#!/bin/sh
# -*- tcl -*- \
exec tclsh "$0" ${1+"$@"}
# Convert the escape sequences and UTF-8 to ABC for abcm2ps
#
# Copyright (C) 2007 Jean-François Moine
# translation table from ABC draft version 2 (accents first)
# ` grave
# ' acute
# ^ circumflex
# , cedilla
# " umlaut
# ~ tilde
# o ring
# = macron or stroke
# '/' slash
# ; ogonek
# v caron
# u breve
# : long Hungarian umlaut
# . dot / dotless
# else, ligatures
# ae ss ng
set seq_lst [list \
\\`A "\xc3\x80" \
\\`E "\xc3\x88" \
\\`I "\xc3\x8c" \
\\`O "\xc3\x92" \
\\`U "\xc3\x99" \
\\`a "\xc3\xa0" \
\\`e "\xc3\xa8" \
\\`i "\xc3\xac" \
\\`o "\xc3\xb2" \
\\`u "\xc3\xb9" \
\\\'A "\xc3\x81" \
\\\'E "\xc3\x89" \
\\\'I "\xc3\x8d" \
\\\'O "\xc3\x93" \
\\\'U "\xc3\x9a" \
\\\'Y "\xc3\x9d" \
\\\'a "\xc3\xa1" \
\\\'e "\xc3\xa9" \
\\\'i "\xc3\xad" \
\\\'o "\xc3\xb3" \
\\\'u "\xc3\xba" \
\\\'y "\xc3\xbd" \
\\\'S "\xc5\x9a" \
\\\'Z "\xc5\xb9" \
\\\'s "\xc5\x9b" \
\\\'z "\xc5\xba" \
\\\'R "\xc5\x94" \
\\\'L "\xc4\xb9" \
\\\'C "\xc4\x86" \
\\\'N "\xc5\x83" \
\\\'r "\xc5\x95" \
\\\'l "\xc4\xba" \
\\\'c "\xc4\x87" \
\\\'n "\xc5\x84" \
\\^A "\xc3\x82" \
\\^E "\xc3\x8a" \
\\^I "\xc3\x8e" \
\\^O "\xc3\x94" \
\\^U "\xc3\x9b" \
\\^a "\xc3\xa2" \
\\^e "\xc3\xaa" \
\\^i "\xc3\xae" \
\\^o "\xc3\xb4" \
\\^u "\xc3\xbb" \
\\^H "\xc4\xa4" \
\\^J "\xc4\xb4" \
\\^h "\xc4\xa5" \
\\^j "\xc4\xb5" \
\\^C "\xc4\x88" \
\\^G "\xc4\x9c" \
\\^S "\xc5\x9c" \
\\^c "\xc4\x89" \
\\^g "\xc4\x9d" \
\\^s "\xc5\x9d" \
\\,C "\xc3\x87" \
\\,c "\xc3\xa7" \
\\,S "\xc5\x9e" \
\\,s "\xc5\x9f" \
\\,T "\xc5\xa2" \
\\,t "\xc5\xa3" \
\\,R "\xc5\x96" \
\\,L "\xc4\xbb" \
\\,G "\xc4\xa2" \
\\,r "\xc5\x97" \
\\,l "\xc4\xbc" \
\\,g "\xc4\xa3" \
\\,N "\xc5\x85" \
\\,K "\xc4\xb6" \
\\,n "\xc5\x86" \
\\,k "\xc4\xb7" \
\\\"A "\xc3\x84" \
\\\"E "\xc3\x8b" \
\\\"I "\xc3\x8f" \
\\\"O "\xc3\x96" \
\\\"U "\xc3\x9c" \
\\\"a "\xc3\xa4" \
\\\"e "\xc3\xab" \
\\\"i "\xc3\xaf" \
\\\"o "\xc3\xb6" \
\\\"u "\xc3\xbc" \
\\\"y "\xc3\xbf" \
\\~A "\xc3\x83" \
\\~N "\xc3\x91" \
\\~O "\xc3\x95" \
\\~a "\xc3\xa3" \
\\~n "\xc3\xb1" \
\\~o "\xc3\xb5" \
\\~I "\xc4\xa8" \
\\~i "\xc4\xa9" \
\\~U "\xc5\xa8" \
\\~u "\xc5\xa9" \
\\oA "\xc3\x85" \
\\oa "\xc3\xa5" \
\\oU "\xc5\xae" \
\\ou "\xc5\xaf" \
\\=E "\xc4\x92" \
\\=e "\xc4\x93" \
\\=A "\xc4\x80" \
\\=I "\xc4\xaa" \
\\=O "\xc5\x8c" \
\\=U "\xc5\xaa" \
\\=a "\xc4\x81" \
\\=i "\xc4\xab" \
\\=o "\xc5\x8d" \
\\=u "\xc5\xab" \
\\=D "\xc4\x90" \
\\=d "\xc4\x91" \
\\=H "\xc4\xa6" \
\\=h "\xc4\xa7" \
\\=T "\xc5\xa6" \
\\=t "\xc5\xa7" \
\\/O "\xc3\x98" \
\\/o "\xc3\xb8" \
\\/D "\xc4\x90" \
\\/d "\xc4\x91" \
\\/L "\xc5\x81" \
\\/l "\xc5\x82" \
"\\;A" "\xc4\x84" \
"\\;a" "\xc4\x85" \
"\\;E" "\xc4\x98" \
"\\;e" "\xc4\x99" \
"\\;I" "\xc4\xae" \
"\\;U" "\xc5\xb2" \
"\\;i" "\xc4\xaf" \
"\\;u" "\xc5\xb3" \
\\vL "\xc4\xbd" \
\\vS "\xc5\xa0" \
\\vT "\xc5\xa4" \
\\vZ "\xc5\xbd" \
\\vl "\xc4\xbe" \
\\vs "\xc5\xa1" \
\\vt "\xc5\xa5" \
\\vz "\xc5\xbe" \
\\vC "\xc4\x8c" \
\\vE "\xc4\x9a" \
\\vD "\xc4\x8e" \
\\vN "\xc5\x87" \
\\vR "\xc5\x98" \
\\vc "\xc4\x8d" \
\\ve "\xc4\x9b" \
\\vd "\xc4\x8f" \
\\vn "\xc5\x88" \
\\vr "\xc5\x99" \
\\uA "\xc4\x82" \
\\ua "\xc4\x83" \
\\uG "\xc4\x9e" \
\\ug "\xc4\x9f" \
\\uU "\xc5\xac" \
\\uu "\xc5\xad" \
\\:O "\xc5\x90" \
\\:U "\xc5\xb0" \
\\:o "\xc5\x91" \
\\:u "\xc5\xb1" \
\\.Z "\xc5\xbb" \
\\.z "\xc5\xbc" \
\\.I "\xc4\xb0" \
\\.i "\xc4\xb1" \
\\.C "\xc4\x8a" \
\\.G "\xc4\xa0" \
\\.c "\xc4\x8b" \
\\.g "\xc4\xa1" \
\\.E "\xc4\x96" \
\\.e "\xc4\x97" \
(C) "\xc2\xa9" \
]
#to be seen \
(#) "\xc2\x81" \
(b) "\xc2\x82" \
(=) "\xc2\x83" \
# append the translation table from the package 'recode' (accents last)
lappend seq_lst \
\\NS "\xc2\xa0" \
\\!! "\xc2\xa1" \
\\Ct "\xc2\xa2" \
\\Pd "\xc2\xa3" \
\\Cu "\xc2\xa4" \
\\Ye "\xc2\xa5" \
\\BB "\xc2\xa6" \
\\SE "\xc2\xa7" \
\\\': "\xc2\xa8" \
\\Co "\xc2\xa9" \
\\-a "\xc2\xaa" \
\\<< "\xc2\xab" \
\\NO "\xc2\xac" \
\\-- "\xc2\xad" \
\\Rg "\xc2\xae" \
\\\'- "\xc2\xaf" \
\\DG "\xc2\xb0" \
\\+- "\xc2\xb1" \
\\2S "\xc2\xb2" \
\\3S "\xc2\xb3" \
\\\'\' "\xc2\xb4" \
\\My "\xc2\xb5" \
\\PI "\xc2\xb6" \
\\.M "\xc2\xb7" \
\\\', "\xc2\xb8" \
\\1S "\xc2\xb9" \
\\-o "\xc2\xba" \
\\>> "\xc2\xbb" \
\\14 "\xc2\xbc" \
\\12 "\xc2\xbd" \
\\34 "\xc2\xbe" \
\\?I "\xc2\xbf" \
\\A! "\xc3\x80" \
\\A\' "\xc3\x81" \
\\A> "\xc3\x82" \
\\A? "\xc3\x83" \
\\A: "\xc3\x84" \
\\AA "\xc3\x85" \
\\AE "\xc3\x86" \
\\C, "\xc3\x87" \
\\E! "\xc3\x88" \
\\E\' "\xc3\x89" \
\\E> "\xc3\x8a" \
\\E: "\xc3\x8b" \
\\I! "\xc3\x8c" \
\\I\' "\xc3\x8d" \
\\I> "\xc3\x8e" \
\\I: "\xc3\x8f" \
\\D- "\xc3\x90" \
\\N? "\xc3\x91" \
\\O! "\xc3\x92" \
\\O\' "\xc3\x93" \
\\O> "\xc3\x94" \
\\O? "\xc3\x95" \
\\O: "\xc3\x96" \
\\*X "\xc3\x97" \
\\O/ "\xc3\x98" \
\\U! "\xc3\x99" \
\\U\' "\xc3\x9a" \
\\U> "\xc3\x9b" \
\\U: "\xc3\x9c" \
\\Y\' "\xc3\x9d" \
\\TH "\xc3\x9e" \
\\ss "\xc3\x9f" \
\\a! "\xc3\xa0" \
\\a\' "\xc3\xa1" \
\\a> "\xc3\xa2" \
\\a? "\xc3\xa3" \
\\a: "\xc3\xa4" \
\\aa "\xc3\xa5" \
\\ae "\xc3\xa6" \
\\c, "\xc3\xa7" \
\\e! "\xc3\xa8" \
\\e\' "\xc3\xa9" \
\\e> "\xc3\xaa" \
\\e: "\xc3\xab" \
\\i! "\xc3\xac" \
\\i\' "\xc3\xad" \
\\i> "\xc3\xae" \
\\i: "\xc3\xaf" \
\\d- "\xc3\xb0" \
\\n? "\xc3\xb1" \
\\o! "\xc3\xb2" \
\\o\' "\xc3\xb3" \
\\o> "\xc3\xb4" \
\\o? "\xc3\xb5" \
\\o: "\xc3\xb6" \
\\-: "\xc3\xb7" \
\\o/ "\xc3\xb8" \
\\u! "\xc3\xb9" \
\\u\' "\xc3\xba" \
\\u> "\xc3\xbb" \
\\u: "\xc3\xbc" \
\\y\' "\xc3\xbd" \
\\th "\xc3\xbe" \
\\y: "\xc3\xbf" \
"\\A;" "\xc4\x84" \
\\\'( "\xcb\x98" \
\\L/ "\xc5\x81" \
\\L< "\xc4\xbd" \
\\S\' "\xc5\x9a" \
\\S< "\xc5\xa0" \
\\S, "\xc5\x9e" \
\\T< "\xc5\xa4" \
\\Z\' "\xc5\xb9" \
\\Z< "\xc5\xbd" \
\\Z. "\xc5\xbb" \
"\\a;" "\xc4\x85" \
"\\\';" "\xcb\x9b" \
\\l/ "\xc5\x82" \
\\l< "\xc4\xbe" \
\\s\' "\xc5\x9b" \
\\\'< "\xcb\x87" \
\\s< "\xc5\xa1" \
\\s, "\xc5\x9f" \
\\t< "\xc5\xa5" \
\\z\' "\xc5\xba" \
\\\'\" "\xcb\x9d" \
\\z< "\xc5\xbe" \
\\z. "\xc5\xbc" \
\\R\' "\xc5\x94" \
\\A( "\xc4\x82" \
\\L\' "\xc4\xb9" \
\\C\' "\xc4\x86" \
\\C< "\xc4\x8c" \
"\\E;" "\xc4\x98" \
\\E< "\xc4\x9a" \
\\D< "\xc4\x8e" \
\\D/ "\xc4\x90" \
\\N\' "\xc5\x83" \
\\N< "\xc5\x87" \
\\O\" "\xc5\x90" \
\\R< "\xc5\x98" \
\\U0 "\xc5\xae" \
\\U\" "\xc5\xb0" \
\\T, "\xc5\xa2" \
\\r\' "\xc5\x95" \
\\a( "\xc4\x83" \
\\l\' "\xc4\xba" \
\\c\' "\xc4\x87" \
\\c< "\xc4\x8d" \
"\\e;" "\xc4\x99" \
\\e< "\xc4\x9b" \
\\d< "\xc4\x8f" \
\\d/ "\xc4\x91" \
\\n\' "\xc5\x84" \
\\n< "\xc5\x88" \
\\o\" "\xc5\x91" \
\\r< "\xc5\x99" \
\\u0 "\xc5\xaf" \
\\u\" "\xc5\xb1" \
\\t, "\xc5\xa3" \
\\\'. "\xcb\x99" \
\\H/ "\xc4\xa6" \
\\H> "\xc4\xa4" \
\\I. "\xc4\xb0" \
\\G( "\xc4\x9e" \
\\J> "\xc4\xb4" \
\\h/ "\xc4\xa7" \
\\h> "\xc4\xa5" \
\\i. "\xc4\xb1" \
\\g( "\xc4\x9f" \
\\j> "\xc4\xb5" \
\\C. "\xc4\x8a" \
\\C> "\xc4\x88" \
\\G. "\xc4\xa0" \
\\G> "\xc4\x9c" \
\\U( "\xc5\xac" \
\\S> "\xc5\x9c" \
\\c. "\xc4\x8b" \
\\c> "\xc4\x89" \
\\g. "\xc4\xa1" \
\\g> "\xc4\x9d" \
\\u( "\xc5\xad" \
\\s> "\xc5\x9d" \
\\kk "\xc4\xb8" \
\\R, "\xc5\x96" \
\\I? "\xc4\xa8" \
\\L, "\xc4\xbb" \
\\E- "\xc4\x92" \
\\G, "\xc4\xa2" \
\\T/ "\xc5\xa6" \
\\r, "\xc5\x97" \
\\i? "\xc4\xa9" \
\\l, "\xc4\xbc" \
\\e- "\xc4\x93" \
\\g, "\xc4\xa3" \
\\t/ "\xc5\xa7" \
\\NG "\xc5\x8a" \
\\ng "\xc5\x8b" \
\\A- "\xc4\x80" \
"\\I;" "\xc4\xae" \
\\E. "\xc4\x96" \
\\I- "\xc4\xaa" \
\\N, "\xc5\x85" \
\\O- "\xc5\x8c" \
\\K, "\xc4\xb6" \
"\\U;" "\xc5\xb2" \
\\U? "\xc5\xa8" \
\\U- "\xc5\xaa" \
\\a- "\xc4\x81" \
"\\i;" "\xc4\xaf" \
\\e. "\xc4\x97" \
\\i- "\xc4\xab" \
\\n, "\xc5\x86" \
\\o- "\xc5\x8d" \
\\k, "\xc4\xb7" \
"\\u;" "\xc5\xb3" \
\\u? "\xc5\xa9" \
\\u- "\xc5\xab"
# glyph names
# (Dbar/dbar --> Dcroat/dcroat)
array set glyph {
0xa0 /space
0xa1 /exclamdown
0xa2 /cent
0xa3 /sterling
0xa4 /currency
0xa5 /yen
0xa6 /brokenbar
0xa7 /section
0xa8 /dieresis
0xa9 /copyright
0xaa /ordfeminine
0xab /guillemotleft
0xac /logicalnot
0xad /hyphen
0xae /registered
0xaf /macron
0xb0 /degree
0xb1 /plusminus
0xb2 /twosuperior
0xb3 /threesuperior
0xb4 /acute
0xb5 /mu
0xb6 /paragraph
0xb7 /periodcentered
0xb8 /cedilla
0xb9 /onesuperior
0xba /ordmasculine
0xbb /guillemotright
0xbc /onequarter
0xbd /onehalf
0xbe /threequarters
0xbf /questiondown
0xc0 /Agrave
0xc1 /Aacute
0xc2 /Acircumflex
0xc3 /Atilde
0xc4 /Adieresis
0xc5 /Aring
0xc6 /AE
0xc7 /Ccedilla
0xc8 /Egrave
0xc9 /Eacute
0xca /Ecircumflex
0xcb /Edieresis
0xcc /Igrave
0xcd /Iacute
0xce /Icircumflex
0xcf /Idieresis
0xd0 /Eth
0xd1 /Ntilde
0xd2 /Ograve
0xd3 /Oacute
0xd4 /Ocircumflex
0xd5 /Otilde
0xd6 /Odieresis
0xd7 /multiply
0xd8 /Oslash
0xd9 /Ugrave
0xda /Uacute
0xdb /Ucircumflex
0xdc /Udieresis
0xdd /Yacute
0xde /Thorn
0xdf /germandbls
0xe0 /agrave
0xe1 /aacute
0xe2 /acircumflex
0xe3 /atilde
0xe4 /adieresis
0xe5 /aring
0xe6 /ae
0xe7 /ccedilla
0xe8 /egrave
0xe9 /eacute
0xea /ecircumflex
0xeb /edieresis
0xec /igrave
0xed /iacute
0xee /icircumflex
0xef /idieresis
0xf0 /eth
0xf1 /ntilde
0xf2 /ograve
0xf3 /oacute
0xf4 /ocircumflex
0xf5 /otilde
0xf6 /odieresis
0xf7 /divide
0xf8 /oslash
0xf9 /ugrave
0xfa /uacute
0xfb /ucircumflex
0xfc /udieresis
0xfd /yacute
0xfe /thorn
0xff /ydieresis
0x100 /Amacron
0x101 /amacron
0x102 /Abreve
0x103 /abreve
0x104 /Aogonek
0x105 /aogonek
0x106 /Cacute
0x107 /cacute
0x108 /Ccircumflex
0x109 /ccircumflex
0x10a /Cdotaccent
0x10b /cdotaccent
0x10c /Ccaron
0x10d /ccaron
0x10e /Dcaron
0x10f /dcaron
0x110 /Dcroat
0x111 /dcroat
0x112 /Emacron
0x113 /emacron
0x116 /Edotaccent
0x117 /edotaccent
0x118 /Eogonek
0x119 /eogonek
0x11a /Ecaron
0x11b /ecaron
0x11c /Gcircumflex
0x11d /gcircumflex
0x11e /Gbreve
0x11f /gbreve
0x120 /Gdotaccent
0x121 /gdotaccent
0x122 /Gcedilla
0x123 /gcedilla
0x124 /Hcircumflex
0x125 /hcircumflex
0x126 /Hstroke
0x127 /hstroke
0x128 /Itilde
0x129 /itilde
0x12a /Imacron
0x12b /imacron
0x12e /Iogonek
0x12f /iogonek
0x130 /Idotaccent
0x131 /dotlessi
0x134 /Jcircumflex
0x135 /jcircumflex
0x136 /Kcedilla
0x137 /kcedilla
0x138 /kra
0x139 /Lacute
0x13a /lacute
0x13b /Lcedilla
0x13c /lcedilla
0x13d /Lcaron
0x13e /lcaron
0x141 /Lslash
0x142 /lslash
0x143 /Nacute
0x144 /nacute
0x145 /Ncedilla
0x146 /ncedilla
0x147 /Ncaron
0x148 /ncaron
0x14a /Eng
0x14b /eng
0x14c /Omacron
0x14d /omacron
0x150 /Ohungarumlaut
0x151 /ohungarumlaut
0x154 /Racute
0x155 /racute
0x156 /Rcedilla
0x157 /rcedilla
0x158 /Rcaron
0x159 /rcaron
0x15a /Sacute
0x15b /sacute
0x15c /Scircumflex
0x15d /scircumflex
0x15e /Scedilla
0x15f /scedilla
0x160 /Scaron
0x161 /scaron
0x162 /Tcedilla
0x163 /tcedilla
0x164 /Tcaron
0x165 /tcaron
0x166 /Tbar
0x167 /tbar
0x168 /Utilde
0x169 /utilde
0x16a /Umacron
0x16b /umacron
0x16c /Ubreve
0x16d /ubreve
0x16e /Uring
0x16f /uring
0x170 /Uhungarumlaut
0x171 /uhungarumlaut
0x172 /Uogonek
0x173 /uogonek
0x179 /Zacute
0x17a /zacute
0x17b /Zdotaccent
0x17c /zdotaccent
0x17d /Zcaron
0x17e /zcaron
0x2c7 /caron
0x2d8 /breve
0x2d9 /dotaccent
0x2db /ogonek
0x2dd /hungarumlaut
}
proc which-enc {c} {
# search the new encoding for a character
global enc_tb enc_nb
set c [format 0x%x $c]
if {![info exists enc_tb($c)]} {
if {$enc_nb >= 0xff} {
puts stderr "Too many utf-8 characters"
return 0x80
}
set enc_tb($c) [format 0x%x $enc_nb]
incr enc_nb
}
#puts "c: $c enc: $enc_tb($c)"
return $enc_tb($c)
}
proc main {fnin fnout} {
# main proc
global enc_tb enc_nb seq_lst glyph
if {[catch {open $fnin r} in]} {
puts "Cannot read file '$fnin'"
exit 1
}
if {$fnout == "-"} {
set out stdout
} else {
if {[catch {open $fnout w} out]} {
puts "Cannot create file '$fnout'"
exit 1
}
}
fconfigure $in -encoding binary
set file [read $in [file size $fnin]]
close $in
# convert the escape sequences to utf-8
if {[string first "\\" $file] >= 0} {
set file [string map $seq_lst $file]
}
# scan the file for utf-8 characters
set result {}
# set enc_tb {}
set enc_nb 0xa0
for {set i 0} {$i < [string length $file]} {incr i} {
set c [string index $file $i]
binary scan $c H* b1
set bh1 0x$b1
if {$bh1 < 0x80} {
append result $c
continue
}
incr i
set c [string index $file $i]
binary scan $c H* b2
set bh2 0x$b2
set b [expr {(($bh1 & 0x0f) << 6) + ($bh2 & 0x3f)}]
set c [which-enc $b]
append result [binary format c $c]
}
if {[info exists enc_tb]} {
puts $out {%%beginps
ISOLatin0Encoding}
foreach v [array names enc_tb] {
#puts "enc: $enc_tb($v) v: $v"
set i [format %02x $enc_tb($v)]
puts $out "dup 16#$i $glyph($v) put"
}
puts $out {pop
%%endps}
}
puts $out $result
}
if {$argc != 2} {
puts {Convert escape sequences and UTF-8 to ABC for abcm2ps
Usage: ./utf2abcm.tcl