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
|
# Copyright 2000-2004 Double Precision, Inc.
# See COPYING for distribution information.
#
#
# Generate unicode upper/lower/titlecase translations.
print '/*
** Copyright 2000-2004 Double Precision, Inc.
** See COPYING for distribution information.
**
*/
#include "courier-unicode.h"
';
my $set=shift;
open (U, "UnicodeData.txt") || die "$!\n";
while (<U>)
{
chomp;
my @fields= split /;/;
my ($code, $uc, $lc, $tc);
$code="0x$fields[0]";
eval "\$code=$code;";
$uc=$fields[12];
if ($uc ne "")
{
eval "\$uc=0x$uc;";
$UC{$code}=$uc;
$FLAG{$code}=1;
}
$lc=$fields[13];
if ($lc ne "")
{
eval "\$lc=0x$lc;";
$LC{$code}=$lc;
$FLAG{$code}=1;
}
$tc=$fields[14];
if ($tc ne "")
{
eval "\$tc=0x$tc;";
$TC{$code}=$tc;
$FLAG{$code}=1;
}
}
close(U);
my $tabsize=2048;
grep ($bucket[ $_ % $tabsize ] .= "$_\n", sort keys %FLAG);
my $maxcnt=0;
for ($i=0; $i < $tabsize; $i++)
{
my $cnt=0;
grep ( ++$cnt, split (/\n/, $bucket[$i]));
$maxcnt=$cnt if $cnt > $maxcnt;
}
print "const unsigned unicode_case_hash=$tabsize;\n";
print "/* unicode_case_maxbucket="
. ($maxcnt+2) . "*/\n";
print "const char32_t unicode_case_tab[][4]={\n";
my $idx=0;
for ($i=0; $i<$tabsize; $i++)
{
$offset[$i]=$idx;
grep {
my $j=$_;
my $u=$UC{$j}+0;
my $l=$LC{$j}+0;
my $t=$TC{$j}+0;
if ($u || $l || $t)
{
$u=$j unless $u;
$l=$j unless $l;
$t=$u unless $t;
printf("{0x%04x,0x%04x,0x%04x,0x%04x},",$j,$u,$l,$t);
print "\n" if ($idx % 4) == 3;
++$idx;
}
} sort split(/\n/, $bucket[$i]);
}
print "{0,0,0,0}};
const unsigned unicode_case_offset[$tabsize]={
";
for ($i=0; $i<$tabsize;$i++)
{
printf("%4d", $offset[$i]);
print "," if $i < $tabsize-1;
print "\n" if ($i % 16) == 15;
}
print "};\n";
|
