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
|
#!/usr/bin/perl
#
# Process enum.list and output ucd.h as well as
# C code indicies for each enum.
#
sub close_frag($) {
my($longname) = @_;
print UCD_H "};\n\n";
print UCD_H "int unicode_property_names_\L${longname}\E(enum unicode_\L${longname}\E, const char **, const char **);\n\n";
print FRAG "};\n";
print FRAG <<EOF;
int
unicode_property_names_\L${longname}\E(enum unicode_\L${longname}\E v,
const char **longname,
const char **shortname)
{
const char *ln, *sn;
int rv;
if ( (unsigned)v >= sizeof enum_names/sizeof(struct libucd_enum_names) ) {
ln = NULL;
sn = NULL;
rv = 1;
} else {
ln = enum_names[v].long_name;
sn = enum_names[v].short_name;
rv = 0;
}
if ( longname ) *longname = ln;
if ( shortname ) *shortname = sn;
return rv;
}
EOF
close(FRAG);
}
open(LIST, '<', "enum.list") or die;
open(UCD_IN, '<', "ucd.h.in") or die;
open(UCD_H, '>', "ucd.h") or die;
mkdir("enums", 0777);
while ( defined($line = <UCD_IN>) ) {
last if ( $line =~ /ENUMS\;/ );
print UCD_H $line;
}
undef $shortname;
while( defined($line = <LIST>) ) {
chomp $line;
next if ( $line =~ /^\s*(\#\#.*|)$/ );
if ( $line =~ /^\#\s*(\S+)\s+\((\S+)\)\s+(long|short)\s*$/ ) {
$prev = $longname;
$longname = $1;
$shortname = $2;
$whichname = ($3 eq 'long') ? 1 : 0;
if ( defined($prev) ) {
close_frag($prev);
}
print UCD_H "enum unicode_\L${longname}\E {\n";
open(FRAG, '>', "enums/${longname}.c") or die;
print FRAG "#include \"libucd_int.h\"\n";
print FRAG "static const struct libucd_enum_names enum_names[] = {\n";
$seqpos = 0;
} elsif ( $line =~ /\;/ ) {
$line =~ s/\s*\#.*$//; # Remove comments
@list = split(/\s*;\s*/, $line);
if ( shift(@list) ne $shortname ) {
die "$0: Unexpected line: $line\n";
}
undef $epos;
if ( $list[0] =~ /^[0-9]+$/ ) {
$epos = shift(@list);
}
# Write ucd.h
# $na is the preferred name, $nx the alternate
($na = $list[$whichname]) =~ tr/-/_/;
($nx = $list[1-$whichname]) =~ tr/-/_/;
# If the Unicode Consortium defines a numeric value,
# use that, otherwise use the sequential order in enum.list.
# For that reason, enum.list should be maintained manually
# and entries may only be added to the end of lists.
$epos = defined($epos) ? $epos : $seqpos;
$seqpos++;
printf UCD_H " %s = %d,\n",
"UC_\U${shortname}\E_${na}", $epos;
if ($nx ne 'n/a' && $nx ne $na && $nx) {
printf UCD_H " %s = %d,\n",
"UC_\U${shortname}\E_${nx}", $epos;
}
# Write generator fragment
($ln = $list[1]) =~ tr/_/ /;
$sn = $list[0];
$sn = ($sn eq 'n/a') ? '0' : "\"$sn\"";
if ( defined($epos) ) {
printf FRAG "\t[%3d] = { \"%s\", %s },\n", $epos, $ln, $sn;
} else {
printf FRAG "\t{ \"%s\", %s },\n", $ln, $sn;
}
} else {
die "$0: Cannot parse: $line\n";
}
}
close_frag($longname);
while ( defined($line = <UCD_IN>) ) {
print UCD_H $line;
}
close(UCD_IN);
close(UCD_H);
|
