xref: /openbsd-src/gnu/usr.bin/perl/t/op/lc.t (revision d13be5d47e4149db2549a9828e244d59dbc43f15) 
1#!./perl
2
3BEGIN {
4    chdir 't';
5    @INC = '../lib';
6    require './test.pl';
7}
8
9plan tests => 93;
10
11is(lc(undef),	   "", "lc(undef) is ''");
12is(lcfirst(undef), "", "lcfirst(undef) is ''");
13is(uc(undef),	   "", "uc(undef) is ''");
14is(ucfirst(undef), "", "ucfirst(undef) is ''");
15
16$a = "HELLO.* world";
17$b = "hello.* WORLD";
18
19is("\Q$a\E."      , "HELLO\\.\\*\\ world.", '\Q\E HELLO.* world');
20is("\u$a"         , "HELLO\.\* world",      '\u');
21is("\l$a"         , "hELLO\.\* world",      '\l');
22is("\U$a"         , "HELLO\.\* WORLD",      '\U');
23is("\L$a"         , "hello\.\* world",      '\L');
24
25is(quotemeta($a)  , "HELLO\\.\\*\\ world",  'quotemeta');
26is(ucfirst($a)    , "HELLO\.\* world",      'ucfirst');
27is(lcfirst($a)    , "hELLO\.\* world",      'lcfirst');
28is(uc($a)         , "HELLO\.\* WORLD",      'uc');
29is(lc($a)         , "hello\.\* world",      'lc');
30
31is("\Q$b\E."      , "hello\\.\\*\\ WORLD.", '\Q\E hello.* WORLD');
32is("\u$b"         , "Hello\.\* WORLD",      '\u');
33is("\l$b"         , "hello\.\* WORLD",      '\l');
34is("\U$b"         , "HELLO\.\* WORLD",      '\U');
35is("\L$b"         , "hello\.\* world",      '\L');
36
37is(quotemeta($b)  , "hello\\.\\*\\ WORLD",  'quotemeta');
38is(ucfirst($b)    , "Hello\.\* WORLD",      'ucfirst');
39is(lcfirst($b)    , "hello\.\* WORLD",      'lcfirst');
40is(uc($b)         , "HELLO\.\* WORLD",      'uc');
41is(lc($b)         , "hello\.\* world",      'lc');
42
43# \x{100} is LATIN CAPITAL LETTER A WITH MACRON; its bijective lowercase is
44# \x{101}, LATIN SMALL LETTER A WITH MACRON.
45
46$a = "\x{100}\x{101}Aa";
47$b = "\x{101}\x{100}aA";
48
49is("\Q$a\E."      , "\x{100}\x{101}Aa.", '\Q\E \x{100}\x{101}Aa');
50is("\u$a"         , "\x{100}\x{101}Aa",  '\u');
51is("\l$a"         , "\x{101}\x{101}Aa",  '\l');
52is("\U$a"         , "\x{100}\x{100}AA",  '\U');
53is("\L$a"         , "\x{101}\x{101}aa",  '\L');
54
55is(quotemeta($a)  , "\x{100}\x{101}Aa",  'quotemeta');
56is(ucfirst($a)    , "\x{100}\x{101}Aa",  'ucfirst');
57is(lcfirst($a)    , "\x{101}\x{101}Aa",  'lcfirst');
58is(uc($a)         , "\x{100}\x{100}AA",  'uc');
59is(lc($a)         , "\x{101}\x{101}aa",  'lc');
60
61is("\Q$b\E."      , "\x{101}\x{100}aA.", '\Q\E \x{101}\x{100}aA');
62is("\u$b"         , "\x{100}\x{100}aA",  '\u');
63is("\l$b"         , "\x{101}\x{100}aA",  '\l');
64is("\U$b"         , "\x{100}\x{100}AA",  '\U');
65is("\L$b"         , "\x{101}\x{101}aa",  '\L');
66
67is(quotemeta($b)  , "\x{101}\x{100}aA",  'quotemeta');
68is(ucfirst($b)    , "\x{100}\x{100}aA",  'ucfirst');
69is(lcfirst($b)    , "\x{101}\x{100}aA",  'lcfirst');
70is(uc($b)         , "\x{100}\x{100}AA",  'uc');
71is(lc($b)         , "\x{101}\x{101}aa",  'lc');
72
73# \x{DF} is LATIN SMALL LETTER SHARP S, its uppercase is SS or \x{53}\x{53};
74# \x{149} is LATIN SMALL LETTER N PRECEDED BY APOSTROPHE, its uppercase is
75# \x{2BC}\x{E4} or MODIFIER LETTER APOSTROPHE and N.
76
77# In EBCDIC \x{DF} is LATIN SMALL LETTER Y WITH DIAERESIS,
78# and it's uppercase is \x{178}, LATIN CAPITAL LETTER Y WITH DIAERESIS.
79
80if (ord("A") == 193) { # EBCDIC
81    is("\U\x{DF}aB\x{149}cD" , "\x{178}AB\x{2BC}NCD",
82       "multicharacter uppercase");
83} elsif (ord("A") == 65) {
84    is("\U\x{DF}aB\x{149}cD" , "SSAB\x{2BC}NCD",
85       "multicharacter uppercase");
86} else {
87    fail("what is your encoding?");
88}
89
90# The \x{DF} is its own lowercase, ditto for \x{149}.
91# There are no single character -> multiple characters lowercase mappings.
92
93if (ord("A") == 193) { # EBCDIC
94    is("\LaB\x{149}cD" , "ab\x{149}cd",
95       "multicharacter lowercase");
96} elsif (ord("A") == 65) {
97    is("\L\x{DF}aB\x{149}cD" , "\x{DF}ab\x{149}cd",
98       "multicharacter lowercase");
99} else {
100    fail("what is your encoding?");
101}
102
103# titlecase is used for \u / ucfirst.
104
105# \x{587} is ARMENIAN SMALL LIGATURE ECH YIWN and its titlecase is
106# \x{535}\x{582} ARMENIAN CAPITAL LETTER ECH + ARMENIAN SMALL LETTER YIWN
107# while its lowercase is
108# \x{587} itself
109# and its uppercase is
110# \x{535}\x{552} ARMENIAN CAPITAL LETTER ECH + ARMENIAN CAPITAL LETTER YIWN
111
112$a = "\x{587}";
113
114is("\L\x{587}" , "\x{587}",        "ligature lowercase");
115is("\u\x{587}" , "\x{535}\x{582}", "ligature titlecase");
116is("\U\x{587}" , "\x{535}\x{552}", "ligature uppercase");
117
118# mktables had problems where many-to-one case mappings didn't work right.
119# The lib/uni/fold.t should give the fourth folding, "casefolding", a good
120# workout (one cannot directly get that from Perl).
121# \x{01C4} is LATIN CAPITAL LETTER DZ WITH CARON
122# \x{01C5} is LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
123# \x{01C6} is LATIN SMALL LETTER DZ WITH CARON
124# \x{03A3} is GREEK CAPITAL LETTER SIGMA
125# \x{03C2} is GREEK SMALL LETTER FINAL SIGMA
126# \x{03C3} is GREEK SMALL LETTER SIGMA
127
128is(lc("\x{1C4}") , "\x{1C6}",      "U+01C4 lc is U+01C6");
129is(lc("\x{1C5}") , "\x{1C6}",      "U+01C5 lc is U+01C6, too");
130
131is(ucfirst("\x{3C2}") , "\x{3A3}", "U+03C2 ucfirst is U+03A3");
132is(ucfirst("\x{3C3}") , "\x{3A3}", "U+03C3 ucfirst is U+03A3, too");
133
134is(uc("\x{1C5}") , "\x{1C4}",      "U+01C5 uc is U+01C4");
135is(uc("\x{1C6}") , "\x{1C4}",      "U+01C6 uc is U+01C4, too");
136
137# #18107: A host of bugs involving [ul]c{,first}. AMS 20021106
138$a = "\x{3c3}foo.bar"; # \x{3c3} == GREEK SMALL LETTER SIGMA.
139$b = "\x{3a3}FOO.BAR"; # \x{3a3} == GREEK CAPITAL LETTER SIGMA.
140
141($c = $b) =~ s/(\w+)/lc($1)/ge;
142is($c , $a, "Using s///e to change case.");
143
144($c = $a) =~ s/(\p{IsWord}+)/uc($1)/ge;
145is($c , $b, "Using s///e to change case.");
146
147($c = $b) =~ s/(\p{IsWord}+)/lcfirst($1)/ge;
148is($c , "\x{3c3}FOO.bAR", "Using s///e to change case.");
149
150($c = $a) =~ s/(\p{IsWord}+)/ucfirst($1)/ge;
151is($c , "\x{3a3}foo.Bar", "Using s///e to change case.");
152
153# #18931: perl5.8.0 bug in \U..\E processing
154# Test case from Nicholas Clark.
155for my $a (0,1) {
156    $_ = 'abcdefgh';
157    $_ .= chr 256;
158    chop;
159    /(.*)/;
160    is(uc($1), "ABCDEFGH", "[perl #18931]");
161}
162
163{
164    foreach (0, 1) {
165	$a = v10.v257;
166	chop $a;
167	$a =~ s/^(\s*)(\w*)/$1\u$2/;
168	is($a, v10, "[perl #18857]");
169    }
170}
171
172
173# [perl #38619] Bug in lc and uc (interaction between UTF-8, substr, and lc/uc)
174
175for ("a\x{100}", "xyz\x{100}") {
176    is(substr(uc($_), 0), uc($_), "[perl #38619] uc");
177}
178for ("A\x{100}", "XYZ\x{100}") {
179    is(substr(lc($_), 0), lc($_), "[perl #38619] lc");
180}
181for ("a\x{100}", "�yz\x{100}") { # � to Ss (different length)
182    is(substr(ucfirst($_), 0), ucfirst($_), "[perl #38619] ucfirst");
183}
184
185# Related to [perl #38619]
186# the original report concerns PERL_MAGIC_utf8.
187# these cases concern PERL_MAGIC_regex_global.
188
189for (map { $_ } "a\x{100}", "abc\x{100}", "\x{100}") {
190    chop; # get ("a", "abc", "") in utf8
191    my $return =  uc($_) =~ /\G(.?)/g;
192    my $result = $return ? $1 : "not";
193    my $expect = (uc($_) =~ /(.?)/g)[0];
194    is($return, 1,       "[perl #38619]");
195    is($result, $expect, "[perl #38619]");
196}
197
198for (map { $_ } "A\x{100}", "ABC\x{100}", "\x{100}") {
199    chop; # get ("A", "ABC", "") in utf8
200    my $return =  lc($_) =~ /\G(.?)/g;
201    my $result = $return ? $1 : "not";
202    my $expect = (lc($_) =~ /(.?)/g)[0];
203    is($return, 1,       "[perl #38619]");
204    is($result, $expect, "[perl #38619]");
205}
206
207for (1, 4, 9, 16, 25) {
208    is(uc "\x{03B0}" x $_, "\x{3a5}\x{308}\x{301}" x $_,
209       'uc U+03B0 grows threefold');
210
211    is(lc "\x{0130}" x $_, "i\x{307}" x $_, 'lc U+0130 grows');
212}
213
214# bug #43207
215my $temp = "Hello";
216for ("$temp") {
217    lc $_;
218    is($_, "Hello");
219}
220
221# new in Unicode 5.1.0
222is(lc("\x{1E9E}"), "\x{df}", "lc(LATIN CAPITAL LETTER SHARP S)");
223