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
|
#!./perl
BEGIN {
unless(grep /blib/, @INC) {
chdir 't' if -d 't';
@INC = '../lib';
}
}
$| = 1;
print "1..25\n";
use charnames ':full';
print "not " unless "Here\N{EXCLAMATION MARK}?" eq "Here!?";
print "ok 1\n";
{
use bytes; # TEST -utf8 can switch utf8 on
print "# \$res=$res \$\@='$@'\nnot "
if $res = eval <<'EOE'
use charnames ":full";
"Here: \N{CYRILLIC SMALL LETTER BE}!";
1
EOE
or $@ !~ /above 0xFF/;
print "ok 2\n";
# print "# \$res=$res \$\@='$@'\n";
print "# \$res=$res \$\@='$@'\nnot "
if $res = eval <<'EOE'
use charnames 'cyrillic';
"Here: \N{Be}!";
1
EOE
or $@ !~ /CYRILLIC CAPITAL LETTER BE.*above 0xFF/;
print "ok 3\n";
}
# If octal representation of unicode char is \0xyzt, then the utf8 is \3xy\2zt
if (ord('A') == 65) { # as on ASCII or UTF-8 machines
$encoded_be = "\320\261";
$encoded_alpha = "\316\261";
$encoded_bet = "\327\221";
$encoded_deseng = "\360\220\221\215";
}
else { # EBCDIC where UTF-EBCDIC may be used (this may be 1047 specific since
# UTF-EBCDIC is codepage specific)
$encoded_be = "\270\102\130";
$encoded_alpha = "\264\130";
$encoded_bet = "\270\125\130";
$encoded_deseng = "\336\102\103\124";
}
sub to_bytes {
pack"a*", shift;
}
{
use charnames ':full';
print "not " unless to_bytes("\N{CYRILLIC SMALL LETTER BE}") eq $encoded_be;
print "ok 4\n";
use charnames qw(cyrillic greek :short);
print "not " unless to_bytes("\N{be},\N{alpha},\N{hebrew:bet}")
eq "$encoded_be,$encoded_alpha,$encoded_bet";
print "ok 5\n";
}
{
use charnames ':full';
print "not " unless "\x{263a}" eq "\N{WHITE SMILING FACE}";
print "ok 6\n";
print "not " unless length("\x{263a}") == 1;
print "ok 7\n";
print "not " unless length("\N{WHITE SMILING FACE}") == 1;
print "ok 8\n";
print "not " unless sprintf("%vx", "\x{263a}") eq "263a";
print "ok 9\n";
print "not " unless sprintf("%vx", "\N{WHITE SMILING FACE}") eq "263a";
print "ok 10\n";
print "not " unless sprintf("%vx", "\xFF\N{WHITE SMILING FACE}") eq "ff.263a";
print "ok 11\n";
print "not " unless sprintf("%vx", "\x{ff}\N{WHITE SMILING FACE}") eq "ff.263a";
print "ok 12\n";
}
{
use charnames qw(:full);
use utf8;
my $x = "\x{221b}";
my $named = "\N{CUBE ROOT}";
print "not " unless ord($x) == ord($named);
print "ok 13\n";
}
{
use charnames qw(:full);
use utf8;
print "not " unless "\x{100}\N{CENT SIGN}" eq "\x{100}"."\N{CENT SIGN}";
print "ok 14\n";
}
{
use charnames ':full';
print "not "
unless to_bytes("\N{DESERET SMALL LETTER ENG}") eq $encoded_deseng;
print "ok 15\n";
}
{
# 20001114.001
no utf8; # naked Latin-1
if (ord("Ä") == 0xc4) { # Try to do this only on Latin-1.
use charnames ':full';
my $text = "\N{LATIN CAPITAL LETTER A WITH DIAERESIS}";
print "not " unless $text eq "\xc4" && ord($text) == 0xc4;
print "ok 16\n";
} else {
print "ok 16 # Skip: not Latin-1\n";
}
}
{
print "not " unless charnames::viacode(0x1234) eq "ETHIOPIC SYLLABLE SEE";
print "ok 17\n";
print "not " if defined charnames::viacode(0x0590); # unused Hebrew
print "ok 18\n";
}
{
print "not " unless
sprintf "%04X\n", charnames::vianame("GOTHIC LETTER AHSA") eq "10330";
print "ok 19\n";
print "not " if
defined charnames::vianame("NONE SUCH");
print "ok 20\n";
}
{
# check that caching at least hasn't broken anything
print "not " unless charnames::viacode(0x1234) eq "ETHIOPIC SYLLABLE SEE";
print "ok 21\n";
print "not " unless
sprintf "%04X\n", charnames::vianame("GOTHIC LETTER AHSA") eq "10330";
print "ok 22\n";
}
print "not " unless "\N{HORIZONTAL TABULATION}" eq "\t";
print "ok 23\n";
print "not " unless "\N{ESCAPE}" eq "\e";
print "ok 24\n";
print "not " unless "\N{NULL}" eq "\c@";
print "ok 25\n";
# TODO: when Unicode 3.2 comes along some names will change
# HORIZONTAL TABULATION -> CHARACTER TABULATION (since ISO 6429
# has been updated), and some names will have shorter aliases
# LINEFEED (LF). Update the tests, and also update the charnames
# pragma to support the 3.1 names, and the shorter aliases.
|
