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
|
use warnings;
use strict;
BEGIN {
chdir 't' if -d 't';
@INC = '../lib';
require './test.pl';
}
plan(20736); # Determined by experimentation
# In this section, test the upper/lower/title case mappings for all characters
# 0-255.
# First compute the case mappings without resorting to the functions we're
# testing.
# Initialize the arrays so each $i maps to itself.
my @posix_to_upper;
for my $i (0 .. 255) {
$posix_to_upper[$i] = chr($i);
}
my @posix_to_lower
= my @posix_to_title
= my @latin1_to_upper
= my @latin1_to_lower
= my @latin1_to_title
= @posix_to_upper;
# Override the elements in the to_lower arrays that have different standard
# lower case mappings. (standard meaning they are 32 numbers apart)
for my $i (0x41 .. 0x5A, 0xC0 .. 0xD6, 0xD8 .. 0xDE) {
my $upper_ord = utf8::unicode_to_native $i;
my $lower_ord = utf8::unicode_to_native($i + 32);
$latin1_to_lower[$upper_ord] = chr($lower_ord);
next if $i > 127;
$posix_to_lower[$upper_ord] = chr($lower_ord);
}
# Same for upper and title
for my $i (0x61 .. 0x7A, 0xE0 .. 0xF6, 0xF8 .. 0xFE) {
my $lower_ord = utf8::unicode_to_native $i;
my $upper_ord = utf8::unicode_to_native($i - 32);
$latin1_to_upper[$lower_ord] = chr($upper_ord);
$latin1_to_title[$lower_ord] = chr($upper_ord);
next if $i > 127;
$posix_to_upper[$lower_ord] = chr($upper_ord);
$posix_to_title[$lower_ord] = chr($upper_ord);
}
# Override the abnormal cases.
$latin1_to_upper[utf8::unicode_to_native 0xB5] = chr(0x39C);
$latin1_to_title[utf8::unicode_to_native 0xB5] = chr(0x39C);
$latin1_to_upper[utf8::unicode_to_native 0xDF] = 'SS';
$latin1_to_title[utf8::unicode_to_native 0xDF] = 'Ss';
$latin1_to_upper[utf8::unicode_to_native 0xFF] = chr(0x178);
$latin1_to_title[utf8::unicode_to_native 0xFF] = chr(0x178);
my $repeat = 25; # Length to make strings.
# Create hashes of strings in several ranges, both for uc and lc.
my %posix;
$posix{'uc'} = 'A' x $repeat;
$posix{'lc'} = 'a' x $repeat ;
my %cyrillic;
$cyrillic{'uc'} = chr(0x42F) x $repeat;
$cyrillic{'lc'} = chr(0x44F) x $repeat;
my %latin1;
$latin1{'uc'} = chr(utf8::unicode_to_native 0xD8) x $repeat;
$latin1{'lc'} = chr(utf8::unicode_to_native 0xF8) x $repeat;
my %empty;
$empty{'lc'} = $empty{'uc'} = "";
# Loop so prefix each character being tested with nothing, and the various
# strings; then loop for suffixes of those strings as well.
for my $prefix (\%empty, \%posix, \%cyrillic, \%latin1) {
for my $suffix (\%empty, \%posix, \%cyrillic, \%latin1) {
for my $i (0 .. 255) { # For each possible posix or latin1 character
my $cp = sprintf "U+%04X", $i;
# First try using latin1 (Unicode) semantics.
use feature "unicode_strings";
my $phrase = 'in uni8bit';
my $char = chr($i);
my $pre_lc = $prefix->{'lc'};
my $pre_uc = $prefix->{'uc'};
my $post_lc = $suffix->{'lc'};
my $post_uc = $suffix->{'uc'};
my $to_upper = $pre_lc . $char . $post_lc;
my $expected_upper = $pre_uc . $latin1_to_upper[$i] . $post_uc;
my $to_lower = $pre_uc . $char . $post_uc;
my $expected_lower = $pre_lc . $latin1_to_lower[$i] . $post_lc;
is (uc($to_upper), $expected_upper,
display("$cp: $phrase: Verify uc($to_upper) eq $expected_upper"));
is (lc($to_lower), $expected_lower,
display("$cp: $phrase: Verify lc($to_lower) eq $expected_lower"));
if ($pre_uc eq "") { # Title case if null prefix.
my $expected_title = $latin1_to_title[$i] . $post_lc;
is (ucfirst($to_upper), $expected_title,
display("$cp: $phrase: Verify ucfirst($to_upper) eq $expected_title"));
my $expected_lcfirst = $latin1_to_lower[$i] . $post_uc;
is (lcfirst($to_lower), $expected_lcfirst,
display("$cp: $phrase: Verify lcfirst($to_lower) eq $expected_lcfirst"));
}
# Then try with posix semantics.
no feature "unicode_strings";
$phrase = 'no uni8bit';
# These don't contribute anything in this case.
next if $suffix == \%cyrillic;
next if $suffix == \%latin1;
next if $prefix == \%cyrillic;
next if $prefix == \%latin1;
$expected_upper = $pre_uc . $posix_to_upper[$i] . $post_uc;
$expected_lower = $pre_lc . $posix_to_lower[$i] . $post_lc;
is (uc($to_upper), $expected_upper,
display("$cp: $phrase: Verify uc($to_upper) eq $expected_upper"));
is (lc($to_lower), $expected_lower,
display("$cp: $phrase: Verify lc($to_lower) eq $expected_lower"));
if ($pre_uc eq "") {
my $expected_title = $posix_to_title[$i] . $post_lc;
is (ucfirst($to_upper), $expected_title,
display("$cp: $phrase: Verify ucfirst($to_upper) eq $expected_title"));
my $expected_lcfirst = $posix_to_lower[$i] . $post_uc;
is (lcfirst($to_lower), $expected_lcfirst,
display("$cp: $phrase: Verify lcfirst($to_lower) eq $expected_lcfirst"));
}
}
}
}
# In this section test that \w, \s, and \b (and complements) work correctly.
# These are the only character classes affected by this pragma. Above ASCII
# range Latin-1 characters are in \w and \s iff the pragma is on.
# Construct the expected full Latin1 values without using anything we're
# testing. All these were determined manually by looking in the manual.
# Boolean: is w[$i] a \w character?
my @w = (0) x 256;
for my $i ( 0x30 .. 0x39, # 0-9
0x41 .. 0x5a, # A-Z
0x61 .. 0x7a, # a-z
0x5F, # _
0xAA, # FEMININE ORDINAL INDICATOR
0xB5, # MICRO SIGN
0xBA, # MASCULINE ORDINAL INDICATOR
0xC0 .. 0xD6, # various
0xD8 .. 0xF6, # various
0xF8 .. 0xFF, # various
)
{
$w[utf8::unicode_to_native $i] = 1;
}
# Boolean: is s[$i] a \s character?
my @s = (0) x 256;
$s[utf8::unicode_to_native 0x09] = 1; # Tab
$s[utf8::unicode_to_native 0x0A] = 1; # LF
$s[utf8::unicode_to_native 0x0B] = 1; # VT
$s[utf8::unicode_to_native 0x0C] = 1; # FF
$s[utf8::unicode_to_native 0x0D] = 1; # CR
$s[utf8::unicode_to_native 0x20] = 1; # SPACE
$s[utf8::unicode_to_native 0x85] = 1; # NEL
$s[utf8::unicode_to_native 0xA0] = 1; # NO BREAK SPACE
for my $i (0 .. 255) {
my $char = chr($i);
my $hex_i = sprintf "%02X", $i;
foreach my $which (\@s, \@w) {
my $basic_name;
if ($which == \@s) {
$basic_name = 's';
} else {
$basic_name = 'w'
}
# Test \w \W \s \S
foreach my $complement (0, 1) {
my $name = '\\' . (($complement) ? uc($basic_name) : $basic_name);
# in and out of [...]
foreach my $charclass (0, 1) {
# And like [^...] or just plain [...]
foreach my $complement_class (0, 1) {
next if ! $charclass && $complement_class;
# Start with the boolean as to if the character is in the
# class, and then complement as needed.
my $expect_success = $which->[$i];
$expect_success = ! $expect_success if $complement;
$expect_success = ! $expect_success if $complement_class;
my $test = $name;
$test = "^$test" if $complement_class;
$test = "[$test]" if $charclass;
$test = "^$test\$";
use feature 'unicode_strings';
my $prefix = "in uni8bit; Verify chr(0x$hex_i)";
if ($expect_success) {
like($char, qr/$test/, display("$prefix =~ qr/$test/"));
} else {
unlike($char, qr/$test/, display("$prefix !~ qr/$test/"));
}
no feature 'unicode_strings';
$prefix = "no uni8bit; Verify chr(0x$hex_i)";
# With the legacy, nothing above 128 should be in the
# class
if (utf8::native_to_unicode($i) >= 128) {
$expect_success = 0;
$expect_success = ! $expect_success if $complement;
$expect_success = ! $expect_success if $complement_class;
}
if ($expect_success) {
like($char, qr/$test/, display("$prefix =~ qr/$test/"));
} else {
unlike($char, qr/$test/, display("$prefix !~ qr/$test/"));
}
}
}
}
}
# Similarly for \b and \B.
foreach my $complement (0, 1) {
my $name = '\\' . (($complement) ? 'B' : 'b');
my $expect_success = ! $w[$i]; # \b is complement of \w
$expect_success = ! $expect_success if $complement;
my $string = "a$char";
my $test = "(^a$name\\x{$hex_i}\$)";
use feature 'unicode_strings';
my $prefix = "in uni8bit; Verify $string";
if ($expect_success) {
like($string, qr/$test/, display("$prefix =~ qr/$test/"));
} else {
unlike($string, qr/$test/, display("$prefix !~ qr/$test/"));
}
no feature 'unicode_strings';
$prefix = "no uni8bit; Verify $string";
if (utf8::native_to_unicode($i) >= 128) {
$expect_success = 1;
$expect_success = ! $expect_success if $complement;
}
if ($expect_success) {
like($string, qr/$test/, display("$prefix =~ qr/$test/"));
like($string, qr/$test/, display("$prefix =~ qr/$test/"));
} else {
unlike($string, qr/$test/, display("$prefix !~ qr/$test/"));
}
}
}
|
