + sed -f %XSRC%/contrib/configdj.sed configure.orig > configure + if errorlevel 1 goto SedError + + Rem Make sure they have a config.site file + set CONFIG_SITE=%XSRC%/contrib/config.site + if not "%CONFIG_SITE%" == "%XSRC%/contrib/config.site" goto SmallEnv + + Rem Make sure crucial file names are not munged by unpacking + test -f %XSRC%/config.h.in + if not errorlevel 1 mv -f %XSRC%/config.h.in %XSRC%/config.h-in + test -f %XSRC%/intl/po2tbl.sed.in + if not errorlevel 1 mv -f %XSRC%/intl/po2tbl.sed.in %XSRC%/intl/po2tblsed.in + test -f %XSRC%/intl/po2tbl.sed + if not errorlevel 1 mv -f %XSRC%/intl/po2tbl.sed %XSRC%/intl/po2tblsed.in + test -f %XSRC%/intl/po2tbl-sed.in + if not errorlevel 1 mv -f %XSRC%/intl/po2tbl-sed.in %XSRC%/intl/po2tblsed.in + test -f %XSRC%/po/Makefile.in.in + if not errorlevel 1 mv -f %XSRC%/po/Makefile.in.in %XSRC%/po/Makefile.in-in + test -f %XSRC%/po/Makefile.am.in + if not errorlevel 1 mv -f %XSRC%/po/Makefile.am.in %XSRC%/po/Makefile.am-in + + Rem Let libtool use _libs all the time. + test -f %XSRC%/ltconfig.orig + if errorlevel 1 update %XSRC%/ltconfig %XSRC%/ltconfig.orig + sed "/objdir=/s|\.libs|_libs|" %XSRC%/ltconfig.orig > ltconfig.tmp + if errorlevel 1 goto SedError + mv -f ltconfig.tmp %XSRC%/ltconfig + + Rem This is required because DOS/Windows are case-insensitive + Rem to file names, and "make install" will do nothing if Make + Rem finds a file called `install'. + if exist INSTALL ren INSTALL INSTALL.txt + + Rem Set HOSTNAME so it shows in config.status + if not "%HOSTNAME%" == "" goto hostdone + if "%windir%" == "" goto msdos + set OS=MS-Windows + if not "%OS%" == "MS-Windows" goto SmallEnv + goto haveos + :msdos + set OS=MS-DOS + if not "%OS%" == "MS-DOS" goto SmallEnv + :haveos + if not "%USERNAME%" == "" goto haveuname + if not "%USER%" == "" goto haveuser + echo No USERNAME and no USER found in the environment, using default values + set HOSTNAME=Unknown PC + if not "%HOSTNAME%" == "Unknown PC" goto SmallEnv + goto userdone + :haveuser + set HOSTNAME=%USER%'s PC + if not "%HOSTNAME%" == "%USER%'s PC" goto SmallEnv + goto userdone + :haveuname + set HOSTNAME=%USERNAME%'s PC + if not "%HOSTNAME%" == "%USERNAME%'s PC" goto SmallEnv + :userdone + set _HOSTNAME=%HOSTNAME%, %OS% + if not "%_HOSTNAME%" == "%HOSTNAME%, %OS%" goto SmallEnv + set HOSTNAME=%_HOSTNAME% + :hostdone + set _HOSTNAME= + set OS= + + Rem install-sh is required by the configure script but clashes with the + Rem various Makefile install-foo targets, so we MUST have it before the + Rem script runs and rename it afterwards + test -f %XSRC%/install-sh + if not errorlevel 1 goto NoRen0 + test -f %XSRC%/install-sh.sh + if not errorlevel 1 mv -f %XSRC%/install-sh.sh %XSRC%/install-sh + :NoRen0 + + if "%NLS%" == "disabled" goto WithoutNLS + + :WithNLS + Rem Recreate the files in the %XSRC%/po subdir with our ported tools. + redir -e /dev/null rm %XSRC%/po/*.gmo + redir -e /dev/null rm %XSRC%/po/stamp-* + redir -e /dev/null rm %XSRC%/po/recode.pot + redir -e /dev/null rm %XSRC%/po/cat-id-tbl.c + redir -e /dev/null rm %XSRC%/po/stamp-cat-id + + Rem We prefer without-included-gettext because libintl.a from gettext package + Rem is the only one that is garanteed to have been ported to DJGPP. + echo Running the ./configure script... + sh ./configure --src=%XSRC% --enable-nls --without-included-gettext + if errorlevel 1 goto CfgError + echo Done. + goto End + + :WithoutNLS + echo Running the ./configure script... + sh ./configure --src=%XSRC% --disable-nls + if errorlevel 1 goto CfgError + echo Done. + goto End + + :SedError + echo ./configure script editing failed! + goto End + + :CfgError + echo ./configure script exited abnormally! + goto End + + :SmallEnv + echo Your environment size is too small. Enlarge it and run me again. + echo Configuration NOT done! + + :End + test -f %XSRC%/install-sh.sh + if not errorlevel 1 goto NoRen1 + test -f %XSRC%/install-sh + if not errorlevel 1 mv -f %XSRC%/install-sh %XSRC%/install-sh.sh + :NoRen1 + set CONFIG_SITE= + set HOSTNAME= + set NLS= + set XSRC= diff -acprNC5 recode-3.5.orig/contrib/configdj.sed recode-3.5.djgpp/contrib/configdj.sed *** recode-3.5.orig/contrib/configdj.sed Thu Jan 1 00:00:00 1970 --- recode-3.5.djgpp/contrib/configdj.sed Sun Apr 8 19:47:40 2001 *************** *** 0 **** --- 1,98 ---- + # po2tbl.sed.in is invalid on MSDOS + s|po2tbl\.sed\.in|po2tblsed.in|g + + # Additional editing of Makefiles and atconfig + /ac_given_INSTALL=/,/^CEOF/ { + /^CEOF$/ i\ + # DJGPP specific Makefile changes.\ + /^aliaspath * *=/s,:,";",g\ + /TEXINPUTS=/s,:,";",g\ + /PATH=/s,:,";",g\ + s,\\.old\\.,_old.,g\ + s,po2tbl\\.sed\\.in,po2tblsed.in,g\ + s,config\\.h\\.in,config.h-in,g\ + s,Makefile\\.in\\.in,Makefile.in-in,g\ + s,Makefile\\.am\\.in,Makefile.am-in,g\ + /^install-info-am:/,/^$/ {\ + /@list=/ s,\\\$(INFO_DEPS),& recode.i,\ + /@for *file/ s,\\\$(INFO_DEPS),& recode.i,\ + s,file-\\[0-9\\]\\[0-9\\],& \\$\\$file[0-9] \\$\\$file[0-9][0-9],\ + } + } + + # Makefile.in.in is renamed to Makefile.in-in... + /^CONFIG_FILES=/,/^EOF/ { + s|po/Makefile\.in|&:po/Makefile.in-in| + } + + # ...and config.h.in into config.h-in + /^ *CONFIG_HEADERS=/,/^EOF/ { + s|config\.h|&:config.h-in| + } + + # Replace (command) > /dev/null with `command > /dev/null`, since + # parenthesized commands always return zero status in the ported Bash, + # even if the named command doesn't exist + /if ([^|;]*null/{ + s,(,`, + s,),, + s,; *then,`; then, + } + + # DOS-style absolute file names should be supported as well + /\*) srcdir=/s,/\*,[\\\\/]* | [A-z]:[\\\\/]*, + /\$]\*) INSTALL=/s,\[/\$\]\*,[\\\\/$]* | [A-z]:[\\\\/]*, + /\$]\*) ac_rel_source=/s,\[/\$\]\*,[\\\\/$]* | [A-z]:[\\\\/]*, + + # Switch the order of the two Sed commands, since DOS path names + # could include a colon + /ac_file_inputs=/s,\( -e "s%\^%\$ac_given_srcdir/%"\)\( -e "s%:% $ac_given_srcdir/%g"\),\2\1, + + # Prevent the spliting of conftest.subs. + # The sed script: conftest.subs is split into 48 or 90 lines long files. + # This will produce sed scripts called conftest.s1, conftest.s2, etc. + # that will not work if conftest.subs contains a multi line sed command + # at line #90. In this case the first part of the sed command will be the + # last line of conftest.s1 and the rest of the command will be the first lines + # of conftest.s2. So both script will not work properly. + # This matches the configure script produced by Autoconf 2.12 + /ac_max_sed_cmds=[0-9]/ s,=.*$,=`sed -n "$=" conftest.subs`, + # This matches the configure script produced by Autoconf 2.14a + /ac_max_sed_lines=[0-9]/ s,=.*$,=`sed -n "$=" $ac_cs_root.subs `, + + # gettext.m4 (serial 5) from GNU gettext 0.10.35 has a bug. + # When the package is configured with --without-included-gettext option + # and the system libintl.a is found then the LIBS variable *MUST* be set to -lintl + # so that this one is used for linking. + /echo.*\$gt_cv_func_gettext_libintl/,/^EOF$/ { + /^fi$/ a\ + if test "$gt_cv_func_gettext_libintl" = yes; then\ + LIBS="$LIBS -lintl -liconv"\ + fi + } + + # We prefer gettext__ instead of gettext. + /checking for gettext in libintl/,/^EOF$/ s,gettext[ ]*(,gettext__(,g + + # The following two items are changes needed for configuring + # and compiling across partitions. + # 1) The given srcdir value is always translated from the + # "x:" syntax into "/dev/x" syntax while we run configure. + /^[ ]*-srcdir=\*.*$/ a\ + ac_optarg=`echo "$ac_optarg" | sed "s,^\\([A-Za-z]\\):,/dev/\\1,"` + /set X `ls -Lt \$srcdir/ i\ + if `echo $srcdir | grep "^/dev/" - > /dev/null`; then\ + srcdir=`echo "$srcdir" | sed -e "s%^/dev/%%" -e "s%/%:/%"`\ + fi + + # 2) We need links across partitions, so we will use "cp -pf" instead of "ln". + /# Make a symlink if possible; otherwise try a hard link./,/EOF/ { + s,;.*then, 2>/dev/null || cp -pf \$srcdir/\$ac_source \$ac_dest&, + } + + # DJGPP's port of gettext 0.10.36 makes use of libiconv.a to recode + # on the fly .gmo files from UNIX charset to MSDOS codepage. This implies + # that in all link phases, -liconv MUST be added to -lintl. + /bindtextdomain[ ]*in[ ]*-lintl/,/failed[ ]*program[ ]*was:/ s,eval[ ]*\$ac_link,& -liconv, + /gettext[ ]*in[ ]*libintl/,/failed[ ]*program[ ]*was:/ s,eval[ ]*\$ac_link,& -liconv, + # /gettext[ ]*in[ ]*-lintl/,/failed[ ]*program[ ]*was:/ s,eval[ ]*\$ac_link,& -liconv, diff -acprNC5 recode-3.5.orig/contrib/fnchange.lst recode-3.5.djgpp/contrib/fnchange.lst *** recode-3.5.orig/contrib/fnchange.lst Thu Jan 1 00:00:00 1970 --- recode-3.5.djgpp/contrib/fnchange.lst Mon Aug 28 19:14:42 2000 *************** *** 0 **** --- 1,3 ---- + recode-3.5/config.h.in recode-3.5/config.h-in + recode-3.5/intl/po2tbl.sed.in recode-3.5/intl/po2tblsed.in + recode-3.5/po/Makefile.in.in recode-3.5/po/Makefile.in-in diff -acprNC5 recode-3.5.orig/contrib/readme.djgpp recode-3.5.djgpp/contrib/readme.djgpp *** recode-3.5.orig/contrib/readme.djgpp Thu Jan 1 00:00:00 1970 --- recode-3.5.djgpp/contrib/readme.djgpp Sun Jun 17 23:53:44 2001 *************** *** 0 **** --- 1,226 ---- + This is a port of Free Recode 3.5 to MSDOS/DJGPP. + + 1.: DJGPP specific changes. + ======================= + + - Changes needed for NLS support with DJGPP. + - Extensive changes in the docs. Added indexing for all + command-line options and all supported charsets. + - Changes in the test suite to make it work on DOS/Windows with + DJGPP tools. + + Thanks to Eli Zaretskii for contributing the patch for docs and + test suite changes. + + Thanks to Daniel Taupin for contributing a patch for html.c + to fixing a bug when attempting to code undefined codes in + the form "✏". + + + All changes I have done against the original GNU distribution + are documented in the diffs file stored in the contrib subdir + of the source package. + + + 2.: Installing the binary package. + ============================== + + 2.1.: Copy the binary distribution into the top DJGPP installation directory. + If you are installing Recode on a dual DOS/WINDOWS 9X systems, you + should first turn off the generation of numeric tails for 8.3 aliases + Windows creats for long file names. For information about how to do + this, please read the DJGPP FAQ List V 2.30, chapter 22.19: "How to Set + Up a Dual DOS/Windows Installation". Please note that you **MUST** turn + off the numeric tail generation for short file names during installation + of the binary package if you want to use Recode on both DOS window on + Win9X **AND** plain DOS. If this is not done Recode will **NOT** be able + to find the .mo files (the catalog files containing the translated + strings) on plain DOS. After the installation has been finished you can + turn on numeric tail generation again if you like. + + 2.2.: Copy the binary distribution into the top DJGPP installation directory + and unzip it running *ONE* of the following commands: + unzip32 rcode35b.zip or + djtarx rcode35b.zip or + pkunzip -d rcode35b.zip + + 2.3.: Edit the djgpp.env file which is located in the top DJGPP installation + directory. Move to the global part of your djgpp.env and add the + following lines: + + +LANG=xx + +LANGUAGE=yy:zz + + The lines must be completely shifted to the left in your djgpp.env file. + Please note the plus sign at the beginning of the lines. This plus sign + allows you to overwrite the contain of the environment variable at the + command line or from inside a batch file or shell script. The plus sign + should **NOT** be omited or a lot of shell scripts, in this and in + other packages, that try to reset this value will stop working. The + LANG entry is obligatory, the LANGUAGE entry may be omited. The + LANGUAGE variable allows you to select an alternate catalog than the + one stipulated by LANG but the LANG variable *ALWAYS* determines the + the DOS codepage to be used to display the translations and can not be + omited or no tarnslations will be perfomed at all. Replace xx, yy and + zz by the language code of the catalogs you want to use. + + Some examples: + If you only want to use the catalog containig the translations for + your mother tongue (in my case the spanish translations) the above + lines will only use the LANG variable and will look like this: + + +LANG=es + + If you want to use the spanish (es) and german (de) catalogs + the above lines will look like this: + + +LANG=es + +LANGUAGE=es:de + + In this case a DJGPP binary that has been compiled with NLS support + will first search for the spanish translations. If this translations + can not be found it will search for the german translations and if + this can also not been found it will default to the build-in english + messages. If you want to reverse this search order the above lines + would look like this one: + + +LANG=es + +LANGUAGE=de:es + + Please note that if you omit the LANG environment variable, the + LANGUAGE variable will not be honuored at all. The LANG varaiable must + always be set to your default catalog. With the aid of LANGUAGE you can + select other catalogs apart of the default one. If for some reason you + want to disable NLS, then you should comment out the LANG variable or + select 'C' (uppercase `c' character) as your catalog: + +LANG=C + + Users not familiar with djgpp.env should refer to kb.info. + This document can be read running the command: + info -f kb -n DJGPP.ENV + + 2.4.: To create an entry for the recode info docs in your dir file, + run from the top DJGPP installation directory the command: + install-info --info-dir=./info ./info/recode.info + + 2.5.: The binaries distributed in this package have NLS support. + I.E. run the command: + recode + and the binary should talk to you in your mother tonge, if + supported. + For futher information about Free Recode please read the info docs. + + + 3.: Building the binaries from sources. + =================================== + + 3.1.: To build the binaries you will need the following binary packages: + djdev203.zip (NOT a prior version) + bsh203b.zip (NOT a prior version) + gcc2952b.zip, bnu2951b.zip, mak3791b.zip, + fil316b.zip, shl112b.zip, txt20b.zip, + txi40b.zip, grep24b.zip, sed302b.zip, + gtxt037b.zip, licv161b.zip + + If you want to run the check you will need also: + dif272b.zip, m4-14b.zip and perl552b.zip. + + All this packages can be found in the v2gnu directory of any + Simtel.NET mirror. + You will need bsh203b.zip and *NOT* a prior version or the build will fail. + The same applies to djdev203.zip. You *MUST* use the updated version of + fil316b.zip (date: 2000-05-30) and shl112b.zip (date: 2000-08-11). + This updated versions have been recompiled with djdev203.zip and know + about the "/dev/env" functionality introduced with djdev203.zip. All the + other packages are the ones I have used to build the binaries from this + sources. Previuos versions of this packages may do the job as well but + I have not tested this. + + 3.2.: Create a temporary directory. Copy the source package: rcode35s.zip + into the directory and unzip it runnig ONE of the following commands: + unzip32 rcode35s.zip or + djtarx rcode35s.zip or + pkunzip -d rcode35s.zip + + 3.3.: This package is preconfigured for NLS support and djdev203. This + implies that you *MUST* install the GNU gettext library (gtxt037b.zip) + *AND* the libiconv library (licv161b.zip) or later if you want to + reconfigure and recompile this package. Of course, this must be done + *BEFORE* reconfiguring and recompiling the package. The configuration + batch file of this package, located in the djgpp directory, allows you + to enable or disable NLS support and to compile from a different + partition than from where the sources are located. config.bat always + configures the package for NLS support enabled and for in place + compilation if no options are given. The available NLS options are: + NLS + no-NLS + + If for some reason you want no NLS support you will have to reconfigure + the package. For this purpose cd into the top srcdir (recode-3.5) and + run the following commands: + make distclean + contrib\configdj no-NLS + + Please note that you *MUST* use the "distclean" option or the config.cache + file will *NOT* be deleted. In this case you are *NOT* reconfiguring + because the configuration informations is read from the cache file instead + of being newly computed. + You *MUST* specify "no-NLS" or config.bat will default to the "NLS" + option. To build the programs in a directory other than where the sources + are, you must add the parameter that specifies the source directory, + e.g: + x:\src\gnu\recode-3.5\contrib\configdj x:/src/gnu/recode-3.5 no-NLS + + Lets assume you want to build the binaries in a directory placed on a + different drive (z:\build in this case) from where the sources are, + then you will run the following commands: + z: + md \build + cd \build + x:\src\gnu\recode-3.5\contrib\configdj x:/src/gnu/recode-3.5 no-NLS + + If you want NLS support you will omit the "no-NLS" option or replace it + by the "NLS" option in the above examples. + The order of the NLS option and the srcdir option does *NOT* matter. + You *MUST* use forward slashes to specify the source directory. + + The batch file will set some environment variables, make MSDOS specific + modifications to the Makefile.ins and supply all other needed options + to the configure script. If NLS support is wanted the batch file will + check if libiconv.a, libintl.a, msgfmt.exe and xgettext.exe are + installed. If one of the above items is missed the batch file will + automatically default to configure the package without NLS support. + + 3.4.: To compile the package run from the top srcdir the command: + make + + 3.5.: Now you can run the tests if you like. From the top srcdir run the + command: + make check + + Non test should fail. + + 3.6.: To install the binaries, header, library, catalogs, and info docs run + the following command from the top srcdir: + make install CATALOGS="xx.gmo yy.gmo zz.gmo" + + This will install the products into your DJGPP installation tree given + by the default prefix "/dev/env/DJDIR". If you prefer to install them + into some other directory you will have to set prefix to the appropiate + value. Replace xx, yy and zz by the language codes of the catalogs you + want to install. + Example: + make install CATALOGS="xx.gmo yy.gmo zz.gmo" prefix=z:/some/other/dir + + 3.7.: Now you have to set the LANG and LANGUAGE environment variable. + Please refer to 2.3. + + + + Send recode specific bug reports to . + Send suggestions and bug reports concerning the DJGPP port to + comp.os.msdos.djgpp or . + + Enjoy. + + Guerrero, Juan Manuel diff -acprNC5 recode-3.5.orig/doc/charset.texi recode-3.5.djgpp/doc/charset.texi *** recode-3.5.orig/doc/charset.texi Sun May 2 02:09:22 1999 --- recode-3.5.djgpp/doc/charset.texi Sun Jun 17 23:56:02 2001 *************** *** 1,616 **** --- 1,1147 ---- @item ANSI_X3.4-1968 + @tindex ANSI_X3.4-1968@r{, aliases and source} + @tindex 367 + @tindex ANSI_X3.4-1986 + @tindex ASCII + @tindex CP367 + @tindex IBM367 + @tindex ISO646-US + @tindex ISO_646.irv(1991) + @tindex US-ASCII + @tindex iso-ir-6 + @tindex us @code{367}, @code{ANSI_X3.4-1986}, @code{ASCII}, @code{CP367}, @code{IBM367}, @code{ISO646-US}, @code{ISO_646.irv:1991}, @code{US-ASCII}, @code{iso-ir-6} and @code{us} are aliases for this charset. Source: ISO 2375 registry. @item ASMO_449 + @tindex ASMO_449@r{, aliases and source} + @tindex ISO_9036 + @tindex arabic7 + @tindex iso-ir-89 @code{ISO_9036}, @code{arabic7} and @code{iso-ir-89} are aliases for this charset. Source: ISO 2375 registry. @item BS_4730 + @tindex BS_4730@r{, aliases and source} + @tindex ISO646-GB + @tindex gb + @tindex iso-ir-4 + @tindex uk @code{ISO646-GB}, @code{gb}, @code{iso-ir-4} and @code{uk} are aliases for this charset. Source: ISO 2375 registry. @item BS_viewdata + @tindex BS_viewdata@r{, aliases and source} + @tindex iso-ir-47 @code{iso-ir-47} is an alias for this charset. Source: ISO 2375 registry. @item CP1250 + @tindex CP1250@r{, aliases and source} + @tindex 1250 + @tindex ms-ee + @tindex windows-1250 @code{1250}, @code{ms-ee} and @code{windows-1250} are aliases for this charset. Source: UNICODE 1.0. @item CP1251 + @tindex CP1251@r{, aliases and source} + @tindex 1251 + @tindex ms-cyrl + @tindex windows-1251 @code{1251}, @code{ms-cyrl} and @code{windows-1251} are aliases for this charset. Source: UNICODE 1.0. @item CP1252 + @tindex CP1252@r{, aliases and source} + @tindex 1252 + @tindex ms-ansi + @tindex windows-1252 @code{1252}, @code{ms-ansi} and @code{windows-1252} are aliases for this charset. Source: UNICODE 1.0. @item CP1253 + @tindex CP1253@r{, aliases and source} + @tindex 1253 + @tindex ms-greek + @tindex windows-1253 @code{1253}, @code{ms-greek} and @code{windows-1253} are aliases for this charset. Source: UNICODE 1.0. @item CP1254 + @tindex CP1254@r{, aliases and source} + @tindex 1254 + @tindex ms-turk + @tindex windows-1254 @code{1254}, @code{ms-turk} and @code{windows-1254} are aliases for this charset. Source: UNICODE 1.0. @item CP1255 + @tindex CP1255@r{, aliases and source} + @tindex 1255 + @tindex ms-hebr + @tindex windows-1255 @code{1255}, @code{ms-hebr} and @code{windows-1255} are aliases for this charset. Source: UNICODE 1.0. @item CP1256 + @tindex CP1256@r{, aliases and source} + @tindex 1256 + @tindex ms-arab + @tindex windows-1256 @code{1256}, @code{ms-arab} and @code{windows-1256} are aliases for this charset. Source: UNICODE 1.0. @item CP1257 + @tindex CP1257@r{, aliases and source} + @tindex 1257 + @tindex WinBaltRim + @tindex windows-1257 @code{1257}, @code{WinBaltRim} and @code{windows-1257} are aliases for this charset. Source: CEN/TC304 N283. @item CSA_Z243.4-1985-1 + @tindex CSA_Z243.4-1985-1@r{, aliases and source} + @tindex ISO646-CA + @tindex ca + @tindex csa7-1 + @tindex iso-ir-121 @code{ISO646-CA}, @code{ca}, @code{csa7-1} and @code{iso-ir-121} are aliases for this charset. Source: ISO 2375 registry. @item CSA_Z243.4-1985-2 + @tindex CSA_Z243.4-1985-2@r{, aliases and source} + @tindex ISO646-CA2 + @tindex csa7-2 + @tindex iso-ir-122 @code{ISO646-CA2}, @code{csa7-2} and @code{iso-ir-122} are aliases for this charset. Source: ISO 2375 registry. @item CSA_Z243.4-1985-gr + @tindex CSA_Z243.4-1985-gr@r{, aliases and source} + @tindex iso-ir-123 @code{iso-ir-123} is an alias for this charset. Source: ISO 2375 registry. @item CSN_369103 + @tindex CSN_369103@r{, aliases and source} + @tindex KOI-8_L2 + @tindex iso-ir-139 + @tindex koi8l2 @code{KOI-8_L2}, @code{iso-ir-139} and @code{koi8l2} are aliases for this charset. Source: ISO 2375 registry. @item CWI + @tindex CWI@r{, aliases and source} + @tindex CWI-2 + @tindex cp-hu @code{CWI-2} and @code{cp-hu} are aliases for this charset. Source: Computerworld Sza'mita'stechnika vol 3 issue 13 1988-06-29. @item DEC-MCS + @tindex DEC-MCS@r{, aliases and source} + @tindex dec @code{dec} is an alias for this charset. VAX/VMS User's Manual, Order Number: AI-Y517A-TE, April 1986. @item DIN_66003 + @tindex DIN_66003@r{, aliases and source} + @tindex ISO646-DE + @tindex de + @tindex iso-ir-21 @code{ISO646-DE}, @code{de} and @code{iso-ir-21} are aliases for this charset. Source: ISO 2375 registry. @item DS_2089 + @tindex DS_2089@r{, aliases and source} + @tindex DS2089 + @tindex ISO646-DK + @tindex dk @code{DS2089}, @code{ISO646-DK} and @code{dk} are aliases for this charset. Source: Danish Standard, DS 2089, February 1974. @item EBCDIC-AT-DE + @tindex EBCDIC-AT-DE@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-AT-DE-A + @tindex EBCDIC-AT-DE-A@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-CA-FR + @tindex EBCDIC-CA-FR@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-DK-NO + @tindex EBCDIC-DK-NO@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-DK-NO-A + @tindex EBCDIC-DK-NO-A@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-ES + @tindex EBCDIC-ES@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-ES-A + @tindex EBCDIC-ES-A@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-ES-S + @tindex EBCDIC-ES-S@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-FI-SE + @tindex EBCDIC-FI-SE@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-FI-SE-A + @tindex EBCDIC-FI-SE-A@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-FR + @tindex EBCDIC-FR@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-IS-FRISS + @tindex EBCDIC-IS-FRISS@r{, aliases and source} + @tindex friss @code{friss} is an alias for this charset. Source: Skyrsuvelar Rikisins og Reykjavikurborgar, feb 1982. @item EBCDIC-IT + @tindex EBCDIC-IT@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-PT + @tindex EBCDIC-PT@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-UK + @tindex EBCDIC-UK@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item EBCDIC-US + @tindex EBCDIC-US@r{, aliases and source} Source: IBM 3270 Char Set Ref Ch 10, GA27-2837-9, April 1987. @item ECMA-cyrillic + @tindex ECMA-cyrillic@r{, aliases and source} + @tindex ECMA-113 + @tindex ECMA-113(1986) + @tindex iso-ir-111 @code{ECMA-113}, @code{ECMA-113:1986} and @code{iso-ir-111} are aliases for this charset. Source: ISO 2375 registry. @item ES + @tindex ES@r{, aliases and source} + @tindex ISO646-ES + @tindex iso-ir-17 @code{ISO646-ES} and @code{iso-ir-17} are aliases for this charset. Source: ISO 2375 registry. @item ES2 + @tindex ES2@r{, aliases and source} + @tindex ISO646-ES2 + @tindex iso-ir-85 @code{ISO646-ES2} and @code{iso-ir-85} are aliases for this charset. Source: ISO 2375 registry. @item GB_1988-80 + @tindex GB_1988-80@r{, aliases and source} + @tindex ISO646-CN + @tindex cn + @tindex iso-ir-57 @code{ISO646-CN}, @code{cn} and @code{iso-ir-57} are aliases for this charset. Source: ISO 2375 registry. @item GOST_19768-87 + @tindex GOST_19768-87@r{, aliases and source} + @tindex ST_SEV_358-88 + @tindex iso-ir-153 @code{ST_SEV_358-88} and @code{iso-ir-153} are aliases for this charset. Source: ISO 2375 registry. @item IBM037 + @tindex IBM037@r{, aliases and source} + @tindex 037 + @tindex CP037 + @tindex ebcdic-cp-ca + @tindex ebcdic-cp-nl + @tindex ebcdic-cp-us + @tindex ebcdic-cp-wt @code{037}, @code{CP037}, @code{ebcdic-cp-ca}, @code{ebcdic-cp-nl}, @code{ebcdic-cp-us} and @code{ebcdic-cp-wt} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM038 + @tindex IBM038@r{, aliases and source} + @tindex 038 + @tindex CP038 + @tindex EBCDIC-INT @code{038}, @code{CP038} and @code{EBCDIC-INT} are aliases for this charset. Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990. @item IBM1004 + @tindex IBM1004@r{, aliases and source} + @tindex 1004 + @tindex CP1004 + @tindex os2latin1 @code{1004}, @code{CP1004} and @code{os2latin1} are aliases for this charset. Source: CEN/TC304 N283, 1994-02-04. @item IBM1026 + @tindex IBM1026@r{, aliases and source} + @tindex 1026 + @tindex CP1026 @code{1026} and @code{CP1026} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM1047 + @tindex IBM1047@r{, aliases and source} + @tindex 1047 + @tindex CP1047 @code{1047} and @code{CP1047} are aliases for this charset. Source: IBM Character Data Representation Architecture. Registry SC09-1391-00 p 150. @item IBM256 + @tindex IBM256@r{, aliases and source} + @tindex 256 + @tindex CP256 + @tindex EBCDIC-INT1 @code{256}, @code{CP256} and @code{EBCDIC-INT1} are aliases for this charset. Source: IBM Registry C-H 3-3220-050. @item IBM273 + @tindex IBM273@r{, aliases and source} + @tindex 273 + @tindex CP273 @code{273} and @code{CP273} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM274 + @tindex IBM274@r{, aliases and source} + @tindex 274 + @tindex CP274 + @tindex EBCDIC-BE @code{274}, @code{CP274} and @code{EBCDIC-BE} are aliases for this charset. Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990. @item IBM275 + @tindex IBM275@r{, aliases and source} + @tindex 275 + @tindex CP275 + @tindex EBCDIC-BR @code{275}, @code{CP275} and @code{EBCDIC-BR} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM277 + @tindex IBM277@r{, aliases and source} + @tindex EBCDIC-CP-DK + @tindex EBCDIC-CP-NO @code{EBCDIC-CP-DK} and @code{EBCDIC-CP-NO} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM278 + @tindex IBM278@r{, aliases and source} + @tindex 278 + @tindex CP278 + @tindex ebcdic-cp-fi + @tindex ebcdic-cp-se @code{278}, @code{CP278}, @code{ebcdic-cp-fi} and @code{ebcdic-cp-se} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM280 + @tindex IBM280@r{, aliases and source} + @tindex 280 + @tindex CP280 + @tindex ebcdic-cp-it @code{280}, @code{CP280} and @code{ebcdic-cp-it} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM281 + @tindex IBM281@r{, aliases and source} + @tindex 281 + @tindex CP281 + @tindex EBCDIC-JP-E @code{281}, @code{CP281} and @code{EBCDIC-JP-E} are aliases for this charset. Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990. @item IBM284 + @tindex IBM284@r{, aliases and source} + @tindex 284 + @tindex CP284 + @tindex ebcdic-cp-es @code{284}, @code{CP284} and @code{ebcdic-cp-es} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM285 + @tindex IBM285@r{, aliases and source} + @tindex 285 + @tindex CP285 + @tindex ebcdic-cp-gb @code{285}, @code{CP285} and @code{ebcdic-cp-gb} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM290 + @tindex IBM290@r{, aliases and source} + @tindex 290 + @tindex CP290 + @tindex EBCDIC-JP-kana @code{290}, @code{CP290} and @code{EBCDIC-JP-kana} are aliases for this charset. Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990. @item IBM297 + @tindex IBM297@r{, aliases and source} + @tindex 297 + @tindex CP297 + @tindex ebcdic-cp-fr @code{297}, @code{CP297} and @code{ebcdic-cp-fr} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM420 + @tindex IBM420@r{, aliases and source} + @tindex 420 + @tindex CP420 + @tindex ebcdic-cp-ar1 @code{420}, @code{CP420} and @code{ebcdic-cp-ar1} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. IBM NLS RM p 11-11. @item IBM423 + @tindex IBM423@r{, aliases and source} + @tindex 423 + @tindex CP423 + @tindex ebcdic-cp-gr @code{423}, @code{CP423} and @code{ebcdic-cp-gr} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM424 + @tindex IBM424@r{, aliases and source} + @tindex 424 + @tindex CP424 + @tindex ebcdic-cp-he @code{424}, @code{CP424} and @code{ebcdic-cp-he} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM437 + @tindex IBM437@r{, aliases and source} + @tindex 437 + @tindex CP437 @code{437} and @code{CP437} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM500 + @tindex IBM500@r{, aliases and source} + @tindex 500 + @tindex 500V1 + @tindex CP500 + @tindex ebcdic-cp-be + @tindex ebcdic-cp-ch @code{500}, @code{500V1}, @code{CP500}, @code{ebcdic-cp-be} and @code{ebcdic-cp-ch} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM850 + @tindex IBM850@r{, aliases and source} + @tindex 850 + @tindex CP850 @code{850} and @code{CP850} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. Source: UNICODE 1.0. @item IBM851 + @tindex IBM851@r{, aliases and source} + @tindex 851 + @tindex CP851 @code{851} and @code{CP851} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM852 + @tindex IBM852@r{, aliases and source} + @tindex 852 + @tindex CP852 + @tindex pcl2 + @tindex pclatin2 @code{852}, @code{CP852}, @code{pcl2} and @code{pclatin2} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM855 + @tindex IBM855@r{, aliases and source} + @tindex 855 + @tindex CP855 @code{855} and @code{CP855} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM857 + @tindex IBM857@r{, aliases and source} + @tindex 857 + @tindex CP857 @code{857} and @code{CP857} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM860 + @tindex IBM860@r{, aliases and source} + @tindex 860 + @tindex CP860 @code{860} and @code{CP860} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM861 + @tindex IBM861@r{, aliases and source} + @tindex 861 + @tindex CP861 + @tindex cp-is @code{861}, @code{CP861} and @code{cp-is} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM862 + @tindex IBM862@r{, aliases and source} + @tindex 862 + @tindex CP862 @code{862} and @code{CP862} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM863 + @tindex IBM863@r{, aliases and source} + @tindex 863 + @tindex CP863 @code{863} and @code{CP863} are aliases for this charset. Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991. @item IBM864 + @tindex IBM864@r{, aliases and source} + @tindex 864 + @tindex CP864 @code{864} and @code{CP864} are aliases for this charset. Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991. @item IBM865 + @tindex IBM865@r{, aliases and source} + @tindex 865 + @tindex CP865 @code{865} and @code{CP865} are aliases for this charset. Source: IBM DOS 3.3 Ref (Abridged), 94X9575 (Feb 1987). @item IBM868 + @tindex IBM868@r{, aliases and source} + @tindex 868 + @tindex CP868 + @tindex cp-ar @code{868}, @code{CP868} and @code{cp-ar} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM869 + @tindex IBM869@r{, aliases and source} + @tindex 869 + @tindex CP869 + @tindex cp-gr @code{869}, @code{CP869} and @code{cp-gr} are aliases for this charset. Source: IBM Keyboard layouts and code pages, PN 07G4586 June 1991. @item IBM870 + @tindex IBM870@r{, aliases and source} + @tindex 870 + @tindex CP870 + @tindex ebcdic-cp-roece + @tindex ebcdic-cp-yu @code{870}, @code{CP870}, @code{ebcdic-cp-roece} and @code{ebcdic-cp-yu} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM871 + @tindex IBM871@r{, aliases and source} + @tindex 871 + @tindex CP871 + @tindex ebcdic-cp-is @code{871}, @code{CP871} and @code{ebcdic-cp-is} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM875 + @tindex IBM875@r{, aliases and source} + @tindex 875 + @tindex CP875 + @tindex EBCDIC-Greek @code{875}, @code{CP875} and @code{EBCDIC-Greek} are aliases for this charset. Source: UNICODE 1.0. @item IBM880 + @tindex IBM880@r{, aliases and source} + @tindex 880 + @tindex CP880 + @tindex EBCDIC-Cyrillic @code{880}, @code{CP880} and @code{EBCDIC-Cyrillic} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM891 + @tindex IBM891@r{, aliases and source} + @tindex 891 + @tindex CP891 @code{891} and @code{CP891} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM903 + @tindex IBM903@r{, aliases and source} + @tindex 903 + @tindex CP903 @code{903} and @code{CP903} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM904 + @tindex IBM904@r{, aliases and source} + @tindex 904 + @tindex CP904 @code{904} and @code{CP904} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IBM905 + @tindex IBM905@r{, aliases and source} + @tindex 905 + @tindex CP905 + @tindex ebcdic-cp-tr @code{905}, @code{CP905} and @code{ebcdic-cp-tr} are aliases for this charset. Source: IBM 3174 Character Set Ref, GA27-3831-02, March 1990. @item IBM918 + @tindex IBM918@r{, aliases and source} + @tindex 918 + @tindex CP918 + @tindex ebcdic-cp-ar2 @code{918}, @code{CP918} and @code{ebcdic-cp-ar2} are aliases for this charset. Source: IBM NLS RM Vol2 SE09-8002-01, March 1990. @item IEC_P27-1 + @tindex IEC_P27-1@r{, aliases and source} + @tindex iso-ir-143 @code{iso-ir-143} is an alias for this charset. Source: ISO 2375 registry. @item INIS + @tindex INIS@r{, aliases and source} + @tindex iso-ir-49 @code{iso-ir-49} is an alias for this charset. Source: ISO 2375 registry. @item INIS-8 + @tindex INIS-8@r{, aliases and source} + @tindex iso-ir-50 @code{iso-ir-50} is an alias for this charset. Source: ISO 2375 registry. @item INIS-cyrillic + @tindex INIS-cyrillic@r{, aliases and source} + @tindex iso-ir-51 @code{iso-ir-51} is an alias for this charset. Source: ISO 2375 registry. @item INVARIANT + @tindex INVARIANT@r{, aliases and source} + @tindex iso-ir-170 @code{iso-ir-170} is an alias for this charset. @item ISO-8859-1 + @tindex ISO-8859-1@r{, aliases and source} + @tindex 819 + @tindex CP819 + @tindex IBM819 + @tindex ISO_8859-1 + @tindex ISO_8859-1(1987) + @tindex iso-ir-100 + @tindex l1 + @tindex latin1 @code{819}, @code{CP819}, @code{IBM819}, @code{ISO_8859-1}, @code{ISO_8859-1:1987}, @code{iso-ir-100}, @code{l1} and @code{latin1} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-10 + @tindex ISO-8859-10@r{, aliases and source} + @tindex ISO_8859-10 + @tindex ISO_8859-10(1993) + @tindex iso-ir-157 + @tindex l6 + @tindex latin6 @code{ISO_8859-10}, @code{ISO_8859-10:1993}, @code{iso-ir-157}, @code{l6} and @code{latin6} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-13 + @tindex ISO-8859-13@r{, aliases and source} + @tindex ISO_8859-13 + @tindex ISO_8859-13(1998) + @tindex iso-baltic + @tindex iso-ir-179a + @tindex l7 + @tindex latin7 @code{ISO_8859-13}, @code{ISO_8859-13:1998}, @code{iso-baltic}, @code{iso-ir-179a}, @code{l7} and @code{latin7} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-14 + @tindex ISO-8859-14@r{, aliases and source} + @tindex ISO_8859-14 + @tindex ISO_8859-14(1998) + @tindex iso-celtic + @tindex iso-ir-199 + @tindex l8 + @tindex latin8 @code{ISO_8859-14}, @code{ISO_8859-14:1998}, @code{iso-celtic}, @code{iso-ir-199}, @code{l8} and @code{latin8} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-15 + @tindex ISO-8859-15@r{, aliases and source} + @tindex ISO_8859-15 + @tindex ISO_8859-15(1998) + @tindex iso-ir-203 + @tindex l9 + @tindex latin9 @code{ISO_8859-15}, @code{ISO_8859-15:1998}, @code{iso-ir-203}, @code{l9} and @code{latin9} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-2 + @tindex ISO-8859-2@r{, aliases and source} + @tindex 912 + @tindex CP912 + @tindex IBM912 + @tindex ISO_8859-2 + @tindex ISO_8859-2(1987) + @tindex iso-ir-101 + @tindex l2 + @tindex latin2 @code{912}, @code{CP912}, @code{IBM912}, @code{ISO_8859-2}, @code{ISO_8859-2:1987}, @code{iso-ir-101}, @code{l2} and @code{latin2} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-3 + @tindex ISO-8859-3@r{, aliases and source} + @tindex ISO_8859-3 + @tindex ISO_8859-3(1988) + @tindex iso-ir-109 + @tindex l3 + @tindex latin3 @code{ISO_8859-3}, @code{ISO_8859-3:1988}, @code{iso-ir-109}, @code{l3} and @code{latin3} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-4 + @tindex ISO-8859-4@r{, aliases and source} + @tindex ISO_8859-4 + @tindex ISO_8859-4(1988) + @tindex iso-ir-110 + @tindex l4 + @tindex latin4 @code{ISO_8859-4}, @code{ISO_8859-4:1988}, @code{iso-ir-110}, @code{l4} and @code{latin4} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-5 + @tindex ISO-8859-5@r{, aliases and source} + @tindex ISO_8859-5 + @tindex ISO_8859-5(1988) + @tindex cyrillic + @tindex iso-ir-144 @code{ISO_8859-5}, @code{ISO_8859-5:1988}, @code{cyrillic} and @code{iso-ir-144} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-6 + @tindex ISO-8859-6@r{, aliases and source} + @tindex ASMO-708 + @tindex ECMA-114 + @tindex ISO_8859-6 + @tindex ISO_8859-6(1987) + @tindex arabic + @tindex iso-ir-127 @code{ASMO-708}, @code{ECMA-114}, @code{ISO_8859-6}, @code{ISO_8859-6:1987}, @code{arabic} and @code{iso-ir-127} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-7 + @tindex ISO-8859-7@r{, aliases and source} + @tindex ECMA-118 + @tindex ELOT_928 + @tindex ISO_8859-7 + @tindex ISO_8859-7(1987) + @tindex greek + @tindex greek8 + @tindex iso-ir-126 @code{ECMA-118}, @code{ELOT_928}, @code{ISO_8859-7}, @code{ISO_8859-7:1987}, @code{greek}, @code{greek8} and @code{iso-ir-126} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-8 + @tindex ISO-8859-8@r{, aliases and source} + @tindex ISO_8859-8 + @tindex ISO_8859-8(1988) + @tindex hebrew + @tindex iso-ir-138 @code{ISO_8859-8}, @code{ISO_8859-8:1988}, @code{hebrew} and @code{iso-ir-138} are aliases for this charset. Source: ISO 2375 registry. @item ISO-8859-9 + @tindex ISO-8859-9@r{, aliases and source} + @tindex ISO_8859-9 + @tindex ISO_8859-9(1989) + @tindex iso-ir-148 + @tindex l5 + @tindex latin5 @code{ISO_8859-9}, @code{ISO_8859-9:1989}, @code{iso-ir-148}, @code{l5} and @code{latin5} are aliases for this charset. Source: ISO 2375 registry. @item ISO_10367-box + @tindex ISO_10367-box@r{, aliases and source} + @tindex iso-ir-155 @code{iso-ir-155} is an alias for this charset. Source: ISO 2375 registry. @item ISO_2033-1983 + @tindex ISO_2033-1983@r{, aliases and source} + @tindex e13b + @tindex iso-ir-98 @code{e13b} and @code{iso-ir-98} are aliases for this charset. Source: ISO 2375 registry. @item ISO_5427 + @tindex ISO_5427@r{, aliases and source} + @tindex iso-ir-37 @code{iso-ir-37} is an alias for this charset. Source: ISO 2375 registry. @item ISO_5427-ext + @tindex ISO_5427-ext@r{, aliases and source} + @tindex ISO_5427(1981) + @tindex iso-ir-54 @code{ISO_5427:1981} and @code{iso-ir-54} are aliases for this charset. Source: ISO 2375 registry. @item ISO_5428 + @tindex ISO_5428@r{, aliases and source} + @tindex ISO_5428(1980) + @tindex iso-ir-55 @code{ISO_5428:1980} and @code{iso-ir-55} are aliases for this charset. Source: ISO 2375 registry. @item ISO_646.basic + @tindex ISO_646.basic@r{, aliases and source} + @tindex ISO_646.basic(1983) + @tindex ref @code{ISO_646.basic:1983} and @code{ref} are aliases for this charset. Source: ISO 2375 registry. @item ISO_646.irv + @tindex ISO_646.irv@r{, aliases and source} + @tindex ISO_646.irv(1983) + @tindex irv + @tindex iso-ir-2 @code{ISO_646.irv:1983}, @code{irv} and @code{iso-ir-2} are aliases for this charset. Source: ISO 2375 registry. @item ISO_6937-2-25 + @tindex ISO_6937-2-25@r{, aliases and source} + @tindex iso-ir-152 @code{iso-ir-152} is an alias for this charset. Source: ISO 2375 registry. @item ISO_8859-supp + @tindex ISO_8859-supp@r{, aliases and source} + @tindex iso-ir-154 + @tindex latin1-2-5 @code{iso-ir-154} and @code{latin1-2-5} are aliases for this charset. Source: ISO 2375 registry. @item IT + @tindex IT@r{, aliases and source} + @tindex ISO646-IT + @tindex iso-ir-15 @code{ISO646-IT} and @code{iso-ir-15} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6220-1969-jp + @tindex JIS_C6220-1969-jp@r{, aliases and source} + @tindex JIS_C6220-1969 + @tindex iso-ir-13 + @tindex katakana + @tindex x0201-7 @code{JIS_C6220-1969}, @code{iso-ir-13}, @code{katakana} and @code{x0201-7} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6220-1969-ro + @tindex JIS_C6220-1969-ro@r{, aliases and source} + @tindex ISO646-JP + @tindex iso-ir-14 + @tindex jp @code{ISO646-JP}, @code{iso-ir-14} and @code{jp} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6229-1984-a + @tindex JIS_C6229-1984-a@r{, aliases and source} + @tindex jp-ocr-a @code{jp-ocr-a} is an alias for this charset. Source: ISO 2375 registry. @item JIS_C6229-1984-b + @tindex JIS_C6229-1984-b@r{, aliases and source} + @tindex ISO646-JP-OCR-B + @tindex jp-ocr-b @code{ISO646-JP-OCR-B} and @code{jp-ocr-b} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6229-1984-b-add + @tindex JIS_C6229-1984-b-add@r{, aliases and source} + @tindex iso-ir-93 + @tindex jp-ocr-b-add @code{iso-ir-93} and @code{jp-ocr-b-add} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6229-1984-hand + @tindex JIS_C6229-1984-hand@r{, aliases and source} + @tindex iso-ir-94 + @tindex jp-ocr-hand @code{iso-ir-94} and @code{jp-ocr-hand} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6229-1984-hand-add + @tindex JIS_C6229-1984-hand-add@r{, aliases and source} + @tindex iso-ir-95 + @tindex jp-ocr-hand-add @code{iso-ir-95} and @code{jp-ocr-hand-add} are aliases for this charset. Source: ISO 2375 registry. @item JIS_C6229-1984-kana + @tindex JIS_C6229-1984-kana@r{, aliases and source} + @tindex iso-ir-96 @code{iso-ir-96} is an alias for this charset. Source: ISO 2375 registry. @item JIS_X0201 + @tindex JIS_X0201@r{, aliases and source} + @tindex X0201 @code{X0201} is an alias for this charset. @item JUS_I.B1.002 + @tindex JUS_I.B1.002@r{, aliases and source} + @tindex ISO646-YU + @tindex iso-ir-141 + @tindex js + @tindex yu @code{ISO646-YU}, @code{iso-ir-141}, @code{js} and @code{yu} are aliases for this charset. Source: ISO 2375 registry. @item JUS_I.B1.003-mac + @tindex JUS_I.B1.003-mac@r{, aliases and source} + @tindex iso-ir-147 + @tindex macedonian @code{iso-ir-147} and @code{macedonian} are aliases for this charset. Source: ISO 2375 registry. @item JUS_I.B1.003-serb + @tindex JUS_I.B1.003-serb@r{, aliases and source} + @tindex iso-ir-146 + @tindex serbian @code{iso-ir-146} and @code{serbian} are aliases for this charset. Source: ISO 2375 registry. @item KOI-7 + @tindex KOI-7@r{, aliases and source} Source: Andrey A. Chernov . @item KOI-8 + @tindex KOI-8@r{, aliases and source} + @tindex GOST_19768-74 @code{GOST_19768-74} is an alias for this charset. Source: Andrey A. Chernov . @item KOI8-R + @tindex KOI8-R@r{, aliases and source} Source: RFC1489 via Gabor Kiss . And Andrey A. Chernov . @item KOI8-RU + @tindex KOI8-RU@r{, aliases and source} Source: http://cad.ntu-kpi.kiev.ua/multiling/koi8-ru/. @item KOI8-U + @tindex KOI8-U@r{, aliases and source} Source: RFC 2319. Mibenum: 2088. Source: http://www.net.ua/KOI8-U/. @item KSC5636 + @tindex KSC5636@r{, aliases and source} + @tindex ISO646-KR @code{ISO646-KR} is an alias for this charset. @item Latin-greek-1 + @tindex Latin-greek-1@r{, aliases and source} + @tindex iso-ir-27 @code{iso-ir-27} is an alias for this charset. Source: ISO 2375 registry. @item MSZ_7795.3 + @tindex MSZ_7795.3@r{, aliases and source} + @tindex ISO646-HU + @tindex hu + @tindex iso-ir-86 @code{ISO646-HU}, @code{hu} and @code{iso-ir-86} are aliases for this charset. Source: ISO 2375 registry. @item NATS-DANO + @tindex NATS-DANO@r{, aliases and source} + @tindex iso-ir-9-1 @code{iso-ir-9-1} is an alias for this charset. Source: ISO 2375 registry. @item NATS-DANO-ADD + @tindex NATS-DANO-ADD@r{, aliases and source} + @tindex iso-ir-9-2 @code{iso-ir-9-2} is an alias for this charset. Source: ISO 2375 registry. @item NATS-SEFI + @tindex NATS-SEFI@r{, aliases and source} + @tindex iso-ir-8-1 @code{iso-ir-8-1} is an alias for this charset. Source: ISO 2375 registry. @item NATS-SEFI-ADD + @tindex NATS-SEFI-ADD@r{, aliases and source} + @tindex iso-ir-8-2 @code{iso-ir-8-2} is an alias for this charset. Source: ISO 2375 registry. @item NC_NC00-10 + @tindex NC_NC00-10@r{, aliases and source} + @tindex ISO646-CU + @tindex NC_NC00-10:81 + @tindex cuba + @tindex iso-ir-151 @code{ISO646-CU}, @code{NC_NC00-10:81}, @code{cuba} and @code{iso-ir-151} are aliases for this charset. Source: ISO 2375 registry. @item NF_Z_62-010 + @tindex NF_Z_62-010@r{, aliases and source} + @tindex ISO646-FR + @tindex fr + @tindex iso-ir-69 @code{ISO646-FR}, @code{fr} and @code{iso-ir-69} are aliases for this charset. Source: ISO 2375 registry. @item NF_Z_62-010_(1973) + @tindex NF_Z_62-010_(1973)@r{, aliases and source} + @tindex ISO646-FR1 + @tindex iso-ir-25 @code{ISO646-FR1} and @code{iso-ir-25} are aliases for this charset. Source: ISO 2375 registry. @item NS_4551-1 + @tindex NS_4551-1@r{, aliases and source} + @tindex ISO646-NO + @tindex iso-ir-60 + @tindex no @code{ISO646-NO}, @code{iso-ir-60} and @code{no} are aliases for this charset. Source: ISO 2375 registry. @item NS_4551-2 + @tindex NS_4551-2@r{, aliases and source} + @tindex ISO646-NO2 + @tindex iso-ir-61 + @tindex no2 @code{ISO646-NO2}, @code{iso-ir-61} and @code{no2} are aliases for this charset. Source: ISO 2375 registry. @item NeXTSTEP + @tindex NeXTSTEP@r{, aliases and source} + @tindex next @code{next} is an alias for this charset. Source: Peter Svanberg - psv@@nada.kth.se. @item PT + @tindex PT@r{, aliases and source} + @tindex ISO646-PT + @tindex iso-ir-16 @code{ISO646-PT} and @code{iso-ir-16} are aliases for this charset. Source: ISO 2375 registry. @item PT2 + @tindex PT2@r{, aliases and source} + @tindex ISO646-PT2 + @tindex iso-ir-84 @code{ISO646-PT2} and @code{iso-ir-84} are aliases for this charset. Source: ISO 2375 registry. @item SEN_850200_B + @tindex SEN_850200_B@r{, aliases and source} + @tindex FI + @tindex ISO646-FI + @tindex ISO646-SE + @tindex SS636127 + @tindex iso-ir-10 + @tindex se @code{FI}, @code{ISO646-FI}, @code{ISO646-SE}, @code{SS636127}, @code{iso-ir-10} and @code{se} are aliases for this charset. Source: ISO 2375 registry. @item SEN_850200_C + @tindex SEN_850200_C@r{, aliases and source} + @tindex ISO646-SE2 + @tindex iso-ir-11 + @tindex se2 @code{ISO646-SE2}, @code{iso-ir-11} and @code{se2} are aliases for this charset. Source: ISO 2375 registry. @item T.61-7bit + @tindex T.61-7bit@r{, aliases and source} + @tindex iso-ir-102 @code{iso-ir-102} is an alias for this charset. Source: ISO 2375 registry. @item baltic + @tindex baltic@r{, aliases and source} + @tindex iso-ir-179 @code{iso-ir-179} is an alias for this charset. Source: ISO 2375 registry. &g1esc x2d56 &g2esc x2e56 &g3esc x2f56. @item greek-ccitt + @tindex greek-ccitt@r{, aliases and source} + @tindex iso-ir-150 @code{iso-ir-150} is an alias for this charset. Source: ISO 2375 registry. @item greek7 + @tindex greek7@r{, aliases and source} + @tindex iso-ir-88 @code{iso-ir-88} is an alias for this charset. Source: ISO 2375 registry. @item greek7-old + @tindex greek7-old@r{, aliases and source} + @tindex iso-ir-18 @code{iso-ir-18} is an alias for this charset. Source: ISO 2375 registry. @item hp-roman8 + @tindex hp-roman8@r{, aliases and source} + @tindex r8 + @tindex roman8 @code{r8} and @code{roman8} are aliases for this charset. Source: LaserJet IIP Printer User's Manual,. HP part no 33471-90901, Hewlet-Packard, June 1989. @item latin-greek + @tindex latin-greek@r{, aliases and source} + @tindex iso-ir-19 @code{iso-ir-19} is an alias for this charset. Source: ISO 2375 registry. @item mac-is + @tindex mac-is@r{, aliases and source} @item macintosh + @tindex macintosh@r{, aliases and source} + @tindex mac @code{mac} is an alias for this charset. Source: The Unicode Standard ver 1.0, ISBN 0-201-56788-1, Oct 1991. @item macintosh_ce + @tindex macintosh_ce@r{, aliases and source} + @tindex macce @code{macce} is an alias for this charset. Source: Macintosh CE fonts. @item sami + @tindex sami@r{, aliases and source} + @tindex iso-ir-158 + @tindex lap + @tindex latin-lap @code{iso-ir-158}, @code{lap} and @code{latin-lap} are aliases for this charset. Source: ISO 2375 registry. diff -acprNC5 recode-3.5.orig/doc/recode.texi recode-3.5.djgpp/doc/recode.texi *** recode-3.5.orig/doc/recode.texi Wed Apr 28 01:23:32 1999 --- recode-3.5.djgpp/doc/recode.texi Sun Jun 17 23:56:02 2001 *************** *** 1,21 **** ! \input texinfo @c %**start of header @setfilename recode.info @settitle The @code{recode} reference manual @finalout @c %**end of header @include version.texi ! @ifinfo ! @format ! START-INFO-DIR-ENTRY * recode: (recode). Conversion between character sets and surfaces. ! END-INFO-DIR-ENTRY ! @end format ! @end ifinfo @ifinfo This file documents the @code{recode} command, which has the purpose of converting files between various character sets and surfaces. --- 1,23 ---- ! \input texinfo @c -*-texinfo-*- -*- coding: latin-1 -*- @c %**start of header @setfilename recode.info @settitle The @code{recode} reference manual + + @c An index for command-line options + @defcodeindex op + @c Put variable and function names together + @syncodeindex vr fn @finalout @c %**end of header @include version.texi ! @dircategory Internationalization and character sets ! @direntry * recode: (recode). Conversion between character sets and surfaces. ! @end direntry @ifinfo This file documents the @code{recode} command, which has the purpose of converting files between various character sets and surfaces. *************** The library recognises or produces nearl *** 81,90 **** --- 83,93 ---- is able to convert files between almost any pair. Most @w{RFC 1345} character sets are supported. The @code{recode} program is a handy front-end to the library. The current @code{recode} release is @value{VERSION}. + @end ifinfo @menu * Tutorial:: Quick Tutorial * Introduction:: Terminology and purpose * Invoking recode:: How to use this program *************** The current @code{recode} release is @va *** 96,107 **** --- 99,115 ---- * CDC:: Charsets for CDC machines * Micros:: Other micro-computer charsets * Miscellaneous:: Various other charsets * Surfaces:: All about surfaces * Internals:: Internal aspects + * Concept Index:: + * Option Index:: + * Library Index:: + * Charset and Surface Index:: @detailmenu + --- The Detailed Node Listing --- Terminology and purpose * Charset overview:: Overview of charsets *************** Internal aspects *** 187,201 **** * Design:: Comments on the library design @end detailmenu @end menu - @end ifinfo - @node Tutorial, Introduction, Top, Top @chapter Quick Tutorial So, really, you just are in a hurry to use @code{recode}, and do not feel like studying this manual? Even reading this paragraph slows you down? We might have a problem, as you will have to do some guess work, and might not become very proficient unless you have a very solid intuition@dots{}. --- 195,209 ---- * Design:: Comments on the library design @end detailmenu @end menu @node Tutorial, Introduction, Top, Top @chapter Quick Tutorial + @cindex @code{recode} use, a tutorial + @cindex tutorial So, really, you just are in a hurry to use @code{recode}, and do not feel like studying this manual? Even reading this paragraph slows you down? We might have a problem, as you will have to do some guess work, and might not become very proficient unless you have a very solid intuition@dots{}. *************** Standardisation) and IETF (Internet Engi *** 315,324 **** --- 323,333 ---- own terminology, this document does not try to stick to either one in a strict way, while it does not want to throw more confusion in the field. On the other hand, it would not be efficient using paraphrases all the time, so @code{recode} coins a few short words, which are explained below. + @cindex charset, what it is A @dfn{charset}, in the context of @code{recode}, is a particular association between computer codes on one side, and a repertoire of intended characters on the other side. Codes are usually taken from a set of consecutive small integers, starting at 0. Some characters have a graphical appearance (glyph) or displayable effect, others have special uses like, for example, *************** It does @emph{not} exactly corresponds t *** 330,339 **** --- 339,349 ---- character set}, that is, a set of characters with an encoding for them. An coded character set does not necessarily use all available code positions, while a MIME charset usually tries to specify them all. A MIME charset might be the union of a few disjoint coded character sets. + @cindex surface, what it is A @dfn{surface} is a term used in @code{recode} only, and is a short for surface transformation of a charset stream. This is any kind of mapping, usually reversible, which associates physical bits in some medium for a stream of characters taken from one or more charsets (usually one). A surface is a kind of varnish added over a charset so it fits in actual *************** those of Keld Simonsen. *** 376,391 **** @end menu @node Charset overview, Surface overview, Introduction, Introduction @section Overview of charsets Recoding is currently possible between many charsets, the bulk of which is described by @w{RFC 1345} tables. @xref{Tabular}. The @code{recode} library also handles some charsets in some specialised ways. These are: @itemize @bullet - @item 6-bit charsets based on CDC display code: 6/12 code from NOS; bang-bang code from Universit@'e de Montr@'eal; @item --- 386,401 ---- @end menu @node Charset overview, Surface overview, Introduction, Introduction @section Overview of charsets + @cindex charsets, overview Recoding is currently possible between many charsets, the bulk of which is described by @w{RFC 1345} tables. @xref{Tabular}. The @code{recode} library also handles some charsets in some specialised ways. These are: @itemize @bullet @item 6-bit charsets based on CDC display code: 6/12 code from NOS; bang-bang code from Universit@'e de Montr@'eal; @item *************** the PC, Apple's code for the Macintosh; *** 400,420 **** @item 8-bit non-ASCII codes: three flavours of EBCDIC; @item 16-bit or 31-bit universal characters, and their transfer encodings. - @end itemize The introduction of @w{RFC 1345} in @code{recode} has brought with it a few charsets having the functionality of older ones, but yet being different in subtle ways. The effects have not been fully investigated yet, so for now, clashes are avoided, the old and new charsets are kept well separate. @node Surface overview, Contributing, Charset overview, Introduction @section Overview of surfaces For various practical considerations, it sometimes happens that the codes making up a text, written in a particular charset, cannot simply be put out in a file one after another without creating problems or breaking other things. Sometimes, 8-bit codes cannot be written on a 7-bit medium, variable length codes need kind of envelopes, newlines require special --- 410,430 ---- @item 8-bit non-ASCII codes: three flavours of EBCDIC; @item 16-bit or 31-bit universal characters, and their transfer encodings. @end itemize The introduction of @w{RFC 1345} in @code{recode} has brought with it a few charsets having the functionality of older ones, but yet being different in subtle ways. The effects have not been fully investigated yet, so for now, clashes are avoided, the old and new charsets are kept well separate. @node Surface overview, Contributing, Charset overview, Introduction @section Overview of surfaces + @cindex surfaces, overview For various practical considerations, it sometimes happens that the codes making up a text, written in a particular charset, cannot simply be put out in a file one after another without creating problems or breaking other things. Sometimes, 8-bit codes cannot be written on a 7-bit medium, variable length codes need kind of envelopes, newlines require special *************** treatment, etc. We sometimes have to ap *** 422,431 **** --- 432,443 ---- of codes, which surfaces are kind of tricks used to fit the charset into those practical constraints. Moreover, similar surfaces or tricks may be useful for many unrelated charsets, and many surfaces can be used at once over a single charset. + @cindex pure charset + @cindex charset, pure So, @code{recode} has machinery to describe a combination of a charset with surfaces used over it in a file. We would use the expression @dfn{pure charset} for referring to a charset free of any surface, that is, the conceptual association between integer codes and character intents. *************** identifying surfaces as such: when it is *** 436,445 **** --- 448,458 ---- surface as if it were a charset, this is preferred, and done. @node Contributing, , Surface overview, Introduction @section Contributions and bug reports + @cindex contributing charsets Even being the @code{recode} author and current maintainer, I am no specialist in charset standards. I only made @code{recode} along the years to solve my own needs, but felt it was applicable for the needs of others. Some FSF people liked the program structure and suggested to make it more widely available. I often rely on @code{recode} users *************** Many users contributed to @code{recode} *** 468,482 **** their interest and involvement. Some suggestions can be integrated quickly while some others have to be delayed, I have to draw a line somewhere when time comes to make a new release, about what would go in it and what would go in the next. Please send suggestions, documentation errors and bug reports to @email{recode-bugs@@iro.umontreal.ca} or, if you prefer, directly to ! Fran@,{c}ois Pinard@footnote{Use @email{pinard@@iro.umontreal.ca} ! to reach me}. Do not be afraid to report details, because this program ! is the mere aggregation of hundreds of details. @node Invoking recode, Library, Introduction, Top @chapter How to use this program With the synopsis of the @code{recode} call, we stress the difference --- 481,497 ---- their interest and involvement. Some suggestions can be integrated quickly while some others have to be delayed, I have to draw a line somewhere when time comes to make a new release, about what would go in it and what would go in the next. + @cindex bug reports, where to send + @cindex reporting bugs Please send suggestions, documentation errors and bug reports to @email{recode-bugs@@iro.umontreal.ca} or, if you prefer, directly to ! @email{pinard@@iro.umontreal.ca, Fran@,{c}ois Pinard}. Do not be afraid ! to report details, because this program is the mere aggregation of ! hundreds of details. @node Invoking recode, Library, Introduction, Top @chapter How to use this program With the synopsis of the @code{recode} call, we stress the difference *************** control. *** 498,507 **** --- 513,524 ---- @end menu @node Synopsis, Requests, Invoking recode, Invoking recode @section Synopsis of @code{recode} call + @cindex @code{recode}, synopsis of invocation + @cindex invocation of @code{recode}, synopsis The general format of the program call is one of: @example recode [@var{option}]@dots{} [@var{charset} | @var{request} [@var{file}]@dots{} ] @end example *************** be given to an optional @var{charset} pa *** 513,523 **** In other calls, the first parameter (@var{request}) always explains which transformations are expected on the files. There are many variations to the aspect of this parameter. We will discuss more complex situations later (@pxref{Requests}), but for many simple cases, this parameter ! merely looks like@footnote{In previous versions or @code{recode}, a single colon @samp{:} was used instead of the two dots @samp{..} for separating charsets, but this was creating problems because colons are allowed in official charset names. The old request syntax is still recognised for compatibility purposes, but is deprecated.}: --- 530,540 ---- In other calls, the first parameter (@var{request}) always explains which transformations are expected on the files. There are many variations to the aspect of this parameter. We will discuss more complex situations later (@pxref{Requests}), but for many simple cases, this parameter ! merely looks like this@footnote{In previous versions or @code{recode}, a single colon @samp{:} was used instead of the two dots @samp{..} for separating charsets, but this was creating problems because colons are allowed in official charset names. The old request syntax is still recognised for compatibility purposes, but is deprecated.}: *************** compatibility purposes, but is deprecate *** 529,538 **** --- 546,557 ---- where @var{before} and @var{after} each gives the name of a charset. Each @var{file} will be read assuming it is coded with charset @var{before}, it will be recoded over itself so to use the charset @var{after}. If there is no @var{file} on the @code{recode} command, the program rather acts as a Unix filter and transforms standard input onto standard output. + @cindex filter operation + @cindex @code{recode}, operation as filter The capability of recoding many files at once is very convenient. For example, one could easily prepare a distribution from @w{Latin-1} to MSDOS, this way: *************** This example also shows that @code{l1} c *** 577,601 **** In the case where the @var{request} is merely written as @var{before}..@var{after}, then @var{before} and @var{after} specify the start charset and the goal charset for the recoding. For @code{recode}, charset names may contain any character, besides a comma, a forward slash, or two periods in a row. But in practice, charset names are currently limited to alphabetic letters (upper or lower case), digits, hyphens, underlines, periods, colons or round parentheses. ! The complete syntax for allowable @var{request} allows for unusual things, which might surprise at first. (Do not pay too much attention ! to these facilities on a first reading.) For example, @var{request} ! may also contain intermediary charsets, like in: @example @var{before}..@var{interim1}..@var{interim2}..@var{after} @end example @noindent meaning that @code{recode} should internally produce the @var{interim1} charset from the start charset, then work out of this @var{interim1} charset to internally produce @var{interim2}, and from there towards the goal charset. In fact, @code{recode} internally combines recipes and automatically uses interim charsets, when there is no direct recipe for --- 596,627 ---- In the case where the @var{request} is merely written as @var{before}..@var{after}, then @var{before} and @var{after} specify the start charset and the goal charset for the recoding. + @cindex charset names, valid characters + @cindex valid characters in charset names For @code{recode}, charset names may contain any character, besides a comma, a forward slash, or two periods in a row. But in practice, charset names are currently limited to alphabetic letters (upper or lower case), digits, hyphens, underlines, periods, colons or round parentheses. ! @cindex request, syntax ! @cindex @code{recode} request syntax ! The complete syntax for a valid @var{request} allows for unusual things, which might surprise at first. (Do not pay too much attention ! to these facilities on first reading.) For example, @var{request} ! may also contain intermediate charsets, like in the following example: @example @var{before}..@var{interim1}..@var{interim2}..@var{after} @end example @noindent + @cindex intermediate charsets + @cindex chaining of charsets in a request + @cindex charsets, chaining in a request meaning that @code{recode} should internally produce the @var{interim1} charset from the start charset, then work out of this @var{interim1} charset to internally produce @var{interim2}, and from there towards the goal charset. In fact, @code{recode} internally combines recipes and automatically uses interim charsets, when there is no direct recipe for *************** following one. For example, the two fol *** 617,641 **** @end example @noindent In this example, the charset input for any recoding sub-request is identical to the charset output by the preceding sub-request. But it does not have ! to be in the general case. One might wonder what would be the meaning of declaring the charset input for a recoding sub-request of being of different nature than the charset output by a preceding sub-request, when ! recodings are chained in this way. These strange usages might have a meaning and be useful for the @code{recode} expert, but they are quite uncommon in practice. More useful is the distinction between the concept of charset, and the concept of surfaces. An encoded charset is represented by: @example @var{pure-charset}/@var{surface1}/@var{surface2}@dots{} @end example @noindent using slashes to introduce surfaces, if any. The order of application of surfaces is usually important, they cannot be freely commuted. In the given example, @var{surface1} is first applied over the @var{pure-charset}, then @var{surface2} is applied over the result. Given this request: --- 643,670 ---- @end example @noindent In this example, the charset input for any recoding sub-request is identical to the charset output by the preceding sub-request. But it does not have ! to be so in the general case. One might wonder what would be the meaning of declaring the charset input for a recoding sub-request of being of different nature than the charset output by a preceding sub-request, when ! recodings are chained in this way. Such a strange usage might have a meaning and be useful for the @code{recode} expert, but they are quite uncommon in practice. + @cindex surfaces, syntax More useful is the distinction between the concept of charset, and the concept of surfaces. An encoded charset is represented by: @example @var{pure-charset}/@var{surface1}/@var{surface2}@dots{} @end example @noindent + @cindex surfaces, commutativity + @cindex commutativity of surfaces using slashes to introduce surfaces, if any. The order of application of surfaces is usually important, they cannot be freely commuted. In the given example, @var{surface1} is first applied over the @var{pure-charset}, then @var{surface2} is applied over the result. Given this request: *************** the @code{recode} program will understan *** 648,657 **** --- 677,689 ---- have @var{surface2} removed first (because it was applied last), then @var{surface1} should be removed. The next step will be to translate the codes from charset @var{before} to charset @var{after}, prior to applying @var{surface3} over the result. + @cindex implied surfaces + @cindex surfaces, implied + @tindex IBM-PC charset, and CR-LF surface Some charsets have one or more @emph{implied} surfaces. In this case, the implied surfaces are automatically handled merely by naming the charset, without any explicit surface to qualify it. Let's take an example to illustrate this feature. The request @samp{pc..l1} will indeed decode MS-DOS end of lines prior to converting IBM-PC codes to @w{Latin-1}, because @samp{pc} *************** the charset @code{IBM-PC}.} which has @c *** 660,699 **** The request @samp{pc/..l1} will @emph{not} decode end of lines, since the slash introduces surfaces, and even if the surface list is empty, it effectively defeats the automatic removal of surfaces for this charset. So, empty surfaces are useful, indeed! Both charsets and surfaces may have predefined alternate names, or aliases. However, and this is rather important to understand, implied surfaces are attached to individual aliases rather than on genuine charsets. Consequently, the official charset name and all of its aliases do not necessarily share the same implied surfaces. The charset and all its aliases may each have its own different set of implied surfaces. Charset names, surface names, or their aliases may always be abbreviated to any unambiguous prefix. Internally in @code{recode}, disambiguating tables are kept separate for charset names and surface names. While recognising a charset name or a surface name (or aliases thereof), @code{recode} ignores all characters besides letters and digits, so for example, the hyphens and underlines being part of an official charset name may safely be omitted (no need to un-confuse them!). There is also no distinction between upper and lower case for charset or surface names. One of the @var{before} or @var{after} keywords may be omitted. If the double dot separator is omitted too, then the charset is interpreted as the @var{before} charset.@footnote{Both @var{before} and @var{after} may ! be omitted, in which case the double dot separator may not. This would ! not be very meaningful, as the recoding reduces to a mere copy in that case.} When a charset name is omitted or left empty, the value of the @code{DEFAULT_CHARSET} variable in the environment is used instead. If this ! variable is not defined, the @code{recode} library uses an @emph{usual charset} which is installation dependent. When this variable is defined but ! has an empty value, charset names may just not be omitted. Unless overriden ! when @code{recode} was installed, this usual charset is @code{Latin-1} for ! Unix systems or @code{IBM-PC} for MS-DOS machines. If the charset name is omitted but followed by surfaces, the surfaces then qualify the usual or default charset. For example, the request @samp{../x} is sufficient for applying an hexadecimal surface to the input text@footnote{MS-DOS is one of those systems for which the default charset --- 692,741 ---- The request @samp{pc/..l1} will @emph{not} decode end of lines, since the slash introduces surfaces, and even if the surface list is empty, it effectively defeats the automatic removal of surfaces for this charset. So, empty surfaces are useful, indeed! + @cindex aliases + @cindex alternate names for charsets and surfaces + @cindex charsets, aliases + @cindex surfaces, aliases Both charsets and surfaces may have predefined alternate names, or aliases. However, and this is rather important to understand, implied surfaces are attached to individual aliases rather than on genuine charsets. Consequently, the official charset name and all of its aliases do not necessarily share the same implied surfaces. The charset and all its aliases may each have its own different set of implied surfaces. + @cindex abbreviated names for charsets and surfaces + @cindex names of charsets and surfaces, abbreviation Charset names, surface names, or their aliases may always be abbreviated to any unambiguous prefix. Internally in @code{recode}, disambiguating tables are kept separate for charset names and surface names. + @cindex letter case, in charset and surface names While recognising a charset name or a surface name (or aliases thereof), @code{recode} ignores all characters besides letters and digits, so for example, the hyphens and underlines being part of an official charset name may safely be omitted (no need to un-confuse them!). There is also no distinction between upper and lower case for charset or surface names. One of the @var{before} or @var{after} keywords may be omitted. If the double dot separator is omitted too, then the charset is interpreted as the @var{before} charset.@footnote{Both @var{before} and @var{after} may ! be omitted, in which case the double dot separator is mandatory. This is ! not very useful, as the recoding reduces to a mere copy in that case.} + @cindex default charset + @cindex charset, default + @vindex DEFAULT_CHARSET When a charset name is omitted or left empty, the value of the @code{DEFAULT_CHARSET} variable in the environment is used instead. If this ! variable is not defined, the @code{recode} library uses the @dfn{usual charset} which is installation dependent. When this variable is defined but ! has an empty value, charset names may not be omitted. Unless overriden ! when @code{recode} was installed, the usual charset is @code{Latin-1} for ! Unix systems or @code{IBM-PC} for MS-DOS/MS-Windows machines. If the charset name is omitted but followed by surfaces, the surfaces then qualify the usual or default charset. For example, the request @samp{../x} is sufficient for applying an hexadecimal surface to the input text@footnote{MS-DOS is one of those systems for which the default charset *************** Many options control listing output gene *** 714,739 **** --- 756,794 ---- they are not meant to accompany actual file recodings. These options are: @table @samp @item --version + @opindex --version + @cindex @code{recode} version, printing The program merely prints its version numbers on standard output, and exits without doing anything else. @item --help + @opindex --help + @cindex help page, printing The program merely prints a page of help on standard output, and exits without doing any recoding. @item -C @itemx --copyright + @opindex -C + @opindex --copyright + @cindex copyright conditions, printing Given this option, all other parameters and options are ignored. The program prints briefly the copyright and copying conditions. See the file @file{COPYING} in the distribution for full statement of the Copyright and copying conditions. @item -h[@var{language}/][@var{name}] @itemx --header[=[@var{language}/][@var{name}]] + @opindex -h + @opindex --header + @cindex source file generation + @cindex programming language support + @cindex languages, programming + @cindex supported programming languages Instead of recoding files, @code{recode} writes a @var{language} source file on standard output and exits. This source is meant to be included in a regular program written in the same programming @var{language}: its purpose is to declare and initialise an array, named @var{name}, which represents the requested recoding. The only acceptable values for *************** table. Also, when attempting to produce *** 751,765 **** relaxes its checking a tiny bit: it ignores the algorithmic part of some tabular recodings, it also avoids the processing of implied surfaces. But this is all fairly technical. Better try and see! Beware that other options might affect the produced source tables, these ! are: @code{-d}, @code{-g} and, particularly, @code{-s}. @item -k @var{pairs} @itemx --known=@var{pairs} ! This particular option is meant to help identifying an unknown charset, using as hints some already identified characters of the charset. Some examples will help introducing the idea. Let's presume here that @code{recode} is run on Unix, where @w{Latin-1} is the --- 806,824 ---- relaxes its checking a tiny bit: it ignores the algorithmic part of some tabular recodings, it also avoids the processing of implied surfaces. But this is all fairly technical. Better try and see! Beware that other options might affect the produced source tables, these ! are: @samp{-d}, @samp{-g} and, particularly, @samp{-s}. @item -k @var{pairs} @itemx --known=@var{pairs} ! @opindex -k ! @opindex --known= ! @cindex unknown charsets ! @cindex guessing charsets ! @cindex charsets, guessing This particular option is meant to help identifying an unknown charset, using as hints some already identified characters of the charset. Some examples will help introducing the idea. Let's presume here that @code{recode} is run on Unix, where @w{Latin-1} is the *************** option @samp{-l}. As for option @samp{- *** 861,870 **** --- 920,933 ---- is interpreted as a charset name, possibly abbreviated to any non ambiguous prefix. @item -l[@var{format}] @itemx --list[=@var{format}] + @opindex -l + @opindex --list + @cindex listing charsets + @cindex information about charsets This option asks for information about all charsets, or about one particular charset. No file will be recoded. If there is no non-option arguments, @code{recode} ignores the @var{format} value of the option, it writes a sorted list of charset names on standard *************** is over two hundred lines. It is best u *** 877,897 **** recode -l | grep -i greek @end example There might be one non-option argument, in which case it is interpreted as a charset name, possibly abbreviated to any non ambiguous prefix. ! This particular usage of the @code{-l} option is obeyed @emph{only} for charsets having a tabular style internal description (@pxref{Tabular}). ! Even if most charsets have this property, some do not, then option ! @code{-l} cannot be used to detail these particular charsets. For knowing if a particular charset can be listed this way, you should merely try and see if this works. The @var{format} value of the option is a keyword from the following list. Keywords may be abbreviated by dropping suffix letters, and even reduced to the first letter only: @table @samp - @item decimal This format asks for the production on standard output of a concise tabular display of the charset, in which character code values are expressed in decimal. --- 940,959 ---- recode -l | grep -i greek @end example There might be one non-option argument, in which case it is interpreted as a charset name, possibly abbreviated to any non ambiguous prefix. ! This particular usage of the @samp{-l} option is obeyed @emph{only} for charsets having a tabular style internal description (@pxref{Tabular}). ! Even if most charsets have this property, some do not, and the option ! @samp{-l} cannot be used to detail these particular charsets. For knowing if a particular charset can be listed this way, you should merely try and see if this works. The @var{format} value of the option is a keyword from the following list. Keywords may be abbreviated by dropping suffix letters, and even reduced to the first letter only: @table @samp @item decimal This format asks for the production on standard output of a concise tabular display of the charset, in which character code values are expressed in decimal. *************** display of the charset. *** 907,938 **** This format requests an extensive display of the charset on standard output, using one line per character showing its decimal, hexadecimal, octal and @code{UCS-2} code values, and also a descriptive comment which should be the 10646 name for the character. The descriptive comment is given in English and ASCII, yet if the English description is not available but a French one is, then the French description is given instead, using @w{Latin-1}. However, if the @code{LANGUAGE} or @code{LANG} environment variable begins with the letters @samp{fr}, then listing preference goes to French when both descriptions are available. - @end table ! When option @code{-l} is used together with a @var{charset} argument, the @var{format} defaults to @code{decimal}. @item -T @itemx --find-subsets ! This option is a maintainer tool for evaluating the redundancy of those charsets, in @code{recode}, which are internally represented by an @code{UCS-2} data table. After the listing has been produced, the program exits ! without doing any recoding. The output of is meant to be sorted, like this: @w{@samp{recode -T | sort}}. The option triggers @code{recode} into comparing all pairs of charsets, seeking those which are subsets of others. The concept and results are better explained through a few examples. ! Consider these three sample lines from @code{-T} output: @example [ 0] IBM891 == IBM903 [ 1] IBM1004 < CP1252 [ 12] INVARIANT < CSA_Z243.4-1985-1 --- 969,1005 ---- This format requests an extensive display of the charset on standard output, using one line per character showing its decimal, hexadecimal, octal and @code{UCS-2} code values, and also a descriptive comment which should be the 10646 name for the character. + @vindex LANGUAGE@r{, when listing charsets} + @vindex LANG@r{, when listing charsets} + @cindex French description of charsets The descriptive comment is given in English and ASCII, yet if the English description is not available but a French one is, then the French description is given instead, using @w{Latin-1}. However, if the @code{LANGUAGE} or @code{LANG} environment variable begins with the letters @samp{fr}, then listing preference goes to French when both descriptions are available. @end table ! When option @samp{-l} is used together with a @var{charset} argument, the @var{format} defaults to @code{decimal}. @item -T @itemx --find-subsets ! @opindex -T ! @opindex --find-subsets ! @cindex identifying subsets in charsets ! @cindex subsets in charsets This option is a maintainer tool for evaluating the redundancy of those charsets, in @code{recode}, which are internally represented by an @code{UCS-2} data table. After the listing has been produced, the program exits ! without doing any recoding. The output is meant to be sorted, like this: @w{@samp{recode -T | sort}}. The option triggers @code{recode} into comparing all pairs of charsets, seeking those which are subsets of others. The concept and results are better explained through a few examples. ! Consider these three sample lines from @samp{-T} output: @example [ 0] IBM891 == IBM903 [ 1] IBM1004 < CP1252 [ 12] INVARIANT < CSA_Z243.4-1985-1 *************** contained within @code{CP1252}, yet ther *** 946,956 **** in @code{CP1252} without being in @code{IBM1004}. The third line says that @code{INVARIANT} is wholly contained within @code{CSA_Z243.4-1985-1}, but twelve characters are in @code{CSA_Z243.4-1985-1} without being in @code{INVARIANT}. The whole output might most probably be reduced and made more significant through a transitivity study. - @end table @node Recoding, Reversibility, Listings, Invoking recode @section Controlling how files are recoded --- 1013,1022 ---- *************** grain control over the recoding operatio *** 959,1039 **** @table @samp @item -c @itemx --colons With @code{Texte} Easy French conventions, use the column @kbd{:} instead of the double-quote @kbd{"} for marking diaeresis. @xref{Texte}. @item -g @itemx --graphics This option is only meaningful while getting @emph{out} of the @code{IBM-PC} charset. In this charset, characters 176 to 223 are used for constructing rulers and boxes, using simple or double horizontal or vertical lines. This option forces the automatic selection of ASCII characters for approximating these rulers and boxes, at cost of making ! the transformation irreversible. Option @code{-g} implies @code{-f}. @item -t @itemx --touch The @emph{touch} option is meaningful only when files are recoded over themselves. Without it, the time-stamps associated with files are preserved, to reflect the fact that changing the code of a file does not really alter its informational contents. When the user wants the recoded files to be time-stamped at the recoding time, this option inhibits the automatic protection of the time-stamps. @item -v @itemx --verbose ! Before doing any recoding, the program will first print on @file{stderr} ! the list of all intermediate charsets planned for recoding, starting with the @var{before} charset and ending with the @var{after} charset. It also prints an indication of the recoding quality, as one of the word @samp{reversible}, @samp{one to one}, @samp{one to many}, @samp{many to one} or @samp{many to many}. This information will appear once or twice. It is shown a second time only when the optimisation and step merging phase succeeds in replacing many single steps by a new one. This option also has a second effect. The program will print on ! @file{stderr} one message per @var{file} recoded, so to keep the user informed of the progress of its command. An easy way to know beforehand the sequence or quality of a recoding is by using the command such as: @example recode -v @var{before}..@var{after} < /dev/null @end example @noindent ! also using the fact that, in @code{recode}, an empty input file produces an empty output file. @item -x @var{charset} @itemx --ignore=@var{charset} This option tells the program to ignore any recoding path through the specified @var{charset}, so disabling any single step using this charset as a start or end point. This may be used when the user wants to force @code{recode} into using an alternate recoding path (yet using chained requests offers a finer control, @pxref{Requests}). @var{charset} may be abbreviated to any unambiguous prefix. - @end table @node Reversibility, Sequencing, Recoding, Invoking recode @section Reversibility issues The following options are somewhat related to reversibility issues: @table @samp - @item -f @itemx --force With this option, irreversible or otherwise erroneous recodings are run to completion, and @code{recode} does not exit with a non-zero status if it would be only because irreversibility matters. @xref{Reversibility}. Without this option, @code{recode} tries to protect you against recoding --- 1025,1128 ---- @table @samp @item -c @itemx --colons + @opindex -c + @opindex --colons + @cindex diaeresis With @code{Texte} Easy French conventions, use the column @kbd{:} instead of the double-quote @kbd{"} for marking diaeresis. @xref{Texte}. @item -g @itemx --graphics + @opindex -g + @opindex --graphics + @cindex IBM graphics characters + @cindex box-drawing characters This option is only meaningful while getting @emph{out} of the @code{IBM-PC} charset. In this charset, characters 176 to 223 are used for constructing rulers and boxes, using simple or double horizontal or vertical lines. This option forces the automatic selection of ASCII characters for approximating these rulers and boxes, at cost of making ! the transformation irreversible. Option @samp{-g} implies @samp{-f}. @item -t @itemx --touch + @opindex -t + @opindex --touch + @cindex time stamps of files + @cindex file time stamps The @emph{touch} option is meaningful only when files are recoded over themselves. Without it, the time-stamps associated with files are preserved, to reflect the fact that changing the code of a file does not really alter its informational contents. When the user wants the recoded files to be time-stamped at the recoding time, this option inhibits the automatic protection of the time-stamps. @item -v @itemx --verbose ! @opindex -v ! @opindex --verbose ! @cindex verbose operation ! @cindex details about recoding ! @cindex recoding details ! @cindex quality of recoding ! Before doing any recoding, the program will first print on the @code{stderr} ! stream the list of all intermediate charsets planned for recoding, starting with the @var{before} charset and ending with the @var{after} charset. It also prints an indication of the recoding quality, as one of the word @samp{reversible}, @samp{one to one}, @samp{one to many}, @samp{many to one} or @samp{many to many}. This information will appear once or twice. It is shown a second time only when the optimisation and step merging phase succeeds in replacing many single steps by a new one. This option also has a second effect. The program will print on ! @code{stderr} one message per recoded @var{file}, so as to keep the user informed of the progress of its command. An easy way to know beforehand the sequence or quality of a recoding is by using the command such as: @example recode -v @var{before}..@var{after} < /dev/null @end example @noindent ! using the fact that, in @code{recode}, an empty input file produces an empty output file. @item -x @var{charset} @itemx --ignore=@var{charset} + @opindex -x + @opindex --ignore + @cindex ignore charsets + @cindex recoding path, rejection This option tells the program to ignore any recoding path through the specified @var{charset}, so disabling any single step using this charset as a start or end point. This may be used when the user wants to force @code{recode} into using an alternate recoding path (yet using chained requests offers a finer control, @pxref{Requests}). @var{charset} may be abbreviated to any unambiguous prefix. @end table @node Reversibility, Sequencing, Recoding, Invoking recode @section Reversibility issues The following options are somewhat related to reversibility issues: @table @samp @item -f @itemx --force + @opindex -f + @opindex --force + @cindex force recoding + @cindex irreversible recoding With this option, irreversible or otherwise erroneous recodings are run to completion, and @code{recode} does not exit with a non-zero status if it would be only because irreversibility matters. @xref{Reversibility}. Without this option, @code{recode} tries to protect you against recoding *************** to start using @samp{-f} right away in s *** 1056,1099 **** whenever convenient, in preparation for the current behaviour. @item -q @itemx --quiet @itemx --silent This option has the sole purpose of inhibiting warning messages about irreversible recodings, and other such diagnostics. It has no other effect, in particular, it does @emph{not} prevent recodings to be aborted or @code{recode} to return a non-zero exit status when irreversible recodings are met. This option is set automatically for the children processes, when recode splits itself in many collaborating copies. Doing so, the diagnostic is ! issued only once by the parent. See option @code{-p}. @item -s @itemx --strict By using this option, the user requests that @code{recode} be very strict while recoding a file, merely losing in the transformation any character which is not explicitly mapped from a charset to another. Such a loss is not reversible and so, will bring @code{recode} to fail, unless the option ! @code{-f} is also given as a kind of counter-measure. ! Using @code{-s} without @code{-f} might render the @code{recode} program ! very susceptible to the slighest file abnormalities. Despite it might be irritating to some users, such paranoia is sometimes wanted and useful. - @end table ! Even if @code{recode} tries hard at keeping the recodings reversible, you should not develop an unconditional confidence in its ability to do so. You @emph{ought} to keep only reasonable expectations about reverse recodings. In particular, consider: @itemize @bullet - @item Most transformations are fully reversible for all inputs, but lose this ! property whenever @code{-s} is specified. @item A few transformations are not meant to be reversible, by design. @item --- 1145,1199 ---- whenever convenient, in preparation for the current behaviour. @item -q @itemx --quiet @itemx --silent + @opindex -q + @opindex --quiet + @opindex --silent + @cindex suppressing diagnostic messages + @cindex error messages, suppressing + @cindex silent operation This option has the sole purpose of inhibiting warning messages about irreversible recodings, and other such diagnostics. It has no other effect, in particular, it does @emph{not} prevent recodings to be aborted or @code{recode} to return a non-zero exit status when irreversible recodings are met. This option is set automatically for the children processes, when recode splits itself in many collaborating copies. Doing so, the diagnostic is ! issued only once by the parent. See option @samp{-p}. @item -s @itemx --strict + @opindex -s + @opindex --strict + @cindex strict operation + @cindex map filling, disable + @cindex disable map filling By using this option, the user requests that @code{recode} be very strict while recoding a file, merely losing in the transformation any character which is not explicitly mapped from a charset to another. Such a loss is not reversible and so, will bring @code{recode} to fail, unless the option ! @samp{-f} is also given as a kind of counter-measure. ! Using @samp{-s} without @samp{-f} might render the @code{recode} program ! very susceptible to the slighest file abnormalities. Despite the fact ! that it might be irritating to some users, such paranoia is sometimes wanted and useful. @end table ! @cindex reversibility of recoding ! Even if @code{recode} tries hard to keep the recodings reversible, you should not develop an unconditional confidence in its ability to do so. You @emph{ought} to keep only reasonable expectations about reverse recodings. In particular, consider: @itemize @bullet @item Most transformations are fully reversible for all inputs, but lose this ! property whenever @samp{-s} is specified. @item A few transformations are not meant to be reversible, by design. @item *************** then back. *** 1126,1139 **** There is another difficulty arising from code equivalences. For example, in a @code{LaTeX} charset file, the string @samp{\^\i@{@}} could be recoded back and forth through another charset and become @samp{\^@{\i@}}. Even if the resulting file is equivalent to the original one, it is not identical. - @end itemize ! Unless option @code{-s} is used, @code{recode} automatically tries to fill mappings with invented correspondences, often making them fully reversible. This filling is not made at random. The algorithm tries to stick to the identity mapping and, when this is not possible, it prefers generating many small permutation cycles, each involving only a few codes. --- 1226,1239 ---- There is another difficulty arising from code equivalences. For example, in a @code{LaTeX} charset file, the string @samp{\^\i@{@}} could be recoded back and forth through another charset and become @samp{\^@{\i@}}. Even if the resulting file is equivalent to the original one, it is not identical. @end itemize ! @cindex map filling ! Unless option @samp{-s} is used, @code{recode} automatically tries to fill mappings with invented correspondences, often making them fully reversible. This filling is not made at random. The algorithm tries to stick to the identity mapping and, when this is not possible, it prefers generating many small permutation cycles, each involving only a few codes. *************** within @code{IBM-PC}, which is 186 in @c *** 1147,1207 **** @code{recode} closes this short permutation loop. As a consequence of this map filling, @code{recode} may sometimes produce @emph{funny} characters. They may look annoying, they are nevertheless helpful when one changes his (her) mind and wants to revert to the prior ! recoding. If you cannot stand these, use option @code{-s}, which asks for a very strict recoding. This map filling sometimes has a few surprising consequences, which some users wrongly interpreted as bugs. Here are two examples. @enumerate @item In some cases, @code{recode} seems to copy a file without recoding it. ! But in fact, it does. Consider you requested: @example recode l1..us < File-Latin1 > File-ASCII cmp File-Latin1 File-ASCII @end example @noindent then @code{cmp} will not report any difference. This is quite normal. ! @w{Latin-1} gets correctly recoded to ASCII for charsets commonalities (which are the first 128 characters, in this case). The remaining last ! 128 @w{Latin-1} characters have no ASCII correspondent. Instead of losing ! them, recode elects to map them to unspecified characters of ASCII, so making the recoding reversible. The simplest way of achieving this is merely to keep those last 128 characters unchanged. The overall effect is copying the file verbatim. If you feel this behaviour is too generous and if you do not wish to ! care about reversibility, simply use option @code{-s}. By doing so, ! @code{recode} will strictly map only those @w{Latin-1} characters which have an ASCII equivalent, and will merely drop those which do not. Then, there is more chance that you will observe a difference between the input and the output file. @item Recoding the wrong way could sometimes give the false impression that ! recoding has @emph{almost} been done properly. Consider you request: @example recode 437..l1 < File-Latin1 > Temp1 recode 437..l1 < Temp1 > Temp2 @end example @noindent so declaring wrongly @file{File-Latin1} to be an IBM-PC file, and ! recoding to Latin1. This is surely ill defined and not meaningful. Yet, if you repeat this step a second time, you might notice that many (not all) characters in @file{Temp2} are identical to those in ! @file{File-Latin1}. A few people try to discover how @code{recode} works by experimenting a little at random, rather than reading and ! understanding the documentation; such results are surely confusing, ! as they provide a feel to those people that they understood something. Reversible codings have this property that, if applied several times in the same direction, they will eventually bring any character back to its original value. Since @code{recode} seeks small permutation cycles when creating reversible codings, besides characters unchanged --- 1247,1310 ---- @code{recode} closes this short permutation loop. As a consequence of this map filling, @code{recode} may sometimes produce @emph{funny} characters. They may look annoying, they are nevertheless helpful when one changes his (her) mind and wants to revert to the prior ! recoding. If you cannot stand these, use option @samp{-s}, which asks for a very strict recoding. This map filling sometimes has a few surprising consequences, which some users wrongly interpreted as bugs. Here are two examples. @enumerate @item In some cases, @code{recode} seems to copy a file without recoding it. ! But in fact, it does. Consider a request: @example recode l1..us < File-Latin1 > File-ASCII cmp File-Latin1 File-ASCII @end example @noindent then @code{cmp} will not report any difference. This is quite normal. ! @w{@code{Latin-1}} gets correctly recoded to ASCII for charsets commonalities (which are the first 128 characters, in this case). The remaining last ! 128 @w{@code{Latin-1}} characters have no ASCII correspondent. Instead ! of losing ! them, @code{recode} elects to map them to unspecified characters of ASCII, so making the recoding reversible. The simplest way of achieving this is merely to keep those last 128 characters unchanged. The overall effect is copying the file verbatim. If you feel this behaviour is too generous and if you do not wish to ! care about reversibility, simply use option @samp{-s}. By doing so, ! @code{recode} will strictly map only those @w{@code{Latin-1}} characters ! which have an ASCII equivalent, and will merely drop those which do not. Then, there is more chance that you will observe a difference between the input and the output file. @item Recoding the wrong way could sometimes give the false impression that ! recoding has @emph{almost} been done properly. Consider the requests: @example recode 437..l1 < File-Latin1 > Temp1 recode 437..l1 < Temp1 > Temp2 @end example @noindent so declaring wrongly @file{File-Latin1} to be an IBM-PC file, and ! recoding to @code{Latin-1}. This is surely ill defined and not meaningful. Yet, if you repeat this step a second time, you might notice that many (not all) characters in @file{Temp2} are identical to those in ! @file{File-Latin1}. Sometimes, people try to discover how @code{recode} works by experimenting a little at random, rather than reading and ! understanding the documentation; results such as this are surely confusing, ! as they provide those people with a false feeling that they understood ! something. Reversible codings have this property that, if applied several times in the same direction, they will eventually bring any character back to its original value. Since @code{recode} seeks small permutation cycles when creating reversible codings, besides characters unchanged *************** by the recoding, most permutation cycles *** 1209,1224 **** fewer of length 3, etc. So, it is just expectable that applying the recoding twice in the same direction will recover most characters, but will fail to recover those participating in permutation cycles of length 3. On the other end, recoding six times in the same direction would recover all characters in cycles of length 1, 2, 3 or 6. - @end enumerate @node Sequencing, Mixed, Reversibility, Invoking recode @section Selecting sequencing methods This program uses a few techniques when it is discovered that many passes are needed to comply with the @var{request}. For example, suppose that four elementary steps were selected at recoding path optimisation time. Then @code{recode} will split itself into four different interconnected tasks, logically equivalent to: --- 1312,1327 ---- fewer of length 3, etc. So, it is just expectable that applying the recoding twice in the same direction will recover most characters, but will fail to recover those participating in permutation cycles of length 3. On the other end, recoding six times in the same direction would recover all characters in cycles of length 1, 2, 3 or 6. @end enumerate @node Sequencing, Mixed, Reversibility, Invoking recode @section Selecting sequencing methods + @cindex sequencing This program uses a few techniques when it is discovered that many passes are needed to comply with the @var{request}. For example, suppose that four elementary steps were selected at recoding path optimisation time. Then @code{recode} will split itself into four different interconnected tasks, logically equivalent to: *************** simulated by using memory buffer, or int *** 1234,1285 **** methods, by replacing @var{strategy} with @samp{memory}, @samp{pipe} or @samp{files}. So, these options may be used to override the default behaviour, which is also explained below. @table @samp - @item --sequence=memory When the recoding requires a combination of two or more elementary recoding steps, this option forces many passes over the data, using in-memory buffers to hold all intermediary results. @c This should be the default behaviour when @c files to be recoded are @emph{small} enough. @item -i @itemx --sequence=files When the recoding requires a combination of two or more elementary recoding steps, this option forces many passes over the data, using intermediate files between passes. This is the default behaviour when files are recoded over themselves. If this option is selected in filter mode, that is, when the program reads standard input and writes standard output, it might take longer for programs further down the pipe chain to start receiving some recoded data. @item -p @itemx --sequence=pipe When the recoding requires a combination of two or more elementary recoding steps, this option forces the program to fork itself into a few copies interconnected with pipes, using the @code{pipe(2)} system call. All copies of the program operate in parallel. This is the default behaviour in filter mode. If this option is used when files are recoded over themselves, this should also save disk space because some temporary ! files might not be needed, at cost of more system overhead. If, at installation time, the @code{pipe(2)} call is said to be ! unavailable, selecting option @code{-p} is equivalent to selecting ! option @code{-i}. ! @end table @node Mixed, Emacs, Sequencing, Invoking recode @section Using mixed charset input In real life and practice, textual files are often made up of many charsets at once. Some parts of the file encode one charset, while other parts encode another charset, and so forth. Usually, a file does not toggle between more than two or three charsets. The means to distinguish ! which charsets are encoded at various places is not always easy. The @code{recode} program is able to handle only a few simple cases of mixed input. The default @code{recode} behaviour is to expect pure charset files, to be recoded as other pure charset files. However, the following options --- 1337,1392 ---- methods, by replacing @var{strategy} with @samp{memory}, @samp{pipe} or @samp{files}. So, these options may be used to override the default behaviour, which is also explained below. @table @samp @item --sequence=memory + @opindex --sequence + @cindex memory sequencing When the recoding requires a combination of two or more elementary recoding steps, this option forces many passes over the data, using in-memory buffers to hold all intermediary results. @c This should be the default behaviour when @c files to be recoded are @emph{small} enough. @item -i @itemx --sequence=files + @opindex -i + @cindex file sequencing When the recoding requires a combination of two or more elementary recoding steps, this option forces many passes over the data, using intermediate files between passes. This is the default behaviour when files are recoded over themselves. If this option is selected in filter mode, that is, when the program reads standard input and writes standard output, it might take longer for programs further down the pipe chain to start receiving some recoded data. @item -p @itemx --sequence=pipe + @opindex -p + @cindex pipe sequencing When the recoding requires a combination of two or more elementary recoding steps, this option forces the program to fork itself into a few copies interconnected with pipes, using the @code{pipe(2)} system call. All copies of the program operate in parallel. This is the default behaviour in filter mode. If this option is used when files are recoded over themselves, this should also save disk space because some temporary ! files might not be needed, at the cost of more system overhead. If, at installation time, the @code{pipe(2)} call is said to be ! unavailable, selecting option @samp{-p} is equivalent to selecting ! option @samp{-i}. (This happens, for example, on MS-DOS systems.) @end table @node Mixed, Emacs, Sequencing, Invoking recode @section Using mixed charset input In real life and practice, textual files are often made up of many charsets at once. Some parts of the file encode one charset, while other parts encode another charset, and so forth. Usually, a file does not toggle between more than two or three charsets. The means to distinguish ! which charsets are encoded at various places is not always available. The @code{recode} program is able to handle only a few simple cases of mixed input. The default @code{recode} behaviour is to expect pure charset files, to be recoded as other pure charset files. However, the following options *************** phenomena. The transliteration which yo *** 1314,1326 **** '[' character in @w{Latin-1}, for example, be transliterated to A-umlaut in `fi', which is a bit non-meaningful. Remember, there is no `[' in `fi'. @end ignore @table @samp - @item -d @itemx --diacritics While converting to or from one of @code{HTML} or @code{LaTeX} charset, limit conversion to some subset of all characters. For @code{HTML}, limit conversion to the subset of all non-ASCII characters. For @code{LaTeX}, limit conversion to the subset of all non-English letters. This is particularly useful, for example, when --- 1421,1436 ---- '[' character in @w{Latin-1}, for example, be transliterated to A-umlaut in `fi', which is a bit non-meaningful. Remember, there is no `[' in `fi'. @end ignore @table @samp @item -d @itemx --diacritics + @opindex -d + @opindex --diacritics + @cindex convert a subset of characters + @cindex partial conversion While converting to or from one of @code{HTML} or @code{LaTeX} charset, limit conversion to some subset of all characters. For @code{HTML}, limit conversion to the subset of all non-ASCII characters. For @code{LaTeX}, limit conversion to the subset of all non-English letters. This is particularly useful, for example, when *************** coded or protected versions of character *** 1337,1357 **** @xref{HTML}. @xref{LaTeX}. @ignore @item -M @itemx --message ! Option -M would be for messages, it would ideally process @w{RFC 1522} inserts in ASCII headers, converting them to the goal code, rewriting some MIME header line too, and stopping its special work at the first empty line. A special combination of both capabilities would be for the recoding of PO files, in which the header, and @code{msgid} and @code{msgstr} strings, might all use different charsets. Recoding some PO files currently looks like a nightmare, which I would like @code{recode} to repair. @end ignore @item -S[@var{language}] @itemx --source[=@var{language}] The bulk of the input file is expected to be written in @code{ASCII}, except for parts, like comments and string constants, which are written using another charset than @code{ASCII}. When @var{language} is @samp{c}, the recoding will proceed only with the contents of comments or strings, while everything else will be copied without recoding. When @var{language} --- 1447,1474 ---- @xref{HTML}. @xref{LaTeX}. @ignore @item -M @itemx --message ! @opindex -M ! @opindex --message ! Option @samp{-M} would be for messages, it would ideally process @w{RFC ! 1522} inserts in ASCII headers, converting them to the goal code, rewriting some MIME header line too, and stopping its special work at the first empty line. A special combination of both capabilities would be for the recoding of PO files, in which the header, and @code{msgid} and @code{msgstr} strings, might all use different charsets. Recoding some PO files currently looks like a nightmare, which I would like @code{recode} to repair. @end ignore @item -S[@var{language}] @itemx --source[=@var{language}] + @opindex -S + @opindex --source + @cindex convert strings and comments + @cindex string and comments conversion The bulk of the input file is expected to be written in @code{ASCII}, except for parts, like comments and string constants, which are written using another charset than @code{ASCII}. When @var{language} is @samp{c}, the recoding will proceed only with the contents of comments or strings, while everything else will be copied without recoding. When @var{language} *************** and with the contents of @code{msgstr} s *** 1362,1372 **** For the above things to work, the non-@code{ASCII} encoding of the comment or string should be such that an @code{ASCII} scan will successfully find where the comment or string ends. Even if @code{ASCII} is the usual charset for writing programs, some ! compilers are able to directly read other charsets, like @code{UTF-8} say. There is currently no provision in @code{recode} for reading mixed charset sources which are not based on @code{ASCII}. It is probable that the need for mixed recoding is not as pressing in such cases. For example, after one does: --- 1479,1489 ---- For the above things to work, the non-@code{ASCII} encoding of the comment or string should be such that an @code{ASCII} scan will successfully find where the comment or string ends. Even if @code{ASCII} is the usual charset for writing programs, some ! compilers are able to directly read other charsets, like @code{UTF-8}, say. There is currently no provision in @code{recode} for reading mixed charset sources which are not based on @code{ASCII}. It is probable that the need for mixed recoding is not as pressing in such cases. For example, after one does: *************** For example, after one does: *** 1375,1411 **** recode -Spo pc/..u8 < @var{input}.po > @var{output}.po @end example @noindent file @file{@var{output}.po} holds a copy of @file{@var{input}.po} in which ! translator comments and the contents of @code{msgstr} strings @emph{only} have been recoded from the @code{IBM-PC} charset to pure @code{UTF-8}, without attempting conversion of end-of-lines. Machine generated comments and original @code{msgid} strings are not to be touched by this recoding. If @var{language} is not specified, @samp{c} is assumed. - @end table @node Emacs, , Mixed, Invoking recode @section Using @code{recode} within Emacs The fact @code{recode} is a filter makes it quite easy to use from within GNU Emacs. For example, recoding the whole buffer from ! the IBM-PC charset to current charset (@w{Latin-1} on Unix) is easily ! done with: @example C-x h C-u M-| recode ibmpc RET @end example @noindent ! The @samp{C-x h} selects the whole buffer, and @samp{C-u M-|} filters and replaces the current region through the given shell command. Here is another example, binding the keys @w{@samp{C-c T}} to the recoding of ! the current region from Easy French to @w{Latin-1} (on Unix) and the key ! @w{@samp{C-u C-c T}} from @w{Latin-1} (on Unix) to Easy French: @example (global-set-key "\C-cT" 'recode-texte) (defun recode-texte (flag) --- 1492,1527 ---- recode -Spo pc/..u8 < @var{input}.po > @var{output}.po @end example @noindent file @file{@var{output}.po} holds a copy of @file{@var{input}.po} in which ! @emph{only} translator comments and the contents of @code{msgstr} strings have been recoded from the @code{IBM-PC} charset to pure @code{UTF-8}, without attempting conversion of end-of-lines. Machine generated comments and original @code{msgid} strings are not to be touched by this recoding. If @var{language} is not specified, @samp{c} is assumed. @end table @node Emacs, , Mixed, Invoking recode @section Using @code{recode} within Emacs The fact @code{recode} is a filter makes it quite easy to use from within GNU Emacs. For example, recoding the whole buffer from ! the @code{IBM-PC} charset to current charset (@w{@code{Latin-1}} on ! Unix) is easily done with: @example C-x h C-u M-| recode ibmpc RET @end example @noindent ! @samp{C-x h} selects the whole buffer, and @samp{C-u M-|} filters and replaces the current region through the given shell command. Here is another example, binding the keys @w{@samp{C-c T}} to the recoding of ! the current region from Easy French to @w{@code{Latin-1}} (on Unix) and the key ! @w{@samp{C-u C-c T}} from @w{@code{Latin-1}} (on Unix) to Easy French: @example (global-set-key "\C-cT" 'recode-texte) (defun recode-texte (flag) *************** the current region from Easy French to @ *** 1417,1426 **** --- 1533,1543 ---- @end example @node Library, Universal, Invoking recode, Top @chapter A recoding library + @cindex recoding library The program named @code{recode} is just an application of its recoding library. The recoding library is available separately for other C programs. A good way to acquire some familiarity with the recoding library is to get acquainted with the @code{recode} program itself. *************** at outer level, and then, various functi *** 1453,1462 **** --- 1570,1580 ---- @end menu @node Outer level, Request level, Library, Library @section Outer level functions + @cindex outer level functions The outer level functions mainly prepare the whole recoding library for use, or do actions which are unrelated to specific recodings. Here is an example of a program which does not really make anything useful. @example *************** main () *** 1473,1493 **** exit (0); @} @end group @end example ! The header file @file{} declares an opaque @code{RECODE_OUTER} structure, which the programmer should use for allocating a variable in his program (let's assume the programmer is a male, here, no prejudice intended). This @samp{outer} variable is given as a first argument to all outer level functions. ! The @file{} header file uses the Boolean type setup by the ! system header file @file{}. But this header file is still fairly new in C standards, and likely does not exist everywhere. If you system does not offer this system header file yet, the proper compilation ! of the @file{} file could be guaranteed through the replacement of the inclusion line by: @example typedef enum @{false = 0, true = 1@} bool; @end example --- 1591,1614 ---- exit (0); @} @end group @end example ! @vindex RECODE_OUTER structure ! The header file @code{} declares an opaque @code{RECODE_OUTER} structure, which the programmer should use for allocating a variable in his program (let's assume the programmer is a male, here, no prejudice intended). This @samp{outer} variable is given as a first argument to all outer level functions. ! @cindex @code{stdbool.h} header ! @cindex @code{bool} data type ! The @code{} header file uses the Boolean type setup by the ! system header file @code{}. But this header file is still fairly new in C standards, and likely does not exist everywhere. If you system does not offer this system header file yet, the proper compilation ! of the @code{} file could be guaranteed through the replacement of the inclusion line by: @example typedef enum @{false = 0, true = 1@} bool; @end example *************** main () *** 1537,1552 **** --- 1658,1676 ---- @noindent but we will not insist on such details in the examples to come. @itemize @bullet @item Initialisation functions + @cindex initialisation functions, outer @example RECODE_OUTER recode_new_outer (@var{auto_abort}); bool recode_delete_outer (@var{outer}); @end example + @findex recode_new_outer + @findex recode_delete_outer The recoding library absolutely needs to be initialised before being used, and @code{recode_new_outer} has to be called once, first. Besides the @var{outer} it is meant to initialise, the function accepts a Boolean argument whether or not the library should automatically issue diagnostics on standard and abort the whole program on errors. When @var{auto_abort} *************** calling it more than once should prefera *** 1571,1586 **** The termination function @code{recode_delete_outer} reclaims the memory allocated by @code{recode_new_outer} for a given @var{outer} variable. Calling @code{recode_delete_outer} prior to program termination is more aesthetic then useful, as all memory resources are automatically reclaimed when the program ends. You may spare this terminating call if you prefer. - @end itemize @node Request level, Task level, Outer level, Library @section Request level functions The request level functions are meant to cover most recoding needs programmers may have; they should provide all usual functionality. Their API is almost stable by now. To get started with request level functions, here is a full example of a program which sole job is to filter @code{ibmpc} code on its standard input into @code{latin1} code on its --- 1695,1710 ---- The termination function @code{recode_delete_outer} reclaims the memory allocated by @code{recode_new_outer} for a given @var{outer} variable. Calling @code{recode_delete_outer} prior to program termination is more aesthetic then useful, as all memory resources are automatically reclaimed when the program ends. You may spare this terminating call if you prefer. @end itemize @node Request level, Task level, Outer level, Library @section Request level functions + @cindex request level functions The request level functions are meant to cover most recoding needs programmers may have; they should provide all usual functionality. Their API is almost stable by now. To get started with request level functions, here is a full example of a program which sole job is to filter @code{ibmpc} code on its standard input into @code{latin1} code on its *************** main () *** 1609,1631 **** exit (success ? 0 : 1); @} @end group @end example ! The header file @file{} declares a @code{RECODE_REQUEST} structure, which the programmer should use for allocating a variable in his program. This @var{request} variable is given as a first argument to all request level functions, and in most cases, may be considered as opaque. @itemize @bullet @item Initialisation functions @example RECODE_REQUEST recode_new_request (@var{outer}); bool recode_delete_request (@var{request}); @end example No @var{request} variable may not be used in other request level functions of the recoding library before having been initialised by @code{recode_new_request}. There may be many such @var{request} variables, in which case, they are independent of one another and they all need to be initialised separately. To avoid memory leaks, a --- 1733,1759 ---- exit (success ? 0 : 1); @} @end group @end example ! @vindex RECODE_REQUEST structure ! The header file @code{} declares a @code{RECODE_REQUEST} structure, which the programmer should use for allocating a variable in his program. This @var{request} variable is given as a first argument to all request level functions, and in most cases, may be considered as opaque. @itemize @bullet @item Initialisation functions + @cindex initialisation functions, request @example RECODE_REQUEST recode_new_request (@var{outer}); bool recode_delete_request (@var{request}); @end example + @findex recode_new_request + @findex recode_delete_request No @var{request} variable may not be used in other request level functions of the recoding library before having been initialised by @code{recode_new_request}. There may be many such @var{request} variables, in which case, they are independent of one another and they all need to be initialised separately. To avoid memory leaks, a *************** calling @code{recode_delete_request} to *** 1634,1700 **** Like for @code{recode_delete_outer}, calling @code{recode_delete_request} prior to program termination, in the example above, may be left out. @item Fields of @code{struct recode_request} Here are the fields of a @code{struct recode_request} which may be meaningfully changed, once a @var{request} has been initialised by @code{recode_new_request}, but before it gets used. It is not very frequent, in practice, that these fields need to be changed. To access the fields, you need to include @file{recodext.h} @emph{instead} of @file{recode.h}, in which case there also is a greater chance that you need to recompile your programs if a new version of the recoding library gets installed. @table @code - @item verbose_flag This field is initially @code{false}. When set to @code{true}, the library will echo to stderr the sequence of elementary recoding steps needed to achieve the requested recoding. @item diaeresis_char This field is initially the ASCII value of a double quote @kbd{"}, but it may also be the ASCII value of a colon @kbd{:}. In @code{texte} charset, some countries use double quotes to mark diaeresis, while other countries prefer colons. This field contains the diaeresis character for the @code{texte} charset. @item make_header_flag This field is initially @code{false}. When set to @code{true}, it indicates that the program is merely trying to produce a recoding table in source form rather than completing any actual recoding. In such a case, the optimisation of step sequence can be attempted much more aggressively. If the step sequence cannot be reduced to a single step, table production will fail. @item diacritics_only This field is initially @code{false}. For @code{HTML} and @code{LaTeX} charset, it is often convenient to recode the diacriticized characters only, while just not recoding other HTML code using ampersands or angular brackets, or La@TeX{} code using backslashes. Set the field to @code{true} for getting this behaviour. In the other charset, one can edit text as well as HTML or La@TeX{} directives. @item ascii_graphics This field is initially @code{false}, and relate to characters 176 to 223 in the @code{ibmpc} charset, which are use to draw boxes. When set to @code{true}, while getting out of @code{ibmpc}, ASCII characters are selected so to graphically approximate these boxes. - @end table @item Study of request strings @example bool recode_scan_request (@var{request}, "@var{string}"); @end example The main role of a @var{request} variable is to describe a set of recoding transformations. Function @code{recode_scan_request} studies the given @var{string}, and stores an internal representation of it into ! @var{request}. Note that @var{string} may be a full-fledge @code{recode} request, possibly including surfaces specifications, intermediary charsets, sequences, aliases or abbreviations (@pxref{Requests}). The internal representation automatically receives some pre-conditioning and optimisation, so the @var{request} may then later be used many times --- 1762,1833 ---- Like for @code{recode_delete_outer}, calling @code{recode_delete_request} prior to program termination, in the example above, may be left out. @item Fields of @code{struct recode_request} + @vindex recode_request structure Here are the fields of a @code{struct recode_request} which may be meaningfully changed, once a @var{request} has been initialised by @code{recode_new_request}, but before it gets used. It is not very frequent, in practice, that these fields need to be changed. To access the fields, you need to include @file{recodext.h} @emph{instead} of @file{recode.h}, in which case there also is a greater chance that you need to recompile your programs if a new version of the recoding library gets installed. @table @code @item verbose_flag + @vindex verbose_flag This field is initially @code{false}. When set to @code{true}, the library will echo to stderr the sequence of elementary recoding steps needed to achieve the requested recoding. @item diaeresis_char + @vindex diaeresis_char This field is initially the ASCII value of a double quote @kbd{"}, but it may also be the ASCII value of a colon @kbd{:}. In @code{texte} charset, some countries use double quotes to mark diaeresis, while other countries prefer colons. This field contains the diaeresis character for the @code{texte} charset. @item make_header_flag + @vindex make_header_flag This field is initially @code{false}. When set to @code{true}, it indicates that the program is merely trying to produce a recoding table in source form rather than completing any actual recoding. In such a case, the optimisation of step sequence can be attempted much more aggressively. If the step sequence cannot be reduced to a single step, table production will fail. @item diacritics_only + @vindex diacritics_only This field is initially @code{false}. For @code{HTML} and @code{LaTeX} charset, it is often convenient to recode the diacriticized characters only, while just not recoding other HTML code using ampersands or angular brackets, or La@TeX{} code using backslashes. Set the field to @code{true} for getting this behaviour. In the other charset, one can edit text as well as HTML or La@TeX{} directives. @item ascii_graphics + @vindex ascii_graphics This field is initially @code{false}, and relate to characters 176 to 223 in the @code{ibmpc} charset, which are use to draw boxes. When set to @code{true}, while getting out of @code{ibmpc}, ASCII characters are selected so to graphically approximate these boxes. @end table @item Study of request strings @example bool recode_scan_request (@var{request}, "@var{string}"); @end example + @findex recode_scan_request The main role of a @var{request} variable is to describe a set of recoding transformations. Function @code{recode_scan_request} studies the given @var{string}, and stores an internal representation of it into ! @var{request}. Note that @var{string} may be a full-fledged @code{recode} request, possibly including surfaces specifications, intermediary charsets, sequences, aliases or abbreviations (@pxref{Requests}). The internal representation automatically receives some pre-conditioning and optimisation, so the @var{request} may then later be used many times *************** principles and is discussed separately, *** 1718,1734 **** --- 1851,1874 ---- @example recode_string (@var{request}, @var{string}); @end example + @findex recode_string The function @code{recode_string} recodes @var{string} according to @var{request}, and directly returns the resulting recoded string freshly allocated, or @code{NULL} if the recoding could not succeed for some reason. When this function is used, it is the responsibility of the programmer to ensure that the memory used by the returned string is later reclaimed. + @findex recode_string_to_buffer + @findex recode_string_to_file + @findex recode_buffer_to_buffer + @findex recode_buffer_to_file + @findex recode_file_to_buffer + @findex recode_file_to_file @example char *recode_string_to_buffer (@var{request}, @var{input_string}, &@var{output_buffer}, &@var{output_length}, &@var{output_allocated}); bool recode_string_to_file (@var{request}, *************** is guaranteed at the end of the produced *** 1789,1798 **** --- 1929,1940 ---- byte size of the recoding. Beyond that @code{NUL}, there might be some extra space after the recoded data, extending to the allocated buffer size. @item file + @findex recode_filter_open@r{, not available} + @findex recode_filter_close@r{, not available} A file is a sequence of bytes held outside computer memory, but buffered through it. For input, one argument provides a pointer to a file already opened for read. The file is then read and recoded from its current position until the end of the file, effectively swallowing it in memory if the destination of the recoding is a buffer. For reading a file *************** should rather use @code{recode_filter_op *** 1801,1815 **** (these two functions are not yet available). For output, one argument provides a pointer to a file already opened for write. The result of the recoding is written to that file starting at its current position. - @end table - @end itemize The following special function is still subject to change: @example void recode_format_table (@var{request}, @var{language}, "@var{name}"); @end example --- 1943,1956 ---- (these two functions are not yet available). For output, one argument provides a pointer to a file already opened for write. The result of the recoding is written to that file starting at its current position. @end table @end itemize + @findex recode_format_table The following special function is still subject to change: @example void recode_format_table (@var{request}, @var{language}, "@var{name}"); @end example *************** void recode_format_table (@var{request}, *** 1817,1826 **** --- 1958,1968 ---- @noindent and is not documented anymore for now. @node Task level, Charset level, Request level, Library @section Task level functions + @cindex task level functions The task level functions are used internally by the request level functions, they allow more explicit control over files and memory buffers holding input and output to recoding processes. The interface specification of task level functions is still subject to change a bit. *************** main () *** 1859,1878 **** exit (success ? 0 : 1); @} @end group @end example ! The header file @file{} declares a @code{RECODE_TASK} structure, which the programmer should use for allocating a variable in ! his program. This @samp{task} variable is given as a first argument to all task level functions. The programmer ought to change and possibly consult a few fields in this structure, using special functions. @itemize @bullet - @item Initialisation functions @example RECODE_TASK recode_new_task (@var{request}); bool recode_delete_task (@var{task}); @end example --- 2001,2023 ---- exit (success ? 0 : 1); @} @end group @end example ! @vindex RECODE_TASK structure ! The header file @code{} declares a @code{RECODE_TASK} structure, which the programmer should use for allocating a variable in ! his program. This @code{task} variable is given as a first argument to all task level functions. The programmer ought to change and possibly consult a few fields in this structure, using special functions. @itemize @bullet @item Initialisation functions + @cindex initialisation functions, task + @findex recode_new_task + @findex recode_delete_task @example RECODE_TASK recode_new_task (@var{request}); bool recode_delete_task (@var{task}); @end example *************** as needed, by various task processors. *** 1897,1916 **** Even if a call to @code{recode_delete_task} is not strictly mandatory before ending the program, it is cleaner to always include it. Moreover, in some future version of the recoding library, it might become required. @item Fields of @code{struct task_request} Here are the fields of a @code{struct task_request} which may be meaningfully changed, once a @var{task} has been initialised by @code{recode_new_task}. In fact, fields are expected to change. Once again, to access the fields, you need to include @file{recodext.h} @emph{instead} of @file{recode.h}, in which case there also is a greater chance that you need to recompile your programs if a new version of the recoding library gets installed. @table @code - @item request The field @code{request} points to the current recoding request, but may be changed as needed between recoding calls, for example when there is a need to achieve the construction of a resulting text made up of many --- 2042,2061 ---- Even if a call to @code{recode_delete_task} is not strictly mandatory before ending the program, it is cleaner to always include it. Moreover, in some future version of the recoding library, it might become required. @item Fields of @code{struct task_request} + @vindex task_request structure Here are the fields of a @code{struct task_request} which may be meaningfully changed, once a @var{task} has been initialised by @code{recode_new_task}. In fact, fields are expected to change. Once again, to access the fields, you need to include @file{recodext.h} @emph{instead} of @file{recode.h}, in which case there also is a greater chance that you need to recompile your programs if a new version of the recoding library gets installed. @table @code @item request The field @code{request} points to the current recoding request, but may be changed as needed between recoding calls, for example when there is a need to achieve the construction of a resulting text made up of many *************** held up-to-date in @code{output.buffer}. *** 1977,2038 **** task level function with no output buffer at all to start with, in which case all three fields should have @code{NULL} as a value. This is the situation immediately after a call to @code{recode_new_task}. @item strategy This field, which is of type @code{enum recode_sequence_strategy}, tells how various recoding steps (passes) will be interconnected. Its initial value is @code{RECODE_STRATEGY_UNDECIDED}, which is a constant defined in the header file @file{}. Other possible values are: @table @code @item RECODE_SEQUENCE_IN_MEMORY Keep intermediate recodings in memory. @item RECODE_SEQUENCE_WITH_FILES Do not fork, use intermediate files. @item RECODE_SEQUENCE_WITH_PIPE Fork processes connected with @code{pipe(2)}. @end table @c FIXME The best for now is to leave this field alone, and let the recoding library decide its strategy, as many combinations have not been tested yet. @item byte_order_mark This field, which is preset to @code{true}, indicates that a byte order mark is to be expected at the beginning of any canonical @code{UCS-2} or @code{UTF-16} text, and that such a byte order mark should be also produced for these charsets. @item fail_level This field, which is of type @code{enum recode_error} (@pxref{Errors}), sets the error level at which task level functions should report a failure. If an error being detected is equal or greater than @code{fail_level}, the function will eventually return @code{false} instead of @code{true}. The preset value for this field is @code{RECODE_NOT_CANONICAL}, that means that if not reset to another value, the library will report failure on @emph{any} error. @item abort_level This field, which is of type @code{enum recode_error} (@pxref{Errors}), sets the error level at which task level functions should immediately interrupt their processing. If an error being detected is equal or greater than @code{abort_level}, the function returns immediately, but the returned value (@code{true} or @code{false}) is still is decided from the setting of @code{fail_level}, not @code{abort_level}. The preset value for this field is @code{RECODE_MAXIMUM_ERROR}, that means that is not reset to another value, the library will never interrupt a recoding task. @item error_so_far This field, which is of type @code{enum recode_error} (@pxref{Errors}), maintains the maximum error level met so far while the recoding task was proceeding. The preset value is @code{RECODE_NO_ERROR}. - @end table @item Task execution @example recode_perform_task (@var{task}); recode_filter_open (@var{task}, @var{file}); recode_filter_close (@var{task}); @end example --- 2122,2196 ---- task level function with no output buffer at all to start with, in which case all three fields should have @code{NULL} as a value. This is the situation immediately after a call to @code{recode_new_task}. @item strategy + @vindex strategy + @vindex RECODE_STRATEGY_UNDECIDED This field, which is of type @code{enum recode_sequence_strategy}, tells how various recoding steps (passes) will be interconnected. Its initial value is @code{RECODE_STRATEGY_UNDECIDED}, which is a constant defined in the header file @file{}. Other possible values are: @table @code @item RECODE_SEQUENCE_IN_MEMORY + @vindex RECODE_SEQUENCE_IN_MEMORY Keep intermediate recodings in memory. @item RECODE_SEQUENCE_WITH_FILES + @vindex RECODE_SEQUENCE_WITH_FILES Do not fork, use intermediate files. @item RECODE_SEQUENCE_WITH_PIPE + @vindex RECODE_SEQUENCE_WITH_PIPE Fork processes connected with @code{pipe(2)}. @end table @c FIXME The best for now is to leave this field alone, and let the recoding library decide its strategy, as many combinations have not been tested yet. @item byte_order_mark + @vindex byte_order_mark This field, which is preset to @code{true}, indicates that a byte order mark is to be expected at the beginning of any canonical @code{UCS-2} or @code{UTF-16} text, and that such a byte order mark should be also produced for these charsets. @item fail_level + @vindex fail_level This field, which is of type @code{enum recode_error} (@pxref{Errors}), sets the error level at which task level functions should report a failure. If an error being detected is equal or greater than @code{fail_level}, the function will eventually return @code{false} instead of @code{true}. The preset value for this field is @code{RECODE_NOT_CANONICAL}, that means that if not reset to another value, the library will report failure on @emph{any} error. @item abort_level + @vindex abort_level + @vindex RECODE_MAXIMUM_ERROR This field, which is of type @code{enum recode_error} (@pxref{Errors}), sets the error level at which task level functions should immediately interrupt their processing. If an error being detected is equal or greater than @code{abort_level}, the function returns immediately, but the returned value (@code{true} or @code{false}) is still is decided from the setting of @code{fail_level}, not @code{abort_level}. The preset value for this field is @code{RECODE_MAXIMUM_ERROR}, that means that is not reset to another value, the library will never interrupt a recoding task. @item error_so_far + @vindex error_so_far This field, which is of type @code{enum recode_error} (@pxref{Errors}), maintains the maximum error level met so far while the recoding task was proceeding. The preset value is @code{RECODE_NO_ERROR}. @end table @item Task execution + @cindex task execution + @findex recode_perform_task + @findex recode_filter_open + @findex recode_filter_close @example recode_perform_task (@var{task}); recode_filter_open (@var{task}, @var{file}); recode_filter_close (@var{task}); @end example *************** and recode all of it on prescribed outpu *** 2043,2105 **** Functions @code{recode_filter_open} and @code{recode_filter_close} are only planned for now. They are meant to read input in piecemeal ways. Even if functionality already exists informally in the library, it has not been made available yet through such interface functions. - @end itemize @node Charset level, Errors, Task level, Library @section Charset level functions Many functions are internal to the recoding library. Some of them have been made external and available, for the @code{recode} program had to retain all its previous functionality while being transformed into a mere application of the recoding library. These functions are not really documented here for the time being, as we hope that many of them will vanish over time. When this set of routines will stabilise, it would be convenient to document them as an API for handling charset names and contents. @example RECODE_CHARSET find_charset (@var{name}, @var{cleaning-type}); bool list_all_charsets (@var{charset}); bool list_concise_charset (@var{charset}, @var{list-format}); bool list_full_charset (@var{charset}); @end example @node Errors, , Charset level, Library @section Handling errors The @code{recode} program, while using the @code{recode} library, needs to control whether recoding problems are reported or not, and then reflect these in the exit status. The program should also instruct the library ! about if the recoding should be abruptly interrupted when an error is met (so sparing processing when it is known in advance that a wrong result would be discarded anyway), or if it should proceed nevertheless. Here is how the library groups errors into levels, listed here in order of increasing severity. @table @code - @item RECODE_NO_ERROR No error was met on previous library calls. @item RECODE_NOT_CANONICAL The input text was using one of the many alternative codings for some phenomenon, but not the one @code{recode} would have canonically generated. So, if the reverse recoding is later attempted, it would produce a text having the same @emph{meaning} as the original text, yet not being byte identical. For example, a @code{Base64} block in which end-of-lines appear elsewhere that at every 76 characters is not canonical. An e-circumflex in @TeX{} ! which is coded @samp{\^@{e@}} instead of @samp{\^e} is not canonical. @item RECODE_AMBIGUOUS_OUTPUT It has been discovered that if the reverse recoding was attempted on the text output by this recoding, we would not obtain the original text, only because an ambiguity was generated by accident in the output text. This ambiguity would then cause the wrong interpretation to be taken. --- 2201,2275 ---- Functions @code{recode_filter_open} and @code{recode_filter_close} are only planned for now. They are meant to read input in piecemeal ways. Even if functionality already exists informally in the library, it has not been made available yet through such interface functions. @end itemize @node Charset level, Errors, Task level, Library @section Charset level functions + @cindex charset level functions + @cindex internal functions Many functions are internal to the recoding library. Some of them have been made external and available, for the @code{recode} program had to retain all its previous functionality while being transformed into a mere application of the recoding library. These functions are not really documented here for the time being, as we hope that many of them will vanish over time. When this set of routines will stabilise, it would be convenient to document them as an API for handling charset names and contents. + @findex find_charset + @findex list_all_charsets + @findex list_concise_charset + @findex list_full_charset @example RECODE_CHARSET find_charset (@var{name}, @var{cleaning-type}); bool list_all_charsets (@var{charset}); bool list_concise_charset (@var{charset}, @var{list-format}); bool list_full_charset (@var{charset}); @end example @node Errors, , Charset level, Library @section Handling errors + @cindex error handling + @cindex handling errors + @cindex error messages The @code{recode} program, while using the @code{recode} library, needs to control whether recoding problems are reported or not, and then reflect these in the exit status. The program should also instruct the library ! whether the recoding should be abruptly interrupted when an error is met (so sparing processing when it is known in advance that a wrong result would be discarded anyway), or if it should proceed nevertheless. Here is how the library groups errors into levels, listed here in order of increasing severity. @table @code @item RECODE_NO_ERROR + @vindex RECODE_NO_ERROR No error was met on previous library calls. @item RECODE_NOT_CANONICAL + @vindex RECODE_NOT_CANONICAL + @cindex non canonical input, error message The input text was using one of the many alternative codings for some phenomenon, but not the one @code{recode} would have canonically generated. So, if the reverse recoding is later attempted, it would produce a text having the same @emph{meaning} as the original text, yet not being byte identical. For example, a @code{Base64} block in which end-of-lines appear elsewhere that at every 76 characters is not canonical. An e-circumflex in @TeX{} ! which is coded as @samp{\^@{e@}} instead of @samp{\^e} is not canonical. @item RECODE_AMBIGUOUS_OUTPUT + @vindex RECODE_AMBIGUOUS_OUTPUT + @cindex ambiguous output, error message It has been discovered that if the reverse recoding was attempted on the text output by this recoding, we would not obtain the original text, only because an ambiguity was generated by accident in the output text. This ambiguity would then cause the wrong interpretation to be taken. *************** where the input text contained an isolat *** 2114,2123 **** --- 2284,2295 ---- Currently, there are many cases in the library where the production of ambiguous output is not properly detected, as it is sometimes a difficult problem to accomplish this detection, or to do it speedily. @item RECODE_UNTRANSLATABLE + @vindex RECODE_UNTRANSLATABLE + @cindex untranslatable input, error message One or more input character could not be recoded, because there is just no representation for this character in the output charset. Here are a few examples. Non-strict mode often allows @code{recode} to *************** compute on-the-fly mappings for unrepres *** 2125,2179 **** mode prohibits such attribution of reversible translations: so strict mode might often trigger such an error. Most @code{UCS-2} codes used to represent Asian characters cannot be expressed in various Latin charsets. @item RECODE_INVALID_INPUT ! The input text does comply with the coding it is declared to hold. So, there is no way by which a reverse recoding would reproduce this text, because @code{recode} should never produce invalid output. ! Here are a few examples. In strict mode, @code{ASCII} text just may ! not contain characters with the eight bit set. @code{UTF-8} encodings ought to be minimal@footnote{The minimality of an @code{UTF-8} encoding is guaranteed on output, but currently, it is not checked on input.}. @item RECODE_SYSTEM_ERROR The underlying system reported an error while the recoding was going on, likely an input/output error. (This error symbol is currently unused in the library.) @item RECODE_USER_ERROR The programmer or user requested something the recoding library is unable to provide, or used the API wrongly. (This error symbol is currently unused in the library.) @item RECODE_INTERNAL_ERROR Something really wrong, which should normally never happen, was detected within the recoding library. This might be due to genuine bugs in the ! library, or maybe also, by un-initialised or overwritten arguments to the API. (This error symbol is currently unused in the library.) @item RECODE_MAXIMUM_ERROR This error code should never be returned, it is only internally used as ! a sentinel over all possible error codes. ! @end table One should be able to set the error level threshold for returning failure at end of recoding, and also the threshold for immediate interruption. If many errors occur while the recoding proceed, which are not severe enough to interrupt the recoding, then the most severe error is retained, while others are forgotten@footnote{Another approach would have been to define the level symbols as masks instead, and to give masks to threshold setting routines, and to retain all errors---yet I never ! met myself such a need in practice, and so, fear it would be overkill. On the other hand, it might be interesting to maintain counters about how many times each kind of error occurred.}. So, in case of an error, the possible actions currently are: @itemize @bullet --- 2297,2361 ---- mode prohibits such attribution of reversible translations: so strict mode might often trigger such an error. Most @code{UCS-2} codes used to represent Asian characters cannot be expressed in various Latin charsets. @item RECODE_INVALID_INPUT + @vindex RECODE_INVALID_INPUT + @cindex invalid input, error message ! The input text does not comply with the coding it is declared to hold. So, there is no way by which a reverse recoding would reproduce this text, because @code{recode} should never produce invalid output. ! Here are a few examples. In strict mode, @code{ASCII} text is not allowed ! to contain characters with the eight bit set. @code{UTF-8} encodings ought to be minimal@footnote{The minimality of an @code{UTF-8} encoding is guaranteed on output, but currently, it is not checked on input.}. @item RECODE_SYSTEM_ERROR + @vindex RECODE_SYSTEM_ERROR + @cindex system detected problem, error message The underlying system reported an error while the recoding was going on, likely an input/output error. (This error symbol is currently unused in the library.) @item RECODE_USER_ERROR + @vindex RECODE_USER_ERROR + @cindex misuse of recoding library, error message The programmer or user requested something the recoding library is unable to provide, or used the API wrongly. (This error symbol is currently unused in the library.) @item RECODE_INTERNAL_ERROR + @vindex RECODE_INTERNAL_ERROR + @cindex internal recoding bug, error message Something really wrong, which should normally never happen, was detected within the recoding library. This might be due to genuine bugs in the ! library, or maybe due to un-initialised or overwritten arguments to the API. (This error symbol is currently unused in the library.) @item RECODE_MAXIMUM_ERROR + @vindex RECODE_MAXIMUM_ERROR This error code should never be returned, it is only internally used as ! a sentinel for the list of all possible error codes. @end table + @cindex error level threshold + @cindex threshold for error reporting One should be able to set the error level threshold for returning failure at end of recoding, and also the threshold for immediate interruption. If many errors occur while the recoding proceed, which are not severe enough to interrupt the recoding, then the most severe error is retained, while others are forgotten@footnote{Another approach would have been to define the level symbols as masks instead, and to give masks to threshold setting routines, and to retain all errors---yet I never ! met myself such a need in practice, and so I fear it would be overkill. On the other hand, it might be interesting to maintain counters about how many times each kind of error occurred.}. So, in case of an error, the possible actions currently are: @itemize @bullet *************** the possible actions currently are: *** 2181,2191 **** @item just let go for now, but return failure at end of recoding, @item interrupt recoding right away and return failure now. @end itemize @noindent ! @xref{Task level}, and particularly the description of fields @code{fail_level}, @code{abort_level} and @code{error_so_far}, for more information about how errors are handled. @ignore @c FIXME: Take a look at these matters, indeed. --- 2363,2373 ---- @item just let go for now, but return failure at end of recoding, @item interrupt recoding right away and return failure now. @end itemize @noindent ! @xref{Task level}, and particularly the description of the fields @code{fail_level}, @code{abort_level} and @code{error_so_far}, for more information about how errors are handled. @ignore @c FIXME: Take a look at these matters, indeed. *************** so in practice. *** 2210,2257 **** @end ignore @node Universal, Tabular, Library, Top @chapter The universal charset Standard @w{ISO 10646} defines a universal character set, intended to encompass in the long run all languages written on this planet. It is based on wide characters, and offer possibilities for two billion characters (@math{2^31}). This charset was to become available in @code{recode} under the name @code{UCS}, with many external surfaces for it. But in the current version, only surfaces of @code{UCS} are offered, each presented as a genuine charset rather than a surface. Such surfaces are only meaningful for the @code{UCS} charset, so it is not that useful to draw a line between the surfaces and the only charset to which they may apply. @code{UCS} stands for Universal Character Set. @code{UCS-2} and @code{UCS-4} are fixed length encodings, using two or four bytes per character respectively. @code{UTF} stands for @code{UCS} Transformation Format, and are variable length encodings dedicated to @code{UCS}. @code{UTF-1} was based on @w{ISO 2022}, it did not succeed@footnote{It is not ! probable that @code{recode} will support @code{UTF-1} ever.}. @code{UTF-2} replaced it, it has been called @code{UTF-FSS} (File System Safe) in Unicode or Plan9 context, but is better known today as @code{UTF-8}. To complete the picture, there is @code{UTF-16} based on 16 bits bytes, and @code{UTF-7} which is meant for transmissions limited to 7-bit bytes. Most often, one might see @code{UTF-8} used for external storage, and @code{UCS-2} used for internal storage. When @code{recode} is producing any representation of @code{UCS}, it uses the replacement character @code{U+FFFD} for any @emph{valid} character which is not representable in the goal charset@footnote{This is when the goal charset allows for 16-bits. For shorter charsets, ! the @code{--strict} (@code{-s}) option decides what happens: either the character is dropped, or a reversible mapping is produced on the fly.}. This happens, for example, when @code{UCS-2} is not capable to echo a wide @code{UCS-4} character, or for a similar reason, an @code{UTF-8} sequence using more than three bytes. The replacement character is meant to represent an existing character. So, it is never produced to represent an invalid sequence or ill-formed character in the input text. ! In such cases, @code{recode} just get rid of the noise, while taking note ! of the error its usual ways. Even if @code{UTF-8} is an encoding, really, it is the encoding of a single character set, and nothing else. It is useful to distinguish between an encoding (a @emph{surface} within @code{recode}) and a charset, but only when the surface may be applied to several charsets. Specifying a charset --- 2392,2443 ---- @end ignore @node Universal, Tabular, Library, Top @chapter The universal charset + @cindex ISO 10646 Standard @w{ISO 10646} defines a universal character set, intended to encompass in the long run all languages written on this planet. It is based on wide characters, and offer possibilities for two billion characters (@math{2^31}). + @tindex UCS This charset was to become available in @code{recode} under the name @code{UCS}, with many external surfaces for it. But in the current version, only surfaces of @code{UCS} are offered, each presented as a genuine charset rather than a surface. Such surfaces are only meaningful for the @code{UCS} charset, so it is not that useful to draw a line between the surfaces and the only charset to which they may apply. + @tindex UTF-1 @code{UCS} stands for Universal Character Set. @code{UCS-2} and @code{UCS-4} are fixed length encodings, using two or four bytes per character respectively. @code{UTF} stands for @code{UCS} Transformation Format, and are variable length encodings dedicated to @code{UCS}. @code{UTF-1} was based on @w{ISO 2022}, it did not succeed@footnote{It is not ! probable that @code{recode} will ever support @code{UTF-1}.}. @code{UTF-2} replaced it, it has been called @code{UTF-FSS} (File System Safe) in Unicode or Plan9 context, but is better known today as @code{UTF-8}. To complete the picture, there is @code{UTF-16} based on 16 bits bytes, and @code{UTF-7} which is meant for transmissions limited to 7-bit bytes. Most often, one might see @code{UTF-8} used for external storage, and @code{UCS-2} used for internal storage. + @c FIXME: the manual never explains what the U+NNNN notation means! When @code{recode} is producing any representation of @code{UCS}, it uses the replacement character @code{U+FFFD} for any @emph{valid} character which is not representable in the goal charset@footnote{This is when the goal charset allows for 16-bits. For shorter charsets, ! the @samp{--strict} (@samp{-s}) option decides what happens: either the character is dropped, or a reversible mapping is produced on the fly.}. This happens, for example, when @code{UCS-2} is not capable to echo a wide @code{UCS-4} character, or for a similar reason, an @code{UTF-8} sequence using more than three bytes. The replacement character is meant to represent an existing character. So, it is never produced to represent an invalid sequence or ill-formed character in the input text. ! In such cases, @code{recode} just gets rid of the noise, while taking note ! of the error in its usual ways. Even if @code{UTF-8} is an encoding, really, it is the encoding of a single character set, and nothing else. It is useful to distinguish between an encoding (a @emph{surface} within @code{recode}) and a charset, but only when the surface may be applied to several charsets. Specifying a charset *************** a charset. Similar considerations apply *** 2272,2313 **** @end menu @node UCS-2, UCS-4, Universal, Universal @section Universal Character Set, 2 bytes One surface of @code{UCS} is usable for the subset defined by its first sixty thousand characters (in fact, @math{31 * 2^11} codes), and uses exactly two bytes per character. It is a mere dump of the internal memory representation which is @emph{natural} for this subset and as such, conveys with it endianness problems. A non-empty @code{UCS-2} file normally begins with a so called @dfn{byte order mark}, having value @code{0xFEFF}. The value @code{0xFFFE} is not an @code{UCS} character, so if this value is seen at the beginning of a file, @code{recode} reacts by swapping all pairs of bytes. The library also properly reacts to other occurrences of @code{0xFEFF} or @code{0xFFFE} elsewhere than at the beginning, because concatenation of @code{UCS-2} files should stay a simple matter, but it might trigger a diagnostic about non canonical input. By default, when producing an @code{UCS-2} file, @code{recode} always ! output the high order byte before the low order byte. But this could be ! easily overridden through the @code{21-Permutation} surface. For example, ! the command: @example recode u8..u2/21 < @var{input} > @var{output} @end example @noindent asks for an @code{UTF-8} to @code{UCS-2} conversion, with swapped byte output. ! Use it as a genuine charset. This charset is available in @code{recode} ! under the name @code{ISO-10646-UCS-2}. Accepted aliases are @code{UCS-2}, ! @code{BMP}, @code{rune} and @code{u2}. The @code{recode} library is able to combine @code{UCS-2} some sequences of codes into single code characters, to represent a few diacriticized characters, ligatures or diphtongs which have been included to ease mapping with other existing charsets. It is also able to explode such single code characters into the corresponding sequence of codes. --- 2458,2508 ---- @end menu @node UCS-2, UCS-4, Universal, Universal @section Universal Character Set, 2 bytes + @tindex UCS-2 + @cindex Unicode One surface of @code{UCS} is usable for the subset defined by its first sixty thousand characters (in fact, @math{31 * 2^11} codes), and uses exactly two bytes per character. It is a mere dump of the internal memory representation which is @emph{natural} for this subset and as such, conveys with it endianness problems. + @cindex byte order mark A non-empty @code{UCS-2} file normally begins with a so called @dfn{byte order mark}, having value @code{0xFEFF}. The value @code{0xFFFE} is not an @code{UCS} character, so if this value is seen at the beginning of a file, @code{recode} reacts by swapping all pairs of bytes. The library also properly reacts to other occurrences of @code{0xFEFF} or @code{0xFFFE} elsewhere than at the beginning, because concatenation of @code{UCS-2} files should stay a simple matter, but it might trigger a diagnostic about non canonical input. By default, when producing an @code{UCS-2} file, @code{recode} always ! outputs the high order byte before the low order byte. But this could be ! easily overridden through the @code{21-Permutation} surface ! (@pxref{Permutations}). For example, the command: @example recode u8..u2/21 < @var{input} > @var{output} @end example @noindent asks for an @code{UTF-8} to @code{UCS-2} conversion, with swapped byte output. ! @tindex ISO-10646-UCS-2, and aliases ! @tindex BMP ! @tindex rune ! @tindex u2 ! Use @code{UCS-2} as a genuine charset. This charset is available in ! @code{recode} under the name @code{ISO-10646-UCS-2}. Accepted aliases ! are @code{UCS-2}, @code{BMP}, @code{rune} and @code{u2}. + @tindex combined-UCS-2 + @cindex combining characters The @code{recode} library is able to combine @code{UCS-2} some sequences of codes into single code characters, to represent a few diacriticized characters, ligatures or diphtongs which have been included to ease mapping with other existing charsets. It is also able to explode such single code characters into the corresponding sequence of codes. *************** copies an @code{UTF-8} @var{input} over *** 2330,2363 **** --- 2525,2568 ---- possible. @node UCS-4, UTF-7, UCS-2, Universal @section Universal Character Set, 4 bytes + @tindex UCS-4 Another surface of @code{UCS} uses exactly four bytes per character, and is a mere dump of the internal memory representation which is @emph{natural} for the whole charset and as such, conveys with it endianness problems. + @tindex ISO-10646-UCS-4, and aliases + @tindex ISO_10646 + @tindex 10646 + @tindex u4 Use it as a genuine charset. This charset is available in @code{recode} under the name @code{ISO-10646-UCS-4}. Accepted aliases are @code{UCS}, @code{UCS-4}, @code{ISO_10646}, @code{10646} and @code{u4}. @node UTF-7, UTF-8, UCS-4, Universal @section Universal Transformation Format, 7 bits + @tindex UTF-7 @code{UTF-7} comes from IETF rather than ISO, and is described by @w{RFC 1642}, in the MIME series. The @code{UTF-7} encoding is meant to fit @code{UCS-2} over channels limited to seven bits per byte. It proceeds from a mix between the spirit of @code{Quoted-Printable} and methods of @code{Base64}, adapted to Unicode contexts. + @tindex UNICODE-1-1-UTF-7, and aliases + @tindex TF-7 + @tindex u7 This charset is available in @code{recode} under the name @code{UNICODE-1-1-UTF-7}. Accepted aliases are @code{UTF-7}, @code{TF-7} and @code{u7}. @node UTF-8, UTF-16, UTF-7, Universal @section Universal Transformation Format, 8 bits + @tindex UTF-8 Even if @code{UTF-8} does not originally come from IETF, there is now @w{RFC 2279} to describe it. In letters sent on 1995-01-21 and 1995-04-20, Markus Kuhn writes: @quotation *************** easy self-synchronisation of software re *** 2383,2393 **** @end quotation @code{UTF-8} is the most common external surface of @code{UCS}, each character uses from one to six bytes, and is able to encode all @math{2^31} characters of the @code{UCS}. It is implemented as a charset, with the ! following properties. @itemize @bullet @item Strict 7-bit @code{ASCII} is completely invariant under @code{UTF-8}, and those are the only one-byte characters. @code{UCS} values and --- 2588,2598 ---- @end quotation @code{UTF-8} is the most common external surface of @code{UCS}, each character uses from one to six bytes, and is able to encode all @math{2^31} characters of the @code{UCS}. It is implemented as a charset, with the ! following properties: @itemize @bullet @item Strict 7-bit @code{ASCII} is completely invariant under @code{UTF-8}, and those are the only one-byte characters. @code{UCS} values and *************** is valid @code{UTF-8}, or to safely stat *** 2410,2463 **** @item In a multi-byte character, if you remove all leading @samp{1} bits of the first byte of a multi-byte character, and the initial @samp{10} bits of all remaining bytes (so keeping 6 bits per byte for those), the remaining bits concatenated are the UCS value. - @end itemize @noindent ! These properties also have a few nice consequences. @itemize @bullet @item Conversion to/from values is algorithmically simple, and reasonably speedy. @item A sequence of @var{N} bytes can hold characters needing up to 2 + 5@var{N} bits in their @code{UCS} representation. Here, @var{N} is a number between 1 and 6. So, @code{UTF-8} is most economical when mapping ASCII (1 byte), ! then @code{UCS-2} (1 to 3 bytes), then @code{UCS-4} (1 to 6 bytes). @item The lexicographic sorting order of @code{UCS} strings is preserved. @item Bytes with value 254 or 255 never appear, and because of that, these are sometimes used when escape mechanisms are needed. - @end itemize In some case, when little processing is done on a lot of strings, one may choose for efficiency reasons to handle @code{UTF-8} strings directly even if variable length, as it is easy to get start of characters. Character insertion or replacement might require moving the remainder of the string in either direction. In most cases, it is faster and easier to convert from @code{UTF-8} to @code{UCS-2} or @code{UCS-4} prior to processing. This charset is available in @code{recode} under the name @code{UTF-8}. Accepted aliases are @code{UTF-2}, @code{UTF-FSS}, @code{FSS_UTF}, @code{TF-8} and @code{u8}. @node UTF-16, count-characters, UTF-8, Universal @section Universal Transformation Format, 16 bits Another external surface of @code{UCS} is also variable length, each character using either two or four bytes. It is usable for the subset defined by the first million characters (@math{17 * 2^16}) of @code{UCS}. ! Martin J. D@"urst writes (to @file{comp.std.internat}, on 1995-03-28): @quotation @code{UTF-16} is another method that reserves two times 1024 codepoints in Unicode and uses them to index around one million additional characters. @code{UTF-16} is a little bit like former multibyte codes, but quite --- 2615,2672 ---- @item In a multi-byte character, if you remove all leading @samp{1} bits of the first byte of a multi-byte character, and the initial @samp{10} bits of all remaining bytes (so keeping 6 bits per byte for those), the remaining bits concatenated are the UCS value. @end itemize @noindent ! These properties also have a few nice consequences: @itemize @bullet @item Conversion to/from values is algorithmically simple, and reasonably speedy. @item A sequence of @var{N} bytes can hold characters needing up to 2 + 5@var{N} bits in their @code{UCS} representation. Here, @var{N} is a number between 1 and 6. So, @code{UTF-8} is most economical when mapping ASCII (1 byte), ! followed by @code{UCS-2} (1 to 3 bytes) and @code{UCS-4} (1 to 6 bytes). @item The lexicographic sorting order of @code{UCS} strings is preserved. @item Bytes with value 254 or 255 never appear, and because of that, these are sometimes used when escape mechanisms are needed. @end itemize In some case, when little processing is done on a lot of strings, one may choose for efficiency reasons to handle @code{UTF-8} strings directly even if variable length, as it is easy to get start of characters. Character insertion or replacement might require moving the remainder of the string in either direction. In most cases, it is faster and easier to convert from @code{UTF-8} to @code{UCS-2} or @code{UCS-4} prior to processing. + @tindex UTF-8, aliases + @tindex UTF-FSS + @tindex FSS_UTF + @tindex TF-8 + @tindex u8 This charset is available in @code{recode} under the name @code{UTF-8}. Accepted aliases are @code{UTF-2}, @code{UTF-FSS}, @code{FSS_UTF}, @code{TF-8} and @code{u8}. @node UTF-16, count-characters, UTF-8, Universal @section Universal Transformation Format, 16 bits + @tindex UTF-16, and aliases Another external surface of @code{UCS} is also variable length, each character using either two or four bytes. It is usable for the subset defined by the first million characters (@math{17 * 2^16}) of @code{UCS}. ! Martin J. D@"urst writes (to @uref{comp.std.internat}, on 1995-03-28): @quotation @code{UTF-16} is another method that reserves two times 1024 codepoints in Unicode and uses them to index around one million additional characters. @code{UTF-16} is a little bit like former multibyte codes, but quite *************** they are. The idea is that one million *** 2466,2481 **** --- 2675,2695 ---- all the rare Chinese ideograms and historical scripts that do not fit into the Base Multilingual Plane of @w{ISO 10646} (with just about 63,000 positions available, now that 2,000 are gone). @end quotation + @tindex Unicode, an alias for UTF-16 + @tindex TF-16 + @tindex u6 This charset is available in @code{recode} under the name @code{UTF-16}. Accepted aliases are @code{Unicode}, @code{TF-16} and @code{u6}. @node count-characters, dump-with-names, UTF-16, Universal @section Frequency count of characters + @tindex count-characters + @cindex counting characters A device may be used to obtain a list of characters in a file, and how many times each character appears. Each count is followed by the @code{UCS-2} value of the character and, when known, the @w{RFC 1345} mnemonic for that character. *************** change in some later version, as it woul *** 2487,2496 **** --- 2701,2714 ---- original bytes, instead of their @code{UCS-2} equivalent. @node dump-with-names, , count-characters, Universal @section Fully interpreted UCS dump + @tindex dump-with-names + @cindex dumping characters, with description + @cindex character streams, description + @cindex description of individual characters Another device may be used to get fully interpreted dumps of an @code{UCS-2} stream of characters, with one @code{UCS-2} character displayed on a full output line. Each line receives the @w{RFC 1345} mnemonic for the character if it exists, the @code{UCS-2} value of the character, and a descriptive comment for that character. As each input character produces its own *************** This charset is available in @code{recod *** 2502,2540 **** This @code{dump-with-names} feature has been implemented as a charset rather than a surface. This is surely debatable. The current implementation allows for dumping charsets other than @code{UCS-2}. For example, the command @w{@samp{recode l2..full < @var{input}}} implies a necessary ! conversion from @code{Latin-2} to @code{UCS-2}, as @code{full-dump} is only connected out from @code{UCS-2}. In such cases, @code{recode} does not display the original @code{Latin-2} codes in the dump, only the corresponding @code{UCS-2} values. To give a simpler example, the command @example echo 'Hello, world!' | recode us..dump @end example @noindent ! produces the following output. @example ! Mne UCS2 Description ! ! H 0048 latin capital letter h ! e 0065 latin small letter e ! l 006C latin small letter l ! l 006C latin small letter l ! o 006F latin small letter o ! , 002C comma ! SP 0020 space ! w 0077 latin small letter w ! o 006F latin small letter o ! r 0072 latin small letter r ! l 006C latin small letter l ! d 0064 latin small letter d ! ! 0021 exclamation mark ! LF 000A line feed (lf) @end example The descriptive comment is given in English and @code{ASCII}, yet if the English description is not available but a French one is, then the French description is given instead, using @code{Latin-1}. However, --- 2720,2758 ---- This @code{dump-with-names} feature has been implemented as a charset rather than a surface. This is surely debatable. The current implementation allows for dumping charsets other than @code{UCS-2}. For example, the command @w{@samp{recode l2..full < @var{input}}} implies a necessary ! conversion from @code{Latin-2} to @code{UCS-2}, as @code{dump-with-names} is only connected out from @code{UCS-2}. In such cases, @code{recode} does not display the original @code{Latin-2} codes in the dump, only the corresponding @code{UCS-2} values. To give a simpler example, the command @example echo 'Hello, world!' | recode us..dump @end example @noindent ! produces the following output: @example ! UCS2 Mne Description ! ! 0048 H latin capital letter h ! 0065 e latin small letter e ! 006C l latin small letter l ! 006C l latin small letter l ! 006F o latin small letter o ! 002C , comma ! 0020 SP space ! 0077 w latin small letter w ! 006F o latin small letter o ! 0072 r latin small letter r ! 006C l latin small letter l ! 0064 d latin small letter d ! 0021 ! exclamation mark ! 000A LF line feed (lf) @end example The descriptive comment is given in English and @code{ASCII}, yet if the English description is not available but a French one is, then the French description is given instead, using @code{Latin-1}. However, *************** echo -n 0x03C6 | recode u2/x2..dump | ta *** 2559,2614 **** @end example @node Tabular, ASCII misc, Universal, Top @chapter Tabular sources (@w{RFC 1345}) An important part of the tabular charset knowledge in @code{recode} comes from @w{RFC 1345} or, alternatively, from the @code{chset} tools, both maintained by Keld Simonsen. The @w{RFC 1345} document: @quotation ``Character Mnemonics & Character Sets'', K. Simonsen, Request for Comments no. 1345, Network Working Group, June 1992. @end quotation @noindent defines many character mnemonics and character sets. The @code{recode} library implements most of @w{RFC 1345}, however: @itemize @bullet @item It does not recognise those charsets which overload character positions: @code{dk-us} and @code{us-dk}. However, see @ref{Mixed}. @item It does not recognise those charsets which combine two characters for representing a third: @code{ANSI_X3.110-1983}, @code{ISO_6937-2-add}, @code{T.101-G2}, @code{T.61-8bit}, @code{iso-ir-90} and @code{videotex-suppl}. @item It does not recognise 16-bits charsets: @code{GB_2312-80}, @code{JIS_C6226-1978}, @code{JIS_C6226-1983}, @code{JIS_X0212-1990} and @code{KS_C_5601-1987}. @item It interprets the charset @code{isoir91} as @code{NATS-DANO} (alias @code{iso-ir-9-1}), @emph{not} as @code{JIS_C6229-1984-a} (alias @code{iso-ir-91}). It also interprets the charset @code{isoir92} as @code{NATS-DANO-ADD} (alias @code{iso-ir-9-2}), @emph{not} as @code{JIS_C6229-1984-b} (alias @code{iso-ir-92}). It might be better just avoiding these two alias names. - @end itemize Keld Simonsen @email{keld@@dkuug.dk} did most of @w{RFC 1345} himself, with some funding from Danish Standards and Nordic standards (INSTA) project. He also did the character set design work, with substantial input from Olle Jaernefors. Keld typed in almost all of the tables, some have been contributed. A number of people have checked the tables in various ways. The RFC lists a number of people who helped. Keld and the @code{recode} maintainer have an arrangement by which any new discovered information submitted by @code{recode} users, about tabular charsets, is forwarded to Keld, eventually merged into Keld's work, and only then, reimported into @code{recode}. Neither the @code{recode} program nor its library try to compete, nor even establish themselves as --- 2777,2849 ---- @end example @node Tabular, ASCII misc, Universal, Top @chapter Tabular sources (@w{RFC 1345}) + @cindex RFC 1345 + @cindex character mnemonics, documentation + @cindex @code{chset} tools An important part of the tabular charset knowledge in @code{recode} comes from @w{RFC 1345} or, alternatively, from the @code{chset} tools, both maintained by Keld Simonsen. The @w{RFC 1345} document: @quotation ``Character Mnemonics & Character Sets'', K. Simonsen, Request for Comments no. 1345, Network Working Group, June 1992. @end quotation @noindent + @cindex deviations from RFC 1345 defines many character mnemonics and character sets. The @code{recode} library implements most of @w{RFC 1345}, however: @itemize @bullet @item + @tindex dk-us@r{, not recognised by }recode + @tindex us-dk@r{, not recognised by }recode It does not recognise those charsets which overload character positions: @code{dk-us} and @code{us-dk}. However, see @ref{Mixed}. @item + @tindex ANSI_X3.110-1983@r{, not recognised by }recode + @tindex ISO_6937-2-add@r{, not recognised by }recode + @tindex T.101-G2@r{, not recognised by }recode + @tindex T.61-8bit@r{, not recognised by }recode + @tindex iso-ir-90@r{, not recognised by }recode It does not recognise those charsets which combine two characters for representing a third: @code{ANSI_X3.110-1983}, @code{ISO_6937-2-add}, @code{T.101-G2}, @code{T.61-8bit}, @code{iso-ir-90} and @code{videotex-suppl}. @item + @tindex GB_2312-80@r{, not recognised by }recode + @tindex JIS_C6226-1978@r{, not recognised by }recode + @tindex JIS_X0212-1990@r{, not recognised by }recode + @tindex KS_C_5601-1987@r{, not recognised by }recode It does not recognise 16-bits charsets: @code{GB_2312-80}, @code{JIS_C6226-1978}, @code{JIS_C6226-1983}, @code{JIS_X0212-1990} and @code{KS_C_5601-1987}. @item + @tindex isoir91 + @tindex isoir92 It interprets the charset @code{isoir91} as @code{NATS-DANO} (alias @code{iso-ir-9-1}), @emph{not} as @code{JIS_C6229-1984-a} (alias @code{iso-ir-91}). It also interprets the charset @code{isoir92} as @code{NATS-DANO-ADD} (alias @code{iso-ir-9-2}), @emph{not} as @code{JIS_C6229-1984-b} (alias @code{iso-ir-92}). It might be better just avoiding these two alias names. @end itemize Keld Simonsen @email{keld@@dkuug.dk} did most of @w{RFC 1345} himself, with some funding from Danish Standards and Nordic standards (INSTA) project. He also did the character set design work, with substantial input from Olle Jaernefors. Keld typed in almost all of the tables, some have been contributed. A number of people have checked the tables in various ways. The RFC lists a number of people who helped. + @cindex @code{recode}, and RFC 1345 Keld and the @code{recode} maintainer have an arrangement by which any new discovered information submitted by @code{recode} users, about tabular charsets, is forwarded to Keld, eventually merged into Keld's work, and only then, reimported into @code{recode}. Neither the @code{recode} program nor its library try to compete, nor even establish themselves as *************** an alternate or diverging reference: @w{ *** 2616,2625 **** --- 2851,2863 ---- genuine source for most tabular information conveyed by @code{recode}. Keld has been more than collaborative so far, so there is no reason that we act otherwise. In a word, @code{recode} should be perceived as the application of external references, but not as a reference in itself. + @tindex RFC1345@r{, a charset, and its aliases} + @tindex 1345 + @tindex mnemonic@r{, an alias for RFC1345 charset} Internally, @w{RFC 1345} associates which each character an unambiguous mnemonic of a few characters, taken from @w{ISO 646}, which is a minimal ASCII subset of 83 characters. The charset made up by these mnemonics is available in @code{recode} under the name @code{RFC1345}. It has @code{mnemonic} and @code{1345} for aliases. As implemened, this charset *************** Currently, @code{recode} does not offer *** 2635,2645 **** variations of this family of representations. They will likely be implemented in some future version, however. @table @code @include charset.texi - @end table @node ASCII misc, IBM and MS, Tabular, Top @chapter ASCII and some derivatives --- 2873,2882 ---- *************** implemented in some future version, howe *** 2651,2667 **** --- 2888,2912 ---- @end menu @node ASCII, ISO 8859, ASCII misc, ASCII misc @section Usual ASCII + @tindex ASCII@r{, an alias for the }ANSI_X3.4-1968@r{ charset} + @tindex ANSI_X3.4-1968@r{, and its aliases} + @tindex IBM367 + @tindex US-ASCII + @tindex cp367 + @tindex iso-ir-6 + @tindex us This charset is available in @code{recode} under the name @code{ASCII}. In fact, it's true name is @code{ANSI_X3.4-1968} as per @w{RFC 1345}, accepted aliases being @code{ANSI_X3.4-1986}, @code{ASCII}, @code{IBM367}, @code{ISO646-US}, @code{ISO_646.irv:1991}, @code{US-ASCII}, @code{cp367}, @code{iso-ir-6} and @code{us}. The shortest way of specifying it in @code{recode} is @code{us}. + @cindex ASCII table, recreating with @code{recode} This documentation used to include ASCII tables. They have been removed since the @code{recode} program can now recreate these easily: @example recode -lf us for commented ASCII *************** recode -lh us for conc *** 2671,2680 **** --- 2916,2926 ---- @end example @node ISO 8859, ASCII-BS, ASCII, ASCII misc @section ASCII extended by Latin Alphabets + @cindex Latin charsets There are many Latin charsets. The following has been written by Tim Lasko @email{lasko@@video.dec.com}, a long while ago: @quotation ISO @w{Latin-1}, or more completely ISO Latin Alphabet No 1, is now *************** Latin-Arabic alphabet (right half all Ar *** 2702,2721 **** @item Latin-Greek alphabet (right half Greek + symbols - in draft ballot). @item Latin-Hebrew alphabet (right half Hebrew + symbols - proposed). @end itemize - @end quotation The ISO Latin Alphabet 1 is available as a charset in @code{recode} under the name @code{Latin-1}. In fact, it's true name is @code{ISO_8859-1:1987} as per @w{RFC 1345}, accepted aliases being @code{CP819}, @code{IBM819}, @code{ISO-8859-1}, @code{ISO_8859-1}, @code{iso-ir-100}, @code{l1} and @code{Latin-1}. The shortest way of specifying it in @code{recode} is @code{l1}. It is an eight-bit code which coincides with ASCII for the lower half. This documentation used to include @w{Latin-1} tables. They have been removed since the @code{recode} program can now recreate these easily: @example --- 2948,2968 ---- @item Latin-Greek alphabet (right half Greek + symbols - in draft ballot). @item Latin-Hebrew alphabet (right half Hebrew + symbols - proposed). @end itemize @end quotation + @tindex Latin-1 The ISO Latin Alphabet 1 is available as a charset in @code{recode} under the name @code{Latin-1}. In fact, it's true name is @code{ISO_8859-1:1987} as per @w{RFC 1345}, accepted aliases being @code{CP819}, @code{IBM819}, @code{ISO-8859-1}, @code{ISO_8859-1}, @code{iso-ir-100}, @code{l1} and @code{Latin-1}. The shortest way of specifying it in @code{recode} is @code{l1}. + @cindex Latin-1 table, recreating with @code{recode} It is an eight-bit code which coincides with ASCII for the lower half. This documentation used to include @w{Latin-1} tables. They have been removed since the @code{recode} program can now recreate these easily: @example *************** recode -lh l1 for conc *** 2726,2738 **** --- 2973,2988 ---- @end example @node ASCII-BS, flat, ISO 8859, ASCII misc @section ASCII 7-bits, @kbd{BS} to overstrike + @tindex ASCII-BS@r{, and its aliases} + @tindex BS@r{, an alias for }ASCII-BS@r{ charset} This charset is available in @code{recode} under the name @code{ASCII-BS}, with @code{BS} as an acceptable alias. + @cindex diacritics, with @code{ASCII-BS} charset The file is straight ASCII, seven bits only. According to the definition of ASCII, diacritics are applied by a sequence of three characters: the letter, one @kbd{BS}, the diacritic mark. We deviate slightly from this by exchanging the diacritic mark and the letter so, on a screen device, the diacritic will disappear and let the letter alone. At recognition time, *************** accent is applied over the @kbd{e} with *** 2772,2784 **** --- 3022,3037 ---- characters have special rules. For the @code{ASCII-BS} charset, reversibility is still possible, but there might be difficult cases. @node flat, , ASCII-BS, ASCII misc @section ASCII without diacritics nor underline + @tindex flat@r{, a charset} This charset is available in @code{recode} under the name @code{flat}. + @cindex diacritics and underlines, removing + @cindex removing diacritics and underlines This code is ASCII expunged of all diacritics and underlines, as long as they are applied using three character sequences, with @kbd{BS} in the middle. Also, despite slightly unrelated, each control character is represented by a sequence of two or three graphic characters. The newline character, however, keeps its functionality and is not represented. *************** Note that charset @code{flat} is a termi *** 2787,2796 **** --- 3040,3051 ---- @emph{to} @code{flat}, but not @emph{from} it. @node IBM and MS, CDC, ASCII misc, Top @chapter Some IBM or Microsoft charsets + @cindex IBM codepages + @cindex codepages The @code{recode} program provides various IBM or Microsoft code pages (@pxref{Tabular}). An easy way to find them all at once out of the @code{recode} program itself is through the command: @example *************** But also, see few special charsets prese *** 2807,2834 **** @end menu @node EBCDIC, IBM-PC, IBM and MS, IBM and MS @section EBCDIC code This charset is the IBM's External Binary Coded Decimal for Interchange Coding. This is an eight bits code. The following three variants were implemented in @code{recode} independently of @w{RFC 1345}: @table @code - @item EBCDIC In @code{recode}, the @code{us..ebcdic} conversion is identical to @samp{dd conv=ebcdic} conversion, and @code{recode} @code{ebcdic..us} conversion is identical to @samp{dd conv=ascii} conversion. This charset also represents the way Control Data Corporation relates EBCDIC to 8-bits ASCII. @item EBCDIC-CCC In @code{recode}, the @code{us..ebcdic-ccc} or @code{ebcdic-ccc..us} conversions represent the way Concurrent Computer Corporation (formerly Perkin Elmer) relates EBCDIC to 8-bits ASCII. @item EBCDIC-IBM In @code{recode}, the @code{us..ebcdic-ibm} conversion is @emph{almost} identical to the GNU @samp{dd conv=ibm} conversion. Given the exact @samp{dd conv=ibm} conversion table, @code{recode} once said: @example --- 3062,3092 ---- @end menu @node EBCDIC, IBM-PC, IBM and MS, IBM and MS @section EBCDIC code + @cindex EBCDIC charsets This charset is the IBM's External Binary Coded Decimal for Interchange Coding. This is an eight bits code. The following three variants were implemented in @code{recode} independently of @w{RFC 1345}: @table @code @item EBCDIC + @tindex EBCDIC@r{, a charset} In @code{recode}, the @code{us..ebcdic} conversion is identical to @samp{dd conv=ebcdic} conversion, and @code{recode} @code{ebcdic..us} conversion is identical to @samp{dd conv=ascii} conversion. This charset also represents the way Control Data Corporation relates EBCDIC to 8-bits ASCII. @item EBCDIC-CCC + @tindex EBCDIC-CCC In @code{recode}, the @code{us..ebcdic-ccc} or @code{ebcdic-ccc..us} conversions represent the way Concurrent Computer Corporation (formerly Perkin Elmer) relates EBCDIC to 8-bits ASCII. @item EBCDIC-IBM + @tindex EBCDIC-IBM In @code{recode}, the @code{us..ebcdic-ibm} conversion is @emph{almost} identical to the GNU @samp{dd conv=ibm} conversion. Given the exact @samp{dd conv=ibm} conversion table, @code{recode} once said: @example *************** No character recodes to 106 *** 2841,2851 **** So I arbitrarily chose to recode 213 by 74 and 229 by 106. This makes the @code{EBCDIC-IBM} recoding reversible, but this is not necessarily the best correction. In any case, I think that GNU @code{dd} should be amended. @code{dd} and @code{recode} should ideally agree on the same correction. So, this table might change once again. - @end table @w{RFC 1345} brings into @code{recode} 15 other EBCDIC charsets, and 21 other charsets having EBCDIC in at least one of their alias names. You can get a list of all these by executing: --- 3099,3108 ---- *************** but @code{VB} or @code{VBS} blocking is *** 2862,2871 **** --- 3119,3133 ---- the converted results. @node IBM-PC, Icon-QNX, EBCDIC, IBM and MS @section IBM's PC code + @tindex IBM-PC + @cindex MS-DOS charsets + @tindex MSDOS + @tindex dos + @tindex pc This charset is available in @code{recode} under the name @code{IBM-PC}, with @code{dos}, @code{MSDOS} and @code{pc} as acceptable aliases. The shortest way of specifying it in @code{recode} is @code{pc}. The charset is aimed towards a PC microcomputer from IBM or any compatible. *************** recode pc..l2/cl < @var{input} > @var{ou *** 2883,2908 **** recode pc/..l2 < @var{input} > @var{output} @end example @w{RFC 1345} brings into @code{recode} 44 @samp{IBM} charsets or code pages, and also 8 other code pages. You can get a list of these all these by ! executing:@footnote{On DOS/Windows, stock shells do not know that apostrohes quote special characters like @kbd{|}, so one need to use double quotes instead of apostrophes.} @example recode -l | egrep -i '(CP|IBM)[0-9]' @end example @noindent All charset or aliases beginning with letters @samp{CP} or @samp{IBM} also have @code{CR-LF} as their implied surface. The same is true for a purely numeric alias in the same family. For example, all of @code{819}, @code{CP819} and @code{IBM819} imply @code{CR-LF} as a surface. Note that @code{ISO-8859-1} does @emph{not} imply a surface, despite it shares the same tabular data as @code{819}. There are a few discrepancies between this @code{IBM-PC} charset and the very similar @w{RFC 1345} charset @code{ibm437}, which have not been analysed yet, so the charsets are being kept separate for now. This might change in the future, and the @code{IBM-PC} charset might disappear. Wizards would be interested in comparing the output of these two commands: --- 3145,3173 ---- recode pc/..l2 < @var{input} > @var{output} @end example @w{RFC 1345} brings into @code{recode} 44 @samp{IBM} charsets or code pages, and also 8 other code pages. You can get a list of these all these by ! executing:@footnote{On DOS/Windows, stock shells do not know that apostrophes quote special characters like @kbd{|}, so one need to use double quotes instead of apostrophes.} @example recode -l | egrep -i '(CP|IBM)[0-9]' @end example @noindent + @cindex CR-LF surface, in IBM-PC charsets + @tindex IBM819@r{, and CR-LF surface} All charset or aliases beginning with letters @samp{CP} or @samp{IBM} also have @code{CR-LF} as their implied surface. The same is true for a purely numeric alias in the same family. For example, all of @code{819}, @code{CP819} and @code{IBM819} imply @code{CR-LF} as a surface. Note that @code{ISO-8859-1} does @emph{not} imply a surface, despite it shares the same tabular data as @code{819}. + @tindex ibm437 There are a few discrepancies between this @code{IBM-PC} charset and the very similar @w{RFC 1345} charset @code{ibm437}, which have not been analysed yet, so the charsets are being kept separate for now. This might change in the future, and the @code{IBM-PC} charset might disappear. Wizards would be interested in comparing the output of these two commands: *************** Both methods give different recodings. *** 2918,2941 **** the fuzziness will have to be explained and settle down one day. @node Icon-QNX, , IBM-PC, IBM and MS @section Unisys' Icon code This charset is available in @code{recode} under the name @code{Icon-QNX}, with @code{QNX} as an acceptable alias. The file is using Unisys' Icon way to represent diacritics with code 25 escape sequences, under the system QNX. This is a seven-bit code, even if eight-bit codes can flow through as part of IBM-PC charset. @node CDC, Micros, IBM and MS, Top @chapter Charsets for CDC machines What is now @code{recode} evolved out, through many transformations ! really, from a set of programs which were originally written in Control ! Data Corporation's assembler (@code{COMPASS}), with bits in FORTRAN, ! and later, rewritten in CDC 6000 Pascal. The CDC heritage shows by the fact some old CDC charsets are still supported. The @code{recode} author used to be familiar with CDC Scope-NOS/BE and Kronos-NOS, and many CDC formats. Reading CDC tapes directly on other machines is often a challenge, and @code{recode} does not always solve --- 3183,3210 ---- the fuzziness will have to be explained and settle down one day. @node Icon-QNX, , IBM-PC, IBM and MS @section Unisys' Icon code + @tindex Icon-QNX@r{, and aliases} + @tindex QNX@r{, an alias for a charset} This charset is available in @code{recode} under the name @code{Icon-QNX}, with @code{QNX} as an acceptable alias. The file is using Unisys' Icon way to represent diacritics with code 25 escape sequences, under the system QNX. This is a seven-bit code, even if eight-bit codes can flow through as part of IBM-PC charset. @node CDC, Micros, IBM and MS, Top @chapter Charsets for CDC machines + @cindex CDC charsets + @cindex charsets for CDC machines What is now @code{recode} evolved out, through many transformations ! really, from a set of programs which were originally written in ! @dfn{COMPASS}, Control Data Corporation's assembler, with bits in FORTRAN, ! and later rewritten in CDC 6000 Pascal. The CDC heritage shows by the fact some old CDC charsets are still supported. The @code{recode} author used to be familiar with CDC Scope-NOS/BE and Kronos-NOS, and many CDC formats. Reading CDC tapes directly on other machines is often a challenge, and @code{recode} does not always solve *************** caret notation over Display Code already *** 2961,2970 **** --- 3230,3240 ---- @end menu @node Display Code, CDC-NOS, CDC, CDC @section Control Data's Display Code + @cindex CDC Display Code, a table This code is not available in @code{recode}, but repeated here for reference. This is a 6-bit code used on CDC mainframes. @example Octal display code to graphic Octal display code to octal ASCII *************** immediately preceeding @emph{pairs} of z *** 3004,3017 **** be considered as part of the end of line and not interpreted as @kbd{::}.}. @node CDC-NOS, Bang-Bang, Display Code, CDC @section ASCII 6/12 from NOS This charset is available in @code{recode} under the name @code{CDC-NOS}, with @code{NOS} as an acceptable alias. ! This is one of the charset in use on CDC Cyber NOS systems to represent ASCII, sometimes named @dfn{NOS 6/12} code for coding ASCII. This code is also known as @dfn{caret ASCII}. It is based on a six bits character set in which small letters and control characters are coded using a @kbd{^} escape and, sometimes, a @kbd{@@} escape. --- 3274,3291 ---- be considered as part of the end of line and not interpreted as @kbd{::}.}. @node CDC-NOS, Bang-Bang, Display Code, CDC @section ASCII 6/12 from NOS + @tindex CDC-NOS@r{, and its aliases} + @tindex NOS This charset is available in @code{recode} under the name @code{CDC-NOS}, with @code{NOS} as an acceptable alias. ! @cindex NOS 6/12 code ! @cindex caret ASCII code ! This is one of the charsets in use on CDC Cyber NOS systems to represent ASCII, sometimes named @dfn{NOS 6/12} code for coding ASCII. This code is also known as @dfn{caret ASCII}. It is based on a six bits character set in which small letters and control characters are coded using a @kbd{^} escape and, sometimes, a @kbd{@@} escape. *************** ASCII character. *** 3042,3051 **** --- 3316,3326 ---- @end example @node Bang-Bang, , CDC-NOS, CDC @section ASCII ``bang bang'' + @tindex Bang-Bang This charset is available in @code{recode} under the name @code{Bang-Bang}. This code, in use on Cybers at Universit@'e de Montr@'eal mainly, served to code a lot of French texts. The original name of this charset is @dfn{ASCII cod@'e Display}. This code is also known as @dfn{Bang-bang}. *************** ASCII character. *** 3081,3116 **** @end example @node Micros, Miscellaneous, CDC, Top @chapter Other micro-computer charsets ! The @code{NeXT} charset, which use to be especially provided in releases of @code{recode} before 3.5, has been integrated since as one @w{RFC 1345} table. @menu * Apple-Mac:: Apple's Macintosh code * AtariST:: Atari ST code @end menu @node Apple-Mac, AtariST, Micros, Micros @section Apple's Macintosh code This charset is available in @code{recode} under the name @code{Apple-Mac}. The shortest way of specifying it in @code{recode} is @code{ap}. The charset is aimed towards a Macintosh micro-computer from Apple. This is an eight bit code. The file is the data fork only. This charset is fairly old in @code{recode}, its tables were produced a long while ago by mere inspection of a printed chart of the Macintosh codes and glyph. ! It has @code{LF} as its implied surface. This means that, if the original end of lines have to be preserved while going out of @code{Apple-Mac}, they should currently be added back through the usage of a surface on the other charset, or better, just never removed. Here are examples for both cases: @example ! recode ap..l2/cl < @var{input} > @var{output} recode ap/..l2 < @var{input} > @var{output} @end example @w{RFC 1345} brings into @code{recode} 2 other Macintosh charsets. You can discover them by using @code{grep} over the output of @samp{recode -l}: --- 3356,3395 ---- @end example @node Micros, Miscellaneous, CDC, Top @chapter Other micro-computer charsets ! @cindex NeXT charsets ! The @code{NeXT} charset, which used to be especially provided in releases of @code{recode} before 3.5, has been integrated since as one @w{RFC 1345} table. @menu * Apple-Mac:: Apple's Macintosh code * AtariST:: Atari ST code @end menu @node Apple-Mac, AtariST, Micros, Micros @section Apple's Macintosh code + @tindex Apple-Mac + @cindex Macintosh charset This charset is available in @code{recode} under the name @code{Apple-Mac}. The shortest way of specifying it in @code{recode} is @code{ap}. The charset is aimed towards a Macintosh micro-computer from Apple. This is an eight bit code. The file is the data fork only. This charset is fairly old in @code{recode}, its tables were produced a long while ago by mere inspection of a printed chart of the Macintosh codes and glyph. ! @cindex CR surface, in Macintosh charsets ! It has @code{CR} as its implied surface. This means that, if the original end of lines have to be preserved while going out of @code{Apple-Mac}, they should currently be added back through the usage of a surface on the other charset, or better, just never removed. Here are examples for both cases: @example ! recode ap..l2/cr < @var{input} > @var{output} recode ap/..l2 < @var{input} > @var{output} @end example @w{RFC 1345} brings into @code{recode} 2 other Macintosh charsets. You can discover them by using @code{grep} over the output of @samp{recode -l}: *************** discover them by using @code{grep} over *** 3118,3127 **** --- 3397,3410 ---- @example recode -l | grep -i mac @end example @noindent + @tindex macintosh@r{, a charset, and its aliases} + @tindex macintosh_ce@r{, and its aliases} + @tindex mac + @tindex macce Charsets @code{macintosh} and @code{macintosh_ce}, as well as their aliases @code{mac} and @code{macce} also have @code{CR} as their implied surface. There are a few discrepancies between the @code{Apple-Mac} charset and the very similar @w{RFC 1345} charset @code{macintosh}, which have not been *************** recode -vh macintosh..Latin-1 *** 3137,3153 **** --- 3420,3438 ---- @noindent The first command use the charset prior to @w{RFC 1345} introduction. Both methods give different recodings. These differences are annoying, the fuzziness will have to be explained and settle down one day. + @cindex @code{recode}, a Macintosh port As a side note, some people ask if there is a Macintosh port of the @code{recode} program. I'm not aware of any. I presume that if the tool fills a need for Macintosh users, someone will port it one of these days? @node AtariST, , Apple-Mac, Micros @section Atari ST code + @tindex AtariST This charset is available in @code{recode} under the name @code{AtariST}. This is the character set used on the Atari ST/TT/Falcon. This is similar to @code{IBM-PC}, but differs in some details: it includes some more accented characters, the graphic characters are mostly replaced by Hebrew characters, *************** difference between text and binary input *** 3159,3175 **** application how to interpret the data. In fact, most of the libraries that come with compilers can grok both @samp{\r\n} and @samp{\n} as end of lines. Many of the users who also have access to Unix systems prefer @samp{\n} to ease porting Unix utilities. So, for easing reversibility, @code{recode} tries to let @samp{\r} undisturbed through recodings. @node Miscellaneous, Surfaces, Micros, Top @chapter Various other charsets Even if these charsets were originally added to @code{recode} for handling texts written in French, they find other uses. We did use them ! lot for writing French diacriticised texts in the past, so @code{recode} knows how to handle these particularly well for French texts. @menu * HTML:: World Wide Web representations * LaTeX:: LaTeX macro calls --- 3444,3461 ---- application how to interpret the data. In fact, most of the libraries that come with compilers can grok both @samp{\r\n} and @samp{\n} as end of lines. Many of the users who also have access to Unix systems prefer @samp{\n} to ease porting Unix utilities. So, for easing reversibility, @code{recode} tries to let @samp{\r} undisturbed through recodings. + @c FIXME: did you mean \n in the last line? @node Miscellaneous, Surfaces, Micros, Top @chapter Various other charsets Even if these charsets were originally added to @code{recode} for handling texts written in French, they find other uses. We did use them ! a lot for writing French diacriticised texts in the past, so @code{recode} knows how to handle these particularly well for French texts. @menu * HTML:: World Wide Web representations * LaTeX:: LaTeX macro calls *************** knows how to handle these particularly w *** 3181,3190 **** --- 3467,3477 ---- @end menu @node HTML, LaTeX, Miscellaneous, Miscellaneous @section World Wide Web representations + @tindex HTML@r{, a charset} This charset is available in @code{recode} under the name @code{HTML}, with @code{h4} as an acceptable alias. @c FIXME - untrue HTML texts used by World Wide Web often use special sequences, beginning with *************** When you recode from another charset to *** 3204,3214 **** occurrences of double quotes, ampersands, and left or right angle brackets are translated into special sequences. However, in practice, people often use ampersands and angle brackets in the other charset for introducing HTML commands, compromising it: it is not pure HTML, not it is pure other charset. These particular translations can be rather inconvenient, ! they may be specifically inhibited through the command option @code{-d} (@pxref{Mixed}). Codes not having a mnemonic entity are output by @code{recode} using the @samp{&#@var{nnn};} notation, where @var{nnn} is a decimal representation of the UCS code value. When there is an entity name for a character, it --- 3491,3501 ---- occurrences of double quotes, ampersands, and left or right angle brackets are translated into special sequences. However, in practice, people often use ampersands and angle brackets in the other charset for introducing HTML commands, compromising it: it is not pure HTML, not it is pure other charset. These particular translations can be rather inconvenient, ! they may be specifically inhibited through the command option @samp{-d} (@pxref{Mixed}). Codes not having a mnemonic entity are output by @code{recode} using the @samp{&#@var{nnn};} notation, where @var{nnn} is a decimal representation of the UCS code value. When there is an entity name for a character, it *************** In addition, there are four entities for *** 3235,3269 **** @samp{&}, @samp{>}, @samp{<} and @samp{"}. @item @w{RFC 2070} (HTML-i18n) added entities to cover the whole right part of @w{ISO 8859-1}. The list is conveniently accessible at ! @url{http://www.alis.com:8085/ietf/html/html-latin1.sgml}. In addition, four i18n-related entities were added: @samp{‌} (@samp{‌}), @samp{‍} (@samp{‍}), @samp{‎} (@samp{‎}) and @samp{‏} (@samp{‏}). @item ! HTML 3.2 (@url{http://www.w3.org/TR/REC-html32.html}) took up the full @w{Latin-1} list but not the i18n-related entities from @w{RFC 2070}. @item ! HTML 4.0 (@url{http://www.w3.org/TR/REC-html40/}) has the whole @w{Latin-1} list, a set of entities for symbols, mathematical symbols, and Greek letters, and another set for markup-significant and internationalization characters comprising the 4 ASCII entities, the 4 i18n-related from @w{RFC 2070} plus some more. - @end itemize When @code{recode} translates to HTML, the translation occurs according ! to @url{http://www.w3.org/TR/REC-html40/sgml/entities.html}. @c Previously: http://www.uni-passau.de/~ramsch/iso8859-1.html It is also assumed that @w{RFC 1866} has an equivalent contents. When translating @emph{from} HTML, @code{recode} accepts some alternative special sequences, to be forgiving when files use older HTML tables. The @code{recode} program can be used to @emph{normalise} an HTML file using oldish conventions. For example, it accepts @samp{&AE;}, as this once was a valid writing, somewhere. However, it should always produce @samp{Æ} instead of @samp{&AE;}. Yet, this is not completely true. If one does: --- 3522,3558 ---- @samp{&}, @samp{>}, @samp{<} and @samp{"}. @item @w{RFC 2070} (HTML-i18n) added entities to cover the whole right part of @w{ISO 8859-1}. The list is conveniently accessible at ! @uref{http://www.alis.com:8085/ietf/html/html-latin1.sgml}. In addition, four i18n-related entities were added: @samp{‌} (@samp{‌}), @samp{‍} (@samp{‍}), @samp{‎} (@samp{‎}) and @samp{‏} (@samp{‏}). @item ! @uref{http://www.w3.org/TR/REC-html32.html, HTML 3.2} took up the full @w{Latin-1} list but not the i18n-related entities from @w{RFC 2070}. @item ! @uref{http://www.w3.org/TR/REC-html40/, HTML 4.0} has the whole ! @w{Latin-1} list, a set of entities for symbols, mathematical symbols, and Greek letters, and another set for markup-significant and internationalization characters comprising the 4 ASCII entities, the 4 i18n-related from @w{RFC 2070} plus some more. @end itemize When @code{recode} translates to HTML, the translation occurs according ! to @uref{http://www.w3.org/TR/REC-html40/sgml/entities.html}. @c Previously: http://www.uni-passau.de/~ramsch/iso8859-1.html It is also assumed that @w{RFC 1866} has an equivalent contents. When translating @emph{from} HTML, @code{recode} accepts some alternative special sequences, to be forgiving when files use older HTML tables. + @cindex normilise an HTML file + @cindex HTML normalization The @code{recode} program can be used to @emph{normalise} an HTML file using oldish conventions. For example, it accepts @samp{&AE;}, as this once was a valid writing, somewhere. However, it should always produce @samp{Æ} instead of @samp{&AE;}. Yet, this is not completely true. If one does: *************** recode h3..u2,u2..h3 < @var{input} *** 3284,3308 **** then @samp{&AE;} should be normalised into @samp{Æ} by the operation. @node LaTeX, Texinfo, HTML, Miscellaneous @section La@TeX{} macro calls This charset is available in @code{recode} under the name @code{LaTeX} and has @code{ltex} as an alias. It is used for ASCII files coded to be read by La@TeX{} or, in certain cases, by @TeX{}. Whenever you recode from another charset to @code{LaTeX}, beware that all occurrences of backslashes @kbd{\} are translated into the string @samp{\backslash@{@}}. However, in practice, people often use backslashes in the other charset for introducing @TeX{} commands, compromising it: it is not pure @TeX{}, nor it is pure other charset. This translation of backslashes into @samp{\backslash@{@}} can be rather inconvenient, ! it may be inhibited through the command option @code{-d} (@pxref{Mixed}). @node Texinfo, African, LaTeX, Miscellaneous @section GNU project documentation files This charset is available in @code{recode} under the name @code{Texinfo} and has @code{texi} and @code{ti} for aliases. It is used by the GNU project for its documentation. Texinfo files may be converted into Info files by the @code{makeinfo} program and into nice printed manuals by the @TeX{} system. --- 3573,3605 ---- then @samp{&AE;} should be normalised into @samp{Æ} by the operation. @node LaTeX, Texinfo, HTML, Miscellaneous @section La@TeX{} macro calls + @tindex LaTeX@r{, a charset} + @tindex ltex + @cindex La@TeX{} files + @cindex @TeX{} files This charset is available in @code{recode} under the name @code{LaTeX} and has @code{ltex} as an alias. It is used for ASCII files coded to be read by La@TeX{} or, in certain cases, by @TeX{}. Whenever you recode from another charset to @code{LaTeX}, beware that all occurrences of backslashes @kbd{\} are translated into the string @samp{\backslash@{@}}. However, in practice, people often use backslashes in the other charset for introducing @TeX{} commands, compromising it: it is not pure @TeX{}, nor it is pure other charset. This translation of backslashes into @samp{\backslash@{@}} can be rather inconvenient, ! it may be inhibited through the command option @samp{-d} (@pxref{Mixed}). @node Texinfo, African, LaTeX, Miscellaneous @section GNU project documentation files + @tindex Texinfo@r{, a charset} + @tindex texi + @tindex ti + @cindex Texinfo files This charset is available in @code{recode} under the name @code{Texinfo} and has @code{texi} and @code{ti} for aliases. It is used by the GNU project for its documentation. Texinfo files may be converted into Info files by the @code{makeinfo} program and into nice printed manuals by the @TeX{} system. *************** in correctly following these changes. S *** 3314,3349 **** --- 3611,3671 ---- @code{recode} should be considered as work still in progress (!). @node African, Cyrillic, Texinfo, Miscellaneous @section African charsets + @cindex African charsets Some African character sets are available for a few languages, when these are heavily used in countries where French is also currently spoken. + @tindex AFRFUL-102-BPI_OCIL@r{, and aliases} + @tindex bambara + @tindex bra + @tindex ewondo + @tindex fulfude + @tindex AFRFUL-103-BPI_OCIL@r{, and aliases} + @tindex t-bambara + @tindex t-bra + @tindex t-ewondo + @tindex t-fulfude One African charset is usable for Bambara, Ewondo and Fulfude, as well as for French. This charset is available in @code{recode} under the name @code{AFRFUL-102-BPI_OCIL}. Accepted aliases are @code{bambara}, @code{bra}, @code{ewondo} and @code{fulfude}. Transliterated forms of the same are available under the name @code{AFRFUL-103-BPI_OCIL}. Accepted aliases are @code{t-bambara}, @code{t-bra}, @code{t-ewondo} and @code{t-fulfude}. + @tindex AFRLIN-104-BPI_OCIL + @tindex lingala + @tindex lin + @tindex sango + @tindex wolof + @tindex AFRLIN-105-BPI_OCIL + @tindex t-lingala + @tindex t-lin + @tindex t-sango + @tindex t-wolof Another African charset is usable for Lingala, Sango and Wolof, as well as for French. This charset is available in @code{recode} under the name @code{AFRLIN-104-BPI_OCIL}. Accepted aliases are @code{lingala}, @code{lin}, @code{sango} and @code{wolof}. Transliterated forms of the same are available under the name @code{AFRLIN-105-BPI_OCIL}. Accepted aliases are @code{t-lingala}, @code{t-lin}, @code{t-sango} and @code{t-wolof}. + @tindex AFRL1-101-BPI_OCIL + @tindex t-francais + @tindex t-fra To ease exchange with @code{ISO-8859-1}, there is a charset conveying transliterated forms for @w{Latin-1} in a way which is compatible with the other African charsets in this series. This charset is available in @code{recode} under the name @code{AFRL1-101-BPI_OCIL}. Accepted aliases are @code{t-fra} and @code{t-francais}. @node Cyrillic, Texte, African, Miscellaneous @section Cyrillic charsets + @cindex Cyrillic charsets The following Cyrillic charsets are already available in @code{recode} through @w{RFC 1345} tables: @code{CP1251} with aliases @code{1251}, @code{ ms-cyrl} and @code{windows-1251}; @code{CSN_369103} with aliases @code{ISO-IR-139} and @code{KOI8_L2}; @code{ECMA-cyrillic} with aliases @code{ECMA-113}, @code{ECMA-113:1986} and @code{iso-ir-111}, @code{IBM880} *************** the extraneous tables describing them ar *** 3360,3384 **** Hopefully, in the long run, Cyrillic will be covered in Keld Simonsen's works to the satisfaction of everybody, and this section will merely disappear. @table @code @item KEYBCS2 This charset is available under the name @code{KEYBCS2}, with @code{Kamenicky} as an accepted alias. @item CORK This charset is available under the name @code{CORK}, with @code{T1} as an accepted alias. @item KOI-8_CS2 This charset is available under the name @code{KOI-8_CS2}. - @end table @node Texte, Mule, Cyrillic, Miscellaneous @section Easy French conventions This charset is available in @code{recode} under the name @code{Texte} and has @code{txte} for an alias. It is a seven bits code, identical to @code{ASCII-BS}, save for French diacritics which are noted using a slightly different convention. --- 3682,3712 ---- Hopefully, in the long run, Cyrillic will be covered in Keld Simonsen's works to the satisfaction of everybody, and this section will merely disappear. @table @code @item KEYBCS2 + @tindex KEYBCS2 + @tindex Kamenicky This charset is available under the name @code{KEYBCS2}, with @code{Kamenicky} as an accepted alias. @item CORK + @tindex CORK + @tindex T1 This charset is available under the name @code{CORK}, with @code{T1} as an accepted alias. @item KOI-8_CS2 + @tindex KOI-8_CS2 This charset is available under the name @code{KOI-8_CS2}. @end table @node Texte, Mule, Cyrillic, Miscellaneous @section Easy French conventions + @tindex Texte + @tindex txte This charset is available in @code{recode} under the name @code{Texte} and has @code{txte} for an alias. It is a seven bits code, identical to @code{ASCII-BS}, save for French diacritics which are noted using a slightly different convention. *************** of coding diacritics. Of course, it wou *** 3388,3397 **** --- 3716,3726 ---- keyboard to make direct eight bits entries and fonts for immediately displaying eight bit ISO @w{Latin-1} characters. But not everybody is so fortunate. In a few mailing environments, and sadly enough, it still happens that the eight bit is often willing-fully destroyed. + @cindex Easy French Easy French has been in use in France for a while. I only slightly adapted it (the diaeresis option) to make it more comfortable to several usages in Qu@'ebec originating from Universit@'e de Montr@'eal. In fact, the main problem for me was not to necessarily to invent Easy French, but to recognise the ``best'' convention to use, (best is not being defined, *************** for @kbd{c} with a cedilla. *** 3414,3427 **** @noindent There is no attempt at expressing the @kbd{ae} and @kbd{oe} diphthongs. French also uses tildes over @kbd{n} and @kbd{a}, but seldomly, and this is not represented either. In some countries, @kbd{:} is used instead of @kbd{"} to mark diaeresis. @code{recode} supports only one convention ! per call, depending on the @code{-c} option of the @code{recode} command. French quotes (sometimes called ``angle quotes'') are noted the same way English quotes are noted in @TeX{}, @emph{id est} by @kbd{``} and @kbd{''}. ! No effort has been put to preserve Latin ligatures (@kbd{ae}, @kbd{oe}) which are representable in several other charsets. So, these ligatures may be lost through Easy French conventions. The convention is prone to losing information, because the diacritic meaning overloads some characters that already have other uses. To --- 3743,3756 ---- @noindent There is no attempt at expressing the @kbd{ae} and @kbd{oe} diphthongs. French also uses tildes over @kbd{n} and @kbd{a}, but seldomly, and this is not represented either. In some countries, @kbd{:} is used instead of @kbd{"} to mark diaeresis. @code{recode} supports only one convention ! per call, depending on the @samp{-c} option of the @code{recode} command. French quotes (sometimes called ``angle quotes'') are noted the same way English quotes are noted in @TeX{}, @emph{id est} by @kbd{``} and @kbd{''}. ! No effort has been put to preserve Latin ligatures (@kbd{@ae{}}, @kbd{@oe{}}) which are representable in several other charsets. So, these ligatures may be lost through Easy French conventions. The convention is prone to losing information, because the diacritic meaning overloads some characters that already have other uses. To *************** There's a meeting at Archie's restaurant *** 3457,3477 **** the single quotes will be mistaken twice for acute accents. So English contractions and suffix possessives could be mangled. @item ! A double quote or colon, depending on @code{-c} option, which follows a vowel is interpreted as diaeresis only if it is followed by another letter. But there are in French several words that @emph{end} with a diaeresis, and the @code{recode} library is aware of them. There are words ending in ``igue'', either feminine words without a relative masculine (besaigu@"e and cigu@"e), or feminine words with a relative masculine@footnote{There are supposed to be seven words in this case. So, one is missing.} (aigu@"e, ambigu@"e, contigu@"e, exigu@"e, subaigu@"e and suraigu@"e). There are also words not ending in ``igue'', but instead, either ending by ``i''@footnote{Look at one of the following sentences (the second has to ! be interpreted with the @code{-c} option): @example "Ai"e! Voici le proble`me que j'ai" Ai:e! Voici le proble`me que j'ai: @end example --- 3786,3806 ---- the single quotes will be mistaken twice for acute accents. So English contractions and suffix possessives could be mangled. @item ! A double quote or colon, depending on @samp{-c} option, which follows a vowel is interpreted as diaeresis only if it is followed by another letter. But there are in French several words that @emph{end} with a diaeresis, and the @code{recode} library is aware of them. There are words ending in ``igue'', either feminine words without a relative masculine (besaigu@"e and cigu@"e), or feminine words with a relative masculine@footnote{There are supposed to be seven words in this case. So, one is missing.} (aigu@"e, ambigu@"e, contigu@"e, exigu@"e, subaigu@"e and suraigu@"e). There are also words not ending in ``igue'', but instead, either ending by ``i''@footnote{Look at one of the following sentences (the second has to ! be interpreted with the @samp{-c} option): @example "Ai"e! Voici le proble`me que j'ai" Ai:e! Voici le proble`me que j'ai: @end example *************** There is an ambiguity between an *** 3481,3490 **** --- 3810,3820 ---- a\"\i, @end tex @ifinfo ai", @end ifinfo + @c FIXME: why not use @dotless{} here? It works, AFAIK. @ignore a@"{@dotless{i}}, @end ignore the small animal, and the indicative future of @emph{avoir} (first person singular), when followed by what could be a diaeresis mark. Hopefully, *************** attention to proper nouns, but this one *** 3509,3524 **** Just to complete this topic, note that it would be wrong to make a rule for all words ending in ``igue'' as needing a diaerisis, as there are counter-examples (becfigue, b@`esigue, bigue, bordigue, bourdigue, brigue, contre-digue, digue, d'intrigue, fatigue, figue, garrigue, gigue, igue, intrigue, ligue, prodigue, sarigue and zigue). - @end enumerate @node Mule, , Texte, Miscellaneous @section Mule as a multiplexed charset This version of @code{recode} barely starts supporting multiplexed or super-charsets, that is, those encoding methods by which a single text stream may contain a combination of more than one constituent charset. The only multiplexed charset in @code{recode} is @code{Mule}, and even then, it is only very partially implemented: the only correspondence --- 3839,3856 ---- Just to complete this topic, note that it would be wrong to make a rule for all words ending in ``igue'' as needing a diaerisis, as there are counter-examples (becfigue, b@`esigue, bigue, bordigue, bourdigue, brigue, contre-digue, digue, d'intrigue, fatigue, figue, garrigue, gigue, igue, intrigue, ligue, prodigue, sarigue and zigue). @end enumerate @node Mule, , Texte, Miscellaneous @section Mule as a multiplexed charset + @tindex Mule@r{, a charset} + @cindex multiplexed charsets + @cindex super-charsets This version of @code{recode} barely starts supporting multiplexed or super-charsets, that is, those encoding methods by which a single text stream may contain a combination of more than one constituent charset. The only multiplexed charset in @code{recode} is @code{Mule}, and even then, it is only very partially implemented: the only correspondence *************** Multiplexed charsets are not to be confu *** 3531,3549 **** which charset is current, at any given place, are kind of informal, and driven from the semantics of what the file contains. On the other side, multiplexed charsets are @emph{designed} to be interpreted fairly precisely, and quite independently of any informational context. The spelling @code{Mule} originally stands for @cite{@emph{mul}tilingual @emph{e}nhancement to GNU Emacs}, it is the result of a collective ! effort orchestrated by Handa Ken'ishi since 1993. When @code{Mule} got rewritten in the main development stream of GNU Emacs 20, the FSF renamed it @code{MULE}, meaning @cite{@emph{mul}tilingual @emph{e}nvironment in GNU Emacs}. Even if the charset @code{Mule} is meant to stay internal to GNU Emacs, it sometimes breaks loose in external files, and as a consequence, a recoding tool is sometimes needed. Within Emacs, ! @code{Mule} comes with @code{leim}, which stands for @cite{@emph{l}ibraries of @emph{e}macs @emph{i}nput @emph{m}ethods}. One of these libraries is named @code{quail}@footnote{Usually, quail means quail egg in Japanese, while egg alone is usually chicken egg. Both quail egg and chicken egg are popular food in Japan. The @code{quail} input system has been named because it is smaller that the previous @code{EGG} system. --- 3863,3882 ---- which charset is current, at any given place, are kind of informal, and driven from the semantics of what the file contains. On the other side, multiplexed charsets are @emph{designed} to be interpreted fairly precisely, and quite independently of any informational context. + @cindex MULE, in Emacs The spelling @code{Mule} originally stands for @cite{@emph{mul}tilingual @emph{e}nhancement to GNU Emacs}, it is the result of a collective ! effort orchestrated by Handa Ken'ichi since 1993. When @code{Mule} got rewritten in the main development stream of GNU Emacs 20, the FSF renamed it @code{MULE}, meaning @cite{@emph{mul}tilingual @emph{e}nvironment in GNU Emacs}. Even if the charset @code{Mule} is meant to stay internal to GNU Emacs, it sometimes breaks loose in external files, and as a consequence, a recoding tool is sometimes needed. Within Emacs, ! @code{Mule} comes with @code{Leim}, which stands for @cite{@emph{l}ibraries of @emph{e}macs @emph{i}nput @emph{m}ethods}. One of these libraries is named @code{quail}@footnote{Usually, quail means quail egg in Japanese, while egg alone is usually chicken egg. Both quail egg and chicken egg are popular food in Japan. The @code{quail} input system has been named because it is smaller that the previous @code{EGG} system. *************** comes from the Japanese sentence @cite{@ *** 3553,3564 **** Of course, the publication of @code{EGG} has been delayed many times@dots{} (Story by Takahashi Naoto)}. @node Surfaces, Internals, Miscellaneous, Top @chapter All about surfaces ! The @dfn{trivial surface} consists into using a fixed number of bits (often eight) for each character, the bits together hold the integer value of the index for the character in its charset table. There are many kinds of surfaces, beyond the trivial one, all having the purpose of increasing selected qualities for the storage or transmission. For example, surfaces might increase the resistance to channel limits --- 3886,3899 ---- Of course, the publication of @code{EGG} has been delayed many times@dots{} (Story by Takahashi Naoto)}. @node Surfaces, Internals, Miscellaneous, Top @chapter All about surfaces + @cindex surface, what it is ! @cindex trivial surface ! The @dfn{trivial surface} consists of using a fixed number of bits (often eight) for each character, the bits together hold the integer value of the index for the character in its charset table. There are many kinds of surfaces, beyond the trivial one, all having the purpose of increasing selected qualities for the storage or transmission. For example, surfaces might increase the resistance to channel limits *************** surfaces were specifically designed for *** 3576,3596 **** not make much sense if applied to other charsets. In such cases, these conceptual surfaces have been implemented as @code{recode} charsets, instead of as surfaces. This choice yields to cleaner syntax and usage. @xref{Universal}. Surfaces are implemented within @code{recode} as special charsets which may only transform to or from the @code{data} special charset. Clever users may use this knowledge for writing surface names in requests exactly as if they were pure charsets, when the only need is to change surfaces without any kind of recoding between real charsets. In such contexts, @code{data} may also be used as if it were some kind of generic, anonymous charset: the request @samp{data..@var{surface}} merely adds the given @var{surface}, while the request @samp{@var{surface}..data} removes it. We are only beginning to experiment with surfaces in @code{recode}, but ! the concept opens the doors to many avenues, it is not clear yet which ones are worth pursuing, and which should be abandoned. This chapter presents all surfaces currently available. @menu * Permutations:: Permuting groups of bytes --- 3911,3933 ---- not make much sense if applied to other charsets. In such cases, these conceptual surfaces have been implemented as @code{recode} charsets, instead of as surfaces. This choice yields to cleaner syntax and usage. @xref{Universal}. + @cindex surfaces, implementation in @code{recode} + @tindex data@r{, a special charset} Surfaces are implemented within @code{recode} as special charsets which may only transform to or from the @code{data} special charset. Clever users may use this knowledge for writing surface names in requests exactly as if they were pure charsets, when the only need is to change surfaces without any kind of recoding between real charsets. In such contexts, @code{data} may also be used as if it were some kind of generic, anonymous charset: the request @samp{data..@var{surface}} merely adds the given @var{surface}, while the request @samp{@var{surface}..data} removes it. We are only beginning to experiment with surfaces in @code{recode}, but ! the concept opens the doors to many avenues; it is not clear yet which ones are worth pursuing, and which should be abandoned. This chapter presents all surfaces currently available. @menu * Permutations:: Permuting groups of bytes *************** presents all surfaces currently availabl *** 3600,3640 **** * Debugging:: Artificial data @end menu @node Permutations, End lines, Surfaces, Surfaces @section Permuting groups of bytes A permutation is a surface transformation which reorders groups of eight-bit bytes. A @emph{21} permutation exchanges pairs of successive bytes. If the text contains an odd number of bytes, the last byte is merely copied. An @emph{4321} permutation inverts the order of quadruples of bytes. If the text does not contains a multiple of four bytes, the remaining bytes are nevertheless permuted as @emph{321} if there are three bytes, @emph{21} if there are two bytes, or merely copied otherwise. @table @code @item 21 This surface is available in @code{recode} under the name @code{21-Permutation} and has @code{swabytes} for an alias. @item 4321 This surface is available in @code{recode} under the name @code{4321-Permutation}. - @end table @node End lines, MIME, Permutations, Surfaces @section Representation for end of lines The same charset might slightly differ, from one system to another, for the single fact that end of lines are not represented identically on all systems. The representation for an end of line within @code{recode} is the @code{ASCII} or @code{UCS} code with value 10, or @kbd{LF}. Other conventions for representing end of lines are available through surfaces. @table @code @item CR This convention is popular on Apple's Macintosh machines. When this surface is applied, each line is terminated by @kbd{CR}, which has @code{ASCII} value 13. Unless the library is operating in strict mode, adding or removing the surface will in fact @emph{exchange} @kbd{CR} and @kbd{LF}, for better reversibility. However, in strict mode, the exchange --- 3937,3984 ---- * Debugging:: Artificial data @end menu @node Permutations, End lines, Surfaces, Surfaces @section Permuting groups of bytes + @cindex permutations of groups of bytes + @cindex byte order swapping + @cindex endiannes, changing A permutation is a surface transformation which reorders groups of eight-bit bytes. A @emph{21} permutation exchanges pairs of successive bytes. If the text contains an odd number of bytes, the last byte is merely copied. An @emph{4321} permutation inverts the order of quadruples of bytes. If the text does not contains a multiple of four bytes, the remaining bytes are nevertheless permuted as @emph{321} if there are three bytes, @emph{21} if there are two bytes, or merely copied otherwise. @table @code @item 21 + @tindex 21-Permutation + @tindex swabytes This surface is available in @code{recode} under the name @code{21-Permutation} and has @code{swabytes} for an alias. @item 4321 + @tindex 4321-Permutation This surface is available in @code{recode} under the name @code{4321-Permutation}. @end table @node End lines, MIME, Permutations, Surfaces @section Representation for end of lines + @cindex end of line format The same charset might slightly differ, from one system to another, for the single fact that end of lines are not represented identically on all systems. The representation for an end of line within @code{recode} is the @code{ASCII} or @code{UCS} code with value 10, or @kbd{LF}. Other conventions for representing end of lines are available through surfaces. @table @code @item CR + @tindex CR@r{, a surface} This convention is popular on Apple's Macintosh machines. When this surface is applied, each line is terminated by @kbd{CR}, which has @code{ASCII} value 13. Unless the library is operating in strict mode, adding or removing the surface will in fact @emph{exchange} @kbd{CR} and @kbd{LF}, for better reversibility. However, in strict mode, the exchange *************** the surface, and any @kbd{LF} will be co *** 3644,3706 **** This surface is available in @code{recode} under the name @code{CR}, it does not have any aliases. This is the implied surface for the Apple Macintosh related charsets. @item CR-LF This convention is popular on Microsoft systems running on IBM PCs and compatible. When this surface is applied, each line is terminated by a sequence of two characters: one @kbd{CR} followed by one @kbd{LF}, in that order. For compatibility with oldish MS-DOS systems, removing a @code{CR-LF} surface will discard the first encountered @kbd{C-z}, which has @code{ASCII} value 26, and everything following it in the text. Adding this surface will not, however, append a @kbd{C-z} to the result. This surface is available in @code{recode} under the name @code{CR-LF} and has @code{cl} for an alias. This is the implied surface for the IBM or Microsoft related charsets or code pages. - @end table Some other charsets might have their own representation for an end of line, which is different from @kbd{LF}. For example, this is the case of various @code{EBCDIC} charsets, or @code{Icon-QNX}. The recoding of end of lines is intimately tied into such charsets, it is not available separately as surfaces. @node MIME, Dump, End lines, Surfaces @section MIME contents encodings @w{RFC 1521} defines two 7-bit surfaces, meant to prepare 8-bit messages for transmission. Base64 is especially usable for binary entities, while Quoted-Printable is especially usable for text entities, in those case the lower 128 characters of the underlying charset coincide with ASCII. @table @code @item Base64 This surface is available in @code{recode} under the name @code{Base64}, with @code{b64} and @code{64} as acceptable aliases. @item Quoted-Printable This surface is available in @code{recode} under the name @code{Quoted-Printable}, with @code{quote-printable} and @code{QP} as acceptable aliases. - @end table Note that @code{UTF-7}, which may be also considered as a MIME surface, is provided as a genuine charset instead, as it necessary relates to @code{UCS-2} and nothing else. @xref{UTF-7}. ! A little historical note, also showing the three levels of acceptation of Internet standards. MIME changed from a ``Proposed Standard'' to a ``Draft Standard'' in 1993, and only became a ``Full Standard'' during 1996-12. @node Dump, Debugging, MIME, Surfaces @section Interpreted character dumps Dumps are surfaces meant to express, in ways which are a bit more readable, the bit patterns used to represent characters. They allow the inspection or debugging of character streams, but also, they may assist a bit the production of C source code which, once compiled, would hold in memory a copy of the original coding. However, @code{recode} does not attempt, in --- 3988,4060 ---- This surface is available in @code{recode} under the name @code{CR}, it does not have any aliases. This is the implied surface for the Apple Macintosh related charsets. @item CR-LF + @tindex CR-LF@r{, a surface} This convention is popular on Microsoft systems running on IBM PCs and compatible. When this surface is applied, each line is terminated by a sequence of two characters: one @kbd{CR} followed by one @kbd{LF}, in that order. + @cindex Ctrl-Z, discarding For compatibility with oldish MS-DOS systems, removing a @code{CR-LF} surface will discard the first encountered @kbd{C-z}, which has @code{ASCII} value 26, and everything following it in the text. Adding this surface will not, however, append a @kbd{C-z} to the result. + @tindex cl This surface is available in @code{recode} under the name @code{CR-LF} and has @code{cl} for an alias. This is the implied surface for the IBM or Microsoft related charsets or code pages. @end table Some other charsets might have their own representation for an end of line, which is different from @kbd{LF}. For example, this is the case of various @code{EBCDIC} charsets, or @code{Icon-QNX}. The recoding of end of lines is intimately tied into such charsets, it is not available separately as surfaces. @node MIME, Dump, End lines, Surfaces @section MIME contents encodings + @cindex MIME encodings + @cindex RFC 1521 @w{RFC 1521} defines two 7-bit surfaces, meant to prepare 8-bit messages for transmission. Base64 is especially usable for binary entities, while Quoted-Printable is especially usable for text entities, in those case the lower 128 characters of the underlying charset coincide with ASCII. @table @code @item Base64 + @tindex Base64 + @tindex b64 + @tindex 64 This surface is available in @code{recode} under the name @code{Base64}, with @code{b64} and @code{64} as acceptable aliases. @item Quoted-Printable + @tindex Quoted-Printable + @tindex quote-printable + @tindex QP This surface is available in @code{recode} under the name @code{Quoted-Printable}, with @code{quote-printable} and @code{QP} as acceptable aliases. @end table Note that @code{UTF-7}, which may be also considered as a MIME surface, is provided as a genuine charset instead, as it necessary relates to @code{UCS-2} and nothing else. @xref{UTF-7}. ! A little historical note, also showing the three levels of acceptance of Internet standards. MIME changed from a ``Proposed Standard'' to a ``Draft Standard'' in 1993, and only became a ``Full Standard'' during 1996-12. @node Dump, Debugging, MIME, Surfaces @section Interpreted character dumps + @cindex dumping characters Dumps are surfaces meant to express, in ways which are a bit more readable, the bit patterns used to represent characters. They allow the inspection or debugging of character streams, but also, they may assist a bit the production of C source code which, once compiled, would hold in memory a copy of the original coding. However, @code{recode} does not attempt, in *************** for that last chunk only. Such a shorte *** 3717,3797 **** properly within a C initialiser, as all members of an array share a single type, and so, have identical sizes. @table @code @item Octal-1 This surface corresponds to an octal expression of each input byte. It is available in @code{recode} under the name @code{Octal-1}, with @code{o1} and @code{o} as acceptable aliases. @item Octal-2 This surface corresponds to an octal expression of each pair of input bytes, except for the last pair, which may be short. It is available in @code{recode} under the name @code{Octal-2} and has @code{o2} for an alias. @item Octal-4 This surface corresponds to an octal expression of each quadruple of input bytes, except for the last quadruple, which may be short. It is available in @code{recode} under the name @code{Octal-4} and has @code{o4} for an alias. @item Decimal-1 This surface corresponds to an decimal expression of each input byte. It is available in @code{recode} under the name @code{Decimal-1}, with @code{d1} and @code{d} as acceptable aliases. @item Decimal-2 This surface corresponds to an decimal expression of each pair of input bytes, except for the last pair, which may be short. It is available in @code{recode} under the name @code{Decimal-2} and has @code{d2} for an alias. @item Decimal-4 This surface corresponds to an decimal expression of each quadruple of input bytes, except for the last quadruple, which may be short. It is available in @code{recode} under the name @code{Decimal-4} and has @code{d4} for an alias. @item Hexadecimal-1 This surface corresponds to an hexadecimal expression of each input byte. It is available in @code{recode} under the name @code{Hexadecimal-1}, with @code{x1} and @code{x} as acceptable aliases. @item Hexadecimal-2 This surface corresponds to an hexadecimal expression of each pair of input bytes, except for the last pair, which may be short. It is available in @code{recode} under the name @code{Hexadecimal-2}, with @code{x2} for an alias. @item Hexadecimal-4 This surface corresponds to an hexadecimal expression of each quadruple of input bytes, except for the last quadruple, which may be short. It is available in @code{recode} under the name @code{Hexadecimal-4}, with @code{x4} for an alias. - @end table When removing a dump surface, that is, when reading a dump results back into a sequence of bytes, the narrower expression for a short last chunk is recognised, so dumping is a fully reversible operation. However, in ! case you want do produce dumps by other means than through @code{recode}, beware that for decimal dumps, the library has to rely on the number of spaces to establish the original byte size of the chunk. ! Despite the library might report reversibility errors, removing a dump ! surface is a rather forgiving process: one may mix bases, group more or ! less numbers per source line, or use shorter chunks elsewhere than at the far end. Also, source lines not beginning with a number are skipped. So, @code{recode} should often be able to read a whole C header file, wrapping the results of a previous dump, and regenerate the original byte string. @node Debugging, , Dump, Surfaces --- 4071,4169 ---- properly within a C initialiser, as all members of an array share a single type, and so, have identical sizes. @table @code @item Octal-1 + @tindex Octal-1 + @tindex o1 This surface corresponds to an octal expression of each input byte. It is available in @code{recode} under the name @code{Octal-1}, with @code{o1} and @code{o} as acceptable aliases. @item Octal-2 + @tindex Octal-2 + @tindex o2 This surface corresponds to an octal expression of each pair of input bytes, except for the last pair, which may be short. It is available in @code{recode} under the name @code{Octal-2} and has @code{o2} for an alias. @item Octal-4 + @tindex Octal-4 + @tindex o4 This surface corresponds to an octal expression of each quadruple of input bytes, except for the last quadruple, which may be short. It is available in @code{recode} under the name @code{Octal-4} and has @code{o4} for an alias. @item Decimal-1 + @tindex Decimal-1 + @tindex d1 This surface corresponds to an decimal expression of each input byte. It is available in @code{recode} under the name @code{Decimal-1}, with @code{d1} and @code{d} as acceptable aliases. @item Decimal-2 + @tindex Decimal-2 + @tindex d2 This surface corresponds to an decimal expression of each pair of input bytes, except for the last pair, which may be short. It is available in @code{recode} under the name @code{Decimal-2} and has @code{d2} for an alias. @item Decimal-4 + @tindex Decimal-4 + @tindex d4 This surface corresponds to an decimal expression of each quadruple of input bytes, except for the last quadruple, which may be short. It is available in @code{recode} under the name @code{Decimal-4} and has @code{d4} for an alias. @item Hexadecimal-1 + @tindex Hexadecimal-1 + @tindex x1 This surface corresponds to an hexadecimal expression of each input byte. It is available in @code{recode} under the name @code{Hexadecimal-1}, with @code{x1} and @code{x} as acceptable aliases. @item Hexadecimal-2 + @tindex Hexadecimal-2 + @tindex x2 This surface corresponds to an hexadecimal expression of each pair of input bytes, except for the last pair, which may be short. It is available in @code{recode} under the name @code{Hexadecimal-2}, with @code{x2} for an alias. @item Hexadecimal-4 + @tindex Hexadecimal-4 + @tindex x4 This surface corresponds to an hexadecimal expression of each quadruple of input bytes, except for the last quadruple, which may be short. It is available in @code{recode} under the name @code{Hexadecimal-4}, with @code{x4} for an alias. @end table When removing a dump surface, that is, when reading a dump results back into a sequence of bytes, the narrower expression for a short last chunk is recognised, so dumping is a fully reversible operation. However, in ! case you want to produce dumps by other means than through @code{recode}, beware that for decimal dumps, the library has to rely on the number of spaces to establish the original byte size of the chunk. ! Although the library might report reversibility errors, removing a dump ! surface is a rather forgiving process: one may mix bases, group a variable ! number of data per source line, or use shorter chunks in places other ! than at the far end. Also, source lines not beginning with a number are skipped. So, @code{recode} should often be able to read a whole C header file, wrapping the results of a previous dump, and regenerate the original byte string. @node Debugging, , Dump, Surfaces *************** the results of a previous dump, and rege *** 3800,3809 **** --- 4172,4182 ---- A few pseudo-surfaces exist to generate debugging data out of thin air. These surfaces are only meant for the expert @code{recode} user, and are only useful in a few contexts, like for generating binary permutations from the recoding or acting on them. + @cindex debugging surfaces Debugging surfaces, @emph{when removed}, insert their generated data at the beginning of the output stream, and copy all the input stream after the generated data, unchanged. This strange removal constraint comes from the fact that debugging surfaces are usually specified in the @emph{before} position instead of the @emph{after} position within a request. *************** effect is an @emph{impression} that debu *** 3815,3856 **** left to right, each appending to the result of the previous. In any case, any real input data gets appended after what was generated. @table @code @item test7 When removed, this surface produces 128 single bytes, the first having value 0, the second having value 1, and so forth until all 128 values have been generated. @item test8 When removed, this surface produces 256 single bytes, the first having value 0, the second having value 1, and so forth until all 256 values have been generated. @item test15 When removed, this surface produces 64509 double bytes, the first having value 0, the second having value 1, and so forth until all values have been generated, but excluding risky @code{UCS-2} values, like all codes from the surrogate @code{UCS-2} area (for @code{UTF-16}), the byte order mark, and values known as invalid @code{UCS-2}. @item test16 When removed, this surface produces 65536 double bytes, the first having value 0, the second having value 1, and so forth until all 65536 values have been generated. - @end table ! For an example, the command @samp{recode l5/test8..dump < /dev/null} is a convoluted way to produce an output similar to @samp{recode -lf l5}. It says to generate all possible 256 bytes and interpret them as @code{ISO-8859-9} codes, while converting them to @code{UCS-2}. Resulting @code{UCS-2} characters are dumped one per line, accompanied with their explicative name. ! @node Internals, , Surfaces, Top @chapter Internal aspects The incoming explanations of the internals of @code{recode} should help people who want to dive into @code{recode} sources for adding new charsets. Adding new charsets does not require much knowledge about the overall organisation of @code{recode}. You can rather concentrate of your new charset, letting the remainder of the @code{recode} --- 4188,4234 ---- left to right, each appending to the result of the previous. In any case, any real input data gets appended after what was generated. @table @code @item test7 + @tindex test7 When removed, this surface produces 128 single bytes, the first having value 0, the second having value 1, and so forth until all 128 values have been generated. @item test8 + @tindex test8 When removed, this surface produces 256 single bytes, the first having value 0, the second having value 1, and so forth until all 256 values have been generated. @item test15 + @tindex test15 When removed, this surface produces 64509 double bytes, the first having value 0, the second having value 1, and so forth until all values have been generated, but excluding risky @code{UCS-2} values, like all codes from the surrogate @code{UCS-2} area (for @code{UTF-16}), the byte order mark, and values known as invalid @code{UCS-2}. @item test16 + @tindex test16 When removed, this surface produces 65536 double bytes, the first having value 0, the second having value 1, and so forth until all 65536 values have been generated. @end table ! As an example, the command @samp{recode l5/test8..dump < /dev/null} is a convoluted way to produce an output similar to @samp{recode -lf l5}. It says to generate all possible 256 bytes and interpret them as @code{ISO-8859-9} codes, while converting them to @code{UCS-2}. Resulting @code{UCS-2} characters are dumped one per line, accompanied with their explicative name. ! @node Internals, Concept Index, Surfaces, Top @chapter Internal aspects + @cindex @code{recode} internals + @cindex internals The incoming explanations of the internals of @code{recode} should help people who want to dive into @code{recode} sources for adding new charsets. Adding new charsets does not require much knowledge about the overall organisation of @code{recode}. You can rather concentrate of your new charset, letting the remainder of the @code{recode} *************** Autoconf, Automake and @code{libtool} fo *** 3872,3881 **** --- 4250,4260 ---- * Design:: Comments on the library design @end menu @node Main flow, New charsets, Internals, Internals @section Overall organisation + @cindex @code{recode}, main flow of operation The @code{recode} mechanics slowly evolved for many years, and it would be tedious to explain all problems I met and mistakes I did all along, yielding the current behaviour. Surely, one of the key choices was to stop trying to do all conversions in memory, one line or one *************** paradigm, and the elementary recoding st *** 3884,3893 **** --- 4263,4273 ---- to another. Most of the control complexity in @code{recode} exists so that each elementary recoding step stays simple, making easier to add new ones. The whole point of @code{recode}, as I see it, is providing a comfortable nest for growing new charset conversions. + @cindex single step The main @code{recode} driver constructs, while initialising all conversion modules, a table giving all the conversion routines available (@dfn{single step}s) and for each, the starting charset and the ending charset. If we consider these charsets as being the nodes of a directed graph, each single step may be considered as oriented *************** character, etc. *** 3899,3917 **** Given a starting code and a goal code, @code{recode} computes the most economical route through the elementary recodings, that is, the best sequence of conversions that will transform the input charset into the final charset. To speed up execution, @code{recode} looks for ! subsequences of conversions which are simple enough to be merged, it then dynamically creates new single steps to represent these mergings. A @dfn{double step} in @code{recode} is a special concept representing a sequence of two single steps, the output of the first single step being the special charset @code{UCS-2}, the input of the second single step being also @code{UCS-2}. Special @code{recode} machinery dynamically produces efficient, reversible, merge-able single steps out of these double steps. I made some statistics about how many internal recoding steps are required between any two charsets chosen at random. The initial recoding layout, before optimisation, always uses between 1 and 6 steps. Optimisation could sometimes produce mere copies, which are counted as no steps at all. In other cases, optimisation is unable to save any step. The number of --- 4279,4300 ---- Given a starting code and a goal code, @code{recode} computes the most economical route through the elementary recodings, that is, the best sequence of conversions that will transform the input charset into the final charset. To speed up execution, @code{recode} looks for ! subsequences of conversions which are simple enough to be merged, and then dynamically creates new single steps to represent these mergings. + @cindex double step A @dfn{double step} in @code{recode} is a special concept representing a sequence of two single steps, the output of the first single step being the special charset @code{UCS-2}, the input of the second single step being also @code{UCS-2}. Special @code{recode} machinery dynamically produces efficient, reversible, merge-able single steps out of these double steps. + @cindex recoding steps, statistics + @cindex average number of recoding steps I made some statistics about how many internal recoding steps are required between any two charsets chosen at random. The initial recoding layout, before optimisation, always uses between 1 and 6 steps. Optimisation could sometimes produce mere copies, which are counted as no steps at all. In other cases, optimisation is unable to save any step. The number of *************** Number of steps run between 1 and 6, bot *** 3926,3935 **** --- 4309,4320 ---- and the expected number of steps decreases by a lesser amount, going from 2.2 to 1.3. This is still manageable. @node New charsets, New surfaces, Main flow, Internals @section Adding new charsets + @cindex adding new charsets + @cindex new charsets, how to add The main part of @code{recode} is written in C, as are most single steps. A few single steps need to recognise sequences of multiple characters, they are often better written in Flex. It is easy for a programmer to add a new charset to @code{recode}. All it requires *************** If you do not need such delayed initiali *** 3982,3994 **** for the function argument. The second function executes the elementary recoding on a whole file. There are a few cases when you can spare writing this function: @itemize @bullet - @item Some single steps do nothing else than a pure copy of the input onto the output, in this case, you can use the predefined function @code{file_one_to_one}, while having a delayed initialisation for presetting the @code{STEP} field @code{one_to_one} to the predefined value @code{one_to_same}. --- 4367,4380 ---- for the function argument. The second function executes the elementary recoding on a whole file. There are a few cases when you can spare writing this function: + @c FIXME: functions file_one_to_one and file_one_to_many don't exist! @itemize @bullet @item + @findex file_one_to_one Some single steps do nothing else than a pure copy of the input onto the output, in this case, you can use the predefined function @code{file_one_to_one}, while having a delayed initialisation for presetting the @code{STEP} field @code{one_to_one} to the predefined value @code{one_to_same}. *************** Some single steps are driven by a table *** 3998,4041 **** another; if the recoding does nothing else, you can use the predefined function @code{file_one_to_one}, while having a delayed initialisation for presetting the @code{STEP} field @code{one_to_one} with your table. @item Some single steps are driven by a table which recodes one character into a string; if the recoding does nothing else, you can use the predefined function @code{file_one_to_many}, while having a delayed initialisation for presetting the @code{STEP} field @code{one_to_many} with your table. - @end itemize If you have a recoding table handy in a suitable format but do not use one of the predefined recoding functions, it is still a good idea to use a delayed initialisation to save it anyway, because @code{recode} option ! @code{-h} will take advantage of this information when available. Finally, edit @file{Makefile.am} to add the source file name of your routines to the @code{C_STEPS} or @code{L_STEPS} macro definition, depending on the fact your routines is written in C or in Flex. @node New surfaces, Design, New charsets, Internals @section Adding new surfaces Adding a new surface is technically quite similar to adding a new charset. @xref{New charsets}. A surface is provided as a set of two transformations: one from the predefined special charset @code{data} to the new surface, meant to apply the surface, the other from the new surface to the predefined special charset @code{data}, meant to remove the surface. Internally in @code{recode}, function @code{declare_step} especially recognises when a charset is so related to @code{data}, and then takes appropriate actions so that charset gets indeed installed as a surface. @node Design, , New surfaces, Internals @section Comments on the library design @itemize @bullet @item Why a shared library? There are many different approaches to reduce system requirements to handle all tables needed in the @code{recode} library. One of them is to have the tables in an external format and only read them in on demand. After having pondered this for a while, I finally decided against it, --- 4384,4431 ---- another; if the recoding does nothing else, you can use the predefined function @code{file_one_to_one}, while having a delayed initialisation for presetting the @code{STEP} field @code{one_to_one} with your table. @item + @findex file_one_to_many Some single steps are driven by a table which recodes one character into a string; if the recoding does nothing else, you can use the predefined function @code{file_one_to_many}, while having a delayed initialisation for presetting the @code{STEP} field @code{one_to_many} with your table. @end itemize If you have a recoding table handy in a suitable format but do not use one of the predefined recoding functions, it is still a good idea to use a delayed initialisation to save it anyway, because @code{recode} option ! @samp{-h} will take advantage of this information when available. Finally, edit @file{Makefile.am} to add the source file name of your routines to the @code{C_STEPS} or @code{L_STEPS} macro definition, depending on the fact your routines is written in C or in Flex. @node New surfaces, Design, New charsets, Internals @section Adding new surfaces + @cindex adding new surfaces + @cindex new surfaces, how to add Adding a new surface is technically quite similar to adding a new charset. @xref{New charsets}. A surface is provided as a set of two transformations: one from the predefined special charset @code{data} to the new surface, meant to apply the surface, the other from the new surface to the predefined special charset @code{data}, meant to remove the surface. + @findex declare_step Internally in @code{recode}, function @code{declare_step} especially recognises when a charset is so related to @code{data}, and then takes appropriate actions so that charset gets indeed installed as a surface. @node Design, , New surfaces, Internals @section Comments on the library design @itemize @bullet @item Why a shared library? + @cindex shared library implementation There are many different approaches to reduce system requirements to handle all tables needed in the @code{recode} library. One of them is to have the tables in an external format and only read them in on demand. After having pondered this for a while, I finally decided against it, *************** this allowed me to tidy up the API, get *** 4062,4072 **** It required a surprising amount of program source massaging. But once this cleaned enough, it was easy to use Gordon Matzigkeit's @code{libtool} package, and take advantage of the Automake interface to neatly turn the non-shared library into a shared one. ! Sites linking with the @code{recode} library, while their system does not support any form of shared libraries, might end up with bulky executables. Surely, the @code{recode} library will have to be used statically, and might not very nicely usable on such systems. It seems that progress has a price for those being slow at it. --- 4452,4462 ---- It required a surprising amount of program source massaging. But once this cleaned enough, it was easy to use Gordon Matzigkeit's @code{libtool} package, and take advantage of the Automake interface to neatly turn the non-shared library into a shared one. ! Sites linking with the @code{recode} library, whose system does not support any form of shared libraries, might end up with bulky executables. Surely, the @code{recode} library will have to be used statically, and might not very nicely usable on such systems. It seems that progress has a price for those being slow at it. *************** around @code{UCS-2} (nor @code{UCS-4}) f *** 4118,4127 **** --- 4508,4518 ---- one day, but it will come out of the natural evolution of @code{recode}. It will then reflect a fact, rather than a preset dogma. @item Why not @code{iconv}? + @cindex @code{iconv} The @code{iconv} routine and library allows for converting characters from an input buffer to an input buffer, synchronously advancing both buffer cursors. If the output buffer is not big enough to receive all of the conversion, the routine returns with the input cursor set at the position where the conversion could later be resumed, and the output *************** arbitrary limitations. In the long run, *** 4176,4189 **** to our users that some recodings may not be made available just because they do not fit the simple model we had in mind when we did it. Instead, we should try to stay opened to the difficulties of real life. There is still a lot of complex needs for Asian people, say, that @code{recode} does not currently address, while it should. Not only the doors should ! stay opened, but we should force them wider! ! @end itemize @contents @bye @c Local Variables: @c texinfo-column-for-description: 24 --- 4567,4608 ---- to our users that some recodings may not be made available just because they do not fit the simple model we had in mind when we did it. Instead, we should try to stay opened to the difficulties of real life. There is still a lot of complex needs for Asian people, say, that @code{recode} does not currently address, while it should. Not only the doors should ! stay open, but we should force them wider! @end itemize + @node Concept Index, Option Index, Internals, Top + @unnumbered Concept Index + + @printindex cp + + @node Option Index, Library Index, Concept Index, Top + @unnumbered Option Index + + This is an alphabetical list of all command-line options accepted by + @code{recode}. + + @printindex op + + @node Library Index, Charset and Surface Index, Option Index, Top + @unnumbered Library Index + + This is an alphabetical index of important functions, data structures, + and variables in the @code{recode} library. + + @printindex fn + + @node Charset and Surface Index, , Library Index, Top + @unnumbered Charset and Surface Index + + This is an alphabetical list of all the charsets and surfaces supported + by @code{recode}, and their aliases. + + @printindex tp + @contents @bye @c Local Variables: @c texinfo-column-for-description: 24 diff -acprNC5 recode-3.5.orig/doc/tables.pl recode-3.5.djgpp/doc/tables.pl *** recode-3.5.orig/doc/tables.pl Mon Apr 26 02:26:02 1999 --- recode-3.5.djgpp/doc/tables.pl Sun Jun 17 23:56:02 2001 *************** *** 1,6 **** --- 1,7 ---- #!/usr/bin/perl -w + # -*- coding: latin-1 -*- # Automatically derive `recode' table files from various sources. # Copyright © 1993, 1994, 1997, 1998, 1999 Free Software Foundation, Inc. # François Pinard , 1993. # This program is free software; you can redistribute it and/or modify *************** sub produce_texinfo { *** 1171,1185 **** --- 1172,1192 ---- open OUTPUT, ">$output_name" or die "Cannot create $output_name\n"; warn "Writing $output_name\n"; for $charset (sort keys %body) { print OUTPUT "\n\@item $charset\n"; + print OUTPUT "\@tindex $charset\@r{, aliases and source}\n"; @list = sort (split (/,/, $list{$charset})); if (@list == 1) { + print OUTPUT '@tindex ', $list[0], "\n"; print OUTPUT '@code{', $list[0], "} is an alias for this charset.\n"; } elsif (@list > 0) { + # FIXME: Here, I suggest to output, for every alias name, + # an index entry like this: + # + # @tindex ALIAS-NAME $string = '@code{' . join ('}, @code{', @list) . '}'; $string =~ s/,([^,]+)$/ and$1/; print OUTPUT $string, " are aliases for this charset.\n"; } print OUTPUT $body{$charset}; diff -acprNC5 recode-3.5.orig/src/html.c recode-3.5.djgpp/src/html.c *** recode-3.5.orig/src/html.c Wed Mar 17 08:05:10 1999 --- recode-3.5.djgpp/src/html.c Sun Jun 17 23:56:02 2001 *************** *** 1,9 **** --- 1,10 ---- /* Conversion of files between different charsets and surfaces. Copyright © 1990, 93, 97, 98, 99 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by François Pinard , 1988. + Contributed by Daniel Taupin , 2000. The `recode' Library is free software; you can redistribute it and/or modify it under the terms of the GNU Library General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. *************** init_ucs2_html_v40 (RECODE_STEP step, *** 505,514 **** --- 506,517 ---- static bool transform_ucs2_html (RECODE_CONST_STEP step, RECODE_TASK task) { Hash_table *table = step->step_table; unsigned value; + unsigned quotient; + unsigned char chquotient; while (get_ucs2 (&value, step, task)) { struct ucs2_to_string lookup; struct ucs2_to_string *entry; *************** transform_ucs2_html (RECODE_CONST_STEP s *** 535,545 **** put_byte ('#', task); while (divider > value) divider /= 10; while (divider) { ! put_byte ('0' + value / divider, task); divider /= 10; } put_byte (';', task); } else --- 538,551 ---- put_byte ('#', task); while (divider > value) divider /= 10; while (divider) { ! quotient = value/divider; ! chquotient = '0' + quotient; ! put_byte (chquotient, task); ! value -= divider*quotient; /* this was the mistake - DT */ divider /= 10; } put_byte (';', task); } else diff -acprNC5 recode-3.5.orig/tests/testsuite recode-3.5.djgpp/tests/testsuite *** recode-3.5.orig/tests/testsuite Fri Apr 2 23:56:36 1999 --- recode-3.5.djgpp/tests/testsuite Sun Jun 17 23:56:02 2001 *************** *** 1,6 **** --- 1,7 ---- #!/bin/sh + # -*- coding: latin-1 -*- # Validation suite for the Free `recode' program and library. # Copyright © 1998, 1999 Progiciels Bourbeau-Pinard inc. # François Pinard , 1998. # Still many parts of `recode' are not exercised by the test suite. A few *************** done *** 36,46 **** # Option `-u' might be less portable, so either change it or use GNU `diff'. if test -n "$at_verbose"; then at_diff='diff -u' else ! at_diff='cmp -s' fi # Each generated debugging script, containing a single test group, cleans # up files at the beginning only, not at the end. This is so we can repeat # the script many times and browse left over files. To cope with such left --- 37,51 ---- # Option `-u' might be less portable, so either change it or use GNU `diff'. if test -n "$at_verbose"; then at_diff='diff -u' else ! if test -n "$COMSPEC$ComSpec"; then ! at_diff='diff -u' ! else ! at_diff='cmp -s' ! fi fi # Each generated debugging script, containing a single test group, cleans # up files at the beginning only, not at the end. This is so we can repeat # the script many times and browse left over files. To cope with such left *************** rm -rf input output stdout stderr *** 1511,1521 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:56: Testing block of lines to Decimal-1' echo dumps.m4:56 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../d1 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 1516,1526 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:56: Testing block of lines to Decimal-1' echo dumps.m4:56 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../d1 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 1580,1591 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../d1 output ! recode /d1 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 1585,1596 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../d1 output ! recode /d1../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:88 > at-check-line *** 1636,1647 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../d1 output ! recode /d1 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 1641,1652 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../d1 output ! recode /d1../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 1756,1766 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:138: Testing block of lines to Decimal-2' echo dumps.m4:138 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../d2 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 1761,1771 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:138: Testing block of lines to Decimal-2' echo dumps.m4:138 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../d2 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 1822,1833 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../d2 output ! recode /d2 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 1827,1838 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../d2 output ! recode /d2../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:170 > at-check-line *** 1878,1889 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../d2 output ! recode /d2 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 1883,1894 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../d2 output ! recode /d2../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 1998,2008 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:220: Testing block of lines to Decimal-4' echo dumps.m4:220 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../d4 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 2003,2013 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:220: Testing block of lines to Decimal-4' echo dumps.m4:220 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../d4 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 2064,2075 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../d4 output ! recode /d4 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 2069,2080 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../d4 output ! recode /d4../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:252 > at-check-line *** 2120,2131 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../d4 output ! recode /d4 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 2125,2136 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../d4 output ! recode /d4../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 2248,2258 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:317: Testing block of lines to Hexadecimal-1' echo dumps.m4:317 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../x1 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 2253,2263 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:317: Testing block of lines to Hexadecimal-1' echo dumps.m4:317 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../x1 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 2321,2332 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../x1 output ! recode /x1 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 2326,2337 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../x1 output ! recode /x1../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:349 > at-check-line *** 2377,2388 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../x1 output ! recode /x1 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 2382,2393 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../x1 output ! recode /x1../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 2501,2511 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:406: Testing block of lines to Hexadecimal-2' echo dumps.m4:406 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../x2 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 2506,2516 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:406: Testing block of lines to Hexadecimal-2' echo dumps.m4:406 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../x2 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 2570,2581 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../x2 output ! recode /x2 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 2575,2586 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../x2 output ! recode /x2../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:438 > at-check-line *** 2626,2637 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../x2 output ! recode /x2 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 2631,2642 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../x2 output ! recode /x2../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 2746,2756 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:486: Testing block of lines to Hexadecimal-4' echo dumps.m4:486 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../x4 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 2751,2761 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:486: Testing block of lines to Hexadecimal-4' echo dumps.m4:486 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../x4 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 2810,2821 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../x4 output ! recode /x4 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 2815,2826 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../x4 output ! recode /x4../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:518 > at-check-line *** 2866,2877 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../x4 output ! recode /x4 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 2871,2882 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../x4 output ! recode /x4../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 2994,3004 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:583: Testing block of lines to Octal-1' echo dumps.m4:583 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../o1 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 2999,3009 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:583: Testing block of lines to Octal-1' echo dumps.m4:583 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../o1 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 3067,3078 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../o1 output ! recode /o1 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 3072,3083 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../o1 output ! recode /o1../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:615 > at-check-line *** 3123,3134 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../o1 output ! recode /o1 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 3128,3139 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../o1 output ! recode /o1../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 3247,3257 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:672: Testing block of lines to Octal-2' echo dumps.m4:672 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../o2 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 3252,3262 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:672: Testing block of lines to Octal-2' echo dumps.m4:672 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../o2 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 3316,3327 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../o2 output ! recode /o2 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 3321,3332 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../o2 output ! recode /o2../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:704 > at-check-line *** 3372,3383 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../o2 output ! recode /o2 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 3377,3388 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../o2 output ! recode /o2../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf input output stdout stderr *** 3496,3506 **** test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:761: Testing block of lines to Octal-4' echo dumps.m4:761 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../o4 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 3501,3511 ---- test -n "$at_verbose" \ && echo $srcdir'/dumps.m4:761: Testing block of lines to Octal-4' echo dumps.m4:761 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../o4 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 3565,3576 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../o4 output ! recode /o4 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 3570,3581 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../o4 output ! recode /o4../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo dumps.m4:793 > at-check-line *** 3621,3632 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../o4 output ! recode /o4 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 3626,3637 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../o4 output ! recode /o4../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** rm -rf stdout stderr *** 3738,3748 **** test -n "$at_verbose" \ && echo $srcdir'/base64.m4:36: Testing block of lines to Base64' echo base64.m4:36 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode ../64 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 3743,3753 ---- test -n "$at_verbose" \ && echo $srcdir'/base64.m4:36: Testing block of lines to Base64' echo base64.m4:36 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x ! recode /../64 < $at_srcdir/dumps-data test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -z "$at_no_redirs" && exec 5>&1 6>& *** 3796,3807 **** test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode ../64 output ! recode /64 output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x --- 3801,3812 ---- test -n "$at_tracex" && set -x set -e while read line; do echo $line > input echo $line > output ! recode /../64 output ! recode /64../ output diff input output done < $at_srcdir/dumps-data set +e test -n "$at_tracex" && set +x *************** echo base64.m4:68 > at-check-line *** 3852,3863 **** test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode ../64 output ! recode /64 output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 3857,3868 ---- test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e cp $at_srcdir/dumps-data output chmod +w output ! recode /../64 output ! recode /64../ output diff $at_srcdir/dumps-data output set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then *************** test -n "$at_verbose" \ *** 4058,4068 **** && echo $srcdir'/african.m4:31: Testing Bambara' echo african.m4:31 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode bambara/qp..t-bambara/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4063,4073 ---- && echo $srcdir'/african.m4:31: Testing Bambara' echo african.m4:31 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode bambara/qp/cl..t-bambara/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4074,4084 **** && echo $srcdir'/african.m4:36: Testing Bambara' echo african.m4:36 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-bambara/64..bambara/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4079,4089 ---- && echo $srcdir'/african.m4:36: Testing Bambara' echo african.m4:36 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-bambara/64/cl..bambara/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4141,4151 **** && echo $srcdir'/african.m4:62: Testing Peul Fulfulde' echo african.m4:62 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode fulfulde/qp..t-fulfulde/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4146,4156 ---- && echo $srcdir'/african.m4:62: Testing Peul Fulfulde' echo african.m4:62 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode fulfulde/qp/cl..t-fulfulde/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4157,4167 **** && echo $srcdir'/african.m4:67: Testing Peul Fulfulde' echo african.m4:67 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-fulfulde/64..fulfulde/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4162,4172 ---- && echo $srcdir'/african.m4:67: Testing Peul Fulfulde' echo african.m4:67 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-fulfulde/64/cl..fulfulde/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4232,4242 **** && echo $srcdir'/african.m4:101: Testing Lingala' echo african.m4:101 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode lingala/qp..t-lingala/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4237,4247 ---- && echo $srcdir'/african.m4:101: Testing Lingala' echo african.m4:101 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode lingala/qp/cl..t-lingala/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4248,4258 **** && echo $srcdir'/african.m4:106: Testing Lingala' echo african.m4:106 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-lingala/64..lingala/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4253,4263 ---- && echo $srcdir'/african.m4:106: Testing Lingala' echo african.m4:106 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-lingala/64/cl..lingala/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4317,4327 **** && echo $srcdir'/african.m4:134: Testing Sango' echo african.m4:134 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode sango/qp..t-sango/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4322,4332 ---- && echo $srcdir'/african.m4:134: Testing Sango' echo african.m4:134 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode sango/qp/cl..t-sango/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4333,4343 **** && echo $srcdir'/african.m4:139: Testing Sango' echo african.m4:139 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-sango/64..sango/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4338,4348 ---- && echo $srcdir'/african.m4:139: Testing Sango' echo african.m4:139 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-sango/64/cl..sango/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4397,4407 **** && echo $srcdir'/african.m4:162: Testing Wolof' echo african.m4:162 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode wolof/qp..t-wolof/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4402,4412 ---- && echo $srcdir'/african.m4:162: Testing Wolof' echo african.m4:162 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp transcript expout ! recode wolof/qp/cl..t-wolof/64 < example test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4413,4423 **** && echo $srcdir'/african.m4:167: Testing Wolof' echo african.m4:167 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-wolof/64..wolof/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 --- 4418,4428 ---- && echo $srcdir'/african.m4:167: Testing Wolof' echo african.m4:167 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x cp example expout ! recode t-wolof/64/cl..wolof/qp < transcript test $? = 0 || exit 1 test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then exec 1>&5 2>&6 *************** test -n "$at_verbose" \ *** 4629,4639 **** echo utf7.m4:20 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e while read line; do ! echo "$line" | recode u7..u6/x2 done < $at_srcdir/utf7-data set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then --- 4634,4644 ---- echo utf7.m4:20 > at-check-line test -z "$at_no_redirs" && exec 5>&1 6>&2 1>stdout 2>stderr test -n "$at_tracex" && set -x set -e while read line; do ! echo "$line" | recode u7/cl..u6/x2 done < $at_srcdir/utf7-data set +e test -n "$at_tracex" && set +x if test -z "$at_no_redirs"; then