utf8.c AOK
- [utf8_to_uv]
+ [utf8_to_uvchr_buf]
Malformed UTF-8 character
my $a = ord "\x80" ;
<<<<<< Add a test when something actually calls utf16_to_utf8
__END__
-# utf8.c [utf8_to_uv] -W
+# utf8.c [utf8_to_uvchr_buf] -W
+# NAME Malformed under 'use utf8' in double-quoted string
BEGIN {
if (ord('A') == 193) {
- print "SKIPPED\n# ebcdic platforms do not generate Malformed UTF-8 warnings.";
+ print "SKIPPED\n# ebcdic platforms generates different Malformed UTF-8 warnings.";
exit 0;
}
}
use utf8 ;
+no warnings; # Malformed is a fatal error, so gets output anyway.
my $a = "snøstorm" ;
-{
- no warnings 'utf8' ;
- my $a = "snøstorm";
- use warnings 'utf8' ;
- my $a = "snøstorm";
+EXPECT
+Malformed UTF-8 character: \xf8\x73\x74\x6f\x72 (unexpected non-continuation byte 0x73, immediately after start byte 0xf8; need 5 bytes, got 1) at - line 10.
+Malformed UTF-8 character (fatal) at - line 10.
+########
+# NAME Malformed under 'use utf8' in single-quoted string
+BEGIN {
+ if (ord('A') == 193) {
+ print "SKIPPED\n# ebcdic platforms generates different Malformed UTF-8 warnings.";
+ exit 0;
+ }
}
+use utf8 ;
+no warnings; # Malformed is a fatal error, so gets output anyway.
+my $a = 'snøstorm' ;
EXPECT
-Malformed UTF-8 character (unexpected non-continuation byte 0x73, immediately after start byte 0xf8) at - line 9.
-Malformed UTF-8 character (unexpected non-continuation byte 0x73, immediately after start byte 0xf8) at - line 14.
+Malformed UTF-8 character: \xf8\x73\x74\x6f\x72 (unexpected non-continuation byte 0x73, immediately after start byte 0xf8; need 5 bytes, got 1) at - line 9.
+Malformed UTF-8 character (fatal) at - line 9.
########
use warnings 'utf8';
my $d7ff = uc(chr(0xD7FF));
use warnings 'utf8';
my $d800 = uc(chr(0xD800));
my $nonUnicode = uc(chr(0x110000));
-my $big_nonUnicode = uc(chr(0x8000_0000));
no warnings 'non_unicode';
my $d800 = uc(chr(0xD800));
my $nonUnicode = uc(chr(0x110000));
-my $big_nonUnicode = uc(chr(0x8000_0000));
EXPECT
Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 2.
Operation "uc" returns its argument for non-Unicode code point 0x110000 at - line 3.
-Operation "uc" returns its argument for non-Unicode code point 0x80000000 at - line 4.
-Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 6.
+Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 5.
+########
+use warnings 'utf8';
+no warnings 'deprecated'; # This is above IV_MAX on 32 bit machines
+my $big_nonUnicode = uc(chr(0x8000_0000));
+no warnings 'non_unicode';
+my $big_nonUnicode = uc(chr(0x8000_0000));
+EXPECT
+Operation "uc" returns its argument for non-Unicode code point 0x80000000 at - line 3.
########
use warnings 'utf8';
my $d7ff = lc pack("U", 0xD7FF);
Operation "ucfirst" returns its argument for UTF-16 surrogate U+DFFF at - line 4.
Operation "ucfirst" returns its argument for non-Unicode code point 0x110000 at - line 14.
########
+# NAME Matching \p{} against above-Unicode
use warnings 'utf8';
chr(0xD7FF) =~ /\p{Any}/;
chr(0xD800) =~ /\p{Any}/;
chr(0x100000) =~ /\p{Any}/;
chr(0x10FFFE) =~ /\p{Any}/;
chr(0x10FFFF) =~ /\p{Any}/;
-chr(0x110000) =~ /\p{Any}/;
+chr(0x110000) =~ /[\p{Any}]/;
+chr(0x110001) =~ /[\w\p{Any}]/;
+chr(0x10FFFF) =~ /\p{All}/;
+chr(0x110002) =~ /[\w\p{All}]/;
+chr(0x110003) =~ /[\p{XPosixWord}]/;
+chr(0x110004) =~ /[\P{XPosixWord}]/;
+chr(0x110005) =~ /^[\p{Unassigned}]/;
+chr(0x110006) =~ /^[\P{Unassigned}]/;
+# Only Unicode properties give non-Unicode warnings, and only those properties
+# which do match above Unicode; and not when something else in the class
+# matches above Unicode. Below we test three ways where something outside the
+# property may match non-Unicode: a code point above it, a class \S that we
+# know at compile time doesn't, and a class \W whose values aren't (at the time
+# of this writing) specified at compile time, but which wouldn't match
+chr(0x110050) =~ /\w/;
+chr(0x110051) =~ /\W/;
+chr(0x110052) =~ /\d/;
+chr(0x110053) =~ /\D/;
+chr(0x110054) =~ /\s/;
+chr(0x110055) =~ /\S/;
+chr(0x110056) =~ /[[:word:]]/;
+chr(0x110057) =~ /[[:^word:]]/;
+chr(0x110058) =~ /[[:alnum:]]/;
+chr(0x110059) =~ /[[:^alnum:]]/;
+chr(0x11005A) =~ /[[:space:]]/;
+chr(0x11005B) =~ /[[:^space:]]/;
+chr(0x11005C) =~ /[[:digit:]]/;
+chr(0x11005D) =~ /[[:^digit:]]/;
+chr(0x11005E) =~ /[[:alpha:]]/;
+chr(0x11005F) =~ /[[:^alpha:]]/;
+chr(0x110060) =~ /[[:ascii:]]/;
+chr(0x110061) =~ /[[:^ascii:]]/;
+chr(0x110062) =~ /[[:cntrl:]]/;
+chr(0x110063) =~ /[[:^cntrl:]]/;
+chr(0x110064) =~ /[[:graph:]]/;
+chr(0x110065) =~ /[[:^graph:]]/;
+chr(0x110066) =~ /[[:lower:]]/;
+chr(0x110067) =~ /[[:^lower:]]/;
+chr(0x110068) =~ /[[:print:]]/;
+chr(0x110069) =~ /[[:^print:]]/;
+chr(0x11006A) =~ /[[:punct:]]/;
+chr(0x11006B) =~ /[[:^punct:]]/;
+chr(0x11006C) =~ /[[:upper:]]/;
+chr(0x11006D) =~ /[[:^upper:]]/;
+chr(0x11006E) =~ /[[:xdigit:]]/;
+chr(0x11006F) =~ /[[:^xdigit:]]/;
+chr(0x110070) =~ /[[:blank:]]/;
+chr(0x110071) =~ /[[:^blank:]]/;
+chr(0x111010) =~ /[\W\p{Unassigned}]/;
+chr(0x111011) =~ /[\W\P{Unassigned}]/;
+chr(0x112010) =~ /[\S\p{Unassigned}]/;
+chr(0x112011) =~ /[\S\P{Unassigned}]/;
+chr(0x113010) =~ /[\x{110000}\p{Unassigned}]/;
+chr(0x113011) =~ /[\x{110000}\P{Unassigned}]/;
no warnings 'utf8';
chr(0xD7FF) =~ /\p{Any}/;
chr(0xD800) =~ /\p{Any}/;
chr(0x100000) =~ /\p{Any}/;
chr(0x10FFFE) =~ /\p{Any}/;
chr(0x10FFFF) =~ /\p{Any}/;
-chr(0x110000) =~ /\p{Any}/;
+chr(0x110000) =~ /[\p{Any}]/;
+chr(0x110001) =~ /[\w\p{Any}]/;
+chr(0x10FFFF) =~ /\p{All}/;
+chr(0x110002) =~ /[\w\p{All}]/;
+chr(0x110003) =~ /[\p{XPosixWord}]/;
+chr(0x110004) =~ /[\P{XPosixWord}]/;
+chr(0x110005) =~ /^[\p{Unassigned}]/;
+chr(0x110006) =~ /^[\P{Unassigned}]/;
+chr(0x110050) =~ /\w/;
+chr(0x110051) =~ /\W/;
+chr(0x110052) =~ /\d/;
+chr(0x110053) =~ /\D/;
+chr(0x110054) =~ /\s/;
+chr(0x110055) =~ /\S/;
+chr(0x110056) =~ /[[:word:]]/;
+chr(0x110057) =~ /[[:^word:]]/;
+chr(0x110058) =~ /[[:alnum:]]/;
+chr(0x110059) =~ /[[:^alnum:]]/;
+chr(0x11005A) =~ /[[:space:]]/;
+chr(0x11005B) =~ /[[:^space:]]/;
+chr(0x11005C) =~ /[[:digit:]]/;
+chr(0x11005D) =~ /[[:^digit:]]/;
+chr(0x11005E) =~ /[[:alpha:]]/;
+chr(0x11005F) =~ /[[:^alpha:]]/;
+chr(0x110060) =~ /[[:ascii:]]/;
+chr(0x110061) =~ /[[:^ascii:]]/;
+chr(0x110062) =~ /[[:cntrl:]]/;
+chr(0x110063) =~ /[[:^cntrl:]]/;
+chr(0x110064) =~ /[[:graph:]]/;
+chr(0x110065) =~ /[[:^graph:]]/;
+chr(0x110066) =~ /[[:lower:]]/;
+chr(0x110067) =~ /[[:^lower:]]/;
+chr(0x110068) =~ /[[:print:]]/;
+chr(0x110069) =~ /[[:^print:]]/;
+chr(0x11006A) =~ /[[:punct:]]/;
+chr(0x11006B) =~ /[[:^punct:]]/;
+chr(0x11006C) =~ /[[:upper:]]/;
+chr(0x11006D) =~ /[[:^upper:]]/;
+chr(0x11006E) =~ /[[:xdigit:]]/;
+chr(0x11006F) =~ /[[:^xdigit:]]/;
+chr(0x110070) =~ /[[:blank:]]/;
+chr(0x110071) =~ /[[:^blank:]]/;
+chr(0x111010) =~ /[\W\p{Unassigned}]/;
+chr(0x111011) =~ /[\W\P{Unassigned}]/;
+chr(0x112010) =~ /[\S\p{Unassigned}]/;
+chr(0x112011) =~ /[\S\P{Unassigned}]/;
+chr(0x113010) =~ /[\x{110000}\p{Unassigned}]/;
+chr(0x113011) =~ /[\x{110000}\P{Unassigned}]/;
+EXPECT
+Matched non-Unicode code point 0x110005 against Unicode property; may not be portable at - line 20.
+Matched non-Unicode code point 0x110006 against Unicode property; may not be portable at - line 21.
+########
+# NAME Matching Unicode property against above-Unicode code point outputs a warning even if optimizer rejects the match (in synthetic start class)
+# Now have to make FATAL to guarantee being output
+use warnings FATAL => 'non_unicode';
+"\x{110000}" =~ /b?\p{Space}/;
+EXPECT
+Matched non-Unicode code point 0x110000 against Unicode property; may not be portable at - line 3.
+########
+# NAME Matching POSIX class property against above-Unicode code point doesn't output a warning
+use warnings 'non_unicode';
+use warnings FATAL => 'non_unicode';
+"\x{110000}" =~ /b?[[:space:]]/;
EXPECT
-Code point 0x110000 is not Unicode, all \p{} matches fail; all \P{} matches succeed at - line 14.
########
use warnings 'utf8';
chr(0x110000) =~ /\p{Any}/;
+########
+# NAME utf8, non_unicode warnings categories work on Matched non-Unicode code point warning
+use warnings qw(utf8 non_unicode);
+chr(0x110000) =~ /^\p{Unassigned}/;
no warnings 'non_unicode';
-chr(0x110000) =~ /\p{Any}/;
+chr(0x110001) =~ /\p{Unassigned}/;
+use warnings 'non_unicode';
+no warnings 'utf8';
+chr(0x110002) =~ /\p{Unassigned}/;
+EXPECT
+Matched non-Unicode code point 0x110000 against Unicode property; may not be portable at - line 2.
+########
+# NAME optimizable regnode should still give non_unicode warnings when fatalized
+use warnings 'utf8';
+use warnings FATAL => 'non_unicode';
+chr(0x110000) =~ /\p{lb=cr}/;
+EXPECT
+Matched non-Unicode code point 0x110000 against Unicode property; may not be portable at - line 3.
+########
+# NAME optimizable regnode should not give non_unicode warnings when warnings are off
+no warnings 'non_unicode';
+chr(0x110000) =~ /\p{lb=cr}/;
+EXPECT
+########
+# NAME 'All' matches above-Unicode without any warning
+use warnings qw(utf8 non_unicode);
+chr(0x110000) =~ /\p{All}/;
EXPECT
-Code point 0x110000 is not Unicode, all \p{} matches fail; all \P{} matches succeed at - line 2.
########
require "../test.pl";
use warnings 'utf8';
sub Is_Super { return '!utf8::Any' }
-print "\x{1100000}" =~ /\p{Is_Super}/, "\n";
+# The extra char is to avoid an optimization that avoids the problem when the
+# property is the only non-latin1 char in a class
+print "\x{1100000}" =~ /^[\p{Is_Super}\x{100}]$/, "\n";
EXPECT
1
########
open(my $fh, "+>:utf8", $file);
print $fh "\x{D7FF}", "\n";
print $fh "\x{D800}", "\n";
+print $fh "\x{D900}", "\n";
+print $fh "\x{DA00}", "\n";
+print $fh "\x{DB00}", "\n";
+print $fh "\x{DC00}", "\n";
+print $fh "\x{DD00}", "\n";
+print $fh "\x{DE00}", "\n";
+print $fh "\x{DF00}", "\n";
print $fh "\x{DFFF}", "\n";
print $fh "\x{E000}", "\n";
print $fh "\x{FDCF}", "\n";
print $fh "\x{FDD0}", "\n";
+print $fh "\x{FDD1}", "\n";
print $fh "\x{FDEF}", "\n";
print $fh "\x{FDF0}", "\n";
+print $fh "\x{FDFE}", "\n";
+print $fh "\x{FDFF}", "\n";
+print $fh "\x{FE00}", "\n";
print $fh "\x{FEFF}", "\n";
print $fh "\x{FFFD}", "\n";
print $fh "\x{FFFE}", "\n";
print $fh "\x{FFFF}", "\n";
print $fh "\x{10000}", "\n";
+print $fh "\x{1FFFD}", "\n";
print $fh "\x{1FFFE}", "\n";
print $fh "\x{1FFFF}", "\n";
+print $fh "\x{20000}", "\n";
+print $fh "\x{2FFFD}", "\n";
print $fh "\x{2FFFE}", "\n";
print $fh "\x{2FFFF}", "\n";
+print $fh "\x{30000}", "\n";
+print $fh "\x{3FFFD}", "\n";
print $fh "\x{3FFFE}", "\n";
print $fh "\x{3FFFF}", "\n";
+print $fh "\x{40000}", "\n";
+print $fh "\x{4FFFD}", "\n";
print $fh "\x{4FFFE}", "\n";
print $fh "\x{4FFFF}", "\n";
+print $fh "\x{50000}", "\n";
+print $fh "\x{5FFFD}", "\n";
print $fh "\x{5FFFE}", "\n";
print $fh "\x{5FFFF}", "\n";
+print $fh "\x{60000}", "\n";
+print $fh "\x{6FFFD}", "\n";
print $fh "\x{6FFFE}", "\n";
print $fh "\x{6FFFF}", "\n";
+print $fh "\x{70000}", "\n";
+print $fh "\x{7FFFD}", "\n";
print $fh "\x{7FFFE}", "\n";
print $fh "\x{7FFFF}", "\n";
+print $fh "\x{80000}", "\n";
+print $fh "\x{8FFFD}", "\n";
print $fh "\x{8FFFE}", "\n";
print $fh "\x{8FFFF}", "\n";
+print $fh "\x{90000}", "\n";
+print $fh "\x{9FFFD}", "\n";
print $fh "\x{9FFFE}", "\n";
print $fh "\x{9FFFF}", "\n";
+print $fh "\x{A0000}", "\n";
+print $fh "\x{AFFFD}", "\n";
print $fh "\x{AFFFE}", "\n";
print $fh "\x{AFFFF}", "\n";
+print $fh "\x{B0000}", "\n";
+print $fh "\x{BFFFD}", "\n";
print $fh "\x{BFFFE}", "\n";
print $fh "\x{BFFFF}", "\n";
+print $fh "\x{C0000}", "\n";
+print $fh "\x{CFFFD}", "\n";
print $fh "\x{CFFFE}", "\n";
print $fh "\x{CFFFF}", "\n";
+print $fh "\x{D0000}", "\n";
+print $fh "\x{DFFFD}", "\n";
print $fh "\x{DFFFE}", "\n";
print $fh "\x{DFFFF}", "\n";
+print $fh "\x{E0000}", "\n";
+print $fh "\x{EFFFD}", "\n";
print $fh "\x{EFFFE}", "\n";
print $fh "\x{EFFFF}", "\n";
+print $fh "\x{F0000}", "\n";
+print $fh "\x{FFFFD}", "\n";
print $fh "\x{FFFFE}", "\n";
print $fh "\x{FFFFF}", "\n";
print $fh "\x{100000}", "\n";
+print $fh "\x{10FFFD}", "\n";
print $fh "\x{10FFFE}", "\n";
print $fh "\x{10FFFF}", "\n";
print $fh "\x{110000}", "\n";
+print $fh "\x{11FFFD}", "\n";
+print $fh "\x{11FFFE}", "\n";
+print $fh "\x{11FFFF}", "\n";
+print $fh "\x{120000}", "\n";
close $fh;
EXPECT
Unicode surrogate U+D800 is illegal in UTF-8 at - line 6.
-Unicode surrogate U+DFFF is illegal in UTF-8 at - line 7.
-Unicode non-character U+FDD0 is illegal for open interchange at - line 10.
-Unicode non-character U+FDEF is illegal for open interchange at - line 11.
-Unicode non-character U+FFFE is illegal for open interchange at - line 15.
-Unicode non-character U+FFFF is illegal for open interchange at - line 16.
-Unicode non-character U+1FFFE is illegal for open interchange at - line 18.
-Unicode non-character U+1FFFF is illegal for open interchange at - line 19.
-Unicode non-character U+2FFFE is illegal for open interchange at - line 20.
-Unicode non-character U+2FFFF is illegal for open interchange at - line 21.
-Unicode non-character U+3FFFE is illegal for open interchange at - line 22.
-Unicode non-character U+3FFFF is illegal for open interchange at - line 23.
-Unicode non-character U+4FFFE is illegal for open interchange at - line 24.
-Unicode non-character U+4FFFF is illegal for open interchange at - line 25.
-Unicode non-character U+5FFFE is illegal for open interchange at - line 26.
-Unicode non-character U+5FFFF is illegal for open interchange at - line 27.
-Unicode non-character U+6FFFE is illegal for open interchange at - line 28.
-Unicode non-character U+6FFFF is illegal for open interchange at - line 29.
-Unicode non-character U+7FFFE is illegal for open interchange at - line 30.
-Unicode non-character U+7FFFF is illegal for open interchange at - line 31.
-Unicode non-character U+8FFFE is illegal for open interchange at - line 32.
-Unicode non-character U+8FFFF is illegal for open interchange at - line 33.
-Unicode non-character U+9FFFE is illegal for open interchange at - line 34.
-Unicode non-character U+9FFFF is illegal for open interchange at - line 35.
-Unicode non-character U+AFFFE is illegal for open interchange at - line 36.
-Unicode non-character U+AFFFF is illegal for open interchange at - line 37.
-Unicode non-character U+BFFFE is illegal for open interchange at - line 38.
-Unicode non-character U+BFFFF is illegal for open interchange at - line 39.
-Unicode non-character U+CFFFE is illegal for open interchange at - line 40.
-Unicode non-character U+CFFFF is illegal for open interchange at - line 41.
-Unicode non-character U+DFFFE is illegal for open interchange at - line 42.
-Unicode non-character U+DFFFF is illegal for open interchange at - line 43.
-Unicode non-character U+EFFFE is illegal for open interchange at - line 44.
-Unicode non-character U+EFFFF is illegal for open interchange at - line 45.
-Unicode non-character U+FFFFE is illegal for open interchange at - line 46.
-Unicode non-character U+FFFFF is illegal for open interchange at - line 47.
-Unicode non-character U+10FFFE is illegal for open interchange at - line 49.
-Unicode non-character U+10FFFF is illegal for open interchange at - line 50.
-Code point 0x110000 is not Unicode, may not be portable at - line 51.
+Unicode surrogate U+D900 is illegal in UTF-8 at - line 7.
+Unicode surrogate U+DA00 is illegal in UTF-8 at - line 8.
+Unicode surrogate U+DB00 is illegal in UTF-8 at - line 9.
+Unicode surrogate U+DC00 is illegal in UTF-8 at - line 10.
+Unicode surrogate U+DD00 is illegal in UTF-8 at - line 11.
+Unicode surrogate U+DE00 is illegal in UTF-8 at - line 12.
+Unicode surrogate U+DF00 is illegal in UTF-8 at - line 13.
+Unicode surrogate U+DFFF is illegal in UTF-8 at - line 14.
+Unicode non-character U+FDD0 is not recommended for open interchange in print at - line 17.
+Unicode non-character U+FDD1 is not recommended for open interchange in print at - line 18.
+Unicode non-character U+FDEF is not recommended for open interchange in print at - line 19.
+Unicode non-character U+FFFE is not recommended for open interchange in print at - line 26.
+Unicode non-character U+FFFF is not recommended for open interchange in print at - line 27.
+Unicode non-character U+1FFFE is not recommended for open interchange in print at - line 30.
+Unicode non-character U+1FFFF is not recommended for open interchange in print at - line 31.
+Unicode non-character U+2FFFE is not recommended for open interchange in print at - line 34.
+Unicode non-character U+2FFFF is not recommended for open interchange in print at - line 35.
+Unicode non-character U+3FFFE is not recommended for open interchange in print at - line 38.
+Unicode non-character U+3FFFF is not recommended for open interchange in print at - line 39.
+Unicode non-character U+4FFFE is not recommended for open interchange in print at - line 42.
+Unicode non-character U+4FFFF is not recommended for open interchange in print at - line 43.
+Unicode non-character U+5FFFE is not recommended for open interchange in print at - line 46.
+Unicode non-character U+5FFFF is not recommended for open interchange in print at - line 47.
+Unicode non-character U+6FFFE is not recommended for open interchange in print at - line 50.
+Unicode non-character U+6FFFF is not recommended for open interchange in print at - line 51.
+Unicode non-character U+7FFFE is not recommended for open interchange in print at - line 54.
+Unicode non-character U+7FFFF is not recommended for open interchange in print at - line 55.
+Unicode non-character U+8FFFE is not recommended for open interchange in print at - line 58.
+Unicode non-character U+8FFFF is not recommended for open interchange in print at - line 59.
+Unicode non-character U+9FFFE is not recommended for open interchange in print at - line 62.
+Unicode non-character U+9FFFF is not recommended for open interchange in print at - line 63.
+Unicode non-character U+AFFFE is not recommended for open interchange in print at - line 66.
+Unicode non-character U+AFFFF is not recommended for open interchange in print at - line 67.
+Unicode non-character U+BFFFE is not recommended for open interchange in print at - line 70.
+Unicode non-character U+BFFFF is not recommended for open interchange in print at - line 71.
+Unicode non-character U+CFFFE is not recommended for open interchange in print at - line 74.
+Unicode non-character U+CFFFF is not recommended for open interchange in print at - line 75.
+Unicode non-character U+DFFFE is not recommended for open interchange in print at - line 78.
+Unicode non-character U+DFFFF is not recommended for open interchange in print at - line 79.
+Unicode non-character U+EFFFE is not recommended for open interchange in print at - line 82.
+Unicode non-character U+EFFFF is not recommended for open interchange in print at - line 83.
+Unicode non-character U+FFFFE is not recommended for open interchange in print at - line 86.
+Unicode non-character U+FFFFF is not recommended for open interchange in print at - line 87.
+Unicode non-character U+10FFFE is not recommended for open interchange in print at - line 90.
+Unicode non-character U+10FFFF is not recommended for open interchange in print at - line 91.
+Code point 0x110000 is not Unicode, may not be portable in print at - line 92.
+Code point 0x11FFFD is not Unicode, may not be portable in print at - line 93.
+Code point 0x11FFFE is not Unicode, may not be portable in print at - line 94.
+Code point 0x11FFFF is not Unicode, may not be portable in print at - line 95.
+Code point 0x120000 is not Unicode, may not be portable in print at - line 96.
########
require "../test.pl";
use warnings 'utf8';
close $fh;
EXPECT
Unicode surrogate U+D800 is illegal in UTF-8 at - line 5.
-Unicode non-character U+FFFF is illegal for open interchange at - line 6.
-Code point 0x110000 is not Unicode, may not be portable at - line 7.
+Unicode non-character U+FFFF is not recommended for open interchange in print at - line 6.
+Code point 0x110000 is not Unicode, may not be portable in print at - line 7.
########
require "../test.pl";
use warnings 'utf8';
print $fh "\x{110000}", "\n";
close $fh;
EXPECT
-Unicode non-character U+FFFF is illegal for open interchange at - line 7.
-Code point 0x110000 is not Unicode, may not be portable at - line 8.
+Unicode non-character U+FFFF is not recommended for open interchange in print at - line 7.
+Code point 0x110000 is not Unicode, may not be portable in print at - line 8.
########
require "../test.pl";
use warnings 'utf8';
close $fh;
EXPECT
Unicode surrogate U+D800 is illegal in UTF-8 at - line 6.
-Code point 0x110000 is not Unicode, may not be portable at - line 8.
+Code point 0x110000 is not Unicode, may not be portable in print at - line 8.
########
require "../test.pl";
use warnings 'utf8';
close $fh;
EXPECT
Unicode surrogate U+D800 is illegal in UTF-8 at - line 6.
-Unicode non-character U+FFFF is illegal for open interchange at - line 7.
+Unicode non-character U+FFFF is not recommended for open interchange in print at - line 7.
+########
+# NAME C<use warnings "nonchar"> works in isolation
+require "../test.pl";
+use warnings 'nonchar';
+my $file = tempfile();
+open(my $fh, "+>:utf8", $file);
+print $fh "\x{FFFF}", "\n";
+close $fh;
+EXPECT
+Unicode non-character U+FFFF is not recommended for open interchange in print at - line 5.
+########
+# NAME C<use warnings "surrogate"> works in isolation
+require "../test.pl";
+use warnings 'surrogate';
+my $file = tempfile();
+open(my $fh, "+>:utf8", $file);
+print $fh "\x{D800}", "\n";
+close $fh;
+EXPECT
+Unicode surrogate U+D800 is illegal in UTF-8 at - line 5.
+########
+# NAME C<use warnings "non_unicode"> works in isolation
+require "../test.pl";
+use warnings 'non_unicode';
+my $file = tempfile();
+open(my $fh, "+>:utf8", $file);
+print $fh "\x{110000}", "\n";
+close $fh;
+EXPECT
+Code point 0x110000 is not Unicode, may not be portable in print at - line 5.
########
require "../test.pl";
no warnings 'utf8';
print $fh "\x{110000}", "\n";
close $fh;
EXPECT
+########
+# NAME Case change crosses 255/256 under non-UTF8 locale
+require '../loc_tools.pl';
+unless (locales_enabled('LC_CTYPE')) {
+ print("SKIPPED\n# locales not available\n"),exit;
+}
+eval { require POSIX; POSIX->import("locale_h") };
+if ($@) {
+ print("SKIPPED\n# no POSIX\n"),exit;
+}
+use warnings 'locale';
+use feature 'fc';
+use locale;
+setlocale(&POSIX::LC_CTYPE, "C");
+my $a;
+$a = lc("\x{178}");
+$a = fc("\x{1E9E}");
+$a = fc("\x{FB05}");
+$a = uc("\x{FB00}");
+$a = ucfirst("\x{149}");
+$a = lcfirst("\x{178}");
+no warnings 'locale';
+$a = lc("\x{178}");
+$a = fc("\x{1E9E}");
+$a = fc("\x{FB05}");
+$a = uc("\x{FB00}");
+$a = ucfirst("\x{149}");
+$a = lcfirst("\x{178}");
+EXPECT
+Can't do lc("\x{178}") on non-UTF-8 locale; resolved to "\x{178}". at - line 14.
+Can't do fc("\x{1E9E}") on non-UTF-8 locale; resolved to "\x{17F}\x{17F}". at - line 15.
+Can't do fc("\x{FB05}") on non-UTF-8 locale; resolved to "\x{FB06}". at - line 16.
+Can't do uc("\x{FB00}") on non-UTF-8 locale; resolved to "\x{FB00}". at - line 17.
+Can't do ucfirst("\x{149}") on non-UTF-8 locale; resolved to "\x{149}". at - line 18.
+Can't do lcfirst("\x{178}") on non-UTF-8 locale; resolved to "\x{178}". at - line 19.
+########
+# NAME Wide character in non-UTF-8 locale
+require '../loc_tools.pl';
+unless (locales_enabled('LC_CTYPE')) {
+ print("SKIPPED\n# locales not available\n"),exit;
+}
+eval { require POSIX; POSIX->import("locale_h") };
+if ($@) {
+ print("SKIPPED\n# no POSIX\n"),exit;
+}
+use warnings 'locale';
+use feature 'fc';
+use locale;
+setlocale(&POSIX::LC_CTYPE, "C");
+my $a;
+$a = lc("\x{100}");
+$a = lcfirst("\x{101}");
+$a = fc("\x{102}");
+$a = uc("\x{103}");
+$a = ucfirst("\x{104}");
+no warnings 'locale';
+$a = lc("\x{100}");
+$a = lcfirst("\x{101}");
+$a = fc("\x{102}");
+$a = uc("\x{103}");
+$a = ucfirst("\x{104}");
+EXPECT
+Wide character (U+100) in lc at - line 14.
+Wide character (U+101) in lcfirst at - line 15.
+Wide character (U+102) in fc at - line 16.
+Wide character (U+103) in uc at - line 17.
+Wide character (U+104) in ucfirst at - line 18.
+########
+# NAME Wide character in UTF-8 locale
+require '../loc_tools.pl';
+unless (locales_enabled('LC_CTYPE')) {
+ print("SKIPPED\n# locales not available\n"),exit;
+}
+eval { require POSIX; POSIX->import("locale_h") };
+if ($@) {
+ print("SKIPPED\n# no POSIX\n"),exit;
+}
+my @utf8_locales = find_utf8_ctype_locale();
+unless (@utf8_locales) {
+ print("SKIPPED\n# no UTF-8 locales\n"),exit;
+}
+use warnings 'locale';
+use feature 'fc';
+use locale;
+setlocale(&POSIX::LC_CTYPE, $utf8_locales[0]);
+my $a;
+$a = lc("\x{100}");
+$a = lcfirst("\x{101}");
+$a = fc("\x{102}");
+$a = uc("\x{103}");
+$a = ucfirst("\x{104}");
+EXPECT
+########
+# NAME Deprecation of too-large code points
+require "../test.pl";
+use warnings 'non_unicode';
+my $max_cp = ~0 >> 1;
+my $max_char = chr $max_cp;
+my $to_warn_cp = $max_cp + 1;
+my $to_warn_char = chr $to_warn_cp;
+$max_char =~ /[\x{110000}\P{Unassigned}]/;
+$to_warn_char =~ /[\x{110000}\P{Unassigned}]/;
+my $temp = qr/$max_char/;
+$temp = qr/$to_warn_char/;
+$temp = uc($max_char);
+$temp = uc($to_warn_char);
+my $file = tempfile();
+open(my $fh, "+>:utf8", $file);
+print $fh $max_char, "\n";
+print $fh $to_warn_char, "\n";
+close $fh;
+EXPECT
+OPTION regex
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 in pattern match \(m//\) at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 in regexp compilation at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 in regexp compilation at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 in regexp compilation at - line \d+.
+Operation "uc" returns its argument for non-Unicode code point 0x7F+ at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 in uc at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 at - line \d+.
+Operation "uc" returns its argument for non-Unicode code point 0x80+ at - line \d+.
+Code point 0x7F+ is not Unicode, may not be portable in print at - line \d+.
+Use of code point 0x80+ is deprecated; the permissible max is 0x7F+\. This will be fatal in Perl 5\.28 in print at - line \d+.
+########
+# NAME [perl #127262]
+BEGIN{
+ if (ord('A') == 193) {
+ print "SKIPPED\n# ebcdic platforms generates different Malformed UTF-8 warnings.";
+ exit 0;
+ }
+ use Config;
+ unless ($Double{double_style_ieee}) {
+ print "SKIPPED\n# non-IEEE fp range.";
+ exit 0;
+ }
+{};$^H=eval'2**400'}Â
+EXPECT
+Malformed UTF-8 character: \xc2\x0a (unexpected non-continuation byte 0x0a, immediately after start byte 0xc2; need 2 bytes, got 1) at - line 11.
https://perl5.git.perl.org / perl5.git / blobdiff