X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/2533d95048cb777fd52cff7a1b436c08caa12dae..78b9063ba31cc2a48b78683b758601c04e4eb340:/t/op/lc.t

diff --git a/t/op/lc.t b/t/op/lc.t
index 18c805f..d75b64e 100644
--- a/t/op/lc.t
+++ b/t/op/lc.t
@@ -1,52 +1,39 @@
 #!./perl
 
-print "1..45\n";
-
-my $test = 1;
-
-sub ok {
-    if ($_[0]) {
-	if ($_[1]) {
-	    print "ok $test - $_[1]\n";
-	} else {
-	    print "ok $test\n";
-	}
-    } else {
-	if ($_[1]) {
-	    print "not ok $test - $_[1]\n";
-	} else {
-	    print "not ok $test\n";
-	}
-    }
-    $test++;
+BEGIN {
+    chdir 't';
+    @INC = '../lib';
+    require './test.pl';
 }
 
+plan tests => 59;
+
 $a = "HELLO.* world";
 $b = "hello.* WORLD";
 
-ok("\Q$a\E."      eq "HELLO\\.\\*\\ world.", '\Q\E HELLO.* world');
-ok("\u$a"         eq "HELLO\.\* world",      '\u');
-ok("\l$a"         eq "hELLO\.\* world",      '\l');
-ok("\U$a"         eq "HELLO\.\* WORLD",      '\U');
-ok("\L$a"         eq "hello\.\* world",      '\L');
-
-ok(quotemeta($a)  eq "HELLO\\.\\*\\ world",  'quotemeta');
-ok(ucfirst($a)    eq "HELLO\.\* world",      'ucfirst');
-ok(lcfirst($a)    eq "hELLO\.\* world",      'lcfirst');
-ok(uc($a)         eq "HELLO\.\* WORLD",      'uc');
-ok(lc($a)         eq "hello\.\* world",      'lc');
-
-ok("\Q$b\E."      eq "hello\\.\\*\\ WORLD.", '\Q\E hello.* WORLD');
-ok("\u$b"         eq "Hello\.\* WORLD",      '\u');
-ok("\l$b"         eq "hello\.\* WORLD",      '\l');
-ok("\U$b"         eq "HELLO\.\* WORLD",      '\U');
-ok("\L$b"         eq "hello\.\* world",      '\L');
-
-ok(quotemeta($b)  eq "hello\\.\\*\\ WORLD",  'quotemeta');
-ok(ucfirst($b)    eq "Hello\.\* WORLD",      'ucfirst');
-ok(lcfirst($b)    eq "hello\.\* WORLD",      'lcfirst');
-ok(uc($b)         eq "HELLO\.\* WORLD",      'uc');
-ok(lc($b)         eq "hello\.\* world",      'lc');
+is("\Q$a\E."      , "HELLO\\.\\*\\ world.", '\Q\E HELLO.* world');
+is("\u$a"         , "HELLO\.\* world",      '\u');
+is("\l$a"         , "hELLO\.\* world",      '\l');
+is("\U$a"         , "HELLO\.\* WORLD",      '\U');
+is("\L$a"         , "hello\.\* world",      '\L');
+
+is(quotemeta($a)  , "HELLO\\.\\*\\ world",  'quotemeta');
+is(ucfirst($a)    , "HELLO\.\* world",      'ucfirst');
+is(lcfirst($a)    , "hELLO\.\* world",      'lcfirst');
+is(uc($a)         , "HELLO\.\* WORLD",      'uc');
+is(lc($a)         , "hello\.\* world",      'lc');
+
+is("\Q$b\E."      , "hello\\.\\*\\ WORLD.", '\Q\E hello.* WORLD');
+is("\u$b"         , "Hello\.\* WORLD",      '\u');
+is("\l$b"         , "hello\.\* WORLD",      '\l');
+is("\U$b"         , "HELLO\.\* WORLD",      '\U');
+is("\L$b"         , "hello\.\* world",      '\L');
+
+is(quotemeta($b)  , "hello\\.\\*\\ WORLD",  'quotemeta');
+is(ucfirst($b)    , "Hello\.\* WORLD",      'ucfirst');
+is(lcfirst($b)    , "hello\.\* WORLD",      'lcfirst');
+is(uc($b)         , "HELLO\.\* WORLD",      'uc');
+is(lc($b)         , "hello\.\* world",      'lc');
 
 # \x{100} is LATIN CAPITAL LETTER A WITH MACRON; its bijective lowercase is
 # \x{101}, LATIN SMALL LETTER A WITH MACRON.
@@ -54,42 +41,59 @@ ok(lc($b)         eq "hello\.\* world",      'lc');
 $a = "\x{100}\x{101}Aa";
 $b = "\x{101}\x{100}aA";
 
-ok("\Q$a\E."      eq "\x{100}\x{101}Aa.", '\Q\E \x{100}\x{101}Aa');
-ok("\u$a"         eq "\x{100}\x{101}Aa",  '\u');
-ok("\l$a"         eq "\x{101}\x{101}Aa",  '\l');
-ok("\U$a"         eq "\x{100}\x{100}AA",  '\U');
-ok("\L$a"         eq "\x{101}\x{101}aa",  '\L');
-
-ok(quotemeta($a)  eq "\x{100}\x{101}Aa",  'quotemeta');
-ok(ucfirst($a)    eq "\x{100}\x{101}Aa",  'ucfirst');
-ok(lcfirst($a)    eq "\x{101}\x{101}Aa",  'lcfirst');
-ok(uc($a)         eq "\x{100}\x{100}AA",  'uc');
-ok(lc($a)         eq "\x{101}\x{101}aa",  'lc');
-
-ok("\Q$b\E."      eq "\x{101}\x{100}aA.", '\Q\E \x{101}\x{100}aA');
-ok("\u$b"         eq "\x{100}\x{100}aA",  '\u');
-ok("\l$b"         eq "\x{101}\x{100}aA",  '\l');
-ok("\U$b"         eq "\x{100}\x{100}AA",  '\U');
-ok("\L$b"         eq "\x{101}\x{101}aa",  '\L');
-
-ok(quotemeta($b)  eq "\x{101}\x{100}aA",  'quotemeta');
-ok(ucfirst($b)    eq "\x{100}\x{100}aA",  'ucfirst');
-ok(lcfirst($b)    eq "\x{101}\x{100}aA",  'lcfirst');
-ok(uc($b)         eq "\x{100}\x{100}AA",  'uc');
-ok(lc($b)         eq "\x{101}\x{101}aa",  'lc');
+is("\Q$a\E."      , "\x{100}\x{101}Aa.", '\Q\E \x{100}\x{101}Aa');
+is("\u$a"         , "\x{100}\x{101}Aa",  '\u');
+is("\l$a"         , "\x{101}\x{101}Aa",  '\l');
+is("\U$a"         , "\x{100}\x{100}AA",  '\U');
+is("\L$a"         , "\x{101}\x{101}aa",  '\L');
+
+is(quotemeta($a)  , "\x{100}\x{101}Aa",  'quotemeta');
+is(ucfirst($a)    , "\x{100}\x{101}Aa",  'ucfirst');
+is(lcfirst($a)    , "\x{101}\x{101}Aa",  'lcfirst');
+is(uc($a)         , "\x{100}\x{100}AA",  'uc');
+is(lc($a)         , "\x{101}\x{101}aa",  'lc');
+
+is("\Q$b\E."      , "\x{101}\x{100}aA.", '\Q\E \x{101}\x{100}aA');
+is("\u$b"         , "\x{100}\x{100}aA",  '\u');
+is("\l$b"         , "\x{101}\x{100}aA",  '\l');
+is("\U$b"         , "\x{100}\x{100}AA",  '\U');
+is("\L$b"         , "\x{101}\x{101}aa",  '\L');
+
+is(quotemeta($b)  , "\x{101}\x{100}aA",  'quotemeta');
+is(ucfirst($b)    , "\x{100}\x{100}aA",  'ucfirst');
+is(lcfirst($b)    , "\x{101}\x{100}aA",  'lcfirst');
+is(uc($b)         , "\x{100}\x{100}AA",  'uc');
+is(lc($b)         , "\x{101}\x{101}aa",  'lc');
 
 # \x{DF} is LATIN SMALL LETTER SHARP S, its uppercase is SS or \x{53}\x{53};
 # \x{149} is LATIN SMALL LETTER N PRECEDED BY APOSTROPHE, its uppercase is
 # \x{2BC}\x{E4} or MODIFIER LETTER APOSTROPHE and N.
 
-ok("\U\x{DF}ab\x{149}cd" eq "SSAB\x{2BC}NCD",
-   "multicharacter uppercase");
+# In EBCDIC \x{DF} is LATIN SMALL LETTER Y WITH DIAERESIS,
+# and it's uppercase is \x{178}, LATIN CAPITAL LETTER Y WITH DIAERESIS.
+
+if (ord("A") == 193) { # EBCDIC
+    is("\U\x{DF}aB\x{149}cD" , "\x{178}AB\x{2BC}NCD",
+       "multicharacter uppercase");
+} elsif (ord("A") == 65) {
+    is("\U\x{DF}aB\x{149}cD" , "SSAB\x{2BC}NCD",
+       "multicharacter uppercase");
+} else {
+    fail("what is your encoding?");
+}
 
 # The \x{DF} is its own lowercase, ditto for \x{149}.
 # There are no single character -> multiple characters lowercase mappings.
 
-ok("\L\x{DF}AB\x{149}CD" eq "\x{DF}ab\x{149}cd",
-   "multicharacter lowercase");
+if (ord("A") == 193) { # EBCDIC
+    is("\LaB\x{149}cD" , "ab\x{149}cd",
+       "multicharacter lowercase");
+} elsif (ord("A") == 65) {
+    is("\L\x{DF}aB\x{149}cD" , "\x{DF}ab\x{149}cd",
+       "multicharacter lowercase");
+} else {
+    fail("what is your encoding?");
+}
 
 # titlecase is used for \u / ucfirst.
 
@@ -102,7 +106,60 @@ ok("\L\x{DF}AB\x{149}CD" eq "\x{DF}ab\x{149}cd",
 
 $a = "\x{587}";
 
-ok("\L\x{587}" eq "\x{587}",        "ligature lowercase");
-ok("\u\x{587}" eq "\x{535}\x{582}", "ligature titlecase");
-ok("\U\x{587}" eq "\x{535}\x{552}", "ligature uppercase");
+is("\L\x{587}" , "\x{587}",        "ligature lowercase");
+is("\u\x{587}" , "\x{535}\x{582}", "ligature titlecase");
+is("\U\x{587}" , "\x{535}\x{552}", "ligature uppercase");
+
+# mktables had problems where many-to-one case mappings didn't work right.
+# The lib/uni/fold.t should give the fourth folding, "casefolding", a good
+# workout (one cannot directly get that from Perl). 
+# \x{01C4} is LATIN CAPITAL LETTER DZ WITH CARON
+# \x{01C5} is LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
+# \x{01C6} is LATIN SMALL LETTER DZ WITH CARON
+# \x{03A3} is GREEK CAPITAL LETTER SIGMA
+# \x{03C2} is GREEK SMALL LETTER FINAL SIGMA
+# \x{03C3} is GREEK SMALL LETTER SIGMA
+
+is(lc("\x{1C4}") , "\x{1C6}",      "U+01C4 lc is U+01C6");
+is(lc("\x{1C5}") , "\x{1C6}",      "U+01C5 lc is U+01C6, too");
+
+is(ucfirst("\x{3C2}") , "\x{3A3}", "U+03C2 ucfirst is U+03A3");
+is(ucfirst("\x{3C3}") , "\x{3A3}", "U+03C3 ucfirst is U+03A3, too");
+
+is(uc("\x{1C5}") , "\x{1C4}",      "U+01C5 uc is U+01C4");
+is(uc("\x{1C6}") , "\x{1C4}",      "U+01C6 uc is U+01C4, too");
+
+# #18107: A host of bugs involving [ul]c{,first}. AMS 20021106
+$a = "\x{3c3}foo.bar"; # \x{3c3} == GREEK SMALL LETTER SIGMA.
+$b = "\x{3a3}FOO.BAR"; # \x{3a3} == GREEK CAPITAL LETTER SIGMA.
+
+($c = $b) =~ s/(\w+)/lc($1)/ge;
+is($c , $a, "Using s///e to change case.");
+
+($c = $a) =~ s/(\w+)/uc($1)/ge;
+is($c , $b, "Using s///e to change case.");
+
+($c = $b) =~ s/(\w+)/lcfirst($1)/ge;
+is($c , "\x{3c3}FOO.bAR", "Using s///e to change case.");
+
+($c = $a) =~ s/(\w+)/ucfirst($1)/ge;
+is($c , "\x{3a3}foo.Bar", "Using s///e to change case.");
+
+# #18931: perl5.8.0 bug in \U..\E processing
+# Test case from Nick Clark.
+for my $a (0,1) {
+    $_ = 'abcdefgh';
+    $_ .= chr 256;
+    chop;
+    /(.*)/;
+    is(uc($1), "ABCDEFGH", "[perl #18931]");
+}
 
+{
+    foreach (0, 1) {
+	$a = v10.v257;
+	chop $a;
+	$a =~ s/^(\s*)(\w*)/$1\u$2/;
+	is($a, v10, "[perl #18857]");
+    } 
+}