$| = 1;
-print "1..834\n";
+print "1..854\n";
BEGIN {
chdir 't' if -d 't';
# Test the Unicode script classes
-print "not " unless chr(0x100) =~ /\p{InLatin}/; # outside Latin-1
+print "not " unless chr(0x100) =~ /\p{IsLatin}/; # outside Latin-1
print "ok 661\n";
-print "not " unless chr(0x212b) =~ /\p{InLatin}/; # Angstrom sign, very outside
+print "not " unless chr(0x212b) =~ /\p{IsLatin}/; # Angstrom sign, very outside
print "ok 662\n";
-print "not " unless chr(0x5d0) =~ /\p{InHebrew}/; # inside HebrewBlock
+print "not " unless chr(0x5d0) =~ /\p{IsHebrew}/; # inside InHebrew
print "ok 663\n";
-print "not " unless chr(0xfb4f) =~ /\p{InHebrew}/; # outside HebrewBlock
+print "not " unless chr(0xfb4f) =~ /\p{IsHebrew}/; # outside InHebrew
print "ok 664\n";
-print "not " unless chr(0xb5) =~ /\p{InGreek}/; # singleton (not in a range)
+print "not " unless chr(0xb5) =~ /\p{IsGreek}/; # singleton (not in a range)
print "ok 665\n";
-print "not " unless chr(0x37a) =~ /\p{InGreek}/; # singleton
+print "not " unless chr(0x37a) =~ /\p{IsGreek}/; # singleton
print "ok 666\n";
-print "not " unless chr(0x386) =~ /\p{InGreek}/; # singleton
+print "not " unless chr(0x386) =~ /\p{IsGreek}/; # singleton
print "ok 667\n";
-print "not " unless chr(0x387) =~ /\P{InGreek}/; # not there
+print "not " unless chr(0x387) =~ /\P{IsGreek}/; # not there
print "ok 668\n";
-print "not " unless chr(0x388) =~ /\p{InGreek}/; # range
+print "not " unless chr(0x388) =~ /\p{IsGreek}/; # range
print "ok 669\n";
-print "not " unless chr(0x38a) =~ /\p{InGreek}/; # range
+print "not " unless chr(0x38a) =~ /\p{IsGreek}/; # range
print "ok 670\n";
-print "not " unless chr(0x38b) =~ /\P{InGreek}/; # not there
+print "not " unless chr(0x38b) =~ /\P{IsGreek}/; # not there
print "ok 671\n";
-print "not " unless chr(0x38c) =~ /\p{InGreek}/; # singleton
+print "not " unless chr(0x38c) =~ /\p{IsGreek}/; # singleton
print "ok 672\n";
##
}
{
- print "not " unless "a" =~ /\p{LowercaseLetter}/;
+ print "not " unless "a" =~ /\p{Lowercase Letter}/;
print "ok 745\n";
- print "not " if "A" =~ /\p{
- Lowercase
- Letter
- }/x;
+ print "not " if "A" =~ /\p{lowercaseletter}/;
print "ok 746\n";
}
{
- print "not " unless "\x{AC00}" =~ /\p{HangulSyllable}/;
+ print "not " unless "\x{AC00}" =~ /\p{HangulSyllables}/;
print "ok 747\n";
}
print ":$S3:" =~ /:(([$sigma])+):/i && $1 eq $S3 && $2 eq $sigma ?
"ok 834\n" : "not ok 834\n";
}
+
+{
+ print "# LATIN SMALL LETTER SHARP S\n";
+
+ use charnames ':full';
+
+ print "\N{LATIN SMALL LETTER SHARP S}" =~
+ /\N{LATIN SMALL LETTER SHARP S}/ ? "ok 835\n" : "not ok 835\n";
+
+ print "\N{LATIN SMALL LETTER SHARP S}" =~
+ /\N{LATIN SMALL LETTER SHARP S}/i ? "ok 836\n" : "not ok 836\n";
+
+ print "\N{LATIN SMALL LETTER SHARP S}" =~
+ /[\N{LATIN SMALL LETTER SHARP S}]/ ? "ok 837\n" : "not ok 837\n";
+
+ print "\N{LATIN SMALL LETTER SHARP S}" =~
+ /[\N{LATIN SMALL LETTER SHARP S}]/i ? "ok 838\n" : "not ok 838\n";
+
+ print "ss" =~
+ /\N{LATIN SMALL LETTER SHARP S}/i ? "ok 839\n" : "not ok 839\n";
+
+ print "SS" =~
+ /\N{LATIN SMALL LETTER SHARP S}/i ? "ok 840\n" : "not ok 840\n";
+
+ print "ss" =~
+ /[\N{LATIN SMALL LETTER SHARP S}]/i ? "ok 841\n" : "not ok 841\n";
+
+ print "SS" =~
+ /[\N{LATIN SMALL LETTER SHARP S}]/i ? "ok 842\n" : "not ok 842\n";
+
+ print "\N{LATIN SMALL LETTER SHARP S}" =~ /ss/i ?
+ "ok 843\n" : "not ok 843\n";
+
+ print "\N{LATIN SMALL LETTER SHARP S}" =~ /SS/i ?
+ "ok 844\n" : "not ok 844\n";
+}
+
+{
+ print "# more whitespace: U+0085, U+2028, U+2029\n";
+
+ # U+0085 needs to be forced to be Unicode, the \x{100} does that.
+ print "<\x{100}\x{0085}>" =~ /<\x{100}\s>/ ? "ok 845\n" : "not ok 845\n";
+ print "<\x{2028}>" =~ /<\s>/ ? "ok 846\n" : "not ok 846\n";
+ print "<\x{2029}>" =~ /<\s>/ ? "ok 847\n" : "not ok 847\n";
+}
+
+{
+ print "# . with /s should work on characters, as opposed to bytes\n";
+
+ my $s = "\x{e4}\x{100}";
+
+ # This is not expected to match: the point is that
+ # neither should we get "Malformed UTF-8" warnings.
+ print $s =~ /\G(.+?)\n/gcs ?
+ "not ok 848\n" : "ok 848\n";
+
+ my @c;
+
+ while ($s =~ /\G(.)/gs) {
+ push @c, $1;
+ }
+
+ print join("", @c) eq $s ? "ok 849\n" : "not ok 849\n";
+
+ my $t1 = "Q003\n\n\x{e4}\x{f6}\n\nQ004\n\n\x{e7}"; # test only chars < 256
+ my $r1 = "";
+ while ($t1 =~ / \G ( .+? ) \n\s+ ( .+? ) ( $ | \n\s+ ) /xgcs) {
+ $r1 .= $1 . $2;
+ }
+
+ my $t2 = $t1 . "\x{100}"; # repeat with a larger char
+ my $r2 = "";
+ while ($t2 =~ / \G ( .+? ) \n\s+ ( .+? ) ( $ | \n\s+ ) /xgcs) {
+ $r2 .= $1 . $2;
+ }
+ $r2 =~ s/\x{100}//;
+ print $r1 eq $r2 ? "ok 850\n" : "not ok 850\n";
+}
+
+{
+ print "# Unicode lookbehind\n";
+
+ print "A\x{100}B" =~ /(?<=A.)B/ ? "ok 851\n" : "not ok 851\n";
+ print "A\x{200}\x{300}B" =~ /(?<=A..)B/ ? "ok 852\n" : "not ok 852\n";
+ print "\x{400}AB" =~ /(?<=\x{400}.)B/ ? "ok 853\n" : "not ok 853\n";
+ print "\x{500\x{600}}B" =~ /(?<=\x{500}.)B/ ? "ok 854\n" : "not ok 854\n";
+}