| 1 | #!./perl
|
|---|
| 2 |
|
|---|
| 3 | BEGIN {
|
|---|
| 4 | chdir 't';
|
|---|
| 5 | @INC = '../lib';
|
|---|
| 6 | require './test.pl';
|
|---|
| 7 | }
|
|---|
| 8 |
|
|---|
| 9 | plan tests => 59;
|
|---|
| 10 |
|
|---|
| 11 | $a = "HELLO.* world";
|
|---|
| 12 | $b = "hello.* WORLD";
|
|---|
| 13 |
|
|---|
| 14 | is("\Q$a\E." , "HELLO\\.\\*\\ world.", '\Q\E HELLO.* world');
|
|---|
| 15 | is("\u$a" , "HELLO\.\* world", '\u');
|
|---|
| 16 | is("\l$a" , "hELLO\.\* world", '\l');
|
|---|
| 17 | is("\U$a" , "HELLO\.\* WORLD", '\U');
|
|---|
| 18 | is("\L$a" , "hello\.\* world", '\L');
|
|---|
| 19 |
|
|---|
| 20 | is(quotemeta($a) , "HELLO\\.\\*\\ world", 'quotemeta');
|
|---|
| 21 | is(ucfirst($a) , "HELLO\.\* world", 'ucfirst');
|
|---|
| 22 | is(lcfirst($a) , "hELLO\.\* world", 'lcfirst');
|
|---|
| 23 | is(uc($a) , "HELLO\.\* WORLD", 'uc');
|
|---|
| 24 | is(lc($a) , "hello\.\* world", 'lc');
|
|---|
| 25 |
|
|---|
| 26 | is("\Q$b\E." , "hello\\.\\*\\ WORLD.", '\Q\E hello.* WORLD');
|
|---|
| 27 | is("\u$b" , "Hello\.\* WORLD", '\u');
|
|---|
| 28 | is("\l$b" , "hello\.\* WORLD", '\l');
|
|---|
| 29 | is("\U$b" , "HELLO\.\* WORLD", '\U');
|
|---|
| 30 | is("\L$b" , "hello\.\* world", '\L');
|
|---|
| 31 |
|
|---|
| 32 | is(quotemeta($b) , "hello\\.\\*\\ WORLD", 'quotemeta');
|
|---|
| 33 | is(ucfirst($b) , "Hello\.\* WORLD", 'ucfirst');
|
|---|
| 34 | is(lcfirst($b) , "hello\.\* WORLD", 'lcfirst');
|
|---|
| 35 | is(uc($b) , "HELLO\.\* WORLD", 'uc');
|
|---|
| 36 | is(lc($b) , "hello\.\* world", 'lc');
|
|---|
| 37 |
|
|---|
| 38 | # \x{100} is LATIN CAPITAL LETTER A WITH MACRON; its bijective lowercase is
|
|---|
| 39 | # \x{101}, LATIN SMALL LETTER A WITH MACRON.
|
|---|
| 40 |
|
|---|
| 41 | $a = "\x{100}\x{101}Aa";
|
|---|
| 42 | $b = "\x{101}\x{100}aA";
|
|---|
| 43 |
|
|---|
| 44 | is("\Q$a\E." , "\x{100}\x{101}Aa.", '\Q\E \x{100}\x{101}Aa');
|
|---|
| 45 | is("\u$a" , "\x{100}\x{101}Aa", '\u');
|
|---|
| 46 | is("\l$a" , "\x{101}\x{101}Aa", '\l');
|
|---|
| 47 | is("\U$a" , "\x{100}\x{100}AA", '\U');
|
|---|
| 48 | is("\L$a" , "\x{101}\x{101}aa", '\L');
|
|---|
| 49 |
|
|---|
| 50 | is(quotemeta($a) , "\x{100}\x{101}Aa", 'quotemeta');
|
|---|
| 51 | is(ucfirst($a) , "\x{100}\x{101}Aa", 'ucfirst');
|
|---|
| 52 | is(lcfirst($a) , "\x{101}\x{101}Aa", 'lcfirst');
|
|---|
| 53 | is(uc($a) , "\x{100}\x{100}AA", 'uc');
|
|---|
| 54 | is(lc($a) , "\x{101}\x{101}aa", 'lc');
|
|---|
| 55 |
|
|---|
| 56 | is("\Q$b\E." , "\x{101}\x{100}aA.", '\Q\E \x{101}\x{100}aA');
|
|---|
| 57 | is("\u$b" , "\x{100}\x{100}aA", '\u');
|
|---|
| 58 | is("\l$b" , "\x{101}\x{100}aA", '\l');
|
|---|
| 59 | is("\U$b" , "\x{100}\x{100}AA", '\U');
|
|---|
| 60 | is("\L$b" , "\x{101}\x{101}aa", '\L');
|
|---|
| 61 |
|
|---|
| 62 | is(quotemeta($b) , "\x{101}\x{100}aA", 'quotemeta');
|
|---|
| 63 | is(ucfirst($b) , "\x{100}\x{100}aA", 'ucfirst');
|
|---|
| 64 | is(lcfirst($b) , "\x{101}\x{100}aA", 'lcfirst');
|
|---|
| 65 | is(uc($b) , "\x{100}\x{100}AA", 'uc');
|
|---|
| 66 | is(lc($b) , "\x{101}\x{101}aa", 'lc');
|
|---|
| 67 |
|
|---|
| 68 | # \x{DF} is LATIN SMALL LETTER SHARP S, its uppercase is SS or \x{53}\x{53};
|
|---|
| 69 | # \x{149} is LATIN SMALL LETTER N PRECEDED BY APOSTROPHE, its uppercase is
|
|---|
| 70 | # \x{2BC}\x{E4} or MODIFIER LETTER APOSTROPHE and N.
|
|---|
| 71 |
|
|---|
| 72 | # In EBCDIC \x{DF} is LATIN SMALL LETTER Y WITH DIAERESIS,
|
|---|
| 73 | # and it's uppercase is \x{178}, LATIN CAPITAL LETTER Y WITH DIAERESIS.
|
|---|
| 74 |
|
|---|
| 75 | if (ord("A") == 193) { # EBCDIC
|
|---|
| 76 | is("\U\x{DF}aB\x{149}cD" , "\x{178}AB\x{2BC}NCD",
|
|---|
| 77 | "multicharacter uppercase");
|
|---|
| 78 | } elsif (ord("A") == 65) {
|
|---|
| 79 | is("\U\x{DF}aB\x{149}cD" , "SSAB\x{2BC}NCD",
|
|---|
| 80 | "multicharacter uppercase");
|
|---|
| 81 | } else {
|
|---|
| 82 | fail("what is your encoding?");
|
|---|
| 83 | }
|
|---|
| 84 |
|
|---|
| 85 | # The \x{DF} is its own lowercase, ditto for \x{149}.
|
|---|
| 86 | # There are no single character -> multiple characters lowercase mappings.
|
|---|
| 87 |
|
|---|
| 88 | if (ord("A") == 193) { # EBCDIC
|
|---|
| 89 | is("\LaB\x{149}cD" , "ab\x{149}cd",
|
|---|
| 90 | "multicharacter lowercase");
|
|---|
| 91 | } elsif (ord("A") == 65) {
|
|---|
| 92 | is("\L\x{DF}aB\x{149}cD" , "\x{DF}ab\x{149}cd",
|
|---|
| 93 | "multicharacter lowercase");
|
|---|
| 94 | } else {
|
|---|
| 95 | fail("what is your encoding?");
|
|---|
| 96 | }
|
|---|
| 97 |
|
|---|
| 98 | # titlecase is used for \u / ucfirst.
|
|---|
| 99 |
|
|---|
| 100 | # \x{587} is ARMENIAN SMALL LIGATURE ECH YIWN and its titlecase is
|
|---|
| 101 | # \x{535}\x{582} ARMENIAN CAPITAL LETTER ECH + ARMENIAN SMALL LETTER YIWN
|
|---|
| 102 | # while its lowercase is
|
|---|
| 103 | # \x{587} itself
|
|---|
| 104 | # and its uppercase is
|
|---|
| 105 | # \x{535}\x{552} ARMENIAN CAPITAL LETTER ECH + ARMENIAN CAPITAL LETTER YIWN
|
|---|
| 106 |
|
|---|
| 107 | $a = "\x{587}";
|
|---|
| 108 |
|
|---|
| 109 | is("\L\x{587}" , "\x{587}", "ligature lowercase");
|
|---|
| 110 | is("\u\x{587}" , "\x{535}\x{582}", "ligature titlecase");
|
|---|
| 111 | is("\U\x{587}" , "\x{535}\x{552}", "ligature uppercase");
|
|---|
| 112 |
|
|---|
| 113 | # mktables had problems where many-to-one case mappings didn't work right.
|
|---|
| 114 | # The lib/uni/fold.t should give the fourth folding, "casefolding", a good
|
|---|
| 115 | # workout (one cannot directly get that from Perl).
|
|---|
| 116 | # \x{01C4} is LATIN CAPITAL LETTER DZ WITH CARON
|
|---|
| 117 | # \x{01C5} is LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
|
|---|
| 118 | # \x{01C6} is LATIN SMALL LETTER DZ WITH CARON
|
|---|
| 119 | # \x{03A3} is GREEK CAPITAL LETTER SIGMA
|
|---|
| 120 | # \x{03C2} is GREEK SMALL LETTER FINAL SIGMA
|
|---|
| 121 | # \x{03C3} is GREEK SMALL LETTER SIGMA
|
|---|
| 122 |
|
|---|
| 123 | is(lc("\x{1C4}") , "\x{1C6}", "U+01C4 lc is U+01C6");
|
|---|
| 124 | is(lc("\x{1C5}") , "\x{1C6}", "U+01C5 lc is U+01C6, too");
|
|---|
| 125 |
|
|---|
| 126 | is(ucfirst("\x{3C2}") , "\x{3A3}", "U+03C2 ucfirst is U+03A3");
|
|---|
| 127 | is(ucfirst("\x{3C3}") , "\x{3A3}", "U+03C3 ucfirst is U+03A3, too");
|
|---|
| 128 |
|
|---|
| 129 | is(uc("\x{1C5}") , "\x{1C4}", "U+01C5 uc is U+01C4");
|
|---|
| 130 | is(uc("\x{1C6}") , "\x{1C4}", "U+01C6 uc is U+01C4, too");
|
|---|
| 131 |
|
|---|
| 132 | # #18107: A host of bugs involving [ul]c{,first}. AMS 20021106
|
|---|
| 133 | $a = "\x{3c3}foo.bar"; # \x{3c3} == GREEK SMALL LETTER SIGMA.
|
|---|
| 134 | $b = "\x{3a3}FOO.BAR"; # \x{3a3} == GREEK CAPITAL LETTER SIGMA.
|
|---|
| 135 |
|
|---|
| 136 | ($c = $b) =~ s/(\w+)/lc($1)/ge;
|
|---|
| 137 | is($c , $a, "Using s///e to change case.");
|
|---|
| 138 |
|
|---|
| 139 | ($c = $a) =~ s/(\w+)/uc($1)/ge;
|
|---|
| 140 | is($c , $b, "Using s///e to change case.");
|
|---|
| 141 |
|
|---|
| 142 | ($c = $b) =~ s/(\w+)/lcfirst($1)/ge;
|
|---|
| 143 | is($c , "\x{3c3}FOO.bAR", "Using s///e to change case.");
|
|---|
| 144 |
|
|---|
| 145 | ($c = $a) =~ s/(\w+)/ucfirst($1)/ge;
|
|---|
| 146 | is($c , "\x{3a3}foo.Bar", "Using s///e to change case.");
|
|---|
| 147 |
|
|---|
| 148 | # #18931: perl5.8.0 bug in \U..\E processing
|
|---|
| 149 | # Test case from Nicholas Clark.
|
|---|
| 150 | for my $a (0,1) {
|
|---|
| 151 | $_ = 'abcdefgh';
|
|---|
| 152 | $_ .= chr 256;
|
|---|
| 153 | chop;
|
|---|
| 154 | /(.*)/;
|
|---|
| 155 | is(uc($1), "ABCDEFGH", "[perl #18931]");
|
|---|
| 156 | }
|
|---|
| 157 |
|
|---|
| 158 | {
|
|---|
| 159 | foreach (0, 1) {
|
|---|
| 160 | $a = v10.v257;
|
|---|
| 161 | chop $a;
|
|---|
| 162 | $a =~ s/^(\s*)(\w*)/$1\u$2/;
|
|---|
| 163 | is($a, v10, "[perl #18857]");
|
|---|
| 164 | }
|
|---|
| 165 | }
|
|---|
