928 lines
25 KiB
Diff
928 lines
25 KiB
Diff
From 0850dba96e3cb8ee37fe405b0cf76d7f910e90e4 Mon Sep 17 00:00:00 2001
|
|
From: Jitka Plesnikova <jplesnik@redhat.com>
|
|
Date: Thu, 18 May 2023 21:02:00 +0200
|
|
Subject: [PATCH] Upgrade to 1.32
|
|
|
|
---
|
|
Makefile.PL | 22 +++++++-------
|
|
Normalize.pm | 81 +++++++++++++++++++++++++++++++++++++---------------
|
|
Normalize.xs | 71 ++++++++++++++-------------------------------
|
|
mkheader | 20 +++----------
|
|
t/fcdc.t | 22 ++------------
|
|
t/form.t | 20 +------------
|
|
t/func.t | 22 ++------------
|
|
t/illegal.t | 22 ++------------
|
|
t/norm.t | 24 ++--------------
|
|
t/null.t | 11 -------
|
|
t/partial1.t | 20 +------------
|
|
t/partial2.t | 24 ++--------------
|
|
t/proto.t | 20 +------------
|
|
t/split.t | 24 ++--------------
|
|
t/test.t | 24 ++--------------
|
|
t/tie.t | 20 +------------
|
|
16 files changed, 118 insertions(+), 329 deletions(-)
|
|
|
|
diff --git a/Makefile.PL b/Makefile.PL
|
|
index 18bc2e2..a848b0d 100644
|
|
--- a/Makefile.PL
|
|
+++ b/Makefile.PL
|
|
@@ -1,4 +1,6 @@
|
|
-require 5.006001;
|
|
+use strict;
|
|
+use warnings;
|
|
+
|
|
use ExtUtils::MakeMaker;
|
|
|
|
my $clean = {};
|
|
@@ -6,7 +8,7 @@ my $clean = {};
|
|
my $mm_ver = ExtUtils::MakeMaker->VERSION;
|
|
|
|
if (-f "Normalize.xs") {
|
|
- print STDERR "Making header files for XS...\n";
|
|
+ print "Making header files for XS...\n";
|
|
|
|
do './mkheader' or die $@ || "mkheader: $!";
|
|
|
|
@@ -29,14 +31,14 @@ WriteMakefile(
|
|
'clean' => $clean,
|
|
'depend' => { 'Normalize.o' => '$(H_FILES)' },
|
|
'PREREQ_PM' => {
|
|
- Carp => 0,
|
|
- constant => 0,
|
|
- DynaLoader => 0,
|
|
- Exporter => 0,
|
|
- File::Spec => 0,
|
|
- strict => 0,
|
|
- warnings => 0,
|
|
- SelectSaver => 0,
|
|
+ 'Carp' => 0,
|
|
+ 'constant' => 0,
|
|
+ 'DynaLoader' => 0,
|
|
+ 'Exporter' => 0,
|
|
+ 'File::Spec' => 0,
|
|
+ 'strict' => 0,
|
|
+ 'warnings' => 0,
|
|
+ 'SelectSaver' => 0,
|
|
},
|
|
($mm_ver < 6.48 ? () : MIN_PERL_VERSION => 5.6.0),
|
|
($mm_ver < 6.46 ? () : (META_MERGE => {
|
|
diff --git a/Normalize.pm b/Normalize.pm
|
|
index adf3db5..c8053f7 100644
|
|
--- a/Normalize.pm
|
|
+++ b/Normalize.pm
|
|
@@ -1,14 +1,5 @@
|
|
package Unicode::Normalize;
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- die "Unicode::Normalize cannot stringify a Unicode code point\n";
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- die "Unicode::Normalize cannot get Unicode code point\n";
|
|
- }
|
|
-}
|
|
-
|
|
use 5.006;
|
|
use strict;
|
|
use warnings;
|
|
@@ -16,7 +7,7 @@ use Carp;
|
|
|
|
no warnings 'utf8';
|
|
|
|
-our $VERSION = '1.26';
|
|
+our $VERSION = '1.32';
|
|
our $PACKAGE = __PACKAGE__;
|
|
|
|
our @EXPORT = qw( NFC NFD NFKC NFKD );
|
|
@@ -40,16 +31,58 @@ our %EXPORT_TAGS = (
|
|
## utilities for tests
|
|
##
|
|
|
|
-sub pack_U {
|
|
- return pack('U*', @_);
|
|
+ # No EBCDIC support on early perls
|
|
+*to_native = ($::IS_ASCII || $] < 5.008)
|
|
+ ? sub { return shift }
|
|
+ : sub { utf8::unicode_to_native(shift) };
|
|
+
|
|
+*from_native = ($::IS_ASCII || $] < 5.008)
|
|
+ ? sub { return shift }
|
|
+ : sub { utf8::native_to_unicode(shift) };
|
|
+
|
|
+# The .t files are all in terms of Unicode, so xlate to/from native
|
|
+sub dot_t_pack_U {
|
|
+ return pack('U*', map { to_native($_) } @_);
|
|
}
|
|
|
|
-sub unpack_U {
|
|
+sub dot_t_unpack_U {
|
|
|
|
# The empty pack returns an empty UTF-8 string, so the effect is to force
|
|
# the shifted parameter into being UTF-8. This allows this to work on
|
|
# Perl 5.6, where there is no utf8::upgrade().
|
|
- return unpack('U*', shift(@_).pack('U*'));
|
|
+ return map { from_native($_) } unpack('U*', shift(@_).pack('U*'));
|
|
+}
|
|
+
|
|
+sub get_printable_string ($) {
|
|
+ use bytes;
|
|
+ my $s = shift;
|
|
+
|
|
+ # DeMorgan's laws cause this to mean ascii printables
|
|
+ return $s if $s =~ /[^[:^ascii:][:^print:]]/;
|
|
+
|
|
+ return join " ", map { sprintf "\\x%02x", ord $_ } split "", $s;
|
|
+}
|
|
+
|
|
+sub ok ($$;$) {
|
|
+ my $count_ref = shift; # Test number in caller
|
|
+ my $p = my $r = shift;
|
|
+ my $x;
|
|
+ if (@_) {
|
|
+ $x = shift;
|
|
+ $p = !defined $x ? !defined $r : !defined $r ? 0 : $r eq $x;
|
|
+ }
|
|
+
|
|
+ print $p ? "ok" : "not ok", ' ', ++$$count_ref, "\n";
|
|
+
|
|
+ return if $p;
|
|
+
|
|
+ my (undef, $file, $line) = caller(1);
|
|
+ print STDERR "# Failed test $$count_ref at $file line $line\n";
|
|
+
|
|
+ return unless defined $x;
|
|
+
|
|
+ print STDERR "# got ", get_printable_string($r), "\n";
|
|
+ print STDERR "# expected ", get_printable_string($x), "\n";
|
|
}
|
|
|
|
require Exporter;
|
|
@@ -343,7 +376,7 @@ Note that C<$unprocessed> will be modified as a side-effect.
|
|
|
|
=head2 Quick Check
|
|
|
|
-(see Annex 8, UAX #15; and F<DerivedNormalizationProps.txt>)
|
|
+(see Annex 8, UAX #15; and F<lib/unicore/DerivedNormalizationProps.txt>)
|
|
|
|
The following functions check whether the string is in that normalization form.
|
|
|
|
@@ -571,8 +604,10 @@ so one could cause Unicode 3.2 to be used in any perl version starting with
|
|
|
|
In older Unicode versions, a small number of characters (all of which are
|
|
CJK compatibility ideographs as far as they have been found) may have
|
|
-an erroneous decomposition mapping (see F<NormalizationCorrections.txt>).
|
|
-Anyhow, this module will neither refer to F<NormalizationCorrections.txt>
|
|
+an erroneous decomposition mapping (see
|
|
+F<lib/unicore/NormalizationCorrections.txt>).
|
|
+Anyhow, this module will neither refer to
|
|
+F<lib/unicore/NormalizationCorrections.txt>
|
|
nor provide any specific version of normalization. Therefore this module
|
|
running on an older perl with an older Unicode database may use
|
|
the erroneous decomposition mapping blindly conforming to the Unicode database.
|
|
@@ -606,27 +641,27 @@ and/or modify it under the same terms as Perl itself.
|
|
|
|
=over 4
|
|
|
|
-=item http://www.unicode.org/reports/tr15/
|
|
+=item L<http://www.unicode.org/reports/tr15/>
|
|
|
|
Unicode Normalization Forms - UAX #15
|
|
|
|
-=item http://www.unicode.org/Public/UNIDATA/CompositionExclusions.txt
|
|
+=item L<http://www.unicode.org/Public/UNIDATA/CompositionExclusions.txt>
|
|
|
|
Composition Exclusion Table
|
|
|
|
-=item http://www.unicode.org/Public/UNIDATA/DerivedNormalizationProps.txt
|
|
+=item L<http://www.unicode.org/Public/UNIDATA/DerivedNormalizationProps.txt>
|
|
|
|
Derived Normalization Properties
|
|
|
|
-=item http://www.unicode.org/Public/UNIDATA/NormalizationCorrections.txt
|
|
+=item L<http://www.unicode.org/Public/UNIDATA/NormalizationCorrections.txt>
|
|
|
|
Normalization Corrections
|
|
|
|
-=item http://www.unicode.org/review/pr-29.html
|
|
+=item L<http://www.unicode.org/review/pr-29.html>
|
|
|
|
Public Review Issue #29: Normalization Issue
|
|
|
|
-=item http://www.unicode.org/notes/tn5/
|
|
+=item L<http://www.unicode.org/notes/tn5/>
|
|
|
|
Canonical Equivalence in Applications - UTN #5
|
|
|
|
diff --git a/Normalize.xs b/Normalize.xs
|
|
index 4acff7f..210917e 100644
|
|
--- a/Normalize.xs
|
|
+++ b/Normalize.xs
|
|
@@ -13,6 +13,9 @@
|
|
#include "perl.h"
|
|
#include "XSUB.h"
|
|
|
|
+#define NEED_utf8_to_uvchr_buf
|
|
+#include "ppport.h"
|
|
+
|
|
/* These 5 files are prepared by mkheader */
|
|
#include "unfcmb.h"
|
|
#include "unfcan.h"
|
|
@@ -23,45 +26,15 @@
|
|
/* The generated normalization tables since v5.20 are in native character set
|
|
* terms. Prior to that, they were in Unicode terms. So we use 'uvchr' for
|
|
* later perls, and redefine that to be 'uvuni' for earlier ones */
|
|
-#if PERL_VERSION < 20
|
|
+#if PERL_VERSION_LT(5,20,0)
|
|
# undef uvchr_to_utf8
|
|
# ifdef uvuni_to_utf8
|
|
# define uvchr_to_utf8 uvuni_to_utf8
|
|
# else /* Perl 5.6.1 */
|
|
# define uvchr_to_utf8 uv_to_utf8
|
|
# endif
|
|
-
|
|
-# undef utf8n_to_uvchr
|
|
-# ifdef utf8n_to_uvuni
|
|
-# define utf8n_to_uvchr utf8n_to_uvuni
|
|
-# else /* Perl 5.6.1 */
|
|
-# define utf8n_to_uvchr utf8_to_uv
|
|
-# endif
|
|
#endif
|
|
|
|
-/* UTF8_ALLOW_BOM is used before Perl 5.8.0 */
|
|
-#ifndef UTF8_ALLOW_BOM
|
|
-#define UTF8_ALLOW_BOM (0)
|
|
-#endif /* UTF8_ALLOW_BOM */
|
|
-
|
|
-#ifndef UTF8_ALLOW_SURROGATE
|
|
-#define UTF8_ALLOW_SURROGATE (0)
|
|
-#endif /* UTF8_ALLOW_SURROGATE */
|
|
-
|
|
-#ifndef UTF8_ALLOW_FE_FF
|
|
-#define UTF8_ALLOW_FE_FF (0)
|
|
-#endif /* UTF8_ALLOW_FE_FF */
|
|
-
|
|
-#ifndef UTF8_ALLOW_FFFF
|
|
-#define UTF8_ALLOW_FFFF (0)
|
|
-#endif /* UTF8_ALLOW_FFFF */
|
|
-
|
|
-#ifndef PERL_UNUSED_VAR
|
|
-# define PERL_UNUSED_VAR(x) ((void)sizeof(x))
|
|
-#endif
|
|
-
|
|
-#define AllowAnyUTF (UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|UTF8_ALLOW_FE_FF|UTF8_ALLOW_FFFF)
|
|
-
|
|
/* check if the string buffer is enough before uvchr_to_utf8(). */
|
|
/* dstart, d, and dlen should be defined outside before. */
|
|
#define Renew_d_if_not_enough_to(need) STRLEN curlen = d - dstart; \
|
|
@@ -71,7 +44,7 @@
|
|
d = dstart + curlen; \
|
|
}
|
|
|
|
-/* if utf8n_to_uvchr() sets retlen to 0 (if broken?) */
|
|
+/* if utf8_to_uvchr_buf() sets retlen to 0 (if broken?) */
|
|
#define ErrRetlenIsZero "panic (Unicode::Normalize %s): zero-length character"
|
|
|
|
/* utf8_hop() hops back before start. Maybe broken UTF-8 */
|
|
@@ -139,8 +112,8 @@ static U8* dec_canonical(UV uv)
|
|
plane = (U8***)UNF_canon[uv >> 16];
|
|
if (! plane)
|
|
return NULL;
|
|
- row = plane[(uv >> 8) & 0xff];
|
|
- return row ? row[uv & 0xff] : NULL;
|
|
+ row = plane[(U8) (uv >> 8)];
|
|
+ return row ? row[(U8) uv] : NULL;
|
|
}
|
|
|
|
static U8* dec_compat(UV uv)
|
|
@@ -151,8 +124,8 @@ static U8* dec_compat(UV uv)
|
|
plane = (U8***)UNF_compat[uv >> 16];
|
|
if (! plane)
|
|
return NULL;
|
|
- row = plane[(uv >> 8) & 0xff];
|
|
- return row ? row[uv & 0xff] : NULL;
|
|
+ row = plane[(U8) (uv >> 8)];
|
|
+ return row ? row[(U8) uv] : NULL;
|
|
}
|
|
|
|
static UV composite_uv(UV uv, UV uv2)
|
|
@@ -175,10 +148,10 @@ static UV composite_uv(UV uv, UV uv2)
|
|
plane = UNF_compos[uv >> 16];
|
|
if (! plane)
|
|
return 0;
|
|
- row = plane[(uv >> 8) & 0xff];
|
|
+ row = plane[(U8) (uv >> 8)];
|
|
if (! row)
|
|
return 0;
|
|
- cell = row[uv & 0xff];
|
|
+ cell = row[(U8) uv];
|
|
if (! cell)
|
|
return 0;
|
|
for (i = cell; i->nextchar; i++) {
|
|
@@ -196,8 +169,8 @@ static U8 getCombinClass(UV uv)
|
|
plane = (U8**)UNF_combin[uv >> 16];
|
|
if (! plane)
|
|
return 0;
|
|
- row = plane[(uv >> 8) & 0xff];
|
|
- return row ? row[uv & 0xff] : 0;
|
|
+ row = plane[(U8) (uv >> 8)];
|
|
+ return row ? row[(U8) uv] : 0;
|
|
}
|
|
|
|
static U8* pv_cat_decompHangul(pTHX_ U8* d, UV uv)
|
|
@@ -244,7 +217,7 @@ U8* pv_utf8_decompose(pTHX_ U8* s, STRLEN slen, U8** dp, STRLEN dlen, bool iscom
|
|
|
|
while (p < e) {
|
|
STRLEN retlen;
|
|
- UV uv = utf8n_to_uvchr(p, e - p, &retlen, AllowAnyUTF);
|
|
+ UV uv = utf8_to_uvchr_buf(p, e, &retlen);
|
|
if (!retlen)
|
|
croak(ErrRetlenIsZero, "decompose");
|
|
p += retlen;
|
|
@@ -289,7 +262,7 @@ U8* pv_utf8_reorder(pTHX_ U8* s, STRLEN slen, U8** dp, STRLEN dlen)
|
|
while (p < e) {
|
|
U8 curCC;
|
|
STRLEN retlen;
|
|
- UV uv = utf8n_to_uvchr(p, e - p, &retlen, AllowAnyUTF);
|
|
+ UV uv = utf8_to_uvchr_buf(p, e, &retlen);
|
|
if (!retlen)
|
|
croak(ErrRetlenIsZero, "reorder");
|
|
p += retlen;
|
|
@@ -366,7 +339,7 @@ U8* pv_utf8_compose(pTHX_ U8* s, STRLEN slen, U8** dp, STRLEN dlen, bool isconti
|
|
while (p < e) {
|
|
U8 curCC;
|
|
STRLEN retlen;
|
|
- UV uv = utf8n_to_uvchr(p, e - p, &retlen, AllowAnyUTF);
|
|
+ UV uv = utf8_to_uvchr_buf(p, e, &retlen);
|
|
if (!retlen)
|
|
croak(ErrRetlenIsZero, "compose");
|
|
p += retlen;
|
|
@@ -636,7 +609,7 @@ checkNFD(src)
|
|
|
|
preCC = 0;
|
|
for (p = s; p < e; p += retlen) {
|
|
- UV uv = utf8n_to_uvchr(p, e - p, &retlen, AllowAnyUTF);
|
|
+ UV uv = utf8_to_uvchr_buf(p, e, &retlen);
|
|
if (!retlen)
|
|
croak(ErrRetlenIsZero, "checkNFD or -NFKD");
|
|
|
|
@@ -673,7 +646,7 @@ checkNFC(src)
|
|
|
|
preCC = 0;
|
|
for (p = s; p < e; p += retlen) {
|
|
- UV uv = utf8n_to_uvchr(p, e - p, &retlen, AllowAnyUTF);
|
|
+ UV uv = utf8_to_uvchr_buf(p, e, &retlen);
|
|
if (!retlen)
|
|
croak(ErrRetlenIsZero, "checkNFC or -NFKC");
|
|
|
|
@@ -731,7 +704,7 @@ checkFCD(src)
|
|
U8 *sCan;
|
|
UV uvLead;
|
|
STRLEN canlen = 0;
|
|
- UV uv = utf8n_to_uvchr(p, e - p, &retlen, AllowAnyUTF);
|
|
+ UV uv = utf8_to_uvchr_buf(p, e, &retlen);
|
|
if (!retlen)
|
|
croak(ErrRetlenIsZero, "checkFCD or -FCC");
|
|
|
|
@@ -740,7 +713,7 @@ checkFCD(src)
|
|
if (sCan) {
|
|
STRLEN canret;
|
|
canlen = (STRLEN)strlen((char *) sCan);
|
|
- uvLead = utf8n_to_uvchr(sCan, canlen, &canret, AllowAnyUTF);
|
|
+ uvLead = utf8_to_uvchr_buf(sCan, sCan + canlen, &canret);
|
|
if (!canret)
|
|
croak(ErrRetlenIsZero, "checkFCD or -FCC");
|
|
}
|
|
@@ -771,7 +744,7 @@ checkFCD(src)
|
|
U8* pCan = utf8_hop(eCan, -1);
|
|
if (pCan < sCan)
|
|
croak(ErrHopBeforeStart);
|
|
- uvTrail = utf8n_to_uvchr(pCan, eCan - pCan, &canret, AllowAnyUTF);
|
|
+ uvTrail = utf8_to_uvchr_buf(pCan, eCan, &canret);
|
|
if (!canret)
|
|
croak(ErrRetlenIsZero, "checkFCD or -FCC");
|
|
preCC = getCombinClass(uvTrail);
|
|
@@ -910,7 +883,7 @@ splitOnLastStarter(src)
|
|
p = utf8_hop(p, -1);
|
|
if (p < s)
|
|
croak(ErrHopBeforeStart);
|
|
- uv = utf8n_to_uvchr(p, e - p, NULL, AllowAnyUTF);
|
|
+ uv = utf8_to_uvchr_buf(p, e, NULL);
|
|
if (getCombinClass(uv) == 0) /* Last Starter found */
|
|
break;
|
|
}
|
|
diff --git a/mkheader b/mkheader
|
|
index 8d4c1b8..669a8a2 100644
|
|
--- a/mkheader
|
|
+++ b/mkheader
|
|
@@ -24,28 +24,16 @@ use Carp;
|
|
use File::Spec;
|
|
use SelectSaver;
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- die "Unicode::Normalize cannot stringify a Unicode code point\n";
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- die "Unicode::Normalize cannot get Unicode code point\n";
|
|
- }
|
|
-}
|
|
-
|
|
our $PACKAGE = 'Unicode::Normalize, mkheader';
|
|
|
|
our $prefix = "UNF_";
|
|
our $structname = "${prefix}complist";
|
|
|
|
# Starting in v5.20, the tables in lib/unicore are built using the platform's
|
|
-# native character set for code points 0-255.
|
|
-*pack_U = ($] ge 5.020)
|
|
- ? sub { return pack('W*', @_).pack('U*'); } # The empty pack returns
|
|
- # an empty UTF-8 string,
|
|
- # so the effect is to
|
|
- # force the return into
|
|
- # being UTF-8.
|
|
+# native character set for code points 0-255. But in v5.35, pack U stopped
|
|
+# trying to compensate
|
|
+*pack_U = ($] ge 5.020 && $] lt 5.035)
|
|
+ ? sub { return pack('U*', map { utf8::unicode_to_native($_) } @_); }
|
|
: sub { return pack('U*', @_); };
|
|
|
|
# %Canon and %Compat will be ($codepoint => $hexstring) after _U_stringify()
|
|
diff --git a/t/fcdc.t b/t/fcdc.t
|
|
index d2ef28b..b5dc195 100644
|
|
--- a/t/fcdc.t
|
|
+++ b/t/fcdc.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -23,20 +12,13 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..70\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
ok(1);
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
sub hexU { _pack_U map hex, split ' ', shift }
|
|
sub answer { defined $_[0] ? $_[0] ? "YES" : "NO" : "MAYBE" }
|
|
|
|
diff --git a/t/form.t b/t/form.t
|
|
index 6bbfb08..9a0850c 100644
|
|
--- a/t/form.t
|
|
+++ b/t/form.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -23,14 +12,7 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..37\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
diff --git a/t/func.t b/t/func.t
|
|
index 2bd6e50..a5eb0b3 100644
|
|
--- a/t/func.t
|
|
+++ b/t/func.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -23,20 +12,13 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..217\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
ok(1);
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
sub hexU { _pack_U map hex, split ' ', shift }
|
|
|
|
# This won't work on EBCDIC platforms prior to v5.8.0, which is when this
|
|
diff --git a/t/illegal.t b/t/illegal.t
|
|
index ccf2b4a..6a1160c 100644
|
|
--- a/t/illegal.t
|
|
+++ b/t/illegal.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -43,14 +32,7 @@ use warnings;
|
|
|
|
BEGIN { $| = 1; print "1..113\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
ok(1);
|
|
|
|
@@ -77,7 +59,7 @@ for my $u (0xD800, 0xDFFF, 0xFDD0, 0xFDEF, 0xFEFF, 0xFFFE, 0xFFFF,
|
|
our $proc; # before the last starter
|
|
our $unproc; # the last starter and after
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
|
|
($proc, $unproc) = splitOnLastStarter(_pack_U(0x41, 0x300, 0x327, 0xFFFF));
|
|
ok($proc eq _pack_U(0x41, 0x300, 0x327));
|
|
diff --git a/t/norm.t b/t/norm.t
|
|
index d3cec3a..ffb7449 100644
|
|
--- a/t/norm.t
|
|
+++ b/t/norm.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -23,21 +12,14 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..64\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(normalize);
|
|
|
|
ok(1);
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
-sub _unpack_U { Unicode::Normalize::unpack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
+sub _unpack_U { Unicode::Normalize::dot_t_unpack_U(@_) }
|
|
|
|
#########################
|
|
|
|
diff --git a/t/null.t b/t/null.t
|
|
index 9a00087..93d1bbc 100644
|
|
--- a/t/null.t
|
|
+++ b/t/null.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
diff --git a/t/partial1.t b/t/partial1.t
|
|
index 3e44a63..97d8343 100644
|
|
--- a/t/partial1.t
|
|
+++ b/t/partial1.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -31,14 +20,7 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..26\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
diff --git a/t/partial2.t b/t/partial2.t
|
|
index 7f19e93..1cf510d 100644
|
|
--- a/t/partial2.t
|
|
+++ b/t/partial2.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -31,21 +20,14 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..26\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
ok(1);
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
-sub _unpack_U { Unicode::Normalize::unpack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
+sub _unpack_U { Unicode::Normalize::undot_t_pack_U(@_) }
|
|
|
|
#########################
|
|
|
|
diff --git a/t/proto.t b/t/proto.t
|
|
index 38c6985..f90777c 100644
|
|
--- a/t/proto.t
|
|
+++ b/t/proto.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -23,14 +12,7 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..48\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
diff --git a/t/split.t b/t/split.t
|
|
index a92957c..ae166f4 100644
|
|
--- a/t/split.t
|
|
+++ b/t/split.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -31,21 +20,14 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..34\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize qw(:all);
|
|
|
|
ok(1);
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
-sub _unpack_U { Unicode::Normalize::unpack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
+sub _unpack_U { Unicode::Normalize::dot_t_unpack_U(@_) }
|
|
|
|
#########################
|
|
|
|
diff --git a/t/test.t b/t/test.t
|
|
index cb4b6ea..cec3ca7 100644
|
|
--- a/t/test.t
|
|
+++ b/t/test.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -23,21 +12,14 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..72\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
use Unicode::Normalize;
|
|
|
|
ok(1);
|
|
|
|
-sub _pack_U { Unicode::Normalize::pack_U(@_) }
|
|
-sub _unpack_U { Unicode::Normalize::unpack_U(@_) }
|
|
+sub _pack_U { Unicode::Normalize::dot_t_pack_U(@_) }
|
|
+sub _unpack_U { Unicode::Normalize::dot_t_unpack_U(@_) }
|
|
|
|
#########################
|
|
|
|
diff --git a/t/tie.t b/t/tie.t
|
|
index 4fdd121..1282405 100644
|
|
--- a/t/tie.t
|
|
+++ b/t/tie.t
|
|
@@ -1,15 +1,4 @@
|
|
|
|
-BEGIN {
|
|
- unless ('A' eq pack('U', 0x41)) {
|
|
- print "1..0 # Unicode::Normalize cannot pack a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
- unless (0x41 == unpack('U', 'A')) {
|
|
- print "1..0 # Unicode::Normalize cannot get a Unicode code point\n";
|
|
- exit 0;
|
|
- }
|
|
-}
|
|
-
|
|
BEGIN {
|
|
if ($ENV{PERL_CORE}) {
|
|
chdir('t') if -d 't';
|
|
@@ -34,14 +23,7 @@ use strict;
|
|
use warnings;
|
|
BEGIN { $| = 1; print "1..17\n"; }
|
|
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";
|
|
-}
|
|
+sub ok { Unicode::Normalize::ok(\$count, @_) }
|
|
|
|
ok(1);
|
|
|
|
--
|
|
2.40.1
|
|
|