From 538bd84228c9d1ae064d871c020d1e684d7d0494 Mon Sep 17 00:00:00 2001 From: Scott Talbert Date: Thu, 16 Jul 2026 19:08:09 -0400 Subject: [PATCH] [PATCH] Update Unicode mapping tables to current versions The primary motivation for this is to resolve a licensing issue with these files (the files have been relicensed with a Debian-approved license), but there were a few minor fixes/additions since the previous update. The generation code/scripts required some modernization to get it working on a current system, as well as needing to handle the format of CP866.TXT, which is a bit different than the other files. Gbp-Pq: Name update-unicode-mapping-tables.patch --- misc/unictabl/mappings/8859-1.TXT | 39 +-- misc/unictabl/mappings/8859-10.TXT | 37 +-- misc/unictabl/mappings/8859-13.TXT | 38 +-- misc/unictabl/mappings/8859-14.TXT | 40 +-- misc/unictabl/mappings/8859-15.TXT | 40 +-- misc/unictabl/mappings/8859-2.TXT | 39 +-- misc/unictabl/mappings/8859-3.TXT | 39 +-- misc/unictabl/mappings/8859-4.TXT | 39 +-- misc/unictabl/mappings/8859-5.TXT | 39 +-- misc/unictabl/mappings/8859-6.TXT | 43 +-- misc/unictabl/mappings/8859-7.TXT | 51 ++- misc/unictabl/mappings/8859-8.TXT | 42 ++- misc/unictabl/mappings/8859-9.TXT | 39 +-- .../mappings/{CP866.txt => CP866.TXT} | 0 misc/unictabl/mappings/KOI8-R.TXT | 34 +- misc/unictabl/mappings/KOI8-U.TXT | 301 ++++++++++++++++++ misc/unictabl/mk_ctable.c | 17 +- misc/unictabl/mk_encodings.sh | 23 +- misc/unictabl/mk_fallbacks.sh | 6 +- src/common/unictabl.inc | 33 +- 20 files changed, 543 insertions(+), 396 deletions(-) rename misc/unictabl/mappings/{CP866.txt => CP866.TXT} (100%) create mode 100644 misc/unictabl/mappings/KOI8-U.TXT diff --git a/misc/unictabl/mappings/8859-1.TXT b/misc/unictabl/mappings/8859-1.TXT index 473ecab..3a55afe 100644 --- a/misc/unictabl/mappings/8859-1.TXT +++ b/misc/unictabl/mappings/8859-1.TXT @@ -1,26 +1,14 @@ +# 8859-1.TXT +# Date: 2015-12-02 20:19:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-1:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-1 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-10.TXT b/misc/unictabl/mappings/8859-10.TXT index 374a42b..0ec67d7 100644 --- a/misc/unictabl/mappings/8859-10.TXT +++ b/misc/unictabl/mappings/8859-10.TXT @@ -1,26 +1,14 @@ +# 8859-10.TXT +# Date: 2015-12-02 21:53:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-10:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.1 +# Table version: 2.0 # Table format: Format A -# Date: 1999 October 11 -# Authors: Ken Whistler -# -# Copyright (c) 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 October 11 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -36,14 +24,15 @@ # # Version history # 1.0 version new. -# 1.1 corrected mistake in mapping of 0xA4 +# 1.1 corrected mistake in mapping of 0xA4 +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-13.TXT b/misc/unictabl/mappings/8859-13.TXT index cd11b53..b613dc0 100644 --- a/misc/unictabl/mappings/8859-13.TXT +++ b/misc/unictabl/mappings/8859-13.TXT @@ -1,26 +1,14 @@ +# 8859-13.TXT +# Date: 2015-12-02 22:03:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-13:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -34,12 +22,16 @@ # # The entries are in ISO/IEC 8859-13 order. # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-14.TXT b/misc/unictabl/mappings/8859-14.TXT index 36038f4..0351d16 100644 --- a/misc/unictabl/mappings/8859-14.TXT +++ b/misc/unictabl/mappings/8859-14.TXT @@ -1,27 +1,15 @@ +# 8859-14.TXT +# Date: 2015-12-02 22:05:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-14:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Markus Kuhn -# Ken Whistler -# -# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Markus Kuhn +# Ken Whistler # # General notes: # @@ -35,12 +23,16 @@ # # The entries are in ISO/IEC 8859-14 order. # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-15.TXT b/misc/unictabl/mappings/8859-15.TXT index 1e31970..ada8fca 100644 --- a/misc/unictabl/mappings/8859-15.TXT +++ b/misc/unictabl/mappings/8859-15.TXT @@ -1,27 +1,15 @@ +# 8859-15.TXT +# Date: 2015-12-02 22:06:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-15:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Markus Kuhn -# Ken Whistler -# -# Copyright (c) 1998 - 1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Markus Kuhn +# Ken Whistler # # General notes: # @@ -37,12 +25,16 @@ # # Version history # +# Version history +# 1.0 version: created +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-2.TXT b/misc/unictabl/mappings/8859-2.TXT index e45df25..20da9ba 100644 --- a/misc/unictabl/mappings/8859-2.TXT +++ b/misc/unictabl/mappings/8859-2.TXT @@ -1,26 +1,14 @@ +# 8859-2.TXT +# Date: 2015-12-02 21:34:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO 8859-2:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-2 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-3.TXT b/misc/unictabl/mappings/8859-3.TXT index 9b6ac69..5a6c5de 100644 --- a/misc/unictabl/mappings/8859-3.TXT +++ b/misc/unictabl/mappings/8859-3.TXT @@ -1,26 +1,14 @@ +# 8859-3.TXT +# Date: 2015-12-02 21:39:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-3:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-3 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-4.TXT b/misc/unictabl/mappings/8859-4.TXT index 662e698..e2f5e72 100644 --- a/misc/unictabl/mappings/8859-4.TXT +++ b/misc/unictabl/mappings/8859-4.TXT @@ -1,26 +1,14 @@ +# 8859-4.TXT +# Date: 2015-12-02 21:41:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-4:1998 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-4 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-5.TXT b/misc/unictabl/mappings/8859-5.TXT index a7ed1ce..a574c3f 100644 --- a/misc/unictabl/mappings/8859-5.TXT +++ b/misc/unictabl/mappings/8859-5.TXT @@ -1,26 +1,14 @@ +# 8859-5.TXT +# Date: 2015-12-02 21:43:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO 8859-5:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -35,15 +23,16 @@ # The entries are in ISO/IEC 8859-5 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-6.TXT b/misc/unictabl/mappings/8859-6.TXT index 69ac7f5..fed0af3 100644 --- a/misc/unictabl/mappings/8859-6.TXT +++ b/misc/unictabl/mappings/8859-6.TXT @@ -1,26 +1,14 @@ +# 8859-6.TXT +# Date: 2015-12-02 21:44:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO 8859-6:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -35,17 +23,18 @@ # The entries are in ISO/IEC 8859-6 order. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. -# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead -# of the Arabic digits (U+0660..U+0669). +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 0x30..0x39 remapped to the ASCII digits (U+0030..U+0039) instead +# of the Arabic digits (U+0660..U+0669). +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/8859-7.TXT b/misc/unictabl/mappings/8859-7.TXT index 52c42d0..610c4b6 100644 --- a/misc/unictabl/mappings/8859-7.TXT +++ b/misc/unictabl/mappings/8859-7.TXT @@ -1,34 +1,23 @@ +# 8859-7.TXT +# Date: 2015-12-02 21:47:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # -# Name: ISO 8859-7:1987 to Unicode -# Unicode version: 3.0 -# Table version: 1.0 +# Name: ISO 8859-7:2003 to Unicode +# Unicode version: 4.0 +# Table version: 3.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 2003-Nov-12 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # # This table contains the data the Unicode Consortium has on how -# ISO 8859-7:1987 characters map into Unicode. +# ISO 8859-7:2003 characters map into Unicode. # # ISO 8859-7:1987 is equivalent to ISO-IR-126, ELOT 928, -# and ECMA 118. +# and ECMA 118. ISO 8859-7:2003 adds two currency signs +# and one other character not in the earlier standard. # # Format: Three tab-separated columns # Column #1 is the ISO 8859-7 code (in hex as 0xXX) @@ -43,12 +32,17 @@ # Remap 0xA1 to U+2018 (instead of 0x02BD) to match text of 8859-7 # Remap 0xA2 to U+2019 (instead of 0x02BC) to match text of 8859-7 # +# 2.0 version updates 1.0 version by adding mappings for the +# three newly added characters 0xA4, 0xA5, 0xAA. +# +# 3.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -214,10 +208,13 @@ 0xA1 0x2018 # LEFT SINGLE QUOTATION MARK 0xA2 0x2019 # RIGHT SINGLE QUOTATION MARK 0xA3 0x00A3 # POUND SIGN +0xA4 0x20AC # EURO SIGN +0xA5 0x20AF # DRACHMA SIGN 0xA6 0x00A6 # BROKEN BAR 0xA7 0x00A7 # SECTION SIGN 0xA8 0x00A8 # DIAERESIS 0xA9 0x00A9 # COPYRIGHT SIGN +0xAA 0x037A # GREEK YPOGEGRAMMENI 0xAB 0x00AB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK 0xAC 0x00AC # NOT SIGN 0xAD 0x00AD # SOFT HYPHEN diff --git a/misc/unictabl/mappings/8859-8.TXT b/misc/unictabl/mappings/8859-8.TXT index 8fc271c..2005b4c 100644 --- a/misc/unictabl/mappings/8859-8.TXT +++ b/misc/unictabl/mappings/8859-8.TXT @@ -1,26 +1,14 @@ +# 8859-8.TXT +# Date: 2015-12-02 21:50:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-8:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 2000-Jan-03 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -37,13 +25,16 @@ # Version history # 1.0 version updates 0.1 version by adding mappings for all # control characters. +# 1.1 version updates to the published 8859-8:1999, correcting +# the mapping of 0xAF and adding mappings for LRM and RLM. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING @@ -219,7 +210,7 @@ 0xAC 0x00AC # NOT SIGN 0xAD 0x00AD # SOFT HYPHEN 0xAE 0x00AE # REGISTERED SIGN -0xAF 0x203E # OVERLINE +0xAF 0x00AF # MACRON 0xB0 0x00B0 # DEGREE SIGN 0xB1 0x00B1 # PLUS-MINUS SIGN 0xB2 0x00B2 # SUPERSCRIPT TWO @@ -263,3 +254,6 @@ 0xF8 0x05E8 # HEBREW LETTER RESH 0xF9 0x05E9 # HEBREW LETTER SHIN 0xFA 0x05EA # HEBREW LETTER TAV +0xFD 0x200E # LEFT-TO-RIGHT MARK +0xFE 0x200F # RIGHT-TO-LEFT MARK + diff --git a/misc/unictabl/mappings/8859-9.TXT b/misc/unictabl/mappings/8859-9.TXT index 22901f1..f18db22 100644 --- a/misc/unictabl/mappings/8859-9.TXT +++ b/misc/unictabl/mappings/8859-9.TXT @@ -1,26 +1,14 @@ +# 8859-9.TXT +# Date: 2015-12-02 21:51:00 GMT [KW] +# © 2015 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: ISO/IEC 8859-9:1999 to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 1999 July 27 -# Authors: Ken Whistler -# -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on magnetic media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. +# Date: 1999 July 27 (header updated: 2015 December 02) +# Authors: Ken Whistler # # General notes: # @@ -37,15 +25,16 @@ # ISO/IEC 8859-9 is also equivalent to ISO-IR-148. # # Version history -# 1.0 version updates 0.1 version by adding mappings for all -# control characters. +# 1.0 version: updates 0.1 version by adding mappings for all +# control characters. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings # # Updated versions of this file may be found in: -# +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/CP866.txt b/misc/unictabl/mappings/CP866.TXT similarity index 100% rename from misc/unictabl/mappings/CP866.txt rename to misc/unictabl/mappings/CP866.TXT diff --git a/misc/unictabl/mappings/KOI8-R.TXT b/misc/unictabl/mappings/KOI8-R.TXT index 5105610..2a1afb7 100644 --- a/misc/unictabl/mappings/KOI8-R.TXT +++ b/misc/unictabl/mappings/KOI8-R.TXT @@ -1,27 +1,15 @@ +# KOI8-R.TXT +# Date: 2016-01-04 23:05:00 GMT [KW] +# © 2016 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # # Name: KOI8-R (RFC1489) to Unicode # Unicode version: 3.0 -# Table version: 1.0 +# Table version: 2.0 # Table format: Format A -# Date: 18 August 1999 +# Date: 18 August 1999 (header updated: 2016-January-04) # Authors: Helmut Richter # -# Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. -# -# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). -# 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 provided on optical media by Unicode, Inc., the sole -# remedy for any claim will be exchange of defective media within 90 -# days of receipt. -# -# Unicode, Inc. hereby grants the right to freely use the information -# supplied in this file in the creation of products supporting the -# Unicode Standard, and to make copies of this file in any form for -# internal or external distribution as long as this notice remains -# attached. -# # General notes: # # This table contains the data the Unicode Consortium has on how @@ -39,10 +27,14 @@ # # Version history # 1.0 version: created. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# +# Updated versions of this file may be found in: +# http://www.unicode.org/Public/MAPPINGS/ # -# Any comments or problems, contact -# Please note that is an archival address; -# notices will be checked, but do not expect an immediate response. +# Any comments or problems, contact us at: +# http://www.unicode.org/reporting.html # 0x00 0x0000 # NULL 0x01 0x0001 # START OF HEADING diff --git a/misc/unictabl/mappings/KOI8-U.TXT b/misc/unictabl/mappings/KOI8-U.TXT new file mode 100644 index 0000000..c533b39 --- /dev/null +++ b/misc/unictabl/mappings/KOI8-U.TXT @@ -0,0 +1,301 @@ +# KOI8-U.TXT +# Date: 2016-01-04 23:09:00 GMT [KW] +# © 2016 Unicode®, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# +# Name: KOI8-U (RFC2319) to Unicode +# Unicode version: 5.1 +# Table version: 2.0 +# Table format: Format A +# Date: 13 October 2008 (header updated: 2016-January-04) +# Authors: Philippe Verdy , +# Helmut Richter +# +# General notes: +# +# This table contains the data the Unicode Consortium has on how +# KOI8-U characters map into Unicode. The underlying document is the +# mapping described in RFC 2319. No statements are made as to whether +# this mapping is the same as the mapping defined as "Code Page 878" +# with some vendors. +# +# The KOI8-U (RFC2319) encoding is a variant based on KOI8-R (RFC1489), +# where the support for four additional Cyrillic letters was added (both small +# and capital letters), replacing 8 box-drawing characters. It is still widely +# used to encode texts in Ukrainian, Byelorussian and Bulgarian. +# +# Format: Three tab-separated columns +# Column #1 is the KOI8-U code (in hex as 0xXX) +# Column #2 is the Unicode (in hex as 0xXXXX) +# Column #3 the Unicode name (follows a comment sign, '#') +# +# The entries are in KOI8-U order. +# +# Version history +# 1.0 version: created. +# 2.0 version: updates to copyright notice and terms of use; no +# changes to character mappings +# +# Updated versions of this file may be found in: +# +# +# Any comments or problems, contact the Unicode Consortium at: +# +# +0x00 0x0000 # NULL +0x01 0x0001 # START OF HEADING +0x02 0x0002 # START OF TEXT +0x03 0x0003 # END OF TEXT +0x04 0x0004 # END OF TRANSMISSION +0x05 0x0005 # ENQUIRY +0x06 0x0006 # ACKNOWLEDGE +0x07 0x0007 # BELL +0x08 0x0008 # BACKSPACE +0x09 0x0009 # HORIZONTAL TABULATION +0x0A 0x000A # LINE FEED +0x0B 0x000B # VERTICAL TABULATION +0x0C 0x000C # FORM FEED +0x0D 0x000D # CARRIAGE RETURN +0x0E 0x000E # SHIFT OUT +0x0F 0x000F # SHIFT IN +0x10 0x0010 # DATA LINK ESCAPE +0x11 0x0011 # DEVICE CONTROL ONE +0x12 0x0012 # DEVICE CONTROL TWO +0x13 0x0013 # DEVICE CONTROL THREE +0x14 0x0014 # DEVICE CONTROL FOUR +0x15 0x0015 # NEGATIVE ACKNOWLEDGE +0x16 0x0016 # SYNCHRONOUS IDLE +0x17 0x0017 # END OF TRANSMISSION BLOCK +0x18 0x0018 # CANCEL +0x19 0x0019 # END OF MEDIUM +0x1A 0x001A # SUBSTITUTE +0x1B 0x001B # ESCAPE +0x1C 0x001C # FILE SEPARATOR +0x1D 0x001D # GROUP SEPARATOR +0x1E 0x001E # RECORD SEPARATOR +0x1F 0x001F # UNIT SEPARATOR +0x20 0x0020 # SPACE +0x21 0x0021 # EXCLAMATION MARK +0x22 0x0022 # QUOTATION MARK +0x23 0x0023 # NUMBER SIGN +0x24 0x0024 # DOLLAR SIGN +0x25 0x0025 # PERCENT SIGN +0x26 0x0026 # AMPERSAND +0x27 0x0027 # APOSTROPHE +0x28 0x0028 # LEFT PARENTHESIS +0x29 0x0029 # RIGHT PARENTHESIS +0x2A 0x002A # ASTERISK +0x2B 0x002B # PLUS SIGN +0x2C 0x002C # COMMA +0x2D 0x002D # HYPHEN-MINUS +0x2E 0x002E # FULL STOP +0x2F 0x002F # SOLIDUS +0x30 0x0030 # DIGIT ZERO +0x31 0x0031 # DIGIT ONE +0x32 0x0032 # DIGIT TWO +0x33 0x0033 # DIGIT THREE +0x34 0x0034 # DIGIT FOUR +0x35 0x0035 # DIGIT FIVE +0x36 0x0036 # DIGIT SIX +0x37 0x0037 # DIGIT SEVEN +0x38 0x0038 # DIGIT EIGHT +0x39 0x0039 # DIGIT NINE +0x3A 0x003A # COLON +0x3B 0x003B # SEMICOLON +0x3C 0x003C # LESS-THAN SIGN +0x3D 0x003D # EQUALS SIGN +0x3E 0x003E # GREATER-THAN SIGN +0x3F 0x003F # QUESTION MARK +0x40 0x0040 # COMMERCIAL AT +0x41 0x0041 # LATIN CAPITAL LETTER A +0x42 0x0042 # LATIN CAPITAL LETTER B +0x43 0x0043 # LATIN CAPITAL LETTER C +0x44 0x0044 # LATIN CAPITAL LETTER D +0x45 0x0045 # LATIN CAPITAL LETTER E +0x46 0x0046 # LATIN CAPITAL LETTER F +0x47 0x0047 # LATIN CAPITAL LETTER G +0x48 0x0048 # LATIN CAPITAL LETTER H +0x49 0x0049 # LATIN CAPITAL LETTER I +0x4A 0x004A # LATIN CAPITAL LETTER J +0x4B 0x004B # LATIN CAPITAL LETTER K +0x4C 0x004C # LATIN CAPITAL LETTER L +0x4D 0x004D # LATIN CAPITAL LETTER M +0x4E 0x004E # LATIN CAPITAL LETTER N +0x4F 0x004F # LATIN CAPITAL LETTER O +0x50 0x0050 # LATIN CAPITAL LETTER P +0x51 0x0051 # LATIN CAPITAL LETTER Q +0x52 0x0052 # LATIN CAPITAL LETTER R +0x53 0x0053 # LATIN CAPITAL LETTER S +0x54 0x0054 # LATIN CAPITAL LETTER T +0x55 0x0055 # LATIN CAPITAL LETTER U +0x56 0x0056 # LATIN CAPITAL LETTER V +0x57 0x0057 # LATIN CAPITAL LETTER W +0x58 0x0058 # LATIN CAPITAL LETTER X +0x59 0x0059 # LATIN CAPITAL LETTER Y +0x5A 0x005A # LATIN CAPITAL LETTER Z +0x5B 0x005B # LEFT SQUARE BRACKET +0x5C 0x005C # REVERSE SOLIDUS +0x5D 0x005D # RIGHT SQUARE BRACKET +0x5E 0x005E # CIRCUMFLEX ACCENT +0x5F 0x005F # LOW LINE +0x60 0x0060 # GRAVE ACCENT +0x61 0x0061 # LATIN SMALL LETTER A +0x62 0x0062 # LATIN SMALL LETTER B +0x63 0x0063 # LATIN SMALL LETTER C +0x64 0x0064 # LATIN SMALL LETTER D +0x65 0x0065 # LATIN SMALL LETTER E +0x66 0x0066 # LATIN SMALL LETTER F +0x67 0x0067 # LATIN SMALL LETTER G +0x68 0x0068 # LATIN SMALL LETTER H +0x69 0x0069 # LATIN SMALL LETTER I +0x6A 0x006A # LATIN SMALL LETTER J +0x6B 0x006B # LATIN SMALL LETTER K +0x6C 0x006C # LATIN SMALL LETTER L +0x6D 0x006D # LATIN SMALL LETTER M +0x6E 0x006E # LATIN SMALL LETTER N +0x6F 0x006F # LATIN SMALL LETTER O +0x70 0x0070 # LATIN SMALL LETTER P +0x71 0x0071 # LATIN SMALL LETTER Q +0x72 0x0072 # LATIN SMALL LETTER R +0x73 0x0073 # LATIN SMALL LETTER S +0x74 0x0074 # LATIN SMALL LETTER T +0x75 0x0075 # LATIN SMALL LETTER U +0x76 0x0076 # LATIN SMALL LETTER V +0x77 0x0077 # LATIN SMALL LETTER W +0x78 0x0078 # LATIN SMALL LETTER X +0x79 0x0079 # LATIN SMALL LETTER Y +0x7A 0x007A # LATIN SMALL LETTER Z +0x7B 0x007B # LEFT CURLY BRACKET +0x7C 0x007C # VERTICAL LINE +0x7D 0x007D # RIGHT CURLY BRACKET +0x7E 0x007E # TILDE +0x7F 0x007F # DELETE +0x80 0x2500 # BOX DRAWINGS LIGHT HORIZONTAL +0x81 0x2502 # BOX DRAWINGS LIGHT VERTICAL +0x82 0x250C # BOX DRAWINGS LIGHT DOWN AND RIGHT +0x83 0x2510 # BOX DRAWINGS LIGHT DOWN AND LEFT +0x84 0x2514 # BOX DRAWINGS LIGHT UP AND RIGHT +0x85 0x2518 # BOX DRAWINGS LIGHT UP AND LEFT +0x86 0x251C # BOX DRAWINGS LIGHT VERTICAL AND RIGHT +0x87 0x2524 # BOX DRAWINGS LIGHT VERTICAL AND LEFT +0x88 0x252C # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL +0x89 0x2534 # BOX DRAWINGS LIGHT UP AND HORIZONTAL +0x8A 0x253C # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL +0x8B 0x2580 # UPPER HALF BLOCK +0x8C 0x2584 # LOWER HALF BLOCK +0x8D 0x2588 # FULL BLOCK +0x8E 0x258C # LEFT HALF BLOCK +0x8F 0x2590 # RIGHT HALF BLOCK +0x90 0x2591 # LIGHT SHADE +0x91 0x2592 # MEDIUM SHADE +0x92 0x2593 # DARK SHADE +0x93 0x2320 # TOP HALF INTEGRAL +0x94 0x25A0 # BLACK SQUARE +0x95 0x2219 # BULLET OPERATOR +0x96 0x221A # SQUARE ROOT +0x97 0x2248 # ALMOST EQUAL TO +0x98 0x2264 # LESS-THAN OR EQUAL TO +0x99 0x2265 # GREATER-THAN OR EQUAL TO +0x9A 0x00A0 # NO-BREAK SPACE +0x9B 0x2321 # BOTTOM HALF INTEGRAL +0x9C 0x00B0 # DEGREE SIGN +0x9D 0x00B2 # SUPERSCRIPT TWO +0x9E 0x00B7 # MIDDLE DOT +0x9F 0x00F7 # DIVISION SIGN +0xA0 0x2550 # BOX DRAWINGS DOUBLE HORIZONTAL +0xA1 0x2551 # BOX DRAWINGS DOUBLE VERTICAL +0xA2 0x2552 # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE +0xA3 0x0451 # CYRILLIC SMALL LETTER IO +0xA4 0x0454 # CYRILLIC SMALL LETTER UKRAINIAN IE +0xA5 0x2554 # BOX DRAWINGS DOUBLE DOWN AND RIGHT +0xA6 0x0456 # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +0xA7 0x0457 # CYRILLIC SMALL LETTER YI (UKRAINIAN) +0xA8 0x2557 # BOX DRAWINGS DOUBLE DOWN AND LEFT +0xA9 0x2558 # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE +0xAA 0x2559 # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE +0xAB 0x255A # BOX DRAWINGS DOUBLE UP AND RIGHT +0xAC 0x255B # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE +0xAD 0x0491 # CYRILLIC SMALL LETTER GHE WITH UPTURN +0xAE 0x255D # BOX DRAWINGS DOUBLE UP AND LEFT +0xAF 0x255E # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE +0xB0 0x255F # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE +0xB1 0x2560 # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT +0xB2 0x2561 # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE +0xB3 0x0401 # CYRILLIC CAPITAL LETTER IO +0xB4 0x0404 # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0xB5 0x2563 # BOX DRAWINGS DOUBLE VERTICAL AND LEFT +0xB6 0x0406 # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0xB7 0x0407 # CYRILLIC CAPITAL LETTER YI (UKRAINIAN) +0xB8 0x2566 # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL +0xB9 0x2567 # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE +0xBA 0x2568 # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE +0xBB 0x2569 # BOX DRAWINGS DOUBLE UP AND HORIZONTAL +0xBC 0x256A # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE +0xBD 0x0490 # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0xBE 0x256C # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL +0xBF 0x00A9 # COPYRIGHT SIGN +0xC0 0x044E # CYRILLIC SMALL LETTER YU +0xC1 0x0430 # CYRILLIC SMALL LETTER A +0xC2 0x0431 # CYRILLIC SMALL LETTER BE +0xC3 0x0446 # CYRILLIC SMALL LETTER TSE +0xC4 0x0434 # CYRILLIC SMALL LETTER DE +0xC5 0x0435 # CYRILLIC SMALL LETTER IE +0xC6 0x0444 # CYRILLIC SMALL LETTER EF +0xC7 0x0433 # CYRILLIC SMALL LETTER GHE +0xC8 0x0445 # CYRILLIC SMALL LETTER HA +0xC9 0x0438 # CYRILLIC SMALL LETTER I +0xCA 0x0439 # CYRILLIC SMALL LETTER SHORT I +0xCB 0x043A # CYRILLIC SMALL LETTER KA +0xCC 0x043B # CYRILLIC SMALL LETTER EL +0xCD 0x043C # CYRILLIC SMALL LETTER EM +0xCE 0x043D # CYRILLIC SMALL LETTER EN +0xCF 0x043E # CYRILLIC SMALL LETTER O +0xD0 0x043F # CYRILLIC SMALL LETTER PE +0xD1 0x044F # CYRILLIC SMALL LETTER YA +0xD2 0x0440 # CYRILLIC SMALL LETTER ER +0xD3 0x0441 # CYRILLIC SMALL LETTER ES +0xD4 0x0442 # CYRILLIC SMALL LETTER TE +0xD5 0x0443 # CYRILLIC SMALL LETTER U +0xD6 0x0436 # CYRILLIC SMALL LETTER ZHE +0xD7 0x0432 # CYRILLIC SMALL LETTER VE +0xD8 0x044C # CYRILLIC SMALL LETTER SOFT SIGN +0xD9 0x044B # CYRILLIC SMALL LETTER YERU +0xDA 0x0437 # CYRILLIC SMALL LETTER ZE +0xDB 0x0448 # CYRILLIC SMALL LETTER SHA +0xDC 0x044D # CYRILLIC SMALL LETTER E +0xDD 0x0449 # CYRILLIC SMALL LETTER SHCHA +0xDE 0x0447 # CYRILLIC SMALL LETTER CHE +0xDF 0x044A # CYRILLIC SMALL LETTER HARD SIGN +0xE0 0x042E # CYRILLIC CAPITAL LETTER YU +0xE1 0x0410 # CYRILLIC CAPITAL LETTER A +0xE2 0x0411 # CYRILLIC CAPITAL LETTER BE +0xE3 0x0426 # CYRILLIC CAPITAL LETTER TSE +0xE4 0x0414 # CYRILLIC CAPITAL LETTER DE +0xE5 0x0415 # CYRILLIC CAPITAL LETTER IE +0xE6 0x0424 # CYRILLIC CAPITAL LETTER EF +0xE7 0x0413 # CYRILLIC CAPITAL LETTER GHE +0xE8 0x0425 # CYRILLIC CAPITAL LETTER HA +0xE9 0x0418 # CYRILLIC CAPITAL LETTER I +0xEA 0x0419 # CYRILLIC CAPITAL LETTER SHORT I +0xEB 0x041A # CYRILLIC CAPITAL LETTER KA +0xEC 0x041B # CYRILLIC CAPITAL LETTER EL +0xED 0x041C # CYRILLIC CAPITAL LETTER EM +0xEE 0x041D # CYRILLIC CAPITAL LETTER EN +0xEF 0x041E # CYRILLIC CAPITAL LETTER O +0xF0 0x041F # CYRILLIC CAPITAL LETTER PE +0xF1 0x042F # CYRILLIC CAPITAL LETTER YA +0xF2 0x0420 # CYRILLIC CAPITAL LETTER ER +0xF3 0x0421 # CYRILLIC CAPITAL LETTER ES +0xF4 0x0422 # CYRILLIC CAPITAL LETTER TE +0xF5 0x0423 # CYRILLIC CAPITAL LETTER U +0xF6 0x0416 # CYRILLIC CAPITAL LETTER ZHE +0xF7 0x0412 # CYRILLIC CAPITAL LETTER VE +0xF8 0x042C # CYRILLIC CAPITAL LETTER SOFT SIGN +0xF9 0x042B # CYRILLIC CAPITAL LETTER YERU +0xFA 0x0417 # CYRILLIC CAPITAL LETTER ZE +0xFB 0x0428 # CYRILLIC CAPITAL LETTER SHA +0xFC 0x042D # CYRILLIC CAPITAL LETTER E +0xFD 0x0429 # CYRILLIC CAPITAL LETTER SHCHA +0xFE 0x0427 # CYRILLIC CAPITAL LETTER CHE +0xFF 0x042A # CYRILLIC CAPITAL LETTER HARD SIGN diff --git a/misc/unictabl/mk_ctable.c b/misc/unictabl/mk_ctable.c index 0ba584d..965d4b3 100644 --- a/misc/unictabl/mk_ctable.c +++ b/misc/unictabl/mk_ctable.c @@ -1,6 +1,7 @@ #include +#include typedef struct { unsigned char c; @@ -31,13 +32,13 @@ int main(int argc, char *argv[]) scanf("%i\t%i\n", &enc, &unic); table[enc].u = unic; table[enc].c = enc; - if (enc < 128 && enc != unic) - fprintf(stderr, "7bit ASCII incompatibilit (%s): %i->%i\n", + if (enc < 128 && enc != unic) + fprintf(stderr, "7bit ASCII incompatibilit (%s): %i->%i\n", argv[2], enc, unic); } - + /* dump it: */ - + printf("\n\n" "/*\n" " * %s to Unicode recoding table\n" @@ -45,9 +46,9 @@ int main(int argc, char *argv[]) " */\n\n" "static const wxUint16 encoding_table__%s[128] = {", argv[2], argv[1], argv[2]); - + for (i = 128; i < 256; i++) - { + { if (i % 8 == 0) printf("\n "); printf(" 0x%04X%c", table[i].u, (i == 255) ? '\n' : ','); @@ -65,9 +66,9 @@ int main(int argc, char *argv[]) printf("\n" "static wxUint16 encoding_table_rev__%s[128] = {", argv[2]); - + for (i = 128; i < 256; i++) - { + { if (i % 4 == 0) printf("\n "); printf("{c:0x%02X,u:0x%04X}%c ", table[i].c, table[i].u, (i == 255) ? '\n' : ','); diff --git a/misc/unictabl/mk_encodings.sh b/misc/unictabl/mk_encodings.sh index 4f04323..0137218 100755 --- a/misc/unictabl/mk_encodings.sh +++ b/misc/unictabl/mk_encodings.sh @@ -19,26 +19,13 @@ echo " * * Parts of this file are based on tables published by Unicode, Inc. * Original tables are freely available at - * ftp://ftp.unicode.org/Public/MAPPINGS + * https://www.unicode.org/Public/MAPPINGS * * Original copyright info as present in mapping tables follows: * * - * Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. - * - * This file is provided as-is by Unicode, Inc. (The Unicode Consortium). - * 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 provided on optical media by Unicode, Inc., the sole - * remedy for any claim will be exchange of defective media within 90 - * days of receipt. - * - * Unicode, Inc. hereby grants the right to freely use the information - * supplied in this file in the creation of products supporting the - * Unicode Standard, and to make copies of this file in any form for - * internal or external distribution as long as this notice remains - * attached. + * © 2015 Unicode®, Inc. + * For terms of use, see http://www.unicode.org/terms_of_use.html */ " > unictabl.inc @@ -48,7 +35,7 @@ echo " * creating C tables..." all_encodings="" -for i in mappings/*.TXT ; do +for i in $(printf '%s\n' mappings/*.TXT | LC_ALL=C sort); do enc=`echo $i | cut -c10- | tr - _ | sed 's/\.TXT//g' |\ sed 's/8859_\(.*\)/ISO8859_\1/g @@ -116,5 +103,5 @@ for i in $all_encodings ; do echo " { wxFONTENCODING_$i, encoding_table__$i}," >> unictabl.inc done -echo " {wxFONTENCODING_MAX /*anything*/, NULL}" >> unictabl.inc +echo " {wxFONTENCODING_MAX /*anything*/, nullptr}" >> unictabl.inc echo " };" >> unictabl.inc diff --git a/misc/unictabl/mk_fallbacks.sh b/misc/unictabl/mk_fallbacks.sh index 4eb4382..1277c0b 100755 --- a/misc/unictabl/mk_fallbacks.sh +++ b/misc/unictabl/mk_fallbacks.sh @@ -14,6 +14,7 @@ add_fallback() echo " * getting list of needed unicode characters..." cat mappings/*.TXT | sed -n '/^0x../p' | \ + sed 's/#[\t ]*/#\t/' | sed -E 's/0x([0-9a-fA-F]+)/0x\U\1/g' | \ cut -f2,4 | sort | uniq | sed -n '/^0x/p' > _tmp1 cat _tmp1 | cut -f1 | sort | uniq > _tmp2 @@ -35,7 +36,7 @@ echo " - for latin capital letters..." cat _tmp3 | grep 'LATIN CAPITAL LETTER [A-Z]$' > _tmp6 cat _tmp3 | grep 'LATIN CAPITAL LETTER [A-Z] WITH' >> _tmp6 -cat _tmp6 | sort +2 > _tmp4 +cat _tmp6 | sort -k3 > _tmp4 cat _tmp4 | while read i ; do code=`echo $i | cut -c1-6` @@ -49,7 +50,7 @@ echo " - for latin small letters..." cat _tmp3 | grep 'LATIN SMALL LETTER [A-Z]$' > _tmp6 cat _tmp3 | grep 'LATIN SMALL LETTER [A-Z] WITH' >> _tmp6 -cat _tmp6 | sort +2 > _tmp4 +cat _tmp6 | sort -k3 > _tmp4 cat _tmp4 | while read i ; do code=`echo $i | cut -c1-6` @@ -70,4 +71,3 @@ echo " * removing infinite loops from fallback tables..." cat _tmp5 | grep -v '\(0x....\) \1' | sort > Fallbacks rm -f _tmp1 _tmp2 _tmp3 _tmp4 _tmp5 _tmp6 - diff --git a/src/common/unictabl.inc b/src/common/unictabl.inc index 2993424..8a6a32e 100644 --- a/src/common/unictabl.inc +++ b/src/common/unictabl.inc @@ -10,26 +10,13 @@ * * Parts of this file are based on tables published by Unicode, Inc. * Original tables are freely available at - * ftp://ftp.unicode.org/Public/MAPPINGS + * https://www.unicode.org/Public/MAPPINGS * * Original copyright info as present in mapping tables follows: * * - * Copyright (c) 1991-1999 Unicode, Inc. All Rights reserved. - * - * This file is provided as-is by Unicode, Inc. (The Unicode Consortium). - * 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 provided on optical media by Unicode, Inc., the sole - * remedy for any claim will be exchange of defective media within 90 - * days of receipt. - * - * Unicode, Inc. hereby grants the right to freely use the information - * supplied in this file in the creation of products supporting the - * Unicode Standard, and to make copies of this file in any form for - * internal or external distribution as long as this notice remains - * attached. + * © 2015 Unicode®, Inc. + * For terms of use, see http://www.unicode.org/terms_of_use.html */ @@ -295,8 +282,8 @@ static const wxUint16 encoding_table__ISO8859_7[128] = { 0x0088, 0x0089, 0x008A, 0x008B, 0x008C, 0x008D, 0x008E, 0x008F, 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009A, 0x009B, 0x009C, 0x009D, 0x009E, 0x009F, - 0x00A0, 0x2018, 0x2019, 0x00A3, 0x0000, 0x0000, 0x00A6, 0x00A7, - 0x00A8, 0x00A9, 0x0000, 0x00AB, 0x00AC, 0x00AD, 0x0000, 0x2015, + 0x00A0, 0x2018, 0x2019, 0x00A3, 0x20AC, 0x20AF, 0x00A6, 0x00A7, + 0x00A8, 0x00A9, 0x037A, 0x00AB, 0x00AC, 0x00AD, 0x0000, 0x2015, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x0384, 0x0385, 0x0386, 0x00B7, 0x0388, 0x0389, 0x038A, 0x00BB, 0x038C, 0x00BD, 0x038E, 0x038F, 0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397, @@ -321,7 +308,7 @@ static const wxUint16 encoding_table__ISO8859_8[128] = { 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009A, 0x009B, 0x009C, 0x009D, 0x009E, 0x009F, 0x00A0, 0x0000, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7, - 0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x203E, + 0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF, 0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7, 0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, @@ -331,7 +318,7 @@ static const wxUint16 encoding_table__ISO8859_8[128] = { 0x05D0, 0x05D1, 0x05D2, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7, 0x05D8, 0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF, 0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4, 0x05E5, 0x05E6, 0x05E7, - 0x05E8, 0x05E9, 0x05EA, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000 + 0x05E8, 0x05E9, 0x05EA, 0x0000, 0x0000, 0x200E, 0x200F, 0x0000 }; @@ -622,7 +609,7 @@ static const wxUint16 encoding_table__KOI8_U[128] = { 0x2264, 0x2265, 0x00A0, 0x2321, 0x00B0, 0x00B2, 0x00B7, 0x00F7, 0x2550, 0x2551, 0x2552, 0x0451, 0x0454, 0x2554, 0x0456, 0x0457, 0x2557, 0x2558, 0x2559, 0x255A, 0x255B, 0x0491, 0x255D, 0x255E, - 0x255F, 0x2560, 0x2561, 0x0401, 0x0403, 0x2563, 0x0406, 0x0407, + 0x255F, 0x2560, 0x2561, 0x0401, 0x0404, 0x2563, 0x0406, 0x0407, 0x2566, 0x2567, 0x2568, 0x2569, 0x256A, 0x0490, 0x256C, 0x00A9, 0x044E, 0x0430, 0x0431, 0x0446, 0x0434, 0x0435, 0x0444, 0x0433, 0x0445, 0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, @@ -853,7 +840,7 @@ static const struct { {0, 0} }; -static const unsigned encoding_unicode_fallback_count = 200; +static const unsigned encoding_unicode_fallback_count = 200; @@ -890,8 +877,8 @@ static const struct { { wxFONTENCODING_CP1255, encoding_table__CP1255}, { wxFONTENCODING_CP1256, encoding_table__CP1256}, { wxFONTENCODING_CP1257, encoding_table__CP1257}, + { wxFONTENCODING_CP866, encoding_table__CP866}, { wxFONTENCODING_KOI8, encoding_table__KOI8}, { wxFONTENCODING_KOI8_U, encoding_table__KOI8_U}, - { wxFONTENCODING_CP866, encoding_table__CP866}, {wxFONTENCODING_MAX /*anything*/, NULL} }; -- 2.30.2