All but ../lib/Unicode/UCD.t pass.
p4raw-id: //depot/perlio@14412
Version v5.7.2 Development release working toward v5.8
--------------
____________________________________________________________________________
+[ 14388] By: jhi on 2002/01/23 15:04:06
+ Log: Small update on todo. Could use a lot more.
+ Branch: perl
+ ! pod/perltodo.pod
+____________________________________________________________________________
+[ 14386] By: jhi on 2002/01/23 14:19:01
+ Log: Subject: [ID 20020121.003] perldata doco bug
+ From: John Stumbles <jstumbles@bluearc.com>
+ Date: Mon, 21 Jan 2002 14:19:56 -0000
+ Message-Id: <4586CA8FDDC2D411A1C700508BB4AC33016765D1@ukexchange.synaxia.com>
+ Branch: perl
+ ! pod/perldata.pod
+____________________________________________________________________________
+[ 14385] By: jhi on 2002/01/23 14:17:52
+ Log: Subject: [PATCH] Re: bless() bug ? Why fails reblessing of 'main::Object' to 'Object' ?
+ From: Michael G Schwern <schwern@pobox.com>
+ Date: Mon, 21 Jan 2002 15:16:42 -0500
+ Message-ID: <20020121201642.GA6659@blackrider>
+ Branch: perl
+ ! embed.fnc embed.h proto.h t/op/universal.t universal.c
+____________________________________________________________________________
+[ 14384] By: jhi on 2002/01/23 13:45:30
+ Log: Subject: [PATCH] Re: eval not catching warnings?
+ From: abigail@foad.org
+ Date: Wed, 23 Jan 2002 15:35:47 +0100
+ Message-ID: <20020123143547.24798.qmail@foad.org>
+ Branch: perl
+ ! pod/perlfunc.pod
+____________________________________________________________________________
+[ 14383] By: jhi on 2002/01/23 03:57:58
+ Log: Subject: [ID 20020122.012] Not OK: perl v5.7.2 +DEVEL14368 on cygwin-multi-64int 1.3.6(0.4732) (UNINSTALLED)
+ From: sthoenna@efn.org (Yitzchak Scott-Thoennes)
+ Date: Tue, 22 Jan 2002 17:00:54 -0800
+ Message-Id: <GtgT8gzkg+CG092yn@efn.org>
+ Branch: perl
+ ! t/run/fresh_perl.t
+____________________________________________________________________________
+[ 14381] By: jhi on 2002/01/23 03:47:05
+ Log: HP-UX 10.20 cc pacifying from Merijn.
+ Branch: perl
+ ! Configure
+____________________________________________________________________________
+[ 14380] By: jhi on 2002/01/23 03:41:26
+ Log: Subject: [PATCH] test.com shebang handling (was Re: VMS@14369)
+ From: "Craig A. Berry" <craigberry@mac.com>
+ Date: Tue, 22 Jan 2002 22:14:26 -0600
+ Message-Id: <a05101000b873de9cf801@[172.16.52.1]>
+ Branch: perl
+ ! vms/test.com
+____________________________________________________________________________
+[ 14379] By: jhi on 2002/01/23 03:11:31
+ Log: AIX cpp bug: having macro arguments and character constants
+ "the same" means trouble (here s and 's')
+ What broke now was 841 and 842 of t/op/pat.t, because of the
+ ANYOF_UNICODE_FOLD_SHARP_S() in utf8.h, ccversion 5.0.1.0
+ (note that breakage happened only under cc_r and usethreads+
+ useithreads)
+ Branch: perl
+ ! utf8.h
+____________________________________________________________________________
+[ 14376] By: jhi on 2002/01/22 16:46:48
+ Log: Subject: [PATCH] Support truncate() in VOS port
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Mon, 21 Jan 02 23:27 est
+ Message-Id: <200201220428.XAA15304@mailhub1.stratus.com>
+ Branch: perl
+ + vos/vos.c
+ ! MANIFEST hints/vos.sh vos/vosish.h
+____________________________________________________________________________
+[ 14374] By: jhi on 2002/01/22 16:36:41
+ Log: Get rid of the _() macro since (1) we require ANSI anyway
+ (2) Other software (NU)seems to use it and we don't need it,
+ so let's give it up.
+ Branch: perl
+ ! Configure Porting/Glossary Porting/config.sh Porting/config_H
+ ! config_h.SH ext/Devel/PPPort/PPPort.pm malloc.c
+ ! plan9/config.plan9 pod/perltoc.pod uconfig.h
+ ! vos/config.alpha.h vos/config.ga.h win32/config_H.bc
+ ! win32/config_H.gc win32/config_H.vc win32/config_H.win64
+ ! wince/config.h wince/config_H.ce
+____________________________________________________________________________
+[ 14371] By: jhi on 2002/01/21 19:36:04
+ Log: Subject: [BUG] /\_/ an unrecognized escape?
+ From: Michael G Schwern <schwern@pobox.com>
+ Date: Mon, 21 Jan 2002 15:22:54 -0500
+ Message-ID: <20020121202254.GA6731@blackrider>
+ Branch: perl
+ ! t/lib/warnings/toke toke.c
+____________________________________________________________________________
+[ 14370] By: jhi on 2002/01/21 19:16:00
+ Log: Undo the renaming of the Unicode data files; the simple
+ solution being not including the *.html files. This means
+ that in the future there is no need for any renamings
+ (well, assuming that the Consortium doesn't cause any),
+ and the files are named like they are in the Consortium
+ website, thus alleviating confusion.
+ Branch: perl
+ + lib/unicore/ArabicShaping.txt lib/unicore/BidiMirroring.txt
+ + lib/unicore/CaseFolding.txt
+ + lib/unicore/CompositionExclusions.txt
+ + lib/unicore/EastAsianWidth.txt lib/unicore/LineBreak.txt
+ + lib/unicore/SpecialCasing.txt lib/unicore/UnicodeData.txt
+ - lib/unicore/ArabShap.txt lib/unicore/BidiMirr.txt
+ - lib/unicore/CaseFold.txt lib/unicore/CompExcl.txt
+ - lib/unicore/EAWidth.txt lib/unicore/LineBrk.txt
+ - lib/unicore/NamesList.html lib/unicore/PropList.html
+ - lib/unicore/SpecCase.txt lib/unicore/UCD.html
+ - lib/unicore/Unicode.html lib/unicore/Unicode.txt
+ - lib/unicore/rename
+ ! (edit 285 files)
+____________________________________________________________________________
+[ 14369] By: jhi on 2002/01/21 15:10:59
+ Log: Update Changes.
+ Branch: perl
+ ! Changes patchlevel.h
+____________________________________________________________________________
+[ 14368] By: jhi on 2002/01/21 14:56:42
+ Log: Subject: RE: BCC for Win32 is unhappy @14331
+ From: "Konovalov, Vadim" <vkonovalov@spb.Lucent.com>
+ Date: Mon, 21 Jan 2002 09:48:40 +0300
+ Message-ID: <80C37C8B4041FB4F9135D70A0AAD71B30F00E5@ru0028exch01.spb.lucent.com>
+
+ (using IV instead of int)
+ Branch: perl
+ ! hv.h
+____________________________________________________________________________
+[ 14367] By: jhi on 2002/01/21 14:29:05
+ Log: path_is_absolute() needs a prototype (and maybe
+ a better name, but that's another story).
+ Branch: perl
+ ! embed.fnc embed.h pp_ctl.c proto.h
+____________________________________________________________________________
+[ 14366] By: jhi on 2002/01/21 14:07:35
+ Log: Subject: Re: coderefs in @INC
+ From: Chris Nandor <pudge@pobox.com>
+ Date: Thu, 17 Jan 2002 11:26:02 -0500
+ Message-Id: <p0510030eb86ca7bc03e0@[10.0.1.177]>
+ Branch: perl
+ ! pp_ctl.c
+____________________________________________________________________________
+[ 14365] By: jhi on 2002/01/21 14:06:11
+ Log: Subject: Re: [PATCH warnings, perldiag] document diagnostics
+ From: Rafael Garcia-Suarez <rgarciasuarez@free.fr>
+ Date: Sun, 20 Jan 2002 22:53:56 +0100
+ Message-ID: <20020120225356.A12093@rafael>
+ Branch: perl
+ ! lib/warnings.pm pod/perldiag.pod t/lib/warnings/2use
+ ! t/lib/warnings/9enabled warnings.h warnings.pl
+____________________________________________________________________________
+[ 14364] By: jhi on 2002/01/21 03:53:08
+ Log: Subject: [PATCH] MakeMaker.pm sub-Makefile.PL tweak for VMS
+ From: "Craig A. Berry" <craigberry@mac.com>
+ Date: Sun, 20 Jan 2002 22:49:42 -0600
+ Message-Id: <a05101004b8714273d60c@[172.16.52.1]>
+ Branch: perl
+ ! lib/ExtUtils/MakeMaker.pm
+____________________________________________________________________________
+[ 14360] By: jhi on 2002/01/20 17:11:12
+ Log: Subject: [PATCH] lib/ExtUtils/t/Command.t -- VOS Fixes
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Sat, 19 Jan 02 17:17 est
+ Message-Id: <200201192218.RAA07911@mailhub1.stratus.com>
+
+ Subject: [PATCH] lib/ExtUtils/t/Command.t -- add more tests
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Sat, 19 Jan 02 17:19 est
+ Message-Id: <200201192218.RAA12331@mailhub2.stratus.com>
+ Branch: perl
+ ! lib/ExtUtils/t/Command.t
+____________________________________________________________________________
+[ 14359] By: jhi on 2002/01/20 17:09:40
+ Log: Subject: [PATCH] lib/AnyDBM_File.t -- VOS fix
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Sat, 19 Jan 02 14:30 est
+ Message-Id: <200201191932.OAA05601@mailhub1.stratus.com>
+ Branch: perl
+ ! lib/AnyDBM_File.t
+____________________________________________________________________________
+[ 14358] By: jhi on 2002/01/20 17:01:38
+ Log: Subject: [REPATCH] Re: [PATCH] ext/File/Glob/t/basic.t - VOS patch
+ From: Rafael Garcia-Suarez <rgarciasuarez@free.fr>
+ Date: Sun, 20 Jan 2002 13:51:36 +0100
+ Message-ID: <20020120135136.A710@rafael>
+ Branch: perl
+ ! ext/File/Glob/t/basic.t
+____________________________________________________________________________
+[ 14354] By: jhi on 2002/01/20 06:35:54
+ Log: Make also hex() and oct() to croak if their arguments
+ cannot be downgraded (that is, if they contain wide
+ characters), just like crypt() does (and use the croak
+ feature of sv_utf8_downgrade()).
+ Branch: perl
+ ! pp.c t/op/oct.t
+____________________________________________________________________________
+[ 14351] By: jhi on 2002/01/19 21:06:58
+ Log: Regen toc.
+ Branch: perl
+ ! pod/perltoc.pod
+____________________________________________________________________________
+[ 14350] By: jhi on 2002/01/19 21:03:07
+ Log: Subject: Re: some file names inside pod/perl*delta files don't match .pod names
+ From: David Dyck <dcd@tc.fluke.com>
+ Date: Sat, 19 Jan 2002 13:31:36 -0800 (PST)
+ Message-ID: <Pine.LNX.4.33.0201191329420.21630-100000@dd.tc.fluke.com>
+ Branch: perl
+ ! pod/perl5004delta.pod pod/perl5005delta.pod
+ ! pod/perl561delta.pod pod/perl56delta.pod
+____________________________________________________________________________
+[ 14349] By: jhi on 2002/01/19 20:07:17
+ Log: FAQ sync.
+ Branch: perl
+ ! pod/perlfaq1.pod pod/perlfaq2.pod
+____________________________________________________________________________
+[ 14348] By: jhi on 2002/01/19 17:58:34
+ Log: Subject: [PATCH lib/Pod/t/Usage.t]
+ From: Abe Timmerman <abe@ztreet.demon.nl>
+ Date: Sat, 19 Jan 2002 19:57:57 +0100
+ Message-ID: <f1gj4usu5m76bv88a3ldptnmo6ld7d44ri@4ax.com>
+ Branch: perl
+ + lib/Pod/t/Usage.t
+ ! MANIFEST
+____________________________________________________________________________
+[ 14347] By: jhi on 2002/01/19 17:57:08
+ Log: Subject: [PATCH] ext/SDBM_File/sdbm.t -- VOS fix
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Sat, 19 Jan 02 13:15 est
+ Message-Id: <200201191814.NAA09367@mailhub2.stratus.com>
+ Branch: perl
+ ! ext/SDBM_File/sdbm.t
+____________________________________________________________________________
+[ 14346] By: jhi on 2002/01/19 17:55:55
+ Log: Integrate perlio; Split out core of sv_magic() into sv_magicext().
+ Branch: perl
+ !> embed.fnc embed.h embedvar.h global.sym perlapi.c perlapi.h
+ !> pod/perlapi.pod pod/perlintern.pod proto.h sv.c util.c
+____________________________________________________________________________
+[ 14345] By: gbarr on 2002/01/19 16:51:23
+ Log: Alternative Time::Local algorithm that uses matematical formula
+ for timegm instead of progressive guessing
+ Branch: perl
+ ! lib/Time/Local.pm
+____________________________________________________________________________
+[ 14344] By: jhi on 2002/01/19 16:11:09
+ Log: Subject: [PATCH] ext/File/Glob/t/basic.t - VOS patch
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Sat, 19 Jan 02 11:20 est
+ Message-Id: <200201191619.LAA07751@mailhub2.stratus.com>
+ Branch: perl
+ ! ext/File/Glob/t/basic.t
+____________________________________________________________________________
+[ 14343] By: jhi on 2002/01/19 16:09:52
+ Log: Subject: [PATCH] ext/Cwd/t/cwd.t -- for VOS
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Fri, 18 Jan 02 22:56 est
+ Message-Id: <200201190400.XAA16899@mailhub1.stratus.com>
+ Branch: perl
+ ! ext/Cwd/t/cwd.t
+____________________________________________________________________________
+[ 14342] By: jhi on 2002/01/19 16:08:19
+ Log: Subject: [PATCH] lib/Time/Local.t patch w/o 2038 check
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Fri, 18 Jan 02 22:48 est
+ Message-Id: <200201190349.WAA28294@mailhub2.stratus.com>
+ Branch: perl
+ ! lib/Time/Local.t
+____________________________________________________________________________
+[ 14341] By: jhi on 2002/01/19 16:06:56
+ Log: Subject: [PATCH] ext/Devel/DProf/DProf.t - different way
+ From: Paul_GreenVOS@vos.stratus.com
+ Date: Fri, 18 Jan 02 16:22 est
+ Message-Id: <200201182125.QAA08563@mailhub1.stratus.com>
+ Branch: perl
+ ! ext/Devel/DProf/DProf.t
+____________________________________________________________________________
+[ 14340] By: jhi on 2002/01/19 03:00:26
+ Log: Subject: [PATCH] Re: ext/Devel/DProf/DProf.t -- use exe_ext
+ From: Tels <perl_dummy@bloodgate.com>
+ Date: Fri, 18 Jan 2002 22:07:14 +0100 (CET)
+ Message-Id: <200201182106.XAA19133@taku.hut.fi>
+ Branch: perl
+ ! t/comp/script.t t/op/stat.t t/run/fresh_perl.t
+____________________________________________________________________________
+[ 14339] By: jhi on 2002/01/19 02:56:26
+ Log: Don't do socketpair udp unless you've got all what it takes.
+ Branch: perl
+ ! util.c
+____________________________________________________________________________
+[ 14338] By: jhi on 2002/01/19 02:51:34
+ Log: Subject: [PATCH] Re: perl@14331 - BeOS now quite happy
+ From: Tels <perl_dummy@bloodgate.com>
+ Date: Fri, 18 Jan 2002 23:07:01 +0100 (CET)
+ Message-Id: <200201182206.AAA15310@taku.hut.fi>
+ Branch: perl
+ ! lib/ExtUtils/MM_BeOS.pm
+____________________________________________________________________________
+[ 14336] By: jhi on 2002/01/19 02:47:50
+ Log: Avoid bare "set", and kiss .uucp goodbye.
+ Branch: perl
+ ! Configure
+____________________________________________________________________________
+[ 14334] By: jhi on 2002/01/18 21:16:08
+ Log: Retract #14327 for now, going to the limit seems
+ to be too much for many platforms.
+ Branch: perl
+ ! lib/Time/Local.t
+____________________________________________________________________________
+[ 14331] By: jhi on 2002/01/18 16:09:38
+ Log: Update Changes.
+ Branch: perl
+ ! Changes patchlevel.h
+____________________________________________________________________________
[ 14330] By: jhi on 2002/01/18 15:07:49
Log: Try to make the connect/read/write timeouting.
Branch: perl
# $Id: Head.U,v 3.0.1.9 1997/02/28 15:02:09 ram Exp $
#
-# Generated on Sat Jan 19 05:47:21 EET 2002 [metaconfig 3.0 PL70]
+# Generated on Thu Jan 24 16:12:51 EET 2002 [metaconfig 3.0 PL70]
# (with additional metaconfig patches by perlbug@perl.org)
cat >c1$$ <<EOF
#endif
int main() {
#if BYTEORDER == 0x1234 || BYTEORDER == 0x4321
- U8 buf[] = "\0\0\0\1\0\0\0\0";
+ U8 *buf = (U8*)"\0\0\0\1\0\0\0\0";
U32 *up;
int i;
/* EXTERN.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* INTERN.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
lib/Unicode/UCD.t See if Unicode character database works
lib/unicore/ArabLink.pl Unicode character database
lib/unicore/ArabLnkGrp.pl Unicode character database
-lib/unicore/ArabShap.txt Unicode character database
-lib/unicore/BidiMirr.txt Unicode character database
+lib/unicore/ArabicShaping.txt Unicode character database
+lib/unicore/BidiMirroring.txt Unicode character database
lib/unicore/Bidirectional.pl Unicode character database
lib/unicore/Blocks.pl Unicode character database
lib/unicore/Blocks.txt Unicode character database
lib/unicore/Canonical.pl Unicode character database
-lib/unicore/CaseFold.txt Unicode character database
+lib/unicore/CaseFolding.txt Unicode character database
lib/unicore/Category.pl Unicode character database
lib/unicore/CombiningClass.pl Unicode character database
-lib/unicore/CompExcl.txt Unicode character database
+lib/unicore/CompositionExclusions.txt Unicode character database
lib/unicore/Decomposition.pl Unicode character database
-lib/unicore/EAWidth.txt Unicode character database
+lib/unicore/EastAsianWidth.txt Unicode character database
lib/unicore/Exact.pl Unicode character database
lib/unicore/Index.txt Unicode character database
lib/unicore/Jamo.txt Unicode character database
lib/unicore/lib/_CanonDC.pl Unicode character database
lib/unicore/lib/_CaseIgn.pl Unicode character database
lib/unicore/lib/_CombAbo.pl Unicode character database
-lib/unicore/LineBrk.txt Unicode character database
+lib/unicore/LineBreak.txt Unicode character database
lib/unicore/Makefile Unicode character database
lib/unicore/mktables Unicode character database generator
lib/unicore/Name.pl Unicode character database
-lib/unicore/NamesList.html Unicode character database
lib/unicore/NamesList.txt Unicode character database
lib/unicore/Number.pl Unicode character database
lib/unicore/Properties Built-in \p{...} / \P{...} property list
-lib/unicore/PropList.html Unicode character database
lib/unicore/PropList.txt Unicode character database
lib/unicore/README.perl Unicode character database
lib/unicore/ReadMe.txt Unicode character database info
-lib/unicore/rename Filename mappings used
lib/unicore/Scripts.pl Unicode character database
lib/unicore/Scripts.txt Unicode character database
-lib/unicore/SpecCase.txt Unicode character database
+lib/unicore/SpecialCasing.txt Unicode character database
lib/unicore/To/Digit.pl Unicode character database
lib/unicore/To/Fold.pl Unicode character database
lib/unicore/To/Lower.pl Unicode character database
lib/unicore/To/Title.pl Unicode character database
lib/unicore/To/Upper.pl Unicode character database
-lib/unicore/UCD.html Unicode character database
-lib/unicore/Unicode.html Unicode character database
-lib/unicore/Unicode.txt Unicode character database
+lib/unicore/UnicodeData.txt Unicode character database
lib/unicore/version The version of the Unicode
lib/UNIVERSAL.pm Base class for ALL classes
lib/User/grent.pm By-name interface to Perl's builtin getgr*
vos/Makefile A helper for maintaining the config.*.* in UNIX
vos/perl.bind VOS bind control file
vos/test_vos_dummies.c Test program for "vos_dummies.c"
+vos/vos.c VOS emulations for missing POSIX functions
vos/vosish.h VOS-specific header file
vos/vos_dummies.c Wrappers to soak up undefined functions
warnings.h The warning numbers
find libraries. It may contain directories that do not exist on
this platform, libpth is the cleaned-up version.
+gmake (Loc.U):
+ This variable is used internally by Configure to determine the
+ full pathname (if any) of the gmake program. After Configure runs,
+ the value is reset to a plain "gmake" and is not useful.
+
grep (Loc.U):
This variable is used internally by Configure to determine the
full pathname (if any) of the grep program. After Configure runs,
shrpenv=''
See the main perl Makefile.SH for actual working usage.
Alternatively, we might be able to use a command line option such
- as -R $archlibexp/CORE (Solaris, NetBSD) or -Wl,-rpath
+ as -R $archlibexp/CORE (Solaris) or -Wl,-rpath
$archlibexp/CORE (Linux).
shsharp (spitshell.U):
# Package name : perl5
# Source directory : .
-# Configuration time: Fri Nov 23 21:51:58 EET 2001
+# Configuration time: Tue Jan 22 18:37:28 EET 2002
# Configured by : jhi
# Target system : osf1 alpha.hut.fi v4.0 878 alpha
ccversion='V5.6-082'
cf_by='jhi'
cf_email='yourname@yourhost.yourplace.com'
-cf_time='Fri Nov 23 21:51:58 EET 2001'
+cf_time='Tue Jan 22 18:37:28 EET 2002'
charsize='1'
chgrp=''
chmod='chmod'
dlsrc='dl_dlopen.xs'
doublesize='8'
drand01='drand48()'
-dynamic_ext='B ByteLoader Cwd DB_File Data/Dumper Devel/DProf Devel/Peek Digest/MD5 Encode Fcntl File/Glob Filter/Util/Call I18N/Langinfo IO IPC/SysV List/Util MIME/Base64 NDBM_File ODBM_File Opcode POSIX PerlIO/Scalar PerlIO/Via SDBM_File Socket Storable Sys/Hostname Sys/Syslog Time/HiRes Unicode/Normalize XS/Typemap attrs re'
+dynamic_ext='B ByteLoader Cwd DB_File Data/Dumper Devel/DProf Devel/PPPort Devel/Peek Digest/MD5 Encode Fcntl File/Glob Filter/Util/Call I18N/Langinfo IO IPC/SysV List/Util MIME/Base64 NDBM_File ODBM_File Opcode POSIX PerlIO/Scalar PerlIO/Via SDBM_File Socket Storable Sys/Hostname Sys/Syslog Time/HiRes Unicode/Normalize XS/Typemap attrs re'
eagain='EAGAIN'
ebcdic='undef'
echo='echo'
eunicefix=':'
exe_ext=''
expr='expr'
-extensions='B ByteLoader Cwd DB_File Data/Dumper Devel/DProf Devel/Peek Digest/MD5 Encode Fcntl File/Glob Filter/Util/Call I18N/Langinfo IO IPC/SysV List/Util MIME/Base64 NDBM_File ODBM_File Opcode POSIX PerlIO/Scalar PerlIO/Via SDBM_File Socket Storable Sys/Hostname Sys/Syslog Time/HiRes Unicode/Normalize XS/Typemap attrs re Devel/PPPort Errno'
+extensions='B ByteLoader Cwd DB_File Data/Dumper Devel/DProf Devel/PPPort Devel/Peek Digest/MD5 Encode Fcntl File/Glob Filter/Util/Call I18N/Langinfo IO IPC/SysV List/Util MIME/Base64 NDBM_File ODBM_File Opcode POSIX PerlIO/Scalar PerlIO/Via SDBM_File Socket Storable Sys/Hostname Sys/Syslog Time/HiRes Unicode/Normalize XS/Typemap attrs re Errno'
extras=''
fflushNULL='define'
fflushall='undef'
gidsize='4'
gidtype='gid_t'
glibpth='/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib'
+gmake='gmake'
grep='grep'
groupcat='cat /etc/group'
groupstype='gid_t'
ivdformat='"ld"'
ivsize='8'
ivtype='long'
-known_extensions='B ByteLoader Cwd DB_File Data/Dumper Devel/DProf Devel/Peek Digest/MD5 Encode Fcntl File/Glob Filter/Util/Call GDBM_File I18N/Langinfo IO IPC/SysV List/Util MIME/Base64 NDBM_File ODBM_File Opcode POSIX PerlIO/Scalar PerlIO/Via SDBM_File Socket Storable Sys/Hostname Sys/Syslog Thread Time/HiRes Unicode/Normalize XS/Typemap attrs re threads threads/shared'
+known_extensions='B ByteLoader Cwd DB_File Data/Dumper Devel/DProf Devel/PPPort Devel/Peek Digest/MD5 Encode Fcntl File/Glob Filter/Util/Call GDBM_File I18N/Langinfo IO IPC/SysV List/Util MIME/Base64 NDBM_File ODBM_File Opcode POSIX PerlIO/Scalar PerlIO/Via SDBM_File Socket Storable Sys/Hostname Sys/Syslog Thread Time/HiRes Unicode/Normalize XS/Typemap attrs re threads threads/shared'
ksh=''
ld='ld'
lddlflags='-shared -expect_unresolved "*" -msym -std -s'
nm='nm'
nm_opt='-p'
nm_so_opt=''
-nonxs_ext='Devel/PPPort Errno'
+nonxs_ext='Errno'
nroff='nroff'
nvEUformat='"E"'
nvFUformat='"F"'
path_sep=':'
perl5='perl'
perl=''
-perl_patchlevel='13165'
+perl_patchlevel='14368'
perladmin='yourname@yourhost.yourplace.com'
perllibs='-lm -lutil'
-perlpath='/opt/perl/bin/perl'
+perlpath='/opt/perl/bin/perl5.7.2'
pg='pg'
phostname=''
pidtype='pid_t'
vendorprefix=''
vendorprefixexp=''
version='5.7.2'
-version_patchlevel_string='version 7 subversion 2 patch 13165'
+version_patchlevel_string='version 7 subversion 2 patch 14368'
versiononly='define'
vi=''
voidflags='15'
PERL_API_REVISION=5
PERL_API_VERSION=5
PERL_API_SUBVERSION=0
-PERL_PATCHLEVEL=13165
+PERL_PATCHLEVEL=14368
PERL_CONFIG_SH=true
# Variables propagated from previous config.sh file.
pp_sys_cflags='ccflags="$ccflags -DNO_EFF_ONLY_OK"'
/*
* Package name : perl5
* Source directory : .
- * Configuration time: Fri Nov 23 21:51:58 EET 2001
+ * Configuration time: Tue Jan 22 18:37:28 EET 2002
* Configured by : jhi
* Target system : osf1 alpha.hut.fi v4.0 878 alpha
*/
#define const
#endif
-/* HAS_CRYPT:
- * This symbol, if defined, indicates that the crypt routine is available
- * to encrypt passwords and the like.
- */
-#define HAS_CRYPT /**/
-
/* HAS_CUSERID:
* This symbol, if defined, indicates that the cuserid routine is
* available to get character login names.
*/
#define HAS_SETSID /**/
-/* Shmat_t:
- * This symbol holds the return type of the shmat() system call.
- * Usually set to 'void *' or 'char *'.
- */
-/* HAS_SHMAT_PROTOTYPE:
- * This symbol, if defined, indicates that the sys/shm.h includes
- * a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
- * but not always right so it should be emitted by the program only
- * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
- */
-#define Shmat_t void * /**/
-#define HAS_SHMAT_PROTOTYPE /**/
-
/* HAS_STRCHR:
* This symbol is defined to indicate that the strchr()/strrchr()
* functions are available for string searching. If not, try the
*/
/*#define I_MEMORY / **/
-/* I_NDBM:
- * This symbol, if defined, indicates that <ndbm.h> exists and should
- * be included.
- */
-#define I_NDBM /**/
-
/* I_NET_ERRNO:
* This symbol, if defined, indicates that <net/errno.h> exists and
* should be included.
*/
/*#define I_VFORK / **/
-/* CAN_PROTOTYPE:
- * If defined, this macro indicates that the C compiler can handle
- * function prototypes.
- */
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
-#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
-
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* preprocessor can make decisions based on it.
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
#define PERL_XS_APIVERSION "5.005"
#define PERL_PM_APIVERSION "5.005"
+/* HAS_CRYPT:
+ * This symbol, if defined, indicates that the crypt routine is available
+ * to encrypt passwords and the like.
+ */
+#define HAS_CRYPT /**/
+
/* SETUID_SCRIPTS_ARE_SECURE_NOW:
* This symbol, if defined, indicates that the bug that prevents
* setuid scripts from being secure is not present in this kernel.
/*#define SETUID_SCRIPTS_ARE_SECURE_NOW / **/
/*#define DOSUID / **/
+/* Shmat_t:
+ * This symbol holds the return type of the shmat() system call.
+ * Usually set to 'void *' or 'char *'.
+ */
+/* HAS_SHMAT_PROTOTYPE:
+ * This symbol, if defined, indicates that the sys/shm.h includes
+ * a prototype for shmat(). Otherwise, it is up to the program to
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
+ * but not always right so it should be emitted by the program only
+ * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
+ */
+#define Shmat_t void * /**/
+#define HAS_SHMAT_PROTOTYPE /**/
+
+/* I_NDBM:
+ * This symbol, if defined, indicates that <ndbm.h> exists and should
+ * be included.
+ */
+#define I_NDBM /**/
+
/* I_STDARG:
* This symbol, if defined, indicates that <stdarg.h> exists and should
* be included.
#define I_STDARG /**/
/*#define I_VARARGS / **/
+/* CAN_PROTOTYPE:
+ * If defined, this macro indicates that the C compiler can handle
+ * function prototypes.
+ */
+/* PROTO_:
+ * This macro is used to declare function parameters for folks who want
+ * to make declarations with prototypes using a different style than
+ * the above macros. Use double parentheses. For example:
+ *
+ * int main PROTO_((int argc, char *argv[]));
+ */
+#define CAN_PROTOTYPE /**/
+#ifdef CAN_PROTOTYPE
+#define PROTO_(args) args
+#else
+#define PROTO_(args) ()
+#endif
+
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* on this system to execute Bourne shell scripts. Usually, this will be
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO / **/
Perl Kit, Version 5.0
- Copyright 1989-2001, Larry Wall
+ Copyright 1989-2002, Larry Wall
All rights reserved.
This program is free software; you can redistribute it and/or modify
+/* XSUB.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#ifndef _INC_PERL_XSUB_H
#define _INC_PERL_XSUB_H 1
/* av.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* av.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
+/* cc_runtime.h
+ *
+ * Copyright (c) 1998-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#define DOOP(ppname) PUTBACK; PL_op = ppname(aTHX); SPAGAIN
#define CCPP(s) OP * s(pTHX)
*/
#$d_setsid HAS_SETSID /**/
-/* Shmat_t:
- * This symbol holds the return type of the shmat() system call.
- * Usually set to 'void *' or 'char *'.
- */
-/* HAS_SHMAT_PROTOTYPE:
- * This symbol, if defined, indicates that the sys/shm.h includes
- * a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
- * but not always right so it should be emitted by the program only
- * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
- */
-#define Shmat_t $shmattype /**/
-#$d_shmatprototype HAS_SHMAT_PROTOTYPE /**/
-
/* HAS_STRCHR:
* This symbol is defined to indicate that the strchr()/strrchr()
* functions are available for string searching. If not, try the
*/
#$i_vfork I_VFORK /**/
-/* CAN_PROTOTYPE:
- * If defined, this macro indicates that the C compiler can handle
- * function prototypes.
- */
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
-#$prototype CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
-
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* preprocessor can make decisions based on it.
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
#$d_drand48proto HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
#$d_sbrkproto HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#$d_telldirproto HAS_TELLDIR_PROTO /**/
#$d_suidsafe SETUID_SCRIPTS_ARE_SECURE_NOW /**/
#$d_dosuid DOSUID /**/
+/* Shmat_t:
+ * This symbol holds the return type of the shmat() system call.
+ * Usually set to 'void *' or 'char *'.
+ */
+/* HAS_SHMAT_PROTOTYPE:
+ * This symbol, if defined, indicates that the sys/shm.h includes
+ * a prototype for shmat(). Otherwise, it is up to the program to
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
+ * but not always right so it should be emitted by the program only
+ * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
+ */
+#define Shmat_t $shmattype /**/
+#$d_shmatprototype HAS_SHMAT_PROTOTYPE /**/
+
/* I_NDBM:
* This symbol, if defined, indicates that <ndbm.h> exists and should
* be included.
#$i_stdarg I_STDARG /**/
#$i_varargs I_VARARGS /**/
+/* CAN_PROTOTYPE:
+ * If defined, this macro indicates that the C compiler can handle
+ * function prototypes.
+ */
+/* PROTO_:
+ * This macro is used to declare function parameters for folks who want
+ * to make declarations with prototypes using a different style than
+ * the above macros. Use double parentheses. For example:
+ *
+ * int main PROTO_((int argc, char *argv[]));
+ */
+#$prototype CAN_PROTOTYPE /**/
+#ifdef CAN_PROTOTYPE
+#define PROTO_(args) args
+#else
+#define PROTO_(args) ()
+#endif
+
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* on this system to execute Bourne shell scripts. Usually, this will be
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
#$d_sockatmarkproto HAS_SOCKATMARK_PROTO /**/
/* cop.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* cv.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* deb.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* doio.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* doop.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
+/* dosish.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#define ABORT() abort();
#ifndef SH_PATH
/* dump.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
s |void |save_lines |AV *array|SV *sv
s |OP* |doeval |int gimme|OP** startop
s |PerlIO *|doopen_pmc |const char *name|const char *mode
+s |bool |path_is_absolute|char *name
#endif
#if defined(PERL_IN_PP_HOT_C) || defined(PERL_DECL_PROT)
#endif
#if defined(PERL_IN_UNIVERSAL_C) || defined(PERL_DECL_PROT)
-s |SV*|isa_lookup |HV *stash|const char *name|int len|int level
+s |SV*|isa_lookup |HV *stash|const char *name|HV *name_stash|int len|int level
#endif
#if defined(PERL_IN_LOCALE_C) || defined(PERL_DECL_PROT)
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * embed.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
/* (Doing namespace management portably in C is really gross.) */
#define save_lines S_save_lines
#define doeval S_doeval
#define doopen_pmc S_doopen_pmc
+#define path_is_absolute S_path_is_absolute
#endif
#if defined(PERL_IN_PP_HOT_C) || defined(PERL_DECL_PROT)
#define do_maybe_phash S_do_maybe_phash
#define save_lines(a,b) S_save_lines(aTHX_ a,b)
#define doeval(a,b) S_doeval(aTHX_ a,b)
#define doopen_pmc(a,b) S_doopen_pmc(aTHX_ a,b)
+#define path_is_absolute(a) S_path_is_absolute(aTHX_ a)
#endif
#if defined(PERL_IN_PP_HOT_C) || defined(PERL_DECL_PROT)
#define do_maybe_phash(a,b,c,d,e) S_do_maybe_phash(aTHX_ a,b,c,d,e)
# endif
#endif
#if defined(PERL_IN_UNIVERSAL_C) || defined(PERL_DECL_PROT)
-#define isa_lookup(a,b,c,d) S_isa_lookup(aTHX_ a,b,c,d)
+#define isa_lookup(a,b,c,d,e) S_isa_lookup(aTHX_ a,b,c,d,e)
#endif
#if defined(PERL_IN_LOCALE_C) || defined(PERL_DECL_PROT)
#define stdize_locale(a) S_stdize_locale(aTHX_ a)
walk_table(\&write_protos, 'proto.h', <<'EOT');
/*
+ * proto.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
* This file is autogenerated from data in embed.pl. Edit that file
* and run 'make regen_headers' to effect changes.
walk_table(\&write_global_sym, 'global.sym', <<'EOT');
#
+# global.sym
+#
+# Copyright (c) 1997-2002, Larry Wall
+#
+# You may distribute under the terms of either the GNU General Public
+# License or the Artistic License, as specified in the README file.
+#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
# This file is autogenerated from data in embed.pl. Edit that file
# and run 'make regen_headers' to effect changes.
open(EM, '> embed.h') or die "Can't create embed.h: $!\n";
print EM <<'END';
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * embed.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
/* (Doing namespace management portably in C is really gross.) */
or die "Can't create embedvar.h: $!\n";
print EM <<'END';
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * embedvar.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
/* (Doing namespace management portably in C is really gross.) */
open(CAPIH, '> perlapi.h') or die "Can't create perlapi.h: $!\n";
print CAPIH <<'EOT';
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * perlapi.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
/* declare accessor functions for Perl variables */
#ifndef __perlapi_h__
close CAPIH;
print CAPI <<'EOT';
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * perlapi.c
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
#include "EXTERN.h"
#include "perl.h"
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * embedvar.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
/* (Doing namespace management portably in C is really gross.) */
#if defined(NEED_newCONSTSUB)
static
#else
-extern void newCONSTSUB _((HV * stash, char * name, SV *sv));
+extern void newCONSTSUB(HV * stash, char * name, SV *sv);
#endif
#if defined(NEED_newCONSTSUB) || defined(NEED_newCONSTSUB_GLOBAL)
rmdir $dir;
if (scalar(@a) != 0 || GLOB_ERROR == 0) {
if ($^O eq 'vos') {
- print "not ok 6 -- hit VOS bug posix-956\n";
+ print "not ok 6 # TODO hit VOS bug posix-956\n";
} else {
print "not ok 6\n";
}
Exporter
File::Copy
File::Spec
-unicore/CombiningClass.pl or unicode/CombiningClass.pl
-unicore/Decomposition.pl or unicode/Decomposition.pl
-unicore/CompExcl.txt or unicode/CompExcl.txt
+unicore/CombiningClass.pl or unicode/CombiningClass.pl
+unicore/Decomposition.pl or unicode/Decomposition.pl
+unicore/CompositionExclusions.txt or unicode/CompExcl.txt
and for the Non-XS version, in addition to the above,
Lingua::KO::Hangul::Util 0.06
my($f, $fh);
foreach my $d (@INC) {
use File::Spec;
- $f = File::Spec->catfile($d, "unicore", "CompExcl.txt");
+ $f = File::Spec->catfile($d, "unicore", "CompositionExclusions.txt");
last if open($fh, $f);
$f = File::Spec->catfile($d, "unicode", "CompExcl.txt");
last if open($fh, $f);
+/* fakestdio.h
+ *
+ * Copyright (c) 2000-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/*
* This is "source level" stdio compatibility mode.
* We try and #define stdio functions in terms of PerlIO.
+/* fakethr.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
typedef int perl_mutex;
typedef int perl_key;
/* form.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#
+# global.sym
+#
+# Copyright (c) 1997-2002, Larry Wall
+#
+# You may distribute under the terms of either the GNU General Public
+# License or the Artistic License, as specified in the README file.
+#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
# This file is autogenerated from data in embed.pl. Edit that file
# and run 'make regen_headers' to effect changes.
+/* globals.c
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#include "INTERN.h"
#define PERL_IN_GLOBALS_C
#include "perl.h"
/* gv.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* gv.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* handy.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
# Make command.
make="/system/gnu_library/bin/gmake"
-_make="/system/gnu_library/bin/gmake"
+# indented to not put it into config.sh
+ _make="/system/gnu_library/bin/gmake"
# Architecture name
archname="hppa1.1"
# VOS has a link() function but it is a dummy.
d_link="undef"
+
+# VOS does not have truncate() but we supply one in vos.c
+d_truncate="define"
+archobjs="vos.o"
+
+# Help gmake find vos.c
+test -h vos.c || ln -s vos/vos.c vos.c
/* hv.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* hv.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* The number of placeholders in the enumerated-keys hash */
#define XHvPLACEHOLDERS(xhv) ((xhv)->xhv_placeholders)
-/* the number of keys that exist() (i.e. excluding placeholers) */
-#define XHvUSEDKEYS(xhv) (XHvTOTALKEYS(xhv) - XHvPLACEHOLDERS(xhv))
+/* the number of keys that exist() (i.e. excluding placeholders) */
+#define XHvUSEDKEYS(xhv) (XHvTOTALKEYS(xhv) - (IV)XHvPLACEHOLDERS(xhv))
/*
* HvKEYS gets the number of keys that actually exist(), and is provided
+/*
+ * keywords.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
#define KEY_NULL 0
#define KEY___FILE__ 1
#define KEY___LINE__ 2
open(KW, ">keywords.h") || die "Can't create keywords.h: $!\n";
select KW;
+print <<EOM;
+/*
+ * keywords.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+EOM
+
# Read & print data.
$keynum = 0;
if ($Is_Dosish || $^O eq 'MacOS') ;
($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,$atime,$mtime,$ctime,
$blksize,$blocks) = stat($Dfile);
- ok(($mode & 0777) == 0640 , "File permissions");
+ ok(($mode & 0777) == ($^O eq 'vos' ? 0750 : 0640) , "File permissions");
}
while (($key,$value) = each(%h)) {
for $key (keys %Prepend_dot_dot) {
next unless defined $self->{PARENT}{$key};
$self->{$key} = $self->{PARENT}{$key};
- # PERL and FULLPERL may be command verbs instead of full
- # file specifications under VMS. If so, don't turn them
- # into a filespec.
- $self->{$key} = $self->catdir("..",$self->{$key})
- unless $self->file_name_is_absolute($self->{$key})
- || ($^O eq 'VMS' and ($key =~ /PERL$/ && $self->{$key} =~ /^[\w\-\$]+$/));
+ unless ($^O eq 'VMS' && $key =~ /PERL$/) {
+ $self->{$key} = $self->catdir("..",$self->{$key})
+ unless $self->file_name_is_absolute($self->{$key});
+ } else {
+ # PERL or FULLPERL will be a command verb or even a command with
+ # an argument instead of a full file specification under VMS. So,
+ # don't turn the command into a filespec, but do add a level to the
+ # path of the argument if not already absolute.
+
+ my @cmd = split /\s+/, $self->{$key};
+ $cmd[1] = $self->catfile('[-]',$cmd[1])
+ unless (scalar(@cmd) < 2 || $self->file_name_is_absolute($cmd[1]));
+ $self->{$key} = join(' ', @cmd);
+ }
}
if ($self->{PARENT}) {
$self->{PARENT}->{CHILDREN}->{$newclass} = $self;
}
BEGIN {
- use Test::More tests => 21;
+ use Test::More tests => 24;
use File::Spec;
}
ok( abs($now - $stamp) <= 1, 'checking modify time stamp' ) ||
print "# mtime == $stamp, should be $now\n";
+SKIP: {
+ if ($^O eq 'amigaos' || $^O eq 'os2' || $^O eq 'MSWin32' ||
+ $^O eq 'NetWare' || $^O eq 'dos' || $^O eq 'cygwin') {
+ skip( "different file permission semantics on $^O\n", 3);
+ }
+
+ # change a file to execute-only
+ @ARGV = ( 0100, 'ecmdfile' );
+ ExtUtils::Command::chmod();
+
+ is( ((stat('ecmdfile'))[2] & 07777) & 0700,
+ 0100, 'change a file to execute-only' );
+
# change a file to read-only
+ @ARGV = ( 0400, 'ecmdfile' );
+ ExtUtils::Command::chmod();
+
+ is( ((stat('ecmdfile'))[2] & 07777) & 0700,
+ ($^O eq 'vos' ? 0500 : 0400), 'change a file to read-only' );
+
+ # change a file to write-only
+ @ARGV = ( 0200, 'ecmdfile' );
+ ExtUtils::Command::chmod();
+
+ is( ((stat('ecmdfile'))[2] & 07777) & 0700,
+ ($^O eq 'vos' ? 0700 : 0200), 'change a file to write-only' );
+ }
+
+ # change a file to read-write
@ARGV = ( 0600, 'ecmdfile' );
ExtUtils::Command::chmod();
- is( ((stat('ecmdfile'))[2] & 07777) & 0700, 0600, 'change a file to read-only' );
+ is( ((stat('ecmdfile'))[2] & 07777) & 0700,
+ ($^O eq 'vos' ? 0700 : 0600), 'change a file to read-write' );
# mkpath
@ARGV = ( File::Spec->join( 'ecmddir', 'temp2' ) );
last;
}
}
- openunicode(\$UNICODEFH, "Unicode.txt");
+ openunicode(\$UNICODEFH, "UnicodeData.txt");
if (defined $UNICODEFH) {
use Search::Dict 1.02;
if (look($UNICODEFH, "$hexk;", { xfrm => sub { $_[0] =~ /^([^;]+);(.+)/; sprintf "%06X;$2", hex($1) } } ) >= 0) {
sub _compexcl {
unless (%COMPEXCL) {
- if (openunicode(\$COMPEXCLFH, "CompExcl.txt")) {
+ if (openunicode(\$COMPEXCLFH, "CompositionExclusions.txt")) {
while (<$COMPEXCLFH>) {
if (/^([0-9A-F]+) \# /) {
my $code = hex($1);
sub _casefold {
unless (%CASEFOLD) {
- if (openunicode(\$CASEFOLDFH, "CaseFold.txt")) {
+ if (openunicode(\$CASEFOLDFH, "CaseFolding.txt")) {
while (<$CASEFOLDFH>) {
if (/^([0-9A-F]+); ([CFSI]); ([0-9A-F]+(?: [0-9A-F]+)*);/) {
my $code = hex($1);
sub _casespec {
unless (%CASESPEC) {
- if (openunicode(\$CASESPECFH, "SpecCase.txt")) {
+ if (openunicode(\$CASESPECFH, "SpecialCasing.txt")) {
while (<$CASESPECFH>) {
if (/^([0-9A-F]+); ([0-9A-F]+(?: [0-9A-F]+)*)?; ([0-9A-F]+(?: [0-9A-F]+)*)?; ([0-9A-F]+(?: [0-9A-F]+)*)?; (\w+(?: \w+)*)?/) {
my ($hexcode, $lower, $title, $upper, $condition) =
upper => $oldupper,
condition => $oldcondition };
} else {
- warn __PACKAGE__, ": SpecCase.txt:", $., ": No oldlocale for 0x$hexcode\n"
+ warn __PACKAGE__, ": SpecialCasing.txt:", $., ": No oldlocale for 0x$hexcode\n"
}
}
my ($locale) =
$_;
}
+sub uniescape {
+ join("",
+ map { $_ > 255 ? sprintf("\\x{%04X}", $_) : chr($_) }
+ unpack("U*", $_[0]));
+}
+
sub stringify {
local($_,$noticks) = @_;
local($v) ;
} elsif ($unctrl eq 'unctrl') {
s/([\"\\])/\\$1/g ;
s/([\000-\037\177])/'^'.pack('c',ord($1)^64)/eg;
+ # uniescape?
s/([\200-\377])/'\\0x'.sprintf('%2X',ord($1))/eg
if $quoteHighBit;
} elsif ($unctrl eq 'quote') {
s/\033/\\e/g;
s/([\000-\037\177])/'\\c'.chr(ord($1)^64)/eg;
}
+ $_ = uniescape($_);
s/([\200-\377])/'\\'.sprintf('%3o',ord($1))/eg if $quoteHighBit;
($noticks || /^\d+(\.\d*)?\Z/)
? $_
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
##
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
##
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
+++ /dev/null
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
-
- "http://www.w3.org/TR/REC-html40/loose.dtd">
-
-<html>
-
-<head>
-<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
-<meta http-equiv="Content-Language" content="en-us">
-<meta name="GENERATOR" content="Microsoft FrontPage 4.0">
-<meta name="ProgId" content="FrontPage.Editor.Document">
-<meta name="keywords"
-content="unicode, normalization, composition, decomposition">
-<meta name="description" content="Specifies the Unicode Normalization Formats">
-<title>UCD: Unicode NamesList File Format</title>
-<link rel="stylesheet" type="text/css" href="http://www.unicode.org/unicode.css">
-<style type="text/css">
-
-<!--
-
-.foo { }
--->
-
-</style>
-</head>
-
-<body bgcolor="#ffffff">
-
-<table width="100%" cellpadding="0" cellspacing="0" border="0">
- <tr>
- <td>
- <table width="100%" border="0" cellpadding="0" cellspacing="0">
- <tr>
- <td class="icon"><a href="http://www.unicode.org"><img border="0"
- src="http://www.unicode.org/webscripts/logo60s2.gif" align="middle"
- alt="[Unicode]" width="34" height="33"></a> <a
- class="bar" href="UnicodeCharacterDatabase-3.1.0.html">Unicode Character
- Database</a></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td class="gray"> </td>
- </tr>
-</table>
- <h1>Unicode NamesList File Format</h1>
-<table height="87" cellSpacing="2" cellPadding="0" width="100%" border="1">
- <tbody>
- <tr>
- <td vAlign="top" width="144">Revision</td>
- <td vAlign="top">3.1</td>
- </tr>
- <tr>
- <td vAlign="top" width="144">Authors</td>
- <td vAlign="top">Asmus Freytag</td>
- </tr>
- <tr>
- <td vAlign="top" width="144">Date</td>
- <td vAlign="top">2001-02-26</td>
- </tr>
- <tr>
- <td vAlign="top" width="144">This Version</td>
- <td vAlign="top"><a href="http://http://www.unicode.org/Public/3.1-Update/NamesList-2.html">http://www.unicode.org/Public/3.1-Update/NamesList-2.html</a></td>
- </tr>
- <tr>
- <td vAlign="top" width="144">Previous Version</td>
- <td vAlign="top"><a href="http://http://www.unicode.org/Public/3.0-Update/NamesList-1.html">http://www.unicode.org/Public/3.0-Update/NamesList-1.html</a></td>
- </tr>
- <tr>
- <td vAlign="top" width="144">Latest Version</td>
- <td vAlign="top"><a href="http://www.unicode.org/Public/UNIDATA/NamesList.html">http://www.unicode.org/Public/UNIDATA/NamesList.html</a></td>
- </tr>
- </tbody>
-</table>
-<h3>
-<br>
-<i>Summary</i></h3>
-<blockquote>
- <p>This file describes the format and contents of NamesList.txt</p>
-</blockquote>
-<h3><i>Status</i></h3>
-<blockquote>
-<p>
-<i>The file and the files described herein are part of the <a href="UnicodeCharacterDatabase-3.1.0.html"> Unicode Character Database</a>
-(UCD)
-and are governed by the <a href="#Terms of Use">UCD Terms of Use</a> stated at the end.</i></p>
-</blockquote>
- <hr width="50%">
-
-<h2>1.0 Introduction</h2>
-
-<p>The Unicode name list file NamesList.txt (also NamesList.lst) is a plain text file used
-to drive the layout of the character code charts in the Unicode Standard. The information
-in this file is a combination of several fields from the UnicodeData.txt and Blocks.txt files,
-together with additional annotations for many characters. This document describes the
-syntax rules for the file format, but also gives brief information on how each construct
-is rendered when laid out for the book. Some of the syntax elements were used in
-preparation of the drafts of the book and may not be present in the final, released form
-of the NamesList.txt file.</p>
-
-<p>The same input file can be used to do the draft preparation for ISO/IEC 10646 (referred
-below as ISO-style). This necessitates the presence of some information in the name list
-file that is not needed (and in fact removed during parsing) for the Unicode book.</p>
-
-<p>With access to the layout program (unibook.exe) it is a simple matter of creating
-name lists for the purpose of formatting working drafts containing proposed characters.</p>
-
-<h3>1.1 NamesList File Overview</h3>
-
-<p>The *.lst files are plain text files which in their most simple form look like this</p>
-
-<p>@@<tab>0020<tab>BASIC LATIN<tab>007F<br>
-; this is a file comment (ignored)<br>
-0020<tab>SPACE<br>
-0021<tab>EXCLAMATION MARK<br>
-0022<tab>QUOTATION MARK<br>
-. . . <br>
-007F<tab>DELETE</p>
-
-<p>The semicolon (as first character), @ and <tab> characters are used by the file
-syntax and must be provided as shown. Hexadecimal digits must be in UPPER CASE). A double
-@@ introduces a block header, with the title, and start and ending code of the block
-provided as shown.</p>
-
-<p>For an ISO-style, minimal name list, only the NAME_LINE and BLOCKHEADER and their
-constituent syntax elements are needed.</p>
-
-<p>The full syntax with all the options is provided in the following sections.</p>
-
-<h3>1.2 NamesList File Structure</h3>
-
-<p>This section gives defines the overall file structure</p>
-
-<pre><strong>NAMELIST: TITLE_PAGE* BLOCK*
-</strong>
-<strong>TITLE_PAGE: TITLE
- | TITLE_PAGE SUBTITLE
- | TITLE_PAGE SUBHEADER
- | TITLE_PAGE IGNORED_LINE
- | TITLE_PAGE EMPTY_LINE
- | TITLE_PAGE COMMENTLINE
- | TITLE_PAGE NOTICE
- | TITLE_PAGE PAGEBREAK
-</strong>
-<strong>BLOCK: BLOCKHEADER
- | BLOCK CHAR_ENTRY
- | BLOCK SUBHEADER
- | BLOCK NOTICE
- | BLOCK EMPTY_LINE
- | BLOCK IGNORED_LINE
- | BLOCK PAGEBREAK
-
-CHAR_ENTRY: NAME_LINE | RESERVED_LINE
- | CHAR_ENTRY ALIAS_LINE
- | CHAR_ENTRY COMMENT_LINE
- | CHAR_ENTRY CROSS_REF
- | CHAR_ENTRY DECOMPOSITION
- | CHAR_ENTRY COMPAT_MAPPING
- | CHAR_ENTRY IGNORED_LINE
- | CHAR_ENTRY EMPTY_LINE
- | CHAR_ENTRY NOTICE
-</strong></pre>
-
-<p>In other words:<br>
-<br>
-Neither TITLE nor SUBTITLE may occur after the first BLOCKHEADER. </p>
-
-<p>Only TITLE, SUBTITLE, SUBHEADER, PAGEBREAK, COMMENT_LINE, and IGNORED_LINE may
-occur before the first BLOCKHEADER.</p>
-
-<p>Directly following either a NAME_LINE or a RESERVED_LINE an uninterrupted sequence of
-the following lines may occur (in any order and repeated as often as needed): ALIAS_LINE,
-CROSS_REF, DECOMPOSITION, COMPAT_MAPPING, NOTICE, EMPTY_LINE and IGNORED_LINE.</p>
-
-<p>Except for EMPTY_LINE, NOTICE and IGNORED_LINE, none of these lines may occur in any other
-place. </p>
-
-<p>Note: A NOTICE displays differently depending on whether it follows a header or title
-or is part of a CHAR_ENTRY.</p>
-
-<h3>1.3 NamesList File Elements</h3>
-
-<p>This section provides the details of the syntax for the individual elements.</p>
-
-<pre><small><strong>ELEMENT SYNTAX</strong> // How rendered</small></pre>
-
-<pre><small><strong>NAME_LINE: CHAR <tab> LINE
-</strong> // the CHAR and the corresponding image are echoed,
- // followed by the name as given in LINE
-
-<strong> CHAR TAB NAME COMMENT LF
-</strong> // Names may have a comment, which is stripped off
- // unless the file is parsed for an ISO style list
-
-<strong>RESERVED_LINE: CHAR TAB <reserved>
-</strong> // the CHAR is echoed followed by an icon for the
- // reserved character and a fixed string e.g. <reserved>
-
-<strong>COMMMENT_LINE: <tab> "*" SP EXPAND_LINE
-</strong> // * is replaced by BULLET, output line as comment
- <strong><tab> EXPAND_LINE</strong>
- // output line as comment
-
-<strong>ALIAS_LINE: <tab> "=" SP LINE
-</strong> // replace = by itself, output line as alias
-
-<strong>CROSS_REF: <tab> "X" SP EXPAND_LINE
-</strong> // X is replaced by a right arrow
-<strong> <tab> "X" SP "(" STRING SP "-" SP CHAR ")"
-</strong> // X is replaced by a right arrow
- // the "(", "-", ")" are removed, the
- // order of CHAR and STRING is reversed
- // i.e. both inputs result in the same output
-
-<strong>IGNORED_LINE: <tab> ";" EXPAND_LINE
-EMPTY_LINE: LF
-</strong> // empty lines and file comments are ignored
-
-<strong>DECOMPOSITION: <tab> ":" EXPAND_LINE
-</strong> // replace ':' by EQUIV, expand line into
- // decomposition
-
-<strong>COMPAT_MAPPING: <tab> "#" SP EXPAND_LINE
-</strong> // replace '#' by APPROX, output line as mapping
-
-<strong>NOTICE: "@+" <tab> LINE
-</strong> // skip '@+', output text as notice
-<strong> "@+" TAB * SP LINE
-</strong> // skip '@', output text as notice
- // "*" expands to a bullet character
- // Notices following a character code apply to the
- // character and are indented. Notices not following
- // a character code apply to the page/block/column
- // and are italicized, but not indented
-
-<strong>SUBTITLE: "@@@+" <tab> LINE
-</strong> // skip "@@@+", output text as subtitle
-
-<strong>SUBHEADER: "@" <tab> LINE
-</strong> // skip '@', output line as text as column header
-
-<strong>BLOCKHEADER: "@@" <tab> BLOCKSTART <tab> BLOCKNAME <tab> BLOCKEND
-</strong> // skip "@@", cause a page break and optional
- // blank page, then output one or more charts
- // followed by the list of character names.
- // use BLOCKSTART and BLOCKEND to define the
- // characters belonging to a block
- // use blockname in page and table headers
- <strong> "@@" <tab> BLOCKSTART <tab> BLOCKNAME COMMENT <tab> BLOCKEND
- </strong>// if a comment is present it replaces the blockname
- // when an ISO-style namelist is laid out
-
-<strong>BLOCKSTART: CHAR</strong> // first character position in block
-<strong>BLOCKEND: CHAR</strong> // last character position in block
-<strong>PAGE_BREAK: "@@"</strong> // insert a (column) break
-
-<strong>TITLE: "@@@" <tab> LINE</strong>
- // skip "@@@", output line as text
- // Title is used in page headers
-
-<strong>EXPAND_LINE: {CHAR | STRING}+ LF </strong>
- // all instances of CHAR *) are replaced by
- // CHAR NBSP x NBSP where x is the single Unicode
- // character corresponding to char
- // If character is combining, it is replaced with
- // CHAR NBSP <circ> x NBSP where <circ> is the
- // dotted circle</small></pre>
-
-<p><strong>Notes:</strong>
-
-</p>
-
-<ul>
- <li>Blocks must be aligned on 16-code point boundary and contain an integer
- multiple of code points. The exception to that rule is for blocks of
- ideographs etc. for which no names are listed in the file. Such blocks must
- end on the actual last character.</li>
- <li>Blocks must be non-overlapping and in ascending order. Namelines
- must be in ascending order and following the block header for the block to
- which they belong.</li>
- <li>Reserved entries are optional, and will be supplied automatically. They
- are required whenever followed by ALIAS_LINE, COMMENT_LINE or CROSS_REF</li>
-</ul>
-
-<h3><strong>1.4 NamesList File Primitives</strong></h3>
-
-<p>The following are the primitives and terminals for the NamesList syntax.</p>
-
-<pre><strong><small>LINE: STRING LF
-COMMENT: "(" NAME ")"
- "(" NAME ")" "*" </small></strong><small>
-<strong>BLOCKNAME:</strong> <sequence of Latin-1 characters, except "(" and ")">
-<strong>NAME</strong>: <sequence of uppercase ASCII letters, digit and hyphen>
-<strong>STRING</strong>: <sequence of Latin-1 characters>
-<strong>CHAR</strong>: <strong>X X X X</strong>
- <strong>| X X X X X</strong>
- <strong>| X X X X X X</strong></small>
-<small><strong>X: "0"|"1"|"2"|"3"|"4"|"5"|"6"|"7"|"8"|"9"|"A"|"B"|"C"|"D"|"E"|"F"
-<tab>:</strong> <sequence of one or more ASCII tab characters 0x09>
-<strong>SP</strong>: <ASCII 0x20>
-<strong>LF</strong>: <any sequence of ASCII 0x0A and 0x0D>
-</small></pre>
-
-<p><strong>Notes:</strong>
-
-<ul>
- <li>Special lookahead logic prevents a mention of a 4 digit standard, such as ISO 9999 from
- being misinterpreted as ISO CHAR. The - in a character range CHAR-CHAR is
- replaced by an EN DASH.</li>
- <li>Use of Latin-1 is supported in unibook.exe, but not portably, unless the file is encoded as
- UTF-16LE.</li>
- <li>The final LF in the file must be present</li>
- <li>A CHAR inside ' or " is expanded, but only its glyph image is printed,
- the
- code value is not echoed.</li>
- <li>Straight quotes in an EXPAND_LINE are replaced by curly quotes using English rules.
- Apostrophes are supported, but nested quotes are not.</li>
-</ul>
-<h2>Modifications</h2>
-<p>Use of 4-6 digit hex notation is now supported.</p>
- <hr width="50%">
-<h2>
-UCD <a name="Terms of Use">Terms of Use</a></h2>
-<h3>
-<i>Disclaimer</i></h3>
-<blockquote>
- <p><i>The Unicode Character Database is provided as is by Unicode, Inc. No
- claims are made as to fitness for any particular purpose. No warranties of any
- kind are expressed or implied. The recipient agrees to determine applicability
- of information provided. If this file has been purchased on magnetic or
- optical media from Unicode, Inc., the sole remedy for any claim will be
- exchange of defective media within 90 days of receipt.</i></p>
- <p><i>This disclaimer is applicable for all other data files accompanying the
- Unicode Character Database, some of which have been compiled by the Unicode
- Consortium, and some of which have been supplied by other sources.</i></p>
-</blockquote>
-<h3><i>Limitations on Rights to Redistribute This Data</i></h3>
-<blockquote>
- <p><i>Recipient is granted the right to make copies in any form for internal
- distribution and to freely use the information supplied in the creation of
- products supporting the Unicode<sup>TM</sup> Standard. The files in the
- Unicode Character Database can be redistributed to third parties or other
- organizations (whether for profit or not) as long as this notice and the
- disclaimer notice are retained. Information can be extracted from these files
- and used in documentation or programs, as long as there is an accompanying
- notice indicating the source.</i></p>
-</blockquote>
- <hr width="50%">
- <div align="center">
- <center>
- <table cellspacing="0" cellpadding="0" border="0">
- <tr>
- <td><a href="../../../../../../index.html"><img
- src="http://www.unicode.org/img/hb_home.gif" border="0"
- alt="Home" width="40" height="49"></a><a
- href="../copyright.html"><img
- src="http://www.unicode.org/img/hb_mid.gif" border="0"
- alt="Terms of Use" width="152" height="49"></a><a
- href="mailto:info@unicode.org"><img
- src="http://www.unicode.org/img/hb_mail.gif" border="0"
- alt="E-mail" width="46" height="49"></a></td>
- </tr>
- </table>
- <script language="Javascript" src="http://www.unicode.org/webscripts/lastModified.js"></script>
- </center>
- </div>
-</form>
-
-</body>
-
-</html>
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
+++ /dev/null
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
-<html>
-
-<head>
-<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
-<meta http-equiv="Content-Language" content="en-us">
-<meta name="GENERATOR" content="Microsoft FrontPage 4.0">
-<meta name="ProgId" content="FrontPage.Editor.Document">
-<meta name="keywords"
-content="unicode, normalization, composition, decomposition">
-<meta name="description" content="Describes PropList.html">
-<title>UCD: Extended Character Properties</title>
-<link rel="stylesheet" type="text/css" href="http://www.unicode.org/unicode.css">
-</head>
-
-<body bgcolor="#ffffff">
-
-<table width="100%" cellpadding="0" cellspacing="0" border="0">
- <tr>
- <td>
- <table width="100%" border="0" cellpadding="0" cellspacing="0">
- <tr>
- <td class="icon"><a href="http://www.unicode.org"><img border="0"
- src="http://www.unicode.org/webscripts/logo60s2.gif" align="middle"
- alt="[Unicode]" width="34" height="33"></a> <a
- class="bar" href="UnicodeCharacterDatabase.html">Unicode Character
- Database</a></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td class="gray"> </td>
- </tr>
-</table>
-<h1>Extended Character Properties</h1>
-<table height="87" cellspacing="2" cellpadding="0" width="100%" border="1">
- <tbody>
- <tr>
- <td valign="top" width="144">Revision</td>
- <td valign="top">3.1.1</td>
- </tr>
- <tr>
- <td valign="top" width="144">Authors</td>
- <td valign="top">Mark Davis</td>
- </tr>
- <tr>
- <td valign="top" width="144">Date</td>
- <td valign="top">2001-07-12</td>
- </tr>
- <tr>
- <td valign="top" width="144">This Version</td>
- <td valign="top"><a
- href="http://www.unicode.org/Public/3.1-Update1/PropList-3.1.1.html">http://www.unicode.org/Public/3.1-Update1/PropList-3.1.1.html</a></td>
- </tr>
- <tr>
- <td valign="top" width="144">Previous Version</td>
- <td valign="top">n/a</td>
- </tr>
- <tr>
- <td valign="top" width="144">Latest Version</td>
- <td valign="top"><a
- href="http://www.unicode.org/Public/UNIDATA/PropList.html">http://www.unicode.org/Public/UNIDATA/PropList.html</a></td>
- </tr>
- </tbody>
-</table>
-<h3><i><br>
-Summary</i></h3>
-<blockquote>
- <p><i>This document describes the format and content of the PropList.txt data
- file in the Unicode Character Database (UCD).</i></p>
-</blockquote>
-<h3><i>Status</i></h3>
-<blockquote>
- <p><i>The file and the files described herein are part of the Unicode
- Character Database and governed by the <a href="#UCD_Terms">UCD Terms of Use</a>
- given below.</i></p>
- <p><i>For general information on file formats and table formats, and the
- implications of normative vs informative properties, see
- UnicodeCharacterDatabase.html.</i></p>
- <p><i><b>Warning: </b>the information in this file does not completely
- describe the use and interpretation of Unicode character properties and
- behavior. It must be used in conjunction with the data in the other files in
- the UCD, and relies on the notation and definitions supplied in <a
- href="http://www.unicode.org/unicode/standard/versions/Unicode3.0.html">The
- Unicode Standard</a>. All chapter references are to Version 3.1.0 of the
- standard.</i></p>
-</blockquote>
-<hr width="50%">
-<h2>Introduction</h2>
-<p align="left">PropList.txt contains extended properties that supplement the
-General Category property described in UnicodeData.html. Unlike the derived
-properties, the properties in PropList.txt cannot be derived directly from
-UnicodeData.txt or other data files of the UCD. These properties are listed in
-the following table.</p>
-<div align="center">
- <center>
- <table border="1" cellspacing="0" cellpadding="3" class="smallText">
- <tr>
- <th>Property Value</th>
- <th>N/I</th>
- <th>Definition and Usage</th>
- </tr>
- <tr>
- <th valign="top">White_space</th>
- <th valign="top">N</th>
- <td valign="top">Space characters and those format control characters
- (such as TAB, CR and LF) which should be treated by programming
- languages as "white space" for the purpose of parsing
- elements.
- <p><b>Note:</b> ZERO WIDTH SPACE and ZERO WIDTH NO-BREAK SPACE are not
- included, since their functions are restricted to line-break control.
- Their names are unfortunately misleading in this respect.</p>
- <p><b>Note: </b>There are other senses of "whitespace" that
- encompass a different set of characters.</p>
- </td>
- </tr>
- <tr>
- <th valign="top">Bidi_Control</th>
- <th valign="top">N</th>
- <td valign="top">Those format control characters which have specific
- functions in the Bidirectional Algorithm.</td>
- </tr>
- <tr>
- <th valign="top">Join_Control</th>
- <th valign="top">N</th>
- <td valign="top">Those format control characters which have specific
- functions for control of cursive joining and ligation.</td>
- </tr>
- <tr>
- <th valign="top">ASCII_Hex_Digit</th>
- <th valign="top">N</th>
- <td valign="top">ASCII characters commonly used for the representation of
- hexadecimal numbers.</td>
- </tr>
- <tr>
- <th valign="top">Dash</th>
- <th valign="top">I</th>
- <td valign="top">Those punctuation characters explicitly called out as
- dashes in the Unicode Standard, plus compatibility equivalents to those.
- Most of these have the Pd General Category, but some have the Sm General
- Category because of their use in mathematics.</td>
- </tr>
- <tr>
- <th valign="top">Hyphen</th>
- <th valign="top">I</th>
- <td valign="top">Those dashes used to mark connections between pieces of
- words, plus the Katakana middle dot. The Katakana middle dot functions
- like a hyphen, but is shaped like a dot rather than a dash.</td>
- </tr>
- <tr>
- <th valign="top">Quotation_Mark</th>
- <th valign="top">I</th>
- <td valign="top">Those punctuation characters that function as quotation
- marks.</td>
- </tr>
- <tr>
- <th valign="top">Terminal_Punctuation</th>
- <th valign="top">I</th>
- <td valign="top">Those punctuation characters that generally mark the end
- of textual units.</td>
- </tr>
- <tr>
- <th valign="top">Other_Math</th>
- <th valign="top">I</th>
- <td valign="top">Math characters that do not have the Sm General Category.</td>
- </tr>
- <tr>
- <th valign="top">Hex_Digit</th>
- <th valign="top">I</th>
- <td valign="top">Characters commonly used for the representation of
- hexadecimal numbers, plus their compatibility equivalents.</td>
- </tr>
- <tr>
- <th valign="top">Other_Alphabetic</th>
- <th valign="top">I</th>
- <td valign="top">Alphabetic characters that do not have L as their major
- class for the General Category (Lu, Ll, Lt, Lm, Lo).</td>
- </tr>
- <tr>
- <th valign="top">Ideographic</th>
- <th valign="top">I</th>
- <td valign="top">Characters considered to be CJKV (Chinese, Japanese,
- Korean, and Vietnamese) ideographs.</td>
- </tr>
- <tr>
- <th valign="top">Diacritic</th>
- <th valign="top">I</th>
- <td valign="top">Characters that linguistically modify the meaning of
- another character to which they apply. Some diacritics are not combining
- characters, and some combining characters are not diacritics.</td>
- </tr>
- <tr>
- <th valign="top">Extender</th>
- <th valign="top">I</th>
- <td valign="top">Characters whose principal function is to extend the
- value or shape of a preceding alphabetic character. Typical of these are
- length and iteration marks.</td>
- </tr>
- <tr>
- <th valign="top">Other_Lowercase</th>
- <th valign="top">I</th>
- <td valign="top">Lowercase characters that do not have the Ll General
- Category.</td>
- </tr>
- <tr>
- <th valign="top">Other_Uppercase</th>
- <th valign="top">I</th>
- <td valign="top">Uppercase characters that do not have the Lu General
- Category.</td>
- </tr>
- <tr>
- <th valign="top">Noncharacter_Code_Point</th>
- <th valign="top">N</th>
- <td valign="top">Code points that are explicitly defined as illegal for
- the encoding of characters. See <a
- href="http://www.unicode.org/unicode/reports/tr27/">Unicode 3.1</a> for
- more information.</td>
- </tr>
- </table>
- </center>
-</div>
-<h2><i><a name="UCD_Terms"><br>
-UCD Terms of Use</a></i></h2>
-<h3><i>Disclaimer</i></h3>
-<blockquote>
- <p><i>The Unicode Character Database is provided as is by Unicode, Inc. No
- claims are made as to fitness for any particular purpose. No warranties of any
- kind are expressed or implied. The recipient agrees to determine applicability
- of information provided. If this file has been purchased on magnetic or
- optical media from Unicode, Inc., the sole remedy for any claim will be
- exchange of defective media within 90 days of receipt.</i></p>
- <p><i>This disclaimer is applicable for all other data files accompanying the
- Unicode Character Database, some of which have been compiled by the Unicode
- Consortium, and some of which have been supplied by other sources.</i></p>
-</blockquote>
-<h3><i>Limitations on Rights to Redistribute This Data</i></h3>
-<blockquote>
- <p><i>Recipient is granted the right to make copies in any form for internal
- distribution and to freely use the information supplied in the creation of
- products supporting the Unicode<sup>TM</sup> Standard. The files in the
- Unicode Character Database can be redistributed to third parties or other
- organizations (whether for profit or not) as long as this notice and the
- disclaimer notice are retained. Information can be extracted from these files
- and used in documentation or programs, as long as there is an accompanying
- notice indicating the source.</i></p>
-</blockquote>
-<hr width="50%">
-<p align="center"><a href="http://www.unicode.org/unicode/copyright.html"><img
-src="http://www.unicode.org/img/hb_home.gif" border="0" alt="Home" width="40"
-height="49"><img src="http://www.unicode.org/img/hb_mid.gif" border="0"
-alt="Terms of Use" width="152" height="49"><img
-src="http://www.unicode.org/img/hb_mail.gif" border="0" alt="E-mail" width="46"
-height="49"></a>
-
-</body>
-
-</html>
http://www.unicode.org/Public/3.1-Update/
-and most of them were renamed to better fit 8.3 filename limitations,
-by which the Perl distribution tries to live. The renamings are listed
-in the file 'rename'.
-
The two big files, NormalizationTest.txt (2.0MB) and Unihan.txt (15.8MB)
-were not copied due to space considerations. Also not included are the
-derived files:
+were not copied due to space considerations. Also not included are any
+*.html files and the derived files:
DerivedBidiClass.txt
DerivedBinaryProperties.txt
DerivedNumericValues.txt
DerivedProperties.html
-The *.pl files are generated from these files by the 'mktables.PL' script.
-
-While the files have been renamed the links in the html files haven't.
+The *.pl files are generated from these files by the mktables script.
--
jhi@iki.fi
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
return <<'END';
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
+++ /dev/null
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
-
- "http://www.w3.org/TR/REC-html40/loose.dtd">
-
-<html>
-
-<head>
-<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
-<meta http-equiv="Content-Language" content="en-us">
-<meta name="GENERATOR" content="Microsoft FrontPage 4.0">
-<meta name="ProgId" content="FrontPage.Editor.Document">
-<link rel="stylesheet" href="http://www.unicode.org/unicode.css" type="text/css">
-<title>Unicode Character Database</title>
-</head>
-
-<body>
-
-<table width="100%" cellpadding="0" cellspacing="0" border="0">
- <tr>
- <td>
- <table width="100%" border="0" cellpadding="0" cellspacing="0">
- <tr>
- <td class="icon"><a href="http://www.unicode.org"><img border="0"
- src="http://www.unicode.org/webscripts/logo60s2.gif" align="middle"
- alt="[Unicode]" width="34" height="33"></a> <a
- class="bar" href="UnicodeCharacterDatabase.html">Unicode Character
- Database</a></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td class="gray"> </td>
- </tr>
-</table>
-<h1>UNICODE CHARACTER DATABASE</h1>
-<table border="1" cellspacing="2" cellpadding="0" height="87" width="100%">
- <tr>
- <td valign="TOP" width="144">Revision</td>
- <td valign="TOP">3.1.0</td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Authors</td>
- <td valign="TOP">Mark Davis and Ken Whistler</td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Date</td>
- <td valign="TOP">2001-02-28</td>
- </tr>
- <tr>
- <td valign="TOP" width="144">This Version</td>
- <td valign="TOP"><a
- href="http://http://www.unicode.org/Public/3.1-Update/UnicodeCharacterDatabase-3.1.0.html">http://www.unicode.org/Public/3.1-Update/UnicodeCharacterDatabase-3.1.0.html</a></td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Previous Version</td>
- <td valign="TOP"><a
- href="http://www.unicode.org/Public/3.0-Update1/UnicodeCharacterDatabase-3.0.1.html">http://www.unicode.org/Public/3.0-Update1/UnicodeCharacterDatabase-3.0.1.html</a></td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Latest Version</td>
- <td valign="TOP"><a
- href="http://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html">http://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html</a></td>
- </tr>
-</table>
-<h3><br>
-S<i>ummary</i></h3>
-<blockquote>
- <p><i>This document describes the format and content of the Unicode Character
- Database (UCD)</i></p>
-</blockquote>
-<h3><i>Status</i></h3>
-<blockquote>
- <p><i>The file and the files described herein are part of the Unicode
- Character Database and are governed by the <a href="#UCD_Terms">UCD Terms of
- Use</a> given below.</i></p>
- <p><i>The <a href="#References">References</a> provide related information
- that is useful in understanding this document.</i></p>
- <p><i><b>Warning: </b>the information in this file does not completely
- describe the use and interpretation of Unicode character properties and
- behavior. It must be used in conjunction with the data in the other files in
- the Unicode Character Database, and relies on the notation and definitions
- supplied in <a
- href="http://www.unicode.org/unicode/standard/versions/Unicode3.0.html">The
- Unicode Standard</a>. All chapter references are to Version 3.1.0 of the
- standard.</i></p>
-</blockquote>
-<h2>Introduction</h2>
-<p>The Unicode Character Database (UCD) is a set of files that define the
-Unicode character properties and internal mappings. This document describes the
-files that are part of <a href="http://www.unicode.org/unicode/reports/tr27/">The
-Unicode Standard, Version 3.1</a> [<a href="#U3.1">U3.1</a>]. The main changes
-in this version are:</p>
-<ul>
- <li>All of the data files have been updated to account for the large number of
- additional characters in Unicode 3.1.</li>
- <li>PropList.txt has been extensively reorganized and reformatted.</li>
- <li>Scripts.txt has been added to the UCD.</li>
- <li>A large number of informative derived property files have been added to
- the UCD.</li>
-</ul>
-<p><i>Files in the UCD use a common format unless otherwise specified. For
-details, see <a href="#UCD_File_Format">UCD File Format</a>.</i></p>
-<h2><a name="Conformance">Conformance</a></h2>
-<p>For information on the meaning and application of the terms normative and
-informative, see "Chapter 4, Character Properties (revision)" in <a
-href="http://www.unicode.org/unicode/reports/tr27/#conformance">UAX #27, Unicode
-3.1</a>.</p>
-<p>Some informative data files contain derived properties, properties that can
-be derived from other properties in the UCD. The derived properties that are
-computed from solely normative properties are themselves normative, while the
-others are informative.</p>
-<h2>UCD Files</h2>
-<p>The following table summarizes the files in the Unicode Character Database.
- For more information about these files, see the referenced technical
-report(s), files, or section of Unicode Standard, Version 3.1.</p>
-<table border="1" cellspacing="0" cellpadding="4">
- <tr>
- <th>".txt" File</th>
- <th>Description</th>
- <th align="center">N/I</th>
- <th>Summary</th>
- </tr>
- <tr>
- <td>ArabicShaping</td>
- <td>Section 8.2</td>
- <td align="center">N</td>
- <td>Basic Arabic and Syriac character shaping properties, such as initial,
- medial and final shapes.</td>
- </tr>
- <tr>
- <td>BidiMirroring</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr9/">UAX #9</a></td>
- <td align="center">I</td>
- <td>Properties for substituting characters in an implementation of
- bidirectional mirroring.</td>
- </tr>
- <tr>
- <td>Blocks</td>
- <td>Chapter 14</td>
- <td align="center">N</td>
- <td>List of block names.</td>
- </tr>
- <tr>
- <td>CaseFolding</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr21/">UTR #21</a></td>
- <td align="center">N</td>
- <td>Mapping from characters to their case-folded forms. This is an
- informative file containing normative derived properties.
- <p><i>Derived from UnicodeData and SpecialCasing.</i></p>
- </td>
- </tr>
- <tr>
- <td>CompositionExclusions</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr15/">UAX #15</a></td>
- <td align="center">N</td>
- <td>Properties for normalization.</td>
- </tr>
- <tr>
- <td><i>DerivedXXX</i></td>
- <td>DerivedProperties.html</td>
- <td align="center">N/I</td>
- <td>Various informative derived files, described in the documentation file.
- Some of the derived properties are normative and some are informative.</td>
- </tr>
- <tr>
- <td>EastAsianWidth</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr11/">UAX #11</a></td>
- <td align="center">I</td>
- <td>Properties for determining the choice of wide vs. narrow glyphs in East
- Asian contexts.</td>
- </tr>
- <tr>
- <td>Index</td>
- <td>Chapter 14</td>
- <td align="center">I</td>
- <td>Index to Unicode characters, as printed in the Unicode Standard. (See <a
- href="#Update_Note">Update Note</a>.)</td>
- </tr>
- <tr>
- <td>Jamo</td>
- <td>Chapter 4</td>
- <td align="center">N</td>
- <td>List of Jamo short names, used in deriving HANGUL SYLLABLE names
- algorithmically.</td>
- </tr>
- <tr>
- <td>LineBreak</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr14/">UAX #14</a></td>
- <td align="center">N/I</td>
- <td>Properties for line breaking.</td>
- </tr>
- <tr>
- <td>NamesList</td>
- <td>Chapter 14</td>
- <td align="center">I</td>
- <td>This file duplicates some of the material in the UnicodeData file, and
- adds annotations used in the character charts.</td>
- </tr>
- <tr>
- <td>NormalizationTest</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr15/">UAX #15</a></td>
- <td align="center">N</td>
- <td>Test file for conformance to Unicode Normalization Forms.</td>
- </tr>
- <tr>
- <td>PropList</td>
- <td>PropList.html</td>
- <td align="center">N/I</td>
- <td>Extended character properties</td>
- </tr>
- <tr>
- <td>Scripts</td>
- <td><a href="http://www.unicode.org/unicode/reports/tr24/">UTR #24</a></td>
- <td align="center">I</td>
- <td>Default scripts values for use in regular expressions.</td>
- </tr>
- <tr>
- <td>SpecialCasing</td>
- <td>Chapter 4,<br>
- <a href="http://www.unicode.org/unicode/reports/tr21/">UTR #21</a></td>
- <td align="center">N</td>
- <td>List of properties required for full case mapping.</td>
- </tr>
- <tr>
- <td>UnicodeData</td>
- <td>UnicodeData.html,<br>
- Chapter 4,<br>
- <a href="http://www.unicode.org/unicode/reports/tr21/">UTR #21</a>,<br>
- <a href="http://www.unicode.org/unicode/reports/tr15/">UAX #15</a></td>
- <td align="center">N/I</td>
- <td>The main file in the UCD. </td>
- </tr>
- <tr>
- <td>Unihan</td>
- <td>Unihan.txt</td>
- <td align="center">N/I</td>
- <td>Extended properties of Han (CJK) characters. (See <a href="#Format_Note">Format
- Note</a>.)</td>
- </tr>
-</table>
-<blockquote>
- <p><b><a name="Update_Note">Update Note</a>: </b>The information in Index.txt
- files matches the appropriate version of the book. Changes in the Unicode
- Character Database since then may not be reflected in these files, since they
- are primarily of archival interest.</p>
- <p><b><a name="Format_Note">Format Note</a>: </b>The file data format differs
- from the standard format, and is described in the header of the file. The
- header also describes which properties are informative and which are
- normative.</p>
-</blockquote>
-<h2><a name="UCD_File_Format">UCD File Format</a></h2>
-<p>Files in the UCD use the following format, unless otherwise specified.</p>
-<ul>
- <li>Each line of data consists of fields separated by semicolons. The fields
- are numbered starting with zero. Code points are expressed as hexadecimal
- numbers with four to six digits. They are written without "U+".
- Within a sequence of code points, spaces are used for separation. Leading
- and trailing spaces within a field are not significant.</li>
-</ul>
-<ul>
- <li>The first field (0) of each line in the Unicode Character Database files
- represents a code point or range. The remaining fields (1..n) are properties
- associated with that code point.</li>
-</ul>
-<ul>
- <li>A range of code points is specified by the form "X..Y". Each
- code point from X to Y has the associated properties. For example:</li>
-</ul>
-<blockquote>
- <pre>0000..007F; Basic Latin
-0080..00FF; Latin-1 Supplement
-
-1680 ; White_space # Zs OGHAM SPACE MARK
-2000..200A; White_space # Zs [11] EN QUAD..HAIR SPACE</pre>
-</blockquote>
-<ul>
- <li>Hash marks ("#") are used to indicate comments: all characters
- from the hash mark to the end of the line are comments, and disregarded when
- parsing data. In many files, the comments on data lines use a common format.</li>
-</ul>
-<blockquote>
- <pre>00BC..00BE ; numeric # No [3] VULGAR FRACTION ONE QUARTER..VULGAR FRACTION THREE QUARTERS</pre>
-</blockquote>
-<ul>
- <li>The first part of the comment is the UCD general category. The symbol
- "L&" indicates characters of type Lu, Ll, or Lt. The code
- point ranges are calculated so that they all have the same General Category
- (or L&). While this results in more ranges than are strictly necessary,
- it makes the contents of the ranges clearer. The second part of the comment
- (in square brackets), indicates the number of items in a range, if there is
- one. The third part is the name of the character in field zero: if it is a
- range, then the character names for the ends of the range are separated by
- "..".</li>
-</ul>
-<p>However, the comments are purely informational, and may change format or be
-omitted in the future. They should not be parsed for content.</p>
-<h2><a name="References">References</a></h2>
-<table cellspacing="12" cellpadding="0" width="100%" border="0">
- <tbody>
- <tr>
- <td valign="top" width="1">[<a name="FAQ">FAQ</a>]</td>
- <td valign="top">Unicode Frequently Asked Questions<br>
- <a href="http://www.unicode.org/unicode/faq/">http://www.unicode.org/unicode/faq/<br>
- </a><i>For answers to common questions on technical issues.</i></td>
- </tr>
- <tr>
- <td valign="top" width="1">[<a name="Glossary">Glossary</a>]</td>
- <td valign="top">Unicode Glossary<a
- href="http://www.unicode.org/glossary/"><br>
- http://www.unicode.org/glossary/<br>
- </a><i>For explanations of terminology used in this and other documents.</i></td>
- </tr>
- <tr>
- <td valign="top" width="1">[<a name="Reports">Reports</a>]</td>
- <td valign="top">Unicode Technical Reports<br>
- <a href="http://www.unicode.org/unicode/reports/">http://www.unicode.org/unicode/reports/<br>
- </a><i>For information on the status and development process for
- technical reports, and for a list of technical reports.</i></td>
- </tr>
- <tr>
- <td valign="top" width="1">[<a name="U3.1">U3.1</a>]</td>
- <td valign="top">Unicode Standard Annex #27: Unicode 3.1<a
- href="http://www.unicode.org/unicode/reports/tr27/"><br>
- http://www.unicode.org/unicode/reports/tr27/</a></td>
- </tr>
- <tr>
- <td valign="top" width="1">[<a name="Versions">Versions</a>]</td>
- <td valign="top">Versions of the Unicode Standard<br>
- <a href="http://www.unicode.org/unicode/standard/versions/">http://www.unicode.org/unicode/standard/versions/<br>
- </a><i>For details on the precise contents of each version of the
- Unicode Standard, and how to cite them.</i></td>
- </tr>
- </tbody>
-</table>
-<h2><br>
-<i><a name="UCD_Terms">UCD Terms of Use</a></i></h2>
-<h3><i>Disclaimer</i></h3>
-<blockquote>
- <p><i>The Unicode Character Database is provided as is by Unicode, Inc. No
- claims are made as to fitness for any particular purpose. No warranties of any
- kind are expressed or implied. The recipient agrees to determine applicability
- of information provided. If this file has been purchased on magnetic or
- optical media from Unicode, Inc., the sole remedy for any claim will be
- exchange of defective media within 90 days of receipt.</i></p>
- <p><i>This disclaimer is applicable for all other data files accompanying the
- Unicode Character Database, some of which have been compiled by the Unicode
- Consortium, and some of which have been supplied by other sources.</i></p>
-</blockquote>
-<h3><i>Limitations on Rights to Redistribute This Data</i></h3>
-<blockquote>
- <p><i>Recipient is granted the right to make copies in any form for internal
- distribution and to freely use the information supplied in the creation of
- products supporting the Unicode<sup>TM</sup> Standard. The files in the
- Unicode Character Database can be redistributed to third parties or other
- organizations (whether for profit or not) as long as this notice and the
- disclaimer notice are retained. Information can be extracted from these files
- and used in documentation or programs, as long as there is an accompanying
- notice indicating the source.</i></p>
-</blockquote>
-<hr width="50%">
-<p align="center"><a href="http://www.unicode.org/unicode/copyright.html"><img
-src="http://www.unicode.org/img/hb_home.gif" border="0" alt="Home" width="40"
-height="49"><img src="http://www.unicode.org/img/hb_mid.gif" border="0"
-alt="Terms of Use" width="152" height="49"><img
-src="http://www.unicode.org/img/hb_mail.gif" border="0" alt="E-mail" width="46"
-height="49"></a>
-
-</body>
-
-</html>
+++ /dev/null
-<html>
-
-<head>
-<meta name="GENERATOR" content="Microsoft FrontPage 4.0">
-<meta name="ProgId" content="FrontPage.Editor.Document">
-<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
-<link rel="stylesheet" href="http://www.unicode.org/unicode.css" type="text/css">
-<title>UnicodeData File Format</title>
-</head>
-
-<body>
-
-<table width="100%" cellpadding="0" cellspacing="0" border="0">
- <tr>
- <td>
- <table width="100%" border="0" cellpadding="0" cellspacing="0">
- <tr>
- <td class="icon"><a href="http://www.unicode.org"><img border="0"
- src="http://www.unicode.org/webscripts/logo60s2.gif" align="middle"
- alt="[Unicode]" width="34" height="33"></a> <a
- class="bar" href="UnicodeCharacterDatabase.html">Unicode Character
- Database</a></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td class="gray"> </td>
- </tr>
-</table>
-<h1>Unicode Data File Format</h1>
-<table border="1" cellspacing="2" cellpadding="0" height="87" width="100%">
- <tr>
- <td valign="TOP" width="144">Revision</td>
- <td valign="TOP">3.1.0</td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Authors</td>
- <td valign="TOP">Mark Davis and Ken Whistler</td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Date</td>
- <td valign="TOP">2001-02-28</td>
- </tr>
- <tr>
- <td valign="TOP" width="144">This Version</td>
- <td valign="TOP"><a
- href="http://www.unicode.org/Public/3.1-Update/UnicodeData-3.1.0.html">http://www.unicode.org/Public/3.1-Update/UnicodeData-3.1.0.html</a></td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Previous Version</td>
- <td valign="TOP"><a
- href="http://www.unicode.org/Public/3.0-Update1/UnicodeData-3.0.1.html">http://www.unicode.org/Public/3.0-Update1/UnicodeData-3.0.1.html</a></td>
- </tr>
- <tr>
- <td valign="TOP" width="144">Latest Version</td>
- <td valign="TOP"><a
- href="http://www.unicode.org/Public/UNIDATA/UnicodeData.html">http://www.unicode.org/Public/UNIDATA/UnicodeData.html</a></td>
- </tr>
-</table>
-<h3><br>
-S<i>ummary</i></h3>
-<blockquote>
- <p><i>This document describes the format and content of the UnicodeData.txt
- file in the Unicode Character Database (UCD).</i></p>
-</blockquote>
-<h3><i>Status</i></h3>
-<blockquote>
- <p><i>The file and the files described herein are part of the Unicode
- Character Database and governed by the <a href="#UCD_Terms">UCD Terms of
- Use</a> given below.</i></p>
- <p><i>For general information on file formats and table formats, and the
- implications of normative vs informative properties, see
- UnicodeCharacterDatabase.html. </i></p>
- <p><i><b>Warning: </b>the information in this file does not completely
- describe the use and interpretation of Unicode character properties and
- behavior. It must be used in conjunction with the data in the other files in
- the UCD, and relies on the notation and definitions supplied in <a
- href="http://www.unicode.org/unicode/standard/versions/Unicode3.0.html">The
- Unicode Standard</a>. All chapter references are to Version 3.1.0 of the
- standard.</i></p>
-</blockquote>
-<h2>Introduction</h2>
-<p>This document describes the format of the UnicodeData.txt file, which is one
-of the files in the Unicode Character Database. The document is divided into the
-following sections:
-<ul>
- <li><a href="#Field Formats">Field Formats</a>
- <ul>
- <li><a href="#General Category">General Category</a></li>
- <li><a href="#Bidirectional Category">Bidirectional Category</a></li>
- <li><a href="#Character Decomposition">Character Decomposition Mapping</a></li>
- <li><a href="#Canonical Combining Classes">Canonical Combining Classes</a></li>
- <li><a href="#Decompositions and Normalization">Decompositions and
- Normalization</a></li>
- <li><a href="#Case Mappings">Case Mappings</a></li>
- </ul>
- </li>
- <li><a href="#Property Invariants">Property Invariants</a></li>
- <li><a href="#Modification History">Modification History</a></li>
-</ul>
-<h2><a name="Field Formats"></a>Field Formats</h2>
-<p>Each line represents the data for one encoded character in the Unicode
-Standard. (For information on the file format, see UCD File Format in
-UnicodeCharacterDatabase.html).
-<p>Every encoded character has a data entry, with the exception of certain
-special ranges, as detailed below.
-<ul>
- <li>These ranges represented only by their start and end characters, since the
- properties in the file are uniform, except for code values (which are all
- sequential and assigned).</li>
- <li>The names of CJK ideograph characters and the names and decompositions of
- Hangul syllable characters are algorithmically derivable. (See the Unicode
- Standard and <a href="http://www.unicode.org/unicode/reports/tr15/">Unicode
- Standard Annex #15</a> for more information).</li>
- <li>Surrogate code values and private use characters have no names.</li>
- <li>The supplementary Private Use characters (U+F0000 .. U+FFFFD, U+100000 ..
- U+10FFFD) are listed as distinct ranges. These correspond to surrogate pairs
- where the first surrogate is in the High Surrogate Private Use section.</li>
-</ul>
-<p>The exact ranges represented by start and end characters are:
-<ul>
- <li>CJK Ideographs Extension A (U+3400 .. U+4DB5)</li>
- <li>CJK Ideographs (U+4E00 .. U+9FA5)</li>
- <li>Hangul Syllables (U+AC00 .. U+D7A3)</li>
- <li>Non-Private Use High Surrogates (U+D800 .. U+DB7F)</li>
- <li>Private Use High Surrogates (U+DB80 .. U+DBFF)</li>
- <li>Low Surrogates (U+DC00 .. U+DFFF)</li>
- <li>The Private Use Area (U+E000 .. U+F8FF)</li>
- <li>CJK Ideographs Extension B (U+20000 .. U+2A6D6)</li>
- <li>Plane 15 Private Use Area (U+F0000 .. U+FFFFD)</li>
- <li>Plane 16 Private Use Area (U+100000 .. U+10FFFD)</li>
-</ul>
-<p>The following table describes the format and meaning of each field in a data
-entry in the UnicodeData file.</p>
-<table border="1" cellspacing="2" cellpadding="2">
- <tr>
- <th valign="top" align="LEFT">
- <p align="LEFT">Field</th>
- <th valign="top" align="LEFT">
- <p align="LEFT">Name</th>
- <th valign="top" align="center">
- <p align="LEFT">N/I</th>
- <th valign="top" align="LEFT">
- <p align="LEFT">Explanation</th>
- </tr>
- <tr>
- <th valign="top">0</th>
- <td valign="top">Code value</td>
- <td valign="top" align="center">N</td>
- <td valign="top">Code value.</td>
- </tr>
- <tr>
- <th valign="top">1</th>
- <td valign="top">Character name</td>
- <td valign="top" align="center">N</td>
- <td valign="top">These names match exactly the names published in Chapter 14
- of the Unicode Standard, Version 3.0.</td>
- </tr>
- <tr>
- <th valign="top">2</th>
- <td valign="top"><a href="#General Category">General Category</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">This is a useful breakdown into various "character
- types" which can be used as a default categorization in
- implementations. See below for a brief explanation.</td>
- </tr>
- <tr>
- <th valign="top">3</th>
- <td valign="top"><a href="#Canonical Combining Classes">Canonical Combining
- Classes</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">The classes used for the Canonical Ordering Algorithm in
- the Unicode Standard. These classes are also printed in Chapter 4 of the
- Unicode Standard.</td>
- </tr>
- <tr>
- <th valign="top">4</th>
- <td valign="top"><a href="#Bidirectional Category">Bidirectional Category</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">See the list below for an explanation of the abbreviations
- used in this field. These are the categories required by the Bidirectional
- Behavior Algorithm in the Unicode Standard. These categories are
- summarized in Chapter 3 of the Unicode Standard.</td>
- </tr>
- <tr>
- <th valign="top">5</th>
- <td valign="top"><a href="#Character Decomposition">Character Decomposition
- Mapping</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">In the Unicode Standard, not all of the mappings are full
- (maximal) decompositions. Recursive application of look-up for
- decompositions will, in all cases, lead to a maximal decomposition. The
- decomposition mappings match exactly the decomposition mappings published
- with the character names in the Unicode Standard.</td>
- </tr>
- <tr>
- <th valign="top">6</th>
- <td valign="top">Decimal digit value</td>
- <td valign="top" align="center">N</td>
- <td valign="top">This is a numeric field. If the character has the decimal
- digit property, as specified in Chapter 4 of the Unicode Standard, the
- value of that digit is represented with an integer value in this field</td>
- </tr>
- <tr>
- <th valign="top">7</th>
- <td valign="top">Digit value</td>
- <td valign="top" align="center">N</td>
- <td valign="top">This is a numeric field. If the character represents a
- digit, not necessarily a decimal digit, the value is here. This covers
- digits which do not form decimal radix forms, such as the compatibility
- superscript digits</td>
- </tr>
- <tr>
- <th valign="top">8</th>
- <td valign="top">Numeric value</td>
- <td valign="top" align="center">N</td>
- <td valign="top">This is a numeric field. If the character has the numeric
- property, as specified in Chapter 4 of the Unicode Standard, the value of
- that character is represented with an integer or rational number in this
- field. This includes fractions as, e.g., "1/5" for U+2155 VULGAR
- FRACTION ONE FIFTH Also included are numerical values for compatibility
- characters such as circled numbers.</td>
- </tr>
- <tr>
- <th valign="top">9</th>
- <td valign="top">Mirrored</td>
- <td valign="top" align="center">N</td>
- <td valign="top">If the character has been identified as a
- "mirrored" character in bidirectional text, this field has the
- value "Y"; otherwise "N". The list of mirrored
- characters is also printed in Chapter 4 of the Unicode Standard.</td>
- </tr>
- <tr>
- <th valign="top">10</th>
- <td valign="top">Unicode 1.0 Name</td>
- <td valign="top" align="center">I</td>
- <td valign="top">This is the old name as published in Unicode 1.0. This name
- is only provided when it is significantly different from the current name
- for the character.</td>
- </tr>
- <tr>
- <th valign="top">11</th>
- <td valign="top">10646 comment field</td>
- <td valign="top" align="center">I</td>
- <td valign="top">This is the ISO 10646 comment field. It appears in
- parentheses in the 10646 names list, or contains an asterisk to mark an
- Annex P note.</td>
- </tr>
- <tr>
- <th valign="top">12</th>
- <td valign="top"><a href="#Case Mappings">Uppercase Mapping</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">Upper case equivalent mapping. If a character is part of an
- alphabet with case distinctions, and has a simple upper case equivalent,
- then the upper case equivalent is in this field. See the explanation below
- on case distinctions. These mappings are always one-to-one, not
- one-to-many or many-to-one.
- <p><i>For full case mappings, see <a
- href="http://www.unicode.org/unicode/reports/tr21/">UTR #21</a> and
- SpecialCasing.txt.</i></p>
- </td>
- </tr>
- <tr>
- <th valign="top">13</th>
- <td valign="top"><a href="#Case Mappings">Lowercase Mapping</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">Similar to Uppercase mapping</td>
- </tr>
- <tr>
- <th valign="top">14</th>
- <td valign="top"><a href="#Case Mappings">Titlecase Mapping</a></td>
- <td valign="top" align="center">N</td>
- <td valign="top">Similar to Uppercase mapping</td>
- </tr>
-</table>
-<h3><a name="General Category"></a>General Category</h3>
-<p>The values in this field are abbreviations for the following values. For more
-information, see the Unicode Standard.</p>
-<blockquote>
- <p><b>Note:</b> the standard does not assign information to control characters
- (except for certain cases in the Bidirectional Algorithm). Implementations
- will generally also assign categories to certain control characters, notably
- CR and LF, according to platform conventions. See <a
- href="http://www.unicode.org/unicode/reports/tr13/">UAX #13: Unicode Newline
- Guidelines</a> for more information.</p>
-</blockquote>
-<table border="0" cellspacing="0" cellpadding="4">
- <tr>
- <th>
- <p align="LEFT">Abbr.</th>
- <th>
- <p align="LEFT">Description</th>
- </tr>
- <tr>
- <td align="CENTER">Lu</td>
- <td>Letter, Uppercase</td>
- </tr>
- <tr>
- <td align="CENTER">Ll</td>
- <td>Letter, Lowercase</td>
- </tr>
- <tr>
- <td align="CENTER">Lt</td>
- <td>Letter, Titlecase</td>
- </tr>
- <tr>
- <td align="CENTER">Lm</td>
- <td>Letter, Modifier</td>
- </tr>
- <tr>
- <td align="CENTER">Lo</td>
- <td>Letter, Other</td>
- </tr>
- <tr>
- <td align="CENTER">Mn</td>
- <td>Mark, Non-Spacing</td>
- </tr>
- <tr>
- <td align="CENTER">Mc</td>
- <td>Mark, Spacing Combining</td>
- </tr>
- <tr>
- <td align="CENTER">Me</td>
- <td>Mark, Enclosing</td>
- </tr>
- <tr>
- <td align="CENTER">Nd</td>
- <td>Number, Decimal Digit</td>
- </tr>
- <tr>
- <td align="CENTER">Nl</td>
- <td>Number, Letter</td>
- </tr>
- <tr>
- <td align="CENTER">No</td>
- <td>Number, Other</td>
- </tr>
- <tr>
- <td align="CENTER">Pc</td>
- <td>Punctuation, Connector</td>
- </tr>
- <tr>
- <td align="CENTER">Pd</td>
- <td>Punctuation, Dash</td>
- </tr>
- <tr>
- <td align="CENTER">Ps</td>
- <td>Punctuation, Open</td>
- </tr>
- <tr>
- <td align="CENTER">Pe</td>
- <td>Punctuation, Close</td>
- </tr>
- <tr>
- <td align="CENTER">Pi</td>
- <td>Punctuation, Initial quote (may behave like Ps or Pe depending on usage)</td>
- </tr>
- <tr>
- <td align="CENTER">Pf</td>
- <td>Punctuation, Final quote (may behave like Ps or Pe depending on usage)</td>
- </tr>
- <tr>
- <td align="CENTER">Po</td>
- <td>Punctuation, Other</td>
- </tr>
- <tr>
- <td align="CENTER">Sm</td>
- <td>Symbol, Math</td>
- </tr>
- <tr>
- <td align="CENTER">Sc</td>
- <td>Symbol, Currency</td>
- </tr>
- <tr>
- <td align="CENTER">Sk</td>
- <td>Symbol, Modifier</td>
- </tr>
- <tr>
- <td align="CENTER">So</td>
- <td>Symbol, Other</td>
- </tr>
- <tr>
- <td align="CENTER">Zs</td>
- <td>Separator, Space</td>
- </tr>
- <tr>
- <td align="CENTER">Zl</td>
- <td>Separator, Line</td>
- </tr>
- <tr>
- <td align="CENTER">Zp</td>
- <td>Separator, Paragraph</td>
- </tr>
- <tr>
- <td align="CENTER">Cc</td>
- <td>Other, Control</td>
- </tr>
- <tr>
- <td align="CENTER">Cf</td>
- <td>Other, Format</td>
- </tr>
- <tr>
- <td align="CENTER">Cs</td>
- <td>Other, Surrogate</td>
- </tr>
- <tr>
- <td align="CENTER">Co</td>
- <td>Other, Private Use</td>
- </tr>
- <tr>
- <td align="CENTER">Cn</td>
- <td>Other, Not Assigned (no characters in the file have this property)</td>
- </tr>
-</table>
-<blockquote>
- <p><b>Note:</b> The term "L&" is sometimes used to stand for
- Uppercase, Lowercase or Titlecase letters (Lu, Ll, or Lt).</p>
-</blockquote>
-<h3><a name="Bidirectional Category"></a>Bidirectional Category</h3>
-<p>Please refer to Chapter 3 for an explanation of the algorithm for
-Bidirectional Behavior and an explanation of the significance of these
-categories. An up-to-date version can be found on <a
-href="http://www.unicode.org/unicode/reports/tr9/">Unicode Standard Annex #9:
-The Bidirectional Algorithm</a>.</p>
-<table border="0" cellpadding="4" cellspacing="0">
- <tr>
- <th valign="TOP" align="LEFT">
- <p align="LEFT">Type</th>
- <th valign="TOP" align="LEFT">
- <p align="LEFT">Description</th>
- </tr>
- <tr>
- <td valign="TOP"><b>L</b></td>
- <td valign="TOP">Left-to-Right</td>
- </tr>
- <tr>
- <td valign="TOP"><b>LRE</b></td>
- <td valign="TOP">Left-to-Right Embedding</td>
- </tr>
- <tr>
- <td valign="TOP"><b>LRO</b></td>
- <td valign="TOP">Left-to-Right Override</td>
- </tr>
- <tr>
- <td valign="TOP"><b>R</b></td>
- <td valign="TOP">Right-to-Left</td>
- </tr>
- <tr>
- <td valign="TOP"><b>AL</b></td>
- <td valign="TOP">Right-to-Left Arabic</td>
- </tr>
- <tr>
- <td valign="TOP"><b>RLE</b></td>
- <td valign="TOP">Right-to-Left Embedding</td>
- </tr>
- <tr>
- <td valign="TOP"><b>RLO</b></td>
- <td valign="TOP">Right-to-Left Override</td>
- </tr>
- <tr>
- <td valign="TOP"><b>PDF</b></td>
- <td valign="TOP">Pop Directional Format</td>
- </tr>
- <tr>
- <td valign="TOP"><b>EN</b></td>
- <td valign="TOP">European Number</td>
- </tr>
- <tr>
- <td valign="TOP"><b>ES</b></td>
- <td valign="TOP">European Number Separator</td>
- </tr>
- <tr>
- <td valign="TOP"><b>ET</b></td>
- <td valign="TOP">European Number Terminator</td>
- </tr>
- <tr>
- <td valign="TOP"><b>AN</b></td>
- <td valign="TOP">Arabic Number</td>
- </tr>
- <tr>
- <td valign="TOP"><b>CS</b></td>
- <td valign="TOP">Common Number Separator</td>
- </tr>
- <tr>
- <td valign="TOP"><b>NSM</b></td>
- <td valign="TOP">Non-Spacing Mark</td>
- </tr>
- <tr>
- <td valign="TOP"><b>BN</b></td>
- <td valign="TOP">Boundary Neutral</td>
- </tr>
- <tr>
- <td valign="TOP"><b>B</b></td>
- <td valign="TOP">Paragraph Separator</td>
- </tr>
- <tr>
- <td valign="TOP"><b>S</b></td>
- <td valign="TOP">Segment Separator</td>
- </tr>
- <tr>
- <td valign="TOP"><b>WS</b></td>
- <td valign="TOP">Whitespace</td>
- </tr>
- <tr>
- <td valign="TOP"><b>ON</b></td>
- <td valign="TOP">Other Neutrals</td>
- </tr>
-</table>
-<h3><a name="Character Decomposition"></a>Character Decomposition Mapping</h3>
-<p>The tags supplied with certain decomposition mappings generally indicate
-formatting information. Where no such tag is given, the mapping is designated as
-canonical. Conversely, the presence of a formatting tag also indicates that the
-mapping is a compatibility mapping and not a canonical mapping. In the absence
-of other formatting information in a compatibility mapping, the tag is used to
-distinguish it from canonical mappings.</p>
-<p>In some instances a canonical mapping or a compatibility mapping may consist
-of a single character. For a canonical mapping, this indicates that the
-character is a canonical equivalent of another single character. For a
-compatibility mapping, this indicates that the character is a compatibility
-equivalent of another single character. The compatibility formatting tags used
-are:</p>
-<table border="0" cellspacing="0" cellpadding="4">
- <tr>
- <th>Tag</th>
- <th>
- <p align="LEFT">Description</th>
- </tr>
- <tr>
- <td align="CENTER"><font> </td>
- <td>A font variant (e.g. a blackletter form).</td>
- </tr>
- <tr>
- <td align="CENTER"><noBreak> </td>
- <td>A no-break version of a space or hyphen.</td>
- </tr>
- <tr>
- <td align="CENTER"><initial> </td>
- <td>An initial presentation form (Arabic).</td>
- </tr>
- <tr>
- <td align="CENTER"><medial> </td>
- <td>A medial presentation form (Arabic).</td>
- </tr>
- <tr>
- <td align="CENTER"><final> </td>
- <td>A final presentation form (Arabic).</td>
- </tr>
- <tr>
- <td align="CENTER"><isolated> </td>
- <td>An isolated presentation form (Arabic).</td>
- </tr>
- <tr>
- <td align="CENTER"><circle> </td>
- <td>An encircled form.</td>
- </tr>
- <tr>
- <td align="CENTER"><super> </td>
- <td>A superscript form.</td>
- </tr>
- <tr>
- <td align="CENTER"><sub> </td>
- <td>A subscript form.</td>
- </tr>
- <tr>
- <td align="CENTER"><vertical> </td>
- <td>A vertical layout presentation form.</td>
- </tr>
- <tr>
- <td align="CENTER"><wide> </td>
- <td>A wide (or zenkaku) compatibility character.</td>
- </tr>
- <tr>
- <td align="CENTER"><narrow> </td>
- <td>A narrow (or hankaku) compatibility character.</td>
- </tr>
- <tr>
- <td align="CENTER"><small> </td>
- <td>A small variant form (CNS compatibility).</td>
- </tr>
- <tr>
- <td align="CENTER"><square> </td>
- <td>A CJK squared font variant.</td>
- </tr>
- <tr>
- <td align="CENTER"><fraction> </td>
- <td>A vulgar fraction form.</td>
- </tr>
- <tr>
- <td align="CENTER"><compat> </td>
- <td>Otherwise unspecified compatibility character.</td>
- </tr>
-</table>
-<p><b>Reminder: </b>There is a difference between decomposition and
-decomposition mapping. The decomposition mappings are defined in the UnicodeData,
-while the decomposition (also termed "full decomposition") is defined
-in Chapter 3 to use those mappings <i>recursively.</i>
-<ul>
- <li>The canonical decomposition is formed by recursively applying the
- canonical mappings, then applying the canonical reordering algorithm.</li>
- <li>The compatibility decomposition is formed by recursively applying the
- canonical <em>and</em> compatibility mappings, then applying the canonical
- reordering algorithm.</li>
-</ul>
-<h3><a name="Canonical Combining Classes"></a>Canonical Combining Classes</h3>
-<table border="0" cellspacing="0" cellpadding="4">
- <tr>
- <th>
- <p align="LEFT">Value</th>
- <th>
- <p align="LEFT">Description</th>
- </tr>
- <tr>
- <td align="RIGHT">0:</td>
- <td>Spacing, split, enclosing, reordrant, and Tibetan subjoined</td>
- </tr>
- <tr>
- <td align="RIGHT">1:</td>
- <td>Overlays and interior</td>
- </tr>
- <tr>
- <td align="RIGHT">7:</td>
- <td>Nuktas</td>
- </tr>
- <tr>
- <td align="RIGHT">8:</td>
- <td>Hiragana/Katakana voicing marks</td>
- </tr>
- <tr>
- <td align="RIGHT">9:</td>
- <td>Viramas</td>
- </tr>
- <tr>
- <td align="RIGHT">10:</td>
- <td>Start of fixed position classes</td>
- </tr>
- <tr>
- <td align="RIGHT">199:</td>
- <td>End of fixed position classes</td>
- </tr>
- <tr>
- <td align="RIGHT">200:</td>
- <td>Below left attached</td>
- </tr>
- <tr>
- <td align="RIGHT">202:</td>
- <td>Below attached</td>
- </tr>
- <tr>
- <td align="RIGHT">204:</td>
- <td>Below right attached</td>
- </tr>
- <tr>
- <td align="RIGHT">208:</td>
- <td>Left attached (reordrant around single base character)</td>
- </tr>
- <tr>
- <td align="RIGHT">210:</td>
- <td>Right attached</td>
- </tr>
- <tr>
- <td align="RIGHT">212:</td>
- <td>Above left attached</td>
- </tr>
- <tr>
- <td align="RIGHT">214:</td>
- <td>Above attached</td>
- </tr>
- <tr>
- <td align="RIGHT">216:</td>
- <td>Above right attached</td>
- </tr>
- <tr>
- <td align="RIGHT">218:</td>
- <td>Below left</td>
- </tr>
- <tr>
- <td align="RIGHT">220:</td>
- <td>Below</td>
- </tr>
- <tr>
- <td align="RIGHT">222:</td>
- <td>Below right</td>
- </tr>
- <tr>
- <td align="RIGHT">224:</td>
- <td>Left (reordrant around single base character)</td>
- </tr>
- <tr>
- <td align="RIGHT">226:</td>
- <td>Right</td>
- </tr>
- <tr>
- <td align="RIGHT">228:</td>
- <td>Above left</td>
- </tr>
- <tr>
- <td align="RIGHT">230:</td>
- <td>Above</td>
- </tr>
- <tr>
- <td align="RIGHT">232:</td>
- <td>Above right</td>
- </tr>
- <tr>
- <td align="RIGHT">233:</td>
- <td>Double below</td>
- </tr>
- <tr>
- <td align="RIGHT">234:</td>
- <td>Double above</td>
- </tr>
- <tr>
- <td align="RIGHT">240:</td>
- <td>Below (iota subscript)</td>
- </tr>
-</table>
-<p><strong>Note: </strong>some of the combining classes in this list do not
-currently have members but are specified here for completeness.</p>
-<h3><a name="Decompositions and Normalization"></a>Decompositions and
-Normalization</h3>
-<p>Decomposition is specified in Chapter 3. <a
-href="http://www.unicode.org/unicode/reports/tr15/"><i>Unicode Standard Annex
-#15: Unicode Normalization Forms</i></a> specifies the interaction between
-decomposition and normalization. That report specifies how the decompositions
-defined in UnicodeData.txt are used to derive normalized forms of Unicode text.</p>
-<p>Note that as of the 2.1.9 update of the Unicode Character Database, the
-decompositions in the UnicodeData.txt file can be used to recursively derive the
-full decomposition in canonical order, without the need to separately apply
-canonical reordering. However, canonical reordering of combining character
-sequences <b><i>must</i></b> still be applied in decomposition when normalizing
-source text which contains any combining marks.</p>
-<h3><a name="Case Mappings"></a>Case Mappings</h3>
-<p>There are a number of complications to case mappings that occur once the
-repertoire of characters is expanded beyond ASCII. For more information, see <a
-href="http://www.unicode.org/unicode/reports/tr21/">UTR #21: Case Mappings</a>.</p>
-<p>For compatibility with existing parsers, UnicodeData.txt only contains case
-mappings for characters where they are one-to-one mappings; it also omits
-information about context-sensitive case mappings. Information about these
-special cases can be found in a separate data file, SpecialCasing.txt.</p>
-<h2><a name="Property Invariants"></a>Property Invariants</h2>
-<p>Values in UnicodeData.txt are subject to correction as errors are found;
-however, some characteristics of the categories themselves can be considered
-invariants. Applications may wish to take these invariants into account when
-choosing how to implement character properties. For more information, see <a
-href="http://www.unicode.org/unicode/standard/policies.html">Unicode Policies</a>.</p>
-<p>The following is a partial list of known invariants for the Unicode Character
-Database.</p>
-<h4>Database Fields</h4>
-<ul>
- <li>The number of fields in UnicodeData.txt is fixed.</li>
- <li>The order of the fields is also fixed.
- <ul>
- <li>Any additional information about character properties to be added in
- the future will appear in separate data tables, rather than being added
- on to the existing table or by subdivision or reinterpretation of
- existing fields.</li>
- </ul>
- </li>
-</ul>
-<h4>General Category</h4>
-<ul>
- <li>There will never be more than 32 General Category values.
- <ul>
- <li>It is very unlikely that the Unicode Technical Committee will
- subdivide the General Category partition any further, since that can
- cause implementations to misbehave. Because the General Category is
- limited to 32 values, 5 bits can be used to represent the information,
- and a 32-bit integer can be used as a bitmask to represent arbitrary
- sets of categories.</li>
- </ul>
- </li>
-</ul>
-<h4>Combining Classes</h4>
-<ul>
- <li>Combining classes are limited to the values 0 to 255.
- <ul>
- <li>In practice, there are far fewer than 256 values used. Implementations
- may take advantage of this fact for compression, since only the ordering
- of the non-zero values matters for the Canonical Reordering Algorithm.
- It is possible for up to 256 values to be used in the future; however,
- UTC decisions in the future may restrict the number of values to 128,
- since this has implementation advantages. [Signed bytes can be used
- without widening to ints in Java, for example.]</li>
- </ul>
- </li>
- <li>All characters other than those of General Category M* have the combining
- class 0.
- <ul>
- <li>Currently, all characters other than those of General Category Mn have
- the value 0. However, some characters of General Category Me or Mc may
- be given non-zero values in the future.</li>
- <li>The precise values above the value 0 are not invariant--only the
- relative ordering is considered normative. For example, it is not
- guaranteed in future versions that the class of U+05B4 will be precisely
- 14.</li>
- </ul>
- </li>
-</ul>
-<h4>Canonical Decomposition</h4>
-<ul>
- <li>Canonical mappings are always in canonical order.</li>
- <li>Canonical mappings have only the first of a pair possibly further
- decomposing.</li>
- <li>Canonical decompositions are "transparent" to other character
- data:
- <ul>
- <li><tt>BIDI(a) = BIDI(principal(canonicalDecomposition(a))</tt></li>
- <li><tt>Category(a) = Category(principal(canonicalDecomposition(a))</tt></li>
- <li><tt>CombiningClass(a) =
- CombiningClass(principal(canonicalDecomposition(a))</tt><br>
- where principal(a) is the first character not of type Mn, or the first
- character if all characters are of type Mn.</li>
- </ul>
- </li>
- <li>However, because there are sometimes missing case pairs, and because of
- some legacy characters, it is only generally true that:
- <ul>
- <li><tt>upper(canonicalDecomposition(a)) = canonicalDecomposition(upper(a))</tt></li>
- <li><tt>lower(canonicalDecomposition(a)) = canonicalDecomposition(lower(a))</tt></li>
- <li><tt>title(canonicalDecomposition(a)) = canonicalDecomposition(title(a))</tt></li>
- </ul>
- </li>
-</ul>
-<h2><a name="Modification History"></a>Modification History</h2>
-<p>This section provides a summary of the changes between update versions of the
-Unicode Standard.</p>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 3.1">Unicode
-3.1</a></h3>
-<p>Modifications made for Version 3.0.1 of UnicodeData.txt include:
-<ul>
- <li>Addition of 2237 new entries, to cover new characters and new ranges of
- unified Han characters encoded in Unicode 3.1.</li>
- <li>Changed General Category value of 16EE..16F0 (Runic golden numbers) from
- No to Nl.</li>
-</ul>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 3.0.1">Unicode
-3.0.1</a></h3>
-<p>Modifications made for Version 3.0.1 of UnicodeData.txt include:
-<ul>
- <li>Added 5- and 6-digit representation of code points past U+FFFF.</li>
- <li>Added Private Use range definitions for Planes 15 and 16.</li>
- <li>Minor additions for the 10646 comment field.</li>
-</ul>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 3.0.0">Unicode
-3.0.0</a></h3>
-<p>Modifications made for Version 3.0.0 of UnicodeData.txt include many new
-characters and a number of property changes. These are summarized in Appendex D
-of <em>The Unicode Standard, Version 3.0.</em></p>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 2.1.9">Unicode
-2.1.9</a></h3>
-<p>Modifications made for Version 2.1.9 of UnicodeData.txt include:
-<ul>
- <li>Corrected combining class for U+05AE HEBREW ACCENT ZINOR.</li>
- <li>Corrected combining class for U+20E1 COMBINING LEFT RIGHT ARROW ABOVE</li>
- <li>Corrected combining class for U+0F35 and U+0F37 to 220.</li>
- <li>Corrected combining class for U+0F71 to 129.</li>
- <li>Added a decomposition for U+0F0C TIBETAN MARK DELIMITER TSHEG BSTAR.</li>
- <li>Added decompositions for several Greek symbol letters:
- U+03D0..U+03D2, U+03D5, U+03D6, U+03F0..U+03F2.</li>
- <li>Removed decompositions from the conjoining jamo block:
- U+1100..U+11F8.</li>
- <li>Changes to decomposition mappings for some Tibetan vowels for consistency
- in normalization. (U+0F71, U+0F73, U+0F77, U+0F79, U+0F81)</li>
- <li>Updated the decomposition mappings for several Vietnamese characters with
- two diacritics (U+1EAC, U+1EAD, U+1EB6, U+1EB7, U+1EC6, U+1EC7, U+1ED8,
- U+1ED9), so that the recursive decomposition can be generated directly in
- canonically reordered form (not a normative change).</li>
- <li>Updated the decomposition mappings for several Arabic compatibility
- characters involving shadda (U+FC5E..U+FC62, U+FCF2..U+FCF4), and two Latin
- characters (U+1E1C, U+1E1D), so that the decompositions are generated
- directly in canonically reordered form (not a normative change).</li>
- <li>Changed BIDI category for: U+00A0 NO-BREAK SPACE, U+2007 FIGURE SPACE,
- U+2028 LINE SEPARATOR.</li>
- <li>Changed BIDI category for extenders of General Category Lm: U+3005,
- U+3021..U+3035, U+FF9E, U+FF9F.</li>
- <li>Changed General Category and BIDI category for the Greek numeral signs:
- U+0374, U+0375.</li>
- <li>Corrected General Category for U+FFE8 HALFWIDTH FORMS LIGHT VERTICAL.</li>
- <li>Added Unicode 1.0 names for many Tibetan characters (informative).</li>
-</ul>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 2.1.8">Unicode
-2.1.8</a></h3>
-<p>Modifications made for Version 2.1.8 of UnicodeData.txt include:
-<ul>
- <li>Added combining class 240 for U+0345 COMBINING GREEK YPOGEGRAMMENI so that
- decompositions involving iota subscript are derivable directly in
- canonically reordered form; this also has a bearing on simplification of
- casing of polytonic Greek.</li>
- <li>Changes in decompositions related to Greek tonos. These result from the
- clarification that monotonic Greek "tonos" should be equated with
- U+0301 COMBINING ACUTE, rather than with U+030D COMBINING VERTICAL LINE
- ABOVE. (All Greek characters in the Greek block involving "tonos";
- some Greek characters in the polytonic Greek in the 1FXX block.)</li>
- <li>Changed decompositions involving dialytika tonos. (U+0390, U+03B0)</li>
- <li>Changed ternary decompositions to binary. (U+0CCB, U+FB2C, U+FB2D) These
- changes simplify normalization.</li>
- <li>Removed canonical decomposition for Latin Candrabindu. (U+0310)</li>
- <li>Corrected error in canonical decomposition for U+1FF4.</li>
- <li>Added compatibility decompositions to clarify collation tables. (U+2100,
- U+2101, U+2105, U+2106, U+1E9A)</li>
- <li>A series of general category changes to assist the convergence of
- Unicode definition of identifier with ISO TR 10176:
- <ul>
- <li>So > Lo: U+0950, U+0AD0, U+0F00, U+0F88..U+0F8B</li>
- <li>Po > Lo: U+0E2F, U+0EAF, U+3006</li>
- <li>Lm > Sk: U+309B, U+309C</li>
- <li>Po > Pc: U+30FB, U+FF65</li>
- <li>Ps/Pe > Mn: U+0F3E, U+0F3F</li>
- </ul>
- </li>
- <li>A series of bidi property changes for consistency.
- <ul>
- <li>L > ET: U+09F2, U+09F3</li>
- <li>ON > L: U+3007</li>
- <li>L > ON: U+0F3A..U+0F3D, U+037E, U+0387</li>
- </ul>
- </li>
- <li>Add case mapping: U+01A6 <-> U+0280</li>
- <li>Updated symmetric swapping value for guillemets: U+00AB, U+00BB, U+2039,
- U+203A.</li>
- <li>Changes to combining class values. Most Indic fixed position class
- non-spacing marks were changed to combining class 0. This fixes some
- inconsistencies in how canonical reordering would apply to Indic scripts,
- including Tibetan. Indic interacting top/bottom fixed position classes were
- merged into single (non-zero) classes as part of this change. Tibetan
- subjoined consonants are changed from combining class 6 to combining class
- 0. Thai pinthu (U+0E3A) moved to combining class 9. Moved two Devanagari
- stress marks into generic above and below combining classes (U+0951,
- U+0952).</li>
- <li>Corrected placement of semicolon near symmetric swapping field. (U+FA0E,
- etc., scattered positions to U+FA29)</li>
-</ul>
-<h3>Version 2.1.7</h3>
-<p><i>This version was for internal change tracking only, and never publicly
-released.</i></p>
-<h3>Version 2.1.6</h3>
-<p><i>This version was for internal change tracking only, and never publicly
-released.</i></p>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 2.1.5">Unicode
-2.1.5</a></h3>
-<p>Modifications made for Version 2.1.5 of UnicodeData.txt include:
-<ul>
- <li>Changed decomposition for U+FF9E and U+FF9F so that correct collation
- weighting will automatically result from the canonical equivalences.</li>
- <li>Removed canonical decompositions for U+04D4, U+04D5, U+04D8, U+04D9,
- U+04E0, U+04E1, U+04E8, U+04E9 (the implication being that no canonical
- equivalence is claimed between these 8 characters and similar Latin
- letters), and updated 4 canonical decompositions for U+04DB, U+04DC, U+04EA,
- U+04EB to reflect the implied difference in the base character.</li>
- <li>Added Pi, and Pf categories and assigned the relevant quotation marks to
- those categories, based on the Unicode Technical Corrigendum on Quotation
- Characters.</li>
- <li>Updating of many bidi properties, following the advice of the ad hoc
- committee on bidi, and to make the bidi properties of compatibility
- characters more consistent.</li>
- <li>Changed category of several Tibetan characters: U+0F3E, U+0F3F,
- U+0F88..U+0F8B to make them non-combining, reflecting the combined opinion
- of Tibetan experts.</li>
- <li>Added case mapping for U+03F2.</li>
- <li>Corrected case mapping for U+0275.</li>
- <li>Added titlecase mappings for U+03D0, U+03D1, U+03D5, U+03D6, U+03F0..
- U+03F2.</li>
- <li>Corrected compatibility label for U+2121.</li>
- <li>Add specific entries for all the CJK compatibility ideographs,
- U+F900..U+FA2D, so the canonical decomposition for each (the URO character
- it is equivalent to) can be carried in the database.</li>
-</ul>
-<h3>Version 2.1.4</h3>
-<p><i>This version was for internal change tracking only, and never publicly
-released.</i></p>
-<h3>Version 2.1.3</h3>
-<p><i>This version was for internal change tracking only, and never publicly
-released.</i></p>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 2.1.2">Unicode
-2.1.2</a></h3>
-<p>Modifications made in updating UnicodeData.txt to Version 2.1.2 for the
-Unicode Standard, Version 2.1 (from Version 2.0) include:
-<ul>
- <li>Added two characters (U+20AC and U+FFFC).</li>
- <li>Amended bidi properties for U+0026, U+002E, U+0040, U+2007.</li>
- <li>Corrected case mappings for U+018E, U+019F, U+01DD, U+0258, U+0275,
- U+03C2, U+1E9B.</li>
- <li>Changed combining order class for U+0F71.</li>
- <li>Corrected canonical decompositions for U+0F73, U+1FBE.</li>
- <li>Changed decomposition for U+FB1F from compatibility to canonical.</li>
- <li>Added compatibility decompositions for U+FBE8, U+FBE9, U+FBF9..U+FBFB.</li>
- <li>Corrected compatibility decompositions for U+2469, U+246A, U+3358.</li>
-</ul>
-<h3>Version 2.1.1</h3>
-<p><i>This version was for internal change tracking only, and never publicly
-released.</i></p>
-<h3><a
-href="http://www.unicode.org/unicode/standard/versions/enumeratedversions.html#Unicode 2.0.0">Unicode
-2.0.0</a></h3>
-<p>The modifications made in updating UnicodeData.txt for the Unicode Standard,
-Version 2.0 include:
-<ul>
- <li>Fixed decompositions with TONOS to use correct NSM: 030D.</li>
- <li>Removed old Hangul Syllables; mapping to new characters are in a separate
- table.</li>
- <li>Marked compatibility decompositions with additional tags.</li>
- <li>Changed old tag names for clarity.</li>
- <li>Revision of decompositions to use first-level decomposition, instead of
- maximal decomposition.</li>
- <li>Correction of all known errors in decompositions from earlier versions.</li>
- <li>Added control code names (as old Unicode names).</li>
- <li>Added Hangul Jamo decompositions.</li>
- <li>Added Number category to match properties list in book.</li>
- <li>Fixed categories of Koranic Arabic marks.</li>
- <li>Fixed categories of precomposed characters to match decomposition where
- possible.</li>
- <li>Added Hebrew cantillation marks and the Tibetan script.</li>
- <li>Added place holders for ranges such as CJK Ideographic Area and the
- Private Use Area.</li>
- <li>Added categories Me, Sk, Pc, Nl, Cs, Cf, and rectified a number of
- mistakes in the database.</li>
-</ul>
-<h2><i><a name="UCD_Terms">UCD Terms of Use</a></i></h2>
-<h3><i>Disclaimer</i></h3>
-<blockquote>
- <p><i>The Unicode Character Database is provided as is by Unicode, Inc. No
- claims are made as to fitness for any particular purpose. No warranties of any
- kind are expressed or implied. The recipient agrees to determine applicability
- of information provided. If this file has been purchased on magnetic or
- optical media from Unicode, Inc., the sole remedy for any claim will be
- exchange of defective media within 90 days of receipt.</i></p>
- <p><i>This disclaimer is applicable for all other data files accompanying the
- Unicode Character Database, some of which have been compiled by the Unicode
- Consortium, and some of which have been supplied by other sources.</i></p>
-</blockquote>
-<h3><i>Limitations on Rights to Redistribute This Data</i></h3>
-<blockquote>
- <p><i>Recipient is granted the right to make copies in any form for internal
- distribution and to freely use the information supplied in the creation of
- products supporting the Unicode<sup>TM</sup> Standard. The files in the
- Unicode Character Database can be redistributed to third parties or other
- organizations (whether for profit or not) as long as this notice and the
- disclaimer notice are retained. Information can be extracted from these files
- and used in documentation or programs, as long as there is an accompanying
- notice indicating the source.</i></p>
-</blockquote>
-<hr width="50%">
-<div align="center">
- <center>
- <table cellspacing="0" cellpadding="0" border="0">
- <tr>
- <td><a href="http://www.unicode.org/unicode/copyright.html"><img
- src="http://www.unicode.org/img/hb_home.gif" border="0" alt="Home"
- width="40" height="49"><img src="http://www.unicode.org/img/hb_mid.gif"
- border="0" alt="Terms of Use" width="152" height="49"><img
- src="http://www.unicode.org/img/hb_mail.gif" border="0" alt="E-mail"
- width="46" height="49"></a></td>
- </tr>
- </table>
- </center>
-</div>
-
-</body>
-
-</html>
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by ./mktables from e.g. Unicode.txt.
+# This file is built by ./mktables from e.g. UnicodeData.txt.
# Any changes made here will be lost!
#
my $HEADER=<<"EOF";
# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
-# This file is built by $0 from e.g. Unicode.txt.
+# This file is built by $0 from e.g. UnicodeData.txt.
# Any changes made here will be lost!
EOF
my %Cat;
##
-## Process Unicode.txt (Categories, etc.)
+## Process UnicodeData.txt (Categories, etc.)
##
sub Unicode_Txt()
{
Fuzzy => 0);
## Initialize Perl-generated categories
- ## (Categories from Unicode.txt are auto-initialized in gencat)
+ ## (Categories from UnicodeData.txt are auto-initialized in gencat)
$Cat{Alnum} = Table->New(Is => 'Alnum', Desc => "[[:Alnum:]]", Fuzzy => 0);
$Cat{Alpha} = Table->New(Is => 'Alpha', Desc => "[[:Alpha:]]", Fuzzy => 0);
$Cat{ASCII} = Table->New(Is => 'ASCII', Desc => "[[:ASCII:]]", Fuzzy => 0);
}
## open ane read file.....
- if (not open IN, "Unicode.txt") {
- die "$0: Unicode.txt: $!\n";
+ if (not open IN, "UnicodeData.txt") {
+ die "$0: UnicodeData.txt: $!\n";
}
##
}
##
-## Process LineBrk.txt
+## Process LineBreak.txt
##
-sub LineBrk_Txt()
+sub LineBreak_Txt()
{
- if (not open IN, "LineBrk.txt") {
- die "$0: LineBrk.txt: $!\n";
+ if (not open IN, "LineBreak.txt") {
+ die "$0: LineBreak.txt: $!\n";
}
my $Lbrk = Table->New();
}
##
-## Process ArabShap.txt.
+## Process ArabicShaping.txt.
##
-sub ArabShap_txt()
+sub ArabicShaping_txt()
{
- if (not open IN, "ArabShap.txt") {
- die "$0: ArabShap.txt: $!\n";
+ if (not open IN, "ArabicShaping.txt") {
+ die "$0: ArabicShaping.txt: $!\n";
}
my $ArabLink = Table->New();
##
## Read in the PropList.txt. It contains extended properties not
-## listed in the Unicode.txt, such as 'Other_Alphabetic':
+## listed in the UnicodeData.txt, such as 'Other_Alphabetic':
## alphabetic but not of the general category L; many modifiers
## belong to this extended property category: while they are not
## alphabets, they are alphabetic in nature.
}
-sub SpecCase_txt()
+sub SpecialCasing_txt()
{
#
# Read in the special cases.
my %CaseInfo;
- if (not open IN, "SpecCase.txt") {
- die "$0: SpecCase.txt: $!\n";
+ if (not open IN, "SpecialCasing.txt") {
+ die "$0: SpecialCasing.txt: $!\n";
}
while (<IN>) {
next unless /^[0-9A-Fa-f]+;/;
#
# Read in the case foldings.
#
-# We will do full case folding, C + F + I (see CaseFold.txt).
+# We will do full case folding, C + F + I (see CaseFolding.txt).
#
-sub CaseFold_txt()
+sub CaseFolding_txt()
{
- if (not open IN, "CaseFold.txt") {
- die "$0: CaseFold.txt: $!\n";
+ if (not open IN, "CaseFolding.txt") {
+ die "$0: CaseFolding.txt: $!\n";
}
my $Fold = Table->New();
WriteAllMappings();
-LineBrk_Txt();
-ArabShap_txt();
+LineBreak_Txt();
+ArabicShaping_txt();
Jamo_txt();
-SpecCase_txt();
-CaseFold_txt();
+SpecialCasing_txt();
+CaseFolding_txt();
exit(0);
+++ /dev/null
-#!/bin/sh
-
-mv ArabicShaping.txt ArabShap.txt
-mv BidiMirroring.txt BidiMirr.txt
-#Blocks.txt Blocks.txt
-mv CaseFolding.txt CaseFold.txt
-mv CompositionExclusions.txt CompExcl.txt
-mv EastAsianWidth.txt EAWidth.txt
-#Index.txt Index.txt
-#Jamo.txt Jamo.txt
-mv LineBreak.txt LineBrk.txt
-#NamesList.html NamesList.html
-#NamesList.txt NamesList.txt
-#PropList.txt PropList.txt
-#PropList.html PropList.html
-#ReadMe.txt ReadMe.txt
-mv SpecialCasing.txt SpecCase.txt
-mv UnicodeCharacterDatabase.html UCD.html
-mv UnicodeData.html Unicode.html
-mv UnicodeData.txt Unicode.txt
$mask |= $DeadBits{$word} if $fatal ;
}
else
- { croak("unknown warnings category '$word'")}
+ { croak("Unknown warnings category '$word'")}
}
return $mask ;
$category = shift ;
if (ref $category) {
croak ("not an object")
- if $category !~ /^([^=]+)=/ ;+
+ if $category !~ /^([^=]+)=/ ;
$category = $1 ;
$isobj = 1 ;
}
$offset = $Offsets{$category};
- croak("unknown warnings category '$category'")
+ croak("Unknown warnings category '$category'")
unless defined $offset;
}
else {
/* locale.c
*
- * Copyright (c) 2001, Larry Wall
+ * Copyright (c) 2001-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
# include <stdlib.h>
# include <stdio.h>
# include <memory.h>
-# define _(arg) arg
# ifndef Malloc_t
# define Malloc_t void *
# endif
/* mg.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* mg.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
+/* miniperlmain.c
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/*
* "The Road goes ever on and on, down from the door where it began."
*/
+/* nostdio.h
+ *
+ * Copyright (c) 1987-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/*
* Strong denial of stdio - make all stdio calls (we can think of) errors
*/
/* numeric.c
*
- * Copyright (c) 2001, Larry Wall
+ * Copyright (c) 2001-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* op.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* op.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by opcode.pl from its data. Any changes made here
- will be lost!
-*/
+/*
+ * opcode.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by opcode.pl from its data. Any changes made here
+ * will be lost!
+ */
#define Perl_pp_i_preinc Perl_pp_preinc
#define Perl_pp_i_predec Perl_pp_predec
$i = 0;
print <<"END";
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by opcode.pl from its data. Any changes made here
- will be lost!
-*/
+/*
+ * opcode.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by opcode.pl from its data. Any changes made here
+ * will be lost!
+ */
#define Perl_pp_i_preinc Perl_pp_preinc
#define Perl_pp_i_predec Perl_pp_predec
END
print ON <<"END";
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by opcode.pl from its data. Any changes made here
- will be lost!
-*/
+/*
+ * opnames.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by opcode.pl from its data. Any changes made here
+ * will be lost!
+ */
typedef enum opcode {
END
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by opcode.pl from its data. Any changes made here
- will be lost!
-*/
+/*
+ * opnames.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by opcode.pl from its data. Any changes made here
+ * will be lost!
+ */
typedef enum opcode {
OP_NULL, /* 0 */
+/* patchlevel.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#ifndef __PATCHLEVEL_H_INCLUDED__
/* do not adjust the whitespace! Configure expects the numbers to be
#if !defined(PERL_PATCHLEVEL_H_IMPLICIT) && !defined(LOCAL_PATCH_COUNT)
static char *local_patches[] = {
NULL
- ,"DEVEL14330"
+ ,"DEVEL14388"
,NULL
};
/* perl.c
*
- * Copyright (c) 1987-2001 Larry Wall
+ * Copyright (c) 1987-2002 Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#endif
PerlIO_printf(PerlIO_stdout(),
- "\n\nCopyright 1987-2001, Larry Wall\n");
+ "\n\nCopyright 1987-2002, Larry Wall\n");
#ifdef MACOS_TRADITIONAL
PerlIO_printf(PerlIO_stdout(),
- "\nMac OS port Copyright 1991-2001, Matthias Neeracher;\n"
+ "\nMac OS port Copyright 1991-2002, Matthias Neeracher;\n"
"maintained by Chris Nandor\n");
#endif
#ifdef MSDOS
#ifdef OS2
PerlIO_printf(PerlIO_stdout(),
"\n\nOS/2 port Copyright (c) 1990, 1991, Raymond Chen, Kai Uwe Rommel\n"
- "Version 5 port Copyright (c) 1994-1999, Andreas Kaiser, Ilya Zakharevich\n");
+ "Version 5 port Copyright (c) 1994-2002, Andreas Kaiser, Ilya Zakharevich\n");
#endif
#ifdef atarist
PerlIO_printf(PerlIO_stdout(),
#endif
#ifdef MPE
PerlIO_printf(PerlIO_stdout(),
- "MPE/iX port Copyright by Mark Klein and Mark Bixby, 1996-2001\n");
+ "MPE/iX port Copyright by Mark Klein and Mark Bixby, 1996-2002\n");
#endif
#ifdef OEMVS
PerlIO_printf(PerlIO_stdout(),
#endif
#ifdef __VOS__
PerlIO_printf(PerlIO_stdout(),
- "Stratus VOS port by Paul_Green@stratus.com, 1997-1999\n");
+ "Stratus VOS port by Paul_Green@stratus.com, 1997-2002\n");
#endif
#ifdef __OPEN_VM
PerlIO_printf(PerlIO_stdout(),
#endif
#ifdef EPOC
PerlIO_printf(PerlIO_stdout(),
- "EPOC port by Olaf Flebbe, 1999-2000\n");
+ "EPOC port by Olaf Flebbe, 1999-2002\n");
#endif
#ifdef UNDER_CE
- printf("WINCE port by Rainer Keuchel, 2001\n");
+ printf("WINCE port by Rainer Keuchel, 2001-2002\n");
printf("Built on " __DATE__ " " __TIME__ "\n\n");
wce_hitreturn();
#endif
/* perl.h
*
- * Copyright (c) 1987-2001, Larry Wall
+ * Copyright (c) 1987-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
*
*/
+
#ifndef H_PERL
#define H_PERL 1
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * perlapi.c
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
#include "EXTERN.h"
#include "perl.h"
-/* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
- This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
- perlvars.h and thrdvar.h. Any changes made here will be lost!
-*/
+/*
+ * perlapi.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ *
+ * !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
+ * This file is built by embed.pl from data in embed.pl, pp.sym, intrpvar.h,
+ * perlvars.h and thrdvar.h. Any changes made here will be lost!
+ */
/* declare accessor functions for Perl variables */
#ifndef __perlapi_h__
/*
- * perlio.c Copyright (c) 1996-2001, Nick Ing-Simmons You may distribute
+ * perlio.c Copyright (c) 1996-2002, Nick Ing-Simmons You may distribute
* under the terms of either the GNU General Public License or the
* Artistic License, as specified in the README file.
*/
+/* perlio.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#ifndef _PERLIO_H
#define _PERLIO_H
/*
+/* perlsdio.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#ifdef PERLIO_IS_STDIO
#ifdef NETWARE
+/* perlsfio.h
+ *
+ * Copyright (c) 1987-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/* The next #ifdef should be redundant if Configure behaves ... */
#ifndef FILE
#define FILE FILE
+/* perlvars.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/****************/
/* Truly global */
/****************/
/* perly.y
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args /* config-skip */
-#else
-#define _(args) () /* config-skip */
-#endif
/* RANDBITS:
* This symbol contains the number of bits of random number the rand()
($days[3], $days[4], $days[5]) = qw/Wed Thu Fri/;
($colors{'red'}, $colors{'blue'}, $colors{'green'})
= (0xff0000, 0x0000ff, 0x00ff00);
- ($folks[0], $folks[-1]) = ($folks[0], $folks[-1]);
+ ($folks[0], $folks[-1]) = ($folks[-1], $folks[0]);
Since changing a slice changes the original array or hash that it's
slicing, a C<foreach> construct will alter some--or even all--of the
=head1 DESCRIPTION
This is not the perldebug(1) manpage, which tells you how to use
-the debugger. This manpage describes low-level details ranging
-between difficult and impossible for anyone who isn't incredibly
-intimate with Perl's guts to understand. Caveat lector.
+the debugger. This manpage describes low-level details concerning
+the debugger's internals, which range from difficult to impossible
+to understand for anyone who isn't incredibly intimate with Perl's guts.
+Caveat lector.
=head1 Debugger Internals
F<INSTALL> podpage in the Perl source tree.
For example, whenever you call Perl's built-in C<caller> function
-from the package DB, the arguments that the corresponding stack
-frame was called with are copied to the @DB::args array. The
-general mechanisms is enabled by calling Perl with the B<-d> switch, the
-following additional features are enabled (cf. L<perlvar/$^P>):
+from the package C<DB>, the arguments that the corresponding stack
+frame was called with are copied to the C<@DB::args> array. These
+mechanisms are enabled by calling Perl with the B<-d> switch.
+Specifically, the following additional features are enabled
+(cf. L<perlvar/$^P>):
=over 4
=item *
Each array C<@{"_<$filename"}> holds the lines of $filename for a
-file compiled by Perl. The same for C<eval>ed strings that contain
-subroutines, or which are currently being executed. The $filename
-for C<eval>ed strings looks like C<(eval 34)>. Code assertions
-in regexes look like C<(re_eval 19)>.
+file compiled by Perl. The same is also true for C<eval>ed strings
+that contain subroutines, or which are currently being executed.
+The $filename for C<eval>ed strings looks like C<(eval 34)>.
+Code assertions in regexes look like C<(re_eval 19)>.
Values in this array are magical in numeric context: they compare
equal to zero only if the line is not breakable.
=item *
When the execution of your program reaches a point that can hold a
-breakpoint, the C<DB::DB()> subroutine is called any of the variables
-$DB::trace, $DB::single, or $DB::signal is true. These variables
+breakpoint, the C<DB::DB()> subroutine is called if any of the variables
+C<$DB::trace>, C<$DB::single>, or C<$DB::signal> is true. These variables
are not C<local>izable. This feature is disabled when executing
inside C<DB::DB()>, including functions called from it
unless C<< $^D & (1<<30) >> is true.
When execution of the program reaches a subroutine call, a call to
C<&DB::sub>(I<args>) is made instead, with C<$DB::sub> holding the
-name of the called subroutine. This doesn't happen if the subroutine
+name of the called subroutine. (This doesn't happen if the subroutine
was compiled in the C<DB> package.)
=back
Note that if C<&DB::sub> needs external data for it to work, no
-subroutine call is possible until this is done. For the standard
-debugger, the C<$DB::deep> variable (how many levels of recursion
-deep into the debugger you can go before a mandatory break) gives
-an example of such a dependency.
+subroutine call is possible without it. As an example, the standard
+debugger's C<&DB::sub> depends on the C<$DB::deep> variable
+(it defines how many levels of recursion deep into the debugger you can go
+before a mandatory break). If C<$DB::deep> is not defined, subroutine
+calls are not possible, even though C<&DB::sub> exists.
=head2 Writing Your Own Debugger
-The minimal working debugger consists of one line
-
+=head3 Environment Variables
+
+The C<PERL5DB> environment variable can be used to define a debugger.
+For example, the minimal "working" debugger (it actually doesn't do anything)
+consists of one line:
+
sub DB::DB {}
-which is quite handy as contents of C<PERL5DB> environment
-variable:
-
+It can easily be defined like this:
+
$ PERL5DB="sub DB::DB {}" perl -d your-script
-Another brief debugger, slightly more useful, could be created
+Another brief debugger, slightly more useful, can be created
with only the line:
sub DB::DB {print ++$i; scalar <STDIN>}
-This debugger would print the sequential number of encountered
-statement, and would wait for you to hit a newline before continuing.
-
-The following debugger is quite functional:
-
+This debugger prints a number which increments for each statement
+encountered and waits for you to hit a newline before continuing
+to the next statement.
+
+The following debugger is actually useful:
+
{
package DB;
sub DB {}
sub sub {print ++$i, " $sub\n"; &$sub}
}
-It prints the sequential number of subroutine call and the name of the
-called subroutine. Note that C<&DB::sub> should be compiled into the
-package C<DB>.
+It prints the sequence number of each subroutine call and the name of the
+called subroutine. Note that C<&DB::sub> is being compiled into the
+package C<DB> through the use of the C<package> directive.
-At the start, the debugger reads your rc file (F<./.perldb> or
-F<~/.perldb> under Unix), which can set important options. This file may
-define a subroutine C<&afterinit> to be executed after the debugger is
-initialized.
+When it starts, the debugger reads your rc file (F<./.perldb> or
+F<~/.perldb> under Unix), which can set important options.
+(A subroutine (C<&afterinit>) can be defined here as well; it is executed
+after the debugger completes its own initialization.)
After the rc file is read, the debugger reads the PERLDB_OPTS
-environment variable and parses this as the remainder of a C<O ...>
-line as one might enter at the debugger prompt.
+environment variable and uses it to set debugger options. The
+contents of this variable are treated as if they were the argument
+of an C<O ...> debugger command (q.v. in L<perldebug/Options>).
+
+=head3 Debugger internal variables
+In addition to the file and subroutine-related variables mentioned above,
+the debugger also maintains various magical internal variables.
+
+=over 4
+
+=item *
-The debugger also maintains magical internal variables, such as
-C<@DB::dbline>, C<%DB::dbline>, which are aliases for
-C<@{"::_<current_file"}> C<%{"::_<current_file"}>. Here C<current_file>
-is the currently selected file, either explicitly chosen with the
+C<@DB::dbline> is an alias for C<@{"::_<current_file"}>, which
+holds the lines of the currently-selected file (compiled by Perl), either
+explicitly chosen with the debugger's C<f> command, or implicitly by flow
+of execution.
+
+Values in this array are magical in numeric context: they compare
+equal to zero only if the line is not breakable.
+
+=item *
+
+C<%DB::dbline>, is an alias for C<%{"::_<current_file"}>, which
+contains breakpoints and actions keyed by line number in
+the currently-selected file, either explicitly chosen with the
debugger's C<f> command, or implicitly by flow of execution.
-Some functions are provided to simplify customization. See
-L<perldebug/"Options"> for description of options parsed by
-C<DB::parse_options(string)>. The function C<DB::dump_trace(skip[,
-count])> skips the specified number of frames and returns a list
-containing information about the calling frames (all of them, if
-C<count> is missing). Each entry is reference to a hash with
-keys C<context> (either C<.>, C<$>, or C<@>), C<sub> (subroutine
+As previously noted, individual entries (as opposed to the whole hash)
+are settable. Perl only cares about Boolean true here, although
+the values used by F<perl5db.pl> have the form
+C<"$break_condition\0$action">.
+
+=back
+
+=head3 Debugger customization fucntions
+
+Some functions are provided to simplify customization.
+
+=over 4
+
+=item *
+
+See L<perldebug/"Options"> for description of options parsed by
+C<DB::parse_options(string)> parses debugger options; see
+L<pperldebug/Options> for a description of options recognized.
+
+=item *
+
+C<DB::dump_trace(skip[,count])> skips the specified number of frames
+and returns a list containing information about the calling frames (all
+of them, if C<count> is missing). Each entry is reference to a hash
+with keys C<context> (either C<.>, C<$>, or C<@>), C<sub> (subroutine
name, or info about C<eval>), C<args> (C<undef> or a reference to
an array), C<file>, and C<line>.
-The function C<DB::print_trace(FH, skip[, count[, short]])> prints
+=item *
+
+C<DB::print_trace(FH, skip[, count[, short]])> prints
formatted info about caller frames. The last two functions may be
convenient as arguments to C<< < >>, C<< << >> commands.
+=back
+
Note that any variables and functions that are not documented in
this manpages (or in L<perldebug>) are considered for internal
use only, and as such are subject to change without notice.
(P) We popped the context stack to an eval context, and then discovered
it wasn't an eval context.
-=item panic: pp_match
+=item panic: pp_match%s
(P) The internal pp_match() routine was called with invalid operational
data.
data Perl expected. Someone's very confused, or perhaps trying to
subvert Perl's population of %ENV for nefarious purposes.
+=item Unknown warnings category '%s'
+
+(F) An error issued by the C<warnings> pragma. You specified a warnings
+category that is unknown to perl at this point.
+
+Note that if you want to enable a warnings category registered by a module
+(e.g. C<use warnings 'File::Find'>), you must have imported this module
+first.
+
=item unmatched [ in regex; marked by <-- HERE in m/%s/
(F) The brackets around a character class must match. If you wish to
=head1 AUTHOR AND COPYRIGHT
-Copyright (c) 1997, 1998, 1999, 2000, 2001 Tom Christiansen and Nathan
-Torkington. All rights reserved.
+Copyright (c) 1997, 1998, 1999, 2000, 2001, 2002 Tom Christiansen and
+Nathan Torkington. All rights reserved.
This documentation is free; you can redistribute it and/or modify it
under the same terms as Perl itself.
=head1 AUTHOR AND COPYRIGHT
-Copyright (c) 1997-2001 Tom Christiansen and Nathan Torkington.
+Copyright (c) 1997-2002 Tom Christiansen and Nathan Torkington.
All rights reserved.
This documentation is free; you can redistribute it and/or modify it
error message. If there was no error, C<$@> is guaranteed to be a null
string. Beware that using C<eval> neither silences perl from printing
warnings to STDERR, nor does it stuff the text of warning messages into C<$@>.
-To do either of those, you have to use the C<$SIG{__WARN__}> facility. See
-L</warn> and L<perlvar>.
+To do either of those, you have to use the C<$SIG{__WARN__}> facility, or
+turn off warnings inside the BLOCK or EXPR using S<C<no warnings 'all'>>.
+See L</warn>, L<perlvar>, L<warnings> and L<perllexwarn>.
Note that, because C<eval> traps otherwise-fatal errors, it is useful for
determining whether a particular feature (such as C<socket> or C<symlink>)
=head1 COPYRIGHT
-Copyright (C) 1998, 2001 Jon Orwant. All Rights Reserved.
+Copyright (C) 1998, 2002 Jon Orwant. All Rights Reserved.
Permission is granted to make and distribute verbatim copies of this
documentation provided the copyright notice and this permission notice are
=item g
C<gccosandvers>, C<gccversion>, C<gidformat>, C<gidsign>, C<gidsize>,
-C<gidtype>, C<glibpth>, C<grep>, C<groupcat>, C<groupstype>, C<gzip>
+C<gidtype>, C<glibpth>, C<gmake>, C<grep>, C<groupcat>, C<groupstype>,
+C<gzip>
=item h
- append a "..." to the produced string if the maximum length is exceeded
- really fancy: print unicode characters as \N{...}
-NOTE: pv_display(), pv_uni_display(), sv_uni_display() are doing
-something like the above.
+NOTE: pv_display(), pv_uni_display(), sv_uni_display() are already
+doing something like the above.
=head2 Overloadable regex assertions
Mark-Jason Dominus has the beginnings of one of these.
-=head2 pack/unpack tutorial
-
-Simon Cozens has the beginnings of one of these.
-
=head2 Rewrite perldoc
There are a few suggestions for what to do with C<perldoc>: maybe a
(see the UNIX FAQ for details). This needs to go somewhere near
pp_sys.c:pp_truncate().
+One can emulate truncate() easily if one has ftruncate().
+This emulation should also go near pp_sys.pp_truncate().
+
+=head2 pack/unpack tutorial
+
+Wolfgang Laun finished what Simon Cozens started.
+
=cut
in the Perl 5.6 series. (The renaming to F<lib/unicore> was done to
avoid naming conflicts with lib/Unicode in case-insensitive filesystems.)
-The main Unicode data file is F<Unicode.txt> (or F<Unicode.301> in
+The main Unicode data file is F<UnicodeData.txt> (or F<Unicode.301> in
Perl 5.6.1.) You can find the C<$Config{installprivlib}> by
perl "-V:installprivlib"
=head1 AUTHOR, COPYRIGHT, AND LICENSE
-Copyright 2001 Jarkko Hietaniemi <jhi@iki.fi>
+Copyright 2001-2002 Jarkko Hietaniemi <jhi@iki.fi>
This document may be distributed under the same terms as Perl itself.
/* pp.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* pp.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* pp_ctl.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* prepare to compile file */
-#ifdef MACOS_TRADITIONAL
- if (PERL_FILE_IS_ABSOLUTE(name)
- || (*name == ':' && name[1] != ':' && strchr(name+2, ':')))
- {
+ if (path_is_absolute(name)) {
tryname = name;
tryrsfp = doopen_pmc(name,PERL_SCRIPT_MODE);
- /* We consider paths of the form :a:b ambiguous and interpret them first
- as global then as local
- */
- if (!tryrsfp && *name == ':' && name[1] != ':' && strchr(name+2, ':'))
- goto trylocal;
}
- else
-trylocal: {
-#else
- if (PERL_FILE_IS_ABSOLUTE(name)
- || (*name == '.' && (name[1] == '/' ||
- (name[1] == '.' && name[2] == '/'))))
- {
- tryname = name;
- tryrsfp = doopen_pmc(name,PERL_SCRIPT_MODE);
- }
- else {
-#endif
+ if (!tryrsfp) {
AV *ar = GvAVn(PL_incgv);
I32 i;
#ifdef VMS
}
}
else {
+ if (!path_is_absolute(name)
+#ifdef MACOS_TRADITIONAL
+ /* We consider paths of the form :a:b ambiguous and interpret them first
+ as global then as local
+ */
+ || (*name == ':' && name[1] != ':' && strchr(name+2, ':'))
+#endif
+ ) {
char *dir = SvPVx(dirsv, n_a);
#ifdef MACOS_TRADITIONAL
char buf[256];
tryname += 2;
break;
}
+ }
}
}
}
return len;
}
+/* perhaps someone can come up with a better name for
+ this? it is not really "absolute", per se ... */
+static bool
+S_path_is_absolute(pTHX_ char *name)
+{
+ if (PERL_FILE_IS_ABSOLUTE(name)
+#ifdef MACOS_TRADITIONAL
+ || (*name == ':' && name[1] != ':' && strchr(name+2, ':')))
+#else
+ || (*name == '.' && (name[1] == '/' ||
+ (name[1] == '.' && name[2] == '/'))))
+#endif
+ {
+ return TRUE;
+ }
+ else
+ return FALSE;
+}
/* pp_hot.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/*SUPPRESS 560*/
if ((rx->startp[i] != -1) && rx->endp[i] != -1 ) {
len = rx->endp[i] - rx->startp[i];
+ if (rx->endp[i] < 0 || rx->startp[i] < 0 ||
+ len < 0 || len > strend - s)
+ DIE(aTHX_ "panic: pp_match start/end pointers");
s = rx->startp[i] + truebase;
sv_setpvn(*SP, s, len);
if (DO_UTF8(TARG) && is_utf8_string((U8*)s, len))
/* pp_pack.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* pp_sort.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* pp_sys.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/*
+ * proto.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
* !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
* This file is autogenerated from data in embed.pl. Edit that file
* and run 'make regen_headers' to effect changes.
STATIC void S_save_lines(pTHX_ AV *array, SV *sv);
STATIC OP* S_doeval(pTHX_ int gimme, OP** startop);
STATIC PerlIO * S_doopen_pmc(pTHX_ const char *name, const char *mode);
+STATIC bool S_path_is_absolute(pTHX_ char *name);
#endif
#if defined(PERL_IN_PP_HOT_C) || defined(PERL_DECL_PROT)
#endif
#if defined(PERL_IN_UNIVERSAL_C) || defined(PERL_DECL_PROT)
-STATIC SV* S_isa_lookup(pTHX_ HV *stash, const char *name, int len, int level);
+STATIC SV* S_isa_lookup(pTHX_ HV *stash, const char *name, HV *name_stash, int len, int level);
#endif
#if defined(PERL_IN_LOCALE_C) || defined(PERL_DECL_PROT)
*
**** Alterations to Henry's code are...
****
- **** Copyright (c) 1991-2001, Larry Wall
+ **** Copyright (c) 1991-2002, Larry Wall
****
**** You may distribute under the terms of either the GNU General Public
**** License or the Artistic License, as specified in the README file.
/* regcomp.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
*/
typedef OP OP_4tree; /* Will be redefined later. */
*
**** Alterations to Henry's code are...
****
- **** Copyright (c) 1991-2001, Larry Wall
+ **** Copyright (c) 1991-2002, Larry Wall
****
**** You may distribute under the terms of either the GNU General Public
**** License or the Artistic License, as specified in the README file.
/* regexp.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
*/
/*
/* run.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* scope.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
+/* scope.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#define SAVEt_ITEM 0
#define SAVEt_SV 1
#define SAVEt_AV 2
/* sv.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
if (!utf8_to_bytes(s, &len)) {
if (fail_ok)
return FALSE;
-#ifdef USE_BYTES_DOWNGRADES
- else if (IN_BYTES) {
- U8 *d = s;
- U8 *e = (U8 *) SvEND(sv);
- int first = 1;
- while (s < e) {
- UV ch = utf8n_to_uvchr(s,(e-s),&len,0);
- if (first && ch > 255) {
- if (PL_op)
- Perl_warner(aTHX_ WARN_UTF8, "Wide character in byte %s",
- OP_DESC(PL_op);
- else
- Perl_warner(aTHX_ WARN_UTF8, "Wide character in byte");
- first = 0;
- }
- *d++ = ch;
- s += len;
- }
- *d = '\0';
- len = (d - (U8 *) SvPVX(sv));
- }
-#endif
else {
if (PL_op)
Perl_croak(aTHX_ "Wide character in %s",
/* sv.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
# check illegal category is caught
use warnings 'this-should-never-be-a-warning-category' ;
EXPECT
-unknown warnings category 'this-should-never-be-a-warning-category' at - line 3
+Unknown warnings category 'this-should-never-be-a-warning-category' at - line 3
BEGIN failed--compilation aborted at - line 3.
########
print $@ ;
EXPECT
Usage: warnings::warn([category,] 'message') at - line 4
-unknown warnings category 'fred' at - line 6
+Unknown warnings category 'fred' at - line 6
########
# check warnings::warnif
print $@ ;
EXPECT
Usage: warnings::warnif([category,] 'message') at - line 4
-unknown warnings category 'fred' at - line 6
+Unknown warnings category 'fred' at - line 6
########
--FILE-- abc.pm
"@mjd_previously_unused_array";
EXPECT
Possible unintended interpolation of @mjd_previously_unused_array in string at - line 3.
+########
+# toke.c
+# The \q should warn, the \_ should NOT warn.
+use warnings 'misc';
+"foo" =~ /\q/;
+"bar" =~ /\_/;
+no warnings 'misc';
+"foo" =~ /\q/;
+"bar" =~ /\_/;
+EXPECT
+Unrecognized escape \q passed through at - line 4.
require './test.pl';
}
-plan tests => 34;
+plan tests => 39;
$h{'abc'} = 'ABC';
$h{'def'} = 'DEF';
{
{ use bytes; ok (bytes::length($d) == $ol) }
}
+
+{
+ my %u;
+ my $u0 = pack("U0U", 0x00FF);
+ my $b0 = "\xC3\xBF"; # 0xCB 0xBF is U+00FF in UTF-8
+ my $u1 = pack("U0U", 0x0100);
+ my $b1 = "\xC4\x80"; # 0xC4 0x80 is U+0100 in UTF-8
+
+ $u{$u0} = 1;
+ $u{$b0} = 2;
+ $u{$u1} = 3;
+ $u{$b1} = 4;
+
+ is(scalar keys %u, 4, "four different Unicode keys");
+ is($u{$u0}, 1, "U+00FF -> 1");
+ is($u{$b0}, 2, "U+00C3 U+00BF -> 2");
+ is($u{$u1}, 3, "U+0100 -> 3 ");
+ is($u{$b1}, 4, "U+00C4 U+0080 -> 4");
+}
unless -d '/dev' && -r '/dev' && -x '/dev';
my $LS = $Config{d_readlink} ? "ls -lL" : "ls -l";
- my $CMD = "$LS /dev";
+ my $CMD = "$LS /dev 2>/dev/null";
my $DEV = qx($CMD);
skip "$CMD failed", 3 if $DEV eq '';
$| = 1;
}
-print "1..91\n";
+print "1..93\n";
$a = {};
bless $a, "Bob";
$a = new Alice;
test $a->isa("Alice");
+test $a->isa("main::Alice"); # check that alternate class names work
test $a->isa("Bob");
+test $a->isa("main::Bob");
test $a->isa("Female");
}
sub DESTROY {
my $self = shift;
- dbmclose(%{$self->{'LT'}});
- return 1;
-}
-package main;
-$test = Foo->new(); # must be package var
-END
-{
+ dbmclose(%{$self->{'LT'}});
1 while unlink 'dbmtest';
1 while unlink <dbmtest.*>;
print "ok\n";
}
+package main;
+$test = Foo->new(); # must be package var
EXPECT
ok
my $CF = File::Spec->catfile(File::Spec->catdir(File::Spec->updir,
"lib", "unicore"),
- "CaseFold.txt");
+ "CaseFolding.txt");
if (open(CF, $CF)) {
my @CF;
+/* taint.c
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/*
* "...we will have peace, when you and all your works have perished--and
* the works of your dark master to whom you would deliver us. You are a
+/* thdrvar.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/*
=head1 Global Variables
*/
+/* thread.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#if defined(USE_5005THREADS) || defined(USE_ITHREADS)
#if defined(VMS)
/* toke.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* FALL THROUGH */
default:
{
- if (ckWARN(WARN_MISC) && isALNUM(*s))
+ if (ckWARN(WARN_MISC) &&
+ isALNUM(*s) &&
+ *s != '_')
Perl_warner(aTHX_ WARN_MISC,
"Unrecognized escape \\%c passed through",
*s);
*/
/*#define HAS_SETSID / **/
-/* Shmat_t:
- * This symbol holds the return type of the shmat() system call.
- * Usually set to 'void *' or 'char *'.
- */
-/* HAS_SHMAT_PROTOTYPE:
- * This symbol, if defined, indicates that the sys/shm.h includes
- * a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
- * but not always right so it should be emitted by the program only
- * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
- */
-#define Shmat_t void * /**/
-/*#define HAS_SHMAT_PROTOTYPE / **/
-
/* HAS_STRCHR:
* This symbol is defined to indicate that the strchr()/strrchr()
* functions are available for string searching. If not, try the
*/
/*#define I_MEMORY / **/
-/* I_NDBM:
- * This symbol, if defined, indicates that <ndbm.h> exists and should
- * be included.
- */
-/*#define I_NDBM / **/
-
/* I_NET_ERRNO:
* This symbol, if defined, indicates that <net/errno.h> exists and
* should be included.
*/
/*#define I_VFORK / **/
-/* CAN_PROTOTYPE:
- * If defined, this macro indicates that the C compiler can handle
- * function prototypes.
- */
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
-/*#define CAN_PROTOTYPE / **/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
-
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* preprocessor can make decisions based on it.
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO / **/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO / **/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
/*#define HAS_TELLDIR_PROTO / **/
/*#define SETUID_SCRIPTS_ARE_SECURE_NOW / **/
/*#define DOSUID / **/
+/* Shmat_t:
+ * This symbol holds the return type of the shmat() system call.
+ * Usually set to 'void *' or 'char *'.
+ */
+/* HAS_SHMAT_PROTOTYPE:
+ * This symbol, if defined, indicates that the sys/shm.h includes
+ * a prototype for shmat(). Otherwise, it is up to the program to
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
+ * but not always right so it should be emitted by the program only
+ * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
+ */
+#define Shmat_t void * /**/
+/*#define HAS_SHMAT_PROTOTYPE / **/
+
+/* I_NDBM:
+ * This symbol, if defined, indicates that <ndbm.h> exists and should
+ * be included.
+ */
+/*#define I_NDBM / **/
+
/* I_STDARG:
* This symbol, if defined, indicates that <stdarg.h> exists and should
* be included.
#define I_STDARG /**/
/*#define I_VARARGS / **/
+/* CAN_PROTOTYPE:
+ * If defined, this macro indicates that the C compiler can handle
+ * function prototypes.
+ */
+/* PERL_PROTO_:
+ * This macro is used to declare function parameters for folks who want
+ * to make declarations with prototypes using a different style than
+ * the above macros. Use double parentheses. For example:
+ *
+ * int main PERL_PROTO_((int argc, char *argv[]));
+ */
+/*#define CAN_PROTOTYPE / **/
+#ifdef CAN_PROTOTYPE
+#else
+#endif
+
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* on this system to execute Bourne shell scripts. Usually, this will be
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO / **/
+/* universal.c
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#include "EXTERN.h"
#define PERL_IN_UNIVERSAL_C
#include "perl.h"
*/
STATIC SV *
-S_isa_lookup(pTHX_ HV *stash, const char *name, int len, int level)
+S_isa_lookup(pTHX_ HV *stash, const char *name, HV* name_stash,
+ int len, int level)
{
AV* av;
GV* gv;
HV* hv = Nullhv;
SV* subgen = Nullsv;
- if (!stash)
- return &PL_sv_undef;
+ /* A stash/class can go by many names (ie. User == main::User), so
+ we compare the stash itself just in case */
+ if (name_stash && (stash == name_stash))
+ return &PL_sv_yes;
if (strEQ(HvNAME(stash), name))
return &PL_sv_yes;
SvPVX(sv), HvNAME(stash));
continue;
}
- if (&PL_sv_yes == isa_lookup(basestash, name, len, level + 1)) {
+ if (&PL_sv_yes == isa_lookup(basestash, name, name_stash,
+ len, level + 1)) {
(void)hv_store(hv,name,len,&PL_sv_yes,0);
return &PL_sv_yes;
}
{
char *type;
HV *stash;
+ HV *name_stash;
stash = Nullhv;
type = Nullch;
stash = gv_stashsv(sv, FALSE);
}
+ name_stash = gv_stashpv(name, FALSE);
+
return (type && strEQ(type,name)) ||
- (stash && isa_lookup(stash, name, strlen(name), 0) == &PL_sv_yes)
+ (stash && isa_lookup(stash, name, name_stash, strlen(name), 0)
+ == &PL_sv_yes)
? TRUE
: FALSE ;
}
+/* unixish.h
+ *
+ * Copyright (c) 1997-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
/*
* The following symbols are defined if your operating system supports
* functions by that name. All Unixes I know of support them, thus they
/* utf8.c
*
- * Copyright (c) 1998-2001, Larry Wall
+ * Copyright (c) 1998-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* utf8.h
*
- * Copyright (c) 1998-2001, Larry Wall
+ * Copyright (c) 1998-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#define UNI_DISPLAY_QQ (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
#define UNI_DISPLAY_REGEX (UNI_DISPLAY_ISPRINT|UNI_DISPLAY_BACKSLASH)
-#define ANYOF_UNICODE_FOLD_SHARP_S(n, s, e) \
- (ANYOF_BITMAP_TEST(n, UNICODE_LATIN_SMALL_LETTER_SHARP_S) && \
- ANYOF_FLAGS(n) & ANYOF_UNICODE && \
- ANYOF_FLAGS(n) & ANYOF_FOLD && \
- ((e) > (s) + 1) && \
- toLOWER((s)[0]) == 's' && \
- toLOWER((s)[1]) == 's')
+#define ANYOF_UNICODE_FOLD_SHARP_S(node, input, end) \
+ (ANYOF_BITMAP_TEST(node, UNICODE_LATIN_SMALL_LETTER_SHARP_S) && \
+ (ANYOF_FLAGS(node) & ANYOF_UNICODE) && \
+ (ANYOF_FLAGS(node) & ANYOF_FOLD) && \
+ ((end) > (input) + 1) && \
+ toLOWER((input)[0]) == 's' && \
+ toLOWER((input)[1]) == 's')
/* utfebcdic.h
*
- * Copyright (c) 2001, Larry Wall, Nick Ing-Simmons
+ * Copyright (c) 2001-2002, Larry Wall, Nick Ing-Simmons
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* util.c
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* util.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
open(script,"$test") || die "Can't run $test.\n";
$_ = <script>;
close(script);
- if (/#!..perl(.*)/) {
- $switch = $1;
- # Add "" to protect uppercase switches on command line
- $switch =~ s/-(\S*[A-Z]\S*)/"-$1"/g;
+ if (/#!.*\bperl.*-\w*([tT])/) {
+ $switch = qq{"-$1"};
} else {
$switch = '';
}
*/
/*#define HAS_SETSID /**/
-/* Shmat_t:
- * This symbol holds the return type of the shmat() system call.
- * Usually set to 'void *' or 'char *'.
- */
-/* HAS_SHMAT_PROTOTYPE:
- * This symbol, if defined, indicates that the sys/shm.h includes
- * a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
- * but not always right so it should be emitted by the program only
- * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
- */
-#define Shmat_t void * /**/
-#define HAS_SHMAT_PROTOTYPE /**/
-
/* HAS_STRCHR:
* This symbol is defined to indicate that the strchr()/strrchr()
* functions are available for string searching. If not, try the
*/
/*#define I_MEMORY /**/
-/* I_NDBM:
- * This symbol, if defined, indicates that <ndbm.h> exists and should
- * be included.
- */
-/*#define I_NDBM /**/
-
/* I_NET_ERRNO:
* This symbol, if defined, indicates that <net/errno.h> exists and
* should be included.
*/
/*#define I_VFORK /**/
-/* CAN_PROTOTYPE:
- * If defined, this macro indicates that the C compiler can handle
- * function prototypes.
- */
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
-#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
-
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* preprocessor can make decisions based on it.
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
/*#define HAS_TELLDIR_PROTO /**/
#define SETUID_SCRIPTS_ARE_SECURE_NOW /**/
/*#define DOSUID /**/
+/* Shmat_t:
+ * This symbol holds the return type of the shmat() system call.
+ * Usually set to 'void *' or 'char *'.
+ */
+/* HAS_SHMAT_PROTOTYPE:
+ * This symbol, if defined, indicates that the sys/shm.h includes
+ * a prototype for shmat(). Otherwise, it is up to the program to
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
+ * but not always right so it should be emitted by the program only
+ * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
+ */
+#define Shmat_t void * /**/
+#define HAS_SHMAT_PROTOTYPE /**/
+
+/* I_NDBM:
+ * This symbol, if defined, indicates that <ndbm.h> exists and should
+ * be included.
+ */
+/*#define I_NDBM /**/
+
/* I_STDARG:
* This symbol, if defined, indicates that <stdarg.h> exists and should
* be included.
#define I_STDARG /**/
/*#define I_VARARGS /**/
+/* CAN_PROTOTYPE:
+ * If defined, this macro indicates that the C compiler can handle
+ * function prototypes.
+ */
+/* PERL_PROTO_:
+ * This macro is used to declare function parameters for folks who want
+ * to make declarations with prototypes using a different style than
+ * the above macros. Use double parentheses. For example:
+ *
+ * int main PERL_PROTO_((int argc, char *argv[]));
+ */
+#define CAN_PROTOTYPE /**/
+#ifdef CAN_PROTOTYPE
+#else
+#endif
+
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* on this system to execute Bourne shell scripts. Usually, this will be
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO /**/
*/
#define HAS_SETSID /**/
-/* Shmat_t:
- * This symbol holds the return type of the shmat() system call.
- * Usually set to 'void *' or 'char *'.
- */
-/* HAS_SHMAT_PROTOTYPE:
- * This symbol, if defined, indicates that the sys/shm.h includes
- * a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
- * but not always right so it should be emitted by the program only
- * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
- */
-#define Shmat_t void * /**/
-#define HAS_SHMAT_PROTOTYPE /**/
-
/* HAS_STRCHR:
* This symbol is defined to indicate that the strchr()/strrchr()
* functions are available for string searching. If not, try the
*/
/*#define I_MEMORY /**/
-/* I_NDBM:
- * This symbol, if defined, indicates that <ndbm.h> exists and should
- * be included.
- */
-/*#define I_NDBM /**/
-
/* I_NET_ERRNO:
* This symbol, if defined, indicates that <net/errno.h> exists and
* should be included.
*/
/*#define I_VFORK /**/
-/* CAN_PROTOTYPE:
- * If defined, this macro indicates that the C compiler can handle
- * function prototypes.
- */
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
-#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
-
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* preprocessor can make decisions based on it.
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
/*#define HAS_TELLDIR_PROTO /**/
#define SETUID_SCRIPTS_ARE_SECURE_NOW /**/
/*#define DOSUID /**/
+/* Shmat_t:
+ * This symbol holds the return type of the shmat() system call.
+ * Usually set to 'void *' or 'char *'.
+ */
+/* HAS_SHMAT_PROTOTYPE:
+ * This symbol, if defined, indicates that the sys/shm.h includes
+ * a prototype for shmat(). Otherwise, it is up to the program to
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
+ * but not always right so it should be emitted by the program only
+ * when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
+ */
+#define Shmat_t void * /**/
+#define HAS_SHMAT_PROTOTYPE /**/
+
+/* I_NDBM:
+ * This symbol, if defined, indicates that <ndbm.h> exists and should
+ * be included.
+ */
+/*#define I_NDBM /**/
+
/* I_STDARG:
* This symbol, if defined, indicates that <stdarg.h> exists and should
* be included.
#define I_STDARG /**/
/*#define I_VARARGS /**/
+/* CAN_PROTOTYPE:
+ * If defined, this macro indicates that the C compiler can handle
+ * function prototypes.
+ */
+/* PERL_PROTO_:
+ * This macro is used to declare function parameters for folks who want
+ * to make declarations with prototypes using a different style than
+ * the above macros. Use double parentheses. For example:
+ *
+ * int main PERL_PROTO_((int argc, char *argv[]));
+ */
+#define CAN_PROTOTYPE /**/
+#ifdef CAN_PROTOTYPE
+#else
+#endif
+
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* on this system to execute Bourne shell scripts. Usually, this will be
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO /**/
--- /dev/null
+/* Beginning of modification history */
+/* Written 02-01-02 by Nick Ing-Simmons (nick@ing-simmons.net) */
+/* End of modification history */
+
+/* VOS doesn't supply a truncate function, so we build one up
+ from the available POSIX functions. */
+
+#include <fcntl.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+int
+truncate(const char *path, off_t len)
+{
+ int fd = open(path,O_WRONLY);
+ int code = -1;
+ if (fd >= 0) {
+ code = ftruncate(fd,len);
+ close(fd);
+ }
+ return code;
+}
/* The following declaration is an avoidance for posix-950. */
extern int ioctl (int fd, int request, ...);
+
+/* Specify a prototype for truncate() since we are supplying one. */
+extern int truncate (const char *path, off_t len);
$mask |= $DeadBits{$word} if $fatal ;
}
else
- { croak("unknown warnings category '$word'")}
+ { croak("Unknown warnings category '$word'")}
}
return $mask ;
$category = shift ;
if (ref $category) {
croak ("not an object")
- if $category !~ /^([^=]+)=/ ;+
+ if $category !~ /^([^=]+)=/ ;
$category = $1 ;
$isobj = 1 ;
}
$offset = $Offsets{$category};
- croak("unknown warnings category '$category'")
+ croak("Unknown warnings category '$category'")
unless defined $offset;
}
else {
/* HAS_SHMAT_PROTOTYPE:
* This symbol, if defined, indicates that the sys/shm.h includes
* a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
* but not always right so it should be emitted by the program only
* when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
*/
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO /**/
/* HAS_SHMAT_PROTOTYPE:
* This symbol, if defined, indicates that the sys/shm.h includes
* a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
* but not always right so it should be emitted by the program only
* when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
*/
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO /**/
/* HAS_SHMAT_PROTOTYPE:
* This symbol, if defined, indicates that the sys/shm.h includes
* a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
* but not always right so it should be emitted by the program only
* when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
*/
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
/* INTSIZE:
* This symbol contains the value of sizeof(int) so that the C
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO /**/
/* HAS_SHMAT_PROTOTYPE:
* This symbol, if defined, indicates that the sys/shm.h includes
* a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
* but not always right so it should be emitted by the program only
* when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
*/
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
/* HAS_SHMAT_PROTOTYPE:
* This symbol, if defined, indicates that the sys/shm.h includes
* a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
* but not always right so it should be emitted by the program only
* when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
*/
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sbrk() function. Otherwise, it is up
* to the program to supply one. Good guesses are
- * extern void* sbrk _((int));
- * extern void* sbrk _((size_t));
+ * extern void* sbrk(int);
+ * extern void* sbrk(size_t);
*/
/*#define HAS_SBRK_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the sockatmark() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern int sockatmark _((int));
+ * extern int sockatmark(int);
*/
/*#define HAS_SOCKATMARK_PROTO /**/
/* HAS_SHMAT_PROTOTYPE:
* This symbol, if defined, indicates that the sys/shm.h includes
* a prototype for shmat(). Otherwise, it is up to the program to
- * guess one. Shmat_t shmat _((int, Shmat_t, int)) is a good guess,
+ * guess one. Shmat_t shmat(int, Shmat_t, int) is a good guess,
* but not always right so it should be emitted by the program only
* when HAS_SHMAT_PROTOTYPE is not defined to avoid conflicting defs.
*/
* If defined, this macro indicates that the C compiler can handle
* function prototypes.
*/
-/* _:
- * This macro is used to declare function parameters for folks who want
- * to make declarations with prototypes using a different style than
- * the above macros. Use double parentheses. For example:
- *
- * int main _((int argc, char *argv[]));
- */
#define CAN_PROTOTYPE /**/
-#ifdef CAN_PROTOTYPE
-#define _(args) args
-#else
-#define _(args) ()
-#endif
/* SH_PATH:
* This symbol contains the full pathname to the shell used on this
* This symbol, if defined, indicates that the system provides
* a prototype for the drand48() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern double drand48 _((void));
+ * extern double drand48(void);
*/
/*#define HAS_DRAND48_PROTO /**/
* This symbol, if defined, indicates that the system provides
* a prototype for the telldir() function. Otherwise, it is up
* to the program to supply one. A good guess is
- * extern long telldir _((DIR*));
+ * extern long telldir(DIR*);
*/
#define HAS_TELLDIR_PROTO /**/
/* $RCSfile: EXTERN.h,v $$Revision: 4.1 $$Date: 92/08/07 18:29:05 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: INTERN.h,v $$Revision: 4.1 $$Date: 92/08/07 18:29:06 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#line 2 "a2p.y"
/* $RCSfile: a2p.y,v $$Revision: 4.1 $$Date: 92/08/07 18:29:12 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: a2p.h,v $$Revision: 4.1 $$Date: 92/08/07 18:29:09 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
%{
/* $RCSfile: a2p.y,v $$Revision: 4.1 $$Date: 92/08/07 18:29:12 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: hash.c,v $$Revision: 4.1 $$Date: 92/08/07 18:29:20 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: hash.h,v $$Revision: 4.1 $$Date: 92/08/07 18:29:21 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* proto.h
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: str.c,v $$Revision: 4.1 $$Date: 92/08/07 18:29:26 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: str.h,v $$Revision: 4.1 $$Date: 92/08/07 18:29:27 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: util.c,v $$Revision: 4.1 $$Date: 92/08/07 18:29:29 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: util.h,v $$Revision: 4.1 $$Date: 92/08/07 18:29:30 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
/* $RCSfile: walk.c,v $$Revision: 4.1 $$Date: 92/08/07 18:29:31 $
*
- * Copyright (c) 1991-2001, Larry Wall
+ * Copyright (c) 1991-2002, Larry Wall
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
+/* xsutils.c
+ *
+ * Copyright (c) 1999-2002, Larry Wall
+ *
+ * You may distribute under the terms of either the GNU General Public
+ * License or the Artistic License, as specified in the README file.
+ *
+ */
+
#include "EXTERN.h"
#define PERL_IN_XSUTILS_C
#include "perl.h"
projects / p5sagit/p5-mst-13.2.git / commitdiff