diff options
| author | Chris 'BinGOs' Williams <chris@bingosnet.co.uk> | 2017-11-13 13:45:36 +0000 |
|---|---|---|
| committer | Chris 'BinGOs' Williams <chris@bingosnet.co.uk> | 2017-11-13 15:16:12 +0000 |
| commit | eaecde9a0a4918a42c66b153f8da8230a67b3ae5 (patch) | |
| tree | 4042a66a8778b1ccc2a1495d9ae5fb03df254561 /cpan/Unicode-Collate | |
| parent | a6509d2bd0745438635bad41675dbe33268ebf4f (diff) | |
| download | perl-eaecde9a0a4918a42c66b153f8da8230a67b3ae5.tar.gz | |
Update Unicode-Collate to CPAN version 1.23
[DELTA]
1.23 Mon Nov 13 19:10:28 2017
- Now UCA_Version 36 (for Unicode 10.0.0) is supported.
* But the default UCA_Version is still 34.
- added nushu.t in t.
1.22 Sat Nov 11 10:53:35 2017
- internal: someone suggests using 'exists' for checking the truth of
$collator->{mapping}{$variable} and $collator->{maxlength}{$variable},
where $variable may stand for codepoints whose mapping is not defined;
though such a problem was not reproduced on my environment.
Diffstat (limited to 'cpan/Unicode-Collate')
107 files changed, 303 insertions, 152 deletions
diff --git a/cpan/Unicode-Collate/Collate.pm b/cpan/Unicode-Collate/Collate.pm index e61ffccbf7..e572e7cb22 100644 --- a/cpan/Unicode-Collate/Collate.pm +++ b/cpan/Unicode-Collate/Collate.pm @@ -17,7 +17,7 @@ use File::Spec; no warnings 'utf8'; -our $VERSION = '1.21'; +our $VERSION = '1.23'; our $PACKAGE = __PACKAGE__; ### begin XS only ### @@ -191,6 +191,7 @@ my %DerivCode = ( 30 => \&_derivCE_24, # 30 == 24 32 => \&_derivCE_32, 34 => \&_derivCE_34, + 36 => \&_derivCE_36, ); sub checkCollator { @@ -440,13 +441,17 @@ sub parseEntry # if and only if "all" CEs are [.0000.0000.0000]. } + # mapping: be an array ref or not exists (any false value is disallowed) $self->{mapping}{$entry} = $is_L3_ignorable ? [] : \@key; + # maxlength: be more than 1 or not exists (any false value is disallowed) if (@uv > 1) { if (!$self->{maxlength}{$uv[0]} || $self->{maxlength}{$uv[0]} < @uv) { $self->{maxlength}{$uv[0]} = @uv; } } + + # contraction: be 1 or not exists (any false value is disallowed) while (@uv > 2) { pop @uv; my $fake_entry = join(CODE_SEP, @uv); # in JCPS @@ -515,7 +520,7 @@ sub splitEnt if ($vers <= 20 && _isIllegal($src[$i])) { $src[$i] = undef; } elsif ($ver9) { - $src[$i] = undef if $map->{ $src[$i] } + $src[$i] = undef if exists $map->{ $src[$i] } ? @{ $map->{ $src[$i] } } == 0 : $uXS && _ignorable_simple($src[$i]); ### XS only } @@ -535,7 +540,7 @@ sub splitEnt my $i_orig = $i; # find contraction - if ($max->{$jcps}) { + if (exists $max->{$jcps}) { my $temp_jcps = $jcps; my $jcpsLen = 1; my $maxLen = $max->{$jcps}; @@ -544,7 +549,7 @@ sub splitEnt next if ! defined $src[$p]; $temp_jcps .= CODE_SEP . $src[$p]; $jcpsLen++; - if ($map->{$temp_jcps}) { + if (exists $map->{$temp_jcps}) { $jcps = $temp_jcps; $i = $p; } @@ -571,7 +576,7 @@ sub splitEnt last unless $curCC; my $tail = CODE_SEP . $src[$p]; - if ($preCC != $curCC && $map->{$jcps.$tail}) { + if ($preCC != $curCC && exists $map->{$jcps.$tail}) { $jcps .= $tail; push @out, $p; } else { @@ -580,8 +585,9 @@ sub splitEnt next if !$long; - if ($preCC_uc != $curCC && ($map->{$jcps_uc.$tail} || - $cont->{$jcps_uc.$tail})) { + if ($preCC_uc != $curCC && + (exists $map->{$jcps_uc.$tail} || + exists $cont->{$jcps_uc.$tail})) { $jcps_uc .= $tail; push @out_uc, $p; } else { @@ -589,7 +595,7 @@ sub splitEnt } } - if (@out_uc && $map->{$jcps_uc}) { + if (@out_uc && exists $map->{$jcps_uc}) { $jcps = $jcps_uc; $src[$_] = undef for @out_uc; } else { @@ -599,7 +605,7 @@ sub splitEnt } # skip completely ignorable - if ($map->{$jcps} ? @{ $map->{$jcps} } == 0 : + if (exists $map->{$jcps} ? @{ $map->{$jcps} } == 0 : $uXS && $jcps !~ /;/ && _ignorable_simple($jcps)) { ### XS only if ($wLen && @buf) { $buf[-1][2] = $i + 1; @@ -648,7 +654,7 @@ sub getWt $u = 0xFFFD if $u !~ /;/ && 0x10FFFF < $u && !$out; my @ce; - if ($map->{$u}) { + if (exists $map->{$u}) { @ce = @{ $map->{$u} }; # $u may be a contraction ### begin XS only ### } elsif ($uXS && _exists_simple($u)) { @@ -666,27 +672,27 @@ sub getWt if (@decH == 2) { my $contract = join(CODE_SEP, @decH); - @decH = ($contract) if $map->{$contract}; + @decH = ($contract) if exists $map->{$contract}; } else { # must be <@decH == 3> - if ($max->{$decH[0]}) { + if (exists $max->{$decH[0]}) { my $contract = join(CODE_SEP, @decH); - if ($map->{$contract}) { + if (exists $map->{$contract}) { @decH = ($contract); } else { $contract = join(CODE_SEP, @decH[0,1]); - $map->{$contract} and @decH = ($contract, $decH[2]); + exists $map->{$contract} and @decH = ($contract, $decH[2]); } # even if V's ignorable, LT contraction is not supported. # If such a situation were required, NFD should be used. } - if (@decH == 3 && $max->{$decH[1]}) { + if (@decH == 3 && exists $max->{$decH[1]}) { my $contract = join(CODE_SEP, @decH[1,2]); - $map->{$contract} and @decH = ($decH[0], $contract); + exists $map->{$contract} and @decH = ($decH[0], $contract); } } @ce = map({ - $map->{$_} ? @{ $map->{$_} } : + exists $map->{$_} ? @{ $map->{$_} } : $uXS && _exists_simple($_) ? _fetch_simple($_) : ### XS only $der->($_); } @decH); @@ -1117,6 +1123,7 @@ The following revisions are supported. The default is 34. 30 7.0.0 7.0.0 (7.0.0) 32 8.0.0 8.0.0 (8.0.0) 34 9.0.0 9.0.0 (9.0.0) + 36 10.0.0 10.0.0(10.0.0) * See below for C<long_contraction> with C<UCA_Version> 22 and 24. @@ -1457,12 +1464,14 @@ those in the CJK Unified Ideographs Extension A etc. U+4E00..U+9FCB if UCA_Version is 20 or 22. U+4E00..U+9FCC if UCA_Version is 24 to 30. U+4E00..U+9FD5 if UCA_Version is 32 or 34. + U+4E00..U+9FEA if UCA_Version is 36. In the CJK Unified Ideographs Extension blocks: Ext.A (U+3400..U+4DB5) and Ext.B (U+20000..U+2A6D6) in any UCA_Version. Ext.C (U+2A700..U+2B734) if UCA_Version is 20 or later. Ext.D (U+2B740..U+2B81D) if UCA_Version is 22 or later. Ext.E (U+2B820..U+2CEA1) if UCA_Version is 32 or later. + Ext.F (U+2CEB0..U+2EBE0) if UCA_Version is 36. Through C<overrideCJK>, ordering of CJK unified ideographs (including extensions) can be overridden. diff --git a/cpan/Unicode-Collate/Collate.xs b/cpan/Unicode-Collate/Collate.xs index 0838f45dc8..ac57b47971 100644 --- a/cpan/Unicode-Collate/Collate.xs +++ b/cpan/Unicode-Collate/Collate.xs @@ -52,11 +52,13 @@ #define CJK_UidIni (0x4E00) #define CJK_UidFin (0x9FA5) -#define CJK_UidF41 (0x9FBB) -#define CJK_UidF51 (0x9FC3) -#define CJK_UidF52 (0x9FCB) -#define CJK_UidF61 (0x9FCC) -#define CJK_UidF80 (0x9FD5) +#define CJK_UidF41 (0x9FBB) /* Unicode 4.1 */ +#define CJK_UidF51 (0x9FC3) /* Unicode 5.1 */ +#define CJK_UidF52 (0x9FCB) /* Unicode 5.2 */ +#define CJK_UidF61 (0x9FCC) /* Unicode 6.1 */ +#define CJK_UidF80 (0x9FD5) /* Unicode 8.0 */ +#define CJK_UidF100 (0x9FEA) /* Unicode 10.0 */ + #define CJK_ExtAIni (0x3400) /* Unicode 3.0 */ #define CJK_ExtAFin (0x4DB5) /* Unicode 3.0 */ #define CJK_ExtBIni (0x20000) /* Unicode 3.1 */ @@ -67,6 +69,8 @@ #define CJK_ExtDFin (0x2B81D) /* Unicode 6.0 */ #define CJK_ExtEIni (0x2B820) /* Unicode 8.0 */ #define CJK_ExtEFin (0x2CEA1) /* Unicode 8.0 */ +#define CJK_ExtFIni (0x2CEB0) /* Unicode 10.0 */ +#define CJK_ExtFFin (0x2EBE0) /* Unicode 10.0 */ #define CJK_CompIni (0xFA0E) #define CJK_CompFin (0xFA29) @@ -78,6 +82,8 @@ static const STDCHAR UnifiedCompat[] = { #define TangIdeoFin (0x187EC) /* Unicode 9.0 */ #define TangCompIni (0x18800) /* Unicode 9.0 */ #define TangCompFin (0x18AF2) /* Unicode 9.0 */ +#define NushuIni (0x1B170) /* Unicode 10.0 */ +#define NushuFin (0x1B2FB) /* Unicode 10.0 */ #define codeRange(bcode, ecode) ((bcode) <= code && code <= (ecode)) @@ -276,28 +282,35 @@ _derivCE_9 (code) _derivCE_24 = 5 _derivCE_32 = 6 _derivCE_34 = 7 + _derivCE_36 = 8 PREINIT: UV base, aaaa, bbbb; U8 a[VCE_Length + 1] = "\x00\x00\x00\x00\x00\x00\x00\x00\x00"; U8 b[VCE_Length + 1] = "\x00\x00\x00\x00\x00\x00\x00\x00\x00"; - bool basic_unified = 0, tangut = 0; + bool basic_unified = 0, tangut = 0, nushu = 0; PPCODE: if (codeRange(CJK_UidIni, CJK_CompFin)) { if (codeRange(CJK_CompIni, CJK_CompFin)) basic_unified = (bool)UnifiedCompat[code - CJK_CompIni]; else - basic_unified = (ix >= 6 ? (code <= CJK_UidF80) : + basic_unified = (ix >= 8 ? (code <= CJK_UidF100) : + ix >= 6 ? (code <= CJK_UidF80) : ix == 5 ? (code <= CJK_UidF61) : ix >= 3 ? (code <= CJK_UidF52) : ix == 2 ? (code <= CJK_UidF51) : ix == 1 ? (code <= CJK_UidF41) : (code <= CJK_UidFin)); - } else if (ix >= 7) { - tangut = (codeRange(TangIdeoIni, TangIdeoFin) || - codeRange(TangCompIni, TangCompFin)); + } else { + if (ix >= 7) + tangut = (codeRange(TangIdeoIni, TangIdeoFin) || + codeRange(TangCompIni, TangCompFin)); + if (ix >= 8) + nushu = (codeRange(NushuIni, NushuFin)); } base = tangut ? 0xFB00 : + nushu + ? 0xFB01 : basic_unified ? 0xFB40 : /* CJK */ ((codeRange(CJK_ExtAIni, CJK_ExtAFin)) @@ -308,11 +321,14 @@ _derivCE_9 (code) || (ix >= 4 && codeRange(CJK_ExtDIni, CJK_ExtDFin)) || - (ix >= 6 && codeRange(CJK_ExtEIni, CJK_ExtEFin))) + (ix >= 6 && codeRange(CJK_ExtEIni, CJK_ExtEFin)) + || + (ix >= 8 && codeRange(CJK_ExtFIni, CJK_ExtFFin))) ? 0xFB80 /* CJK ext. */ : 0xFBC0; /* others */ - aaaa = tangut ? base : base + (code >> 15); - bbbb = (tangut ? (code - TangIdeoIni) : (code & 0x7FFF)) | 0x8000; + aaaa = tangut || nushu ? base : base + (code >> 15); + bbbb = (tangut ? (code - TangIdeoIni) : + nushu ? (code - NushuIni) : (code & 0x7FFF)) | 0x8000; a[1] = (U8)(aaaa >> 8); a[2] = (U8)(aaaa & 0xFF); b[1] = (U8)(bbbb >> 8); @@ -373,7 +389,8 @@ _isUIdeo (code, uca_vers) if (codeRange(CJK_CompIni, CJK_CompFin)) basic_unified = (bool)UnifiedCompat[code - CJK_CompIni]; else - basic_unified = (uca_vers >= 32 ? (code <= CJK_UidF80) : + basic_unified = (uca_vers >= 36 ? (code <= CJK_UidF100) : + uca_vers >= 32 ? (code <= CJK_UidF80) : uca_vers >= 24 ? (code <= CJK_UidF61) : uca_vers >= 20 ? (code <= CJK_UidF52) : uca_vers >= 18 ? (code <= CJK_UidF51) : @@ -392,6 +409,8 @@ _isUIdeo (code, uca_vers) (uca_vers >= 22 && codeRange(CJK_ExtDIni, CJK_ExtDFin)) || (uca_vers >= 32 && codeRange(CJK_ExtEIni, CJK_ExtEFin)) + || + (uca_vers >= 36 && codeRange(CJK_ExtFIni, CJK_ExtFFin)) ); OUTPUT: RETVAL @@ -560,6 +579,7 @@ varCE (self, vce) U8 *a, *v, *d; STRLEN alen, vlen; bool ig_l2; + IV uca_vers; UV totwt; CODE: if (SvROK(self) && SvTYPE(SvRV(self)) == SVt_PVHV) @@ -604,8 +624,18 @@ varCE (self, vce) d[7] = d[1]; /* wt level 1 to 4 */ d[8] = d[2]; } else { - d[7] = (U8)(Shift4Wt >> 8); - d[8] = (U8)(Shift4Wt & 0xFF); + svp = hv_fetch(selfHV, "UCA_Version", 11, FALSE); + if (!svp) + croak("Panic: no $self->{UCA_Version} in varCE"); + uca_vers = SvIV(*svp); + + /* completely ignorable or the second derived CE */ + if (uca_vers >= 36 && d[3] + d[4] + d[5] + d[6] == 0) { + d[7] = d[8] = '\0'; + } else { + d[7] = (U8)(Shift4Wt >> 8); + d[8] = (U8)(Shift4Wt & 0xFF); + } } } else { /* shift-trimmed or completely ignorable */ d[7] = d[8] = '\0'; diff --git a/cpan/Unicode-Collate/Collate/CJK/Big5.pm b/cpan/Unicode-Collate/Collate/CJK/Big5.pm index e430dbac3e..2fd7ac16c1 100644 --- a/cpan/Unicode-Collate/Collate/CJK/Big5.pm +++ b/cpan/Unicode-Collate/Collate/CJK/Big5.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %u2p; my $wt = 0x8000; diff --git a/cpan/Unicode-Collate/Collate/CJK/GB2312.pm b/cpan/Unicode-Collate/Collate/CJK/GB2312.pm index 094bb550ee..6b593c1d41 100644 --- a/cpan/Unicode-Collate/Collate/CJK/GB2312.pm +++ b/cpan/Unicode-Collate/Collate/CJK/GB2312.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %u2p; my $wt = 0x8000; diff --git a/cpan/Unicode-Collate/Collate/CJK/JISX0208.pm b/cpan/Unicode-Collate/Collate/CJK/JISX0208.pm index d4624bdeea..df9c38cd38 100644 --- a/cpan/Unicode-Collate/Collate/CJK/JISX0208.pm +++ b/cpan/Unicode-Collate/Collate/CJK/JISX0208.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %u2p; my $wt = 0x8000; diff --git a/cpan/Unicode-Collate/Collate/CJK/Korean.pm b/cpan/Unicode-Collate/Collate/CJK/Korean.pm index 7d2d52affe..7e69d0cd83 100644 --- a/cpan/Unicode-Collate/Collate/CJK/Korean.pm +++ b/cpan/Unicode-Collate/Collate/CJK/Korean.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %jamo2prim = ( '1100', 0x3BF5, '1101', 0x3BF6, '1102', 0x3BF7, '1103', 0x3BF8, diff --git a/cpan/Unicode-Collate/Collate/CJK/Pinyin.pm b/cpan/Unicode-Collate/Collate/CJK/Pinyin.pm index 4f3a5db01b..75524af7d0 100644 --- a/cpan/Unicode-Collate/Collate/CJK/Pinyin.pm +++ b/cpan/Unicode-Collate/Collate/CJK/Pinyin.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %u2p; my $wt = 0x8000; diff --git a/cpan/Unicode-Collate/Collate/CJK/Stroke.pm b/cpan/Unicode-Collate/Collate/CJK/Stroke.pm index e6ba88788e..ac74667369 100644 --- a/cpan/Unicode-Collate/Collate/CJK/Stroke.pm +++ b/cpan/Unicode-Collate/Collate/CJK/Stroke.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %u2p; my $wt = 0x8000; diff --git a/cpan/Unicode-Collate/Collate/CJK/Zhuyin.pm b/cpan/Unicode-Collate/Collate/CJK/Zhuyin.pm index 2dbd97a560..e82b234c6e 100644 --- a/cpan/Unicode-Collate/Collate/CJK/Zhuyin.pm +++ b/cpan/Unicode-Collate/Collate/CJK/Zhuyin.pm @@ -4,7 +4,7 @@ use 5.006; use strict; use warnings; -our $VERSION = '1.21'; +our $VERSION = '1.23'; my %u2p; my $wt = 0x8000; diff --git a/cpan/Unicode-Collate/Collate/Locale.pm b/cpan/Unicode-Collate/Collate/Locale.pm index 3de45c3b49..0bde742b16 100644 --- a/cpan/Unicode-Collate/Collate/Locale.pm +++ b/cpan/Unicode-Collate/Collate/Locale.pm @@ -5,7 +5,7 @@ use warnings; use Carp; use base qw(Unicode::Collate); -our $VERSION = '1.21'; +our $VERSION = '1.23'; my $PL_EXT = '.pl'; diff --git a/cpan/Unicode-Collate/Collate/Locale/af.pl b/cpan/Unicode-Collate/Collate/Locale/af.pl index 7713a25201..88da28a952 100644 --- a/cpan/Unicode-Collate/Collate/Locale/af.pl +++ b/cpan/Unicode-Collate/Collate/Locale/af.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0149 ; [.1DB9.0020.0009] # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE ENTRY diff --git a/cpan/Unicode-Collate/Collate/Locale/ar.pl b/cpan/Unicode-Collate/Collate/Locale/ar.pl index 6cf9e189e2..31bb2e574d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ar.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ar.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0629 ; [.231D.0021.0002] # ARABIC LETTER TEH MARBUTA FE94 ; [.231D.0021.0019] # ARABIC LETTER TEH MARBUTA FINAL FORM diff --git a/cpan/Unicode-Collate/Collate/Locale/as.pl b/cpan/Unicode-Collate/Collate/Locale/as.pl index 768779747a..ffcb2dc848 100644 --- a/cpan/Unicode-Collate/Collate/Locale/as.pl +++ b/cpan/Unicode-Collate/Collate/Locale/as.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0982 ; [.26CD.0020.0002][.FFF1.0000.0000] # BENGALI SIGN ANUSVARA 0981 ; [.26CD.0020.0002][.FFF2.0000.0000] # BENGALI SIGN CANDRABINDU diff --git a/cpan/Unicode-Collate/Collate/Locale/az.pl b/cpan/Unicode-Collate/Collate/Locale/az.pl index d8fecacf1e..ec68857993 100644 --- a/cpan/Unicode-Collate/Collate/Locale/az.pl +++ b/cpan/Unicode-Collate/Collate/Locale/az.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # schwa doesn't require tailoring entry => <<'ENTRY', # for DUCET v9.0.0 00E7 ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CEDILLA diff --git a/cpan/Unicode-Collate/Collate/Locale/be.pl b/cpan/Unicode-Collate/Collate/Locale/be.pl index a64ba84ad9..872fa0047d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/be.pl +++ b/cpan/Unicode-Collate/Collate/Locale/be.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0451 ; [.205B.0020.0002] # CYRILLIC SMALL LETTER IO 0435 0308 ; [.205B.0020.0002] # CYRILLIC SMALL LETTER IO diff --git a/cpan/Unicode-Collate/Collate/Locale/bn.pl b/cpan/Unicode-Collate/Collate/Locale/bn.pl index 51299688d0..2fd8eba702 100644 --- a/cpan/Unicode-Collate/Collate/Locale/bn.pl +++ b/cpan/Unicode-Collate/Collate/Locale/bn.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0982 ; [.26CD.0020.0002][.FFF1.0000.0000] # BENGALI SIGN ANUSVARA 0983 ; [.26CD.0020.0002][.FFF2.0000.0000] # BENGALI SIGN VISARGA diff --git a/cpan/Unicode-Collate/Collate/Locale/ca.pl b/cpan/Unicode-Collate/Collate/Locale/ca.pl index e5b69290c7..defe6b9ae4 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ca.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ca.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0063 0068 ; [.1C7B.0020.0002] # <LATIN SMALL LETTER C, LATIN SMALL LETTER H> 0063 0048 ; [.1C7B.0020.0007][.0000.0000.0002] # <LATIN SMALL LETTER C, LATIN CAPITAL LETTER H> diff --git a/cpan/Unicode-Collate/Collate/Locale/cs.pl b/cpan/Unicode-Collate/Collate/Locale/cs.pl index 04e6d20f29..17f4cc8b1c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/cs.pl +++ b/cpan/Unicode-Collate/Collate/Locale/cs.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 010D ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/cy.pl b/cpan/Unicode-Collate/Collate/Locale/cy.pl index 0d36a63a40..67b4998cf5 100644 --- a/cpan/Unicode-Collate/Collate/Locale/cy.pl +++ b/cpan/Unicode-Collate/Collate/Locale/cy.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0063 0068 ; [.1C7B.0020.0002] # <LATIN SMALL LETTER C, LATIN SMALL LETTER H> 0043 0068 ; [.1C7B.0020.0007] # <LATIN CAPITAL LETTER C, LATIN SMALL LETTER H> diff --git a/cpan/Unicode-Collate/Collate/Locale/da.pl b/cpan/Unicode-Collate/Collate/Locale/da.pl index 028655871a..34f6cec6d0 100644 --- a/cpan/Unicode-Collate/Collate/Locale/da.pl +++ b/cpan/Unicode-Collate/Collate/Locale/da.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, upper_before_lower => 1, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/de_at_ph.pl b/cpan/Unicode-Collate/Collate/Locale/de_at_ph.pl index f3fefdfd62..ccb7daa92e 100644 --- a/cpan/Unicode-Collate/Collate/Locale/de_at_ph.pl +++ b/cpan/Unicode-Collate/Collate/Locale/de_at_ph.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E4 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH DIAERESIS 0061 0308 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH DIAERESIS diff --git a/cpan/Unicode-Collate/Collate/Locale/de_phone.pl b/cpan/Unicode-Collate/Collate/Locale/de_phone.pl index 1e085dac6e..e3357d38e0 100644 --- a/cpan/Unicode-Collate/Collate/Locale/de_phone.pl +++ b/cpan/Unicode-Collate/Collate/Locale/de_phone.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E4 ; [.1C47.0021.0002][.1CAA.0021.0002] # LATIN SMALL LETTER A WITH DIAERESIS 0061 0308 ; [.1C47.0021.0002][.1CAA.0021.0002] # LATIN SMALL LETTER A WITH DIAERESIS diff --git a/cpan/Unicode-Collate/Collate/Locale/dsb.pl b/cpan/Unicode-Collate/Collate/Locale/dsb.pl index 7ee380f692..f6d3fbd0e0 100644 --- a/cpan/Unicode-Collate/Collate/Locale/dsb.pl +++ b/cpan/Unicode-Collate/Collate/Locale/dsb.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 010D ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/ee.pl b/cpan/Unicode-Collate/Collate/Locale/ee.pl index b701bce57a..a1b5401e0c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ee.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ee.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # d-tail, open-e, f-hook, gamma, eng, open-o, v-hook don't require tailoring entry => <<'ENTRY', # for DUCET v9.0.0 0302 ; [.0000.0029.0002] # COMBINING CIRCUMFLEX ACCENT diff --git a/cpan/Unicode-Collate/Collate/Locale/eo.pl b/cpan/Unicode-Collate/Collate/Locale/eo.pl index 05786c89a1..19236515b9 100644 --- a/cpan/Unicode-Collate/Collate/Locale/eo.pl +++ b/cpan/Unicode-Collate/Collate/Locale/eo.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0109 ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CIRCUMFLEX 0063 0302 ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CIRCUMFLEX diff --git a/cpan/Unicode-Collate/Collate/Locale/es.pl b/cpan/Unicode-Collate/Collate/Locale/es.pl index 3c04f6e7ec..3d2a947f92 100644 --- a/cpan/Unicode-Collate/Collate/Locale/es.pl +++ b/cpan/Unicode-Collate/Collate/Locale/es.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00F1 ; [.1DBA.0020.0002] # LATIN SMALL LETTER N WITH TILDE 006E 0303 ; [.1DBA.0020.0002] # LATIN SMALL LETTER N WITH TILDE diff --git a/cpan/Unicode-Collate/Collate/Locale/es_trad.pl b/cpan/Unicode-Collate/Collate/Locale/es_trad.pl index 5c72166f65..42add428cf 100644 --- a/cpan/Unicode-Collate/Collate/Locale/es_trad.pl +++ b/cpan/Unicode-Collate/Collate/Locale/es_trad.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0063 0068 ; [.1C7B.0020.0002] # <LATIN SMALL LETTER C, LATIN SMALL LETTER H> 0043 0068 ; [.1C7B.0020.0007] # <LATIN CAPITAL LETTER C, LATIN SMALL LETTER H> diff --git a/cpan/Unicode-Collate/Collate/Locale/et.pl b/cpan/Unicode-Collate/Collate/Locale/et.pl index 03fd7fa29a..2f300ff5c1 100644 --- a/cpan/Unicode-Collate/Collate/Locale/et.pl +++ b/cpan/Unicode-Collate/Collate/Locale/et.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0161 ; [.1E92.0020.0002] # LATIN SMALL LETTER S WITH CARON 0073 030C ; [.1E92.0020.0002] # LATIN SMALL LETTER S WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/fa.pl b/cpan/Unicode-Collate/Collate/Locale/fa.pl index 765e289338..23ea1b2999 100644 --- a/cpan/Unicode-Collate/Collate/Locale/fa.pl +++ b/cpan/Unicode-Collate/Collate/Locale/fa.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0650 ; [.0000.0077.0002] # ARABIC KASRA 064B ; [.0000.007B.0002] # ARABIC FATHATAN diff --git a/cpan/Unicode-Collate/Collate/Locale/fi.pl b/cpan/Unicode-Collate/Collate/Locale/fi.pl index de271b4ef3..ef14df5c55 100644 --- a/cpan/Unicode-Collate/Collate/Locale/fi.pl +++ b/cpan/Unicode-Collate/Collate/Locale/fi.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # in cldr test/fi.xml why x{110}x < xdx though xd < x{110} ? entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002][.0000.0039.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/fi_phone.pl b/cpan/Unicode-Collate/Collate/Locale/fi_phone.pl index fbd5ab58eb..45d4fbcbf3 100644 --- a/cpan/Unicode-Collate/Collate/Locale/fi_phone.pl +++ b/cpan/Unicode-Collate/Collate/Locale/fi_phone.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # in cldr test/fi.xml why x{110}x < xdx though xd < x{110} ? entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002][.0000.0039.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/fil.pl b/cpan/Unicode-Collate/Collate/Locale/fil.pl index 249e596ae3..ac0ace0e1b 100644 --- a/cpan/Unicode-Collate/Collate/Locale/fil.pl +++ b/cpan/Unicode-Collate/Collate/Locale/fil.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00F1 ; [.1DBA.0020.0002] # LATIN SMALL LETTER N WITH TILDE 006E 0303 ; [.1DBA.0020.0002] # LATIN SMALL LETTER N WITH TILDE diff --git a/cpan/Unicode-Collate/Collate/Locale/fo.pl b/cpan/Unicode-Collate/Collate/Locale/fo.pl index 6abbe9f8d5..c11be2c66e 100644 --- a/cpan/Unicode-Collate/Collate/Locale/fo.pl +++ b/cpan/Unicode-Collate/Collate/Locale/fo.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE 0064 0335 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/fr_ca.pl b/cpan/Unicode-Collate/Collate/Locale/fr_ca.pl index 97e08dafe3..f2633d012d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/fr_ca.pl +++ b/cpan/Unicode-Collate/Collate/Locale/fr_ca.pl @@ -1,4 +1,4 @@ +{ - locale_version => 1.21, + locale_version => 1.23, backwards => 2, }; diff --git a/cpan/Unicode-Collate/Collate/Locale/gu.pl b/cpan/Unicode-Collate/Collate/Locale/gu.pl index 1917b4ea70..b83b98a331 100644 --- a/cpan/Unicode-Collate/Collate/Locale/gu.pl +++ b/cpan/Unicode-Collate/Collate/Locale/gu.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0A82 ; [.2739.0020.0002][.FFF1.0000.0000] # GUJARATI SIGN ANUSVARA 0A81 ; [.2739.0021.0002][.FFF1.0000.0000] # GUJARATI SIGN CANDRABINDU diff --git a/cpan/Unicode-Collate/Collate/Locale/ha.pl b/cpan/Unicode-Collate/Collate/Locale/ha.pl index 41dfc512f8..74791959d8 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ha.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ha.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # b-hook, d-hook, k-hook, y-hook don't require tailoring entry => <<'ENTRY', # for DUCET v9.0.0 0073 0068 ; [.1E72.0020.0002] # <LATIN SMALL LETTER S, LATIN SMALL LETTER H> diff --git a/cpan/Unicode-Collate/Collate/Locale/haw.pl b/cpan/Unicode-Collate/Collate/Locale/haw.pl index 0910e0045b..db912174f6 100644 --- a/cpan/Unicode-Collate/Collate/Locale/haw.pl +++ b/cpan/Unicode-Collate/Collate/Locale/haw.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0065 ; [.1C48.0020.0002][.FFF1.0000.0000] # LATIN SMALL LETTER E 0045 ; [.1C48.0020.0008][.FFF1.0000.0000] # LATIN CAPITAL LETTER E diff --git a/cpan/Unicode-Collate/Collate/Locale/he.pl b/cpan/Unicode-Collate/Collate/Locale/he.pl index 44a38341f7..a1acd0ac72 100644 --- a/cpan/Unicode-Collate/Collate/Locale/he.pl +++ b/cpan/Unicode-Collate/Collate/Locale/he.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 05F3 ; [*0305.001F.0002] # HEBREW PUNCTUATION GERESH 05F4 ; [*030C.001F.0002] # HEBREW PUNCTUATION GERSHAYIM diff --git a/cpan/Unicode-Collate/Collate/Locale/hi.pl b/cpan/Unicode-Collate/Collate/Locale/hi.pl index bc6f1bf1f8..ae935fe22e 100644 --- a/cpan/Unicode-Collate/Collate/Locale/hi.pl +++ b/cpan/Unicode-Collate/Collate/Locale/hi.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0902 ; [.265B.0020.0002][.FFF1.0000.0000] # DEVANAGARI SIGN ANUSVARA 0901 ; [.265B.0021.0002][.FFF1.0000.0000] # DEVANAGARI SIGN CANDRABINDU diff --git a/cpan/Unicode-Collate/Collate/Locale/hr.pl b/cpan/Unicode-Collate/Collate/Locale/hr.pl index 53314281e9..28c0b231e8 100644 --- a/cpan/Unicode-Collate/Collate/Locale/hr.pl +++ b/cpan/Unicode-Collate/Collate/Locale/hr.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 010D ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/hu.pl b/cpan/Unicode-Collate/Collate/Locale/hu.pl index 7027ab9ab6..c2686f8ff5 100644 --- a/cpan/Unicode-Collate/Collate/Locale/hu.pl +++ b/cpan/Unicode-Collate/Collate/Locale/hu.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0063 0073 ; [.1C7B.0020.0002] # <LATIN SMALL LETTER C, LATIN SMALL LETTER S> 0063 0053 ; [.1C7B.0020.0007][.0000.0000.0002] # <LATIN SMALL LETTER C, LATIN CAPITAL LETTER S> diff --git a/cpan/Unicode-Collate/Collate/Locale/hy.pl b/cpan/Unicode-Collate/Collate/Locale/hy.pl index 552c7fb149..2edd8cc988 100644 --- a/cpan/Unicode-Collate/Collate/Locale/hy.pl +++ b/cpan/Unicode-Collate/Collate/Locale/hy.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0587 ; [.22B3.0020.0002][.FFF1.0000.0000] # ARMENIAN SMALL LIGATURE ECH YIWN 0584 ; [.22B3.0020.0002][.FFF0.0000.0000] # ARMENIAN SMALL LETTER KEH diff --git a/cpan/Unicode-Collate/Collate/Locale/ig.pl b/cpan/Unicode-Collate/Collate/Locale/ig.pl index c6f252bb9d..47528ccf98 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ig.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ig.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0063 0068 ; [.1C61.0020.0002] # <LATIN SMALL LETTER C, LATIN SMALL LETTER H> 0043 0068 ; [.1C61.0020.0007] # <LATIN CAPITAL LETTER C, LATIN SMALL LETTER H> diff --git a/cpan/Unicode-Collate/Collate/Locale/is.pl b/cpan/Unicode-Collate/Collate/Locale/is.pl index faa588b932..3df7aa4534 100644 --- a/cpan/Unicode-Collate/Collate/Locale/is.pl +++ b/cpan/Unicode-Collate/Collate/Locale/is.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E1 ; [.1C5F.0020.0002] # LATIN SMALL LETTER A WITH ACUTE 0061 0301 ; [.1C5F.0020.0002] # LATIN SMALL LETTER A WITH ACUTE diff --git a/cpan/Unicode-Collate/Collate/Locale/ja.pl b/cpan/Unicode-Collate/Collate/Locale/ja.pl index 5ea4730ad6..26550c402b 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ja.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ja.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::JISX0208; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::JISX0208::weightJISX0208, entry => <<'ENTRY', # for DUCET v9.0.0 30A1 ; [.3D5A.0020.000F.0002] # KATAKANA LETTER SMALL A diff --git a/cpan/Unicode-Collate/Collate/Locale/kk.pl b/cpan/Unicode-Collate/Collate/Locale/kk.pl index 5fb33a11a0..8cea65ca53 100644 --- a/cpan/Unicode-Collate/Collate/Locale/kk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/kk.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0451 ; [.205B.0020.0002] # CYRILLIC SMALL LETTER IO 0435 0308 ; [.205B.0020.0002] # CYRILLIC SMALL LETTER IO diff --git a/cpan/Unicode-Collate/Collate/Locale/kl.pl b/cpan/Unicode-Collate/Collate/Locale/kl.pl index 43c7be2dad..92e547010d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/kl.pl +++ b/cpan/Unicode-Collate/Collate/Locale/kl.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE 0064 0335 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/kn.pl b/cpan/Unicode-Collate/Collate/Locale/kn.pl index a43fa85390..d1969d5094 100644 --- a/cpan/Unicode-Collate/Collate/Locale/kn.pl +++ b/cpan/Unicode-Collate/Collate/Locale/kn.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0C82 ; [.284C.0020.0002][.FFF1.0000.0000] # KANNADA SIGN ANUSVARA 0C83 ; [.284C.0020.0002][.FFF2.0000.0000] # KANNADA SIGN VISARGA diff --git a/cpan/Unicode-Collate/Collate/Locale/ko.pl b/cpan/Unicode-Collate/Collate/Locale/ko.pl index a11a4cb61c..407dea5ffd 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ko.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ko.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::Korean; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::Korean::weightKorean, entry => <<'ENTRY', # for DUCET v9.0.0 F967 ; [.3BFC.0021.0002.4E0D][.3C80.0020.0002] # CJK COMPATIBILITY IDEOGRAPH-F967 diff --git a/cpan/Unicode-Collate/Collate/Locale/kok.pl b/cpan/Unicode-Collate/Collate/Locale/kok.pl index 9cd5b1fd64..b4b87b6282 100644 --- a/cpan/Unicode-Collate/Collate/Locale/kok.pl +++ b/cpan/Unicode-Collate/Collate/Locale/kok.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0902 ; [.265B.0020.0002][.FFF1.0000.0000] # DEVANAGARI SIGN ANUSVARA 0901 ; [.265B.0021.0002][.FFF1.0000.0000] # DEVANAGARI SIGN CANDRABINDU diff --git a/cpan/Unicode-Collate/Collate/Locale/lkt.pl b/cpan/Unicode-Collate/Collate/Locale/lkt.pl index 496655273f..7c066dea72 100644 --- a/cpan/Unicode-Collate/Collate/Locale/lkt.pl +++ b/cpan/Unicode-Collate/Collate/Locale/lkt.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 010D ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/ln.pl b/cpan/Unicode-Collate/Collate/Locale/ln.pl index 441c4a0356..f1e01cc722 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ln.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ln.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 025B ; [.1CAB.0020.0002] # LATIN SMALL LETTER OPEN E 0190 ; [.1CAB.0020.0008] # LATIN CAPITAL LETTER OPEN E diff --git a/cpan/Unicode-Collate/Collate/Locale/lt.pl b/cpan/Unicode-Collate/Collate/Locale/lt.pl index 83c346b709..b5881a2c86 100644 --- a/cpan/Unicode-Collate/Collate/Locale/lt.pl +++ b/cpan/Unicode-Collate/Collate/Locale/lt.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # in cldr test/lt.xml why I-dot-acute > I-dot though i-dot-acute < i-dot ? entry => <<'ENTRY', # for DUCET v9.0.0 0049 0307 ; [.1D32.0020.0008][.0000.002E.0002] # <LATIN CAPITAL LETTER I, COMBINING DOT ABOVE> diff --git a/cpan/Unicode-Collate/Collate/Locale/lv.pl b/cpan/Unicode-Collate/Collate/Locale/lv.pl index 4cd2f257bd..ffe9cdf69c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/lv.pl +++ b/cpan/Unicode-Collate/Collate/Locale/lv.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 010D ; [.1C8E.0020.0002] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.1C8E.0020.0002] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/mk.pl b/cpan/Unicode-Collate/Collate/Locale/mk.pl index 8e9c9543df..95c35f3c8b 100644 --- a/cpan/Unicode-Collate/Collate/Locale/mk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/mk.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, suppress => [0x0418, 0x0438], entry => <<'ENTRY', # for DUCET v9.0.0 0453 ; [.2056.0020.0002] # CYRILLIC SMALL LETTER GJE diff --git a/cpan/Unicode-Collate/Collate/Locale/ml.pl b/cpan/Unicode-Collate/Collate/Locale/ml.pl index cebee507b8..59a6fc1572 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ml.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ml.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0D3D ; [.0000.00C6.0002] # MALAYALAM SIGN AVAGRAHA 0D57 ; [.28CD.0020.0002] # MALAYALAM AU LENGTH MARK diff --git a/cpan/Unicode-Collate/Collate/Locale/mr.pl b/cpan/Unicode-Collate/Collate/Locale/mr.pl index 4a88db46ed..ccd4540b42 100644 --- a/cpan/Unicode-Collate/Collate/Locale/mr.pl +++ b/cpan/Unicode-Collate/Collate/Locale/mr.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0902 ; [.265B.0020.0002][.FFF1.0000.0000] # DEVANAGARI SIGN ANUSVARA 0901 ; [.265B.0021.0002][.FFF1.0000.0000] # DEVANAGARI SIGN CANDRABINDU diff --git a/cpan/Unicode-Collate/Collate/Locale/mt.pl b/cpan/Unicode-Collate/Collate/Locale/mt.pl index e1edfb5337..752dff175d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/mt.pl +++ b/cpan/Unicode-Collate/Collate/Locale/mt.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, upper_before_lower => 1, entry => <<'ENTRY', # for DUCET v9.0.0 010B ; [.1C79.0020.0002] # LATIN SMALL LETTER C WITH DOT ABOVE diff --git a/cpan/Unicode-Collate/Collate/Locale/nb.pl b/cpan/Unicode-Collate/Collate/Locale/nb.pl index f7170c7e77..9e104eb13c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/nb.pl +++ b/cpan/Unicode-Collate/Collate/Locale/nb.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE 0064 0335 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/nn.pl b/cpan/Unicode-Collate/Collate/Locale/nn.pl index f7170c7e77..9e104eb13c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/nn.pl +++ b/cpan/Unicode-Collate/Collate/Locale/nn.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE 0064 0335 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/nso.pl b/cpan/Unicode-Collate/Collate/Locale/nso.pl index db1915b5b3..69c02112a7 100644 --- a/cpan/Unicode-Collate/Collate/Locale/nso.pl +++ b/cpan/Unicode-Collate/Collate/Locale/nso.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00EA ; [.1CAB.0020.0002] # LATIN SMALL LETTER E WITH CIRCUMFLEX 0065 0302 ; [.1CAB.0020.0002] # LATIN SMALL LETTER E WITH CIRCUMFLEX diff --git a/cpan/Unicode-Collate/Collate/Locale/om.pl b/cpan/Unicode-Collate/Collate/Locale/om.pl index c3a1aac219..60e06b4ef3 100644 --- a/cpan/Unicode-Collate/Collate/Locale/om.pl +++ b/cpan/Unicode-Collate/Collate/Locale/om.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0063 0068 ; [.1F22.0020.0002] # <LATIN SMALL LETTER C, LATIN SMALL LETTER H> 0043 0068 ; [.1F22.0020.0007] # <LATIN CAPITAL LETTER C, LATIN SMALL LETTER H> diff --git a/cpan/Unicode-Collate/Collate/Locale/or.pl b/cpan/Unicode-Collate/Collate/Locale/or.pl index a3926ad638..909cf0fd2d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/or.pl +++ b/cpan/Unicode-Collate/Collate/Locale/or.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0B01 ; [.278B.0020.0002][.FFF1.0000.0000] # ORIYA SIGN CANDRABINDU 0B02 ; [.278B.0020.0002][.FFF2.0000.0000] # ORIYA SIGN ANUSVARA diff --git a/cpan/Unicode-Collate/Collate/Locale/pa.pl b/cpan/Unicode-Collate/Collate/Locale/pa.pl index 4d6d7a4c61..a7963cc3dd 100644 --- a/cpan/Unicode-Collate/Collate/Locale/pa.pl +++ b/cpan/Unicode-Collate/Collate/Locale/pa.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0A71 ; [.0000.00C3.0002] # GURMUKHI ADDAK 0A03 ; [.0000.00C2.0002] # GURMUKHI SIGN VISARGA diff --git a/cpan/Unicode-Collate/Collate/Locale/pl.pl b/cpan/Unicode-Collate/Collate/Locale/pl.pl index b12bb78ad4..c2880dc752 100644 --- a/cpan/Unicode-Collate/Collate/Locale/pl.pl +++ b/cpan/Unicode-Collate/Collate/Locale/pl.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0105 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH OGONEK 0061 0328 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH OGONEK diff --git a/cpan/Unicode-Collate/Collate/Locale/ro.pl b/cpan/Unicode-Collate/Collate/Locale/ro.pl index eebf0df435..be2a882421 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ro.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ro.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0103 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH BREVE 0061 0306 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH BREVE diff --git a/cpan/Unicode-Collate/Collate/Locale/sa.pl b/cpan/Unicode-Collate/Collate/Locale/sa.pl index 4a88db46ed..ccd4540b42 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sa.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sa.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0902 ; [.265B.0020.0002][.FFF1.0000.0000] # DEVANAGARI SIGN ANUSVARA 0901 ; [.265B.0021.0002][.FFF1.0000.0000] # DEVANAGARI SIGN CANDRABINDU diff --git a/cpan/Unicode-Collate/Collate/Locale/se.pl b/cpan/Unicode-Collate/Collate/Locale/se.pl index f3966e13a7..d8bfcd76ef 100644 --- a/cpan/Unicode-Collate/Collate/Locale/se.pl +++ b/cpan/Unicode-Collate/Collate/Locale/se.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # eng, g-stroke, t-stroke don't require tailoring entry => <<'ENTRY', # for DUCET v9.0.0 00E1 ; [.1C5F.0020.0002] # LATIN SMALL LETTER A WITH ACUTE diff --git a/cpan/Unicode-Collate/Collate/Locale/si.pl b/cpan/Unicode-Collate/Collate/Locale/si.pl index bbb1742276..e89c65cb01 100644 --- a/cpan/Unicode-Collate/Collate/Locale/si.pl +++ b/cpan/Unicode-Collate/Collate/Locale/si.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0D82 ; [.28E1.0020.0002][.FFF1.0000.0000] # SINHALA SIGN ANUSVARAYA 0D83 ; [.28E1.0020.0002][.FFF2.0000.0000] # SINHALA SIGN VISARGAYA diff --git a/cpan/Unicode-Collate/Collate/Locale/si_dict.pl b/cpan/Unicode-Collate/Collate/Locale/si_dict.pl index a63379e8c6..236512b249 100644 --- a/cpan/Unicode-Collate/Collate/Locale/si_dict.pl +++ b/cpan/Unicode-Collate/Collate/Locale/si_dict.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0D82 ; [.28E1.0020.0002][.FFF1.0000.0000] # SINHALA SIGN ANUSVARAYA 0D83 ; [.28E1.0020.0002][.FFF2.0000.0000] # SINHALA SIGN VISARGAYA diff --git a/cpan/Unicode-Collate/Collate/Locale/sk.pl b/cpan/Unicode-Collate/Collate/Locale/sk.pl index 06da36e62f..3875670bb5 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sk.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E4 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH DIAERESIS 0061 0308 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH DIAERESIS diff --git a/cpan/Unicode-Collate/Collate/Locale/sl.pl b/cpan/Unicode-Collate/Collate/Locale/sl.pl index 9631acf8d9..d7d1bd3e33 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sl.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sl.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 010D ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON 0063 030C ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CARON diff --git a/cpan/Unicode-Collate/Collate/Locale/sq.pl b/cpan/Unicode-Collate/Collate/Locale/sq.pl index 5f70b1b3a8..7fa8224251 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sq.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sq.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E7 ; [.1C8E.0020.0002] # LATIN SMALL LETTER C WITH CEDILLA 0063 0327 ; [.1C8E.0020.0002] # LATIN SMALL LETTER C WITH CEDILLA diff --git a/cpan/Unicode-Collate/Collate/Locale/sr.pl b/cpan/Unicode-Collate/Collate/Locale/sr.pl index 559ccf6d2c..ab970974ee 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sr.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sr.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, suppress => [0x0418, 0x0438], entry => <<'ENTRY', # for DUCET v9.0.0 0439 ; [.2080.0020.0002][.0000.0026.0002] # CYRILLIC SMALL LETTER SHORT I diff --git a/cpan/Unicode-Collate/Collate/Locale/sv.pl b/cpan/Unicode-Collate/Collate/Locale/sv.pl index 605656f4fa..b9d563010d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sv.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sv.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE 0064 0335 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl b/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl index 6325de0012..496e7544ad 100644 --- a/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl +++ b/cpan/Unicode-Collate/Collate/Locale/sv_refo.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0111 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE 0064 0335 ; [.1C8F.0021.0002] # LATIN SMALL LETTER D WITH STROKE diff --git a/cpan/Unicode-Collate/Collate/Locale/ta.pl b/cpan/Unicode-Collate/Collate/Locale/ta.pl index c3b3136d54..6f977b0006 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ta.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ta.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0B82 ; [.27CE.0020.0002][.FFF0.0000.0000] # TAMIL SIGN ANUSVARA 0B83 ; [.27CE.0020.0002][.FFF1.0000.0000] # TAMIL SIGN VISARGA diff --git a/cpan/Unicode-Collate/Collate/Locale/te.pl b/cpan/Unicode-Collate/Collate/Locale/te.pl index cfd9e0c656..d1d95fdc72 100644 --- a/cpan/Unicode-Collate/Collate/Locale/te.pl +++ b/cpan/Unicode-Collate/Collate/Locale/te.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0C01 ; [.2802.0020.0002][.FFF1.0000.0000] # TELUGU SIGN CANDRABINDU 0C02 ; [.2802.0020.0002][.FFF2.0000.0000] # TELUGU SIGN ANUSVARA diff --git a/cpan/Unicode-Collate/Collate/Locale/th.pl b/cpan/Unicode-Collate/Collate/Locale/th.pl index f433e203e9..6885adf89d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/th.pl +++ b/cpan/Unicode-Collate/Collate/Locale/th.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, variable => 'shifted', alternate => 'shifted', entry => <<'ENTRY', # for DUCET v9.0.0 diff --git a/cpan/Unicode-Collate/Collate/Locale/tn.pl b/cpan/Unicode-Collate/Collate/Locale/tn.pl index db1915b5b3..69c02112a7 100644 --- a/cpan/Unicode-Collate/Collate/Locale/tn.pl +++ b/cpan/Unicode-Collate/Collate/Locale/tn.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00EA ; [.1CAB.0020.0002] # LATIN SMALL LETTER E WITH CIRCUMFLEX 0065 0302 ; [.1CAB.0020.0002] # LATIN SMALL LETTER E WITH CIRCUMFLEX diff --git a/cpan/Unicode-Collate/Collate/Locale/to.pl b/cpan/Unicode-Collate/Collate/Locale/to.pl index a1a4fafef9..92d65db1c2 100644 --- a/cpan/Unicode-Collate/Collate/Locale/to.pl +++ b/cpan/Unicode-Collate/Collate/Locale/to.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 006E 0067 ; [.1DBA.0020.0002] # <LATIN SMALL LETTER N, LATIN SMALL LETTER G> 004E 0067 ; [.1DBA.0020.0007] # <LATIN CAPITAL LETTER N, LATIN SMALL LETTER G> diff --git a/cpan/Unicode-Collate/Collate/Locale/tr.pl b/cpan/Unicode-Collate/Collate/Locale/tr.pl index 742464d725..ecdd5ea4a5 100644 --- a/cpan/Unicode-Collate/Collate/Locale/tr.pl +++ b/cpan/Unicode-Collate/Collate/Locale/tr.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E7 ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CEDILLA 0063 0327 ; [.1C7B.0020.0002] # LATIN SMALL LETTER C WITH CEDILLA diff --git a/cpan/Unicode-Collate/Collate/Locale/ug_cyrl.pl b/cpan/Unicode-Collate/Collate/Locale/ug_cyrl.pl index 356fa987d0..1760e1d9d2 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ug_cyrl.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ug_cyrl.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 04D9 ; [.205B.0020.0002] # CYRILLIC SMALL LETTER SCHWA 04D8 ; [.205B.0020.0008] # CYRILLIC CAPITAL LETTER SCHWA diff --git a/cpan/Unicode-Collate/Collate/Locale/uk.pl b/cpan/Unicode-Collate/Collate/Locale/uk.pl index 956fd9721d..4327023706 100644 --- a/cpan/Unicode-Collate/Collate/Locale/uk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/uk.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0491 ; [.2037.0020.0002] # CYRILLIC SMALL LETTER GHE WITH UPTURN 0490 ; [.2037.0020.0008] # CYRILLIC CAPITAL LETTER GHE WITH UPTURN diff --git a/cpan/Unicode-Collate/Collate/Locale/ur.pl b/cpan/Unicode-Collate/Collate/Locale/ur.pl index c7a8e4ae49..6c076427de 100644 --- a/cpan/Unicode-Collate/Collate/Locale/ur.pl +++ b/cpan/Unicode-Collate/Collate/Locale/ur.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0623 ; [.230B.0021.0002] # ARABIC LETTER ALEF WITH HAMZA ABOVE 0627 0654 ; [.230B.0021.0002] # ARABIC LETTER ALEF WITH HAMZA ABOVE diff --git a/cpan/Unicode-Collate/Collate/Locale/vi.pl b/cpan/Unicode-Collate/Collate/Locale/vi.pl index 2fc4cd7ea4..66713ac877 100644 --- a/cpan/Unicode-Collate/Collate/Locale/vi.pl +++ b/cpan/Unicode-Collate/Collate/Locale/vi.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # 0306 is not a Vietnamese tone, just to avoid \x{306} eq. to something. entry => <<'ENTRY', # for DUCET v9.0.0 0309 ; [.0000.0026.0002][.0000.00F0.0000] # COMBINING HOOK ABOVE diff --git a/cpan/Unicode-Collate/Collate/Locale/vo.pl b/cpan/Unicode-Collate/Collate/Locale/vo.pl index 2a2ff1e070..5f40776d70 100644 --- a/cpan/Unicode-Collate/Collate/Locale/vo.pl +++ b/cpan/Unicode-Collate/Collate/Locale/vo.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 00E4 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH DIAERESIS 0061 0308 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH DIAERESIS diff --git a/cpan/Unicode-Collate/Collate/Locale/wae.pl b/cpan/Unicode-Collate/Collate/Locale/wae.pl index 075e169f72..2edbc2b17d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/wae.pl +++ b/cpan/Unicode-Collate/Collate/Locale/wae.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0061 0061 ; [.1C47.0020.0002][.0000.0024.0002] # <LATIN SMALL LETTER A, LATIN SMALL LETTER A> 00E4 00E4 ; [.1C47.0020.0002][.0000.002D.0002] # <LATIN SMALL LETTER A WITH DIAERESIS, LATIN SMALL LETTER A WITH DIAERESIS> diff --git a/cpan/Unicode-Collate/Collate/Locale/wo.pl b/cpan/Unicode-Collate/Collate/Locale/wo.pl index 1272e3f10c..4e640d895d 100644 --- a/cpan/Unicode-Collate/Collate/Locale/wo.pl +++ b/cpan/Unicode-Collate/Collate/Locale/wo.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, # eng doesn't require tailoring entry => <<'ENTRY', # for DUCET v9.0.0 00E0 ; [.1C48.0020.0002] # LATIN SMALL LETTER A WITH GRAVE diff --git a/cpan/Unicode-Collate/Collate/Locale/yo.pl b/cpan/Unicode-Collate/Collate/Locale/yo.pl index 0fdb943336..63f39dc622 100644 --- a/cpan/Unicode-Collate/Collate/Locale/yo.pl +++ b/cpan/Unicode-Collate/Collate/Locale/yo.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 1EB9 ; [.1CAB.0020.0002] # LATIN SMALL LETTER E WITH DOT BELOW 0065 0323 ; [.1CAB.0020.0002] # LATIN SMALL LETTER E WITH DOT BELOW diff --git a/cpan/Unicode-Collate/Collate/Locale/zh.pl b/cpan/Unicode-Collate/Collate/Locale/zh.pl index 46b6028bd7..c18914460c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh.pl @@ -1,5 +1,5 @@ +{ - locale_version => 1.21, + locale_version => 1.23, entry => <<'ENTRY', # for DUCET v9.0.0 0101 ; [.1C47.001C.0002] # LATIN SMALL LETTER A WITH MACRON 0061 0304 ; [.1C47.001C.0002] # LATIN SMALL LETTER A WITH MACRON diff --git a/cpan/Unicode-Collate/Collate/Locale/zh_big5.pl b/cpan/Unicode-Collate/Collate/Locale/zh_big5.pl index ede0ca8330..5d7f0af83a 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh_big5.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh_big5.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::Big5; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::Big5::weightBig5, entry => <<'ENTRY', # for DUCET v9.0.0 0101 ; [.1C47.001C.0002] # LATIN SMALL LETTER A WITH MACRON diff --git a/cpan/Unicode-Collate/Collate/Locale/zh_gb.pl b/cpan/Unicode-Collate/Collate/Locale/zh_gb.pl index 14f572226b..0f6868cfd1 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh_gb.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh_gb.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::GB2312; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::GB2312::weightGB2312, entry => <<'ENTRY', # for DUCET v9.0.0 0101 ; [.1C47.001C.0002] # LATIN SMALL LETTER A WITH MACRON diff --git a/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl b/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl index fc866216b2..5403f77172 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh_pin.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::Pinyin; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::Pinyin::weightPinyin, entry => <<'ENTRY', # for DUCET v9.0.0 0101 ; [.1C47.001C.0002] # LATIN SMALL LETTER A WITH MACRON diff --git a/cpan/Unicode-Collate/Collate/Locale/zh_strk.pl b/cpan/Unicode-Collate/Collate/Locale/zh_strk.pl index 2b2aefb167..2fcf337d2c 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh_strk.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh_strk.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::Stroke; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::Stroke::weightStroke, entry => <<'ENTRY', # for DUCET v9.0.0 0101 ; [.1C47.001C.0002] # LATIN SMALL LETTER A WITH MACRON diff --git a/cpan/Unicode-Collate/Collate/Locale/zh_zhu.pl b/cpan/Unicode-Collate/Collate/Locale/zh_zhu.pl index 74918f6390..e1204b8edc 100644 --- a/cpan/Unicode-Collate/Collate/Locale/zh_zhu.pl +++ b/cpan/Unicode-Collate/Collate/Locale/zh_zhu.pl @@ -1,6 +1,6 @@ use Unicode::Collate::CJK::Zhuyin; +{ - locale_version => 1.21, + locale_version => 1.23, overrideCJK => \&Unicode::Collate::CJK::Zhuyin::weightZhuyin, entry => <<'ENTRY', # for DUCET v9.0.0 02C9 ; [.0000.0199.0002] # MODIFIER LETTER MACRON diff --git a/cpan/Unicode-Collate/t/cjkrange.t b/cpan/Unicode-Collate/t/cjkrange.t index 2c1ace7c22..4ed8710a9d 100644 --- a/cpan/Unicode-Collate/t/cjkrange.t +++ b/cpan/Unicode-Collate/t/cjkrange.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..715\n"; } # 1 + 51 x @Versions +BEGIN { $| = 1; print "1..901\n"; } # 1 + 60 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -47,14 +47,16 @@ my $coll = Unicode::Collate->new( # 9FC4..9FCB are CJK UI since UCA_Version 20 (Unicode 5.2). # 9FCC is CJK UI since UCA_Version 24 (Unicode 6.1). # 9FCD..9FD5 are CJK UI since UCA_Version 32 (Unicode 8.0). +# 9FD6..9FEA are CJK UI since UCA_Version 36 (Unicode 10.0). # 3400..4DB5 are CJK UI Ext.A since UCA_Version 8 (Unicode 3.0). # 20000..2A6D6 are CJK UI Ext.B since UCA_Version 8 (Unicode 3.1). # 2A700..2B734 are CJK UI Ext.C since UCA_Version 20 (Unicode 5.2). # 2B740..2B81D are CJK UI Ext.D since UCA_Version 22 (Unicode 6.0). # 2B820..2CEA1 are CJK UI Ext.E since UCA_Version 32 (Unicode 8.0). +# 2CEB0..2EBE0 are CJK UI Ext.F since UCA_Version 36 (Unicode 10.0). -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); for my $v (@Versions) { $coll->change(UCA_Version => $v); @@ -71,7 +73,9 @@ for my $v (@Versions) { ok($coll->cmp("\x{3400}", "\x{9FCC}") == ($v >= 24 ? 1 : -1)); # new ok($coll->cmp("\x{3400}", "\x{9FCD}") == ($v >= 32 ? 1 : -1)); # new ok($coll->cmp("\x{3400}", "\x{9FD5}") == ($v >= 32 ? 1 : -1)); # new - ok($coll->cmp("\x{3400}", "\x{9FD6}") == -1); # na + ok($coll->cmp("\x{3400}", "\x{9FD6}") == ($v >= 36 ? 1 : -1)); # new + ok($coll->cmp("\x{3400}", "\x{9FEA}") == ($v >= 36 ? 1 : -1)); # new + ok($coll->cmp("\x{3400}", "\x{9FEB}") == -1); # na ok($coll->cmp("\x{3400}", "\x{9FFF}") == -1); # na # UI < UI @@ -85,8 +89,10 @@ for my $v (@Versions) { ok($coll->cmp("\x{9FCB}", "\x{9FCC}") == -1); # new < new ok($coll->cmp("\x{9FCC}", "\x{9FCD}") == -1); # new < new ok($coll->cmp("\x{9FCD}", "\x{9FD5}") == -1); # new < new - ok($coll->cmp("\x{9FD5}", "\x{9FD6}") == -1); # new < na - ok($coll->cmp("\x{9FD6}", "\x{9FFF}") == -1); # na < na + ok($coll->cmp("\x{9FD5}", "\x{9FD6}") == -1); # new < new + ok($coll->cmp("\x{9FD6}", "\x{9FEA}") == -1); # new < new + ok($coll->cmp("\x{9FEA}", "\x{9FEB}") == -1); # new < na + ok($coll->cmp("\x{9FEB}", "\x{9FFF}") == -1); # na < na # Ext.A < Ext.B ok($coll->cmp("\x{3400}", "\x{20000}") == -1); @@ -125,5 +131,12 @@ for my $v (@Versions) { ok($coll->cmp("\x{2FFF}", "\x{2CEA1}") == ($v >= 32 ? 1 : -1)); # na > E ok($coll->cmp("\x{2FFF}", "\x{2CEA2}") == -1); # na < na ok($coll->cmp("\x{2FFF}", "\x{2CEAF}") == -1); # na < na + + # Ext.F + ok($coll->cmp("\x{2CEB0}","\x{2EBE0}") == -1); # F < F + ok($coll->cmp("\x{2FFF}", "\x{2CEB0}") == ($v >= 36 ? 1 : -1)); # na > F + ok($coll->cmp("\x{2FFF}", "\x{2EBE0}") == ($v >= 36 ? 1 : -1)); # na > F + ok($coll->cmp("\x{2FFF}", "\x{2EBE1}") == -1); # na < na + ok($coll->cmp("\x{2FFF}", "\x{2EBEF}") == -1); # na < na } diff --git a/cpan/Unicode-Collate/t/compatui.t b/cpan/Unicode-Collate/t/compatui.t index 9c51afe375..96dffd4091 100644 --- a/cpan/Unicode-Collate/t/compatui.t +++ b/cpan/Unicode-Collate/t/compatui.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..981\n"; } # 1 + 70 x @Versions +BEGIN { $| = 1; print "1..1051\n"; } # 1 + 70 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -33,7 +33,7 @@ ok(1); ######################### -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); # 12 compatibility ideographs are treated as unified ideographs: # FA0E, FA0F, FA11, FA13, FA14, FA1F, FA21, FA23, FA24, FA27, FA28, FA29. diff --git a/cpan/Unicode-Collate/t/hangtype.t b/cpan/Unicode-Collate/t/hangtype.t index 3427a8a39f..42d0c61a50 100644 --- a/cpan/Unicode-Collate/t/hangtype.t +++ b/cpan/Unicode-Collate/t/hangtype.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..701\n"; } # 1 + 50 x @Versions +BEGIN { $| = 1; print "1..751\n"; } # 1 + 50 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -33,7 +33,7 @@ ok(1); ######################### -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); for my $v (@Versions) { ok(Unicode::Collate::getHST(0x0000, $v), ''); diff --git a/cpan/Unicode-Collate/t/illegal.t b/cpan/Unicode-Collate/t/illegal.t index e901402a2a..c9ac787016 100644 --- a/cpan/Unicode-Collate/t/illegal.t +++ b/cpan/Unicode-Collate/t/illegal.t @@ -30,7 +30,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..151\n"; } # 81 + 5 x @Versions +BEGIN { $| = 1; print "1..156\n"; } # 81 + 5 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -192,7 +192,7 @@ my $out = Unicode::Collate->new( overrideOut => sub { 0xFFFD }, ); -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); for my $v (@Versions) { $out->change(UCA_Version => $v); diff --git a/cpan/Unicode-Collate/t/loc_es.t b/cpan/Unicode-Collate/t/loc_es.t index 3e685a8cec..cd482fea29 100644 --- a/cpan/Unicode-Collate/t/loc_es.t +++ b/cpan/Unicode-Collate/t/loc_es.t @@ -37,7 +37,7 @@ my $objEs = Unicode::Collate::Locale-> new(locale => 'ES', normalization => undef); ok($objEs->getlocale, 'es'); -ok($objEs->locale_version, 1.21); +ok($objEs->locale_version, 1.23); $objEs->change(level => 1); diff --git a/cpan/Unicode-Collate/t/loc_estr.t b/cpan/Unicode-Collate/t/loc_estr.t index b8470cb4ea..cc02ad9260 100644 --- a/cpan/Unicode-Collate/t/loc_estr.t +++ b/cpan/Unicode-Collate/t/loc_estr.t @@ -37,7 +37,7 @@ my $objEsTrad = Unicode::Collate::Locale-> new(locale => 'ES-trad', normalization => undef); ok($objEsTrad->getlocale, 'es__traditional'); -ok($objEsTrad->locale_version, 1.21); +ok($objEsTrad->locale_version, 1.23); $objEsTrad->change(level => 1); diff --git a/cpan/Unicode-Collate/t/nushu.t b/cpan/Unicode-Collate/t/nushu.t new file mode 100644 index 0000000000..4293a9af5d --- /dev/null +++ b/cpan/Unicode-Collate/t/nushu.t @@ -0,0 +1,73 @@ + +BEGIN { + unless ('A' eq pack('U', 0x41)) { + print "1..0 # Unicode::Collate cannot pack a Unicode code point\n"; + exit 0; + } + unless (0x41 == unpack('U', 'A')) { + print "1..0 # Unicode::Collate cannot get a Unicode code point\n"; + exit 0; + } + if ($ENV{PERL_CORE}) { + chdir('t') if -d 't'; + @INC = $^O eq 'MacOS' ? qw(::lib) : qw(../lib); + } +} + +use strict; +use warnings; +BEGIN { $| = 1; print "1..185\n"; } # 5 + 12 x @Versions +my $count = 0; +sub ok ($;$) { + my $p = my $r = shift; + if (@_) { + my $x = shift; + $p = !defined $x ? !defined $r : !defined $r ? 0 : $r eq $x; + } + print $p ? "ok" : "not ok", ' ', ++$count, "\n"; +} + +use Unicode::Collate; + +ok(1); + +######################### + +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); + +my $Collator = Unicode::Collate->new( + table => 'keys.txt', + normalization => undef, + UCA_Version => 36, +); + +ok($Collator->viewSortKey("\x{1B170}"), + '[FB01 8000 | 0020 | 0002 | FFFF |]'); +ok($Collator->viewSortKey("\x{1B171}"), + '[FB01 8001 | 0020 | 0002 | FFFF |]'); +ok($Collator->viewSortKey("\x{1B200}"), + '[FB01 8090 | 0020 | 0002 | FFFF |]'); +ok($Collator->viewSortKey("\x{1B2FB}"), + '[FB01 818B | 0020 | 0002 | FFFF |]'); + +# Nushu < CJK UI (4E00) < Unassigned. + +# 1B170..1B2FB are Nushu Characters since UCA_Version 36 (Unicode 10.0). + +for my $v (@Versions) { + $Collator->change(UCA_Version => $v); + + ok($Collator->cmp("\x{1B16F}", "\x{4E00}") == 1); + ok($Collator->cmp("\x{1B170}", "\x{4E00}") == ($v >= 36 ? -1 : 1)); + ok($Collator->cmp("\x{1B171}", "\x{4E00}") == ($v >= 36 ? -1 : 1)); + ok($Collator->cmp("\x{1B1FF}", "\x{4E00}") == ($v >= 36 ? -1 : 1)); + ok($Collator->cmp("\x{1B200}", "\x{4E00}") == ($v >= 36 ? -1 : 1)); + ok($Collator->cmp("\x{1B2FB}", "\x{4E00}") == ($v >= 36 ? -1 : 1)); + ok($Collator->cmp("\x{1B2FC}", "\x{4E00}") == 1); + ok($Collator->cmp("\x{1B2FF}", "\x{4E00}") == 1); + + ok($Collator->lt("\x{1B170}", "\x{1B171}")); + ok($Collator->lt("\x{1B171}", "\x{1B1FF}")); + ok($Collator->lt("\x{1B1FF}", "\x{1B200}")); + ok($Collator->lt("\x{1B200}", "\x{1B2FB}")); +} diff --git a/cpan/Unicode-Collate/t/overcjk0.t b/cpan/Unicode-Collate/t/overcjk0.t index c2d80dc96e..12e599de58 100644 --- a/cpan/Unicode-Collate/t/overcjk0.t +++ b/cpan/Unicode-Collate/t/overcjk0.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..552\n"; } # 6 + 39 x @Versions +BEGIN { $| = 1; print "1..696\n"; } # 6 + 46 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -60,14 +60,16 @@ ok($ignoreCJK->lt("Pe\x{5B57}rl", "Perl")); # 'r' is unassigned. # 9FC4..9FCB are CJK UI since UCA_Version 20 (Unicode 5.2). # 9FCC is CJK UI since UCA_Version 24 (Unicode 6.1). # 9FCD..9FD5 are CJK UI since UCA_Version 32 (Unicode 8.0). +# 9FD6..9FEA are CJK UI since UCA_Version 36 (Unicode 10.0). # 3400..4DB5 are CJK UI Ext.A since UCA_Version 8 (Unicode 3.0). # 20000..2A6D6 are CJK UI Ext.B since UCA_Version 8 (Unicode 3.1). # 2A700..2B734 are CJK UI Ext.C since UCA_Version 20 (Unicode 5.2). # 2B740..2B81D are CJK UI Ext.D since UCA_Version 22 (Unicode 6.0). # 2B820..2CEA1 are CJK UI Ext.E since UCA_Version 32 (Unicode 8.0). +# 2CEB0..2EBE0 are CJK UI Ext.F since UCA_Version 36 (Unicode 10.0). -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); for my $v (@Versions) { $ignoreCJK->change(UCA_Version => $v); @@ -90,8 +92,11 @@ for my $v (@Versions) { ok($ignoreCJK->cmp("\x{9FCF}", "") == ($v >= 32 ? 0 : 1)); ok($ignoreCJK->cmp("\x{9FD0}", "") == ($v >= 32 ? 0 : 1)); ok($ignoreCJK->cmp("\x{9FD5}", "") == ($v >= 32 ? 0 : 1)); - ok($ignoreCJK->cmp("\x{9FD6}", "") == 1); - ok($ignoreCJK->cmp("\x{9FDF}", "") == 1); + ok($ignoreCJK->cmp("\x{9FD6}", "") == ($v >= 36 ? 0 : 1)); + ok($ignoreCJK->cmp("\x{9FDF}", "") == ($v >= 36 ? 0 : 1)); + ok($ignoreCJK->cmp("\x{9FEA}", "") == ($v >= 36 ? 0 : 1)); + ok($ignoreCJK->cmp("\x{9FEB}", "") == 1); + ok($ignoreCJK->cmp("\x{9FFF}", "") == 1); # Ext.A ok($ignoreCJK->cmp("\x{3400}", "") == 0); @@ -122,5 +127,11 @@ for my $v (@Versions) { ok($ignoreCJK->cmp("\x{2CEA1}","") == ($v >= 32 ? 0 : 1)); ok($ignoreCJK->cmp("\x{2CEA2}","") == 1); ok($ignoreCJK->cmp("\x{2CEAF}","") == 1); + + # Ext.F + ok($ignoreCJK->cmp("\x{2CEB0}","") == ($v >= 36 ? 0 : 1)); + ok($ignoreCJK->cmp("\x{2EBE0}","") == ($v >= 36 ? 0 : 1)); + ok($ignoreCJK->cmp("\x{2EBE1}","") == 1); + ok($ignoreCJK->cmp("\x{2EBEF}","") == 1); } diff --git a/cpan/Unicode-Collate/t/overcjk1.t b/cpan/Unicode-Collate/t/overcjk1.t index cf80786e24..8441979425 100644 --- a/cpan/Unicode-Collate/t/overcjk1.t +++ b/cpan/Unicode-Collate/t/overcjk1.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..277\n"; } # 11 + 19 x @Versions +BEGIN { $| = 1; print "1..356\n"; } # 11 + 23 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -60,13 +60,15 @@ ok($overCJK->lt("a\x{4E03}", "A\x{4E01}")); ##### +# 4E00..9FA5 are CJK UI. # 9FA6..9FBB are CJK UI since UCA_Version 14 (Unicode 4.1). # 9FBC..9FC3 are CJK UI since UCA_Version 18 (Unicode 5.1). # 9FC4..9FCB are CJK UI since UCA_Version 20 (Unicode 5.2). # 9FCC is CJK UI since UCA_Version 24 (Unicode 6.1). # 9FCD..9FD5 are CJK UI since UCA_Version 32 (Unicode 8.0). +# 9FD6..9FEA are CJK UI since UCA_Version 36 (Unicode 10.0). -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); for my $v (@Versions) { $overCJK->change(UCA_Version => $v); @@ -87,7 +89,11 @@ for my $v (@Versions) { ok($overCJK->cmp("a\x{9FCC}", "A\x{9FCD}") == ($v >= 32 ? 1 : -1)); ok($overCJK->cmp("a\x{9FCD}", "A\x{9FCF}") == ($v >= 32 ? 1 : -1)); ok($overCJK->cmp("a\x{9FCF}", "A\x{9FD5}") == ($v >= 32 ? 1 : -1)); - ok($overCJK->cmp("a\x{9FD5}", "A\x{9FD6}") == -1); - ok($overCJK->cmp("a\x{9FD6}", "A\x{9FDF}") == -1); + ok($overCJK->cmp("a\x{9FD5}", "A\x{9FD6}") == ($v >= 36 ? 1 : -1)); + ok($overCJK->cmp("a\x{9FD6}", "A\x{9FDF}") == ($v >= 36 ? 1 : -1)); + ok($overCJK->cmp("a\x{9FDF}", "A\x{9FEA}") == ($v >= 36 ? 1 : -1)); + ok($overCJK->cmp("a\x{9FEA}", "A\x{9FEB}") == -1); + ok($overCJK->cmp("a\x{9FEB}", "A\x{9FEF}") == -1); + ok($overCJK->cmp("a\x{9FEF}", "A\x{9FFF}") == -1); } diff --git a/cpan/Unicode-Collate/t/tangut.t b/cpan/Unicode-Collate/t/tangut.t index 76ff22da7f..171a205661 100644 --- a/cpan/Unicode-Collate/t/tangut.t +++ b/cpan/Unicode-Collate/t/tangut.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..355\n"; } # 5 + 25 x @Versions +BEGIN { $| = 1; print "1..380\n"; } # 5 + 25 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -33,7 +33,7 @@ ok(1); ######################### -my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (8, 9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); my $Collator = Unicode::Collate->new( table => 'keys.txt', diff --git a/cpan/Unicode-Collate/t/view.t b/cpan/Unicode-Collate/t/view.t index f3472e1073..63a0e922be 100644 --- a/cpan/Unicode-Collate/t/view.t +++ b/cpan/Unicode-Collate/t/view.t @@ -16,7 +16,7 @@ BEGIN { use strict; use warnings; -BEGIN { $| = 1; print "1..114\n"; } # 62 + 4 x @Versions +BEGIN { $| = 1; print "1..174\n"; } # 62 + 8 x @Versions my $count = 0; sub ok ($;$) { my $p = my $r = shift; @@ -268,26 +268,35 @@ ok($el->viewSortKey("L\x{FF2C}\x{216C}\x{2112}\x{24C1}"), ##### 62 -my @Versions = (9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34); +my @Versions = (9, 11, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32, 34, 36); for my $v (@Versions) { $Collator->change(UCA_Version => $v); my $app = $v >= 26 ? ' |]' : ']'; + my $sec = $v >= 36 ? '' : ' FFFF'; $Collator->change(variable => 'Shifted', level => 4); ok($Collator->viewSortKey("1+2"), '[0A0C 0A0D | 0020 0020 | 0002 0002 | FFFF 039F FFFF'.$app); + ok($Collator->viewSortKey("\x{4E02}"), + '[FB40 CE02 | 0020 | 0002 | FFFF'.$sec.$app); $Collator->change(variable => 'Shift-Trimmed'); ok($Collator->viewSortKey("1+2"), '[0A0C 0A0D | 0020 0020 | 0002 0002 | 039F'.$app); + ok($Collator->viewSortKey("\x{4E02}"), + '[FB40 CE02 | 0020 | 0002 |'.$app); $Collator->change(variable => 'Non-ignorable', level => 3); ok($Collator->viewSortKey("1+2"), '[0A0C 039F 0A0D | 0020 0020 0020 | 0002 0002 0002 |]'); + ok($Collator->viewSortKey("\x{4E02}"), + '[FB40 CE02 | 0020 | 0002 |]'); $Collator->change(variable => 'Blanked'); ok($Collator->viewSortKey("1+2"), '[0A0C 0A0D | 0020 0020 | 0002 0002 |]'); + ok($Collator->viewSortKey("\x{4E02}"), + '[FB40 CE02 | 0020 | 0002 |]'); } |