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
|
#! /bin/sh
#
# make-afmtodit-tables -- script for creating the 'unicode_decomposed'
# and 'AGL_to_unicode' tables
#
# Copyright (C) 2005-2020 Free Software Foundation, Inc.
# Written by Werner Lemberg <wl@gnu.org>
#
# This file is part of groff.
#
# groff 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 3 of the License, or
# (at your option) any later version.
#
# groff 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, see <http://www.gnu.org/licenses/>.
#
# usage:
#
# make-afmtodit-tables \
# UnicodeData.txt version-string glyphlist.txt > afmtodit.in
#
# 'UnicodeData.txt' is the central database file from the Unicode
# standard. Unfortunately, it doesn't contain a version number, which
# must be thus provided manually as an additional parameter.
#
# 'glyphlist.txt' holds the Adobe Glyph List (AGL).
#
# This program needs a C preprocessor.
#
if [ $# -ne 3 ]
then
echo "usage: $0 UnicodeData.txt UNICODE-VERSION-STRING" \
"glyphlist.txt > afmtodit.tables"
exit 2
fi
unicode_data="$1"
unicode_version="$2"
glyph_list="$3"
for f in "$1" "$3"
do
if ! [ -r "$f" ]
then
echo "$0: '$f' does not exist or is not readable" >&2
exit 1
fi
done
# Handle UnicodeData.txt.
#
# Remove ranges and control characters,
# then extract the decomposition field,
# then remove lines without decomposition,
# then remove all compatibility decompositions.
cat "$1" \
| sed -e '/^[^;]*;</d' \
| sed -e 's/;[^;]*;[^;]*;[^;]*;[^;]*;\([^;]*\);.*$/;\1/' \
| sed -e '/^[^;]*;$/d' \
| sed -e '/^[^;]*;</d' > $$1
# Prepare input for running cpp.
cat $$1 \
| sed -e 's/^\([^;]*\);/#define \1 /' \
-e 's/ / u/g' > $$2
cat $$1 \
| sed -e 's/^\([^;]*\);.*$/\1 u\1/' >> $$2
# Run C preprocessor to recursively decompose.
"${CPP:-cpp}" $$2 $$3
# Convert it back to original format.
cat $$3 \
| sed -e '/#/d' \
-e '/^$/d' \
-e 's/ \+/ /g' \
-e 's/ *$//' \
-e 's/u//g' \
-e 's/^\([^ ]*\) /\1;/' > $$4
# Write comment.
cat <<END
# This table was algorithmically derived from the file 'UnicodeData.txt'
# for Unicode $unicode_version, available from unicode.org,
# on `date '+%Y-%m-%d'`.
END
# Emit first table.
echo 'my %unicode_decomposed = ('
cat $$4 \
| sed -e 's/ /_/g' \
-e 's/\(.*\);\(.*\)/ "\1", "\2",/'
echo ');'
echo ''
# Write comment.
cat <<END
# This table was algorithmically derived from the Adobe Glyph List (AGL)
# file 'glyphlist.txt' from the GitHub Adobe Type Tools agl-aglfn
# project, on `date '+%Y-%m-%d'`.
#
# See "groff:" comments for altered mappings.
END
# Convert AGL syntax to a chunk of Perl.
cat "$3" \
| sed -e '/#/d' \
-e 's/ /_/g' \
-e '/;\(E\|F[0-8]\)/d' \
-e 's/\(.*\);\(.*\)/ "\1", "\2",/' > $$5
# Perform groff replacements.
sed \
-e 's/\("Delta"\), "2206",$/\1, "0394", # groff: not U+2206/' \
-e 's/\("Omega"\), "2126",$/\1, "03A9", # groff: not U+2126/' \
-e 's/\("mu"\), "00B5",$/\1, "03BC", # groff: not U+00B5/' \
< $$5 > $$6
# Emit second table.
echo 'my %AGL_to_unicode = ('
cat $$6
echo ');'
# Remove temporary files.
rm $$1 $$2 $$3 $$4 $$5 $$6
# Local Variables:
# fill-column: 72
# End:
# vim: set textwidth=72:
|
