summaryrefslogtreecommitdiff
path: root/Build/source
diff options
context:
space:
mode:
authorKarl Berry <karl@freefriends.org>2009-04-10 23:37:36 +0000
committerKarl Berry <karl@freefriends.org>2009-04-10 23:37:36 +0000
commitc1d46af88c872513681359f3318adf75eff204e6 (patch)
tree202d1e8a757550ae18d69a6dafe5e79d9a3b072e /Build/source
parent62492735ac0c6382dbfb0dcfc2c5480eaa295b37 (diff)
accfonts scripts in scripts/ (report from Robin Fairbairns, 10 Apr 2009 10:16:31)
git-svn-id: svn://tug.org/texlive/trunk@12685 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Build/source')
-rw-r--r--Build/source/texk/texlive/linked_scripts/ChangeLog4
-rw-r--r--Build/source/texk/texlive/linked_scripts/Makefile.am3
-rw-r--r--Build/source/texk/texlive/linked_scripts/accfonts/mkt1font1012
-rw-r--r--Build/source/texk/texlive/linked_scripts/accfonts/vpl2ovp1085
-rw-r--r--Build/source/texk/texlive/linked_scripts/accfonts/vpl2vpl994
5 files changed, 3098 insertions, 0 deletions
diff --git a/Build/source/texk/texlive/linked_scripts/ChangeLog b/Build/source/texk/texlive/linked_scripts/ChangeLog
new file mode 100644
index 00000000000..beaba4b46b0
--- /dev/null
+++ b/Build/source/texk/texlive/linked_scripts/ChangeLog
@@ -0,0 +1,4 @@
+2009-04-11 Karl Berry <karl@tug.org>
+
+ * Makefile.am (nobase_dist_script_SCRIPTS): add accfonts scripts.
+
diff --git a/Build/source/texk/texlive/linked_scripts/Makefile.am b/Build/source/texk/texlive/linked_scripts/Makefile.am
index 7ae19d440e5..1e4754d58cf 100644
--- a/Build/source/texk/texlive/linked_scripts/Makefile.am
+++ b/Build/source/texk/texlive/linked_scripts/Makefile.am
@@ -25,6 +25,9 @@ nobase_dist_scriptx_SCRIPTS = \
scriptdir = ${prefix}/texmf-dist/scripts
nobase_dist_script_SCRIPTS = \
+ accfonts/mkt1font \
+ accfonts/vpl2ovp \
+ accfonts/vpl2vpl \
bengali/ebong.py \
context/lua/luatools.lua \
context/lua/mtxrun.lua \
diff --git a/Build/source/texk/texlive/linked_scripts/accfonts/mkt1font b/Build/source/texk/texlive/linked_scripts/accfonts/mkt1font
new file mode 100644
index 00000000000..966ba5932d9
--- /dev/null
+++ b/Build/source/texk/texlive/linked_scripts/accfonts/mkt1font
@@ -0,0 +1,1012 @@
+#!/usr/bin/perl
+
+# Mkt1font: a program to generate accented Type 1 PostScript fonts
+# Copyright (C) 1997 John D. Smith
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+$version = 0.25;
+#-----------------------------------------------------------------------------#
+$description =
+"Syntax: mkt1font -n fontname -d definition-file -a afm-file -f font-file
+ [-s shrink-factor] [-c candrabindu-adjustment] [-b]
+
+Mkt1font creates new Type 1 PostScript fonts based on existing fonts
+(\"input fonts\"). In order to do this it makes use of I. Lee
+Hetherington's programs t1asm and t1disasm, which must be present on
+the system. A successful run will generate an AFM file and a PFB
+file, as well as a DIS file containing a disassembled version of the
+PFB file (including useful comments). Four options must be specified
+on the command line, as follows:
+
+ -n should name the font it is intended to generate. Avoid names
+ such as \"myfont\", as both mkt1font and other programs attempt
+ to draw conclusions from the name; better would be something
+ like \"Utopia_French-BoldItalic\". The generated font files
+ will also use this for their basename.
+
+ -d should refer to a font definition file. This file (which could
+ usefully be named, e.g., \"French.def\") should consist of
+ lines of character definitions, in the form
+ \"number\" \"character\"
+ or
+ \"number\" \"character\" \"accent\"
+ Here \"number\" represents the character's position in the new
+ encoding and may be expressed in decimal, octal or hex;
+ \"character\" names the character (e.g. \"comma\", \"eight\",
+ \"A\") or consists of the word \".notdef\" (indicating that
+ the specified number's \"slot\" in the new encoding is to be
+ empty); and \"accent\" optionally names an accent to be placed
+ on the character. In addition to the standard accents available
+ in PostScript fonts, \"underbar\" and \"underdot\" are also
+ available, as are \"under\" versions of all the normal
+ superscript accents (\"underdieresis\", \"underring\", etc.).
+ The Indian accent \"candrabindu\" may also be specified: it
+ is formed by overprinting a breve with a dotaccent. Finally,
+ \"overdot\" may be used as a synonym for \"dotaccent\".
+
+ If the character named in the \"accent\" position is not in fact
+ a valid accent character, the program interprets the definition
+ as a request for a digraph formed from the \"character\" and the
+ \"accent\". A digraph consisting of, say, \"k\" and \"h\" will be
+ indistinguishable from the letters \"k\" and \"h\" printed
+ consecutively, but the digraph \"kh\" can itself receive accents
+ like any other character: see next paragraph.
+
+ A new character (such as \"amacron\" or \"kh\") may be freely
+ used in the \"character\" position of a further definition (such
+ as \"amacron breve\" or \"kh underbar\"). There is no constraint
+ on the ordering of definitions within a definition file. The
+ definition of \"a macron\" does not have to precede that of
+ \"amacron breve\": requests for \"impossible\" characters are
+ deferred until their constituents have had a chance to come into
+ being.
+
+ \"Slots\" for which no new definition is given retain the
+ definition they have in the input font.
+
+ The definition file may also contain blank lines and comments
+ (introduced by \"\#\").
+
+ -a should refer to the AFM (Adobe Font Metrics) file for the input
+ font.
+
+ -f should refer to the binary font file (PFB) for the input font.
+ (In fact the equivalent ASCII file (PFA) is also acceptable for
+ input, but the output font is always in PFB format.)
+
+ -s may optionally give the factor, expressed as a per-thousand
+ value, by which normally superscript accents (such as dieresis,
+ ring) should be shrunk when they are used as subscript accents
+ (such as underdieresis, underring). Values of around 800 may be
+ found useful.
+
+ -c may optionally give two comma-separated numerical values to
+ adjust the x and y coordinates of the dotaccent placed within a
+ breve to form the candrabindu accent.
+
+ -b may optionally be specified to block the use of predefined
+ accented characters, forcing mkt1font to define its own
+ versions. This may be useful to secure a consistent appearance
+ in cases where a font designer does not share mkt1font's views
+ on where accents should be placed.
+
+The -h option prints this help.
+";
+#-----------------------------------------------------------------------------#
+
+########################
+# Packages and constants
+########################
+#
+use File::Basename;
+use Getopt::Std;
+$cmdline = basename($0) . " " . join " ", @ARGV;
+getopts('n:d:a:f:c:s:bh');
+if ($opt_h or !($opt_n && $opt_d && $opt_a && $opt_f) or ($#ARGV >= 0)) {
+ print STDERR $description;
+ exit 1;
+}
+($enc = basename($opt_d)) =~ s/\..*$//;
+if ($opt_n =~ /\s/) { die "Font name cannot contain whitespace\n" }
+($famname = $opt_n) =~ s/^(.*)-.*?$/$1/;
+if ($opt_s) { $shrink = $opt_s / 1000 } else { $shrink = 1 }
+@months = ( "January", "February", "March", "April",
+ "May", "June", "July", "August",
+ "September", "October", "November", "December"
+ );
+@lt = localtime;
+$date = "$months[$lt[4]] $lt[3], ${ \($lt[5] + 1900) }";
+if ($opt_c) { ($cbx, $cby) = $opt_c =~ /^(.*),(.*)$/ } # candrabindu
+
+###############
+# Read DEF file
+###############
+#
+open DEF, $opt_d or die "Cannot open $opt_d: $!\n";
+while (<DEF>) {
+ next if (/^\s*$/ || /^\#/);
+ s/\s*(\#.*)?$//;
+ push @deflines, $_;
+}
+close DEF;
+
+###############
+# Read AFM file
+###############
+#
+# File header
+#
+open AFM, $opt_a or die "Cannot open $opt_a: $!\n";
+while (<AFM>) {
+ if (/^StartFontMetrics/) {
+ $afmhead = $_;
+ do {
+ $_ = <AFM>;
+ $afmhead .= $_;
+ }
+ until $_ =~ /^StartCharMetrics \d+\r?$/;
+ $afmhead =~ s/\r//gm; # Might be DOS file
+ $afmhead =~ /^FontName (.*)$/m;
+ $ofname = $1;
+ $afmbanner = "\nComment Based on $ofname; modified for $enc encoding";
+ $afmbanner .= "\nComment by John Smiths's program mkt1font ";
+ $afmbanner .= "(v. $version) " if $version;
+ $afmbanner .= "on $date";
+ $afmbanner .= "\nComment Command line: $cmdline";
+ $afmhead =~ s/(\n^FontName )(.*)$/$1$opt_n/m;
+ $afmhead =~ s/(\n^FullName )(.*)$/$1$opt_n/m;
+ $afmhead =~ s/(\n^FamilyName )(.*)$/$1$famname/m;
+ $afmhead =~ s/\n^Comment /$afmbanner$&/m;
+ $afmhead =~ s/(\n^EncodingScheme ).*$/$1FontSpecific/m;
+ if ($afmhead =~ /\n^ItalicAngle (.*)$/m) { $italangle = $1 }
+ if ($afmhead =~ /\n^CapHeight (.*)$/m) { $capheight = $1 }
+ if ($afmhead =~ /\n^XHeight (.*)$/m) { $xheight = $1 }
+ if ($afmhead =~ /\n^FontBBox -?\d+ (-?\d+) (-?\d+) (-?\d+)$/m) {
+ ($maxdp, $maxrs, $maxht) = ($1, $2, $3);
+ }
+ }
+ #
+ # Encoded chars
+ #
+ if (/(^C (\d+) ; WX \d+ ; N ([a-zA-Z_][a-zA-Z0-9_.]*|\.notdef) ; B .* ;( L .* ;)?)\r?$/) {
+ $metrics_enc[$2] = "$1\n";
+ }
+ #
+ # Unencoded chars
+ #
+ elsif (/(^C -1 ; WX \d+ ; N ([a-zA-Z_][a-zA-Z0-9_.]*|\.notdef) ; B .* ;( L .* ;)?)\r?$/) {
+ $metrics_unenc .= "$1\n";
+ }
+ #
+ # Kerns etc.
+ #
+ if (/^EndCharMetrics\r?$/) {
+ $afmtail = $_;
+ do {
+ $_ = <AFM>;
+ $afmtail .= $_;
+ }
+ until eof(AFM);
+ $afmtail =~ s/[\r\cZ]//gm; # Might be DOS file
+ }
+}
+if ($afmtail =~ /(\A(?:.|\n)*^StartKernPairs )\d+\n((?:.|\n)*)(^EndKernPairs(?:.|\n)*\Z)/m) {
+ ($kstart, $kdefs, $kend) = ($1, $2, $3);
+}
+close AFM;
+
+###############################
+# Read and disassemble PFB file
+###############################
+#
+open PFB, $opt_f or die "Cannot open $opt_f: $!\n";
+$_ = <PFB>;
+unless (/%!/) { die "File $opt_f is not a PostScript font\n" }
+close PFB;
+$disfile1 = "mkt1font$$.dis";
+system "t1disasm $opt_f >$disfile1 2>/dev/null";
+open DIS, $disfile1 or die "Cannot open disassembled font file: $!\n";
+while (<DIS>) {
+ #
+ # Locate crucial definitions
+ #
+ if (/^\/(.*?) ?{ ?noaccess def ?} ?executeonly def$/) {
+ $nd = $1;
+ ($rend = $nd) =~ s/\|/\\|/g; # Regexp version
+ next;
+ }
+ if (/^\/(.*?) ?{ ?noaccess put ?} ?executeonly def$/) {
+ $np = $1;
+ ($renp = $np) =~ s/\|/\\|/g; # Regexp version
+ next;
+ }
+ if (/^\/Subrs (\d+) array/) {
+ $subrsnum = $1;
+ do {
+ #
+ # Store subroutine definitions in @subrs
+ #
+ $l = $_ = <DIS>;
+ if (/^dup (\d+) {$/) {
+ $subrnum = $1;
+ $subrdef = $_;
+ do {
+ $_ = <DIS>;
+ $subrdef .= $_;
+ }
+ until /^\t} ?$renp$/;
+ }
+ #
+ # "correct" t1disasm output so t1asm will accept it as input
+ #
+ $subrdef =~ s/^(\t})($rend|$renp)$/$1 $2/m;
+ $subrs[$subrnum] = $subrdef;
+ }
+ until ($l !~ /^dup \d+ {$/);
+ next;
+ }
+ if (/^2 index \/CharStrings (\d+) dict dup begin/) {
+ #
+ # do *not* use "$" to anchor the end of this line, because
+ # it may end with an invisible trailing space!
+ #
+ $chdefsnum = $1;
+ do {
+ #
+ # Store character definitions in %chstrings
+ #
+ $l = $_ = <DIS>;
+ if (/^\/([a-zA-Z_][a-zA-Z0-9_.]*|\.notdef|\.null) {$/) {
+ $chname = $1;
+ $chdef = $_;
+ do {
+ $_ = <DIS>;
+ $chdef .= $_;
+ }
+ until /^\t} ?$rend$/;
+ }
+ #
+ #"correct" t1disasm output so t1asm will accept it as input
+ #
+ $chdef =~ s/^(\t})($rend|$renp)$/$1 $2/m;
+ $chstrings{$chname} = $chdef;
+ }
+ until ($l !~ /^\/([a-zA-Z_][a-zA-Z0-9_.]*|\.notdef|\.null) {$/);
+ #
+ # File tail
+ #
+ if (/^end/) {
+ $distail = $_;
+ do {
+ $_ = <DIS>;
+ $distail .= $_;
+ }
+ until eof(DIS);
+ }
+ }
+}
+close DIS;
+unless ($nd) { die "Cannot find \"noaccess def\" definition\n" }
+unless ($np) { die "Cannot find \"noaccess put\" definition\n" }
+unless ($subrsnum) { die "Cannot find size of Subrs array\n" }
+unless ($chdefsnum) { die "Cannot find size of CharStrings dict\n" }
+
+##################
+# Set up constants
+##################
+#
+$subacc = "(cedilla|ogonek|commaaccent)";
+$supacc = "(grave|acute|circumflex|tilde|macron|breve|dotaccent|overdot|dieresis|ring|hungarumlaut|caron|candrabindu)";
+$underacc = "(underdot|under$supacc)";
+$accents = "($subacc|$supacc|$underacc|underbar)";
+$underadp = -230; # depth of "under" accs
+$underddp = -213; # depth of underdot
+if ($opt_n =~ /Bold/) { $thk = 72 } else { $thk = 52 } # thickness and
+$underbdp = -(82 + $thk); # depth of underbar
+getcharinfo("macron");
+$accheight = $chht{macron}; # height of macron
+$accdepth = $chdp{macron}; # "depth" of macron
+$v1 = $accheight - $xheight; # vertical offset for double accents
+$v2 = $capheight - $xheight; # vertical offset for accented caps etc
+#
+# Italic adjustment: tan(angle)
+#
+$itadj = sin($italangle * 3.14159 / 180) / cos($italangle * 3.14159 / 180);
+
+###########################
+# Create uni0237 (dotlessj)
+###########################
+#
+$chstrings{uni0237} = $chstrings{j} . "\n";
+$chstrings{uni0237} =~ /\A(.*?)(\t[-0-9 ]+?[rvh]moveto)(\n.+)(\n\t.*?(-?\d+) [rv]moveto)(.*?)(\n\tendchar.*?)\Z/ms;
+($one, $two, $three, $four, $five, $six, $seven) = ($1, $2, $3, $4, $5, $6, $7);
+if ($five > 0) { $chstrings{uni0237} = $one . $two . $three . $seven }
+else {
+ findend("j1", ($two . $three));
+ $j1end = "\t$hend{j1} $vend{j1} rmoveto";
+ $chstrings{uni0237} = $one . $j1end . $four . $six . $seven
+}
+$chstrings{uni0237} =~s/\A\/j /\/uni0237 /m;
+getcharinfo("j");
+getcharinfo("dotlessi");
+$metrics_unenc .= "C -1 ; WX $chwd{j} ; N uni0237 ; B $chls{j} $chdp{j} $chrs{j} $chht{dotlessi} ;\n";
+#
+######################
+# Build the characters
+######################
+#
+# First build a list of definitions supplied by user
+#
+for (@deflines) {
+ if (/^\s*(\d+|0[0-7]+|0x[0-9a-fA-F]+)\s+([a-zA-Z_][a-zA-Z0-9_.]*?|\.notdef)(?:\s+([a-zA-Z_][a-zA-Z0-9_.]*))?$/) {
+ ($num, $char, $acc) = ($1, $2, $3);
+ $num = oct $num if $num =~ /^0/;
+ if ($num > 255) { die "Bad definition (number out of range): $_\n" }
+ $def = {};
+ $def->{qdef} = $_;
+ $def->{num} = $num;
+ $def->{char} = $char;
+ $def->{acc} = $acc;
+ $def->{nchar} = $char . $acc;
+ push @nchars, $def->{nchar};
+ push @defs, $def;
+ }
+ else { die "Bad definition: $_\n" }
+}
+#
+# Work through the list
+#
+while (@defs) {
+ $def = shift @defs;
+ $qdef = $def->{qdef};
+ $num = $def->{num};
+ $char = $def->{char};
+ $acc = $def->{acc};
+ $nchar = $def->{nchar};
+ #
+ # If we can't handle $char/$acc yet, but believe we will be able
+ # to later, send the definition to the back of the queue. In case
+ # it later turns out we were wrong, allow only five loops before
+ # giving up.
+ #
+ if (!grep / ; N $char ; /, @metrics_enc
+ and $metrics_unenc !~ / ; N $char ; /m) {
+ if (grep /^$char$/, @nchars) {
+ unless (++$def->{requeue} > 5) {
+ push @defs, $def;
+ next;
+ }
+ }
+ else { die "Bad definition (no such character): $qdef\n" }
+ }
+ if ($acc
+ and !grep / ; N $acc ; /, @metrics_enc
+ and $metrics_unenc !~ / ; N $acc ; /m
+ and $acc !~ /^$accents$/) {
+ if (grep /^$acc$/, @nchars) {
+ unless (++$def->{requeue} > 5) {
+ push @defs, $def;
+ next;
+ }
+ }
+ else { die "Bad definition (no such accent): $qdef\n" }
+ }
+ #
+ # First deal with .notdef
+ #
+ if ($nchar eq ".notdef") {
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ undef $metrics_enc[$num];
+ }
+ #
+ # Now look for new char among existing encoded chars (unless blocked by -b)
+ #
+ else {
+ if (!($acc and $opt_b)
+ and @foundit = grep / ; N $nchar ; /, @metrics_enc) {
+ ($foundit = shift @foundit) =~ s/^C (\d+)/C $num/;
+ $prevnum = $1;
+ unless ($prevnum == $num) {
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ $metrics_enc[$num] = $foundit;
+ }
+ fixkerns($char, $acc);
+ }
+ #
+ # Next look among existing unencoded chars (unless blocked by -b)
+ #
+ elsif (!($acc and $opt_b)
+ and $metrics_unenc =~ s/^C -1 ; WX \d+ ; N $nchar ; B .* ;( L .* ;)?\n//m) {
+ ($foundit = $&) =~ s/^C -1/C $num$1/m;
+ $old = $metrics_enc[$num];
+ if ($old) {
+ $old =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ }
+ $metrics_enc[$num] = $foundit;
+ fixkerns($char, $acc);
+ }
+ #
+ # If it can't be built from sub-elements, issue a warning and move on
+ #
+ elsif (!$acc) { warn "No such character - ignoring definition: $qdef\n" }
+ #
+ # Now build the char
+ #
+ else {
+ #
+ # First get rid of predefined afm entries and synonyms
+ #
+ $metrics_unenc =~ s/^C -1 ; WX \d+ ; N $nchar ; B .* ;( L .* ;)?\n//m;
+ $kdefs =~ s/\nKPX .*$nchar .*$//gm;
+ if ($acc eq "overdot") {
+ $nchar2 = $char . "dotaccent";
+ $metrics_unenc =~ s/^C -1 ; WX \d+ ; N $nchar2 ; B .* ;( L .* ;)?\n//m;
+ $kdefs =~ s/\nKPX .*$nchar2 .*$//gm;
+ delete $chstrings{$nchar2};
+ }
+ #
+ # Go!
+ #
+ if ($acc =~ /^$subacc$/) {
+ subacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^$supacc$/) {
+ supacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^$underacc$/) {
+ underacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^underbar$/) {
+ underb($num, $char, $nchar);
+ fixkerns($char, $acc);
+ }
+ else {
+ digraph($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ }
+ }
+}
+
+################
+# Write AFM file
+################
+#
+open OUTAFM, ">$opt_n.afm";
+foreach (@metrics_enc) { # Avoid duplicate entries
+ ($chname) = /( ; N [a-zA-Z_][a-zA-Z0-9_.]* ; )/;
+ $metrics_unenc =~ s/^C -1 .*$chname.*\n//gm if $chname;
+}
+$chmetricnum = split(/\n/, $metrics_unenc);
+$chmetricnum += grep /^C /, @metrics_enc;
+$afmhead =~ s/^(FontBBox -?\d+ )-?\d+ -?\d+ -?\d+$/$1$maxdp $maxrs $maxht/m;
+$afmhead =~ s/^(StartCharMetrics )\d+$/$1$chmetricnum/m;
+$encoding = "/Encoding 256 array\n0 1 255 {1 index exch /.notdef put} for\n";
+print OUTAFM $afmhead;
+for $i (0 .. 255) {
+ $line = $metrics_enc[$i];
+ if ($line) {
+ print OUTAFM $line;
+ if ($line =~ /^C \d+ ; WX \d+ ; N ([a-zA-Z_][a-zA-Z0-9_.]*) ; /) {
+ $encoding .= "dup $i /$1 put\n";
+ }
+ }
+}
+$encoding .= "readonly def\n";
+print OUTAFM $metrics_unenc;
+#
+# Tidy up kerns
+#
+if ($kdefs) {
+ $kdefs = join("\n", sort split /\n/, $kdefs); # sort
+ $kdefs .= "\n";
+ $kdefs =~ s/((^KPX .*?)-?\d+$)\n\2.*$/$1/gm; # remove duplicates
+ $kdefs =~ s/^\s*\n//gm; # and blank lines
+ $knum = split(/\n/, $kdefs);
+ $afmtail = $kstart . $knum . "\n" . $kdefs . $kend;
+}
+#
+# Eliminate composite character definitions
+#
+$afmtail =~ s/\n(Start|End)Composites.*$//gm;
+$afmtail =~ s/\nCC .*;$//gm;
+print OUTAFM $afmtail;
+close OUTAFM;
+
+#########################
+# Write DIS and PFB files
+#########################
+#
+$disfile2 = "$opt_n.dis";
+open OUTDIS, ">$disfile2";
+$disbanner = "% Based on $ofname; modified for $enc encoding\n";
+$disbanner .= "% by John Smiths's program mkt1font ";
+$disbanner .= "(v. $version) " if $version;
+$disbanner .= "on $date\n";
+$disbanner .= "% Command line: $cmdline";
+open DIS, $disfile1;
+while (<DIS>) { # get header
+ s/^(%!.*: ).*$/$1$opt_n\n$disbanner/;
+ s/(\/FullName \().*(\).*)$/$1$opt_n$2/;
+ s/(\/FamilyName \().*(\).*)$/$1$famname$2/;
+ s/(\/FontName \/).*?( .*)$/$1$opt_n$2/;
+ s/(\/FontBBox {-?\d+ )-?\d+ -?\d+ -?\d+/$1$maxdp $maxrs $maxht/m;
+ if (/^\/Encoding /) {
+ print OUTDIS $encoding;
+ next;
+ }
+ next if (/\/UniqueID .*$/);
+ s /(\/BlueValues \[.*)(\] def)$/$1 $accheight $accheight$2/;
+ if (/(\/Subrs )\d+( array)$/) {
+ print OUTDIS "$1$subrsnum$2\n";
+ last;
+ }
+ else { print OUTDIS }
+}
+close DIS;
+unlink $disfile1;
+foreach $subrdef (@subrs) { print OUTDIS $subrdef }
+$chdefsnum = scalar(keys(%chstrings));
+print OUTDIS "$nd\n2 index /CharStrings $chdefsnum dict dup begin\n";
+foreach (sort values %chstrings) { print OUTDIS }
+print OUTDIS $distail;
+close OUTDIS;
+system "t1asm -b $disfile2 >$opt_n.pfb 2>/dev/null";
+
+#####################
+# End of main program
+#####################
+
+sub subacc {
+ #
+ # Subscript accents
+ #
+ my ($num, $char, $acc, $nchar) = @_;
+ my ($old, $astr, $h, $H, $V, $chdef, $acdef, $pstr);
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ getcharinfo($char) unless defined $chwd{$char};
+ getcharinfo($acc) unless defined $chwd{$acc};
+ $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B $chls{$char} ";
+ $astr .= "$chdp{$acc} $chrs{$char} $chht{$char} ;\n";
+ $metrics_enc[$num] = $astr;
+ $h = round(($chwd{$char} - $chwd{$acc}) / 2 + $chls{$acc});
+ unless (defined $hend{$char}) { findend($char, $chstrings{$char}) }
+ $H = $h - $hend{$char} - $chls{$char};
+ $V = -$vend{$char};
+ $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m;
+ $chdef = $1;
+ $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m;
+ $acdef = $1;
+ $acdef = fixhints($nchar, $acc, $acdef, $h, 0);
+ $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n";
+ $pstr .= "\t$H $V rmoveto\n$acdef";
+ $chstrings{$nchar} = $pstr;
+}
+
+sub supacc {
+ #
+ # Superscript accents
+ #
+ my ($num, $char, $acc, $nchar) = @_;
+ my ($old, $cb, $astr, $h, $v, $H, $V, $it, $chdef, $acdef, $pstr, $newchar);
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ if ($char eq "i") { $char = "dotlessi" }
+ if ($char eq "j") { $char = "uni0237" }
+ if ($acc eq "overdot") { $acc = "dotaccent" }
+ if ($acc eq "candrabindu") {
+ $acc = "breve";
+ $chstrings{"dotaccent"} =~ /^\/dotaccent {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m;
+ $cb = $1;
+ }
+ getcharinfo($char) unless defined $chwd{$char};
+ getcharinfo($acc) unless defined $chwd{$acc};
+ $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B ";
+ $astr .= "$chls{$char} $chdp{$char} $chrs{$char} ";
+ $v = $chht{$acc};
+ if ($chht{$char} >= $accheight + $v2) { # double accs
+ $v += ($v1 + $v2); # on caps etc.
+ $it = ($v1 + $v2) * $itadj;
+ }
+ elsif ($chht{$char} > 1.15 * $xheight) {
+ if ($char =~ /$supacc$/ and $char !~ /under$supacc$/) {
+ $v += $v1; # double accents
+ $it = $v1 * $itadj;
+ }
+ else {
+ $v += $v2; # accented caps etc.
+ $it = $v2 * $itadj;
+ }
+ }
+ else { $it = 0 }
+ if ($v > $maxht) { $maxht = $v }
+ $astr .= "$v ;\n";
+ $metrics_enc[$num] = $astr;
+ $v -= $chht{$acc};
+ $h = round(($chwd{$char} - $chwd{$acc}) / 2 + $chls{$acc} - $it);
+ unless (defined $hend{$char}) { findend($char, $chstrings{$char}) }
+ $H = $h - $hend{$char} - $chls{$char};
+ $V = $v - $vend{$char};
+ $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m;
+ $chdef = $1;
+ $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m;
+ $acdef = $1;
+ $acdef = fixhints($nchar, $acc, $acdef, $h, $v);
+ $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n";
+ $pstr .= "\t$H $V rmoveto\n$acdef";
+ if ($cb) { # candrabindu
+ getcharinfo("dotaccent") unless defined $chwd{dotaccent};
+ $h = round(($chwd{$char} - $chwd{dotaccent}) / 2 + $chls{dotaccent} - $it);
+ $h += $cbx;
+ $v += $cby;
+ $cb = fixhints($nchar, "dotaccent", $cb, $h, $v);
+ $newchar = $char . $acc;
+ unless (defined $hend{$newchar}) { findend($newchar, $pstr) }
+ $H = $h - $hend{$newchar} - $chls{$char};
+ $V = $v - $vend{$newchar};
+ $pstr =~ s/\tendchar\n\t} $rend\n\Z//m;
+ $pstr .= " % $nchar: start of dotaccent\n\t$H $V rmoveto\n$cb";
+ }
+$chstrings{$nchar} = $pstr;
+}
+
+sub underacc {
+ #
+ # Dropped accents
+ #
+ # The Fontographer hack below is necessary because Fontographer (which
+ # I have had to use to build TrueType and Macintosh versions of fonts)
+ # seems not to respect the depths for characters specified in afm files
+ # it has imported: it sets the depth to the lowest point in the path,
+ # whether or not a mark was made there. So it is not possible to
+ # implement (e.g.) underring by diving down low and then printing a
+ # ring at its normal height.
+ #
+ my ($num, $char, $acc, $nchar) = @_;
+ my ($old, $acname, $astr, $h, $v, $H, $V, $chdef, $acdef, $begin, $line, $end, $pstr);
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ $acc =~ s/^under//;
+ $acname = $acc;
+ if ($acc eq "dot") { $acc = "period" }
+ if ($acc eq "candrabindu") { die "Bad definition (no such accent): $qdef\n" }
+ getcharinfo($char) unless defined $chwd{$char};
+ getcharinfo($acc) unless defined $chwd{$acc};
+ if ($acc =~ /^$supacc$/) {
+ $v = round($underadp + ($chdp{$acc} - $accdepth) * $shrink);
+ }
+ else { $v = $underddp + $chdp{$acc} }
+ if ($v < $maxdp) { $maxdp = $v }
+ $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B $chls{$char} ";
+ $astr .= "$v $chrs{$char} $chht{$char} ;\n";
+ $metrics_enc[$num] = $astr;
+ if ($acc =~ /^$supacc$/) {
+ $h = round(($chwd{$char} - ($chwd{$acc} * $shrink)) / 2
+ + $chls{$acc} * $shrink - ($v - $accdepth * $shrink) * $itadj);
+ }
+ else {
+ $h = round(($chwd{$char} - $chwd{$acc}) / 2 + $chls{$acc} - $v * $itadj);
+ }
+ unless (defined $hend{$char}) { findend($char, $chstrings{$char}) }
+ $H = $h - $hend{$char} - $chls{$char};
+ if ($acc =~ /^$supacc$/) { $V = $underadp - $vend{$char} }
+ else { $V = $v - $chdp{$acc} - $vend{$char} }
+ #
+ # Adjustment for smaller, therefore lower, shrunken accent defs
+ #
+ if ($acc =~ /^$supacc$/) {
+ $V += round($chdp{$acc} * (1 - $shrink) / $shrink);
+ }
+ $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m;
+ $chdef = $1;
+ $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m;
+ $acdef = $1;
+ if ($acc =~ /^$supacc$/ and $opt_s) { $acdef = fixshrink($acc, $acdef) }
+ if ($acc =~ /^$supacc$/) {
+ $acdef = fixhints($nchar, $acc, $acdef, $h, $underadp);
+ }
+ else { $acdef = fixhints($nchar, $acc, $acdef, $h, $underddp) }
+ #
+ # Bloody Fontographer! We can't just say
+ # if ($acc =~ /^$supacc$/) { $V -= $accdepth }
+ # Instead we have to go through the following rigmarole:
+ #
+ if ($acc =~ /^$supacc$/) {
+ if ($acdef =~ /^(.*moveto)$/m) {
+ ($begin, $line, $end) = ($`, $1, $');
+ if ($line =~ /^\t(-?\d+) (-?\d+)( rmoveto)$/) {
+ $acdef = "$begin\t$1 " . ($2 - $accdepth) . $3 . $end;
+ }
+ elsif ($line =~ /^\t(-?\d+)( vmoveto)$/) {
+ $acdef = "$begin\t" . ($1 - $accdepth) . $2 . $end;
+ }
+ elsif ($line =~ /\t(-?\d+) hmoveto$/) {
+ $acdef = "$begin\t$1 " . (-$accdepth) . "rmoveto" . $end;
+ }
+ }
+ else { $acdef =~ s/\A/\t-$accdepth vmoveto\n/m }
+ }
+ $pstr = "/$nchar {\n$chdef % $nchar: start of $acname\n";
+ $pstr .= "\t$H $V rmoveto\n$acdef";
+ $chstrings{$nchar} = $pstr;
+}
+
+sub underb {
+ #
+ # Underbar
+ #
+ my ($num, $char, $nchar) = @_;
+ my ($old, $astr, $l, $h, $v, $H, $V, $bdef, $chdef, $acdef, $pstr);
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ $v = $underbdp + $thk;
+ getcharinfo($char) unless defined $chwd{$char};
+ $h = round(0.1 * $chwd{$char} - $underbdp * $itadj);
+ $l = round(0.8 * $chwd{$char});
+ $astr = "C $num ; WX $chwd{$char} ; N $nchar ; B $chls{$char} ";
+ $astr .= "$underbdp $chrs{$char} $chht{$char} ;\n";
+ $metrics_enc[$num] = $astr;
+ unless (defined $hend{$char}) { findend($char, $chstrings{$char}) }
+ $H = $h - $hend{$char} - $chls{$char};
+ $V = -$vend{$char};
+ $bdef = "\t$underbdp $thk hstem\n\t$v vmoveto\n\t-$thk vlineto\n\t";
+ $bdef .= "$l hlineto\n\t$thk vlineto\n\tclosepath\n";
+ $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m;
+ $chdef = $1;
+ $acdef = fixhints($nchar, "underbar", $bdef, $h, 0);
+ $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n";
+ $pstr .= "\t$H $V rmoveto\n$acdef\tendchar\n\t} $nd\n";
+ $chstrings{$nchar} = $pstr;
+}
+
+sub digraph {
+ #
+ # Make a new character consisting of two existing characters
+ #
+ my ($num, $char, $acc, $nchar) = @_;
+ my ($old, $kern, $w, $newrs, $astr, $H, $V, $chdef, $acdef, $pstr);
+ ($old = $metrics_enc[$num]) =~ s/^C $num/C -1/;
+ $metrics_unenc .= $old unless $metrics_unenc =~ /$old/m;
+ getcharinfo($char) unless defined $chwd{$char};
+ getcharinfo($acc) unless defined $chwd{$acc};
+ if ($kdefs =~ /^KPX $char $acc (-?\d+)$/m) { $kern = $1 };
+ $w = $chwd{$char} + $chwd{$acc} + $kern;
+ $newrs = $chrs{$char} + $chwd{$acc} + $kern;
+ if ($newrs > $maxrs) { $maxrs = $newrs }
+ $astr = "C $num ; WX " . $w . " ; N $nchar ; B $chls{$char} ";
+ $astr .= (min($chdp{$char}, $chdp{$acc})) . " $newrs ";
+ $astr .= (max($chht{$char}, $chht{$acc})) . " ;\n";
+ $metrics_enc[$num] = $astr;
+ unless (defined $hend{$char}) { findend($char, $chstrings{$char}) }
+ $H = $chwd{$char} + $chls{$acc} + $kern - $hend{$char};
+ $V = -$vend{$char};
+ $chstrings{$char} =~ /^\/$char {\n(\t.+?hsbw\n(.|\n)*?)\tendchar\n\t} $rend\n/m;
+ ($chdef = $1) =~ s/-?\d+( hsbw\n)/$w$1/m;
+ $chstrings{$acc} =~ /^\/$acc {\n\t.+? .+?hsbw\n((.|\n)+?\t} $rend\n)/m;
+ $acdef = $1;
+ $acdef = fixhints($nchar, $acc, $acdef, ($chwd{$char} + $kern), 0);
+ $pstr = "/$nchar {\n$chdef % $nchar: start of $acc\n";
+ $pstr .= "\t$H $V rmoveto\n$acdef";
+ $chstrings{$nchar} = $pstr;
+}
+
+sub max {
+ #
+ # Return greater of two values
+ #
+ my ($a, $b) = @_;
+ return $a > $b ? $a : $b;
+}
+
+sub min {
+ #
+ # Return lesser of two values
+ #
+ my ($a, $b) = @_;
+ return $a > $b ? $b : $a;
+}
+
+sub round {
+ #
+ # Return nearest integer value
+ #
+ my ($num) = shift;
+ my $n1, $n2;
+ if ($num < 0) { $n1 = (0 - $num) }
+ else { $n1 = $num }
+ $n2 = int($n1);
+ if (($n1 - $n2) >= 0.5) { $n2++ }
+ if ($num < 0) { return (0 - $n2) }
+ else { return $n2 }
+}
+
+sub getcharinfo {
+ #
+ # Store character metric information
+ #
+ my $char = shift;
+ my $foundit;
+ my $metrics_all = join("", @metrics_enc) . $metrics_unenc;
+ if ($metrics_all =~ /^.* ; N $char ; .*$/m) { $foundit = $& }
+ else { die "Bad definition (no such character/accent): $char\n" }
+ $foundit =~ /^C (-?\d+) ; WX (\d+) ; N $char ; B (.+?) (.+?) (.+?) (.+?) ;/;
+ ($chnum{$char}, $chwd{$char}, $chls{$char},
+ $chdp{$char}, $chrs{$char}, $chht{$char}) = ($1, $2, $3, $4, $5, $6);
+}
+
+sub fixkerns {
+ #
+ # Generalise the kerning info contained in the afm file by applying
+ # it to new accented chars. Do not kern lower-case chars bearing
+ # superscript accents with capitals, quotes or a preceding "f".
+ #
+ my ($char, $acc) = @_;
+ my ($lchar, $rchar);
+ if ($acc =~ /^$accents$/) { $lchar = $rchar = $char }
+ else {
+ $lchar = $char;
+ $rchar = $acc;
+ }
+ if ($char =~ /^[a-z]/ and $acc =~ /^$supacc$/) {
+ if ($kdefs =~ /^(KPX $char)(( (?:[a-pr-z][a-zA-Z]*|q(?!uote).*?) )-?\d+)$/m) {
+ ($one, $three) = ($1, $3);
+ $kdefs =~ s[^(KPX $char)(( (?:[a-pr-z][a-zA-Z]*|q(?!uote).*?) )-?\d+)$]
+ [$&\n$1$acc$2]gm
+ unless $kdefs =~ /^$one$acc$three/m;
+ }
+ if ($kdefs =~ /^(KPX (?:[a-eg-pr-z][a-zA-Z]*|q(?!uote).*?) $char)( -?\d+)$/m) {
+ $one = $1;
+ $kdefs =~ s[^(KPX (?:[a-eg-pr-z][a-zA-Z]*|q(?!uote).*?) $char)( -?\d+)$]
+ [$&\n$1$acc$2]gm
+ unless $kdefs =~ /^$one$acc /m;
+ }
+ }
+ else {
+ if ($kdefs =~ /^(KPX )$rchar(( [a-zA-Z]+ )-?\d+)$/m) {
+ ($one, $three) = ($1, $3);
+ $kdefs =~ s[^(KPX )$rchar(( [a-zA-Z]+ )-?\d+)$]
+ [$&\n$1$char$acc$2]gm
+ unless $kdefs =~ /^$one$char$acc$three/m;
+ }
+ if ($kdefs =~ /^(KPX [a-zA-Z]+ )$char( -?\d+)$/m) {
+ $one = $1;
+ $kdefs =~ s[^(KPX [a-zA-Z]+ )$char( -?\d+)$]
+ [$&\n$1$char$acc$2]gm
+ unless $kdefs =~ /^$one$char$acc /m;
+ }
+ }
+}
+
+sub fixshrink {
+ #
+ # Multiply all coordinates in a character definition by $shrink,
+ # creating new subroutines as necessary.
+ #
+ my ($ch, $chdef) = @_;
+ my (@chdef, $line, $snum, $subrdef);
+ @chdef = split(/\n/, $chdef);
+ $chdef = "";
+ foreach $line (@chdef) {
+ if ($line =~ /^\t(\d+) .*call(other)?subr$/) {
+ $snum = $1;
+ $subrdef = $subrs[$snum];
+ $subrdef = fixshrink($ch, $subrdef);
+ $subrdef =~ s/^(dup )$snum \{$/$1$subrsnum {\n % $nchar: shrink $ch/m;
+ $subrs[$subrsnum] = $subrdef;
+ $line =~ s/^\t$snum/\t$subrsnum/;
+ $subrsnum++;
+ }
+ else { $line =~ s/-?\d+/int($& * $shrink)/ge unless $line =~ /^dup / }
+ $chdef .= "$line\n";
+ }
+ return $chdef;
+}
+
+sub fixhints {
+ #
+ # First adjust any Flex "0 callsubr" lines for horizontal and
+ # vertical offset. Then collect the hints from the accent definition,
+ # remove them, adjust for horizontal and vertical offset, and
+ # place them in a numbered subroutine. Have the definition call
+ # the subroutine.
+ #
+ my ($nchar, $acc, $acdef, $h, $v) = @_;
+ my $subrdef;
+ $acdef =~ s[^(\t-?\d+ )(-?\d+) (-?\d+)( 0 callsubr)$]
+ [$1 . ($2 + $h) . " " . ($3 + $v) . $4]gme;
+ if ($subrdef = join("\n", grep /^\t.*[hv]stem$/, split(/\n/, $acdef))) {
+ $acdef = join("\n", grep !/^\t.*[hv]stem$/, split(/\n/, $acdef)) . "\n";
+ }
+ elsif ($acdef =~ s/\A(?:\t(\d+) callsubr\n)((?:.|\n)*)\Z/$2/m) {
+ $subrdef = $subrs[$1];
+ $subrdef = join("\n", grep /^\t.*[hv]stem$/, split(/\n/, $subrdef))
+ }
+ $subrdef =~ s/^(\t)(-?\d+)( .*hstem)$/$1 . ($2 + $v) . $3/gme;
+ $subrdef =~ s/^(\t)(-?\d+)( .*vstem)$/$1 . ($2 + $h) . $3/gme;
+ if ($subrdef) {
+ $subrs[$subrsnum] = "dup $subrsnum {\n % $nchar: hints for $acc\n";
+ $subrs[$subrsnum] .= "$subrdef\n\treturn\n\t} $np\n";
+ $acdef = "\t$subrsnum 1 3 callothersubr\n\tpop\n\tcallsubr\n" . $acdef;
+ $subrsnum++;
+ }
+ return $acdef;
+}
+
+sub findend {
+ #
+ # Calculate the current point reached at the end of the character
+ # definition. Place the horizontal offset in $hend{$char}, the
+ # vertical offset in $vend{$char}.
+ #
+ my ($char, $def) = @_;
+ my $line;
+ foreach $line (split /\n/, $def) {
+ SWITCH: {
+ $line =~ /^\t(-?\d+) h(line|move)to$/
+ && do {
+ $hend{$char} += $1;
+ last SWITCH;
+ };
+ $line =~ /^\t(-?\d+) v(line|move)to$/
+ && do {
+ $vend{$char} += $1;
+ last SWITCH;
+ };
+ $line =~ /^\t(-?\d+) (-?\d+) r(line|move)to$/
+ && do {
+ $hend{$char} += $1;
+ $vend{$char} += $2;
+ last SWITCH;
+ };
+ $line =~ /^\t(-?\d+) (-?\d+) (-?\d+) (-?\d+) hvcurveto$/
+ && do {
+ $hend{$char} += ($1 + $2);
+ $vend{$char} += ($3 + $4);
+ last SWITCH;
+ };
+ $line =~ /^\t(-?\d+) (-?\d+) (-?\d+) (-?\d+) vhcurveto$/
+ && do {
+ $hend{$char} += ($2 + $4);
+ $vend{$char} += ($1 + $3);
+ last SWITCH;
+ };
+ $line =~ /^\t(-?\d+) (-?\d+) (-?\d+) (-?\d+) (-?\d+) (-?\d+) rrcurveto$/
+ && do {
+ $hend{$char} += ($1 + $3 + $5);
+ $vend{$char} += ($2 + $4 + $6);
+ last SWITCH;
+ };
+ $line =~ /^\t(\d+) callsubr$/
+ && do {
+ findend($char, $subrs[$1]);
+ last SWITCH;
+ };
+ $line =~ /^\t-?\d+ (-?\d+) (-?\d+) 0 callsubr$/ # Flex
+ && do {
+ $hend{$char} = $1;
+ $vend{$char} = $2;
+ last SWITCH;
+ };
+ }
+ }
+}
diff --git a/Build/source/texk/texlive/linked_scripts/accfonts/vpl2ovp b/Build/source/texk/texlive/linked_scripts/accfonts/vpl2ovp
new file mode 100644
index 00000000000..eb88bfd3dda
--- /dev/null
+++ b/Build/source/texk/texlive/linked_scripts/accfonts/vpl2ovp
@@ -0,0 +1,1085 @@
+#!/usr/bin/perl
+
+# Vpl2ovp: a program to generate accented virtual fonts for Omega
+# Copyright (C) 2008 John D. Smith
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+$version = 0.25;
+#------------------------------------------------------------------------#
+$description =
+"Syntax: vpl2ovp -d definition-file [-s shrink-factor]
+ [-c candrabindu-adjustment] [-b] vpl-file
+
+Vpl2ovp creates new Omega virtual fonts based on existing TeX
+fonts or virtual fonts (\"input fonts\"). A successful run will
+read a pl (Property List) or vpl (Virtual Property List) file
+and a definition file, and will generate a new ovp (Omega
+Virtual Property List) file on standard output. The input font
+is assumed to adhere to the standard TeX encoding for text
+fonts unless it was created with either of the programs afm2pl
+or afm2tfm, in which case it is assumed to conform to
+(respectively) the Adobe Standard Encoding or the encoding
+specified in the file dvips.enc. In either case, the name of
+the input font is assumed to be the name of the input file
+without its .vpl or .pl extension: it must conform to normal
+TeX conventions for naming fonts, as vpl2ovp attempts to draw
+conclusions from it about the kind of font it is dealing with.
+
+A typical complete sequence of commands to create a new virtual
+font might therefore be
+ tftopl cmr10.tfm cmr10.pl
+ vpl2ovp -d Unicode1.def cmr10.pl >cmr10-uni1.ovp
+ ovp2ovf cmr10-uni1.ovp cmr10-uni1.ovf cmr10-uni1.ofm
+for a Computer Modern font, or
+ afm2pl Times-Roman.afm rptmr.pl
+ pltotf rptmr.pl rptmr.tfm
+ vpl2ovp -d Unicode1.def rptmr.pl >ptmr-uni1.ovp
+ ovp2ovf ptmr-uni1.ovp ptmr-uni1.ovf ptmr-uni1.ofm
+for a PostScript font.
+
+Another approach for a PostScript font is to use afm2tfm:
+ afm2tfm Times-Roman.afm -t dvips.enc -v ptmr rptmr
+ vpl2ovp -d Unicode1.def ptmr.vpl >ptmr-uni1.ovp
+ ovp2ovf ptmr-uni1.ovp ptmr-uni1.ovf ptmr-uni1.ofm
+-- but this is now deprecated, as afm2tfm generates incorrect
+values for the heights of some characters, and this can lead to
+bad accent placing.
+
+In order to keep the whole of the character range \"F0-\"FF free for
+the requirements of the encoding specified in the definition file,
+certain modifications are made to input fonts following the dvips.enc
+encoding to bring them into greater conformity with the TeX norm. In
+particular, the characters dotaccent and hungarumlaut are placed in
+the positions assigned by TeX (\"5F, \"7D), not those enforced by
+dvips.enc (\"C7, \"CD). The f-ligatures, double quotes and dashes are
+also moved from the upper half of the original 8-bit character set to
+their normal TeX positions. As a result, the following characters are
+not found in the lower half of the character set: quotesingle,
+quotedbl, backslash, underscore, braceleft, bar, braceright. These
+characters can, however, be assigned positions in the output font if
+they are needed. (Indeed, they could all be explicitly restored to
+their dvips.enc positions if this were desired.)
+
+Options:
+
+ -d should refer to a font definition file. This file (which could
+ usefully be named, e.g., \"Unicode1.def\") should consist of
+ lines of character definitions, in the form
+ \"number\" \"character\"
+ or
+ \"number\" \"character\" \"accent\"
+ Here \"number\" represents the character's position in the new
+ encoding and may be expressed in decimal, octal or hex;
+ \"character\" names the character (e.g. \"comma\", \"eight\",
+ \"A\") or consists of the word \".notdef\" (indicating that
+ the specified number's \"slot\" in the new encoding is to be
+ empty); and \"accent\" optionally names an accent to be placed
+ on the character. In addition to the standard accents available
+ in PostScript fonts, \"underbar\" and \"underdot\" are also
+ available, as are \"under\" versions of all the normal
+ superscript accents (\"underdieresis\", \"underring\", etc.).
+ The Indian accent \"candrabindu\" may also be specified: it
+ is formed by overprinting a breve with a dotaccent. Finally,
+ \"overdot\" may be used as a synonym for \"dotaccent\".
+
+ Note that all accents used in defining accented characters must
+ themselves be defined in the .def file. Those which exist in the
+ source font should simply be referenced by name in their
+ appropriate Unicode position (e.g. \"0x0304 macron\"); those
+ which do not should be defined as the character \"space\"
+ followed by the name of the accent (e.g. \"0x0310 space
+ candrabindu\").
+
+ If the character named in the \"accent\" position is not in fact
+ a valid accent character, the program interprets the definition
+ as a request for a digraph formed from the \"character\" and the
+ \"accent\". A digraph consisting of, say, \"k\" and \"h\" will be
+ indistinguishable from the letters \"k\" and \"h\" printed
+ consecutively, but the digraph \"kh\" can itself receive accents
+ like any other character: see next paragraph.
+
+ A new character (such as \"amacron\" or \"kh\") may be freely
+ used in the \"character\" position of a further definition (such
+ as \"amacron breve\" or \"kh underbar\"). There is no constraint
+ on the ordering of definitions within a definition file. The
+ definition of \"a macron\" does not have to precede that of
+ \"amacron breve\": requests for \"impossible\" characters are
+ deferred until their constituents have had a chance to come into
+ being.
+
+ \"Slots\" for which no new definition is given retain the
+ definition they have in the input font.
+
+ The definition file may also contain blank lines and comments
+ (introduced by \"\#\").
+
+ -s may optionally give the factor, expressed as a per-thousand
+ value, by which normally superscript accents (such as dieresis,
+ ring) should be shrunk when they are used as subscript accents
+ (such as underdieresis, underring). Values of around 800 may be
+ found useful.
+
+ -c may optionally give two comma-separated numerical values to
+ adjust the x and y coordinates of the dotaccent placed within a
+ breve to form the candrabindu accent. A coordinate scheme using
+ \"DESIGNUNITS R 1000\" is assumed.
+
+ -b may optionally be specified to block the use of predefined
+ accented characters, forcing vpl2ovp to define its own
+ versions. This may be useful to secure a consistent appearance
+ in cases where a font designer does not share vpl2ovp's views
+ on where accents should be placed.
+
+ -h prints this help.
+";
+#------------------------------------------------------------------------#
+
+########################
+# Packages and constants
+########################
+#
+use File::Basename;
+use Getopt::Std;
+$cmdline = basename($0) . " " . join " ", @ARGV;
+getopts('d:s:c:bh');
+if ($opt_h or !$opt_d or $#ARGV != 0) {
+ print STDERR $description;
+ exit 1;
+}
+
+$filename = $ARGV[0];
+$dummycodepoint = 0xF8FF;
+($fontname = $filename) =~ s/\..*$//;
+($encname = basename($opt_d)) =~ s/\..*$//;
+$vtitle = "(VTITLE Font $fontname modified for $encname encoding by vpl2ovp";
+$vtitle .= " v. $version" if $version;
+$vtitle .= ")\n(COMMENT Command line: $cmdline)";
+$vtitle .= "\n(OFMLEVEL H 0)";
+
+#
+# Flags for bold and small caps. These are probably a bit iffy, but
+# there's not much that can be done about it.
+#
+if ($fontname =~ /(^p.*b[oi]?[c]?$|^[^p].*bx[a-z]*[0-9]+$)/) { $bold = 1 }
+if ($fontname =~ /(^p.*c$|^[^p].*csc[a-z]*[0-9]+$)/) { $scaps = 1 }
+if ($opt_s) { $shrink = $opt_s / 1000 } else { $shrink = 1 }
+
+#
+# Array to convert from number to vpl representation
+#
+foreach $i (0 .. 0xFFFF) {
+ $nv[$i] = (chr($i) =~ /[0-9A-Za-z]/ ? "C " . chr $i : sprintf("H %04lX", $i));
+}
+
+#
+# Now the encoding vectors.
+#
+@TeXenc = (
+ "Gamma", "Delta", "Theta", "Lambda",
+ "Xi", "Pi", "Sigma", "Upsilon",
+ "Phi", "Psi", "Omega", "ff",
+ "fi", "fl", "ffi", "ffl",
+ "dotlessi", "dotlessj", "grave", "acute",
+ "caron", "breve", "macron", "ring",
+ "cedilla", "germandbls", "ae", "oe",
+ "oslash", "AE", "OE", "Oslash",
+ "space", "exclam", "quotedblright", "numbersign",
+ "dollar", "percent", "ampersand", "quoteright",
+ "parenleft", "parenright", "asterisk", "plus",
+ "comma", "hyphen", "period", "slash",
+ "zero", "one", "two", "three",
+ "four", "five", "six", "seven",
+ "eight", "nine", "colon", "semicolon",
+ "exclamdown", "equal", "questiondown", "question",
+ "at", "A", "B", "C",
+ "D", "E", "F", "G",
+ "H", "I", "J", "K",
+ "L", "M", "N", "O",
+ "P", "Q", "R", "S",
+ "T", "U", "V", "W",
+ "X", "Y", "Z", "bracketleft",
+ "quotedblleft", "bracketright", "circumflex", "dotaccent",
+ "quoteleft", "a", "b", "c",
+ "d", "e", "f", "g",
+ "h", "i", "j", "k",
+ "l", "m", "n", "o",
+ "p", "q", "r", "s",
+ "t", "u", "v", "w",
+ "x", "y", "z", "endash",
+ "emdash", "hungarumlaut", "tilde", "dieresis"
+);
+
+@dvipsenc = (
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "quotesingle", "exclamdown", "questiondown",
+ "dotlessi", "dotlessj", "grave", "acute",
+ "caron", "breve", "macron", "ring",
+ "cedilla", "germandbls", "ae", "oe",
+ "oslash", "AE", "OE", "Oslash",
+ "space", "exclam", "quotedbl", "numbersign",
+ "dollar", "percent", "ampersand", "quoteright",
+ "parenleft", "parenright", "asterisk", "plus",
+ "comma", "hyphen", "period", "slash",
+ "zero", "one", "two", "three",
+ "four", "five", "six", "seven",
+ "eight", "nine", "colon", "semicolon",
+ "less", "equal", "greater", "question",
+ "at", "A", "B", "C",
+ "D", "E", "F", "G",
+ "H", "I", "J", "K",
+ "L", "M", "N", "O",
+ "P", "Q", "R", "S",
+ "T", "U", "V", "W",
+ "X", "Y", "Z", "bracketleft",
+ "backslash", "bracketright", "circumflex", "underscore",
+ "quoteleft", "a", "b", "c",
+ "d", "e", "f", "g",
+ "h", "i", "j", "k",
+ "l", "m", "n", "o",
+ "p", "q", "r", "s",
+ "t", "u", "v", "w",
+ "x", "y", "z", "braceleft",
+ "bar", "braceright", "tilde", "dieresis",
+ "asciicircum", "asciitilde", "Ccedilla", "Iacute",
+ "Icircumflex", "atilde", "edieresis", "egrave",
+ "scaron", "zcaron", "Eth", "ff",
+ "ffi", "ffl", ".notdef", ".notdef",
+ ".notdef", ".notdef", "Scaron", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ "Ydieresis", ".notdef", "Zcaron", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", "cent", "sterling",
+ "fraction", "yen", "florin", "section",
+ "currency", "copyright", "quotedblleft", "guillemotleft",
+ "guilsinglleft", "guilsinglright", "fi", "fl",
+ "degree", "endash", "dagger", "daggerdbl",
+ "periodcentered", ".notdef", "paragraph", "bullet",
+ "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright",
+ "ellipsis", "perthousand", ".notdef", ".notdef",
+ "Agrave", "Aacute", "Acircumflex", "Atilde",
+ "Adieresis", "Aring", ".notdef", "dotaccent",
+ "Egrave", "Eacute", "Ecircumflex", "Edieresis",
+ "Igrave", "hungarumlaut", "ogonek", "Idieresis",
+ "emdash", "Ntilde", "Ograve", "Oacute",
+ "Ocircumflex", "Otilde", "Odieresis", ".notdef",
+ ".notdef", "Ugrave", "Uacute", "Ucircumflex",
+ "Udieresis", "Yacute", "Thorn", ".notdef",
+ "agrave", "aacute", "acircumflex", "ordfeminine",
+ "adieresis", "aring", ".notdef", "ccedilla",
+ "Lslash", "eacute", "ecircumflex", "ordmasculine",
+ "igrave", "iacute", "icircumflex", "idieresis",
+ ".notdef", "ntilde", "ograve", "oacute",
+ "ocircumflex", "otilde", "odieresis", ".notdef",
+ "lslash", "ugrave", "uacute", "ucircumflex",
+ "udieresis", "yacute", "thorn", "ydieresis"
+);
+
+@adobeenc=(
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ "space", "exclam", "quotedbl", "numbersign",
+ "dollar", "percent", "ampersand", "quoteright",
+ "parenleft", "parenright", "asterisk", "plus",
+ "comma", "hyphen", "period", "slash",
+ "zero", "one", "two", "three",
+ "four", "five", "six", "seven",
+ "eight", "nine", "colon", "semicolon",
+ "less", "equal", "greater", "question",
+ "at", "A", "B", "C",
+ "D", "E", "F", "G",
+ "H", "I", "J", "K",
+ "L", "M", "N", "O",
+ "P", "Q", "R", "S",
+ "T", "U", "V", "W",
+ "X", "Y", "Z", "bracketleft",
+ "backslash", "bracketright", "asciicircum", "underscore",
+ "quoteleft", "a", "b", "c",
+ "d", "e", "f", "g",
+ "h", "i", "j", "k",
+ "l", "m", "n", "o",
+ "p", "q", "r", "s",
+ "t", "u", "v", "w",
+ "x", "y", "z", "braceleft",
+ "bar", "braceright", "asciitilde", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "exclamdown", "cent", "sterling",
+ "fraction", "yen", "florin", "section",
+ "currency", "quotesingle", "quotedblleft", "guillemotleft",
+ "guilsinglleft", "guilsinglright", "fi", "fl",
+ ".notdef", "endash", "dagger", "daggerdbl",
+ "periodcentered", ".notdef", "paragraph", "bullet",
+ "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright",
+ "ellipsis", "perthousand", ".notdef", "questiondown",
+ ".notdef", "grave", "acute", "circumflex",
+ "tilde", "macron", "breve", "dotaccent",
+ "dieresis", ".notdef", "ring", "cedilla",
+ ".notdef", "hungarumlaut", "ogonek", "caron",
+ "emdash", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "AE", ".notdef", "ordfeminine",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ "Lslash", "Oslash", "OE", "ordmasculine",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "ae", ".notdef", ".notdef",
+ ".notdef", "dotlessi", ".notdef", ".notdef",
+ "lslash", "oslash", "oe", "germandbls",
+ ".notdef", ".notdef", ".notdef", ".notdef"
+);
+
+###############
+# Read DEF file
+###############
+#
+open DEF, $opt_d or die "Cannot open $opt_d: $!\n";
+while (<DEF>) {
+ next if (/^\s*$/ || /^\#/);
+ s/\s*(\#.*)?$//;
+ push @deflines, $_;
+}
+close DEF;
+
+###############
+# Read VPL file
+###############
+#
+# File header
+#
+$vplhead = <> or exit 1;
+unless ($vplhead =~ /^\((VTITLE|FAMILY) /) {
+ die "$filename is not a vpl file: giving up\n"
+}
+do {
+ $_ = <>;
+ $vplhead .= $_;
+} until ($_ =~ /^\(LIGTABLE$/ or eof);
+if (eof) {
+ die "$filename does not seem to be a text font (no LIGTABLE): giving up\n";
+}
+if ($vplhead =~ s/\A\(VTITLE(.*)$/$vtitle\n(COMMENT Old vtitle:$1/m) {
+ $vplhead =~ s/\n\(COMMENT Please edit that VTITLE .*\)$//m;
+ @enc = @dvipsenc;
+ $dvips = 1;
+}
+elsif ($vplhead =~ /\A\(FAMILY.*\)\n\(CODINGSCHEME ADOBESTANDARDENCODING\)$/m) {
+ $vplhead =~ s/\A/$vtitle\n/m;
+ @enc = @adobeenc;
+ $dvips = 0;
+}
+else {
+ $vplhead =~ s/\A/$vtitle\n/m;
+ @enc = @TeXenc;
+ $dvips = 0;
+}
+if ($vplhead =~ /^\(CODINGSCHEME TEX MATH SYMBOLS/m) {
+ die "$filename is a TeX math font: giving up\n";
+}
+unless ($vplhead =~ s/^(\(CODINGSCHEME .*\+\s?)(\S+)\)$/$1$encname)/m) {
+ $vplhead =~ s/^(\(CODINGSCHEME .*)\)$/$1 + $encname)/m;
+}
+if ($vplhead =~ s/^\(DESIGNUNITS R (.+)\)\n//m) { $scale = $1 }
+else { $scale = 1 }
+$vplhead =~ s/^\(COMMENT.*DESIGNSIZE.*\)\n//gm;
+$vplhead =~ s/^\(BOUNDARYCHAR.*\)\n//gm;
+if ($vplhead =~ /^ \(SLANT R (.+)\)/m) { $slant = $1 }
+if ($vplhead =~ /^ \(XHEIGHT [DR] (.+)\)/m) { $xheight = $1 }
+unless ($vplhead =~ /^\(MAPFONT /m) {
+ if ($vplhead =~ /^\(DESIGNSIZE R (.*)\)$/m) { $dsize = $1 *$scale }
+ $mapfont = "\n(MAPFONT D 0\n (FONTNAME $fontname)\n (FONTDSIZE R $dsize)\n )";
+ $vplhead =~ s/\n\(LIGTABLE\Z/$mapfont$&/m;
+}
+$vplhead =~ s/^(\(FONTDIMEN)/(SEVENBITSAFEFLAG FALSE)\n$1/m;
+if ($opt_s) {
+ $vplhead =~ s[^(\(MAPFONT D )0(.*?)( \))]
+ [$&\n${1}1$2 (FONTAT R ${ \($shrink * $scale) })\n$3]ms;
+}
+@vplhead = split /^/, $vplhead;
+foreach (@vplhead) {
+ s[(?<!(IGNSIZE|MAPFONT)) [RD] (-?)([0-9.]+)\)]
+ [" R " . $2 . $3/$scale . ")"]ge
+}
+
+#
+# Ligatures and kerns
+#
+do {
+ $_ = <>;
+ s/ \(comment .*$//i;
+ s/^( \((?:LABEL|KRN) )O ([0-7]+)(.*)$/$1 . sprintf("H %04lX", oct $2) . $3/e;
+if (/ \(LIG /) {
+ s/O ([0-7]+)/sprintf("H %04lX", oct $1)/ge;
+ }
+ $ligs .= $_;
+} until $_ =~ /^ \)/;
+#
+# Now build a hash to convert from vpl representation to char name
+# and use it to make ligtable readable
+#
+foreach $i (0 .. 255) { $vc{$nv[$i]} = $enc[$i] }
+$ligs =~ s/^( \((?:LABEL|KRN) )(\S+ \S+)(.*\))$/$1$vc{$2}$3/gm;
+$ligs =~ s/^( \(LIG )(\S+ \S+) (\S+ \S+)\)$/$1$vc{$2} $vc{$3})/gm;
+#
+# Character definitions: store "encoded" defs in @chars, store *all*
+# defs in %allchars
+#
+$_ = <>;
+do {
+ if (/^\(CHARACTER/) {
+ $character = $_;
+ do {
+ $_ = <>;
+ $character .= $_;
+ } until $_ =~ /^ \)/;
+ storeinfo($character);
+ $_ = <>;
+ }
+} until eof;
+foreach $i (0 .. $#chars) {
+ if ($chars[$i] and $enc[$i] ne ".notdef") {
+ $allchars{$enc[$i]} = $chars[$i];
+ }
+}
+
+##################
+# Set up constants
+##################
+
+$subacc = "(cedilla|ogonek|commaaccent)";
+$supacc = "(grave|acute|circumflex|tilde|macron|breve|dotaccent|overdot|dieresis|ring|hungarumlaut|caron|candrabindu)";
+$underacc = "(underdot|under$supacc)";
+$accents = "($subacc|$supacc|$underacc|underbar)";
+$underadp = 0.230; # depth of "under" accs
+$underddp = 0.213; # depth of underdot
+if ($bold) { $thk = 0.072 } else { $thk = 0.052 } # thickness and
+$underbdp = 0.082 + $thk; # depth of underbar
+$capheight = $allchars{"X"}{ht};
+$accheight = $allchars{"macron"}{ht};
+$accdepth = $accheight - $thk * $scale; # probable approx. "depth" of macron
+$v1 = $accheight - $xheight; # vertical offset for double accents
+$v2 = $capheight - $xheight; # vertical offset for accented caps etc
+if ($scaps) { # accented small caps
+ $scoffset = $allchars{"x"}{ht} - $xheight;
+ $v1 += $scoffset;
+}
+if ($opt_c) { # candrabindu
+ ($cbx, $cby) = $opt_c =~ /^(.*),(.*)$/;
+ $cbx += ($allchars{"breve"}{wd} - $allchars{"dotaccent"}{wd}) / 2;
+ $cbx /= 1000;
+ $cby /= 1000;
+}
+
+######################
+# Build the characters
+######################
+#
+# First normalise dvips.enc encoding quirks
+#
+if ($dvips) {
+ chmove("fi", 014);
+ chmove("fl", 015);
+ chmove("quotedblright", 042);
+ chmove("quotedblleft", 0134);
+ chmove("dotaccent", 0137);
+ chmove("endash", 0173);
+ chmove("emdash", 0174);
+ chmove("hungarumlaut", 0175);
+}
+#
+# Now build a list of definitions supplied by user
+#
+for (@deflines) {
+ if (/^\s*(\d+|0[0-7]+|0x[0-9a-fA-F]+)\s+([a-zA-Z]+?|\.notdef)(?:\s+([a-zA-Z]+))?$/) {
+ ($num, $char, $acc) = ($1, $2, $3);
+ $num = oct $num if $num =~ /^0/;
+ if ($num > 0xFFFF) { die "Bad definition (number out of range): $_\n" }
+ $def = {};
+ $def->{qdef} = $_;
+ $def->{num} = $num;
+ $def->{char} = $char;
+ $def->{acc} = $acc;
+ if ($char eq "space") { $def->{nchar} = $acc }
+ else { $def->{nchar} = $char . $acc }
+ push @nchars, $def->{nchar};
+ push @defs, $def;
+ }
+ else { die "Bad definition: $_\n" }
+}
+#
+# Work through the list
+#
+while (@defs) {
+ $def = shift @defs;
+ $qdef = $def->{qdef};
+ $num = $def->{num};
+ $char = $def->{char};
+ $acc = $def->{acc};
+ $nchar = $def->{nchar};
+ #
+ # If we can't handle $char/$acc yet, but believe we will be able
+ # to later, send the definition to the back of the queue. In case
+ # it later turns out we were wrong, allow only five loops before
+ # giving up.
+ #
+ if (!$allchars{$char} and $char ne ".notdef") {
+ if (grep /^$char$/, @nchars) {
+ unless (++$def->{requeue} > 5) {
+ push @defs, $def;
+ next;
+ }
+ }
+ else { die "Bad definition (no such character): $qdef\n" }
+ }
+ if ($acc and !$allchars{$acc} and $acc !~ /^$accents$/) {
+ if (grep /^$acc$/, @nchars) {
+ unless (++$def->{requeue} > 5) {
+ push @defs, $def;
+ next;
+ }
+ }
+ else { die "Bad definition (no such accent): $qdef\n" }
+ }
+ #
+ # Remove any existing claims on $num
+ #
+ @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/,
+ @{ $allchars{$chars[$num]{id}}{num} };
+ #
+ # First deal with .notdef
+ #
+ if ($nchar eq ".notdef") {
+ undef $chars[$num];
+ }
+ #
+ # Next look among existing chars (unless blocked by -b)
+ #
+ elsif (!($acc and $opt_b) and $allchars{$nchar}) {
+ push( @{ $allchars{$nchar}{num} }, $num);
+ $chars[$num] = $allchars{$nchar};
+ }
+ #
+ # If it can't be built from sub-elements, issue a warning and move on
+ #
+ elsif (!$acc) {
+ warn "No such character - ignoring definition: $qdef\n";
+ undef $chars[$num];
+ }
+ #
+ # Now build the char
+ #
+ else {
+ #
+ # First get rid of predefined/duplicated ligtable statements
+ # and character definitions; also synonyms
+ #
+ $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar .*|.*$nchar)\)$//gm;
+ $allchars{$nchar} = ();
+ if ($acc eq "overdot") {
+ $nchar2 = $char . "dotaccent";
+ $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar2 .*|.*$nchar2)\)$//gm;
+ delete $allchars{$nchar2};
+ }
+ #
+ # Store the info that will be needed to have the character
+ # linked into the LIGTABLE
+ #
+ push @newligs, "$char: (LIG $acc $nchar)";
+ #
+ # Go!
+ #
+ if ($acc =~ /^$subacc$/) {
+ subacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^$supacc$/) {
+ supacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^$underacc$/) {
+ underacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^underbar$/) {
+ underb($num, $char, $nchar);
+ fixkerns($char, $acc);
+ }
+ else {
+ digraph($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ }
+}
+
+###################
+# Sort out ligtable
+###################
+#
+# Pull in the newly created ligatures
+#
+foreach $newlig (@newligs) {
+ $newlig =~ s/^(.+)://;
+ $newelm1 = $1;
+ unless ($ligs =~ s/(^ \(LABEL $newelm1\)\n)/$1$newlig\n/m) {
+ $ligs =~ s[^( \)\n)]
+ [ \(LABEL $newelm1\)\n$newlig\n \(STOP\)\n$1]m
+ }
+}
+#
+# Convert to vpl representation, eliminating statements invoking
+# "unencoded" characters
+#
+@liglist = split /\n/, $ligs;
+$ligs = "";
+foreach (@liglist) {
+ if (/^( \(LIG \S+ )(\S+)\)$/) {
+ if ($n = ${ $allchars{$2}{num} }[0]) {
+ s/^( \(LIG \S+ )(\S+)\)$/$1$nv[$n])/;
+ }
+ else { next }
+ }
+ if (/^( \((?:LABEL|LIG|KRN) )([^ )]+)(.*)$/) {
+ ($one, $two, $three) = ($1, $2, $3);
+ foreach $n (@{ $allchars{$two}{num} }) {
+ $ligs .= "$one$nv[$n]$three\n";
+ }
+ }
+ else { $ligs .= "$_\n" }
+}
+#
+# Eliminate sequences orphaned by elimination of a LABEL
+#
+@liglist = split / \(STOP\)\n/, $ligs;
+$ligs = "";
+foreach (@liglist) {
+ if (/^ \(LABEL /m) { $ligs .= "$_ (STOP)\n" }
+ elsif (/^ \)$/m) { $ligs .= $_ }
+}
+#
+# Eliminate empty statements
+#
+$ligs =~ s/(^ \(LABEL .*\)\n)+ \(STOP\)\n//gm;
+@ligs = split /^/, $ligs;
+foreach (@ligs) {
+ s/ [RD] (-?)([0-9.]+)\)/" R " . $1 . $2\/$scale . ")"/ge
+}
+
+####################
+# Output the results
+####################
+#
+print @vplhead, @ligs;
+foreach $i (0 .. 0xFFFF) { if (defined $chars[$i]{id}) { printchar($i) } }
+
+#####################
+# End of main program
+#####################
+
+sub storeinfo {
+ #
+ # Extract info from a character definition and store it in @chars
+ #
+ my $char = shift;
+ my $num;
+ if ($char =~ /\A\(CHARACTER O ([0-7]+)/m) { $num = oct $1 }
+ elsif ($char =~ /\A\(CHARACTER C (.)/m) { $num = ord $1 }
+ $chars[$num]{id} = $enc[$num];
+ push( @{ $chars[$num]{num} }, $num);
+ if ($char =~ /^ \(CHARWD R (.*?)\)$/m) { $chars[$num]{wd} = $1 }
+ if ($char =~ /^ \(CHARHT R (.*?)\)$/m) { $chars[$num]{ht} = $1 }
+ if ($char =~ /^ \(CHARDP R (.*?)\)$/m) { $chars[$num]{dp} = $1 }
+ if ($char =~ /^ \(CHARIC R (.*?)\)$/m) { $chars[$num]{ic} = $1 }
+ if ($char =~ /^ \(MAP\n((.|\n)*)^ \)/m) { $chars[$num]{map} = $1 }
+ else { $chars[$num]{map} = " (SETCHAR $nv[$num])\n" }
+ $chars[$num]{map} =~ s[(\(SETCHAR )O ([0-7]+)\)]
+ [$1 . sprintf("H %04lX", oct $2) . ")"]gme
+}
+
+sub printchar {
+ #
+ # Extract info from @chars and build it into a character definition
+ #
+ my $num = shift;
+ my @ch;
+ push @ch, "(CHARACTER ";
+ if (chr($num) =~ /[0-9A-Za-z]/) { push @ch, "C " . chr($num) }
+ else {
+ push @ch, sprintf("H %04lX", $num);
+ push @ch, " (COMMENT " . $chars[$num]{id} . ")";
+ }
+ push @ch, "\n";
+ push @ch, " (CHARWD R " . $chars[$num]{wd} . ")\n"
+ if defined $chars[$num]{wd};
+ push @ch, " (CHARHT R " . $chars[$num]{ht} . ")\n"
+ if defined $chars[$num]{ht};
+ push @ch, " (CHARDP R " . $chars[$num]{dp} . ")\n" if $chars[$num]{dp};
+ push @ch, " (CHARIC R " . $chars[$num]{ic} . ")\n" if $chars[$num]{ic};
+ push @ch, " (MAP\n";
+ push @ch, $chars[$num]{map};
+ push @ch, " )\n";
+ push @ch, " )\n";
+ foreach (@ch) {
+ s/(?<!SELECTFONT) [RD] (-?)([0-9.]+)\)/" R " . $1 . $2\/$scale . ")"/ge
+ }
+ print @ch
+}
+
+sub chmove {
+ #
+ # Move a character
+ #
+ my ($char, $num) = @_;
+ my $i;
+ foreach $i (@{ $allchars{$char}{num} }) { undef $chars[$i] }
+ @{ $allchars{$char}{num} } = ();
+ @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/,
+ @{ $allchars{$chars[$num]{id}}{num} };
+ push( @{ $allchars{$char}{num} }, $num);
+ $chars[$num] = $allchars{$char};
+}
+
+sub max {
+ #
+ # Return greater of two values
+ #
+ my ($a, $b) = @_;
+ return $a > $b ? $a : $b;
+}
+
+sub subacc {
+ #
+ # Subscript accents
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($h, $s1, $s2, $s3);
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$char}{ht};
+ $allchars{$id}{dp} = $allchars{$acc}{dp};
+ $allchars{$id}{ic} = $allchars{$char}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2);
+ if ($h > 0) { $s2 = " (MOVERIGHT R $h) " }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 = " (MOVELEFT R $h) ";
+ }
+ else { $s2 = " " }
+ $s3 = $allchars{$acc}{map};
+ $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ $allchars{$id}{map} = " $s1\n$s2$s3\n";
+ $chars[$num] = $allchars{$id};
+}
+
+sub supacc {
+ #
+ # Superscript accents
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($cb, $h, $hadj, $tallchar, $ic, $s1, $s2, $s3);
+ if ($char eq "i" and $allchars{"dotlessi"}) { $char = "dotlessi" }
+ if ($char eq "j" and $allchars{"dotlessj"}) { $char = "dotlessj" }
+ if ($acc eq "overdot") { $acc = "dotaccent" }
+ if ($acc eq "candrabindu") {
+ $acc = "breve";
+ ($cb = $allchars{"dotaccent"}{map}) =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ }
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$acc}{ht};
+ $allchars{$id}{dp} = $allchars{$char}{dp};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ if ($scaps and $char =~ /^[a-z]/) { # accented small caps
+ $tallchar = 1;
+ if ($char =~ /$supacc$/
+ and $char !~ /under$supacc$/) { # double accs
+ $s2 = " (MOVEUP R $v1)";
+ $allchars{$id}{ht} += $v1;
+ $hadj = sprintf("%.3f", $v1 * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ else { # single accs
+ $s2 = " (MOVEUP R $scoffset)";
+ $allchars{$id}{ht} += $scoffset;
+ $hadj = sprintf("%.3f", $scoffset * $slant);
+ $ic = $allchars{$acc}{ic} + $hadj;
+ }
+ }
+ elsif ($allchars{$char}{ht} >= ($accheight + $v2)) { # double accs
+ $tallchar = 1; # on caps etc.
+ $s2 = " (MOVEUP R ${ \($v1 + $v2) })";
+ $allchars{$id}{ht} += ($v1 + $v2);
+ $hadj = sprintf("%.3f", ($v1 + $v2) * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ elsif ($allchars{$char}{ht} > 1.15 * $xheight) {
+ $tallchar = 1;
+ if ($char =~ /$supacc$/
+ and $char !~ /under$supacc$/) { # double accs
+ $s2 = " (MOVEUP R $v1)";
+ $allchars{$id}{ht} += $v1;
+ $hadj = sprintf("%.3f", $v1 * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ else { # caps etc.
+ $s2 = " (MOVEUP R $v2)";
+ $allchars{$id}{ht} += $v2;
+ $hadj = sprintf("%.3f", $v2 * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ }
+ else { # single accs
+ $s2 = " ";
+ $ic = $allchars{$acc}{ic};
+ }
+ $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2);
+ unless ($tallchar) { $ic -= $h }
+ $allchars{$id}{ic} = $ic unless $ic < 0;
+ $h += $hadj;
+ if ($h > 0) { $s2 .= " (MOVERIGHT R $h) " }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 .= " (MOVELEFT R $h) ";
+ }
+ else { $s2 .= " " }
+ $s3 = $allchars{$acc}{map};
+ $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ if ($cb) { # candrabindu
+ $cb = $s2 . $cb;
+ if ($cbx) {
+ unless (($cb =~ s/(MOVERIGHT R )([0-9.]+)/$1 . ($2 + $cbx * $scale)/e)
+ or ($cb =~ s/(MOVELEFT R )([0-9.]+)/$1 . ($2 - $cbx * $scale)/e)) {
+ $cb =~ s/^( +)/"$1(MOVERIGHT R " . ($cbx * $scale) . ") "/e;
+ }
+ }
+ if ($cby) {
+ unless ($cb =~ s/(MOVEUP R )([0-9.]+)/$1 . ($2 + $cby * $scale)/e) {
+ $cb =~ s/^( +)/"$1(MOVEUP R " . ($cby * $scale) . ") "/e;
+ }
+ }
+ $cb .= "\n";
+ $s1 = "(PUSH) " . $s1;
+ $s3 .= " (POP)";
+ }
+ $allchars{$id}{map} = " $s1\n$s2$s3\n$cb";
+ $chars[$num] = $allchars{$id};
+}
+
+sub underacc {
+ #
+ # Dropped accents
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($h, $v, $s1, $s2, $s3);
+ $acc =~ s/^under//;
+ if ($acc eq "dot") { $acc = "period" }
+ if ($acc eq "candrabindu") { die "Bad definition (no such accent): $qdef\n" }
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$char}{ht};
+ $allchars{$id}{ic} = $allchars{$char}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ if ($acc =~ /^$supacc$/) {
+ $v = $allchars{$id}{dp} = $underadp * $scale * $shrink;
+ $v += ($accdepth * $shrink);
+ }
+ else {
+ $v = $allchars{$id}{dp} = $underddp * $scale + $allchars{$acc}{dp};
+ }
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ if ($acc =~ /^$supacc$/) {
+ $h = ($allchars{$char}{wd} - ($allchars{$acc}{wd} * $shrink)) / 2 - $v * $slant;
+ if ($opt_s) { $s2 = " (SELECTFONT D 1)\n" }
+ }
+ else {
+ $h = ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2 - $v * $slant;
+ }
+ $h = sprintf("%.3f", $h);
+ if ($h > 0) {
+ $s2 .= " (MOVEDOWN R $v) (MOVERIGHT R $h) ";
+ }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 .= " (MOVEDOWN R $v) (MOVELEFT R $h) ";
+ }
+ else { $s2 = " (MOVEDOWN R $v) " }
+ $s3 = $allchars{$acc}{map};
+ $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ if ($opt_s and $acc =~ /^$supacc$/) { $s3 .= "\n (SELECTFONT D 0)" }
+ $allchars{$id}{map} = " $s1\n$s2$s3\n";
+ $chars[$num] = $allchars{$id};
+}
+
+sub underb {
+ #
+ # Underbar
+ #
+ my ($num, $char, $id) = @_;
+ my ($h, $w, $dp, $s1, $s2, $s3);
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$char}{ht};
+ $allchars{$id}{dp} = $dp = $underbdp * $scale;
+ $allchars{$id}{ic} = $allchars{$char}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ $h = sprintf("%.3f", ($allchars{$id}{wd} / 10 - $dp * $slant));
+ $w = sprintf("%.3f", ($allchars{$id}{wd} * 8 / 10));
+ if ($h > 0) {
+ $s2 = " (MOVEDOWN R $dp) (MOVERIGHT R $h) ";
+ }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 = " (MOVEDOWN R $dp) (MOVELEFT R $h) ";
+ }
+ else { $s2 .= " (MOVEDOWN R $dp) " }
+ $s3 = "(SETRULE R ${ \($thk) } R $w)";
+ $allchars{$id}{map} = " $s1\n$s2$s3\n";
+ $chars[$num] = $allchars{$id};
+ #
+ # If the character to be underscored is a digraph, fix up the LIGTABLE
+ #
+ if (grep /^$char$/, @digraphs) {
+ pop @newligs;
+ dummychar(0x035F, "uni035F") unless defined $allchars{uni035F};
+ $char =~ /^(.)(.)$/;
+ ($one, $two) = ($1, $2);
+ $one_ = $one . "_uni035F";
+ dummychar($dummycodepoint--, $one_) unless defined $allchars{$one_};
+ push @newligs, "$one: (LIG uni035F $one_)"
+ unless (grep /^$one: \(LIG uni035F $one_\)$/, @newligs);
+ push @newligs, "$one_: (LIG $two $id)";
+ }
+}
+
+sub digraph {
+ #
+ # Make a new character consisting of two existing characters
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($one, $two, $kern, $s1, $s2, $charZWJ);
+ #
+ # Remove the ligature info -- we don't want every occurrence of
+ # e.g."kh" to be converted into a digraph.
+ #
+ pop @newligs;
+ #
+ # List all digraphs for future reference
+ #
+ push @digraphs, $id;
+ if ($ligs =~ /^ \(LABEL $char\)\n(.*?)\n \(KRN $acc R (-?[0-9.]+)\)\n/ms) {
+ ($one, $two) = ($1, $2);
+ }
+ $kern = $two if $one !~ /^ \(STOP\)$/m;
+ $allchars{$id}{wd} = $allchars{$char}{wd} + $allchars{$acc}{wd};
+ $allchars{$id}{wd} += $kern;
+ $allchars{$id}{ht} = max($allchars{$char}{ht}, $allchars{$acc}{ht});
+ $allchars{$id}{dp} = max($allchars{$char}{dp}, $allchars{$acc}{dp});
+ $allchars{$id}{ic} = $allchars{$acc}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ chomp ($s2 = $allchars{$acc}{map});
+ $s1 =~ s/(\(SETCHAR .*?\))/$1\n$s2/;
+ if ($kern) {
+ if ($kern < 0) {
+ $kern = -$kern;
+ $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVELEFT R $kern)/;
+ }
+ else { $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVERIGHT R $kern)/ }
+ }
+ $allchars{$id}{map} = $s1;
+ $chars[$num] = $allchars{$id};
+}
+
+sub dummychar {
+ #
+ # Make a new dummy character
+ #
+ my ($num, $id) = @_;
+ $allchars{$id}{wd} = 0;
+ $allchars{$id}{ht} = 0;
+ $allchars{$id}{dp} = 0;
+ $allchars{$id}{ic} = 0;
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $allchars{$id}{map} = " (SETCHAR H 0020)\n";
+ $chars[$num] = $allchars{$id};
+}
+
+sub fixkerns {
+ #
+ # Generalise the kerning info contained in the vpl file by applying
+ # it to new accented chars. Do not kern lower-case chars bearing
+ # superscript accents with capitals, quotes or a preceding "f".
+ #
+ my ($char, $acc) = @_;
+ my ($olabel, $nlabel, @liglist, $lchar, $rchar);
+ return if $char eq "space";
+ if ($acc =~ /^$accents$/) { $lchar = $rchar = $char }
+ else {
+ $lchar = $char;
+ $rchar = $acc;
+ }
+ unless ($char =~ /^[a-z]/ and $acc =~ /^$supacc$/) {
+ $ligs =~ s[(\n \(LABEL )$rchar\)(?!\n \(LIG.*$)]
+ [$&$1$char$acc)]gm
+ unless $ligs =~ /\n \(LABEL $char$acc\)$/m;
+ $ligs =~ s[(\n \(LABEL )$rchar\)(\n \(LIG.*$)+(?!\n \(STOP\))]
+ [$&$1$char$acc)]gm
+ unless $ligs =~ /\n \(LABEL $char$acc\)$/m;
+ $ligs =~ s[(\n \(KRN )$lchar( .*)$]
+ [$&$1$char$acc$2]gm;
+ }
+ else {
+ if ($ligs =~ /\n \(LABEL $char\).*?\(STOP\)/s) {
+ $nlabel = $olabel = $&;
+ $nlabel =~ s/(\n \(LABEL $char)\)/$1$acc)/
+ unless $ligs =~ /\n \(LABEL $char$acc\)/m;
+ $nlabel =~ s/\n \(LIG .*\)$//gm;
+ $nlabel =~ s/\n \(LABEL (?!$char$acc).*\)$//gm;
+ $nlabel =~ s/\n \(KRN ([A-Z]|quote).*\)$//gm;
+ $ligs =~ s/(\n \(LABEL )$char\).*?\(STOP\)/$olabel$nlabel/s;
+ }
+ @liglist = split /\n \(STOP\)/, $ligs;
+ foreach (@liglist) {
+ unless (/\n \(LABEL ([A-Zf]|quote).*\)$/m) {
+ s/(\n \(KRN $char)( .*\))$/$&$1$acc$2/gm;
+ }
+ }
+ $ligs = join("\n (STOP)", @liglist);
+ }
+}
diff --git a/Build/source/texk/texlive/linked_scripts/accfonts/vpl2vpl b/Build/source/texk/texlive/linked_scripts/accfonts/vpl2vpl
new file mode 100644
index 00000000000..65ded28ce59
--- /dev/null
+++ b/Build/source/texk/texlive/linked_scripts/accfonts/vpl2vpl
@@ -0,0 +1,994 @@
+#!/usr/bin/perl
+
+# Vpl2vpl: a program to generate accented virtual fonts for TeX
+# Copyright (C) 1997 John D. Smith
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+$version = 0.25;
+#------------------------------------------------------------------------#
+$description =
+"Syntax: vpl2vpl -d definition-file [-s shrink-factor]
+ [-c candrabindu-adjustment] [-b] vpl-file
+
+Vpl2vpl creates new TeX virtual fonts based on existing fonts or
+virtual fonts (\"input fonts\"). A successful run will read a pl
+(Property List) or vpl (Virtual Property List) file and a definition
+file, and will generate a new vpl (Virtual Property List) file on
+standard output. The input font is assumed to adhere to the standard
+TeX encoding for text fonts unless it was created with either of the
+programs afm2pl or afm2tfm, in which case it is assumed to conform to
+(respectively) the Adobe Standard Encoding or the encoding specified
+in the file dvips.enc. In either case, the name of the input font is
+assumed to be the name of the input file without its .vpl or .pl
+extension: it must conform to normal TeX conventions for naming fonts,
+as vpl2vpl attempts to draw conclusions from it about the kind of font
+it is dealing with.
+
+A typical complete sequence of commands to create a new virtual
+font might therefore be
+ tftopl cmr10.tfm cmr10.pl
+ vpl2vpl -d ISO-Latin1.def cmr10.pl >cmr10_isol1.vpl
+ vptovf cmr10_isol1.vpl cmr10_isol1.vf cmr10_isol1.tfm
+for a Computer Modern font, or
+ afm2pl Times-Roman.afm rptmr.pl
+ pltotf rptmr.pl rptmr.tfm
+ vpl2vpl -d ISO-Latin1.def rptmr.pl >ptmr-isol1.vpl
+ vptovf ptmr-isol1.vpl ptmr-isol1.vf ptmr-isol1.tfm
+for a PostScript font.
+
+Another approach for a PostScript font is to use afm2tfm:
+ afm2tfm Times-Roman.afm -t dvips.enc -v ptmr rptmr
+ vpl2vpl -d ISO-Latin1.def ptmr.vpl >ptmr-isol1.vpl
+ vptovf ptmr-isol1.vpl ptmr-isol1.vf ptmr-isol1.tfm
+-- but this is now deprecated, as afm2tfm generates incorrect
+values for the heights of some characters, and this can lead to
+bad accent placing.
+
+In order to keep the whole upper half of the character set free for
+the requirements of the encoding specified in the definition file,
+certain modifications are made to input fonts following the
+dvips.enc encoding to bring them into greater conformity with the
+TeX norm. In particular, the characters dotaccent and hungarumlaut
+are placed in the positions assigned by TeX (\"5F, \"7D), not those
+enforced by dvips.enc (\"C7, \"CD). The f-ligatures, double quotes
+and dashes are also moved from the upper half of the character set
+to their normal TeX positions. As a result, the following characters
+are not found in the lower half of the character set: quotesingle,
+quotedbl, backslash, underscore, braceleft, bar, braceright. These
+characters can, however, be assigned positions in the output font if
+they are needed. (Indeed, they could all be explicitly restored to
+their dvips.enc positions if this were desired.)
+
+Options:
+
+ -d should refer to a font definition file. This file (which could
+ usefully be named, e.g., \"French.def\") should consist of
+ lines of character definitions, in the form
+ \"number\" \"character\"
+ or
+ \"number\" \"character\" \"accent\"
+ Here \"number\" represents the character's position in the new
+ encoding and may be expressed in decimal, octal or hex;
+ \"character\" names the character (e.g. \"comma\", \"eight\",
+ \"A\") or consists of the word \".notdef\" (indicating that
+ the specified number's \"slot\" in the new encoding is to be
+ empty); and \"accent\" optionally names an accent to be placed
+ on the character. In addition to the standard accents available
+ in PostScript fonts, \"underbar\" and \"underdot\" are also
+ available, as are \"under\" versions of all the normal
+ superscript accents (\"underdieresis\", \"underring\", etc.).
+ The Indian accent \"candrabindu\" may also be specified: it
+ is formed by overprinting a breve with a dotaccent. Finally,
+ \"overdot\" may be used as a synonym for \"dotaccent\".
+
+ If the character named in the \"accent\" position is not in fact
+ a valid accent character, the program interprets the definition
+ as a request for a digraph formed from the \"character\" and the
+ \"accent\". A digraph consisting of, say, \"k\" and \"h\" will be
+ indistinguishable from the letters \"k\" and \"h\" printed
+ consecutively, but the digraph \"kh\" can itself receive accents
+ like any other character: see next paragraph.
+
+ A new character (such as \"amacron\" or \"kh\") may be freely
+ used in the \"character\" position of a further definition (such
+ as \"amacron breve\" or \"kh underbar\"). There is no constraint
+ on the ordering of definitions within a definition file. The
+ definition of \"a macron\" does not have to precede that of
+ \"amacron breve\": requests for \"impossible\" characters are
+ deferred until their constituents have had a chance to come into
+ being.
+
+ \"Slots\" for which no new definition is given retain the
+ definition they have in the input font.
+
+ The definition file may also contain blank lines and comments
+ (introduced by \"\#\").
+
+ -s may optionally give the factor, expressed as a per-thousand
+ value, by which normally superscript accents (such as dieresis,
+ ring) should be shrunk when they are used as subscript accents
+ (such as underdieresis, underring). Values of around 800 may be
+ found useful.
+
+ -c may optionally give two comma-separated numerical values to
+ adjust the x and y coordinates of the dotaccent placed within a
+ breve to form the candrabindu accent. A coordinate scheme using
+ \"DESIGNUNITS R 1000\" is assumed.
+
+ -b may optionally be specified to block the use of predefined
+ accented characters, forcing vpl2vpl to define its own
+ versions. This may be useful to secure a consistent appearance
+ in cases where a font designer does not share vpl2vpl's views
+ on where accents should be placed.
+
+ -h prints this help.
+";
+#------------------------------------------------------------------------#
+
+########################
+# Packages and constants
+########################
+#
+use File::Basename;
+use Getopt::Std;
+$cmdline = basename($0) . " " . join " ", @ARGV;
+getopts('d:s:c:bh');
+if ($opt_h or !$opt_d or $#ARGV != 0) {
+ print STDERR $description;
+ exit 1;
+}
+
+$filename = $ARGV[0];
+($fontname = $filename) =~ s/\..*$//;
+($encname = basename($opt_d)) =~ s/\..*$//;
+$vtitle = "(VTITLE Font $fontname modified for $encname encoding by vpl2vpl";
+$vtitle .= " v. $version" if $version;
+$vtitle .= ")\n(COMMENT Command line: $cmdline)";
+
+#
+# Flags for bold and small caps. These are probably a bit iffy, but
+# there's not much that can be done about it.
+#
+if ($fontname =~ /(^p.*b[oi]?[c]?$|^[^p].*bx[a-z]*[0-9]+$)/) { $bold = 1 }
+if ($fontname =~ /(^p.*c$|^[^p].*csc[a-z]*[0-9]+$)/) { $scaps = 1 }
+if ($opt_s) { $shrink = $opt_s / 1000 } else { $shrink = 1 }
+
+#
+# Array to convert from number to vpl representation
+#
+foreach $i (0 .. 255) {
+ $nv[$i] = (chr($i) =~ /[0-9A-Za-z]/ ? "C " . chr $i : sprintf("O %lo", $i));
+}
+
+#
+# Now the encoding vectors.
+#
+@TeXenc = (
+ "Gamma", "Delta", "Theta", "Lambda",
+ "Xi", "Pi", "Sigma", "Upsilon",
+ "Phi", "Psi", "Omega", "ff",
+ "fi", "fl", "ffi", "ffl",
+ "dotlessi", "dotlessj", "grave", "acute",
+ "caron", "breve", "macron", "ring",
+ "cedilla", "germandbls", "ae", "oe",
+ "oslash", "AE", "OE", "Oslash",
+ "space", "exclam", "quotedblright", "numbersign",
+ "dollar", "percent", "ampersand", "quoteright",
+ "parenleft", "parenright", "asterisk", "plus",
+ "comma", "hyphen", "period", "slash",
+ "zero", "one", "two", "three",
+ "four", "five", "six", "seven",
+ "eight", "nine", "colon", "semicolon",
+ "exclamdown", "equal", "questiondown", "question",
+ "at", "A", "B", "C",
+ "D", "E", "F", "G",
+ "H", "I", "J", "K",
+ "L", "M", "N", "O",
+ "P", "Q", "R", "S",
+ "T", "U", "V", "W",
+ "X", "Y", "Z", "bracketleft",
+ "quotedblleft", "bracketright", "circumflex", "dotaccent",
+ "quoteleft", "a", "b", "c",
+ "d", "e", "f", "g",
+ "h", "i", "j", "k",
+ "l", "m", "n", "o",
+ "p", "q", "r", "s",
+ "t", "u", "v", "w",
+ "x", "y", "z", "endash",
+ "emdash", "hungarumlaut", "tilde", "dieresis"
+);
+
+@dvipsenc = (
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "quotesingle", "exclamdown", "questiondown",
+ "dotlessi", "dotlessj", "grave", "acute",
+ "caron", "breve", "macron", "ring",
+ "cedilla", "germandbls", "ae", "oe",
+ "oslash", "AE", "OE", "Oslash",
+ "space", "exclam", "quotedbl", "numbersign",
+ "dollar", "percent", "ampersand", "quoteright",
+ "parenleft", "parenright", "asterisk", "plus",
+ "comma", "hyphen", "period", "slash",
+ "zero", "one", "two", "three",
+ "four", "five", "six", "seven",
+ "eight", "nine", "colon", "semicolon",
+ "less", "equal", "greater", "question",
+ "at", "A", "B", "C",
+ "D", "E", "F", "G",
+ "H", "I", "J", "K",
+ "L", "M", "N", "O",
+ "P", "Q", "R", "S",
+ "T", "U", "V", "W",
+ "X", "Y", "Z", "bracketleft",
+ "backslash", "bracketright", "circumflex", "underscore",
+ "quoteleft", "a", "b", "c",
+ "d", "e", "f", "g",
+ "h", "i", "j", "k",
+ "l", "m", "n", "o",
+ "p", "q", "r", "s",
+ "t", "u", "v", "w",
+ "x", "y", "z", "braceleft",
+ "bar", "braceright", "tilde", "dieresis",
+ "asciicircum", "asciitilde", "Ccedilla", "Iacute",
+ "Icircumflex", "atilde", "edieresis", "egrave",
+ "scaron", "zcaron", "Eth", "ff",
+ "ffi", "ffl", ".notdef", ".notdef",
+ ".notdef", ".notdef", "Scaron", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ "Ydieresis", ".notdef", "Zcaron", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", "cent", "sterling",
+ "fraction", "yen", "florin", "section",
+ "currency", "copyright", "quotedblleft", "guillemotleft",
+ "guilsinglleft", "guilsinglright", "fi", "fl",
+ "degree", "endash", "dagger", "daggerdbl",
+ "periodcentered", ".notdef", "paragraph", "bullet",
+ "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright",
+ "ellipsis", "perthousand", ".notdef", ".notdef",
+ "Agrave", "Aacute", "Acircumflex", "Atilde",
+ "Adieresis", "Aring", ".notdef", "dotaccent",
+ "Egrave", "Eacute", "Ecircumflex", "Edieresis",
+ "Igrave", "hungarumlaut", "ogonek", "Idieresis",
+ "emdash", "Ntilde", "Ograve", "Oacute",
+ "Ocircumflex", "Otilde", "Odieresis", ".notdef",
+ ".notdef", "Ugrave", "Uacute", "Ucircumflex",
+ "Udieresis", "Yacute", "Thorn", ".notdef",
+ "agrave", "aacute", "acircumflex", "ordfeminine",
+ "adieresis", "aring", ".notdef", "ccedilla",
+ "Lslash", "eacute", "ecircumflex", "ordmasculine",
+ "igrave", "iacute", "icircumflex", "idieresis",
+ ".notdef", "ntilde", "ograve", "oacute",
+ "ocircumflex", "otilde", "odieresis", ".notdef",
+ "lslash", "ugrave", "uacute", "ucircumflex",
+ "udieresis", "yacute", "thorn", "ydieresis"
+);
+
+@adobeenc=(
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ "space", "exclam", "quotedbl", "numbersign",
+ "dollar", "percent", "ampersand", "quoteright",
+ "parenleft", "parenright", "asterisk", "plus",
+ "comma", "hyphen", "period", "slash",
+ "zero", "one", "two", "three",
+ "four", "five", "six", "seven",
+ "eight", "nine", "colon", "semicolon",
+ "less", "equal", "greater", "question",
+ "at", "A", "B", "C",
+ "D", "E", "F", "G",
+ "H", "I", "J", "K",
+ "L", "M", "N", "O",
+ "P", "Q", "R", "S",
+ "T", "U", "V", "W",
+ "X", "Y", "Z", "bracketleft",
+ "backslash", "bracketright", "asciicircum", "underscore",
+ "quoteleft", "a", "b", "c",
+ "d", "e", "f", "g",
+ "h", "i", "j", "k",
+ "l", "m", "n", "o",
+ "p", "q", "r", "s",
+ "t", "u", "v", "w",
+ "x", "y", "z", "braceleft",
+ "bar", "braceright", "asciitilde", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "exclamdown", "cent", "sterling",
+ "fraction", "yen", "florin", "section",
+ "currency", "quotesingle", "quotedblleft", "guillemotleft",
+ "guilsinglleft", "guilsinglright", "fi", "fl",
+ ".notdef", "endash", "dagger", "daggerdbl",
+ "periodcentered", ".notdef", "paragraph", "bullet",
+ "quotesinglbase", "quotedblbase", "quotedblright", "guillemotright",
+ "ellipsis", "perthousand", ".notdef", "questiondown",
+ ".notdef", "grave", "acute", "circumflex",
+ "tilde", "macron", "breve", "dotaccent",
+ "dieresis", ".notdef", "ring", "cedilla",
+ ".notdef", "hungarumlaut", "ogonek", "caron",
+ "emdash", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "AE", ".notdef", "ordfeminine",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ "Lslash", "Oslash", "OE", "ordmasculine",
+ ".notdef", ".notdef", ".notdef", ".notdef",
+ ".notdef", "ae", ".notdef", ".notdef",
+ ".notdef", "dotlessi", ".notdef", ".notdef",
+ "lslash", "oslash", "oe", "germandbls",
+ ".notdef", ".notdef", ".notdef", ".notdef"
+);
+
+###############
+# Read DEF file
+###############
+#
+open DEF, $opt_d or die "Cannot open $opt_d: $!\n";
+while (<DEF>) {
+ next if (/^\s*$/ || /^\#/);
+ s/\s*(\#.*)?$//;
+ push @deflines, $_;
+}
+close DEF;
+
+###############
+# Read VPL file
+###############
+#
+# File header
+#
+$vplhead = <> or exit 1;
+unless ($vplhead =~ /^\((VTITLE|FAMILY) /) {
+ die "$filename is not a vpl file: giving up\n"
+}
+do {
+ $_ = <>;
+ $vplhead .= $_;
+} until ($_ =~ /^\(LIGTABLE$/ or eof);
+if (eof) {
+ die "$filename does not seem to be a text font (no LIGTABLE): giving up\n";
+}
+if ($vplhead =~ s/\A\(VTITLE(.*)$/$vtitle\n(COMMENT Old vtitle:$1/m) {
+ $vplhead =~ s/\n\(COMMENT Please edit that VTITLE .*\)$//m;
+ @enc = @dvipsenc;
+ $dvips = 1;
+}
+elsif ($vplhead =~ /\A\(FAMILY.*\)\n\(CODINGSCHEME ADOBESTANDARDENCODING\)$/m) {
+ $vplhead =~ s/\A/$vtitle\n/m;
+ @enc = @adobeenc;
+ $dvips = 0;
+}
+else {
+ $vplhead =~ s/\A/$vtitle\n/m;
+ @enc = @TeXenc;
+ $dvips = 0;
+}
+if ($vplhead =~ /^\(CODINGSCHEME TEX MATH SYMBOLS/m) {
+ die "$filename is a TeX math font: giving up\n";
+}
+unless ($vplhead =~ s/^(\(CODINGSCHEME .*\+\s?)(\S+)\)$/$1$encname)/m) {
+ $vplhead =~ s/^(\(CODINGSCHEME .*)\)$/$1 + $encname)/m;
+}
+if ($vplhead =~ /^\(DESIGNUNITS R (.+)\)/m) { $scale = $1 }
+else {$scale = 1 }
+if ($vplhead =~ /^ \(SLANT R (.+)\)/m) { $slant = $1 }
+if ($vplhead =~ /^ \(XHEIGHT [DR] (.+)\)/m) { $xheight = $1 }
+unless ($vplhead =~ /^\(MAPFONT /m) {
+ if ($vplhead =~ /^\(DESIGNSIZE R (.*)\)$/m) { $dsize = $1 }
+ $mapfont = "\n(MAPFONT D 0\n (FONTNAME $fontname)\n (FONTDSIZE R $dsize)\n )";
+ $vplhead =~ s/\n\(LIGTABLE\Z/$mapfont$&/m;
+}
+if ($opt_s) {
+ $vplhead =~ s[^(\(MAPFONT D )0(.*?)( \))]
+ [$&\n${1}1$2 (FONTAT R ${ \($shrink * $scale) })\n$3]ms;
+}
+
+#
+# Ligatures and kerns
+#
+do {
+ $_ = <>;
+ s/ \(comment .*$//i;
+ $ligs .= $_;
+} until $_ =~ /^ \)/;
+#
+# Now build a hash to convert from vpl representation to char name
+# and use it to make ligtable readable
+#
+foreach $i (0 .. 255) { $vc{$nv[$i]} = $enc[$i] }
+$ligs =~ s/^( \((?:LABEL|KRN) )(\S+ \S+)(.*\))$/$1$vc{$2}$3/gm;
+$ligs =~ s/^( \(LIG )(\S+ \S+) (\S+ \S+)\)$/$1$vc{$2} $vc{$3})/gm;
+
+#
+# Character definitions: store "encoded" defs in @chars, store *all*
+# defs in %allchars
+#
+$_ = <>;
+do {
+ if (/^\(CHARACTER/) {
+ $character = $_;
+ do {
+ $_ = <>;
+ $character .= $_;
+ } until $_ =~ /^ \)/;
+ storeinfo($character);
+ $_ = <>;
+ }
+} until eof;
+foreach $i (0 .. $#chars) {
+ if ($chars[$i] and $enc[$i] ne ".notdef") {
+ $allchars{$enc[$i]} = $chars[$i];
+ }
+}
+
+##################
+# Set up constants
+##################
+
+$subacc = "(cedilla|ogonek|commaaccent)";
+$supacc = "(grave|acute|circumflex|tilde|macron|breve|dotaccent|overdot|dieresis|ring|hungarumlaut|caron|candrabindu)";
+$underacc = "(underdot|under$supacc)";
+$accents = "($subacc|$supacc|$underacc|underbar)";
+$underadp = 0.230; # depth of "under" accs
+$underddp = 0.213; # depth of underdot
+if ($bold) { $thk = 0.072 } else { $thk = 0.052 } # thickness and
+$underbdp = 0.082 + $thk; # depth of underbar
+$capheight = $allchars{"X"}{ht};
+$accheight = $allchars{"macron"}{ht};
+$accdepth = $accheight - $thk * $scale; # probable approx. "depth" of macron
+$v1 = $accheight - $xheight; # vertical offset for double accents
+$v2 = $capheight - $xheight; # vertical offset for accented caps etc
+if ($scaps) { # accented small caps
+ $scoffset = $allchars{"x"}{ht} - $xheight;
+ $v1 += $scoffset;
+}
+if ($opt_c) { # candrabindu
+ ($cbx, $cby) = $opt_c =~ /^(.*),(.*)$/;
+ $cbx += ($allchars{"breve"}{wd} - $allchars{"dotaccent"}{wd}) / 2;
+ $cbx /= 1000;
+ $cby /= 1000;
+}
+
+######################
+# Build the characters
+######################
+#
+# First normalise dvips.enc encoding quirks
+#
+if ($dvips) {
+ chmove("fi", 014);
+ chmove("fl", 015);
+ chmove("quotedblright", 042);
+ chmove("quotedblleft", 0134);
+ chmove("dotaccent", 0137);
+ chmove("endash", 0173);
+ chmove("emdash", 0174);
+ chmove("hungarumlaut", 0175);
+}
+#
+# Now build a list of definitions supplied by user
+#
+for (@deflines) {
+ if (/^\s*(\d+|0[0-7]+|0x[0-9a-fA-F]+)\s+([a-zA-Z]+?|\.notdef)(?:\s+([a-zA-Z]+))?$/) {
+ ($num, $char, $acc) = ($1, $2, $3);
+ $num = oct $num if $num =~ /^0/;
+ if ($num > 255) { die "Bad definition (number out of range): $_\n" }
+ $def = {};
+ $def->{qdef} = $_;
+ $def->{num} = $num;
+ $def->{char} = $char;
+ $def->{acc} = $acc;
+ $def->{nchar} = $char . $acc;
+ push @nchars, $def->{nchar};
+ push @defs, $def;
+ }
+ else { die "Bad definition: $_\n" }
+}
+#
+# Work through the list
+#
+while (@defs) {
+ $def = shift @defs;
+ $qdef = $def->{qdef};
+ $num = $def->{num};
+ $char = $def->{char};
+ $acc = $def->{acc};
+ $nchar = $def->{nchar};
+ #
+ # If we can't handle $char/$acc yet, but believe we will be able
+ # to later, send the definition to the back of the queue. In case
+ # it later turns out we were wrong, allow only five loops before
+ # giving up.
+ #
+ if (!$allchars{$char} and $char ne ".notdef") {
+ if (grep /^$char$/, @nchars) {
+ unless (++$def->{requeue} > 5) {
+ push @defs, $def;
+ next;
+ }
+ }
+ else { die "Bad definition (no such character): $qdef\n" }
+ }
+ if ($acc and !$allchars{$acc} and $acc !~ /^$accents$/) {
+ if (grep /^$acc$/, @nchars) {
+ unless (++$def->{requeue} > 5) {
+ push @defs, $def;
+ next;
+ }
+ }
+ else { die "Bad definition (no such accent): $qdef\n" }
+ }
+ #
+ # Remove any existing claims on $num
+ #
+ @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/,
+ @{ $allchars{$chars[$num]{id}}{num} };
+ #
+ # First deal with .notdef
+ #
+ if ($nchar eq ".notdef") {
+ undef $chars[$num];
+ }
+ #
+ # Next look among existing chars (unless blocked by -b)
+ #
+ elsif (!($acc and $opt_b) and $allchars{$nchar}) {
+ push( @{ $allchars{$nchar}{num} }, $num);
+ $chars[$num] = $allchars{$nchar};
+ }
+ #
+ # If it can't be built from sub-elements, issue a warning and move on
+ #
+ elsif (!$acc) {
+ warn "No such character - ignoring definition: $qdef\n";
+ undef $chars[$num];
+ }
+ #
+ # Now build the char
+ #
+ else {
+ #
+ # First get rid of predefined/duplicated ligtable statements
+ # and character definitions; also synonyms
+ #
+ $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar .*|.*$nchar)\)$//gm;
+ $allchars{$nchar} = ();
+ if ($acc eq "overdot") {
+ $nchar2 = $char . "dotaccent";
+ $ligs =~ s/\n \((LABEL|KRN|LIG) ($nchar2 .*|.*$nchar2)\)$//gm;
+ delete $allchars{$nchar2};
+ }
+ #
+ # Go!
+ #
+ if ($acc =~ /^$subacc$/) {
+ subacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^$supacc$/) {
+ supacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^$underacc$/) {
+ underacc($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ elsif ($acc =~ /^underbar$/) {
+ underb($num, $char, $nchar);
+ fixkerns($char, $acc);
+ }
+ else {
+ digraph($num, $char, $acc, $nchar);
+ fixkerns($char, $acc);
+ }
+ }
+}
+
+###################
+# Sort out ligtable
+###################
+#
+# Convert to vpl representation, eliminating statements invoking
+# "unencoded" characters
+#
+@liglist = split /\n/, $ligs;
+$ligs = "";
+foreach (@liglist) {
+ if (/^( \(LIG \S+ )(\S+)\)$/) {
+ if ($n = ${ $allchars{$2}{num} }[0]) {
+ s/^( \(LIG \S+ )(\S+)\)$/$1$nv[$n])/;
+ }
+ else { next }
+ }
+ if (/^( \((?:LABEL|LIG|KRN) )([^ )]+)(.*)$/) {
+ ($one, $two, $three) = ($1, $2, $3);
+ foreach $n (@{ $allchars{$two}{num} }) {
+ $ligs .= "$one$nv[$n]$three\n";
+ }
+ }
+ else { $ligs .= "$_\n" }
+}
+#
+# Eliminate sequences orphaned by elimination of a LABEL
+#
+@liglist = split / \(STOP\)\n/, $ligs;
+$ligs = "";
+foreach (@liglist) {
+ if (/^ \(LABEL /m) { $ligs .= "$_ (STOP)\n" }
+ elsif (/^ \)$/m) { $ligs .= $_ }
+}
+#
+# Eliminate empty statements
+#
+$ligs =~ s/(^ \(LABEL .*\)\n)+ \(STOP\)\n//gm;
+
+####################
+# Output the results
+####################
+#
+print $vplhead, $ligs;
+foreach $i (0 .. 255) { if (defined $chars[$i]{id}) { printchar($i) } }
+
+#####################
+# End of main program
+#####################
+
+sub storeinfo {
+ #
+ # Extract info from a character definition and store it in @chars
+ #
+ my $char = shift;
+ my $num;
+ if ($char =~ /\A\(CHARACTER O ([0-7]+)/m) { $num = oct $1 }
+ elsif ($char =~ /\A\(CHARACTER C (.)/m) { $num = ord $1 }
+ $chars[$num]{id} = $enc[$num];
+ push( @{ $chars[$num]{num} }, $num);
+ if ($char =~ /^ \(CHARWD R (.*?)\)$/m) { $chars[$num]{wd} = $1 }
+ if ($char =~ /^ \(CHARHT R (.*?)\)$/m) { $chars[$num]{ht} = $1 }
+ if ($char =~ /^ \(CHARDP R (.*?)\)$/m) { $chars[$num]{dp} = $1 }
+ if ($char =~ /^ \(CHARIC R (.*?)\)$/m) { $chars[$num]{ic} = $1 }
+ if ($char =~ /^ \(MAP\n((.|\n)*)^ \)/m) { $chars[$num]{map} = $1 }
+ else { $chars[$num]{map} = " (SETCHAR $nv[$num])\n" }
+}
+
+sub printchar {
+ #
+ # Extract info from @chars and build it into a character definition
+ #
+ my $num = shift;
+ print "(CHARACTER ";
+ if (chr($num) =~ /[0-9A-Za-z]/) { print "C " . chr($num) }
+ else {
+ printf "O %lo", $num;
+ print " (COMMENT " . $chars[$num]{id} . ")";
+ }
+ print "\n";
+ print " (CHARWD R " . $chars[$num]{wd} . ")\n" if $chars[$num]{wd};
+ print " (CHARHT R " . $chars[$num]{ht} . ")\n" if $chars[$num]{ht};
+ print " (CHARDP R " . $chars[$num]{dp} . ")\n" if $chars[$num]{dp};
+ print " (CHARIC R " . $chars[$num]{ic} . ")\n" if $chars[$num]{ic};
+ print " (MAP\n";
+ print $chars[$num]{map};
+ print " )\n";
+ print " )\n";
+}
+
+sub chmove {
+ #
+ # Move a character
+ #
+ my ($char, $num) = @_;
+ my $i;
+ foreach $i (@{ $allchars{$char}{num} }) { undef $chars[$i] }
+ @{ $allchars{$char}{num} } = ();
+ @{ $allchars{$chars[$num]{id}}{num} } = grep !/$num/,
+ @{ $allchars{$chars[$num]{id}}{num} };
+ push( @{ $allchars{$char}{num} }, $num);
+ $chars[$num] = $allchars{$char};
+}
+
+sub max {
+ #
+ # Return greater of two values
+ #
+ my ($a, $b) = @_;
+ return $a > $b ? $a : $b;
+}
+
+sub subacc {
+ #
+ # Subscript accents
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($h, $s1, $s2, $s3);
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$char}{ht};
+ $allchars{$id}{dp} = $allchars{$acc}{dp};
+ $allchars{$id}{ic} = $allchars{$char}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2);
+ if ($h > 0) { $s2 = " (MOVERIGHT R $h) " }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 = " (MOVELEFT R $h) ";
+ }
+ else { $s2 = " " }
+ $s3 = $allchars{$acc}{map};
+ $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ $allchars{$id}{map} = " $s1\n$s2$s3\n";
+ $chars[$num] = $allchars{$id};
+}
+
+sub supacc {
+ #
+ # Superscript accents
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($cb, $h, $hadj, $tallchar, $ic, $s1, $s2, $s3);
+ if ($char eq "i" and $allchars{"dotlessi"}) { $char = "dotlessi" }
+ if ($char eq "j" and $allchars{"dotlessj"}) { $char = "dotlessj" }
+ if ($acc eq "overdot") { $acc = "dotaccent" }
+ if ($acc eq "candrabindu") {
+ $acc = "breve";
+ ($cb = $allchars{"dotaccent"}{map}) =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ }
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$acc}{ht};
+ $allchars{$id}{dp} = $allchars{$char}{dp};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ if ($scaps and $char =~ /^[a-z]/) { # accented small caps
+ $tallchar = 1;
+ if ($char =~ /$supacc$/
+ and $char !~ /under$supacc$/) { # double accs
+ $s2 = " (MOVEUP R $v1)";
+ $allchars{$id}{ht} += $v1;
+ $hadj = sprintf("%.3f", $v1 * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ else { # single accs
+ $s2 = " (MOVEUP R $scoffset)";
+ $allchars{$id}{ht} += $scoffset;
+ $hadj = sprintf("%.3f", $scoffset * $slant);
+ $ic = $allchars{$acc}{ic} + $hadj;
+ }
+ }
+ elsif ($allchars{$char}{ht} >= ($accheight + $v2)) { # double accs
+ $tallchar = 1; # on caps etc.
+ $s2 = " (MOVEUP R ${ \($v1 + $v2) })";
+ $allchars{$id}{ht} += ($v1 + $v2);
+ $hadj = sprintf("%.3f", ($v1 + $v2) * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ elsif ($allchars{$char}{ht} > 1.15 * $xheight) {
+ $tallchar = 1;
+ if ($char =~ /$supacc$/
+ and $char !~ /under$supacc$/) { # double accs
+ $s2 = " (MOVEUP R $v1)";
+ $allchars{$id}{ht} += $v1;
+ $hadj = sprintf("%.3f", $v1 * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ else { # caps etc.
+ $s2 = " (MOVEUP R $v2)";
+ $allchars{$id}{ht} += $v2;
+ $hadj = sprintf("%.3f", $v2 * $slant);
+ $ic = $allchars{$char}{ic};
+ }
+ }
+ else { # single accs
+ $s2 = " ";
+ $ic = $allchars{$acc}{ic};
+ }
+ $h = sprintf("%.3f", ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2);
+ unless ($tallchar) { $ic -= $h }
+ $allchars{$id}{ic} = $ic unless $ic < 0;
+ $h += $hadj;
+ if ($h > 0) { $s2 .= " (MOVERIGHT R $h) " }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 .= " (MOVELEFT R $h) ";
+ }
+ else { $s2 .= " " }
+ $s3 = $allchars{$acc}{map};
+ $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ if ($cb) { # candrabindu
+ $cb = $s2 . $cb;
+ if ($cbx) {
+ unless (($cb =~ s/(MOVERIGHT R )([0-9.]+)/$1 . ($2 + $cbx * $scale)/e)
+ or ($cb =~ s/(MOVELEFT R )([0-9.]+)/$1 . ($2 - $cbx * $scale)/e)) {
+ $cb =~ s/^( +)/"$1(MOVERIGHT R " . ($cbx * $scale) . ") "/e;
+ }
+ }
+ if ($cby) {
+ unless ($cb =~ s/(MOVEUP R )([0-9.]+)/$1 . ($2 + $cby * $scale)/e) {
+ $cb =~ s/^( +)/"$1(MOVEUP R " . ($cby * $scale) . ") "/e;
+ }
+ }
+ $cb .= "\n";
+ $s1 = "(PUSH) " . $s1;
+ $s3 .= " (POP)";
+ }
+ $allchars{$id}{map} = " $s1\n$s2$s3\n$cb";
+ $chars[$num] = $allchars{$id};
+}
+
+sub underacc {
+ #
+ # Dropped accents
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($h, $v, $s1, $s2, $s3);
+ $acc =~ s/^under//;
+ if ($acc eq "dot") { $acc = "period" }
+ if ($acc eq "candrabindu") { die "Bad definition (no such accent): $qdef\n" }
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$char}{ht};
+ $allchars{$id}{ic} = $allchars{$char}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ if ($acc =~ /^$supacc$/) {
+ $v = $allchars{$id}{dp} = $underadp * $scale * $shrink;
+ $v += ($accdepth * $shrink);
+ }
+ else {
+ $v = $allchars{$id}{dp} = $underddp * $scale + $allchars{$acc}{dp};
+ }
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ if ($acc =~ /^$supacc$/) {
+ $h = ($allchars{$char}{wd} - ($allchars{$acc}{wd} * $shrink)) / 2 - $v * $slant;
+ if ($opt_s) { $s2 = " (SELECTFONT D 1)\n" }
+ }
+ else {
+ $h = ($allchars{$char}{wd} - $allchars{$acc}{wd}) / 2 - $v * $slant;
+ }
+ $h = sprintf("%.3f", $h);
+ if ($h > 0) {
+ $s2 .= " (MOVEDOWN R $v) (MOVERIGHT R $h) ";
+ }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 .= " (MOVEDOWN R $v) (MOVELEFT R $h) ";
+ }
+ else { $s2 = " (MOVEDOWN R $v) " }
+ $s3 = $allchars{$acc}{map};
+ $s3 =~ s/\A.*(\(SETCHAR . .+?\)).*\Z/$1/s;
+ if ($opt_s and $acc =~ /^$supacc$/) { $s3 .= "\n (SELECTFONT D 0)" }
+ $allchars{$id}{map} = " $s1\n$s2$s3\n";
+ $chars[$num] = $allchars{$id};
+}
+
+sub underb {
+ #
+ # Underbar
+ #
+ my ($num, $char, $id) = @_;
+ my ($h, $w, $dp, $s1, $s2, $s3);
+ $allchars{$id}{wd} = $allchars{$char}{wd};
+ $allchars{$id}{ht} = $allchars{$char}{ht};
+ $allchars{$id}{dp} = $dp = $underbdp * $scale;
+ $allchars{$id}{ic} = $allchars{$char}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ $s1 =~ s/\A (.*)\n\Z/(PUSH) $1 (POP)/s;
+ $h = sprintf("%.3f", ($allchars{$id}{wd} / 10 - $dp * $slant));
+ $w = sprintf("%.3f", ($allchars{$id}{wd} * 8 / 10));
+ if ($h > 0) {
+ $s2 = " (MOVEDOWN R $dp) (MOVERIGHT R $h) ";
+ }
+ elsif ($h < 0) {
+ $h = -$h;
+ $s2 = " (MOVEDOWN R $dp) (MOVELEFT R $h) ";
+ }
+ else { $s2 .= " (MOVEDOWN R $dp) " }
+ $s3 = "(SETRULE R ${ \($thk * $scale) } R $w)";
+ $allchars{$id}{map} = " $s1\n$s2$s3\n";
+ $chars[$num] = $allchars{$id};
+}
+
+sub digraph {
+ #
+ # Make a new character consisting of two existing characters
+ #
+ my ($num, $char, $acc, $id) = @_;
+ my ($one, $two, $kern, $s1, $s2);
+ if ($ligs =~ /^ \(LABEL $char\)\n(.*?)\n \(KRN $acc R (-?[0-9.]+)\)\n/ms) {
+ ($one, $two) = ($1, $2);
+ }
+ $kern = $two if $one !~ /^ \(STOP\)$/m;
+ $allchars{$id}{wd} = $allchars{$char}{wd} + $allchars{$acc}{wd};
+ $allchars{$id}{wd} += $kern;
+ $allchars{$id}{ht} = max($allchars{$char}{ht}, $allchars{$acc}{ht});
+ $allchars{$id}{dp} = max($allchars{$char}{dp}, $allchars{$acc}{dp});
+ $allchars{$id}{ic} = $allchars{$acc}{ic};
+ $allchars{$id}{id} = $id;
+ push( @{ $allchars{$id}{num} }, $num);
+ $s1 = $allchars{$char}{map};
+ chomp ($s2 = $allchars{$acc}{map});
+ $s1 =~ s/(\(SETCHAR .*?\))/$1\n$s2/;
+ if ($kern) {
+ if ($kern < 0) {
+ $kern = -$kern;
+ $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVELEFT R $kern)/;
+ }
+ else { $s1 =~ s/(\(SETCHAR .*?\))/$1 (MOVERIGHT R $kern)/ }
+ }
+ $allchars{$id}{map} = $s1;
+ $chars[$num] = $allchars{$id};
+}
+
+sub fixkerns {
+ #
+ # Generalise the kerning info contained in the vpl file by applying
+ # it to new accented chars. Do not kern lower-case chars bearing
+ # superscript accents with capitals, quotes or a preceding "f".
+ #
+ my ($char, $acc) = @_;
+ my ($olabel, $nlabel, @liglist, $lchar, $rchar);
+ if ($acc =~ /^$accents$/) { $lchar = $rchar = $char }
+ else {
+ $lchar = $char;
+ $rchar = $acc;
+ }
+ unless ($char =~ /^[a-z]/ and $acc =~ /^$supacc$/) {
+ $ligs =~ s[(\n \(LABEL )$rchar\)(?!\n \(LIG.*$)]
+ [$&$1$char$acc)]gm
+ unless $ligs =~ /\n \(LABEL $char$acc\)$/m;
+ $ligs =~ s[(\n \(LABEL )$rchar\)(\n \(LIG.*$)+(?!\n \(STOP\))]
+ [$&$1$char$acc)]gm
+ unless $ligs =~ /\n \(LABEL $char$acc\)$/m;
+ $ligs =~ s[(\n \(KRN )$lchar( .*)$]
+ [$&$1$char$acc$2]gm;
+ }
+ else {
+ if ($ligs =~ /\n \(LABEL $char\).*?\(STOP\)/s) {
+ $nlabel = $olabel = $&;
+ $nlabel =~ s/(\n \(LABEL $char)\)/$1$acc)/
+ unless $ligs =~ /\n \(LABEL $char$acc\)/m;
+ $nlabel =~ s/\n \(LIG .*\)$//gm;
+ $nlabel =~ s/\n \(LABEL (?!$char$acc).*\)$//gm;
+ $nlabel =~ s/\n \(KRN ([A-Z]|quote).*\)$//gm;
+ $ligs =~ s/(\n \(LABEL )$char\).*?\(STOP\)/$olabel$nlabel/s;
+ }
+ @liglist = split /\n \(STOP\)/, $ligs;
+ foreach (@liglist) {
+ unless (/\n \(LABEL ([A-Zf]|quote).*\)$/m) {
+ s/(\n \(KRN $char)( .*\))$/$&$1$acc$2/gm;
+ }
+ }
+ $ligs = join("\n (STOP)", @liglist);
+ }
+}