summaryrefslogtreecommitdiff
path: root/language/chinese/CJK/cjk-4.8.5/contrib/wadalab/makeuniwada.pl
blob: 826ea3d3cba2b26e989abbb07fdf438aac2eb318 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
#! /usr/bin/perl -w
#
# Copyright (C) 1994-2021  Werner Lemberg <wl@gnu.org>
#
# 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 in doc/COPYING; if not, write to the Free
# Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
# MA 02110-1301 USA

# This script creates virtual subfonts in Unicode encoding for Wadalab
# subfonts. It can merge a JIS X 0208 and JIS X 0212 family into a single
# set of Unicode subfonts.
#
# As prerequisites, it needs the files `JIS0208.TXT' and `JIS0212.TXT' from
# the `OBSOLETE' directory in the `MAPPINGS' tree on ftp.unicode.org. It
# also needs the file `DNP.sfd' which gives the relationship between JIS X
# 0208 (and JIS X 0212) in EUC encoding and wadalab's DNP font encoding.
# The program `vptovf' must be available (and in the path).
#
# Call the script as
#
#   perl makeuniwada.pl namestem1 [namestem2] uni_namestem
#
# `namestem1' is the font in JIS X 0208 encoding.  The optional `namestem2'
# argument is the font in JIS X 0212, and `uni_namestem' holds the prefix
# for the Unicode subfonts. `makeuniwada.pl' reads all AFM files from the
# given wadalab font families.
#
# Example:
#
#   perl makeuniwada.pl dmj mc2j udmj
#
# This call mixes the mincho-0-12 (dmj) with mincho-1-8 (mc2j) families.

use strict;

my $prog = $0;
$prog =~ s@.*/@@;

if ($#ARGV < 1 || $#ARGV > 2) {
  die("usage: $prog namestem1 [namestem2] uni_namestem\n");
}

my $namestem1;
my $namestem2;
my $two_encodings = 0;
my @args = @ARGV;

$namestem1 = $ARGV[0];
if ($#ARGV == 2) {
  $namestem2 = $ARGV[1];
  $two_encodings = 1;
  shift;
}
my $uninamestem = $ARGV[1];


# Read `DNP.sfd'.

my %sfd;
my @subfonts;

read_sfdfile("DNP.sfd", \%sfd, \@subfonts);


# Read encoding files.
#
# The files `JIS0208.TXT' and `JIS0212.TXT' are from the `OBSOLETE'
# directory in the `MAPPINGS' tree on ftp.unicode.org.

my %jisx0208;
my %jisx0212;

read_encfile("JIS0208.TXT", \%jisx0208, 1);
if ($two_encodings) {
  read_encfile("JIS0212.TXT", \%jisx0212, 0);
}


# Read AFM files.

my @unicode;

foreach my $sub (@subfonts) {
  my $afmname = "$namestem1$sub.afm";

  if (-f $afmname) {
    read_afmfile($afmname, \@unicode, \%sfd, \%jisx0208, $sub);
  }
}
if ($two_encodings) {
  foreach my $sub (@subfonts) {
    my $afmname = "$namestem2$sub.afm";

    if (-f $afmname) {
      read_afmfile($afmname, \@unicode, \%sfd, \%jisx0212, $sub);
    }
  }
}


# Write VPL files.

my $index = 0;
foreach my $i (0 .. 255) {
  my @entries;

  foreach my $j (0 .. 255) {
    if (defined ($unicode[$index])) {
      push(@entries, "$j $unicode[$index]");
    }
    $index++;
  }

  if ($#entries >= 0) {
    write_vplfile($uninamestem . sprintf("%02x.vpl", $i), \@entries);
  }
}


# Generate VF and TFM files, then remove the VPL files.

my @vplfiles = glob("$uninamestem*.vpl");
foreach my $vplfile (@vplfiles) {
  print("Processing \`$vplfile'...\n");
  my $arg = "vptovf $vplfile";
  system($arg) == 0
  || die("$prog: calling \`$arg' failed: $?");;
  print("Removing \`$vplfile'...\n");
  unlink($vplfile);
}


# Read an SFD file.
#
#   $1: Name of the SFD file.
#   $2: Reference to the target hash file, mapping from the subfont index
#       to the character code.  The format of the hash key is the
#       concatenation of the subfont suffix, a space, and the index.
#   $3: Reference to a target array which holds the subfont suffixes.

sub read_sfdfile {
  my ($sfdfile, $sfdhash, $sfdarray) = @_;

  print("Reading subfont definition file \`$sfdfile'...\n");

  open(SFD, $sfdfile)
  || die("$prog: can't open \`$sfdfile': $!\n");

  # This loop doesn't handle the complete syntax of SFD files yet.
  while (<SFD>) {
    chop;
    my @field = split(" ");
    next if ($#field < 0);
    next if ($field[0] =~ /^#/);

    my $suffix = $field[0];
    push(@{$sfdarray}, $suffix);

    shift(@field);
    my $index = 0;

    while (@field) {
      if ($field[0] =~ /(.*):$/) {
        $index = $1;
      }
      elsif ($field[0] =~ /(0x[0-9A-Fa-f]+)_(0x[0-9A-Fa-f]+)/) {
        foreach my $i (hex($1) .. hex($2)) {
          $sfdhash->{"$suffix $index"} = $i;
          $index++;
        }
      }
      shift(@field);
    }
  }
  close(SFD);
}


# Read encoding file.
#
#   $1: Name of the encoding file.
#   $2: Reference to the target hash file, mapping from the charset
#       to Unicode.
#   $3: Set to 1 if the needed mapping data is not in field 1 and 2, but in
#       field 2 and 3.

sub read_encfile {
  my ($encfile, $enchash, $doshift) = @_;

  print("Reading encoding file \`$encfile'...\n");

  open(ENC, $encfile)
  || die("$prog: can't open \`$encfile': $!\n");

  while (<ENC>) {
    chop;
    my @field = split(" ");
    next if ($#field < 0);
    next if ($field[0] =~ /^#/);

    if ($doshift) {
      shift(@field);
    }

    my $unicode = $field[1];
    $unicode =~ s/0x//;
    my $value = hex($field[0]) + 0x8080;
    $enchash->{$value} = hex($unicode);
  }
  close(ENC);
}


# Read AFM file.
#
#   $1: Name of the AFM file.
#   $2: Reference to the target array which maps from Unicode to the string
#       "<subfont name> <subfont index> <width> <height> <depth>".
#   $3: Reference to the SFD hash (as extracted by `read_sfdfile').
#   $4: Reference to the encoding hash (as extracted by `read_encfile').
#   $5: Suffix.

sub read_afmfile {
  my ($afmfile, $unicarray, $sfdhash, $enchash, $suffix) = @_;

  print("Reading metric file \`$afmfile'...\n");

  open(AFM, $afmfile)
  || die("$prog: can't open \`$afmfile': $!\n");

  $afmfile =~ s/\.[^.]*$//;
  while (<AFM>) {
    if (/^C (\d+) ;/) {
      my $key = "$suffix $1";
      my $value = $sfdhash->{$key};
      my $unicvalue = $enchash->{$value};
      my $s = "$afmfile $1";

      # Add advance width.
      / WX (.*?) ;/;
      $s .= " $1";

      # Add glyph height and depth.
      / B .*? (.*?) .*? (.*?) ;/;
      $s .= " $1 $2";

      $unicarray->[$unicvalue] = $s;
    }
  }
  close(AFM);
}


# Write VPL file.
#
#   $1: Name of the VPL file.
#   $2: Reference to list which holds the font entries.  An entry has the
#       form `<idx> <subfont> <subfont_idx> <adv_width> <height> <depth>'.

sub write_vplfile {
  my ($vplfile, $glypharray) = @_;

  my %subfonts;
  my $subcount = 0;

  foreach my $entry (@{$glypharray}) {
    my @field = split(" ", $entry);
    my $subfont = $field[1];
    if (!defined ($subfonts{$subfont})) {
      $subfonts{$subfont} = $subcount;
      $subcount++;
    }
  }

  print("Writing virtual property list file \`$vplfile'...\n");

  open(VPL, ">", $vplfile)
  || die("$prog: can't open \`$vplfile': $!\n");
  my $oldfh = select(VPL);

  print("(VTITLE Created by \`$prog " . join(" ", @args) . "')\n");
  print("(FAMILY TEX-\U$uninamestem\E)\n");
  print("(CODINGSCHEME DNPUNICODE)\n");
  print("(FONTDIMEN\n");
  print("   (SPACE R 0.5)\n");
  print("   (XHEIGHT R 0.4)\n");
  print("   (QUAD R 1)\n");
  print("   )\n");

  foreach my $subfont
             (sort { $subfonts{$a} <=> $subfonts{$b} } keys %subfonts) {
    print("(MAPFONT D $subfonts{$subfont}\n");
    print("   (FONTNAME $subfont)\n");
    print("   )\n");
  }

  foreach my $entry (@{$glypharray}) {
    my @field = split(" ", $entry);
    my $index = $field[0];
    my $subnumber = $subfonts{$field[1]};
    my $subindex = $field[2];
    my $adv_width = $field[3] / 1000.0;
    my $depth = $field[4] / -1000.0;
    my $height = $field[5] / 1000.0;

    print("(CHARACTER D $index\n");
    print("   (CHARWD R $adv_width)\n");
    print("   (CHARHT R $height)\n");
    print("   (CHARDP R $depth)\n");
    print("   (MAP\n");
    print("      (SELECTFONT D $subnumber)\n");
    print("      (SETCHAR D $subindex)\n");
    print("      )\n");
    print("   )\n");
  }

  close(VPL);
  select($oldfh);
}


# eof